CN114064383A - Information processing method, system, equipment and computer storage medium - Google Patents
Information processing method, system, equipment and computer storage medium Download PDFInfo
- Publication number
- CN114064383A CN114064383A CN202010761891.8A CN202010761891A CN114064383A CN 114064383 A CN114064383 A CN 114064383A CN 202010761891 A CN202010761891 A CN 202010761891A CN 114064383 A CN114064383 A CN 114064383A
- Authority
- CN
- China
- Prior art keywords
- data
- information
- database
- time
- sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 57
- 238000003672 processing method Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 claims abstract description 62
- 230000008569 process Effects 0.000 claims abstract description 40
- 238000013528 artificial neural network Methods 0.000 claims description 83
- 230000000306 recurrent effect Effects 0.000 claims description 80
- 238000012545 processing Methods 0.000 claims description 78
- 230000015654 memory Effects 0.000 claims description 35
- 238000004891 communication Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 description 22
- 230000008859 change Effects 0.000 description 15
- 230000004044 response Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 9
- 238000012423 maintenance Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000003247 decreasing effect Effects 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3055—Monitoring arrangements for monitoring the status of the computing system or of the computing system component, e.g. monitoring if the computing system is on, off, available, not available
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3089—Monitoring arrangements determined by the means or processing involved in sensing the monitored data, e.g. interfaces, connectors, sensors, probes, agents
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses an information processing method, comprising the following steps: acquiring first data; the first data comprises at least one operation state information of the database at a first moment and at least one operation parameter of a first time interval; the first time is used for representing the time in the historical operation process of the database; a first period representing a time period of a preset length before the first time; acquiring second data; second data representing at least one operating parameter of the database at the current time; obtaining first information based on the first data and the second data; the first information is used for representing the running state information of the database at a second moment and/or a second period; the second moment is used for representing the future moment of operation of the database; a second time period representing a future time period of a preset length of the database operation. The above method may predict the operating state of the database at a future time and/or for a future period of time. The application also discloses an information processing system, an information processing device and a computer storage medium.
Description
Technical Field
The present application relates to the field of electronic information technology, and in particular, to an information processing method, system, device, and computer-readable storage medium.
Background
Along with the long-term high-load and multi-concurrent operation of the database, the operation state of the database is inevitable and abnormal. In the related art, it is common to monitor key data representing the operation status of the database and determine whether the operation status of the current database is normal according to the key data. However, the above scheme can only determine whether the current operation state of the database is abnormal according to the currently actually detected key data of the database, and cannot predict whether the future time or the future time period of the database is abnormal when the database is not abnormal.
Disclosure of Invention
The application provides an information processing method, which can realize the prediction of the running state information of a database at the future time, thereby solving the problem that whether the database is abnormal in the future running can not be predicted when the database is not abnormal in the related technology.
The application provides an information processing method, which comprises the following steps:
acquiring first data; wherein the first data comprises at least one operation state information of a first moment of the database and the at least one operation parameter of a first time interval; the first time is used for representing the time in the historical operation process of the database; the first time interval is used for representing a time interval with a preset length before the first time;
acquiring second data; wherein the second data is used for representing the at least one operation parameter of the database at the current moment;
obtaining first information based on the first data and the second data; the first information is used for representing the running state information of the database at a second moment and/or a second time period; the second time is used for representing the future time of the operation of the database; the second time period is used for representing a future time period with a preset length of the database operation.
In some embodiments, said deriving said first information based on said first data and said second data comprises:
acquiring an information classification rule;
processing the at least one operating parameter in the first data based on the information classification rule to obtain at least one first sequence; wherein the first sequence is indicative of a sequence of state changes of the at least one operating parameter over the first period of time;
combining the at least one operating state information with the at least one first sequence to obtain at least one second sequence;
and processing the second data based on the at least one second sequence to obtain the first information.
In some embodiments, the processing the at least one operating parameter in the first data based on the information classification rule to obtain at least one first sequence includes:
obtaining a first classification rule and a second classification rule based on the information classification rule; wherein the first classification rule is a classification rule representing the at least one operating parameter in the first data; the second classification rule is used for representing an interval division rule of parameter values of the at least one operation parameter in the first data;
and processing the operating parameters in the first data based on the first classification rule and the second classification rule to obtain at least one first sequence.
In some embodiments, the processing the second data based on the at least one second sequence to obtain the first information includes:
acquiring a trained recurrent neural network; wherein the recurrent neural network is configured to predict the at least one operating state parameter value at the second time and/or for the second time period of the database;
and processing the second data based on the trained recurrent neural network and the at least one second sequence to obtain the first information.
In some embodiments, the obtaining a trained recurrent neural network includes:
and training the recurrent neural network based on the first data to obtain the trained recurrent neural network.
In some embodiments, the processing the second data based on the trained recurrent neural network and the at least one second sequence to obtain the first information includes:
processing the second data based on the trained recurrent neural network to obtain at least one third sequence; wherein the at least one third sequence comprises the at least one operating parameter value for the second time instant and/or the second time period of the database;
obtaining the first information based on the at least one third sequence and the at least one second sequence.
In some embodiments, the obtaining the first information based on the at least one third sequence and the at least one second sequence includes:
clustering the at least one second sequence to obtain at least one cluster;
and processing the at least one third sequence based on the at least one cluster to obtain the first information.
In some embodiments, the processing the second data based on the trained recurrent neural network to obtain at least one third sequence includes:
inputting the second data into the trained recurrent neural network to obtain third data;
and processing the third data based on the information classification rule to obtain at least one third sequence.
The present application also provides an information processing system, the system comprising: a processor, a memory, and a communication bus; the communication bus is used for realizing communication connection between the processor and the memory;
the processor is used for executing the program of the information processing method in the memory to realize the following steps:
acquiring first data; the first data comprises at least one operation state information of a first moment of the database and at least one operation parameter information of a first time interval; the first time is used for representing the time in the historical operation process of the database; the first time interval is used for representing a time interval with a preset length before the first time;
acquiring second data; the second data is used for representing the at least one piece of operation parameter information of the database at the current moment;
obtaining first information based on the first data and the second data; the first information is used for representing the running state information of the database at a second moment and/or a second time period; the second time is used for representing the future time of the operation of the database; the second time period is used for representing a future time period with a preset length of the database operation.
The present application also provides an information processing apparatus including: the device comprises an acquisition module and a processing module; wherein:
the acquisition module is used for acquiring first data and second data; wherein the first data comprises at least one operation state information of a first moment of the database and the at least one operation parameter of a first time interval; the first time is used for representing the time in the historical operation process of the database; the first time interval is used for representing a time interval with a preset length before the first time; the second data is used for representing the at least one operation parameter of the database at the current moment;
the processing module is used for obtaining first information based on the first data and the second data; the first information is used for representing the running state information of the database at a second moment and/or a second time period; the second time is used for representing the future time of the operation of the database; the second time period is used for representing a future time period with a preset length of the database operation.
The present application also provides a computer-readable storage medium storing one or more programs, which are executable by one or more processors to implement the steps of the information processing method of any one of the above.
The information processing method includes the steps of firstly obtaining at least one operation state information representing a first moment in a historical operation process of a database, also obtaining at least one operation parameter representing a preset length time period before the first moment, then obtaining second data representing the at least one operation parameter of the database at the current moment, and then obtaining operation state information representing the future moment of the database based on the first data and the second data. Therefore, the information processing method provided by the application can predict the running state information of the database at the future time according to the running state information and the at least one running parameter in the historical running process of the database and by combining the information of the at least one running parameter at the current time, thereby solving the problem that whether the database is abnormal in the future running can not be predicted when the database is not abnormal in the related technology.
Drawings
Fig. 1 is a schematic flowchart of a first information processing method provided in the present application;
FIG. 2 is a schematic flow chart of a second information processing method provided in the present application;
FIG. 3 is a flowchart illustrating an embodiment of an information processing method according to the present disclosure;
FIG. 4 is a schematic flow chart of an information handling system provided herein;
fig. 5 is a block diagram of an information processing apparatus provided in the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The information processing method provided by the application relates to the technical field of electronic information, in particular to an information processing method, an information processing system, information processing equipment and a computer readable storage medium.
With the development of information technology, many data of the internet or cloud are stored in a database, and with the increase of the data storage amount of the database, the increase of the number of requests for accessing the database, and the increase of the database running time, some problems inevitably occur in the database running process, such as steep increase of the number of connections, slow request backlog, slow response, and the like, which all have adverse effects on users and upper-layer services. When the various problems occur in the database operation process, abnormal information needs to be sent to a database manager or a technical maintenance worker in time.
In the related art, in order to monitor the operation state of the database in real time, a third-party component is usually used for realizing, for example, a telegraf component is used for collecting various parameter data in the operation process of the database, an inflixdb component is used for storing the parameter data, and then a zabbix component is used for visually displaying, for example, displaying in a curve mode in a coordinate system, so that operation and maintenance personnel can conveniently check and analyze the various parameter data.
In order to determine whether the database is abnormal according to the acquired parameter data, thresholds corresponding to the acquired various parameters are also set in the related technology, when the acquired parameter value is greater than the corresponding set threshold, the current operation of the database is considered to have a fault, and at this time, a mail can be sent to an administrator or an operation maintenance staff, or information is sent to remind a mail receiver and an information receiver of the mail to handle the fault in time.
In order to get rid of the dependence on third-party components and the defect of inflexible fault detection caused by fixed threshold values, an Artificial Intelligence (AI) technology is also introduced in the related technology, and the technology trains a plurality of key parameters and values thereof when abnormality occurs in historical operation of a database to obtain a trained AI model. And then, acquiring numerical values corresponding to the key parameters in the database operation process by using the trained AI model, and judging the acquisition result so as to obtain an information report of the current operation state of the database.
However, in the two technical solutions in the related art, whether the database is abnormal or not is judged by monitoring various parameters in the current operation process of the database, that is, the above solutions in the related art are both passive monitoring, and the implementation of these solutions requires operation and maintenance personnel to pay attention to the visual page at any time and judge the index, so that the dependency on the experience of the operation and maintenance personnel is obvious, and the situation of failure and missing inspection is easily caused. And the AI mode reduces the probability of false alarm or false alarm, but the method cannot judge the possibility of future fault occurrence. Therefore, according to the above-mentioned scheme in the related art, it is impossible to predict and judge whether the state of the database at a future time in the operation process is an abnormal state, so that it is impossible to prevent and process the abnormality that may occur in the database in the near future.
In view of the above problems, embodiments of the present application provide an information processing method that can be implemented by a processor of an information processing apparatus. As shown in fig. 1, the information processing method includes the steps of:
The first data comprises at least one operation state information of the database at a first moment and at least one operation parameter of a first time interval; the first time is used for representing the time in the historical operation process of the database; and a first period representing a time period of a preset length before the first time.
In one embodiment, the database may be a multi-user database of multiple types of data.
In one embodiment, the database may be a database storing public data, such as data corresponding to some news websites.
In one embodiment, the database may be a database storing private data, such as a database storing data of a company or organization itself, but not open to the public.
In one embodiment, the database may be a database widely used in data storage, such as an Oracle database, a Mysql database, or the like.
In one embodiment, the first time may be used to indicate a certain historical time during the historical operation of the database.
In one embodiment, the first time may be used to represent a plurality of historical times during the historical operation of the database.
In one embodiment, the first time period may be used to represent a fixed length time period, such as 5 minutes, prior to the first time.
In one embodiment, the first time period may be used to indicate a time period with a non-fixed length before the first time, such as a kth first time period, corresponding to a time period with a length of K1 before the kth first time, where K is an integer greater than 1, and K1 is a number greater than 1, and the unit may be minutes.
In one embodiment, the first period may be a period before the first time that is set to a length according to the need of the database analysis.
In one embodiment, the first time period may be a time period with a corresponding length before the first time, which is set according to different types of data stored in the database. For example, if the kth type of data is stored in the database, all the first time periods related to the first type of data operation are set as follows: a time period of length K2 before the first time; where K2 is a number greater than 1, the units may be minutes.
In one embodiment, the first period may be a period of time with a corresponding length before the first time, which is set according to different types of databases, for example, for a kth type database, the first period of time set for the kth type database is: a time period of length K3 before the first time; where K3 is a number greater than 1 in minutes.
In an embodiment, the first period may be a period of time corresponding to a length before the first time, which is set according to different access loads of the database data, for example, for a kth database, a period of time corresponding to a length is set for a change interval with different access loads.
In one embodiment, the first period may be a period of time with a corresponding length before the first time, which is set according to different database operation periods, for example, for the kth database, different periods of time with different corresponding lengths are set for different periods of time in a day, a week, a month, a quarter, and a year.
In one embodiment, the at least one operation state information at the first time may indicate that the operation state of the database is normal or abnormal at the first time.
In one embodiment, the at least one operation state information at the first time may indicate that the database operation state is a state of load saturation of data access at the first time.
In one embodiment, the at least one operation status information at the first time may indicate a status of whether a corresponding speed of access to any type of data by the database at the first time is stuck.
In one embodiment, the at least one operation state information at the first time may indicate a state of whether the speed of the database access to the specified category of data is stuck at the first returning time.
In an embodiment, the at least one operation state information at the first time may further include identification information of a database corresponding to the at least one operation state information at the first time.
In one embodiment, the at least one operation state information at the first time may include at least one parameter information corresponding to each specific state and capable of characterizing the operation state of the database, in addition to the information of the specific state of the database operation at the first time and the identification information of the database.
In one embodiment, the at least one operating parameter of the first time period may be a number of key operating parameters used to characterize the operating state of the database.
In one embodiment, the at least one operating parameter of the first time period may be a plurality of key operating parameters that are set correspondingly according to different operating states of the database.
In one embodiment, the at least one operating parameter of the first time period may be a plurality of key operating parameters that are set correspondingly according to different database operating time periods.
In one embodiment, the at least one operating parameter of the first time period may be a plurality of key operating parameters set correspondingly according to different data stored in the database.
In one embodiment, the at least one operating parameter of the first time period may be a plurality of key operating parameters set correspondingly according to different types of databases.
In one embodiment, the at least one operational parameter of the first time period may include at least three key operational parameters in order to provide a sufficient and comprehensive reflection of the operational status of the data.
In one embodiment, the at least one operation status information at the first time is in a one-to-one correspondence with the at least one operation parameter at the first time period, for example, the mth operation status information corresponds to the mth group of at least one operation parameter. Wherein M is an integer greater than or equal to 1.
And 102, acquiring second data.
And the second data is used for representing at least one operation parameter of the database at the current moment.
In one embodiment, the second data may be used to indicate a number of key operating parameters that can reflect the operating status of the database during the current time operation of the database.
In one embodiment, the second data may be a current time, and represents a number of key operating parameters of the database for accessing a corresponding operating state for a given data.
In one embodiment, the second data may be an operation parameter corresponding to the type of the database at the current time and capable of reflecting the operation state of the database.
In one embodiment, the second data may be a parameter corresponding to the operation time period of the database at the current time and capable of reflecting the operation state of the database.
In one embodiment, the second data may be a parameter reflecting the current operating state of the database and corresponding to at least one operating parameter of the first time period.
It should be noted that, in order to efficiently process the acquired second data, in an implementation process of the information processing method provided in the embodiment of the present application, the first data and the second data are acquired sequentially.
And 103, obtaining first information based on the first data and the second data.
The first information is used for representing the running state information of the database at a second moment and/or a second time period; the second moment is used for representing the future moment of operation of the database; a second time period representing a future time period of a preset length of the database operation.
In one embodiment, the first information may be used to indicate the operation status information of the database at the next time and/or in the next time period adjacent to the current time.
In one embodiment, the first information may be used to indicate the operation status information of the database at a second time and/or within a second time period after a period of time separated from the current time, for example, the operation status information of the database after 5 minutes from the current time; and/or the running state information of the database within a time span of three minutes after five minutes of the current time.
In one embodiment, the first information may be the operation status information of the database at a second time after a time period corresponding to the current time, and/or within the second time period, which is set according to the database, for example, the operation status information of the database within a time period with a length of M1 after the time period K4 of the current time of the kth database, and/or after the time period K4; wherein K4 is a number greater than 0 in minutes; m1 is a number greater than 0 and may be in minutes.
In one embodiment, the first information may be the operation state information at a second time after a delay time period corresponding to the operation time period set according to the operation time period of the database based on the current time, and/or within the second time period.
In one embodiment, the first information may include identification information of the database.
In one embodiment, the first information may be operation status information corresponding to the first data and used for representing the second time of the database and/or the second time period.
In practical applications, the processor may be at least one of an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a Central Processing Unit (CPU), a controller, a microcontroller, and a microprocessor.
The information processing method provided by the embodiment of the application comprises the steps of firstly obtaining at least one operation state information representing a first moment in a historical operation process of a database, also obtaining at least one operation parameter representing a preset length time period before the first moment, then obtaining second data representing at least one operation parameter of the database at the current moment, and then obtaining the operation state information representing the future moment of the database based on the first data and the second data. Therefore, the information processing method provided by the embodiment of the application can predict the running state information of the database at the future time and/or in the future time period according to the running state information and at least one running parameter in the historical running process of the database and by combining the information of the at least one running parameter at the current time, thereby solving the problem that whether the database is abnormal in the future running cannot be predicted in the related technology when the database is not abnormal.
Based on the foregoing embodiments, an embodiment of the present application provides an information processing method, as shown in fig. 2, the information processing method including the steps of:
The first data comprises at least one operation state information of the database at a first moment and at least one operation parameter of a first time interval; the first time is used for representing the time in the historical operation process of the database; and a first period representing a time period of a preset length before the first time.
And the second data is used for representing at least one operation parameter of the database at the current moment.
In step 203, the information classification rule may be a rule for classifying the second data.
In one embodiment, the information classification rule may be a classification rule corresponding to a type of the operation parameter included in the second data.
In one embodiment, the information classification rule may be a classification rule corresponding to a type of the operation parameter included in the first data.
In one embodiment, the information classification rule may be a classification rule for filtering out parameters of specified types from the second data or a plurality of operation parameters included in the second data.
In one embodiment, the information classification rules may vary from database type to database type.
In one embodiment, the information classification rules may be different according to different database operation periods.
In one embodiment, the information classification rule may be a different information classification rule corresponding to different types of data access operations of the database.
And 204, processing at least one operation parameter in the first data based on the information classification rule to obtain at least one first sequence.
Wherein the first sequence is indicative of a sequence of state changes of the at least one operating parameter over a first period of time.
In one embodiment, the first sequence may be used to represent a sequence of changes in the database over a first period of time to the at least one operating parameter in the first data.
In one embodiment, the first sequence may be used to represent a sequence of the database over a first period of time that represents a percentage of change in the amount of change in the at least one operating parameter in the first data.
In an embodiment, the first sequence may be a series of variation matching results obtained by first obtaining a variation of at least one operating parameter in the first data in the first time period, and then matching the variation with a preset variation interval of at least one operating parameter in the first data.
In one embodiment, the first sequence may be a sequence of state changes for a number of operating parameters specified in the first data.
In an embodiment, the at least one operating parameter in the first data is processed based on the information classification rule to obtain at least one first sequence, which may be based on the information classification rule, first classifying the at least one operating parameter in the first data, then performing variation statistics on classification results, and then obtaining the at least one first sequence based on results of the variation statistics and the classification results.
In an embodiment, the at least one operating parameter in the first data is processed based on the information classification rule to obtain at least one first sequence, which may be classifying the at least one operating parameter in the first data based on the information classification rule, encoding a variation of each classified operating parameter, and then obtaining the at least one first sequence based on the classification result and the encoding result.
Illustratively, step 204 may be implemented by steps A1-A2:
and A1, obtaining a first classification rule and a second classification rule based on the information classification rule.
The first classification rule is used for representing a classification rule of at least one operation parameter in the first data; and the second classification rule is used for representing an interval division rule of parameter values of at least one operating parameter in the first data.
In one embodiment, the first classification rule may be a rule for classifying specified ones of the at least one operation parameter of the first data.
In one embodiment, the first classification rule may be a rule that classifies each of the operating parameters of the first data into different classes.
In one embodiment, the first classification rule may be a rule that classifies each of the operating parameters into different classes according to a parameter value of each of the operating parameters in the first data.
In an embodiment, the second classification rule may be a rule for performing interval division on parameter values corresponding to a plurality of specified operation parameters in the at least one operation parameter of the first data.
In one embodiment, the second classification rule may be a rule for matching a parameter value of at least one operating parameter of the first data with a preset parameter interval.
In one embodiment, the second classification rule may be a rule that performs interval division according to a result of a combination operation after performing the combination operation on parameter values of any one of the at least one operation parameter of the first data.
Step A2, processing the operation parameters in the first data based on the first classification rule and the second classification rule to obtain at least one first sequence.
In an embodiment, the operation parameters in the first data are processed based on a first classification rule and a second classification rule to obtain at least one first sequence, where the at least one first sequence may be obtained by performing category division on the at least one operation parameter in the first data based on the first classification rule, performing interval division on a parameter value of each operation parameter in a category division result obtained by performing the category division on the operation parameter based on the second classification rule, and combining the category division result with a corresponding interval division result to obtain the at least one first sequence.
In an embodiment, the operation parameters in the first data are processed based on a first classification rule and a second classification rule to obtain at least one first sequence, where the operation parameters specified in the operation parameters of the first data are classified, the parameter values of the corresponding operation parameters in the classification results are partitioned based on the second classification rule, and then the classification results are combined with the rule of partitioning the intervals to obtain at least one first sequence.
In an embodiment, when the operation parameters in the first data belong to the same type, the operation parameters are not required to be divided by the first classification rule, and the interval division can be directly performed based on the second classification parameter, so as to obtain at least one first sequence.
In one embodiment, the at least one operating state information is obtained from the first data.
In one embodiment, the at least one operation status information and the at least one first sequence are combined to obtain at least one second sequence, and the at least one operation status information may be correspondingly combined with each obtained first sequence to obtain the at least one second sequence.
In one embodiment, the at least one operation status information and the at least one first sequence are combined to obtain the at least one second sequence, where the at least one second sequence may be obtained by selecting a plurality of operation status information from the at least one operation status information and correspondingly selecting a corresponding sequence from the first sequence, and then combining the selected plurality of operation status information and the corresponding sequence.
And step 206, processing the second data based on at least one second sequence to obtain the first information.
In one embodiment, the at least one second sequence includes information of a change in state of the at least one operating parameter over a first time period in the first sequence.
In one embodiment, the second data is processed based on the at least one second sequence to obtain the first information, where the change trajectory of the second data may be determined based on information of a state change of the at least one operating parameter in the first time period included in the at least one second sequence, and the first information is obtained from the change trajectory.
In an embodiment, the second data is processed based on the at least one second sequence to obtain the first information, and the second data and the at least one second sequence may be subjected to double matching of parameters and parameter values to obtain a change trajectory corresponding to the second data, and then the first information is obtained based on the change trajectory.
Illustratively, step 206 may be implemented by step B1-step B2:
and step B1, acquiring the trained recurrent neural network.
And the recurrent neural network is used for predicting at least one operation state parameter value of the database at a second moment or a second time period.
In one embodiment, the recurrent neural network may be a neural network for predicting a value of a parameter corresponding to a plurality of specified operating parameters of the at least one operating state parameter at a future time in the database.
In one embodiment, the recurrent neural network may be a time-recurrent neural network.
In one embodiment, the recurrent neural network may be a Long Short-Term Memory neural network (LSTM).
In one embodiment, the Recurrent neural network may be a Gated Recurrent Unit neural network (GRU).
In one embodiment, the trained recurrent neural network may be obtained by training in at least one of the following manners based on training sample data: unsupervised learning mode, supervised learning mode, semi-supervised learning mode.
Illustratively, step B1 may be implemented by step B101:
and B101, training the recurrent neural network based on the first data to obtain the trained recurrent neural network.
In an embodiment, the recurrent neural network is trained based on the first data to obtain a trained recurrent neural network, and the parameter value corresponding to at least one operation parameter in the first time period in the first data is input to the recurrent neural network, and the output of the recurrent neural network is matched with at least one operation state information in the first data, and then various parameters of the recurrent neural network are adjusted according to the matching result.
In an embodiment, the training of the recurrent neural network based on the first data to obtain the trained recurrent neural network may be to input at least one operating parameter in the first time period in the first data to the recurrent neural network, so that the recurrent neural network can adjust each parameter of the recurrent neural network according to a parameter value of the at least one operating parameter, and thus the recurrent neural network can obtain a variation trend of the at least one operating parameter in the first time period.
And step B2, processing the second data based on the trained recurrent neural network and at least one second sequence to obtain first information.
In one embodiment, the second data is processed based on the trained recurrent neural network and the at least one second sequence to obtain first information, which may be inputting the second data into the trained recurrent neural network to obtain a processing result, wherein the processing result is used for representing at least one state parameter associated with the operation state of the database at a future time; and then analyzing the processing result based on at least one second sequence to obtain first information.
In an embodiment, the second data is processed based on the trained recurrent neural network and the at least one second sequence to obtain the first information, where the at least one second sequence and the second data are simultaneously input to the recurrent neural network, and the first information is obtained according to an output result of the recurrent neural network.
Illustratively, step B2 may also be implemented by steps C1-C2:
and step C1, processing the second data based on the trained recurrent neural network to obtain at least one third sequence.
Wherein the at least one third sequence comprises at least one operating parameter value for a second time instant and/or a second time period of the database.
In one embodiment, the at least one third sequence may include values of the operating parameters corresponding to the specified operating parameters in the at least one operating parameter information at a future time in the database.
Correspondingly, the second data is processed based on the trained recurrent neural network to obtain at least one third sequence, and the second data may be input into the trained recurrent neural network to obtain operation parameter values corresponding to a plurality of designated operation parameters in at least one operation parameter at a future time of the database.
In one embodiment, the at least one third sequence may be used to represent the value of the operating parameter corresponding to the at least one operating parameter at a specified time in the future of the database.
Correspondingly, the second data is processed based on the trained recurrent neural network to obtain at least one third sequence, and the second data may be input into the trained recurrent neural network to obtain an operating parameter value corresponding to at least one operating parameter for representing a specified future time of the database.
In one embodiment, the at least one third sequence may be used to represent the value of the operating parameter corresponding to the at least one operating parameter in any future period of time of the database.
Correspondingly, the second data is processed based on the trained recurrent neural network to obtain at least one third sequence, and the second data may be input into the trained recurrent neural network to obtain an operating parameter value corresponding to at least one operating parameter for representing any future period of the database.
In one embodiment, the at least one third sequence may be used to represent the value of the operating parameter corresponding to the at least one operating parameter within a specified period of time in the future of the database.
Accordingly, the second data is processed based on the trained recurrent neural network to obtain at least one third sequence, which may be inputting the second data into the trained recurrent neural network to obtain an operating parameter value corresponding to at least one operating parameter for a specified period of time in the future of the database.
In one embodiment, the at least one third sequence may be used to represent values of a number of specified operating parameters of the at least one operating parameter over some specified period of time in the future of the database.
Correspondingly, the second data is processed based on the trained recurrent neural network to obtain at least one third sequence, and the second data may be input into the trained recurrent neural network to obtain operation parameter values corresponding to a plurality of specified operation parameters in at least one operation parameter information for representing a certain specified time period in the future of the database.
Illustratively, the step C1 can also be realized through the step D1-the step D2:
and D1, inputting the second data into the trained recurrent neural network to obtain third data.
In one embodiment, second data may be input to the trained recurrent neural network, so that the trained recurrent neural network may make a prediction based on the second data, resulting in at least one operating parameter value representing an operating state of the database at a future time.
In one embodiment, the third data may further include database identification information, time information of a future time, and development trend information of the third data.
And D2, processing the third data based on the information classification rule to obtain at least one third sequence.
In an embodiment, the at least one third sequence may be obtained by processing the third data according to a first classification rule and/or a second classification rule in the information classification rules.
Specifically, when the third data only includes one type of operation parameter, the parameter value corresponding to the operation parameter may be directly divided into intervals based on the second classification rule.
When the third data includes at least two types of operation parameters, the operation parameters may be classified based on the first classification rule, and then the parameter values corresponding to the various types of operation parameters may be partitioned based on the second classification rule.
And step C2, obtaining the first information based on the at least one third sequence and the at least one second sequence.
In one embodiment, the first information may be obtained by matching at least one third sequence with at least one second sequence.
Illustratively, step C2 may be implemented by steps E1-E2.
And E1, clustering the at least one second sequence to obtain at least one cluster.
In one embodiment, the cluster of classes is used to indicate a set of second sequences having the same characteristics in at least one of the second sequences.
In one embodiment, the clustering is performed from at least one second sequence, and the features of the second sequences in different clusters are different from each other in at least one cluster obtained by clustering.
In one embodiment, the Clustering of the at least one second sequence may be performed by a Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm that is robust to Noise.
In an embodiment, the at least one second sequence is clustered to obtain at least one class cluster, and a second number of class clusters can be obtained from the first number of second sequences, wherein the second number is smaller than the first number, and in some embodiments, the second number can be much smaller than the first number, thereby achieving a significant reduction in data size.
And E2, processing the at least one third sequence based on the at least one class cluster to obtain the first information.
In an embodiment, the processing of the at least one third sequence based on the at least one cluster class to obtain the first information may be matching each cluster in the at least one cluster class with each sequence in the at least one third sequence to obtain the first information.
In an embodiment, the processing of the at least one third sequence based on the at least one class cluster to obtain the first information may be performed by first analyzing the third sequence and then performing feature matching on the analysis result and the at least one class cluster to obtain the first information.
In an embodiment, based on at least one class cluster, processing at least one third sequence to obtain first information, matching any one class cluster in the at least one class cluster with any one third sequence in the at least one third sequence to obtain a successful matching result between the pth class cluster and the lth third sequence, and then obtaining the first information according to the successful matching result; wherein P and L are integers greater than 0.
In one embodiment, the first information may also be a result of a failure of matching any one of the at least one cluster class with any one of the at least one third sequence. At this time, it is necessary to update the first data based on the current third sequence and/or the second data corresponding to the third sequence, and update at least one second sequence according to the update result, so that a new cluster with a wider data coverage and more complete features can be obtained. Then, at least one third sequence may be processed according to the new cluster class to obtain the first information.
Specifically, fig. 3 is a flowchart of a specific implementation of the information processing method provided in the embodiment of the present application. In the specific implementation flowchart of the information processing method shown in fig. 3, the information processing method mainly includes a state association calculation module, a time sequence index prediction module, a state association knowledge base, a state real-time prediction module, a second data acquisition part, and a fault list part.
In fig. 3, example 1, example 2, and example 3 correspond to examples of different databases, where examples 1-3 may be examples of the same type of database or may be examples of databases of different types from each other.
In fig. 3, the second data includes the current-time operating status information obtained in real time from the examples 1 to 3 and at least one operating parameter, that is, the corresponding current parameter in fig. 3.
In fig. 3, the first data includes at least one operation state information at the first time and at least one operation parameter for the first time period, which are acquired from the examples 1 to 3.
In fig. 3, the state association calculating module is configured to obtain first data, and exemplarily, further configured to extract and screen out target parameters to be analyzed from the first data according to needs, such as several pieces of key parameter information associated with abnormal operation states of the database, and abnormal information corresponding to the several pieces of key parameter information. Specifically, for example, the data request non-response problem of example 1 occurred at the first time, or the at least one operation parameter and its parameter value related to the data request non-response problem of example 1 in the first period before the first time. The first time may be, for example, 35 minutes 20 seconds at 23 o ' clock 1/10/2019, and the first time interval may be a time interval between 30 minutes 20 seconds at 23 o ' clock 1/10/2019 and 35 minutes 20 seconds at 23 o ' clock 1/10/2019. Illustratively, the first time period may be a time period of any length of time prior to the first time, such as three minutes, four minutes, etc. Illustratively, the at least one operation parameter may be, for example, a Real connection Count (RC), a Slow connection Count (SC), and a Response Time (RT). The running state of the database can be an abnormal state in the running process of the database.
In fig. 3, the state association calculating module is further configured to obtain at least one first sequence according to the obtained first data. In particular, in case that the at least one operating parameter comprises RC, SC and RT, the parameter values of RC, SC and RT may be comprised in the at least one first sequence. Moreover, the time length covered by the parameter values corresponding to the above various parameters included in the first sequence can be matched with the first time period. The at least one operating parameter value within each sequence may be an instantaneous value at the time of data acquisition, or an average value within a preset time length range at the time of data acquisition, such as an average value of RC within 20 seconds.
Illustratively, the first sequence may be in the following format: and the RC/SC/RT combines the running state information in the first data with the first sequence to obtain a second sequence, wherein the format of the second sequence is as follows: state name/state occurrence position/state occurrence time/RC/SC/RT, the state name in the second sequence may be used to indicate a name corresponding to a specific state, for example, RC is too small; the state occurrence position can represent a database instance of the state occurrence corresponding to the state name, compared with instance 1; the state occurrence time may represent the actual occurrence time of the state corresponding to the state name, for example, XX month, XX day, X hour and X minute in XXX year, and RC/SC/RT represents the parameter state capable of representing RC, SC, RT corresponding to the state occurrence time. When the state contained in the first sequence is a fault state, the second sequence may include the following: fault name/fault location/fault occurrence time/RC/SC/RT. The failure name may be a specific name of the failure, such as no response; the state occurrence position can be a database instance of the fault occurrence, such as the Mysql database instance 2, the fault occurrence time can be a time accurate to the second or millisecond level, such as 23 points, 34 points and 15 seconds on 25 days of 12 months in 2019, and the RC/SC/RT can be used for representing the state of parameters for representing the RC/SC/RT when the fault occurs.
In fig. 3, the state association calculating module is further configured to classify the obtained at least one second sequence based on an information classification rule, and perform interval division on a parameter interval in each sequence to obtain at least one information-extended second sequence. For example, the status name is obtained from the second sequence, such as responding too long, the database identifier where the above status occurs, such as example 2 of Mysql database, is obtained, and the time when the status occurs, such as 23 o 'clock and 34 s at 25 o' clock in 12/month in 2019 and 15 s, is also obtained. Specifically, under the condition that at least one of the operation parameters is RC, SC, and RT, the intervals of the above three parameters may be divided, so as to reflect the variation trend of the parameter values corresponding to each parameter.
For example, the state association calculating module may further expand each parameter in the second sequence into two corresponding sub-parameters Y and Z, where the sub-parameter Y is used to represent an interval value of each parameter value, and the sub-parameter Z is an interval value of a change rate of the parameter value corresponding to each parameter. Further, in order to better perform interval division on the parameter values of the respective parameters, the sub-parameter Y corresponding value and the sub-parameter Z corresponding value are respectively divided into intervals, for example, for the interval division of the sub-parameter Y, an interval between a maximum value and a minimum value of the parameter value of the sub-parameter Y may be equally divided into five intervals, for example, the sub-parameter Y may be divided into the following 5 intervals: EL very low/SL very low/C normal/SH very high/EH very high; for the interval division of the sub-parameter Z, a difference between the value of the sub-parameter Z at the m-th time and the sum of the sub-parameter Z at the m-1 th time may be calculated to obtain a variation ratio between the sub-parameter Z at the m-th time and the sub-parameter Z at the m-1 th time, where m is an integer greater than 1, for example, the sub-parameter Z may be divided into the following 5 corresponding intervals: according to the following, the value of the sub-parameter X of one dimension can be increased, and the value of the sub-parameter X can be increased or decreased, so as to obtain eight value intervals of a20/a230/a370/a710/R20/R230/R370/R710, wherein a represents an increase and R represents a decrease, and the eight value intervals respectively represent an increase of 20%/an increase of 30%/an increase of 70%/a decrease of 20%/a decrease of 30% -70%/a decrease of more than 70%, considering that a change trend is required.
The state association calculation module may further add a parameter number to the 8 value intervals, so as to obtain, for example: RC-EH, representing that the index of the real-time connection number is high at present; RT-R230, representing a reduction in the response time index of between 20% and 30%.
Through the above processing of the state association calculation module, through the first data, at least one second sequence after information expansion with the following format can be obtained: the fault name/fault location/fault time/real-time connection number current indicator value interval/real-time connection number change rate interval/slow connection number change rate interval/response time current indicator value interval/response time change rate interval, for example, there are 9 fields: response time too long/southern CRM5 database # 3 example/20191010163429/RC-EH/RC-A20/SC-EL/SC-R710/RT-C/RT-R370, the meaning of the various fields in the above example are as follows: southern CRM5 database No. 3 example showed a response over-long time at 34 minutes 29 seconds at 10, 16 of 2019 and a corresponding RC over-high and increased by 20%, SC over-low and decreased by more than 70% in the first period, RT at a typical level and decreased by 30% -70%.
In addition, the state association calculation module is further configured to cluster the second sequence after the at least one information extension to obtain at least one class cluster. The number of the at least one second sequence obtained by the processing of the state association calculation module may be very large, so that the large data size is not convenient for subsequent data processing, and the cluster obtained by clustering the second sequence includes sufficient operating parameter characteristic information in the at least one second sequence, so that the data size can be greatly reduced.
Each of the plurality of class clusters obtained after the processing by the state association calculation module has obvious characteristics and can have a wide representative meaning, for example, class cluster one: contains 123 faults, which can be characterized roughly as: the database response is slow-RC is high-RC is increased by 30% to 70% -RT is high-RT is increased by more than 70%; cluster two: contains 234 faults, which can be characterized roughly as: too high RC-lower SC-less than 20% reduction in SC number-very high RT-more than 70% increase in RT. Moreover, the more the number of the second sequences included in the class cluster is, the more significant the validity of the class cluster is, and under the condition that the second sequence indicates a failure sequence, the more the number of the second sequences is included in each class cluster, which may be the more effective the class cluster for subsequent data processing.
The state association calculating module is further configured to store the obtained class clusters in a state association knowledge base, for example, the class clusters with the number of the second sequences being greater than P may be set as valid class clusters, P may be set according to an actual situation, P may be an integer greater than 0, such as 20, and the valid class clusters may be stored in the state association knowledge base. When at least one operating parameter represents key parameter information during occurrence of a Fault, the state association knowledge base may be a Fault index association knowledge base (FRDB), and accordingly, an effective class cluster corresponding to the Fault may be stored in the Fault index association knowledge base, where the stored rule is as follows: the cluster number/cluster contains 10 fields in total, namely the number of faults/three parameters (current parameter value interval coding/parameter value change interval coding two fields/fault name/fault position of each parameter (RC/SC/RT)).
In fig. 3, the timing indicator prediction module is configured to obtain at least one operation parameter of the database at the current time, that is, the second data, and further configured to process the at least one operation parameter of the database at the current time through the trained recurrent neural network to predict a parameter value of the at least one operation parameter at the second time and/or in the second time period. Illustratively, the recurrent neural network may be LSTM.
In fig. 3, the real-time status prediction module is configured to process the predicted parameter value of the at least one operating parameter at the second time and/or in the second time period by using the method for processing the first data to obtain the at least one second sequence after information expansion, so as to obtain at least one third sequence. And each parameter, the interval corresponding to the parameter value, the ascending and descending trend and the like in the at least one third sequence are consistent with the at least one second sequence.
When the at least one operation parameter represents an operation parameter of the database at the time of the occurrence of the fault, the at least one third sequence may be an information set of various operation parameters, parameter value corresponding intervals, a rising and falling trend and the like at the time of the occurrence of the fault at the second time and/or the second time period.
And the state real-time prediction module is further used for acquiring various clusters from the state association knowledge base and matching at least one third sequence with each cluster, so as to determine the cluster to which the at least one third sequence belongs. Illustratively, in the case that the at least one third sequence represents various parameter information at the time of the occurrence of the fault, the real-time status prediction module obtains the class clusters from the FRDB and matches the at least one piece of association information with the respective class clusters. When the matching is successful, a fault list is output, wherein the fault list can comprise all information contained in the at least one third sequence, or the information in the at least one third sequence can be extracted to form more intuitive information, for example, the 'Mysql database instance 3 has a fault that the RC is too slow correspondingly at 16 o 23 min 38 s at 1/15/2020, and please pay attention in time'. In addition, the data in the fault list can be sent to a database administrator or to a data operation and maintenance personnel in the form of mail or information.
Therefore, according to the information processing method provided by the embodiment of the application, at least one type of operation state information at a first time including a time in a database historical operation process is obtained, a time period with a preset length before the first time of the database, namely a first parameter of at least one operation parameter at the first time is obtained, a second parameter including at least one operation parameter at the current time of the database is obtained, then at least one operation parameter is processed according to an information classification rule, and at least one second sequence is obtained. That is to say, in the information processing method provided in the embodiment of the present application, the first information is obtained based on at least one operation parameter in the database operation historical time and at least one operation parameter information at the current time, and the first information obtained in the above manner can better conform to the actual situation of the database operation state, that is, the prediction of the operation state of the database at the future time and/or in the future time period can be more accurate, so that a database manager or a database technical maintenance person can be prompted to intervene and process a possible fault in advance, and further impact of a serious or large-scale database fault on various data services can be reduced.
Based on the foregoing embodiments, the present application provides an information processing system 3, as shown in fig. 4, where the information processing system 3 includes a processor 31, a memory 32, and a communication bus;
wherein, the communication bus is used for realizing the communication connection between the processor 31 and the memory 32;
a processor 31 for executing a program of the information processing method in the memory 32 to realize the steps of:
acquiring first data; the first data comprises at least one operation state information of the database at a first moment and at least one operation parameter information of a first time interval; the first time is used for representing the time in the historical operation process of the database; a first period representing a time period of a preset length before a first time;
acquiring second data; the second data is used for representing at least one piece of operation parameter information of the database at the current moment;
obtaining first information based on the first data and the second data; the first information is used for representing the running state information of the database at a second moment and/or a second time period; the second moment is used for representing the future moment of the operation of the database; a second time period representing a future time period of a preset length of the database operation.
A processor 31 for executing a program of the information processing method in the memory 32 to realize the steps of:
obtaining first information based on the first data and the second data, including:
acquiring an information classification rule;
processing at least one operation parameter in the first data based on the information classification rule to obtain at least one first sequence; wherein the first sequence is indicative of a sequence of state changes of at least one operating parameter over a first period of time;
combining the at least one operating state information with the at least one first sequence to obtain at least one second sequence;
and processing the second data based on at least one second sequence to obtain the first information.
A processor 31 for executing a program of the information processing method in the memory 32 to realize the steps of:
processing at least one operating parameter in the first data based on the information classification rule to obtain at least one first sequence, including:
obtaining a first classification rule and a second classification rule based on the information classification rule; the first classification rule is used for representing a classification rule of at least one operation parameter in the first data; a second classification rule representing an interval division rule of a parameter value of at least one operating parameter in the first data;
and processing the operating parameters in the first data based on the first classification rule and the second classification rule to obtain at least one first sequence.
A processor 31 for executing a program of the information processing method in the memory 32 to realize the steps of:
processing the second data based on the at least one second sequence to obtain first information, comprising:
acquiring a trained recurrent neural network; the recurrent neural network is used for predicting at least one operation state parameter value of a second moment and/or a second time interval of the database;
and processing the second data based on the trained recurrent neural network and at least one second sequence to obtain first information.
A processor 31 for executing a program of the information processing method in the memory 32 to realize the steps of:
acquiring a trained recurrent neural network, comprising:
and training the recurrent neural network based on the first data to obtain the trained recurrent neural network.
A processor 31 for executing a program of the information processing method in the memory 32 to realize the steps of:
processing the second data based on the trained recurrent neural network and the at least one second sequence to obtain first information, wherein the processing comprises the following steps:
processing the second data based on the trained recurrent neural network to obtain at least one third sequence; at least one third sequence comprises at least one operation parameter information value of the database at a second time and/or a second time period;
the first information is obtained based on the at least one third sequence and the at least one second sequence.
A processor 31 for executing a program of the information processing method in the memory 32 to realize the steps of:
obtaining first information based on the at least one third sequence and the at least one second sequence, comprising:
clustering at least one second sequence to obtain at least one cluster;
and processing the at least one third sequence based on the at least one cluster to obtain the first information.
A processor 31 for executing a program of the information processing method in the memory 32 to realize the steps of:
processing the second data based on the trained recurrent neural network to obtain at least one third sequence, including:
inputting the second data into the trained recurrent neural network to obtain third data;
and processing the third data based on the information classification rule to obtain at least one third sequence.
In practical applications, the processor 31 may be at least one of an ASIC, a DSP, a PLD, an FPGA, a CPU, a controller, a microcontroller, and a microprocessor.
The Memory 32 may be a Volatile Memory (Volatile Memory), such as a RAM; or a Non-volatile Memory (Non-volatile Memory) such as a ROM, a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, HDD) or a Solid-State Drive (SSD); or a combination of the above types of memories and provides instructions and data to the processor 31.
The information processing system 3 provided in the embodiment of the present application first obtains at least one kind of operation state information representing a first time in a historical operation process of the database, and also obtains at least one operation parameter representing a preset length time period before the first time, then obtains second data representing at least one operation parameter of the database at the current time, and then obtains operation state information representing a future time of the database based on the first data and the second data. Therefore, the information processing system 3 provided in the embodiment of the present application can predict the operation state information of the database at a future time and/or a future time period according to the operation state information and the at least one operation parameter in the historical operation process of the database and by combining the information of the at least one operation parameter at the current time, thereby solving the problem that whether the database is abnormal in the future operation cannot be predicted when the database is not abnormal in the related art.
Based on the foregoing embodiments, an embodiment of the present application provides an information processing apparatus 4, as shown in fig. 5, the information processing apparatus 4 including: an acquisition module 41 and a processing module 42; wherein,
an obtaining module 41, configured to obtain first data and second data; the first data comprises at least one operation state information of the database at a first moment and at least one operation parameter of a first time interval; the first time is used for representing the time in the historical operation process of the database; a first period representing a time period of a preset length before a first time; second data representing at least one operating parameter of the database at the current time;
a processing module 42, configured to obtain first information based on the first data and the second data; the first information is used for representing the running state information of the database at a second moment and/or a second time period; the second moment is used for representing the future moment of the operation of the database; a second time period representing a future time period of a preset length of the database operation.
An obtaining module 41, configured to obtain an information classification rule;
a processing module 42, configured to process at least one operation parameter in the first data based on the information classification rule to obtain at least one first sequence; combining the at least one operating state information with the at least one first sequence to obtain at least one second sequence;
wherein the first sequence is indicative of a sequence of state changes of the at least one operating parameter over a first period of time.
A processing module 42, configured to obtain a first classification rule and a second classification rule based on the information classification rule; processing the operation parameters in the first data based on the first classification rule and the second classification rule to obtain at least one first sequence; the first classification rule is used for representing a classification rule of at least one operation parameter in the first data; and the second classification rule is used for representing an interval division rule of parameter values of at least one operating parameter in the first data.
A processing module 42, configured to obtain a trained recurrent neural network; the recurrent neural network is used for predicting at least one operation state parameter value of a second moment and/or a second time interval of the database;
and processing the second data based on the trained recurrent neural network and at least one second sequence to obtain first information.
And the processing module 42 is configured to train the recurrent neural network based on the first data, so as to obtain a trained recurrent neural network.
A processing module 42, configured to process the second data based on the trained recurrent neural network to obtain at least one third sequence; obtaining first information based on the at least one third sequence and the at least one second sequence; wherein the at least one third sequence comprises at least one operational parameter information value for a future time instance of the database.
A processing module 42, configured to cluster the at least one second sequence to obtain at least one cluster;
and processing the at least one third sequence based on the at least one cluster to obtain the first information.
The processing module 42 is configured to input the second data to the trained recurrent neural network to obtain third data;
and processing the third data based on the information classification rule to obtain at least one third sequence.
And processing the second data based on at least one second sequence to obtain the first information.
In practical applications, the obtaining module 41 and the processing module 42 may be implemented by a processor located in an electronic device, where the processor is at least one of an ASIC, a DSP, a DSPD, a PLD, an FPGA, a CPU, a controller, a microcontroller, and a microprocessor.
The information processing apparatus 4 provided in the embodiment of the present application first obtains at least one operation state information representing a first time in a historical operation process of a database, and also obtains at least one operation parameter representing a preset length time period before the first time, then obtains second data representing at least one operation parameter of the database at the current time, and then obtains the operation state information representing the future time of the database based on the first data and the second data. Therefore, the information processing device 4 provided in the embodiment of the present application can predict the operation state information of the database at the future time and/or in the future time period according to the operation state information and the at least one operation parameter in the historical operation process of the database and by combining the information of the at least one operation parameter at the current time, thereby solving the problem that whether the database is abnormal in the future operation cannot be predicted when the database is not abnormal in the related art.
Based on the foregoing embodiments, the present application provides a computer-readable storage medium storing one or more programs, which can be executed by multiple processors to implement the steps of any of the information processing methods as described above.
The computer-readable storage medium may be a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Programmable Read Only Memory (EPROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a magnetic Random Access Memory (FRAM), a Flash Memory (Flash Memory), a magnetic surface Memory, an optical Disc, or a Compact Disc Read-Only Memory (CD-ROM); and may be various electronic devices such as mobile phones, computers, tablet devices, personal digital assistants, etc., including one or any combination of the above-mentioned memories.
The foregoing description of the various embodiments is intended to highlight various differences between the embodiments, and the same or similar parts may be referred to each other, and for brevity, will not be described again herein.
The methods disclosed in the method embodiments provided by the present application can be combined arbitrarily without conflict to obtain new method embodiments.
Features disclosed in various product embodiments provided by the application can be combined arbitrarily to obtain new product embodiments without conflict.
The features disclosed in the various method or apparatus embodiments provided herein may be combined in any combination to arrive at new method or apparatus embodiments without conflict.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method described in the embodiments of the present application.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are included in the scope of the present application.
Claims (11)
1. An information processing method, characterized in that the method comprises:
acquiring first data; wherein the first data comprises at least one operation state information of a first moment of the database and the at least one operation parameter of a first time interval; the first time is used for representing the time in the historical operation process of the database; the first time interval is used for representing a time interval with a preset length before the first time;
acquiring second data; wherein the second data is used for representing the at least one operation parameter of the database at the current moment;
obtaining first information based on the first data and the second data; the first information is used for representing the running state information of the database at a second moment and/or a second time period; the second time is used for representing the future time of the operation of the database; the second time period is used for representing a future time period with a preset length of the database operation.
2. The method of claim 1, wherein obtaining the first information based on the first data and the second data comprises:
acquiring an information classification rule;
processing the at least one operating parameter in the first data based on the information classification rule to obtain at least one first sequence; wherein the first sequence is indicative of a sequence of state changes of the at least one operating parameter over the first period of time;
combining the at least one operating state information with the at least one first sequence to obtain at least one second sequence;
and processing the second data based on the at least one second sequence to obtain the first information.
3. The method of claim 2, wherein the processing the at least one operating parameter in the first data based on the information classification rule to obtain at least one first sequence comprises:
obtaining a first classification rule and a second classification rule based on the information classification rule; wherein the first classification rule is a classification rule representing the at least one operating parameter in the first data; the second classification rule is used for representing an interval division rule of parameter values of the at least one operation parameter in the first data;
and processing the operating parameters in the first data based on the first classification rule and the second classification rule to obtain at least one first sequence.
4. The method of claim 2, wherein the processing the second data based on the at least one second sequence to obtain the first information comprises:
acquiring a trained recurrent neural network; wherein the recurrent neural network is configured to predict the at least one operating state parameter value at the second time and/or for the second time period of the database;
and processing the second data based on the trained recurrent neural network and the at least one second sequence to obtain the first information.
5. The method of claim 4, wherein the obtaining a trained recurrent neural network comprises:
and training the recurrent neural network based on the first data to obtain the trained recurrent neural network.
6. The method of claim 4, wherein the processing the second data based on the trained recurrent neural network and the at least one second sequence to obtain the first information comprises:
processing the second data based on the trained recurrent neural network to obtain at least one third sequence; wherein the at least one third sequence comprises the at least one operating parameter value for the second time instant and/or the second time period of the database;
obtaining the first information based on the at least one third sequence and the at least one second sequence.
7. The method of claim 6, wherein obtaining the first information based on the at least one third sequence and the at least one second sequence comprises:
clustering the at least one second sequence to obtain at least one cluster;
and processing the at least one third sequence based on the at least one cluster to obtain the first information.
8. The method of claim 6, wherein the processing the second data based on the trained recurrent neural network to obtain at least one third sequence comprises:
inputting the second data into the trained recurrent neural network to obtain third data;
and processing the third data based on the information classification rule to obtain at least one third sequence.
9. An information processing system, the system comprising: a processor, a memory, and a communication bus; the communication bus is used for realizing communication connection between the processor and the memory;
the processor is used for executing the program of the information processing method in the memory to realize the following steps:
acquiring first data; the first data comprises at least one operation state information of a first moment of the database and at least one operation parameter information of a first time interval; the first time is used for representing the time in the historical operation process of the database; the first time interval is used for representing a time interval with a preset length before the first time;
acquiring second data; the second data is used for representing the at least one piece of operation parameter information of the database at the current moment;
obtaining first information based on the first data and the second data; the first information is used for representing the running state information of the database at a second moment and/or a second time period; the second time is used for representing the future time of the operation of the database; the second time period is used for representing a future time period with a preset length of the database operation.
10. An information processing apparatus characterized by comprising: the device comprises an acquisition module and a processing module; wherein:
the acquisition module is used for acquiring first data and second data; wherein the first data comprises at least one operation state information of a first moment of the database and the at least one operation parameter of a first time interval; the first time is used for representing the time in the historical operation process of the database; the first time interval is used for representing a time interval with a preset length before the first time; the second data is used for representing the at least one operation parameter of the database at the current moment;
the processing module is used for obtaining first information based on the first data and the second data; the first information is used for representing the running state information of the database at a second moment and/or a second time period; the second time is used for representing the future time of the operation of the database; the second time period is used for representing a future time period with a preset length of the database operation.
11. A computer-readable storage medium characterized by storing one or more programs, which are executable by one or more processors, to implement the steps of the information processing method according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010761891.8A CN114064383A (en) | 2020-07-31 | 2020-07-31 | Information processing method, system, equipment and computer storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010761891.8A CN114064383A (en) | 2020-07-31 | 2020-07-31 | Information processing method, system, equipment and computer storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114064383A true CN114064383A (en) | 2022-02-18 |
Family
ID=80227757
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010761891.8A Pending CN114064383A (en) | 2020-07-31 | 2020-07-31 | Information processing method, system, equipment and computer storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114064383A (en) |
-
2020
- 2020-07-31 CN CN202010761891.8A patent/CN114064383A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111475804B (en) | Alarm prediction method and system | |
CN110865929B (en) | Abnormality detection early warning method and system | |
CN111010291B (en) | Business process abnormity warning method and device, electronic equipment and storage medium | |
CN113556258B (en) | Anomaly detection method and device | |
CN111275333B (en) | Pollution data processing method and device | |
CN104021264B (en) | A kind of failure prediction method and device | |
CN109918279B (en) | Electronic device, method for identifying abnormal operation of user based on log data and storage medium | |
CN110471821B (en) | Abnormality change detection method, server, and computer-readable storage medium | |
CN115098705B (en) | Network security event analysis method and system based on knowledge graph reasoning | |
CN109063969B (en) | Account risk assessment method and device | |
CN111309539A (en) | Abnormity monitoring method and device and electronic equipment | |
CN111176953A (en) | Anomaly detection and model training method thereof, computer equipment and storage medium | |
CN112989332B (en) | Abnormal user behavior detection method and device | |
US20230156043A1 (en) | System and method of supporting decision-making for security management | |
CN115689396B (en) | Pollutant emission control method, device, equipment and medium | |
CN115660262B (en) | Engineering intelligent quality inspection method, system and medium based on database application | |
Chen et al. | Pattern recognition using clustering algorithm for scenario definition in traffic simulation-based decision support systems | |
CN105825130B (en) | A kind of information security method for early warning and device | |
CN113672600A (en) | Anomaly detection method and system | |
CN115277220A (en) | Industrial control network traffic safety classification method and system and readable storage device | |
CN111813644A (en) | System performance evaluation method and device, electronic equipment and computer readable medium | |
CN118154186A (en) | Method, device and server for determining abnormal operation of transaction service | |
CN114139931A (en) | Enterprise data evaluation method and device, computer equipment and storage medium | |
CN109711450A (en) | A kind of power grid forecast failure collection prediction technique, device, electronic equipment and storage medium | |
CN116714469A (en) | Charging pile health monitoring method, device, terminal and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |