CN117093675A - Operation ticket searching and matching method, device and storage medium - Google Patents
Operation ticket searching and matching method, device and storage medium Download PDFInfo
- Publication number
- CN117093675A CN117093675A CN202311347187.8A CN202311347187A CN117093675A CN 117093675 A CN117093675 A CN 117093675A CN 202311347187 A CN202311347187 A CN 202311347187A CN 117093675 A CN117093675 A CN 117093675A
- Authority
- CN
- China
- Prior art keywords
- operation ticket
- matching
- ticket
- standardized
- request information
- 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
- 238000000034 method Methods 0.000 title claims abstract description 87
- 238000013136 deep learning model Methods 0.000 claims abstract description 51
- 230000008569 process Effects 0.000 claims abstract description 33
- 239000013598 vector Substances 0.000 claims description 25
- 238000012545 processing Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 2
- 230000015654 memory Effects 0.000 description 26
- 238000004364 calculation method Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 8
- 239000000284 extract Substances 0.000 description 5
- 238000012216 screening Methods 0.000 description 4
- 230000014509 gene expression Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000003252 repetitive effect Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of electric operation tickets, and particularly discloses a retrieval matching method, a retrieval matching device and a storage medium of an operation ticket, wherein the retrieval matching method comprises the following steps: receiving target operation ticket request information of a user; invoking a pre-trained deep learning model according to target operation ticket request information to identify and process the target operation ticket request information so as to obtain a standardized dispatch text, wherein the pre-trained deep learning model can identify and process the target operation ticket request information according to a preset professional prompt word so as to obtain the standardized dispatch text; performing similarity retrieval and matching on the standardized dispatching order text and an operation ticket database to obtain a retrieval and matching result, wherein the operation ticket database comprises integrated data of history tickets and typical tickets; when available operation tickets matched with the standardized dispatching order text exist in the retrieval matching result, determining a target operation ticket according to the available operation ticket, and outputting the target operation ticket. The operation ticket searching and matching method provided by the invention has the advantage of high efficiency.
Description
Technical Field
The present invention relates to the technical field of electric operation tickets, and in particular, to a method for matching operation tickets, a device for matching operation tickets, and a storage medium.
Background
In an electric power system, in order to realize operations such as schedule change and power transformation, a series of operations are generally required to be performed in a specific order on electric power equipment. For convenience of management and upon execution of operations, these operations are consolidated into the form of operation tickets. The operation ticket is not only the basis of the field operation of the actual operator, but also can be used as the historical data for the subsequent use.
The use of historical data is here embodied in the ticket stage, and the process of generating an operation ticket is referred to as ticket. The ticket involves searching for historical tickets that are consistent with the operational tasks or compiling new tickets based on the relationship profile of the substation equipment. Therefore, the history operation ticket which is the same as or similar to the current operation task is searched in the history operation ticket, repeated work can be avoided, and accuracy can be improved.
In addition, typical tickets are also often used to avoid repetitive work. A typical ticket is a standardized ticket that is commonly used for repetitive, conventional tasks. It contains standard steps for certain operational tasks and can be used for multiple similar operations. The purpose of a typical ticket is to improve the standardization level of the operation ticket, reduce errors in the operation process, and ensure the safety and the high efficiency of the operation. Thus, the operation ticket may be compiled based on a template of a typical ticket, thereby avoiding repeated writing of the same operation steps and ensuring standardization of operations.
In the current practical process, the operation ticket is mostly retrieved by on-site operators to manually read the paper documents according to the dispatching instructions, and automation and intellectualization are lacking. In practical use, the retrieval and matching of operation tickets has the following problems and difficulties:
(1) In case of emergency or in case of frequent and multiple editing of operation tickets, the searching and matching process is complicated, the efficiency is low and the time is long.
(2) The standardization degree is not high, scheduling orders issued by different schedulers have different expressions, the understanding difficulty is high, and the searching and matching difficulty is high.
(3) It is difficult to avoid human errors in manually writing operation tickets.
Due to the existence of the problems, the retrieval and matching working efficiency of the historical data is low, the labor cost is wasted, human errors are difficult to avoid, and the safe operation of the power grid is influenced.
Therefore, how to improve the efficiency and accuracy of operation ticket searching is a technical problem to be solved by those skilled in the art.
Disclosure of Invention
The invention provides a retrieval matching method of an operation ticket, a retrieval matching device of the operation ticket and a storage medium, which solve the problem of low retrieval matching efficiency of the operation ticket in the related technology.
As a first aspect of the present invention, there is provided a search matching method of an operation ticket, comprising:
receiving target operation ticket request information of a user;
invoking a pre-trained deep learning model according to the target operation ticket request information to identify and process the target operation ticket request information so as to obtain a standardized dispatch text, wherein the pre-trained deep learning model can identify and process the target operation ticket request information according to a preset professional prompt word so as to obtain the standardized dispatch text;
performing similarity retrieval and matching on the standardized dispatching order text and an operation ticket database to obtain a retrieval and matching result, wherein the operation ticket database comprises integrated data of history tickets and typical tickets;
and when the available operation ticket matched with the standardized dispatch order text exists in the search matching result, determining a target operation ticket according to the available operation ticket, and outputting the target operation ticket.
Further, the pre-trained deep learning model can identify and process the target operation ticket request information according to a preset professional prompt word and obtain a standardized dispatch instruction text, which comprises the following steps:
extracting operation content of the target operation ticket request information according to a preset scheduling order information extraction prompt word so as to form an initial scheduling order;
And carrying out standardized processing on the initial scheduling command according to a preset standardized prompting word so as to obtain a standardized scheduling command text.
Further, the pre-trained deep learning model can identify and process the target operation ticket request information according to a preset professional prompt word and obtain operation task text information, and the method further includes:
judging whether the content of the target operation ticket request information is a professional field question according to a preset professional type judgment prompt word;
if the content of the target operation ticket request information is a professional field question, the target operation ticket request information is not filtered;
if the content of the target operation ticket request information is a non-professional field question, filtering the target operation ticket request information;
the content of the professional field questioning is that the target operation ticket request information comprises power industry related knowledge, and the non-professional field questioning is that the content except the power industry related knowledge is removed.
Further, performing similarity retrieval matching on the standardized dispatching order text and the operation ticket database to obtain a retrieval matching result, including:
performing data integration according to the history ticket and the typical ticket to obtain an operation ticket database;
Vectorizing the standardized dispatching order text to obtain a vectorized dispatching order;
and carrying out similarity retrieval and matching on the vectorization scheduling order and the data content in the operation ticket database to obtain a retrieval and matching result.
Further, the operation ticket database is obtained by integrating data according to the history ticket and the typical ticket, and comprises the following steps:
performing data preprocessing on the history ticket and the typical ticket to obtain operation ticket preprocessing data;
and vectorizing and storing the operation ticket preprocessing data based on an embedded model to obtain an operation ticket database.
Further, performing similarity retrieval matching on the vectorization scheduling order and the data content in the operation ticket database to obtain a retrieval matching result, including:
respectively carrying out vector similarity matching on the vectorization scheduling order and the data in the operation ticket database;
and obtaining a retrieval matching result according to the judgment result of the vector similarity and the similarity preset threshold value.
Further, obtaining a search matching result according to the judgment result of the vector similarity and the similarity preset threshold value comprises the following steps:
if a judging result that the vector similarity is smaller than the similarity preset threshold exists, determining that an available operation ticket matched with the standardized scheduling text exists in the retrieval matching result;
And if the judgment result that the vector similarity is smaller than the similarity preset threshold value does not exist, determining that no available operation ticket matched with the standardized dispatching order text exists in the retrieval matching result.
Further, when there is an available operation ticket matching with the standardized dispatch text in the search matching result, determining a target operation ticket according to the available operation ticket, and outputting the target operation ticket, including:
invoking a pre-trained deep learning model according to the available operation tickets, and inputting the available operation tickets into the pre-trained deep learning model to determine target operation tickets matched with the standardized dispatch texts in the available operation tickets, wherein the pre-trained deep learning model can match the available operation tickets with the standardized dispatch texts according to preset matching prompt words, and obtain target operation tickets;
and outputting the target operation ticket.
As another aspect of the present invention, there is provided an operation ticket search matching apparatus for implementing the operation ticket search matching method described above, wherein the operation ticket search matching apparatus includes:
The receiving module is used for receiving target operation ticket request information of a user;
the scheduling order generating module is used for calling a pre-trained deep learning model according to the target operation ticket request information to identify and process the target operation ticket request information so as to obtain a standardized scheduling order text, and the pre-trained deep learning model can identify and process the target operation ticket request information according to a preset professional prompt word so as to obtain the standardized scheduling order text;
the retrieval matching module is used for carrying out similarity retrieval matching on the standardized dispatching order text and an operation ticket database to obtain a retrieval matching result, wherein the operation ticket database comprises integrated data of history tickets and typical tickets;
and the output module is used for determining a target operation ticket according to the available operation ticket when the available operation ticket matched with the standardized dispatch text exists in the search matching result, and outputting the target operation ticket.
As another aspect of the present invention, there is provided a storage medium containing computer instructions which, when loaded and executed by a processor, implement the above-described operation ticket retrieval matching method.
According to the operation ticket searching and matching method, the pre-trained deep learning model is called according to the target operation ticket request information of the user to identify and process the target operation ticket request information so as to obtain the standardized dispatch text, then similarity searching and matching are conducted on the operation ticket database integrated by the history ticket and the typical ticket and the standardized dispatch text so as to determine a searching and matching result, and the target operation ticket which accords with the standardized dispatch text is determined according to the searching and matching result. The operation ticket retrieval matching method can accurately extract the scheduling command and effectively improve retrieval matching efficiency in a mode of identifying the target operation ticket request information after learning the target operation ticket request information based on the pre-trained deep learning model; in addition, the method for obtaining the target operation ticket by obtaining the text information of the operation task based on the pre-trained deep learning model and then carrying out similarity retrieval and matching with the operation ticket database can be used without rule definition and logic definition, so that the method can be suitable for different scenes.
Drawings
The accompanying drawings are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate the invention and together with the description serve to explain, without limitation, the invention.
Fig. 1 is a flowchart of a method for matching operation tickets by searching.
Fig. 2 is a flowchart for obtaining standardized dispatch texts provided by the present invention.
Fig. 3 is a flowchart of the normalization process of the scheduling command provided by the present invention.
Fig. 4 is a flowchart of obtaining a search matching result provided by the present invention.
FIG. 5 is a flow chart of the present invention for matching tickets to obtain available tickets.
Fig. 6 is a flowchart of a method for obtaining a target ticket by screening a GPT model according to the present invention.
Fig. 7 is a flowchart of the overall implementation process of the operation ticket searching and matching method provided by the invention.
Fig. 8 is a block diagram of an electronic device according to the present invention.
Detailed Description
It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other. The invention will be described in detail below with reference to the drawings in connection with embodiments.
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the invention herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Most of the current operation ticket searching and matching are based on manual reading by field operators according to scheduling instructions, and the problems of high searching and matching difficulty, low efficiency and the like exist.
Based on this, in this embodiment, there is provided a method for matching operation tickets in search, fig. 1 is a flowchart of the method for matching operation tickets in search, as shown in fig. 1, including:
S100, receiving target operation ticket request information of a user;
in the embodiment of the invention, when the user needs to search and match the operation ticket, the target operation ticket request information is sent, so that the target operation ticket request information of the user can be received to search and match according to the target operation ticket request information.
It should be appreciated that the target ticket request information may include, in particular, some device information as well as specific operations.
For example, the target ticket request information in the electric power field may specifically include "disconnect 223 switch line side-hung ground", "change load of 2# from 1# back", and so on.
The target ticket request information may be a standardized instruction or a spoken instruction, which is not limited herein.
S200, invoking a pre-trained deep learning model according to the target operation ticket request information to identify and process the target operation ticket request information so as to obtain a standardized dispatch text, wherein the pre-trained deep learning model can identify and process the target operation ticket request information according to a preset professional prompt word so as to obtain the standardized dispatch text;
In the embodiment of the invention, the target operation ticket request information is identified based on a pre-trained deep learning model to obtain a standardized dispatching order text.
It should be appreciated that, in order to implement the recognition process for the target ticket request information, the pre-trained deep learning model may be implemented based on a preset professional prompt.
For example, the Pre-trained deep learning model may be a GPT (generating Pre-Trained Transformer, generating Pre-trained transducer model) model, and based on the GPT model, the GPT model may perform recognition processing on the target operation ticket request information by setting a prompt word. The user can input detailed description of equipment information and specific operation, and the GPT model can recognize the specific description through preset professional prompt words, so that standardized dispatching order text can be obtained.
S300, carrying out similarity retrieval and matching on the standardized dispatching order text and an operation ticket database to obtain a retrieval and matching result, wherein the operation ticket database comprises integrated data of history tickets and typical tickets;
in the embodiment of the invention, the history ticket and the typical ticket are integrated to form the operation ticket database, the standardized dispatch text obtained in the previous step is subjected to similarity retrieval and matching with the operation ticket database, and whether the available operation ticket matched with the standardized dispatch text exists or not is determined according to the retrieval and matching result.
And S400, when the available operation ticket matched with the standardized dispatch order text exists in the search matching result, determining a target operation ticket according to the available operation ticket, and outputting the target operation ticket.
In the embodiment of the invention, after the matching is searched according to the similarity, if available operation tickets matched with the standardized dispatch text exist in the search matching result, a target operation ticket which accords with the standardized dispatch text can be further determined in the available operation tickets, and the target operation ticket is output.
Therefore, the operation ticket searching and matching method provided by the invention comprises the steps of calling a pre-trained deep learning model according to target operation ticket request information of a user to identify and process the target operation ticket request information so as to obtain a standardized dispatch text, then carrying out similarity searching and matching on an operation ticket database integrated by a history ticket and a typical ticket and the standardized dispatch text so as to determine a searching and matching result, and determining a target operation ticket conforming to the standardized dispatch text according to the searching and matching result. The operation ticket retrieval matching method can accurately extract the scheduling command and effectively improve retrieval matching efficiency in a mode of identifying the target operation ticket request information after learning the target operation ticket request information based on the pre-trained deep learning model; in addition, the method for obtaining the target operation ticket by obtaining the text information of the operation task based on the pre-trained deep learning model and then carrying out similarity retrieval and matching with the operation ticket database can be used without rule definition and logic definition, so that the method can be suitable for different scenes.
In an embodiment of the present invention, in order to obtain a standardized dispatch text according to target operation ticket request information, the pre-trained deep learning model may identify and process the target operation ticket request information according to a preset professional prompt word and obtain a standardized dispatch text, as shown in fig. 2, including:
s210, extracting operation content of the target operation ticket request information according to a preset scheduling order information extraction prompt word so as to form an initial scheduling order;
in the embodiment of the present invention, taking the pre-trained deep learning model as a GPT model as an example, the target operation ticket request information received by the GPT model is, for example, a non-standard spoken-language scheduling instruction: "the operation of hanging the ground wire is now required, and the switch line to be operated is the one 223. This switch is needed to flank the ground wire.
The extracting prompt words of the preset scheduling instruction information aiming at the target operation ticket request information can be specifically as follows:
"please extract the equipment information and specific operations from the scheduling command according to the user input. Please answer in the following standard format:
the operating device is mentioned in the scheduling reams: xxx >; < operations mentioned in the scheduling reams: xxx-
The following is the user input { context }.
Therefore, the GPT model extracts the prompt word based on the above preset schedule information to extract the device to be operated as "223 switch line", and the specific operation to be extracted is "side-hung ground line". In the above example, after the GPT model performs the information extraction operation, the obtained output result of the scheduling command is:
"operating device is mentioned in scheduling order: 223 switching lines; operations mentioned in the scheduling reams: and (5) hanging a ground wire laterally.
S220, carrying out standardized processing on the initial scheduling command according to a preset standardized prompting word so as to obtain a standardized scheduling command text.
After the prompt word is extracted from the preset schedule information to the initial schedule, the description of the initial schedule is still a non-standardized description, so that standardized processing is still required to obtain the standardized schedule.
In the embodiment of the present invention, in order to implement the standardized processing of the scheduling, as shown in fig. 3, the initial scheduling obtained after the scheduling information extraction is completed is: "operating device is mentioned in scheduling order: 223 switching lines; operations mentioned in the scheduling reams: and hanging a ground wire on the side, and carrying out standardized processing on the initial scheduling command according to a preset standardized prompting word, wherein the preset standardized prompting word specifically comprises:
"please refer to the operation device and the operation task in the schedule, and re-describe, generate a standard and standard schedule text, and the following is the information extracted according to the schedule: < { context } ".
After the preset standardized prompt word is spliced with the initial scheduling command, the spliced text is obtained as follows:
"please refer to the operation device and the operation task in the schedule, and re-describe, generate a standard and standard schedule text, and the following is the information extracted according to the schedule: the operating device is mentioned in the scheduling reams: 223 switching lines; operations mentioned in the scheduling reams: side hanging ground wire > ".
The GPT model can obtain a standardized scheduling instruction text according to the spliced text: "223 switch line side hung ground".
It should be understood that the standardized schedule text can be obtained by inputting the spliced text information obtained after the initialization schedule is spliced with the preset standardized prompt word into the GPT model.
In the embodiment of the present invention, because the target operation request information may be a non-professional field question due to the incorrect input of the user, in order to ensure that the target operation request information is all a professional field question so as to enable subsequent search matching, the pre-trained deep learning model can identify and process the target operation ticket request information according to a preset professional prompt word and obtain operation task text information, and further includes:
Judging whether the content of the target operation ticket request information is a professional field question according to a preset professional type judgment prompt word;
if the content of the target operation ticket request information is a professional field question, the target operation ticket request information is not filtered;
if the content of the target operation ticket request information is a non-professional field question, filtering the target operation ticket request information;
the content of the professional field questioning is that the target operation ticket request information comprises power industry related knowledge, and the non-professional field questioning is that the content except the power industry related knowledge is removed.
It should be understood that when judging the content of the target operation request information, the pre-trained deep learning model is implemented based on a preset professional type judgment prompt word, and in the embodiment of the present invention, the pre-trained deep learning model still takes a GPT model as an example, and the preset professional type judgment prompt word may specifically be:
please judge the type of the current user input according to the user input. Please answer in the format of < non-professional field questions > or < professional field questions >.
The definition of the professional field question is: knowledge about power industry related commands belongs to questions in the professional field.
Definition of non-professional field questions: other inputs than those related to the power industry are all questions in the non-professional field.
The following is the user input { context }.
When the GPT model receives similar content of 'how weather today' input by a user as target operation request information, the GPT model answers as 'non-professional field question', and the information is filtered; when the GPT model receives the content which is input by a user and is similar to the content that the ground wire is hung on the side of the switch line of the split 223 and the load of the 2# is changed from the 1# to the back is changed as target operation request information, the GPT model answers as a professional field question and does not filter the content.
In the embodiment of the present invention, after the standardized schedule text is obtained, search matching may be performed based on the standardized schedule text and the operation ticket database, specifically, as shown in fig. 4, similarity search matching is performed on the standardized schedule text and the operation ticket database, so as to obtain a search matching result, including:
s310, integrating data according to the history ticket and the typical ticket to obtain an operation ticket database;
in the embodiment of the invention, the method specifically comprises the following steps:
performing data preprocessing on the history ticket and the typical ticket to obtain operation ticket preprocessing data;
And vectorizing and storing the operation ticket preprocessing data based on an embedded model to obtain an operation ticket database.
It should be noted that the embedding model may be specifically a text2vec model, and of course, may also be other embedding models, for example, a word embedding model. According to the embodiment of the invention, the text2vec model can realize the effects of excellent Chinese support and more accurate matching result.
Specifically, the following is an example description of two specific operation tickets in the operation ticket database:
(1) Operation ticket 1 in operation ticket database
Operation tasks: the load of the No. 2 is changed from the No. 1 to the reverse
The operation content is as follows: 1. the 345 automatic switching handle is changed into a manual mode; 2. putting ring closing optional hop 345;3. the check 382 should be pulled apart; 4. pushing 382 the cart into an operational position; 5. checking 382 that the trolley is in the run position; 6. closing 382;7. the check 382 should be closed.
(2) Operation ticket 2 in operation ticket database
Operation tasks: the switch P554 two 223 and CQX219 two 224 is opened, the switch trolley 223 and 224 is pulled out, and the ground wire is hung on the side of the switch circuit 223 and 224
The operation content is as follows: 1. checking 223 three-phase lamp lighting of the live display on the line side; 2. pulling open 223;3. inspection 223 should be pulled apart; 4. checking 224 the three-phase lamp of the live display on the line side; 5. pulling 224;6. check 224 should be pulled apart; 7. pulling the 223 trolley to a standby position; 8. the trolley is checked 223 for a standby position.
In the embodiment of the invention, repeated data deletion, format unification and other preprocessing operations can be performed on the history ticket and the typical ticket, and operation ticket preprocessing data is obtained.
S320, vectorizing the standardized dispatching order text to obtain a vectorized dispatching order;
it should be appreciated that in order to enable efficient and quick implementation of search matching with the contents of the operation ticket database, the standardized schedule text is also vectorized herein to obtain a vectorized schedule.
S330, carrying out similarity retrieval and matching on the vectorization scheduling order and the data content in the operation ticket database to obtain a retrieval and matching result.
Specifically, to achieve similarity retrieval matching, specifically may include:
respectively carrying out vector similarity matching on the vectorization scheduling order and the data in the operation ticket database;
and obtaining a retrieval matching result according to the judgment result of the vector similarity and the similarity preset threshold value.
It should be understood that the similarity between vectors can be obtained by calculating the cosine distance, the euclidean distance or other similarity calculation methods between vectors, so as to realize vector similarity matching between the standard dispatching order and the integrated historical data, and thus, the matching inquiry of the historical operation ticket can be carried out.
In the embodiment of the invention, as shown in fig. 5, a search matching result is obtained by setting a similarity threshold to judge the vector similarity when performing similarity matching. The following describes similarity calculation by taking Euclidean distance as an example.
When receiving the standardized schedule text: after the ground wire is hung on the side of the switch circuit of 'tearing down 223', vectorizing the text of the standardized dispatching order to obtain a vectorized dispatching order, and matching the vectorized dispatching order with the content in the operation ticket database according to the calculated Euclidean distance. Wherein, three-dimensional Euclidean distance calculation formula:
d=(x2-x1) 2 +(y2-y1) 2 +(z2-z1) 2 ，
the calculation result of the three-dimensional Euclidean distance calculation formula is represented by a vector of 'disconnecting 223 the switch line side hanging ground wire', which is: (1.93517, -7.08082, 8.17411), i.e. x2, y2, z2 are 1.93517, -7.08082, 8.17411, respectively;
"operational task: disassembling 223 the switch line side hanging ground wire; the operation content is as follows: 1. pulling apart 223-7;2. check 223-7 should be pulled apart; the vector of "is: (9.40192, 5.84075, -7.84949), i.e. x1, y1, z1 are 9.40192,5.84075, -7.84949, respectively;
substituting the vector into the three-dimensional Euclidean distance calculation formula to calculate so as to obtain the matching similarity: 21.8969.
In the embodiment of the invention, obtaining the search matching result according to the judgment result of the vector similarity and the similarity preset threshold value comprises the following steps:
if a judging result that the vector similarity is smaller than the similarity preset threshold exists, determining that an available operation ticket matched with the operation task text information exists in the retrieval matching result;
and if the judgment result that the vector similarity is smaller than the similarity preset threshold value does not exist, determining that no available operation ticket matched with the operation task text information exists in the retrieval matching result.
Here, for example, a preset threshold of 100 is set, and a matching result is obtained based on the calculation method of the vector similarity:
(1) Operation ticket 1
Operation tasks: side-hanging ground wire for disconnecting 223 switch circuit
The operation content is as follows: 1. pulling apart 223-7;2. check 223-7 should be pulled apart;
match similarity (smaller closer): 21.9
(2) Operation ticket 2
Operation tasks: side-hanging ground wire for dismounting 269 switch circuit
The operation content is as follows: 1. pulling apart 269-7;2. checking 269-7 should be pulled apart;
match similarity (smaller closer): 125.3
Since the preset similarity threshold is set to 100, only ticket 1 can be used as the available ticket, i.e. the available ticket is:
Operation tasks: side-hanging ground wire for disconnecting 223 switch circuit
The operation content is as follows: 1. pulling apart 223-7;2. inspection 223-7 should be pulled apart.
It should be understood that the setting of the similarity preset threshold is not limited herein, and may be set as needed.
In the embodiment of the present invention, since a plurality of available tickets may be obtained through the above vector similarity calculation, in order to obtain a target ticket more accurately, when an available ticket matching the standardized dispatch text exists in the search matching result, determining a target ticket according to the available ticket, and outputting the target ticket, including:
invoking a pre-trained deep learning model according to the available operation tickets, and inputting the available operation tickets into the pre-trained deep learning model to determine target operation tickets matched with the standardized dispatch texts in the available operation tickets, wherein the pre-trained deep learning model can match the available operation tickets with the standardized dispatch texts according to preset matching prompt words, and obtain target operation tickets;
and outputting the target operation ticket.
Specifically, if a plurality of available tickets are matched according to the vector similarity, as shown in the following example, a plurality of available tickets are matched:
(1) Available operation ticket 1
Operation tasks: side-hanging ground wire for disconnecting 223 switch circuit
The operation content is as follows: 1. pulling apart 223-7;2. check 223-7 should be pulled apart;
match similarity (smaller closer): 54.3
(2) Available operation ticket 2
Operation tasks: side-hanging ground wire for disconnecting 226 switch circuit
The operation content is as follows: 1. pulling 226-7 apart; 2. check 226-7 should be pulled apart;
match similarity (smaller closer): 72.3
Here the target ticket matching the standardized dispatch text is further screened and judged based on a pre-trained deep learning model.
As shown in fig. 6, the pre-trained deep learning model is still exemplified by a GPT model, which determines available operation tickets based on preset matching prompt words, and determines a target operation ticket matching with the standardized dispatch text. The preset matching prompt words used by the GPT model in this step may specifically be:
"the following are available tickets that match satisfying the similarity threshold:
{context}
please see the standardized scheduling order: { query }. And judging and matching available operation tickets conforming to the current standardized dispatching order text.
According to the preset matching prompt words and the matched available operation tickets, the spliced text after the prompt words are spliced is as follows:
"the following are available tickets that match satisfying the similarity threshold:
operation tasks: side-hanging ground wire for disconnecting 223 switch circuit
The operation content is as follows: 1. pulling apart 223-7;2. check 223-7 should be pulled apart;
operation tasks: side-hanging ground wire for disconnecting 226 switch circuit
The operation content is as follows: 1. pulling 226-7 apart; 2. check 226-7 should be pulled apart;
please see the standardized scheduling order: the switch line side is disconnected 223 by hanging the ground wire. And judging and matching available operation tickets conforming to the current standardized scheduling command.
And after the spliced text is input into the GPT model, outputting the obtained GPT model:
"operational task: side-hanging ground wire for disconnecting 223 switch circuit
The operation content is as follows: 1. pulling apart 223-7;2. check 223-7 should be pulled apart).
And outputting the GPT model, namely, screening available operation tickets according to the spliced text by the GPT model to obtain a target operation ticket, and finally outputting the target operation ticket as an operation ticket matched with the standardized dispatch text.
It should be understood that if the GPT model cannot obtain the matching target ticket after screening the available tickets, the available tickets that do not meet the condition will be output.
In summary, the operation ticket searching and matching method provided by the invention adopts a pre-trained deep learning model to realize the identification and processing of the operation ticket, and the screening of the available operation ticket finally obtains the target operation ticket. Compared with the traditional natural language model, the pre-trained deep learning model has stronger universality and can be used for various different natural language processing tasks without great modification. In addition, the pre-trained deep learning model has strong semantic understanding capability, can understand the semantic and context information in sentences, and generates coherent texts. The pre-training stage of the pre-training deep learning model learns rich semantic knowledge and language modes in large-scale text corpus data, so that the method can flexibly adapt to different tasks and data, and has the capabilities of extracting information, understanding and correcting errors in texts, normalizing and standardizing the texts.
In addition, in combination with the operation ticket searching and matching method shown in fig. 7, the operation ticket searching and matching method provided by the invention has the following beneficial effects:
(1) Adaptability to different scenarios
In the prior art, the process logic of generating the operation ticket by the work plan is complex, the traditional scheme realizes the association processing of the logic in the form of predefined rules and predefined dictionaries, and the process is strongly dependent on manual understanding and setting, so that if the operation ticket writing scene of different rules is involved, the rules need to be modified or newly built; the operation ticket searching and matching method can realize the mode of searching and matching the historical operation ticket and the typical ticket, does not need to define rules and set logic, and can adapt to different scenes only by historical data.
(2) Correcting spoken language expression
Because the work plan is manually formulated, a large amount of spoken language and nonstandard expression exist, and the traditional scheme can cause uncertainty in the generation process; the deep learning model based on pre-training realizes the function of standardization after extracting information from the scheduling command, has the capability of standardization of the scheduling command expressed by spoken language, and can solve the problems.
(3) Promotion of search matching efficiency
The method realizes the search matching from the dispatching order in the form of natural language directly to the operation ticket, and greatly improves the search matching efficiency of the history operation ticket and the typical ticket.
(4) Continuous optimization of space
The traditional scheme has strong judgment of human rules, so that the capability of continuously optimizing and upgrading is not provided; the invention is based on the searching and matching method of the history ticket and the typical ticket, and the generating effect of the operation ticket is continuously optimized along with the increase of the data volume (such as the history ticket and the typical ticket number).
As another embodiment of the present invention, there is provided an operation ticket search matching apparatus for implementing the operation ticket search matching method described above, wherein, as shown in fig. 7, the operation ticket search matching apparatus includes:
a receiving module 100, configured to receive target operation ticket request information of a user;
the dispatcher generation module 200 is configured to invoke a pre-trained deep learning model according to the target operation ticket request information to identify and process the target operation ticket request information so as to obtain a standardized dispatcher text, where the pre-trained deep learning model can identify and process the target operation ticket request information according to a preset professional prompt word so as to obtain the standardized dispatcher text;
The search matching module 300 is configured to perform similarity search matching on the standardized dispatch text and an operation ticket database, so as to obtain a search matching result, where the operation ticket database includes integrated data of a history ticket and a typical ticket;
and the matching output module 400 is used for determining a target operation ticket according to the available operation ticket and outputting the target operation ticket when the available operation ticket matched with the standardized dispatch text exists in the search matching result.
According to the operation ticket searching and matching device provided by the invention, the target operation ticket request information is identified and processed by calling the pre-trained deep learning model according to the target operation ticket request information of the user, so that the standardized dispatch text is obtained, then the similarity searching and matching are carried out on the operation ticket database integrated by the history ticket and the typical ticket and the standardized dispatch text, so that the searching and matching result is determined, and the target operation ticket which accords with the standardized dispatch text is determined according to the searching and matching result. The operation ticket retrieval and matching device can accurately extract the scheduling command and effectively improve retrieval and matching efficiency by means of identifying the target operation ticket request information after learning the target operation ticket request information based on the pre-trained deep learning model; in addition, the method for obtaining the target operation ticket by obtaining the text information of the operation task based on the pre-trained deep learning model and then carrying out similarity retrieval and matching with the operation ticket database can be used without rule definition and logic definition, so that the method can be suitable for different scenes.
The specific working process and principle of the operation ticket searching and matching device provided by the invention can refer to the description of the operation ticket searching and matching method, and the description is omitted here.
As another embodiment of the present invention, an electronic device is provided, including a memory communicatively coupled to a processor, the memory configured to store computer instructions, and the processor configured to load and execute the computer instructions to implement the aforementioned method of matching operation tickets.
As shown in fig. 8, the electronic device 80 may include: at least one processor 81, such as a CPU (Central Processing Unit ), at least one communication interface 83, a memory 84, at least one communication bus 82. Wherein the communication bus 82 is used to enable connected communication between these components. The communication interface 83 may include a Display screen (Display) and a Keyboard (Keyboard), and the optional communication interface 83 may further include a standard wired interface and a wireless interface. The memory 84 may be a high-speed RAM memory (Random Access Memory, volatile random access memory) or a non-volatile memory (non-volatile memory), such as at least one disk memory. The memory 84 may also optionally be at least one memory device located remotely from the aforementioned processor 81. Wherein the memory 84 stores an application program and the processor 81 invokes the program code stored in the memory 84 for performing any of the method steps described above.
The communication bus 82 may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The communication bus 82 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in fig. 8, but not only one bus or one type of bus.
Wherein the memory 84 may include volatile memory (English) such as random-access memory (RAM); the memory may also include a nonvolatile memory (english: non-volatile memory), such as a flash memory (english: flash memory), a hard disk (english: hard disk drive, abbreviated as HDD) or a solid state disk (english: solid-state drive, abbreviated as SSD); the memory 84 may also include a combination of the types of memory described above.
The processor 81 may be a central processor (English: central processing unit, abbreviated: CPU), a network processor (English: network processor, abbreviated: NP) or a combination of CPU and NP.
The processor 81 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a Programmable Logic Device (PLD), or a combination thereof (English: programmable logic device). The PLD may be a complex programmable logic device (English: complex programmable logic device, abbreviated: CPLD), a field programmable gate array (English: field-programmable gate array, abbreviated: FPGA), a general-purpose array logic (English: generic arraylogic, abbreviated: GAL), or any combination thereof.
Optionally, the memory 84 is also used for storing program instructions. The processor 81 may invoke program instructions to implement the operation ticket retrieval matching method as shown in the fig. 1 embodiment of the present invention.
As another embodiment of the present invention, there is provided a storage medium including computer instructions which, when loaded and executed by a processor, implement the above-described operation ticket retrieval matching method.
In an embodiment of the present invention, there is provided a non-transitory computer-readable storage medium storing computer-executable instructions that can perform the search matching method of the operation ticket in any of the above-described method embodiments. Wherein the storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a Flash Memory (Flash Memory), a Hard Disk (HDD), or a Solid State Drive (SSD); the storage medium may also comprise a combination of memories of the kind described above.
It is to be understood that the above embodiments are merely illustrative of the application of the principles of the present invention, but not in limitation thereof. Various modifications and improvements may be made by those skilled in the art without departing from the spirit and substance of the invention, and are also considered to be within the scope of the invention.
Claims (10)
1. A search matching method for an operation ticket, comprising:
receiving target operation ticket request information of a user;
invoking a pre-trained deep learning model according to the target operation ticket request information to identify and process the target operation ticket request information so as to obtain a standardized dispatch text, wherein the pre-trained deep learning model can identify and process the target operation ticket request information according to a preset professional prompt word so as to obtain the standardized dispatch text;
performing similarity retrieval and matching on the standardized dispatching order text and an operation ticket database to obtain a retrieval and matching result, wherein the operation ticket database comprises integrated data of history tickets and typical tickets;
and when the available operation ticket matched with the standardized dispatch order text exists in the search matching result, determining a target operation ticket according to the available operation ticket, and outputting the target operation ticket.
2. The method for matching operation ticket retrieval according to claim 1, wherein the pre-trained deep learning model is capable of identifying and processing the target operation ticket request information according to a preset professional prompt word and obtaining standardized dispatch command text, and comprises the following steps:
extracting operation content of the target operation ticket request information according to a preset scheduling order information extraction prompt word so as to form an initial scheduling order;
and carrying out standardized processing on the initial scheduling command according to a preset standardized prompting word so as to obtain a standardized scheduling command text.
3. The method for matching operation ticket retrieval according to claim 2, wherein the pre-trained deep learning model is capable of identifying and processing the target operation ticket request information according to a preset professional prompt word and obtaining operation task text information, and further comprising:
judging whether the content of the target operation ticket request information is a professional field question according to a preset professional type judgment prompt word;
if the content of the target operation ticket request information is a professional field question, the target operation ticket request information is not filtered;
if the content of the target operation ticket request information is a non-professional field question, filtering the target operation ticket request information;
The content of the professional field questioning is that the target operation ticket request information comprises power industry related knowledge, and the non-professional field questioning is that the content except the power industry related knowledge is removed.
4. A method for matching operation ticket search according to any one of claims 1 to 3, wherein matching the standardized dispatch order text with the operation ticket database by similarity search to obtain search matching result comprises:
performing data integration according to the history ticket and the typical ticket to obtain an operation ticket database;
vectorizing the standardized dispatching order text to obtain a vectorized dispatching order;
and carrying out similarity retrieval and matching on the vectorization scheduling order and the data content in the operation ticket database to obtain a retrieval and matching result.
5. The method for matching operation ticket search according to claim 4, wherein the step of integrating data based on the history ticket and the typical ticket to obtain an operation ticket database comprises the steps of:
performing data preprocessing on the history ticket and the typical ticket to obtain operation ticket preprocessing data;
and vectorizing and storing the operation ticket preprocessing data based on an embedded model to obtain an operation ticket database.
6. The method for matching operation ticket search according to claim 4, wherein matching the vectorized scheduling order with the data content in the operation ticket database by similarity search, obtaining a search matching result, comprises:
respectively carrying out vector similarity matching on the vectorization scheduling order and the data in the operation ticket database;
and obtaining a retrieval matching result according to the judgment result of the vector similarity and the similarity preset threshold value.
7. The method for matching search of operation ticket according to claim 6, wherein obtaining search matching result according to the judgment result of the vector similarity and the similarity preset threshold value comprises:
if a judging result that the vector similarity is smaller than the similarity preset threshold exists, determining that an available operation ticket matched with the standardized scheduling text exists in the retrieval matching result;
and if the judgment result that the vector similarity is smaller than the similarity preset threshold value does not exist, determining that no available operation ticket matched with the standardized dispatching order text exists in the retrieval matching result.
8. A search matching method for operation tickets according to any one of claims 1 to 3, characterized in that when there is an available operation ticket matching with the standardized dispatch text in the search matching result, determining a target operation ticket from the available operation ticket and outputting the target operation ticket, comprising:
Invoking a pre-trained deep learning model according to the available operation tickets, and inputting the available operation tickets into the pre-trained deep learning model to determine target operation tickets matched with the standardized dispatch texts in the available operation tickets, wherein the pre-trained deep learning model can match the available operation tickets with the standardized dispatch texts according to preset matching prompt words, and obtain target operation tickets;
and outputting the target operation ticket.
9. A search matching device for operation tickets for implementing the search matching method for operation tickets according to any one of claims 1 to 8, characterized in that the search matching device for operation tickets comprises:
the receiving module is used for receiving target operation ticket request information of a user;
the scheduling order generating module is used for calling a pre-trained deep learning model according to the target operation ticket request information to identify and process the target operation ticket request information so as to obtain a standardized scheduling order text, and the pre-trained deep learning model can identify and process the target operation ticket request information according to a preset professional prompt word so as to obtain the standardized scheduling order text;
The retrieval matching module is used for carrying out similarity retrieval matching on the standardized dispatching order text and an operation ticket database to obtain a retrieval matching result, wherein the operation ticket database comprises integrated data of history tickets and typical tickets;
and the output module is used for determining a target operation ticket according to the available operation ticket when the available operation ticket matched with the standardized dispatch text exists in the search matching result, and outputting the target operation ticket.
10. A storage medium comprising computer instructions which, when loaded and executed by a processor, implement the method of matching the retrieval of an operation ticket according to any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311347187.8A CN117093675A (en) | 2023-10-18 | 2023-10-18 | Operation ticket searching and matching method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311347187.8A CN117093675A (en) | 2023-10-18 | 2023-10-18 | Operation ticket searching and matching method, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117093675A true CN117093675A (en) | 2023-11-21 |
Family
ID=88777165
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311347187.8A Pending CN117093675A (en) | 2023-10-18 | 2023-10-18 | Operation ticket searching and matching method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117093675A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118365464A (en) * | 2024-04-23 | 2024-07-19 | 北京中天华胜科技有限公司 | Automatic invoicing and invoice management system and method based on artificial intelligence |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109165275A (en) * | 2018-07-24 | 2019-01-08 | 国网浙江省电力有限公司电力科学研究院 | Intelligent substation operation order information intelligent search matching process based on deep learning |
| CN110188345A (en) * | 2019-04-28 | 2019-08-30 | 北京科东电力控制系统有限责任公司 | A kind of intelligent identification Method and device of electric power operation ticket |
| CN111353487A (en) * | 2019-08-20 | 2020-06-30 | 国网浙江省电力有限公司台州供电公司 | Equipment information extraction method for transformer substation |
| CN113792538A (en) * | 2021-08-27 | 2021-12-14 | 北京科东电力控制系统有限责任公司 | Method and device for quickly generating operation ticket of power distribution network |
| CN116484826A (en) * | 2023-06-19 | 2023-07-25 | 广东电网有限责任公司 | Operation ticket generation method, device, equipment and storage medium |
-
2023
- 2023-10-18 CN CN202311347187.8A patent/CN117093675A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109165275A (en) * | 2018-07-24 | 2019-01-08 | 国网浙江省电力有限公司电力科学研究院 | Intelligent substation operation order information intelligent search matching process based on deep learning |
| CN110188345A (en) * | 2019-04-28 | 2019-08-30 | 北京科东电力控制系统有限责任公司 | A kind of intelligent identification Method and device of electric power operation ticket |
| CN111353487A (en) * | 2019-08-20 | 2020-06-30 | 国网浙江省电力有限公司台州供电公司 | Equipment information extraction method for transformer substation |
| CN113792538A (en) * | 2021-08-27 | 2021-12-14 | 北京科东电力控制系统有限责任公司 | Method and device for quickly generating operation ticket of power distribution network |
| CN116484826A (en) * | 2023-06-19 | 2023-07-25 | 广东电网有限责任公司 | Operation ticket generation method, device, equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118365464A (en) * | 2024-04-23 | 2024-07-19 | 北京中天华胜科技有限公司 | Automatic invoicing and invoice management system and method based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109145294B (en) | Text entity identification method and device, electronic equipment and storage medium | |
| CN109376353B (en) | Natural language processing-based power grid starting operation ticket generation device and method | |
| CN114168716B (en) | Deep learning-based automatic engineering cost extraction and analysis method and device | |
| CN106777296A (en) | Method and system are recommended in a kind of talent's search based on semantic matches | |
| CN111651474B (en) | Method and system for converting natural language into structured query language | |
| CN111274817A (en) | Intelligent software cost measurement method based on natural language processing technology | |
| CN117093675A (en) | Operation ticket searching and matching method, device and storage medium | |
| CN112417852B (en) | Method and device for judging importance of code segment | |
| CN112417996B (en) | Information processing method and device for industrial drawing, electronic equipment and storage medium | |
| CN117408631B (en) | Operation ticket generation method, device and storage medium | |
| CN111831624A (en) | Data table creating method and device, computer equipment and storage medium | |
| CN111753517A (en) | Document comparison method, device, equipment and medium based on RPA and AI | |
| CN117882080A (en) | Method and device for converting industry standard specifications into at least one instantiated rule | |
| WO2019164503A1 (en) | Ranking of engineering templates via machine learning | |
| CN110458383B (en) | Method and device for realizing demand processing servitization, computer equipment and storage medium | |
| CN118035463A (en) | Method and system for constructing power grid dispatching multi-mode knowledge graph | |
| CN117521629A (en) | Bridge detection report generation method based on large language model | |
| CN111723580B (en) | Power dispatching station information graph validation method based on voice recognition and image recognition | |
| CN113010682B (en) | Command ticket system checking method, device and storage medium | |
| CN110442716B (en) | Intelligent text data processing method and device, computing equipment and storage medium | |
| CN113918726A (en) | Retrieval method and system for fault knowledge of electric power main transformer equipment | |
| CN117474457B (en) | Intelligent auxiliary system for dangerous chemical and industrial and trade equipment emergency management law enforcement inspection | |
| WO2024108986A1 (en) | Communication network service processing method and device | |
| CN113987194A (en) | Knowledge graph construction method and device and electronic equipment | |
| CN118607486A (en) | AIGC-based text labeling method, AIGC-based text labeling device, computer equipment 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 |