CN109526027B - Cell capacity optimization method, device, equipment and computer storage medium - Google Patents

Cell capacity optimization method, device, equipment and computer storage medium Download PDF

Info

Publication number
CN109526027B
CN109526027B CN201811424903.7A CN201811424903A CN109526027B CN 109526027 B CN109526027 B CN 109526027B CN 201811424903 A CN201811424903 A CN 201811424903A CN 109526027 B CN109526027 B CN 109526027B
Authority
CN
China
Prior art keywords
cell
data
public opinion
target
key data
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.)
Active
Application number
CN201811424903.7A
Other languages
Chinese (zh)
Other versions
CN109526027A (en
Inventor
王希
陈桂桢
陈向荣
陈如松
瞿俊
杨家珠
林凤城
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Mobile Communications Group Co Ltd
China Mobile Group Fujian Co Ltd
Original Assignee
China Mobile Communications Group Co Ltd
China Mobile Group Fujian Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Mobile Communications Group Co Ltd, China Mobile Group Fujian Co Ltd filed Critical China Mobile Communications Group Co Ltd
Priority to CN201811424903.7A priority Critical patent/CN109526027B/en
Publication of CN109526027A publication Critical patent/CN109526027A/en
Application granted granted Critical
Publication of CN109526027B publication Critical patent/CN109526027B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/02—Traffic management, e.g. flow control or congestion control
    • H04W28/0289—Congestion control
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H04L41/147—Network analysis or design for predicting network behaviour
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/02—Traffic management, e.g. flow control or congestion control
    • H04W28/06—Optimizing the usage of the radio link, e.g. header compression, information sizing, discarding information
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W72/00—Local resource management
    • H04W72/04—Wireless resource allocation
    • H04W72/044—Wireless resource allocation based on the type of the allocated resource
    • H04W72/0453—Resources in frequency domain, e.g. a carrier in FDMA

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Quality & Reliability (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses a cell capacity optimization method, a device, equipment and a computer storage medium. The cell capacity optimization method comprises the following steps: acquiring multiple groups of key data related to cell loads of multiple cells in an area to be optimized in multiple pieces of network public opinion data; predicting a target cell in which the cell load in a plurality of cells is to be in a congestion state according to the plurality of groups of key data and the plurality of pieces of network public opinion data; and optimizing the capacity of the target cell according to the cell type of the target cell. According to the embodiment of the invention, the target cell with the cell load to be in a congestion state can be predicted according to the network public opinion data, so that the capacity of the target cell can be optimized in time.

Description

Cell capacity optimization method, device, equipment and computer storage medium
Technical Field
The present invention belongs to the field of mobile communication technology, and in particular, to a method, an apparatus, a device, and a computer storage medium for optimizing cell capacity.
Background
Currently, the existing method for optimizing the capacity of a cell periodically collects capacity indexes through an Operation and Maintenance Center (OMC), aggregates the collected capacity indexes in a cycle granularity, performs manual review on the capacity indexes of each cell according to a carrier frequency capacity expansion standard, and increases hardware equipment of the cell when the capacity indexes reach a capacity expansion threshold, so as to expand the cell in a carrier frequency increasing manner.
Generally, a carrier frequency capacity expansion standard can be determined according to the cell classification of a big packet, a middle packet and a small packet, so that whether the capacity class index of each cell in different classifications in the seven-day average self-busy period reaches a capacity expansion threshold or not is judged according to the carrier frequency capacity expansion standard, and when the capacity class index of any cell in the seven-day average self-busy period reaches the capacity expansion threshold, the carrier frequency is increased to expand the capacity. The carrier frequency capacity expansion criteria of the cells under different categories may be as shown in table 1.
TABLE 1 Carrier frequency Capacity expansion Standard Table
Figure GDA0001945369350000011
The self-busy hour of the cell can be an hour with the maximum cell utilization rate within 24 hours a day, and the cell utilization rate is the maximum value of the uplink utilization rate or the downlink utilization rate.
As shown in table 1, when any cell satisfies: when the number of the effective RRC users reaches the capacity expansion threshold, the uplink utilization rate or the downlink utilization rate reaches the capacity expansion threshold, and the uplink flow or the downlink flow reaches the capacity expansion threshold, the cell is determined to be required to be expanded.
Although the method can realize the capacity optimization of the cell with the overhigh load to a certain extent, the current data acquisition interface is single in the prior art, and the capacity index acquired by the OMC is the only capacity expansion basis, so that the reference basis dimension is single, and the judgment of the capacity problem of the cell is inaccurate. In addition, the load state of a cell is monitored and analyzed manually, and then whether the cell needs to be expanded or not is judged, so that the rationality of the capacity setting of the cell cannot be found in time, the hysteresis of the capacity problem of the cell cannot be found, the capacity requirement of the cell cannot be pre-judged, and the trend of the capacity problem of the cell cannot be analyzed in a targeted manner. Moreover, the aggregation granularity of the method is too large, so that the problem of instantaneous capacity, such as temporary behaviors sensitive to time, such as large-scale commercial activities, can be easily covered.
Disclosure of Invention
Embodiments of the present invention provide a cell capacity optimization method, apparatus, device, and computer storage medium, which can predict a target cell whose cell load will be in a congested state according to network public opinion data, so as to perform capacity optimization on the target cell in time.
In one aspect, an embodiment of the present invention provides a cell capacity optimization method, including:
acquiring multiple groups of key data related to cell loads of multiple cells in an area to be optimized in multiple pieces of network public opinion data;
predicting a target cell of which the cell load is in a congestion state in a plurality of cells according to a plurality of groups of key data and a plurality of pieces of network public opinion data;
and optimizing the capacity of the target cell according to the cell type of the target cell.
Preferably, the key data includes at least time and place related to an event related to the cyber public opinion data.
Further, acquiring multiple sets of key data related to the load of multiple cells in the area to be optimized in multiple pieces of internet public opinion data includes:
determining parts of speech corresponding to a plurality of words in each piece of network public opinion data;
and acquiring words related to the cell load as key data according to the part of speech.
Further, predicting a target cell in which cell loads will be in a congested state among the plurality of cells according to the plurality of sets of key data and the plurality of pieces of internet public opinion data includes:
Acquiring network public opinion data related to target time and corresponding key data;
determining a feature vector corresponding to the key data according to the network public opinion data, and clustering the key data according to the feature vector based on a hierarchical clustering method;
and predicting the target cell in which the cell load corresponding to the target time is in the congestion state according to the clustering result.
Preferably, determining a feature vector corresponding to the key data according to the internet public opinion data, and clustering the key data according to the feature vector based on a hierarchical clustering method, including:
and stopping clustering the key data when the ratio of the cluster quantity after the key data clustering to the initial cluster quantity of the feature vectors reaches a preset threshold value.
Further, predicting a target cell in which the cell load corresponding to the target time is to be in a congested state according to the clustering result, including:
predicting a target place where the crowd will gather at the target time according to the clustering result;
and determining a target cell with the cell load to be in a congestion state according to the target location.
Further, performing capacity optimization on the target cell according to the cell type to which the target cell belongs includes:
if the target cell is a small cell, carrying out carrier wave shunting on the target cell;
And if the target cell is a medium packet cell or a large packet cell, adding a carrier to the target cell.
In another aspect, an embodiment of the present invention provides a cell capacity optimization apparatus, where the apparatus includes:
the data extraction module is configured to acquire multiple groups of key data related to cell loads of multiple cells in an area to be optimized in multiple pieces of network public opinion data;
a data processing module configured to predict a target cell in which cell loads will be in a congested state among a plurality of cells according to a plurality of sets of key data and a plurality of pieces of network public opinion data;
and the cell optimization module is configured to perform capacity optimization on the target cell according to the cell type to which the target cell belongs.
In another aspect, an embodiment of the present invention provides a cell capacity optimization device, where the device includes: a processor and a memory storing computer program instructions;
the processor, when executing the computer program instructions, implements the cell capacity optimization method described above.
In another aspect, an embodiment of the present invention provides a computer storage medium, where computer program instructions are stored on the computer storage medium, and when the computer program instructions are executed by a processor, the method for optimizing cell capacity described above is implemented.
The cell capacity optimization method, device, equipment and computer storage medium of the embodiment of the invention can utilize key data related to cell loads of a plurality of cells in an area to be optimized in network public opinion data, predict a target cell in a congestion state of the cell load in the area to be optimized according to the key data and the network public opinion data, accordingly perform capacity optimization on the target cell in a targeted manner according to the category of unused cells to which the target cell belongs, so as to determine the target cell to be optimized in time, and improve the accuracy of predicting the target cell by utilizing multi-dimensional reference data (network public opinion data), so as to perform capacity optimization of the target cell in various forms, thereby realizing a diversified capacity optimization scheme and saving capacity optimization cost.
Compared with the traditional capacity expansion mode, the method has more foresight, can perform targeted advanced optimization according to a predicted result before the capacity of a cell reaches the bottleneck, can effectively cope with future user scale growth, and ensures user perception and network smooth operation.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart illustrating a cell capacity optimization method according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a method for obtaining internet public opinion data according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an example of internet public opinion data in the embodiment of the present invention;
FIG. 4 is a flowchart illustrating a specific method of step S110 in the embodiment of the present invention;
FIG. 5 is a flowchart illustrating a specific method of step S120 according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of clustering results obtained by a clustering method according to an embodiment of the present invention;
fig. 7 is a flowchart illustrating a specific method of step S123 in the embodiment of the present invention.
FIG. 8 is a schematic diagram of the clustering result shown in FIG. 6 with latitude and longitude information added;
fig. 9 is a schematic structural diagram of a cell capacity optimization apparatus according to an embodiment of the present invention;
fig. 10 is a schematic diagram of a hardware structure of a cell capacity optimization device according to an embodiment of the present invention.
Detailed Description
Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, 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 … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
In order to solve the problems in the prior art, embodiments of the present invention provide a method, an apparatus, a device, and a computer storage medium for optimizing cell capacity. First, a method for optimizing cell capacity according to an embodiment of the present invention is described below.
Fig. 1 is a flowchart illustrating a cell capacity optimization method according to an embodiment of the present invention. As shown in fig. 1, the cell capacity optimization method includes:
S110, obtaining multiple groups of key data related to cell loads of multiple cells in an area to be optimized in multiple pieces of network public opinion data;
s120, predicting a target cell in a congestion state of cell loads in a plurality of cells according to the plurality of groups of key data and the plurality of pieces of network public opinion data;
and S130, optimizing the capacity of the target cell according to the cell type of the target cell.
The cell capacity optimization method can utilize key data related to cell loads of a plurality of cells in an area to be optimized in network public sentiment data, predict a target cell in a congestion state of the cell loads in the area to be optimized according to the key data and the network public sentiment data, and accordingly carry out capacity optimization on the target cell in a targeted manner according to the type of an unused cell to which the target cell belongs, so that the target cell to be optimized can be determined in time, accuracy of predicting the target cell is improved by utilizing multidimensional reference data (network public sentiment data), so that various forms of capacity optimization can be carried out on the target cell, diversified capacity optimization schemes are achieved, and capacity optimization cost is saved.
In the embodiment of the present invention, before step S110, a plurality of pieces of internet public opinion data corresponding to the area to be optimized need to be obtained based on the internet data.
Since the collection of the internet public opinion data mainly aims at information mining of internet data, the discovery of potential and valuable internet public opinion data in the internet data by using a data mining technology is an information source for analyzing a target cell to be optimized in the embodiment of the invention. Generally, a Web page capable of interacting with a network database contains a large amount of internet data, and can be regarded as a huge network public opinion information database. However, the internet data in the Web page is semi-structured or unstructured, and meanwhile, with the rapid increase of the Web page, the internet data in the Web page is continuously updated, so that the Web page becomes an information source with extremely strong dynamics, and the Web public opinion data acquisition by using the Web page is relatively complex.
Fig. 2 is a flow chart illustrating a method for obtaining internet public opinion data according to an embodiment of the present invention. As shown in fig. 2, the method for acquiring internet public opinion data may include:
s210, acquiring a Web page related to an area to be optimized from Internet data through a search engine;
s220, crawling public opinion information from a Web page by using a network crawler;
and S230, carrying out data analysis on the public opinion information to obtain network public opinion data, and storing each piece of network public opinion data in a text data form respectively.
In step S210, the area to be optimized may be used as a subject term to be searched in a search engine. For example, when the area to be optimized is the state, the state may be used as a subject word, and a search may be performed in a search engine such as Baidu, 360, Saogu, etc. to obtain a Web page related to the state.
In step S220, a Web crawler may be used to obtain corresponding public opinion information from Web pages such as micro blogs, forums, posts, news media, etc. included in the Web page, so as to obtain multi-dimensional reference data for predicting a target cell to be optimized.
In step S230, since the public opinion information obtained in step S220 is generally a character string and cannot be directly applied to data analysis, the public opinion information may be subjected to data analysis to convert the public opinion information represented by the character string into text data as network public opinion data.
The microblog attendance activity is a subjective behavior of people, and due to the fact that the microblog attendance activity has time and place information, the microblog attendance activity can well reflect the occurring or impending crowd gathering condition. In the following, taking public opinion information obtained from a microblog sign-in activity page as an example, a method for obtaining network public opinion data according to an embodiment of the present invention is described:
Firstly, a data acquisition strategy is formulated based on an area to be optimized, namely, a region range related to internet data to be acquired is set and retrieved.
And then, selecting sign-in data of which the place is located in the area range in the microblog sign-in activity as public opinion information.
Finally, calling the place/near _ timeline of the Sina microblog API interface to collect data, wherein the collected public opinion information is the json microblog data, so that the character strings of the json microblog data need to be analyzed, the text content of the microblog data is extracted, and the text content is stored as a plurality of pieces of online public opinion data as shown in FIG. 3.
Preferably, the key data in the embodiment of the present invention at least includes time and place related to an event related to the internet public opinion data. Specifically, the time when the event possibly causing crowd gathering related to the internet public opinion data occurs may be determined according to the time, and the place where the event possibly causing crowd gathering occurs may be determined according to the place, for example, a place name, an address, a place category, and the like. Since the event may lead to crowd aggregation, the cell load of a cell related to the event among a plurality of cells in the area to be optimized may be affected. Thereby, the time and place related to the event to which the network public opinion data relates can be taken as the key data related to the cell load of the plurality of cells in the area to be optimized.
It should be noted that, in order to better predict whether the event related to the network public opinion data will cause the cell load of the related cell to be in a congestion state through the network public opinion data, the size of the crowd related to the event related to the network public opinion data may also be used as the key data in the implementation of the present invention.
Fig. 4 shows a flowchart of a specific method of step S110 in the embodiment of the present invention. As shown in fig. 4, the specific method for acquiring multiple sets of key data related to the load of multiple cells in the area to be optimized in step S110 includes:
s111, determining parts of speech corresponding to a plurality of words in each piece of network public opinion data;
and S112, acquiring words related to cell load as key data according to the parts of speech.
Compared with the structured data in the traditional database, the network public opinion data obtained from the Web page is semi-structured or unstructured data, and the key data for data analysis is difficult to be directly obtained from the network public opinion data, so a series of preprocessing is required to be performed so as to capture the key data in a text form from the network public opinion data, and the network public opinion data and the key data thereof are conveniently used for analyzing the target cell in the follow-up process.
In step S111, it is first necessary to perform word segmentation processing on the internet public opinion data. In the embodiment of the present invention, the internet public opinion data is stored in a text data form, so that an Institute of Computing Technology (Chinese Lexical Analysis System, ICTCLASs) may be adopted to perform text segmentation on each piece of internet public opinion data to obtain a plurality of words, perform part-of-speech tagging on the words, identify new words that do not exist in the user dictionary, and store the identified new words in the user dictionary.
The step S112 will be described in detail by taking an example in which the key data includes a time and a place related to an event related to the internet public opinion data.
After text segmentation and part-of-speech tagging are performed on the network public opinion data, the time data of year, month, day, time, grade and the like of the time of the related event, which are judged, can be classified into time classification and reserved as key data. The method comprises the steps of filtering words with too high or too low occurrence frequency in network public opinion data such as tone words by using a 'stop word bank', screening nouns and verbs with strong event description as data characteristics of the network public opinion data, classifying according to time, and storing the data characteristics of all the network public opinion data so as to reduce the dimensionality of the data characteristics of the network public opinion data.
And then, obtaining the relevant places of the events related to the network public opinion data from the data features of the network public opinion data by using a feature extraction method. Feature extraction is a method for extracting effective and key information from segmented text data, and aims to separate useful information from noise data and reduce the dimensionality of the data. Because the geographic information included in the microblog data often has a certain heterogeneity, that is, there may sometimes exist a plurality of different naming modes for the same geographic location, for example, standard names, common names, and alternative names of geographic entities of a place. Therefore, when a place related to an event is acquired as key data by means of feature extraction, purposeful screening is required, for example, a keyword may be screened by exhaustive enumeration of standard names, common names, alternative names, and the like of geographic entities of the place, so as to screen out the keyword related to the place as key data. Taking the screening of the key data about the place for the internet public opinion data shown in fig. 3 as an example, the content of the event related to the internet public opinion data shown in fig. 3 is "the food festival will be developed on the Mingmu road in Fuzhou in 2018, 2, 11 days", so that the keywords about the place are analyzed as [ 'Fuzhou', 'food festival', 'street open', 'food street', 'Ming', 'Mingmu', ] according to the content of the event, and the results of the screening of the key data about the place can be more accurate by using the keywords about the place as the key data about the place.
It should be noted that, in the embodiment of the present invention, since the target cell to be optimized, whose cell load may be in a congestion state, is to be predicted, when obtaining the key data of the network public opinion data, the network public opinion data corresponding to the event that is about to occur after the time of data collection and analysis is only analyzed, so as to reduce the data processing amount, save the data processing cost, and improve the data processing efficiency.
In the embodiment of the invention, the data characteristics of a plurality of groups of network public opinion data acquired aiming at each network public opinion data and the corresponding key data can be classified according to time and then stored, so that the data characteristics of the network public opinion data to be analyzed and the corresponding key data can be conveniently extracted in the following process.
Fig. 5 shows a flowchart of a specific method of step S120 in the embodiment of the present invention. As shown in fig. 5, the specific method for predicting the target cell whose cell load will be in a congested state in the plurality of cells according to the plurality of sets of key data and the plurality of pieces of internet public opinion data in step S120 includes:
s121, acquiring network public opinion data related to target time and corresponding key data;
S122, determining a feature vector corresponding to the key data according to the network public sentiment data, and clustering the key data according to the feature vector based on a hierarchical clustering method;
and S123, predicting the target cell of which the cell load corresponding to the target time is in a congestion state according to the clustering result.
The step S120 of performing predictive analysis of the target cell to be optimized by using the internet public opinion data and the corresponding key data based on the internet public opinion data mainly aims to analyze and mine the data characteristics of the internet public opinion data obtained by processing the internet public opinion data by using the step S110 and the keywords about the location in the corresponding key data, thereby finding a hot event in the event related to the internet public opinion data and tracking the hot event to finally determine the target cell. Next, a specific method for performing predictive analysis of a target cell to be optimized based on internet public opinion data by using the data characteristics of the internet public opinion data and the keywords about the location in the corresponding key data will be described in detail.
After the internet public opinion data related to the target time and the corresponding key data are obtained in step S121, the process of predictive analysis of the target cell to be optimized is entered. The target time may be set as needed, for example, a certain date, or a certain time in a certain date.
First, a Vector Space Model (VSM) is used to determine a feature Vector corresponding to a keyword about a location in a data feature of internet public opinion data. VSM is a model proposed by Salton et al to represent the importance of a word in text data in the end of the 20 th century 60 years, and is a mainstream model in current natural language processing, and a vector space model is used to represent text data, and feature selection and weight calculation are performed on words in the text data to form an N-dimensional space vector.
The Term Frequency and inverse Document Frequency (TF-IDF) statistical method is a classic weight calculation method based on a VSM model and firstly proposed by Jones, and is applied to the field of information retrieval for evaluating the importance degree of a word on a Document or a category in a file set or a corpus. The main idea of the TF-IDF statistical method is as follows: if a word or word appears more frequently in one category and rarely in other categories, the word or word is considered to have a good category distinction capability and is suitable for classification. In the embodiment of the invention, a TF-IDF statistical method may be adopted to calculate importance of the keyword about the place to the multiple pieces of internet public opinion data, so as to determine importance degree of the keyword about the place in the key data to the multiple pieces of internet public opinion data, thereby determining whether to use the keyword about the place for subsequent analysis processing.
Specifically, the calculation method of the TF-IDF statistical method is as follows:
first, a word frequency TF (i, j) is determined, and the word frequency TF (i, j) represents the number of times of occurrence of the keyword i in the internet public opinion data j.
Then, determining the inverse text frequency IDF, wherein the calculation formula of the inverse text frequency IDF is as follows:
IDF＝log(N/Ni+0.01)
wherein N represents the total number of the network public opinion data, and Ni represents the number of the network public opinion data with the keyword i.
Finally, the product of the word frequency TF (i, j) and the inverse text frequency IDF is used as a feature vector W [ j ] [ i ] of the keyword i, the feature vector W [ j ] [ i ] is a two-dimensional matrix, and the calculation formula of the feature vector W [ j ] [ i ] is as follows:
W[j][i]＝TF(i,j)*IDF(i)
the weight of each keyword i in each microblog data can be simply, intuitively and quickly obtained by counting the feature vectors W [ j ] [ i ] of the keywords i. And forming a matrix by using the feature vectors of the keywords of all the network public opinion data to obtain a vector space model.
After a vector space model is obtained and the weight of each keyword is determined, key data can be clustered according to the feature vectors based on a hierarchical clustering method. Specifically, the keywords in the relevant places in the key data can be arranged in a descending order according to the feature vectors, a weight threshold is set, and the keywords in the relevant places for clustering in the key data are screened out according to the weight threshold.
In the embodiment of the invention, the hot spot event is determined by screening out the keywords about the place for clustering in the key data, a hot spot discovery algorithm is adopted, and the hot spot discovery algorithm essentially belongs to a text clustering algorithm in data mining. Compared with the traditional vector space model based on TF-IDF for direct clustering, the embodiment of the invention avoids the problem that the accuracy of data clustering is influenced because the concept similarity condition existing among words is not considered, and particularly avoids the problem that the obtained similarity is greatly deviated from the actual condition when Chinese texts are clustered.
In the embodiment of the invention, a bottom-up hierarchical clustering method can be adopted to cluster the keywords about the places for clustering in the screened key data, and the method is an unsupervised learning method, the core idea of the method is the combination of clusters, in the clustering process, all the keywords form a cluster at the beginning, and then two clusters with the shortest distance are repeatedly combined until the number of the clusters reaches the specified number.
Further, in the embodiment of the present invention, a key point of clustering by using a hierarchical clustering method is to determine a distance (similarity measure) between two clusters, and the following three common methods for calculating the similarity measure are provided:
1. single strand method: and taking the distance between two nearest points of two different clusters as the similarity of the two clusters.
2. The full-chain method comprises the following steps: and taking the distance between two farthest points of two different clusters as the similarity of the two clusters.
3. Group average method: and taking all point combinations from two different clusters, calculating the distance between the points, and taking the average value of the distances as the similarity of the two clusters.
Specifically, in the embodiment of the present invention, a specific method for clustering keywords related to a place by using a hierarchical clustering method includes the following steps:
a) the keywords about the location in each piece of network public opinion data are used as a cluster, a network public opinion data set D in n cluster target topics is constructed as { D1, …, di, …, dn }, and a cluster Ci of a single piece of network public opinion data is constructed as { di }, and the clusters form a cluster C of the network public opinion data set D as { C1, …, Ci, …, Cn }.
b) Calculating the similarity sim (Ci, Cj) between every two clusters (Ci, Cj) in the cluster C, and recording as a similarity matrix S;
c) Selecting two clusters max (sim (Ci, Cj)) with the largest similarity, combining Ci and Cj into a new cluster C ═ Ci ═ u Cj, so as to form a new cluster C ═ C1, …, Cn-1} of D, and updating a similarity matrix S at the same time;
d) if the number of the clusters is equal to 1 or reaches the specified number, ending the process, otherwise, repeating the steps b and c.
Since all keywords regarding a place are clustered into one class when the number of classes is equal to 1, clustering is excessive, and thus a hotspot event cannot be obtained. Therefore, in the embodiment of the present invention, in step S122, determining a feature vector corresponding to the key data according to the internet public opinion data, and clustering the key data according to the feature vector based on a hierarchical clustering method, includes: and stopping clustering the key data when the ratio of the cluster quantity after the key data clustering to the initial cluster quantity of the feature vectors reaches a preset threshold value.
Specifically, when the ratio of the number of clustered clusters to the initial number of clusters of the feature vector reaches a predetermined threshold, it may be determined that the number of clusters reaches a specified number, and thus, clustering of the keyword may be ended.
In an example of the present invention, keywords related to a place in a plurality of pieces of internet public opinion data within a target time may be extracted, and then, a hierarchical clustering algorithm is used for clustering, in order to prevent an excessive merging phenomenon of clusters, when the clustering algorithm is executed, it is specified that a ratio of the number of clustered clusters to the number of clusters with an initial feature vector reaches 10%, as an exit condition, so as to ensure that a clustering method obtains a proper clustering result. In this case, the obtained clustering result is shown in fig. 6, and the target cell related to the keyword can be predicted from the frequency of occurrence of the keyword with respect to the location in the clustering result.
Fig. 7 shows a flowchart of a specific method of step S123 in the embodiment of the present invention. As shown in fig. 7, the step S123 of predicting the target cell whose cell load corresponding to the target time is to be in the congestion state according to the clustering result includes:
s310, predicting a target place where crowd gathering will occur at target time according to a clustering result;
and S320, determining a target cell with the cell load in a congestion state according to the target location.
Step S310 is explained by taking the clustering result shown in fig. 6 as an example. The places with more occurrence frequency can be used as target places where people are likely to gather at the target time. Specifically, a preset number of places in front of the frequency may be selected as the target places, or a place with a frequency greater than a predetermined frequency may be selected as the target place.
After the target location is determined, the geographic location of the target location, that is, the latitude and longitude information of the target location, may be obtained. However, the data about a place disclosed in the internet public opinion data generally relates only to the place name and address information of the place, and does not give specific latitude and longitude information. For the places without the longitude and latitude information reported, a request for analyzing the coordinates of the target place can be generated through a Baidu coordinate picking system according to a grammar rule, so that the formatted longitude and latitude information of the target place can be found from the Internet data. Finally, the latitude and longitude information may be saved into the clustering result, as shown in fig. 8.
After the latitude and longitude information of the target location is determined, cells within a predetermined range around the target location can be set as target cells according to the geographical position of the target location, and the number of the target cells can be one or more. For example, a cell within an area within a radius of 500 meters of the target location may be set as the target cell.
In this embodiment of the present invention, the step S130 of performing capacity optimization on the target cell according to the cell type to which the target cell belongs includes:
if the target cell is a small cell, carrying out carrier wave shunting on the target cell;
and if the target cell is a medium packet cell or a large packet cell, adding a carrier to the target cell.
The target cell is classified into cell categories such as small cell, medium cell or large cell according to the occurrence frequency of the target site in the clustering result. Then, different capacity optimization schemes are adopted for the cell types to which the cells belong.
When the target cell is a small cell, the carrier of the target cell is shunted to the carriers of the same frequency band of the peripheral idle cell or shunted to the carriers of other idle frequency bands of the target cell only by modifying the cell parameters of the cell, so as to realize the carrier balance of the target cell and the peripheral cell, thereby realizing the capacity optimization of the target cell and saving the capacity optimization cost on the premise of not increasing hardware equipment. When the target cell is a medium-packet cell or a large-packet cell, the number of carriers of the target cell can be increased by increasing hardware equipment, so as to optimize the cell capacity.
Therefore, the cell capacity optimization method provided by the embodiment of the invention can predict the target location of the internet users which is possibly gathered based on the big data so as to indirectly predict the target cell to be optimized, improve the accuracy of the cell capacity expansion scheme and change the defect of single reference dimension.
Fig. 9 is a schematic structural diagram illustrating a cell capacity optimizing apparatus according to an embodiment of the present invention. As shown in fig. 9, the cell capacity optimizing apparatus includes:
a data extraction module 401 configured to obtain multiple sets of key data related to cell loads of multiple cells in an area to be optimized from multiple pieces of internet public opinion data;
a data processing module 402 configured to predict a target cell in which cell load will be in a congested state among a plurality of cells according to a plurality of sets of key data and a plurality of pieces of network public opinion data;
a cell optimization module 403 configured to perform capacity optimization on the target cell according to the cell category to which the target cell belongs.
Wherein the key data at least comprises time and place related to the event related to the network public opinion data.
In the embodiment of the present invention, the cell capacity optimizing apparatus further includes a data collecting module 404 configured to obtain a plurality of pieces of internet public opinion data corresponding to the area to be optimized based on the internet data.
In an embodiment of the present invention, the data extraction module 401 is further configured to: determining parts of speech corresponding to a plurality of words in each piece of network public opinion data; and acquiring words related to the cell load as key data according to the part of speech.
In an embodiment of the present invention, the data processing module 402 is further configured to: acquiring network public opinion data related to target time and corresponding key data; determining a feature vector corresponding to the key data according to the network public opinion data, and clustering the key data according to the feature vector based on a hierarchical clustering method; and predicting the target cell of which the cell load corresponding to the target time is in a congestion state according to the clustering result.
Further, determining a feature vector corresponding to the key data according to the internet public opinion data, and clustering the key data according to the feature vector based on a hierarchical clustering method, comprising: and stopping clustering the key data when the ratio of the cluster quantity after the key data clustering to the initial cluster quantity of the feature vectors reaches a preset threshold value.
Further, predicting a target cell in which the cell load corresponding to the target time is to be in a congested state according to the clustering result, including: predicting a target place where the crowd will gather at the target time according to the clustering result; and determining a target cell with the cell load to be in a congestion state according to the target location.
In this embodiment of the present invention, the cell optimization module 403 is further configured to: if the target cell is a small cell, carrying out carrier wave shunting on the target cell; and if the target cell is a medium packet cell or a large packet cell, adding carriers to the target cell.
The cell capacity optimization device provided by the embodiment of the invention can realize automatic optimization of cell capacity based on network public opinion data, specifically, can predict the time and place of possible aggregation of network users through the acquisition and processing of the network public opinion data, and can also predict the scale of crowd aggregation so as to determine a target place, then find out a target cell to be optimized through the longitude and latitude information of the target place, and optimize the cell capacity of the target cell.
In summary, the cell capacity optimization method and device in the embodiments of the present invention can determine the target location where crowd accumulation is likely to occur in advance based on time and geographic location, and determine the target cell to be optimized, thereby providing more decision bases for capacity optimization of the cell. Compared with the traditional capacity expansion mode, the method has more prospective, performs targeted advanced optimization according to a predicted result before the cell capacity reaches a bottleneck, can effectively cope with future user scale growth, and ensures user perception and stable network operation.
Fig. 10 is a schematic diagram illustrating a hardware structure of a cell capacity optimizing device according to an embodiment of the present invention.
The cell capacity optimizing device may include a processor 501 and a memory 502 storing computer program instructions.
Specifically, the processor 501 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured as one or more Integrated circuits implementing embodiments of the present invention.
Memory 502 may include a mass storage for data or instructions. By way of example, and not limitation, memory 502 may include a Hard Disk Drive (HDD), a floppy Disk Drive, flash memory, an optical Disk, a magneto-optical Disk, magnetic tape, or a Universal Serial Bus (USB) Drive or a combination of two or more of these. Memory 502 may include removable or non-removable (or fixed) media, where appropriate. The memory 502 may be internal or external to the integrated gateway disaster recovery device, where appropriate. In a particular embodiment, the memory 502 is non-volatile solid-state memory. In a particular embodiment, the memory 502 includes Read Only Memory (ROM). Where appropriate, the ROM may be mask-programmed ROM, Programmable ROM (PROM), Erasable PROM (EPROM), Electrically Erasable PROM (EEPROM), electrically rewritable ROM (EAROM), or flash memory or a combination of two or more of these.
The processor 501 reads and executes the computer program instructions stored in the memory 502 to implement any one of the cell capacity optimization methods in the above embodiments.
In one example, the cell capacity optimization device may also include a communication interface 503 and a bus 510, respectively. As shown in fig. 10, the processor 501, the memory 502, and the communication interface 503 are connected via a bus 510 to complete communication therebetween.
The communication interface 503 is mainly used for implementing communication between modules, apparatuses, units and/or devices in the embodiments of the present invention.
The bus 510 comprises hardware, software, or both to couple the components of the cell capacity optimization device to each other. By way of example, and not limitation, a bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hypertransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus or a combination of two or more of these. Bus 510 may include one or more buses, where appropriate. Although specific buses have been described and shown in the embodiments of the invention, any suitable buses or interconnects are contemplated by the invention.
The cell capacity optimization device can execute the cell capacity optimization method in the embodiment of the invention, thereby realizing the cell capacity optimization method and the device combined with the application.
In addition, in combination with the cell capacity optimization method in the foregoing embodiments, embodiments of the present invention may provide a computer storage medium to implement. The computer storage medium having computer program instructions stored thereon; the computer program instructions, when executed by a processor, implement any of the cell capacity optimization methods in the above embodiments.
It is to be understood that the invention is not limited to the specific arrangements and instrumentality described above and shown in the drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications and additions or change the order between the steps after comprehending the spirit of the present invention.
The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments noted in this patent describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
As described above, only the specific embodiments of the present invention are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present invention, and these modifications or substitutions should be covered within the scope of the present invention.

Claims (7)

1. A method for optimizing cell capacity, comprising:
acquiring multiple groups of key data related to cell loads of multiple cells in an area to be optimized in multiple pieces of network public opinion data, wherein the key data at least comprise time and places related to events related to the network public opinion data;
Predicting a target cell of the plurality of cells, of which the cell load is to be in a congestion state, according to the plurality of groups of key data and the plurality of pieces of network public opinion data;
performing capacity optimization on the target cell according to the cell type of the target cell;
the method for acquiring multiple groups of key data related to the load of multiple cells in an area to be optimized in multiple pieces of network public opinion data comprises the following steps:
determining parts of speech corresponding to a plurality of words in each piece of network public opinion data;
acquiring the words related to the cell load according to the part of speech as the key data;
the predicting, according to the plurality of sets of key data and the plurality of pieces of network public opinion data, a target cell in the plurality of cells, for which the cell load is to be in a congested state, includes:
acquiring the network public opinion data related to the target time and corresponding key data;
determining a feature vector corresponding to the key data according to the network public opinion data, and clustering the key data according to the feature vector based on a hierarchical clustering method;
and predicting the target cell in which the cell load corresponding to the target time is in a congestion state according to the clustering result.
2. The method of optimizing cell capacity according to claim 1, wherein determining a feature vector corresponding to the key data according to the internet public opinion data, and clustering the key data according to the feature vector based on a hierarchical clustering method, comprises:
and when the ratio of the cluster number after the key data clustering to the initial cluster number of the feature vectors reaches a preset threshold value, stopping clustering the key data.
3. The method of claim 1, wherein predicting the target cell whose cell load corresponding to the target time is to be in a congested state according to a clustering result comprises:
predicting a target place where the target time is to be aggregated by people according to the clustering result;
and determining the target cell with the cell load to be in a congestion state according to the target location.
4. The cell capacity optimization method according to claim 1, wherein performing capacity optimization on the target cell according to the cell category to which the target cell belongs comprises:
if the target cell is a small cell, carrying out carrier wave shunting on the target cell;
And if the target cell is a medium packet cell or a large packet cell, adding a carrier to the target cell.
5. An apparatus for optimizing cell capacity, the apparatus comprising:
the data extraction module is configured to acquire multiple groups of key data related to cell loads of multiple cells in an area to be optimized in multiple pieces of network public opinion data;
a data processing module configured to predict a target cell of the plurality of cells, in which the cell load will be in a congested state, according to the plurality of sets of key data and the plurality of pieces of network public opinion data;
a cell optimization module configured to perform capacity optimization on the target cell according to a cell category to which the target cell belongs;
the data extraction module further configured to:
determining parts of speech corresponding to a plurality of words in each piece of network public opinion data;
acquiring the words related to the cell load according to the part of speech as the key data;
the data processing module further configured to:
acquiring the network public opinion data related to the target time and corresponding key data;
determining a feature vector corresponding to the key data according to the network public opinion data, and clustering the key data according to the feature vector based on a hierarchical clustering method;
And predicting the target cell of which the cell load corresponding to the target time is in a congestion state according to the clustering result.
6. A cell capacity optimizing device, characterized in that the device comprises: a processor and a memory storing computer program instructions;
the processor, when executing the computer program instructions, implements the cell capacity optimization method of any of claims 1-4.
7. A computer storage medium having computer program instructions stored thereon which, when executed by a processor, implement the cell capacity optimization method of any one of claims 1-4.
CN201811424903.7A 2018-11-27 2018-11-27 Cell capacity optimization method, device, equipment and computer storage medium Active CN109526027B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811424903.7A CN109526027B (en) 2018-11-27 2018-11-27 Cell capacity optimization method, device, equipment and computer storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811424903.7A CN109526027B (en) 2018-11-27 2018-11-27 Cell capacity optimization method, device, equipment and computer storage medium

Publications (2)

Publication Number Publication Date
CN109526027A CN109526027A (en) 2019-03-26
CN109526027B true CN109526027B (en) 2022-07-01

Family

ID=65794445

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811424903.7A Active CN109526027B (en) 2018-11-27 2018-11-27 Cell capacity optimization method, device, equipment and computer storage medium

Country Status (1)

Country Link
CN (1) CN109526027B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110944339B (en) * 2019-10-12 2022-09-30 中国通信建设集团设计院有限公司 Load distribution method, device and equipment for cell in base station
CN112911611B (en) * 2019-11-19 2022-07-01 中国移动通信集团山东有限公司 Cell optimization method, device, storage medium and source base station
CN114173318B (en) * 2021-12-09 2023-05-12 中国联合网络通信集团有限公司 Method, device and equipment for identifying region to be optimized

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101763431A (en) * 2010-01-06 2010-06-30 电子科技大学 PL clustering method based on massive network public sentiment information
CN103246644A (en) * 2013-04-02 2013-08-14 亿赞普(北京)科技有限公司 Method and device for processing Internet public opinion information
CN103324665A (en) * 2013-05-14 2013-09-25 亿赞普(北京)科技有限公司 Hot spot information extraction method and device based on micro-blog
CN103544255A (en) * 2013-10-15 2014-01-29 常州大学 Text semantic relativity based network public opinion information analysis method
CN104080091A (en) * 2014-07-22 2014-10-01 重庆邮电大学 Family base station frequency spectrum allocation method based on load prediction grouping in layered heterogenous network
CN104113857A (en) * 2013-04-18 2014-10-22 中国移动通信集团甘肃有限公司 Wireless capacity optimization method and device
CN104794161A (en) * 2015-03-24 2015-07-22 浪潮集团有限公司 Method for monitoring network public opinions
CN105068991A (en) * 2015-07-30 2015-11-18 成都鼎智汇科技有限公司 Big data based public sentiment discovery method
CN105208603A (en) * 2015-10-15 2015-12-30 南京理工大学 LTE network multi-target load balancing method
CN105472660A (en) * 2014-09-11 2016-04-06 中国移动通信集团公司 Load balancing method and system and network equipment
CN108321810A (en) * 2018-02-12 2018-07-24 华南理工大学 Inhibit the distribution Multiple Time Scales powerless control method of grid-connected voltage fluctuation
CN108845881A (en) * 2018-05-30 2018-11-20 有米科技股份有限公司 The method and device of server capacity dynamic adjustment

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9703892B2 (en) * 2005-09-14 2017-07-11 Millennial Media Llc Predictive text completion for a mobile communication facility
US10621653B2 (en) * 2014-03-31 2020-04-14 Monticello Enterprises LLC System and method for providing payments for users in connection with a device software module having a payment application programming interface
CN107330557A (en) * 2017-06-28 2017-11-07 中国石油大学(华东) It is a kind of to be divided based on community and the public sentiment hot tracking of entropy and Forecasting Methodology and device

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101763431A (en) * 2010-01-06 2010-06-30 电子科技大学 PL clustering method based on massive network public sentiment information
CN103246644A (en) * 2013-04-02 2013-08-14 亿赞普(北京)科技有限公司 Method and device for processing Internet public opinion information
CN104113857A (en) * 2013-04-18 2014-10-22 中国移动通信集团甘肃有限公司 Wireless capacity optimization method and device
CN103324665A (en) * 2013-05-14 2013-09-25 亿赞普(北京)科技有限公司 Hot spot information extraction method and device based on micro-blog
CN103544255A (en) * 2013-10-15 2014-01-29 常州大学 Text semantic relativity based network public opinion information analysis method
CN104080091A (en) * 2014-07-22 2014-10-01 重庆邮电大学 Family base station frequency spectrum allocation method based on load prediction grouping in layered heterogenous network
CN105472660A (en) * 2014-09-11 2016-04-06 中国移动通信集团公司 Load balancing method and system and network equipment
CN104794161A (en) * 2015-03-24 2015-07-22 浪潮集团有限公司 Method for monitoring network public opinions
CN105068991A (en) * 2015-07-30 2015-11-18 成都鼎智汇科技有限公司 Big data based public sentiment discovery method
CN105208603A (en) * 2015-10-15 2015-12-30 南京理工大学 LTE network multi-target load balancing method
CN108321810A (en) * 2018-02-12 2018-07-24 华南理工大学 Inhibit the distribution Multiple Time Scales powerless control method of grid-connected voltage fluctuation
CN108845881A (en) * 2018-05-30 2018-11-20 有米科技股份有限公司 The method and device of server capacity dynamic adjustment

Also Published As

Publication number Publication date
CN109526027A (en) 2019-03-26

Similar Documents

Publication Publication Date Title
CN110245981B (en) Crowd type identification method based on mobile phone signaling data
CN107577688B (en) Original article influence analysis system based on media information acquisition
CN103218435B (en) Method and system for clustering Chinese text data
CN102760138B (en) Classification method and device for user network behaviors and search method and device for user network behaviors
CN103176983B (en) A kind of event method for early warning based on internet information
CN107862022B (en) Culture resource recommendation system
CN101819573B (en) Self-adaptive network public opinion identification method
JP5092165B2 (en) Data construction method and system
Huang et al. Topic detection from large scale of microblog stream with high utility pattern clustering
CN109526027B (en) Cell capacity optimization method, device, equipment and computer storage medium
CN101477554A (en) User interest based personalized meta search engine and search result processing method
US10467255B2 (en) Methods and systems for analyzing reading logs and documents thereof
CN101404033A (en) Automatic generation method and system for noumenon hierarchical structure
Jin et al. Patent maintenance recommendation with patent information network model
CN103810162A (en) Method and system for recommending network information
CN111599219B (en) Multi-data-source flight takeoff time prediction method based on sequencing learning
US20200394318A1 (en) Privacy trustworthiness based api access
CN104809252A (en) Internet data extraction system
CN103761286B (en) A kind of Service Source search method based on user interest
CN103324641A (en) Information record recommendation method and device
CN103823847A (en) Keyword extension method and device
CN107133321B (en) Method and device for analyzing search characteristics of page
CN103870489A (en) Chinese name self-extension recognition method based on search logs
CN113282641A (en) Webpage search data information intelligent classification management method and system based on user behavior deep analysis and computer storage medium
KR20130089699A (en) Method, search server and computer readable recording medium for determining ranking of stock-collection with stock exchange information

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
GR01 Patent grant
GR01 Patent grant