CN110008251B - Data processing method and device based on time sequence data and computer equipment - Google Patents
Data processing method and device based on time sequence data and computer equipment Download PDFInfo
- Publication number
- CN110008251B CN110008251B CN201910171923.6A CN201910171923A CN110008251B CN 110008251 B CN110008251 B CN 110008251B CN 201910171923 A CN201910171923 A CN 201910171923A CN 110008251 B CN110008251 B CN 110008251B
- Authority
- CN
- China
- Prior art keywords
- data
- time sequence
- feature
- characteristic
- visual
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2474—Sequence data queries, e.g. querying versioned data
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to a data processing method, device and computer equipment based on time sequence data for data analysis. The method comprises the following steps: receiving a resource acquisition request sent by a terminal, wherein the resource acquisition request comprises a request type and request information; acquiring a plurality of visual data according to the resource acquisition request and the request information, wherein the visual data comprises a category identifier; acquiring a plurality of time sequence data from the visual data according to the category identification; performing time sequence feature processing and feature extraction on the plurality of time sequence data, and extracting feature variables reaching a threshold value and corresponding dimension feature values; acquiring a preset time sequence data mining model according to the request type, and analyzing the characteristic variable and the corresponding dimension characteristic value through the time sequence data mining model to obtain corresponding analysis result data; and generating corresponding view resource data according to the analysis result data in a preset mode, and pushing the view resource data to the terminal. By adopting the method, the mining efficiency and accuracy of the time sequence data can be effectively improved.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for processing data based on time-series data and a computer device.
Background
With the rapid development of computer technology, data mining technology has also become increasingly important. The time sequence is an important high-dimensional data type, is a sequence formed by arranging sampling values of a certain physical quantity of an objective object at different time points according to time sequence, and has wide application in the fields of economic management and engineering. By utilizing time sequence data mining, useful information which is contained in the data and is relevant to time can be obtained, and knowledge extraction is realized.
However, in many cases, the time series data is processed in a single dimension, and the time series data itself has high dimension, complexity, dynamics, high noise and a large scale characteristic. In the visual layer, the image can be realized very widely along with the time, but the time-based visualization is usually framed in a line graph or a scatter graph taking time as a coordinate, so that the information capture limitation is large, and the efficiency and the accuracy of mining the time-based data are low.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a data processing method, apparatus, and computer device based on time series data, which can effectively improve the mining efficiency and accuracy of time series data.
A method of data processing based on time series data, the method comprising:
receiving a resource acquisition request sent by a terminal, wherein the resource acquisition request comprises a request type and request information;
acquiring a plurality of visual data according to the resource acquisition request and the request information, wherein the visual data comprises a category identifier;
acquiring a plurality of time sequence data from the visual data according to the category identification;
performing time sequence feature processing on the plurality of time sequence data to obtain feature variables and dimension feature values corresponding to the plurality of time sequence data;
extracting the characteristic variable and the corresponding dimension characteristic value, wherein the characteristic variable reaches a threshold value;
acquiring a preset time sequence data mining model according to the request type, and analyzing the characteristic variable and the corresponding dimension characteristic value through the time sequence data mining model to obtain corresponding analysis result data;
and generating corresponding view resource data according to the analysis result data in a preset mode, and pushing the view resource data to the terminal.
In one embodiment, the visualized data includes a category identifier and a data identifier, and the step of acquiring a plurality of time series data from the visualized time series data according to the category identifier includes: acquiring base table data and an objective function corresponding to the visual data according to the category identification and the data identification; acquiring time sequence distribution data in the visual data according to the base table data and the objective function; and converting the time sequence distribution data into time sequence data according to a preset mode.
In one embodiment, the step of acquiring time sequence distribution data in the visualized data according to the base table data and the objective function includes: acquiring coordinate matrix data and corresponding parameter weights according to the base table data and the objective function; and acquiring corresponding time sequence distribution data according to the coordinate matrix data and the corresponding parameter weight.
In one embodiment, the step of extracting features of feature variables corresponding to the plurality of multi-dimensional time series data according to a preset algorithm includes: performing cluster analysis on the characteristic variables corresponding to the multi-dimensional time sequence data to obtain a plurality of cluster results; calculating correlation among a plurality of characteristic variables according to the plurality of clustering results; and performing feature selection according to the correlation among the feature variables, and extracting feature variables reaching a preset threshold and corresponding dimension features.
In one embodiment, the step of analyzing the feature variable and the corresponding dimension feature value through the time-series data mining model includes: calculating the weight of the characteristic variable through the time sequence data mining model; calculating corresponding predicted values of a plurality of characteristic variables corresponding to a plurality of preset time sequence parameters according to the dimension characteristic values and weights of the characteristic variables through the time sequence data mining model; and generating analysis result data corresponding to the request type according to the plurality of preset time sequence parameters and the corresponding predicted values.
In one embodiment, the analysis result data includes a plurality of preset time sequence parameters and corresponding predicted values, and the method further includes: acquiring a preset integration function according to the request type; integrating corresponding view resource data through the integration function according to a plurality of preset time sequence parameters and corresponding predicted values in the analysis result data; and adding event type identification and corresponding interface calling parameters to the view resource data.
A data processing apparatus based on time series data, the apparatus comprising:
the resource acquisition module is used for receiving a resource acquisition request sent by the terminal, wherein the resource acquisition request comprises a request type and request information;
The data acquisition module is used for acquiring a plurality of visual data according to the resource acquisition request and the request information, wherein the visual data comprises a category identifier; acquiring a plurality of time sequence data from the visual data according to the category identification;
the characteristic processing module is used for carrying out time sequence characteristic processing on the plurality of time sequence data to obtain characteristic variables and dimension characteristic values corresponding to the plurality of time sequence data; extracting the characteristic variable and the corresponding dimension characteristic value, wherein the characteristic variable reaches a threshold value;
the data mining module is used for acquiring a preset time sequence data mining model according to the request type, analyzing the characteristic variable and the corresponding dimension characteristic value through the time sequence data mining model, and obtaining corresponding analysis result data;
and the view generation module is used for generating corresponding view resource data according to the analysis result data in a preset mode and pushing the view resource data to the terminal.
In one embodiment, the visual data includes a category identifier and a data identifier, and the data acquisition module is further configured to acquire base table data and an objective function corresponding to the visual data according to the category identifier and the data identifier; acquiring time sequence distribution data in the visual data according to the base table data and the objective function; and converting the time sequence distribution data into time sequence data according to a preset mode.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the time-series data based data processing method provided in any one of the embodiments of the present application when the computer program is executed.
A computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a time-series data based data processing method provided in any one of the embodiments of the present application.
According to the data processing method, the device and the computer equipment based on the time sequence data, after the server receives the resource acquisition request sent by the terminal, the resource acquisition request comprises the request type and the request information, and the server acquires a plurality of visual data according to the resource acquisition request and the request information, wherein the visual data comprises the category identification. The server further obtains a plurality of time sequence data from the visual data according to the category identification, so that the time sequence data in the visual data can be effectively obtained. The server further performs time sequence feature processing on the plurality of time sequence data to obtain feature variables and dimension feature values corresponding to the plurality of time sequence data; and extracting the characteristic variable reaching the threshold value and the corresponding dimension characteristic value. Acquiring a preset time sequence data mining model according to the request type, analyzing the characteristic variable and the corresponding dimension characteristic value through the time sequence data mining model to obtain corresponding analysis result data, further generating corresponding view resource data according to the analysis result data in a preset mode, and pushing the view resource data to the terminal. The time sequence data in the visual data is extracted, the time sequence data is subjected to characteristic extraction, and then the time sequence data is analyzed through a time sequence data mining model, so that valuable information in the time sequence data can be effectively mined for further analysis, and the mining efficiency and accuracy of the time sequence data can be effectively improved.
Drawings
FIG. 1 is an application scenario diagram of a data processing method based on time series data in one embodiment;
FIG. 2 is a flow chart of a method of processing data based on time series data in one embodiment;
FIG. 3 is a flowchart illustrating a step of acquiring time series data according to one embodiment;
FIG. 4 is a flow chart of an analysis step of time series data through a time series data mining model in one embodiment;
FIG. 5 is a block diagram of a data processing apparatus based on time series data in one embodiment;
fig. 6 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The data processing method based on time sequence data can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smartphones, tablet computers, and portable wearable devices, and the server 104 may be implemented by a stand-alone server or a server cluster composed of a plurality of servers. The user may send a resource acquisition request to the server 104 through the corresponding terminal 102, the resource acquisition request including a request type and request information. After receiving the resource acquisition request sent by the terminal 102, the server 104 acquires a plurality of visual data according to the resource acquisition request and the request information, where the visual data includes a category identifier. The server 104 further obtains a plurality of time series data from the visualized data according to the category identification, thereby effectively obtaining the time series data in the visualized data. The server 104 further performs time sequence feature processing on the plurality of time sequence data to obtain feature variables and dimension feature values corresponding to the plurality of time sequence data; and extracting the characteristic variable reaching the threshold value and the corresponding dimension characteristic value. The method comprises the steps of obtaining a preset time sequence data mining model according to a request type, analyzing feature variables and corresponding dimension feature values through the time sequence data mining model to obtain corresponding analysis result data, generating corresponding view resource data according to a preset mode by the server 104 according to the analysis result data, and pushing the view resource data to the terminal 102. The time sequence data in the visual data is extracted, the time sequence data is subjected to characteristic extraction, and then the time sequence data is analyzed through a time sequence data mining model, so that valuable information in the time sequence data can be effectively mined for further analysis, and the mining efficiency and accuracy of the time sequence data can be effectively improved.
In one embodiment, as shown in fig. 2, there is provided a data processing method for giving time series data, which is described by taking the server in fig. 1 as an example, including the steps of:
The user can send a data acquisition request to the server through the corresponding terminal, wherein the request type is included in the data acquisition request. The request type may be a type of the acquired target data resource, for example, a request type such as time series data prediction and data mining. The request information may be parameter information input by a user, such as a time dimension parameter, or the like.
The visual data may be data in which time series data are integrated through a specific integration function and presented in a visual form, and each visual data includes a category identifier. The category identification may represent a visual graphic type to which the visual data corresponds. For example, the visual data may include weather data, public opinion data, medical data, and the like, and the visual data may be in the form of various view data, table data, and the like. Such as statistical maps, distribution maps, heat maps, scatter maps, etc.
The server may acquire a plurality of visual data from the local database according to the resource acquisition request and the request information, or may acquire a plurality of visual data from the third party database. Further, the resource acquisition request may further include request information, and the server acquires a plurality of visual data according to the resource acquisition request and the request information.
And step 206, acquiring a plurality of time series data from the visualized data according to the category identification.
The time series data refers to time series data recorded in time series with the same unified index. The time series data can comprise dimension characteristics corresponding to a plurality of dimensions. After the server acquires a plurality of visual data according to the resource acquisition request, acquiring base table data and an objective function corresponding to the visual data according to the category identification, wherein the base table data can represent basic data required by the visual data, and the objective function can be an integration function required by integrating the visual data and the like. The server further obtains time sequence distribution data in the visual data according to the base table data and the objective function, and converts the time sequence distribution data into time sequence data according to a preset mode.
And step 208, performing time sequence feature processing on the plurality of time sequence data to obtain feature variables and dimension feature values corresponding to the plurality of time sequence data.
And 210, extracting the characteristic variable and the corresponding dimension characteristic value, wherein the characteristic variable reaches the threshold value.
After the server acquires a plurality of time sequence data from the visual data, time sequence feature processing is carried out on the plurality of time sequence data, the plurality of time sequence data are converted into corresponding feature vectors according to time sequence, the plurality of feature vectors are converted into a plurality of feature variables and corresponding dimension feature values, and the dimension feature values can be expressed as feature dimensions to which the feature variables belong. And obtaining characteristic variables and dimension characteristic values corresponding to the time series data. For example, the server can preprocess feature vectors corresponding to the time series data in a mean filling mode, a custom filling mode, a book model filling mode and the like, and can perform time series diagram feature processing on the time series data through a data mean value, a variance, a standard deviation and the like, so that feature variables and dimension feature values corresponding to the time series data are extracted.
The server further performs feature extraction on a plurality of feature variables corresponding to the plurality of time sequence data, and extracts feature variables reaching a threshold value and corresponding dimension feature values. After the time sequence feature processing is carried out on the feature vectors corresponding to the time sequence feature vectors by the server, feature extraction is carried out on a plurality of time sequence feature vectors according to a preset feature dimension reduction algorithm, and feature variables reaching a threshold value are extracted. For example, the dimension of the whole feature variable can be reduced by utilizing algorithms such as singular value decomposition, principal component analysis and the like, so that the feature extraction of the time sequence data can be effectively performed, and valuable feature variables and corresponding dimension feature values can be extracted.
After the server extracts the feature variable and the corresponding dimension feature value reaching the threshold value, a preset time sequence data mining model is obtained, the extracted feature variable and the corresponding dimension feature value are input into the time sequence data mining model, and the time sequence data is analyzed through the time sequence data mining model. Specifically, the server can calculate the weight of the characteristic variable through a time sequence data mining model, calculate corresponding predicted values of a plurality of characteristic variables corresponding to a plurality of preset time sequence parameters according to the dimension characteristic values and the weights of the model characteristic variable through the time sequence data mining model, and further generate analysis result data corresponding to the request type according to the plurality of preset time sequence parameters and the corresponding predicted values.
After the server generates the analysis result data, the server can further generate the corresponding view resource data according to a preset mode. Specifically, the server may acquire a corresponding integration function according to a request type in the resource acquisition request, and integrate corresponding view resource data through the integration function according to a plurality of preset time sequence parameters and corresponding predicted values in the analysis result data, so that the server pushes the view resource data to the terminal. The time sequence data in the visual data is extracted, the time sequence data is subjected to characteristic extraction, and then the time sequence data is analyzed through a time sequence data mining model, so that valuable information in the time sequence data can be effectively mined for further analysis, and the mining efficiency and accuracy of the time sequence data can be effectively improved.
In the above data processing method based on time series data, after the server receives the resource acquisition request sent by the terminal, the resource acquisition request includes a request type and request information, and the server acquires a plurality of visual data according to the resource acquisition request and the request information, where the visual data includes a category identifier. The server further obtains a plurality of time sequence data from the visual data according to the category identification, so that the time sequence data in the visual data can be effectively obtained. The server further performs time sequence feature processing on the plurality of time sequence data to obtain feature variables and dimension feature values corresponding to the plurality of time sequence data; and extracting the characteristic variable reaching the threshold value and the corresponding dimension characteristic value. Acquiring a preset time sequence data mining model according to the request type, analyzing the characteristic variable and the corresponding dimension characteristic value through the time sequence data mining model to obtain corresponding analysis result data, further generating corresponding view resource data according to the analysis result data in a preset mode, and pushing the view resource data to the terminal. The time sequence data in the visual data is extracted, the time sequence data is subjected to characteristic extraction, and then the time sequence data is analyzed through a time sequence data mining model, so that valuable information in the time sequence data can be effectively mined for further analysis, and the mining efficiency and accuracy of the time sequence data can be effectively improved.
In one embodiment, the visualized data includes a category identifier and a data identifier, and as shown in fig. 3, the step of acquiring a plurality of time series data from the visualized time series data according to the category identifier and the data identifier specifically includes the following steps:
and 302, acquiring base table data and an objective function corresponding to the visual data according to the category identification and the data identification.
The base table data may be a data table storing physical records corresponding to the visualized data, for example, a data relationship mapping table. The category identifier may represent a type of the visualized data, the data identifier may represent an identification code of each visualized data, and an association mapping relation table may be pre-established between the data representation and the base table data.
And step 304, acquiring time sequence distribution data in the visualized data according to the base table data and the objective function.
After receiving a resource acquisition request sent by a terminal, a server acquires a plurality of visual data according to a request type and request information in the resource acquisition request, wherein the visual data comprises a category identifier and a data identifier. The server further obtains a plurality of time sequence data from the visualized data according to the category identification. The visual data can be visual data of different categories which are generated in advance according to the base table data and the preset integration function, and each type of visual data can correspond to the same target integration function.
Specifically, the server obtains an objective function corresponding to the visual data according to the category identifier, where the objective function may be an objective integration function for integrating the visual data. And the server acquires a preset association relation mapping table according to the data identification, and further acquires the base table data corresponding to the data identification. The server can further acquire time sequence distribution data in the visual data through an objective function according to the base table data, and further convert the acquired time sequence distribution data into time sequence data according to a preset mode. For example, the visualized data such as the histogram and the distribution density can be embedded by using the python visualized function to generate the corresponding visualized data. When the time sequence data is extracted, the corresponding python visual function and the base table data can be utilized to analyze and obtain the corresponding time sequence distribution data, and then the time sequence distribution data contained in the visual data can be effectively extracted.
In one embodiment, obtaining timing distribution data in the visualization data from the base table data and the objective function includes: acquiring coordinate matrix data and corresponding parameter weights according to the base table data and the objective function; and acquiring corresponding time sequence distribution data according to the coordinate matrix data and the corresponding parameter weight.
After receiving a resource acquisition request sent by a terminal, a server acquires a plurality of visual data according to a request type and request information in the resource acquisition request, wherein the visual data comprises a category identifier and a data identifier. The server further obtains a plurality of time sequence data from the visualized data according to the category identification. The visual data can be visual data of different categories which are generated in advance according to the base table data and the preset integration function, and each type of visual data can correspond to the same target integration function.
Specifically, the server obtains an objective function corresponding to the visual data according to the category identifier, where the objective function may be an objective integration function for integrating the visual data. And the server acquires a preset association relation mapping table according to the data identification, and further acquires the base table data corresponding to the data identification. The visualized data includes coordinate matrix data, where the coordinate matrix data may include feature vectors of multiple dimensions and corresponding parameter weights, and for example, may include feature vectors corresponding to abscissa and ordinate and corresponding parameter weights.
The server further obtains coordinate matrix data and corresponding parameter weights according to the base table data and the objective function, and further obtains corresponding time sequence distribution data in the visualized data according to the coordinate matrix data and the corresponding parameter weights, for example, the time sequence distribution data can be time sequence distribution information based on time dimension, and can also comprise time sequence distribution information of multiple dimensions. After the server acquires the time sequence data in the visual data, the acquired time sequence distribution data is further converted into the time sequence data according to a preset mode. The coordinate matrix data of the visual data can be effectively obtained through the base table data and the objective function, and then the time sequence distribution data in the visual data can be effectively obtained.
In one embodiment, the step of extracting features of feature variables corresponding to the plurality of multi-dimensional time series data according to a preset algorithm includes: performing cluster analysis on characteristic variables corresponding to the multi-dimensional time sequence data to obtain a plurality of clustering results; calculating correlation among a plurality of characteristic variables according to a plurality of clustering results; and selecting the characteristics according to the correlation among the characteristic variables, and extracting the characteristic variables reaching a preset threshold value and corresponding dimension characteristics.
After receiving a resource acquisition request sent by a terminal, a server acquires a plurality of visual data according to a request type and request information in the resource acquisition request, wherein the visual data comprises a category identifier and a data identifier. The server further obtains a plurality of time sequence data from the visualized data according to the category identification.
After the server acquires a plurality of time sequence data from the visual data, time sequence feature processing is carried out on the plurality of time sequence data, the plurality of time sequence data are converted into corresponding feature vectors according to time sequence, and the plurality of feature vectors are converted into a plurality of feature variables and corresponding dimension feature values, so that feature variables and dimension feature values corresponding to the plurality of time sequence data are obtained. For example, the server can preprocess feature vectors corresponding to the time series data in a mean filling mode, a custom filling mode, a book model filling mode and the like, and can perform time series diagram feature processing on the time series data through a data mean value, a variance, a standard deviation and the like, so that feature variables and dimension feature values corresponding to the time series data are extracted.
The server further performs feature extraction on a plurality of feature variables corresponding to the plurality of time sequence data, and extracts feature variables reaching a threshold value and corresponding dimension feature values. Specifically, after extracting feature variables and corresponding dimension feature values corresponding to a plurality of time sequence data, a server performs cluster analysis on the feature variables and the corresponding dimension feature values by adopting a preset clustering algorithm. For example, a method of k-means (k-means algorithm) clustering may be employed. And the server performs multiple clustering through the multiple feature variables and the corresponding dimension feature values to obtain multiple clustering results.
The server further respectively combines the characteristic variables in the clustering results to obtain a plurality of combined characteristic variables. And obtaining a target variable, and performing correlation test on the plurality of combined characteristic variables by using the target variable. And when the verification passes, adding an interactive label to the combined characteristic variable. And analyzing the corresponding characteristic variable by utilizing the combined characteristic variable added with the interactive label. The combined feature variable after the interactive label is added can be the feature variable reaching the preset threshold, and the server extracts the corresponding dimension feature value reaching the preset threshold feature variable.
The server further obtains a preset time sequence data mining model according to the request type, and analyzes the characteristic variable and the corresponding dimension characteristic value through the time sequence data mining model to obtain corresponding analysis result data. And generating corresponding view resource data according to the analysis result data in a preset mode, and pushing the view resource data to the terminal. By analyzing the big data of the time sequence data, valuable characteristic variables and corresponding dimension characteristic values in the time sequence data can be effectively extracted, and then the time sequence data can be effectively mined.
In one embodiment, as shown in fig. 4, the steps of analyzing the time series data through the time series data mining model specifically include the following:
And step 406, generating analysis result data corresponding to the request type according to the plurality of preset time sequence parameters and the corresponding predicted values.
Before the server acquires the preset time sequence data mining model, the time sequence data mining model needs to be built and trained in advance. Specifically, the server may obtain a plurality of time series data from a local or third party database, and the server further performs cluster analysis on the plurality of time series data. Specifically, the server performs feature extraction on the plurality of time series data, and extracts corresponding feature variables and corresponding dimension feature values. After extracting the characteristic variables and the dimension characteristic values of a plurality of time sequences, the server performs cluster analysis on the characteristic variables by adopting a preset clustering algorithm, and obtains a plurality of clustering results after clustering the characteristic variables for a plurality of times. The server further respectively combines the characteristic variables in the clustering results to obtain a plurality of combined characteristic variables, and correlates the combined characteristic variables. And the server extracts the characteristic variable reaching the preset threshold and the corresponding dimension characteristic value.
After the server extracts the plurality of characteristic variables and the corresponding dimension characteristic values, a time sequence data mining model is built according to a preset algorithm and the plurality of characteristic variables and the corresponding dimension characteristic values. The time-series data mining model can be a model based on a decision tree or a neural network.
Further, the server may also obtain a large amount of time series data and generate training set data and verification set data using the large amount of time series data. And the server inputs a large amount of time sequence data in the training set into the time sequence data mining model for training to obtain a preliminary time sequence data mining model. The server further trains and verifies the preliminary time sequence data mining model by utilizing a large amount of time sequence data in the verification set, and when the data meeting the preset evaluation value in the verification set reaches the preset ratio, the trained time sequence data mining model is obtained. After large data analysis is carried out on a large amount of time sequence data, a time sequence data mining model is established and trained according to a preset mode by utilizing the extracted characteristic variables and the dimension characteristic values, and therefore the time sequence data mining model with high analysis accuracy can be effectively constructed.
After receiving a resource acquisition request sent by a terminal, a server acquires a plurality of visual data according to a request type and request information in the resource acquisition request, wherein the visual data comprises a category identifier and a data identifier. The server further obtains a plurality of time sequence data from the visualized data according to the category identification.
After the server acquires a plurality of time sequence data from the visual data, time sequence feature processing is carried out on the plurality of time sequence data, the plurality of time sequence data are converted into corresponding feature vectors according to time sequence, and the plurality of feature vectors are converted into a plurality of feature variables and corresponding dimension feature values, so that feature variables and dimension feature values corresponding to the plurality of time sequence data are obtained. The server further performs feature extraction on a plurality of feature variables corresponding to the plurality of time sequence data, and extracts feature variables reaching a threshold value and corresponding dimension feature values.
The server further obtains a preset time sequence data mining model according to the request type, inputs the extracted characteristic variable and the corresponding dimension characteristic value into the time sequence data mining model, calculates the weight of the characteristic variable through the time sequence data mining model, calculates corresponding predicted values of the characteristic variable corresponding to the preset time sequence parameters according to the dimension characteristic value and the weight of the characteristic variable through the time sequence data mining model, and generates analysis result data corresponding to the request type according to the preset time sequence parameters and the corresponding predicted values. After the server generates the analysis result data, the server can further generate corresponding view resource data according to a preset mode and push the view resource data to the terminal. The time sequence data in the visual data is extracted, the time sequence data is subjected to characteristic extraction, and then the time sequence data is analyzed through a time sequence data mining model, so that valuable information in the time sequence data can be effectively mined for further analysis, and the mining efficiency and accuracy of the time sequence data can be effectively improved.
For example, the server may acquire a plurality of visual data, such as weather visual data of one week, a large amount of morbidity data, public opinion data, medical data, and the like. The server further extracts time sequence data in the visual data, extracts characteristic variables and corresponding dimension characteristic values in the time sequence data, analyzes the characteristic variables and the corresponding dimension characteristic values in the time sequence data through a preset time sequence data analysis model, analyzes the correlation between the probability of occurrence and each characteristic variable in the time sequence data, and further obtains corresponding predicted values of a plurality of preset time sequence parameters such as the probability of occurrence, the number of occurrence, the occurrence distribution situation and the like corresponding to the plurality of characteristic variables. Therefore, the time sequence data can be effectively utilized to mine and analyze the incidence probability of certain epidemic diseases in a specific time period, and the corresponding epidemic diseases can be effectively prevented.
In one embodiment, the analysis result data includes a plurality of preset time sequence parameters and corresponding predicted values, and the method further includes: acquiring a preset integration function according to the request type; integrating corresponding view resource data through an integration function according to a plurality of preset time sequence parameters and corresponding predicted values in the analysis result data; event type identification and corresponding interface call parameters are added to the view resource data.
After the server receives a resource acquisition request sent by the terminal, the resource acquisition request comprises a request type and request information, and the server acquires a plurality of visual data according to the resource acquisition request and the request information, wherein the visual data comprises a category identifier. The server further obtains a plurality of time sequence data from the visual data according to the category identification, and performs time sequence feature processing on the plurality of time sequence data to obtain feature variables and dimension feature values corresponding to the plurality of time sequence data; and extracting the characteristic variable reaching the threshold value and the corresponding dimension characteristic value.
The server further obtains a preset time sequence data mining model according to the request type, analyzes the characteristic variable and the corresponding dimension characteristic value through the time sequence data mining model to obtain corresponding analysis result data, and further generates corresponding view resource data according to the analysis result data in a preset mode. Specifically, the server may obtain a preset integration function according to the request type, integrate corresponding view resource data through the integration function according to a plurality of preset time sequence parameters and corresponding predicted values in the analysis result data, and add event type identifiers and corresponding interface call parameters to the view resource data.
The analysis result data may include a plurality of corresponding predicted values of the preset timing parameters. For example, parameters such as probability of onset, occurrence distribution, etc. based on the time dimension may be included, and corresponding predictive values. For example, the time dimension may be time units per day or per week every 3 hours, every 12 hours. The server may integrate the corresponding predicted values of the plurality of preset timing parameters into corresponding view data by acquiring a preset timing distribution integration function, for example, a python visualization function, for example, the corresponding view data may be embedded into the corresponding view data by using a histogram visualization function, a distribution density, a heat map, and the like, and a corresponding visual image may be drawn by using a nested function.
And the server integrates the corresponding view resource data through the integration function according to a plurality of preset time sequence parameters and corresponding predicted values in the analysis result data, further adds event type identification and corresponding interface call parameters to the view resource data, and integrates and stores the corresponding classes. The method is beneficial to the server or the terminal to call the generated view resource data, so that when the server or the terminal acquires the associated time sequence data or view data again, the server or the terminal can call the view resource data obtained through mining and analysis directly according to the event type identifier and the corresponding interface call parameters, and further the analysis efficiency and the utilization value of the time sequence data are improved.
After the server generates the corresponding view resource data, the view resource data is pushed to the terminal. The time sequence data in the visual data is extracted, the time sequence data is subjected to characteristic extraction, and then the time sequence data is analyzed through a time sequence data mining model, so that valuable information in the time sequence data can be effectively mined for further analysis, and the mining efficiency and the analysis efficiency of the time sequence data can be effectively improved.
It should be understood that, although the steps in the flowcharts of fig. 2-4 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2-4 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily occur sequentially, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or steps.
In one embodiment, as shown in fig. 5, there is provided a data processing apparatus based on time series data, including: a request receiving module 502, a data acquisition module 504, a feature processing module 506, a data mining module 508, and a view generation module 510, wherein:
a request receiving module 502, configured to receive a resource acquisition request sent by a terminal, where the resource acquisition request includes a request type and request information;
a data acquisition module 504, configured to acquire a plurality of visual data according to the resource acquisition request and the request information, where the visual data includes a category identifier; acquiring a plurality of time sequence data from the visual data according to the category identification;
the feature processing module 506 is configured to perform time sequence feature processing on the plurality of time sequence data, so as to obtain feature variables and dimension feature values corresponding to the plurality of time sequence data; extracting the characteristic variable reaching the threshold value and the corresponding dimension characteristic value;
the data mining module 508 is configured to obtain a preset time-series data mining model according to the request type, and analyze the feature variable and the corresponding dimension feature value through the time-series data mining model to obtain corresponding analysis result data;
The view generating module 510 is configured to generate corresponding view resource data according to the analysis result data in a preset manner, and push the view resource data to the terminal.
In one embodiment, the visualized data includes a category identifier and a data identifier, and the data acquisition module 504 is further configured to acquire base table data and an objective function corresponding to the visualized data according to the category identifier and the data identifier; acquiring time sequence distribution data in the visual data according to the base table data and the objective function; and converting the time sequence distribution data into time sequence data according to a preset mode.
In one embodiment, the data acquisition module 504 is further configured to acquire coordinate matrix data and corresponding parameter weights according to the base table data and the objective function; and acquiring corresponding time sequence distribution data according to the coordinate matrix data and the corresponding parameter weight.
In one embodiment, the feature processing module 506 is further configured to perform cluster analysis on feature variables corresponding to the plurality of time series data, so as to obtain a plurality of cluster results; calculating correlation among a plurality of characteristic variables according to a plurality of clustering results; and selecting the characteristics according to the correlation among the characteristic variables, and extracting the characteristic variables reaching a preset threshold value and corresponding dimension characteristics.
In one embodiment, the data mining module 508 is further configured to calculate weights for the feature variables by a time-series data mining model; calculating corresponding predicted values of a plurality of characteristic variables corresponding to a plurality of preset time sequence parameters according to the dimension characteristic values and weights of the characteristic variables through a time sequence data mining model; and generating analysis result data corresponding to the request type according to the plurality of preset time sequence parameters and the corresponding predicted values.
In one embodiment, the analysis result data includes a plurality of preset time sequence parameters and corresponding predicted values, and the view generation module 510 is further configured to obtain a preset integration function according to the request type; integrating corresponding view resource data through an integration function according to a plurality of preset time sequence parameters and corresponding predicted values in the analysis result data; event type identification and corresponding interface call parameters are added to the view resource data.
For specific limitations of the data processing apparatus based on time series data, reference may be made to the above limitation of the data processing method based on time series data, and no further description is given here. Each of the modules in the above-described time series data based data processing apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing visualization data, time sequence data, view resource data and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a data processing method based on time series data.
It will be appreciated by those skilled in the art that the structure shown in fig. 6 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory storing a computer program and a processor implementing the steps of the time-series data based data processing method provided in any one of the embodiments of the present application when the computer program is executed.
In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, which when executed by a processor implements the steps of the time-series data based data processing method provided in any one of the embodiments of the present application.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (10)
1. A method of data processing based on time series data, the method comprising:
receiving a resource acquisition request sent by a terminal, wherein the resource acquisition request comprises a request type and request information;
acquiring a plurality of visual data according to the resource acquisition request and the request information, wherein the visual data comprises a category identifier;
acquiring a plurality of time sequence data from the visual data according to the category identification;
Performing time sequence feature processing on the plurality of time sequence data to obtain feature variables and dimension feature values corresponding to the plurality of time sequence data;
performing cluster analysis on the characteristic variables corresponding to the time sequence data to obtain a plurality of cluster results;
calculating correlation among a plurality of characteristic variables according to the plurality of clustering results;
performing feature selection according to the correlation among the feature variables, and extracting feature variables reaching a threshold value and corresponding dimension feature values;
acquiring a preset time sequence data mining model according to the request type, and calculating the weight of the characteristic variable through the time sequence data mining model;
calculating corresponding predicted values of a plurality of characteristic variables corresponding to a plurality of preset time sequence parameters according to the dimension characteristic values and weights of the characteristic variables through the time sequence data mining model; generating analysis result data corresponding to the request type according to the plurality of preset time sequence parameters and the corresponding predicted values;
integrating corresponding view resource data through a preset integration function according to a plurality of preset time sequence parameters and corresponding predicted values in the analysis result data, and pushing the view resource data to the terminal.
2. The method of claim 1, wherein the visual data includes a category identification and a data identification, and wherein the step of obtaining a plurality of time series data from the visual data according to the category identification comprises:
acquiring base table data and an objective function corresponding to the visual data according to the category identification and the data identification;
acquiring time sequence distribution data in the visual data according to the base table data and the objective function;
and converting the time sequence distribution data into time sequence data according to a preset mode.
3. The method of claim 2, wherein the step of obtaining timing distribution data in the visualization data from the base table data and the objective function comprises:
acquiring coordinate matrix data and corresponding parameter weights according to the base table data and the objective function;
and acquiring corresponding time sequence distribution data according to the coordinate matrix data and the corresponding parameter weight.
4. The method according to claim 1, wherein the analysis result data includes a plurality of preset timing parameters and corresponding predicted values, and the integration function is obtained according to the request type; the method further comprises the steps of:
And adding event type identification and corresponding interface calling parameters to the view resource data.
5. A data processing apparatus based on time series data, the apparatus comprising:
the resource acquisition module is used for receiving a resource acquisition request sent by the terminal, wherein the resource acquisition request comprises a request type and request information;
the data acquisition module is used for acquiring a plurality of visual data according to the resource acquisition request and the request information, wherein the visual data comprises a category identifier; acquiring a plurality of time sequence data from the visual data according to the category identification;
the characteristic processing module is used for carrying out time sequence characteristic processing on the plurality of time sequence data to obtain characteristic variables and dimension characteristic values corresponding to the plurality of time sequence data; performing cluster analysis on the characteristic variables corresponding to the time sequence data to obtain a plurality of cluster results; calculating correlation among a plurality of characteristic variables according to the plurality of clustering results; performing feature selection according to the correlation among the feature variables, and extracting feature variables reaching a threshold value and corresponding dimension feature values;
the data mining module is used for acquiring a preset time sequence data mining model according to the request type, and calculating the weight of the characteristic variable through the time sequence data mining model; calculating corresponding predicted values of a plurality of characteristic variables corresponding to a plurality of preset time sequence parameters according to the dimension characteristic values and weights of the characteristic variables through the time sequence data mining model; generating analysis result data corresponding to the request type according to the plurality of preset time sequence parameters and the corresponding predicted values;
And the view generation module is used for integrating corresponding view resource data through a preset integration function according to a plurality of preset time sequence parameters and corresponding predicted values in the analysis result data and pushing the view resource data to the terminal.
6. The apparatus of claim 5, wherein the visual data comprises a category identifier and a data identifier, and the data acquisition module is further configured to acquire base table data and an objective function corresponding to the visual data according to the category identifier and the data identifier; acquiring time sequence distribution data in the visual data according to the base table data and the objective function; and converting the time sequence distribution data into time sequence data according to a preset mode.
7. The apparatus of claim 6, wherein the data acquisition module is further configured to acquire coordinate matrix data and corresponding parameter weights from the base table data and the objective function; and acquiring corresponding time sequence distribution data according to the coordinate matrix data and the corresponding parameter weight.
8. The apparatus of claim 5, wherein the integration function is obtained based on the request type; the view generation module is further used for adding event type identification and corresponding interface call parameters to the view resource data.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 4 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 4.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910171923.6A CN110008251B (en) | 2019-03-07 | 2019-03-07 | Data processing method and device based on time sequence data and computer equipment |
| PCT/CN2019/116234 WO2020177366A1 (en) | 2019-03-07 | 2019-11-07 | Data processing method and apparatus based on time sequence data, and computer device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910171923.6A CN110008251B (en) | 2019-03-07 | 2019-03-07 | Data processing method and device based on time sequence data and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110008251A CN110008251A (en) | 2019-07-12 |
| CN110008251B true CN110008251B (en) | 2023-07-04 |
Family
ID=67166718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910171923.6A Active CN110008251B (en) | 2019-03-07 | 2019-03-07 | Data processing method and device based on time sequence data and computer equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110008251B (en) |
| WO (1) | WO2020177366A1 (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110008251B (en) * | 2019-03-07 | 2023-07-04 | 平安科技（深圳）有限公司 | Data processing method and device based on time sequence data and computer equipment |
| CN110489613B (en) * | 2019-07-29 | 2022-04-26 | 北京航空航天大学 | Collaborative visual data recommendation method and device |
| CN110716926B (en) * | 2019-09-06 | 2022-09-20 | 未鲲(上海)科技服务有限公司 | Periodic view data generation method and device, computer equipment and storage medium |
| CN112561337A (en) * | 2020-12-16 | 2021-03-26 | 北京明略软件系统有限公司 | Method and device for determining object type |
| CN113157788B (en) * | 2021-04-13 | 2024-02-13 | 福州外语外贸学院 | Big data mining method and system |
| CN115114345B (en) * | 2022-04-02 | 2024-04-09 | 腾讯科技（深圳）有限公司 | Feature representation extraction method, device, equipment, storage medium and program product |
| CN114936581B (en) * | 2022-06-01 | 2024-04-26 | 中国人民解放军63796部队 | Multi-parameter association mining method based on time sequence data segmentation |
| CN115442243B (en) * | 2022-08-31 | 2024-04-16 | 西南大学 | Sequential network node centrality evaluation method and device based on sequential path tree |
| CN116804993B (en) * | 2023-08-22 | 2023-12-08 | 北京龙德缘电力科技发展有限公司 | Visual expression method with time sequence data characteristics |
| CN117493444B (en) * | 2024-01-02 | 2024-04-09 | 广州海洋地质调查局三亚南海地质研究所 | Data extraction and loading method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5742811A (en) * | 1995-10-10 | 1998-04-21 | International Business Machines Corporation | Method and system for mining generalized sequential patterns in a large database |
| CN101853277A (en) * | 2010-05-14 | 2010-10-06 | 南京信息工程大学 | Vulnerability data mining method based on classification and association analysis |
| CN104679827A (en) * | 2015-01-14 | 2015-06-03 | 北京得大信息技术有限公司 | Big data-based public information association method and mining engine |
| CN106651200A (en) * | 2016-12-29 | 2017-05-10 | 中国西电电气股份有限公司 | Electrical load management method and system for industrial enterprise aggregate user |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7747641B2 (en) * | 2004-07-09 | 2010-06-29 | Microsoft Corporation | Modeling sequence and time series data in predictive analytics |
| CN108462605B (en) * | 2018-02-06 | 2022-03-15 | 国家电网公司 | Data prediction method and device |
| CN110008251B (en) * | 2019-03-07 | 2023-07-04 | 平安科技（深圳）有限公司 | Data processing method and device based on time sequence data and computer equipment |
-
2019
- 2019-03-07 CN CN201910171923.6A patent/CN110008251B/en active Active
- 2019-11-07 WO PCT/CN2019/116234 patent/WO2020177366A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5742811A (en) * | 1995-10-10 | 1998-04-21 | International Business Machines Corporation | Method and system for mining generalized sequential patterns in a large database |
| CN101853277A (en) * | 2010-05-14 | 2010-10-06 | 南京信息工程大学 | Vulnerability data mining method based on classification and association analysis |
| CN104679827A (en) * | 2015-01-14 | 2015-06-03 | 北京得大信息技术有限公司 | Big data-based public information association method and mining engine |
| CN106651200A (en) * | 2016-12-29 | 2017-05-10 | 中国西电电气股份有限公司 | Electrical load management method and system for industrial enterprise aggregate user |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020177366A1 (en) | 2020-09-10 |
| CN110008251A (en) | 2019-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110008251B (en) | Data processing method and device based on time sequence data and computer equipment | |
| CN111950329B (en) | Target detection and model training method, device, computer equipment and storage medium | |
| CN110008250B (en) | Social security data processing method and device based on data mining and computer equipment | |
| CN109829020B (en) | Method and device for pushing place resource data, computer equipment and storage medium | |
| CN109325118B (en) | Unbalanced sample data preprocessing method and device and computer equipment | |
| CN110245132B (en) | Data anomaly detection method, device, computer readable storage medium and computer equipment | |
| CN109886719B (en) | Data mining processing method and device based on grid and computer equipment | |
| CN110866491B (en) | Target retrieval method, apparatus, computer-readable storage medium, and computer device | |
| CN109935338A (en) | Data prediction processing method, device and computer equipment based on machine learning | |
| CN109783785B (en) | Method and device for generating experiment detection report and computer equipment | |
| CN110737818B (en) | Network release data processing method, device, computer equipment and storage medium | |
| CN109271356B (en) | Log file format processing method, device, computer equipment and storage medium | |
| CN109886554B (en) | Illegal behavior discrimination method, device, computer equipment and storage medium | |
| CN111178949B (en) | Service resource matching reference data determining method, device, equipment and storage medium | |
| CN110046577B (en) | Pedestrian attribute prediction method, device, computer equipment and storage medium | |
| CN112035611B (en) | Target user recommendation method, device, computer equipment and storage medium | |
| CN112231038B (en) | Work order information display method, device, computer equipment and storage medium | |
| CN114139015A (en) | Video storage method, device, equipment and medium based on key event identification | |
| CN111242840A (en) | Handwritten character generation method, apparatus, computer device and storage medium | |
| CN110956195A (en) | Image matching method and device, computer equipment and storage medium | |
| CN116629435A (en) | Risk prediction method, risk prediction device, computer equipment and storage medium | |
| CN110162689B (en) | Information pushing method, device, computer equipment and storage medium | |
| CN111898035B (en) | Data processing strategy configuration method and device based on Internet of things and computer equipment | |
| CN112749539B (en) | Text matching method, text matching device, computer readable storage medium and computer equipment | |
| CN117454190A (en) | Log data analysis method and device |
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 |