Offline feature analysis method and device, computer device and storage medium

Abstract

The application relates to an offline feature analysis method and device, computer equipment and a storage medium. The method comprises the following steps: in response to receiving an offline task data set, performing splitting processing on an offline service sample table to obtain a corresponding split sample table; wherein the offline task data set comprises an offline task type and the offline service sample table; in response to a selection operation of a to-be-queried feature, querying an offline sample data set corresponding to an offline sample in each split sample table according to the to-be-queried feature to obtain a feature query result of the corresponding offline sample; inputting each feature query result into a preconfigured feature analysis model corresponding to the offline task type to obtain a corresponding feature analysis result; and performing merging processing on each feature query result and the corresponding feature analysis result to generate an offline feature analysis result statistical table. The method can improve the accuracy and timeliness of feature analysis.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to an offline feature analysis method, apparatus, computer equipment, and storage medium. Background Technology

[0002] With the continuous development of digitalization, big data, cloud computing, and artificial intelligence, multi-dimensional raw business data from users is used in the process of creating and training data models. The information processed from this raw business data is called features. However, traditional offline feature analysis methods suffer from low accuracy and timeliness because business personnel need to manually operate and maintain them on offline service platforms. Summary of the Invention

[0003] Therefore, it is necessary to provide an offline feature analysis method, apparatus, computer equipment, and storage medium that can improve the accuracy and timeliness of feature analysis in response to the above-mentioned technical problems.

[0004] Firstly, an offline feature analysis method is provided, the method comprising:

[0005] In response to receiving the offline task dataset, the offline service sample table is split to obtain the corresponding split sample table; the offline task dataset includes offline task types and offline service sample tables;

[0006] In response to the selection operation of the feature to be queried, the offline sample dataset corresponding to the offline sample in each split sample table is queried according to the feature to be queried, and the feature query results of the corresponding offline sample are obtained.

[0007] The query results of each feature are input into the pre-configured feature analysis model corresponding to the offline task type to obtain the corresponding feature analysis results;

[0008] The query results for each feature and the corresponding feature analysis results are merged to generate an offline feature analysis result statistics table.

[0009] In one embodiment, the method further includes:

[0010] Obtain the initial offline service sample table output by the offline service platform, the offline sample service data output by the sample data center, and the local files stored by the feature analysis platform;

[0011] The initial offline service sample table, offline sample service data, and local files are processed to generate an offline service sample table; the data processing includes data cleaning and data format conversion.

[0012] In one embodiment, the offline service sample table is split to obtain a corresponding split sample table, including:

[0013] In response to the setting operation of sample splitting parameters, a sample splitting rule is generated based on the sample splitting parameters; wherein, the sample splitting parameters include the sample slicing time;

[0014] The offline service sample table is split according to the sample splitting rules to obtain the corresponding split sample table.

[0015] In one embodiment, the offline task dataset includes offline task execution methods; based on the features to be queried, the offline sample datasets corresponding to the offline samples in each split sample table are queried to obtain the feature query results of the corresponding offline samples, including:

[0016] In response to the asynchronous task execution mode of offline tasks, the offline sample datasets corresponding to the offline samples in each split sample table are asynchronously queried to obtain the feature query results of the corresponding offline samples.

[0017] In one embodiment, the offline sample dataset corresponding to the offline samples in each split sample table is queried according to the feature to be queried to obtain the feature query result of the corresponding offline sample, and the method further includes:

[0018] In response to the offline task execution mode being a synchronous task operation, the offline sample datasets corresponding to the offline samples in each split sample table are synchronously polled to obtain the feature query results of the corresponding offline samples.

[0019] In one embodiment, the feature query results include sample identity data and sample personal feature data; the feature analysis results include sample behavioral features.

[0020] In one embodiment, the method includes:

[0021] The offline feature analysis results statistics table is output to the sample data center so that the sample data center can store the offline feature analysis results statistics table.

[0022] Secondly, an offline feature analysis device is provided, which includes a sample splitting module, a feature query module, a feature analysis module, and a result statistics module.

[0023] The sample splitting module, in response to receiving the offline task dataset, splits the offline service sample table according to a preset slicing time to obtain the corresponding split sample table. The offline task dataset includes the offline task type and the offline service sample table. The feature query module, in response to the selection operation of the feature to be queried, queries the offline sample datasets corresponding to the offline samples in each split sample table according to the feature to be queried, and obtains the feature query results of the corresponding offline samples. The feature analysis module is used to input the feature query results into the pre-configured feature analysis model corresponding to the offline task type to obtain the corresponding feature analysis results. The result statistics module is used to merge the feature query results and the corresponding feature analysis results to generate an offline feature analysis result statistics table.

[0024] Thirdly, a computer device is provided, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of any of the methods described in the above method embodiments.

[0025] Fourthly, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of any of the methods described in the above method embodiments.

[0026] The aforementioned offline feature analysis method, apparatus, computer equipment, and storage medium, in response to receiving an offline task dataset, split the offline service sample table to obtain corresponding split sample tables; wherein, the offline task dataset includes offline task types and offline service sample tables; then, in response to the selection operation of the feature to be queried, query the offline sample datasets corresponding to the offline samples in each split sample table according to the feature to be queried, and obtain the feature query results of the corresponding offline samples; next, input each feature query result into a pre-configured feature analysis model corresponding to the offline task type to obtain the corresponding feature analysis results; finally, merge each feature query result and the corresponding feature analysis results to generate an offline feature analysis result statistics table, thereby providing an offline feature analysis service with unified feature definitions and improving the accuracy and timeliness of offline feature analysis. Attached Figure Description

[0027] Figure 1 This is a diagram illustrating the application environment of an offline feature analysis method in one embodiment;

[0028] Figure 2 This is a schematic diagram of the first process of an offline feature analysis method in one embodiment;

[0029] Figure 3 This is a flowchart illustrating the process of splitting an offline service sample table to obtain a corresponding split sample table in one embodiment.

[0030] Figure 4 This is a schematic diagram of the second process of an offline feature analysis method in one embodiment;

[0031] Figure 5 This is a flowchart illustrating the process of querying the offline sample datasets corresponding to the offline samples in each split sample table based on the features to be queried in one embodiment, and obtaining the feature query results of the corresponding offline samples.

[0032] Figure 6 This is a schematic diagram of the third process of an offline feature analysis method in one embodiment;

[0033] Figure 7 This is a structural block diagram of an offline feature analysis device in one embodiment;

[0034] Figure 8 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0036] To facilitate understanding of this application, a more complete description will be provided below with reference to the accompanying drawings, which illustrate embodiments of the present application. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that the disclosure of this application will be thorough and complete.

[0037] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0038] It is understood that the terms "first," "second," etc., used herein may be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish one element from another. For example, without departing from the scope of this application, a first resistor may be referred to as a second resistor, and similarly, a second resistor may be referred to as a first resistor. Both the first resistor and the second resistor are resistors, but they are not the same resistor.

[0039] It is understood that the term "connection" in the following embodiments should be understood as "electrical connection," "communication connection," etc., if the connected circuits, modules, units, etc., have electrical signal or data transmission with each other.

[0040] When used herein, the singular forms of “a,” “an,” and “the” may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising,” “including,” or “having,” etc., specify the presence of the stated feature, whole, step, operation, component, part, or combination thereof, but do not preclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts, or combinations thereof.

[0041] The offline feature analysis method provided in this application can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices, and server 104 can be a standalone server or a server cluster consisting of multiple servers.

[0042] In a specific example, server 104 can be, but is not limited to, an offline task platform server. The above is just a specific example, and in actual applications, it can be flexibly set according to needs, without any restrictions.

[0043] In one embodiment, such as Figure 2 As shown, an offline feature analysis method is provided, which can be applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps 201 to 204.

[0044] Step 201: In response to receiving the offline task dataset, the offline service sample table is split to obtain the corresponding split sample table.

[0045] The offline task dataset includes offline task types and an offline service sample table. Specifically, the offline task type characterizes the specific task content of the offline task. The offline service sample table includes at least one offline sample dataset.

[0046] In a specific example, the offline sample dataset includes sample identity recognition data and sample business data. The sample identity recognition data is used to identify sample identities; the sample business data is used to characterize the relevant attributes of sample business behavior. This is merely a specific example; in actual applications, the dataset can be flexibly configured according to requirements, and no restrictions are imposed here.

[0047] Specifically, when server 104 receives the offline task dataset, it can split the offline service sample table to obtain the split sample table corresponding to the offline service sample table. This makes it easier to query the offline sample dataset corresponding to the offline samples in the split sample table. Compared with querying directly using the offline service sample table, this improves query efficiency and feature analysis speed.

[0048] In one embodiment, such as Figure 3 As shown, the offline service sample table is split to obtain the corresponding split sample table, including steps 301 and 302.

[0049] Step 301: In response to the setting operation of the sample splitting parameters, generate sample splitting rules based on the sample splitting parameters.

[0050] The sample splitting parameters include the sample slicing time. The sample splitting rules characterize the splitting method for the offline service sample table. Specifically, when setting the sample splitting parameters, server 104 generates sample splitting rules based on the sample splitting parameters.

[0051] Step 302: Split the offline service sample table according to the sample splitting rules to obtain the corresponding split sample table.

[0052] Specifically, server 104 splits the offline service sample table according to the sample splitting rules to obtain the corresponding split sample table. It can be understood that server 104 can split the offline service sample table based on the sample slice time and the recording time of each offline sample in the offline service sample table according to the sample splitting rules to obtain the corresponding split sample table.

[0053] In this embodiment, in response to the setting operation of sample splitting parameters, sample splitting rules are generated according to the sample splitting parameters; then, the offline service sample table is split according to the sample splitting rules to obtain the corresponding split sample table, which facilitates querying the offline sample dataset corresponding to the offline samples in the split sample table. Compared with directly using the offline service sample table for querying, this improves query efficiency and feature analysis speed.

[0054] In one embodiment, such as Figure 4 As shown, the above method also includes steps 401 and 402.

[0055] Step 401: Obtain the initial offline service sample table output by the offline service platform, the offline sample service data output by the sample data center, and the local files stored by the feature analysis platform.

[0056] Step 402: Process the initial offline service sample table, offline sample service data, and local files to generate the offline service sample table.

[0057] Data processing includes data cleaning and data format conversion. Server 104 can acquire the initial offline service sample table output by the offline service platform, the offline sample service data output by the sample data center, and the local files stored by the feature analysis platform. Then, it processes the initial offline service sample table, the offline sample service data, and the local files to generate an offline service sample table, thereby realizing the function of receiving and processing sample data from multiple data sources and improving the convenience of offline feature analysis.

[0058] In this embodiment, the initial offline service sample table output by the offline service platform, the offline sample service data output by the sample data center, and the local files stored by the feature analysis platform are obtained. Then, the initial offline service sample table, the offline sample service data, and the local files are processed to generate an offline service sample table, thereby realizing the function of receiving and processing sample data from multiple data sources and improving the convenience of offline feature analysis.

[0059] Step 202: In response to the selection operation of the feature to be queried, query the offline sample dataset corresponding to the offline sample in each split sample table according to the feature to be queried, and obtain the feature query result of the corresponding offline sample.

[0060] The server 104 is pre-configured with a database of features to be queried, which stores features with a unified feature definition. When selecting features to be queried, the server 104 can query the offline sample datasets corresponding to the offline samples in each split sample table based on the features to be queried, thereby obtaining the feature query results of the offline samples corresponding to each split sample table. This unifies the feature definition during feature query, improves the efficiency of feature query, and facilitates the management of the feature query process.

[0061] In a specific example, the database of features to be queried stores various sample personal characteristic data, including education level, age, income, occupation type, and marital status. Specifically, the feature selection operation determines age, income, and education level as the query features. Then, based on age, income, and education level in the query features, the offline sample datasets corresponding to the offline samples in each split sample table are queried to obtain the feature query results for the corresponding offline samples. For example, the feature query results for offline sample 1 include an age of 27, an income of 200,000 / year, and a master's degree. The above is only a specific example; in actual applications, it can be flexibly set according to needs and is not limited here.

[0062] In one embodiment, such as Figure 5 As shown, the offline task dataset includes offline task execution methods. Specifically, step 501 involves querying the offline sample datasets corresponding to the offline samples in each split sample table based on the features to be queried, to obtain the feature query results for the corresponding offline samples.

[0063] Step 501: In response to the offline task execution mode being asynchronous task operation, asynchronous task waiting for active query is performed on the offline sample dataset corresponding to the offline sample in each split sample table to obtain the feature query results of the corresponding offline sample.

[0064] Specifically, when the offline task execution mode is asynchronous, the server 104 performs asynchronous tasks to wait for active queries on the offline sample datasets corresponding to the offline samples in each split sample table, and obtains the feature query results of the corresponding offline samples. This facilitates asynchronous task operations and improves the convenience of offline feature analysis.

[0065] In this embodiment, in response to the offline task execution mode being asynchronous task operation, the offline sample datasets corresponding to the offline samples in each split sample table are subjected to asynchronous task waiting for active query to obtain the feature query results of the corresponding offline samples. This facilitates asynchronous task operation and improves the convenience of offline feature analysis.

[0066] In one embodiment, such as Figure 5 As shown, the offline sample dataset corresponding to the offline sample in each split sample table is queried according to the feature to be queried, and the feature query results of the corresponding offline sample are obtained. Step 502 is also included.

[0067] Step 502: In response to the offline task execution mode being a synchronous task operation, the offline sample datasets corresponding to the offline samples in each split sample table are subjected to a synchronous task and actively polled to obtain the feature query results of the corresponding offline samples.

[0068] Specifically, when the offline task execution mode is a synchronous task operation, the server 104 performs a synchronous task waiting for active polling of the offline sample datasets corresponding to the offline samples in each split sample table to obtain the feature query results of the corresponding offline samples. This facilitates synchronous task operation and improves the convenience of offline feature analysis.

[0069] In this embodiment, in response to the offline task execution mode being a synchronous task operation, the offline sample datasets corresponding to the offline samples in each split sample table are subjected to synchronous task waiting and active polling to obtain the feature query results of the corresponding offline samples. This facilitates support for synchronous task operations and improves the convenience of offline feature analysis.

[0070] Step 203: Input the query results of each feature into the pre-configured feature analysis model corresponding to the offline task type to obtain the corresponding feature analysis results.

[0071] Specifically, server 104 is configured with a feature analysis model database, which stores feature analysis models corresponding to various offline task types. Server 104 inputs the query results of each feature into the pre-configured feature analysis model corresponding to the offline task type to obtain the corresponding feature analysis results, thereby realizing automated offline feature analysis, avoiding manual operation by business personnel, and improving the accuracy and timeliness of feature analysis.

[0072] In one embodiment, the feature query results include sample identity data and sample personal feature data; the feature analysis results include sample behavioral features.

[0073] In a specific example, the offline task type is credit assessment. Based on the age, income, and education level among the query features, the offline sample datasets corresponding to the offline samples in each split sample table are queried to obtain the feature query results for the corresponding offline samples. For example, the feature query results for offline sample 1 include an age of 27, an income of 200,000 / year, and a master's degree. These feature query results are then input into a pre-configured feature analysis model corresponding to credit assessment to obtain the corresponding feature analysis results. Among these, the feature analysis result including sample behavioral characteristics confirms that the sample can repay on time within three days. This is just a specific example; in actual applications, it can be flexibly configured according to needs and is not limited here.

[0074] Step 204: Merge the query results of each feature and the corresponding feature analysis results to generate an offline feature analysis result statistics table.

[0075] Specifically, server 104 merges the query results of each feature with the corresponding feature analysis results to generate an offline feature analysis result statistics table, thereby providing an offline feature analysis service with unified feature definitions and improving the accuracy and timeliness of offline feature analysis.

[0076] In the aforementioned offline feature analysis method, in response to receiving the offline task dataset, the offline service sample table is split to obtain corresponding split sample tables; wherein, the offline task dataset includes offline task types and offline service sample tables; then, in response to the selection operation of the feature to be queried, the offline sample datasets corresponding to the offline samples in each split sample table are queried according to the feature to be queried, to obtain the feature query results of the corresponding offline samples; next, the feature query results are input into the pre-configured feature analysis model corresponding to the offline task type to obtain the corresponding feature analysis results; finally, the feature query results and the corresponding feature analysis results are merged to generate an offline feature analysis result statistics table, thereby providing an offline feature analysis service with unified feature definitions and improving the accuracy and timeliness of offline feature analysis.

[0077] In one embodiment, such as Figure 6 As shown, the above method includes step 601.

[0078] Step 601: Output the offline feature analysis result statistics table to the sample data center so that the sample data center stores the offline feature analysis result statistics table.

[0079] Specifically, server 104 outputs the offline feature analysis result statistics table to the sample data center, thereby enabling the sample data center to store the offline feature analysis result statistics table, which facilitates feature management and operation decoupling from business, while ensuring that feature analysis records are traceable.

[0080] In this embodiment, the offline feature analysis result statistics table is output to the sample data center so that the sample data center stores the offline feature analysis result statistics table, which facilitates feature management and operation decoupling from business, while ensuring that feature analysis records can be traced back.

[0081] It should be understood that, although Figure 2-6 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 2-6 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but may be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but may be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0082] Secondly, such as Figure 7As shown, an offline feature analysis device is provided, which includes a sample splitting module 710, a feature query module 720, a feature analysis module 730, and a result statistics module 740.

[0083] The sample splitting module 710 is used to split the offline service sample table according to a preset slicing time in response to receiving the offline task dataset, thereby obtaining the corresponding split sample table; wherein the offline task dataset includes offline task types and offline service sample tables; the feature query module 720 is used to query the offline sample datasets corresponding to the offline samples in each split sample table according to the selected feature to be queried, thereby obtaining the feature query results of the corresponding offline samples; the feature analysis module 730 is used to input the feature query results into the pre-configured feature analysis model corresponding to the offline task type, thereby obtaining the corresponding feature analysis results; the result statistics module 740 is used to merge the feature query results and the corresponding feature analysis results to generate an offline feature analysis result statistics table.

[0084] In one embodiment, the above-described apparatus further includes an offline service sample table acquisition module.

[0085] The offline service sample table acquisition module is used to acquire the initial offline service sample table output by the offline service platform, the offline sample service data output by the sample data center, and the local files stored by the feature analysis platform. The offline service sample table acquisition module is also used to process the initial offline service sample table, offline sample service data, and local files to generate an offline service sample table. The data processing includes data cleaning and data format conversion.

[0086] In one embodiment, the sample splitting module 710 includes a sample splitting unit.

[0087] The sample splitting unit is used to generate sample splitting rules in response to the setting operation of sample splitting parameters; the sample splitting parameters include sample slicing time; the sample splitting unit is used to split the offline service sample table according to the sample splitting rules to obtain the corresponding split sample table.

[0088] In one embodiment, the offline task dataset includes offline task execution methods; the feature query module 720 includes a first query unit.

[0089] The first query unit is used to respond to the offline task execution mode being asynchronous task operation, and to perform asynchronous task waiting active query on the offline sample dataset corresponding to the offline sample in each split sample table to obtain the feature query results of the corresponding offline sample.

[0090] In one embodiment, the feature query module 720 further includes a second query unit.

[0091] The second query unit is used to respond to the offline task execution mode being a synchronous task operation, and to perform a synchronous task waiting for active polling on the offline sample datasets corresponding to the offline samples in each split sample table to obtain the feature query results of the corresponding offline samples.

[0092] In one embodiment, the feature query results include sample identity data and sample personal feature data; the feature analysis results include sample behavioral features.

[0093] In one embodiment, the above-described apparatus includes a data storage module.

[0094] The data storage module is used to output the offline feature analysis result statistics table to the sample data center so that the sample data center can store the offline feature analysis result statistics table.

[0095] Specific limitations regarding the offline feature analysis device can be found in the limitations of the offline feature analysis method described above, and will not be repeated here. Each module in the aforementioned offline feature analysis device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0096] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and 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 stores offline task datasets. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements an offline feature analysis method.

[0097] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0098] Thirdly, a computer device is provided, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of any of the methods described in the above method embodiments.

[0099] Fourthly, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of any of the methods described in the above method embodiments.

[0100] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile 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 various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0101] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0102] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. An offline feature analysis method, the method comprising: In response to receiving the offline task dataset, the offline service sample table is split to obtain the corresponding split sample table; wherein, the offline task dataset includes offline task types and the offline service sample table; In response to the selection operation of the feature to be queried, the offline sample datasets corresponding to the offline samples in each of the split sample tables are queried according to the feature to be queried, and the feature query results of the corresponding offline samples are obtained. The feature query results are input into the pre-configured feature analysis model corresponding to the offline task type to obtain the corresponding feature analysis results; The query results of each feature and the corresponding feature analysis results are merged to generate an offline feature analysis result statistics table; Obtain the initial offline service sample table output by the offline service platform, the offline sample service data output by the sample data center, and the local files stored by the feature analysis platform; The initial offline service sample table, the offline sample service data, and the local file are processed to generate the offline service sample table; wherein, the data processing includes data cleaning and data format conversion.

2. The method according to claim 1, characterized in that, The process of splitting the offline service sample table to obtain the corresponding split sample table includes: In response to the setting operation of sample splitting parameters, a sample splitting rule is generated according to the sample splitting parameters; wherein, the sample splitting parameters include the sample slicing time; The offline service sample table is split according to the sample splitting rules to obtain the corresponding split sample table.

3. The method according to claim 1, characterized in that, The offline task dataset includes offline task execution methods; the step of querying the offline sample datasets corresponding to the offline samples in each of the split sample tables according to the features to be queried, to obtain the feature query results of the corresponding offline samples, includes: In response to the offline task execution mode being asynchronous task operation, the offline sample datasets corresponding to the offline samples in each of the split sample tables are subjected to asynchronous task waiting for active query to obtain the feature query results of the corresponding offline samples.

4. The method according to claim 1, characterized in that, The step of querying the offline sample datasets corresponding to the offline samples in each of the split sample tables based on the features to be queried, and obtaining the feature query results of the corresponding offline samples, further includes: In response to the offline task execution mode being a synchronous task operation, the offline sample datasets corresponding to the offline samples in each of the split sample tables are subjected to a synchronous task waiting for active polling to obtain the feature query results of the corresponding offline samples.

5. The method according to claim 1, characterized in that, The feature query results include sample identity recognition data and sample personal feature data; the feature analysis results include sample behavioral features.

6. The method according to claim 1, characterized in that, The method includes: The offline feature analysis result statistics table is output to the sample data center so that the sample data center stores the offline feature analysis result statistics table.

7. An offline feature analysis device, characterized in that, The device includes: The sample splitting module is used to split the offline service sample table according to a preset slicing time in response to receiving the offline task dataset, so as to obtain the corresponding split sample table; wherein, the offline task dataset includes offline task types and the offline service sample table; The feature query module is used to respond to the selection operation of the feature to be queried, and to query the offline sample dataset corresponding to the offline sample in each of the split sample tables according to the feature to be queried, so as to obtain the feature query result of the corresponding offline sample; The feature analysis module is used to input the query results of each feature into the pre-configured feature analysis model corresponding to the offline task type to obtain the corresponding feature analysis results; The results statistics module is used to merge the query results of each feature and the corresponding feature analysis results to generate an offline feature analysis results statistics table. The offline service sample table acquisition module is used to acquire the initial offline service sample table output by the offline service platform, the offline sample service data output by the sample data center, and the local files stored by the feature analysis platform. The offline service sample table acquisition module is also used to process the initial offline service sample table, offline sample service data and local files to generate an offline service sample table; the data processing includes data cleaning and data format conversion.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images