Data processing method, device, computer equipment and storage medium

By identifying and filling the missing feature values ​​in data processing, the problem of inefficient data processing of computer equipment is solved, and a more efficient data processing process is achieved.

CN110659316BInactive Publication Date: 2024-11-01CHINA PING AN LIFE INSURANCE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN201910744973.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2019-08-13
Publication Date
2024-11-01
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

If there is a missing output data during data processing of computer equipment, it will lead to inefficient data processing.

Method used

By obtaining feature parameters in the data list, identifying missing feature values, obtaining reference parameters and positioning information, finding missing positions, and filling the reference feature values ​​to the missing positions according to the filling method, a new data list is generated to improve data processing efficiency.

Benefits of technology

By filling in missing feature values, we ensure that there are no missing parameters during the data processing process, thereby improving the efficiency and accuracy of data processing, and it is suitable for applications such as product prediction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN110659316B_ABST
    Figure CN110659316B_ABST
Patent Text Reader

Abstract

The present application relates to a data processing method, device, computer equipment and storage medium. The method includes: obtaining a data list, the data list contains characteristic parameters, when the characteristic parameters in the data list have missing characteristic values, obtaining reference parameters corresponding to the characteristic parameters, extracting reference characteristic values ​​in the reference parameters, and obtaining positioning information of the characteristic parameters, searching for the missing position of the characteristic values ​​in the characteristic parameters according to the positioning information, obtaining a filling method according to the missing position of the characteristic values, and filling the reference characteristic values ​​to the missing position of the characteristic values ​​according to the filling method, obtaining a new data list, executing the characteristic parameters in the new data list to obtain target data, and the target data is used for product prediction. Filling the characteristic parameters with missing characteristic values, since the characteristic parameters with missing characteristic values ​​are filled, the efficiency of data processing can be improved when data processing is performed according to the characteristic parameters without missing characteristic values.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a data processing method, apparatus, computer device and storage medium. Background Art

[0002] With the rapid development of Internet technology and computer technology, it is becoming more and more common to use computer equipment for data processing. Data processing can be to process a large amount of incomprehensible data into valuable data. When computer equipment processes data, it often uses data processing tools, such as data processing models. When computer equipment uses data processing models for data processing, it usually inputs the data to be processed into the data processing model, and obtains the processed data as output through the data processing model.

[0003] However, when a computer device processes model data, if the output data is missing, there will be a problem of low data processing efficiency. Summary of the invention

[0004] Based on this, it is necessary to provide a data processing method, device, computer equipment and storage medium to improve the efficiency of data processing in response to the above technical problems.

[0005] A data processing method, the method comprising:

[0006] Obtaining a data list, wherein the data list includes characteristic parameters;

[0007] When a characteristic parameter in the data list has a missing characteristic value, obtaining a reference parameter corresponding to the characteristic parameter;

[0008] Extracting reference characteristic values ​​from the reference parameters, obtaining location information of the characteristic parameters, and searching for missing locations of characteristic values ​​in the characteristic parameters according to the location information;

[0009] Acquire a filling method according to the missing position of the eigenvalue, and fill the missing position of the eigenvalue with the reference eigenvalue according to the filling method to obtain a new data list;

[0010] The characteristic parameters in the new data list are executed to obtain target data, where the target data is used for product prediction.

[0011] In one embodiment, the obtaining the positioning information of the characteristic parameter includes:

[0012] Extracting keywords from the feature parameters;

[0013] Obtaining a keyword list, wherein the keyword list is used to record the corresponding relationship between the keywords and the keyword position information;

[0014] According to the keyword list, searching for keyword position information corresponding to the keyword;

[0015] The positioning information of the feature parameters is generated according to the keyword position information.

[0016] In one of the embodiments, the positioning information includes a characteristic parameter identifier, and the characteristic parameter identifier is used to distinguish different characteristic parameters;

[0017] The searching for a missing position of a characteristic value in the characteristic parameter according to the positioning information includes:

[0018] Obtaining a characteristic parameter identifier in the positioning information, and searching for a characteristic parameter according to the characteristic parameter identifier;

[0019] Acquire a feature value position corresponding to the feature parameter, and determine the feature value missing position according to the feature value position.

[0020] In one embodiment, the obtaining of a filling method according to the missing position of the characteristic value includes:

[0021] Acquire selection information corresponding to the missing position of the feature value, wherein the selection information is divided into first selection information and second selection information;

[0022] When the selection information is the first selection information, obtaining an automatic filling method;

[0023] When the selection information is the second selection information, a passive filling method is acquired.

[0024] In one embodiment, the filling of the reference feature value to the feature value missing position according to the filling method to obtain a new data list includes:

[0025] When the filling mode is an automatic filling mode, the reference characteristic value is automatically copied to the position where the characteristic value is missing to obtain a new data list.

[0026] In one embodiment, the step of filling the reference feature value to the feature value missing position according to the filling method to obtain a new data list further includes:

[0027] When the filling mode is a passive filling mode, obtaining an editing instruction corresponding to the passive filling mode;

[0028] Edit the reference characteristic value according to the editing instruction to obtain an edited reference characteristic value;

[0029] The edited reference eigenvalues ​​are filled into the missing positions of the eigenvalues ​​to obtain a new data list.

[0030] A data processing device, comprising:

[0031] A data list acquisition module is used to acquire a data list, wherein the data list includes characteristic parameters;

[0032] A reference parameter acquisition module, used for acquiring a reference parameter corresponding to the characteristic parameter when a characteristic value of the characteristic parameter in the data list is missing;

[0033] A feature value missing position acquisition module is used to extract the reference feature value in the reference parameter, obtain the positioning information of the feature parameter, and find the feature value missing position in the feature parameter according to the positioning information;

[0034] A feature value filling module, used for obtaining a filling method according to the missing position of the feature value, and filling the reference feature value into the missing position of the feature value according to the filling method to obtain a new data list;

[0035] The parameter execution module is used to execute the characteristic parameters in the new data list to obtain target data, and the target data is used for product prediction.

[0036] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0037] Obtaining a data list, wherein the data list includes characteristic parameters;

[0038] When a characteristic parameter in the data list has a missing characteristic value, obtaining a reference parameter corresponding to the characteristic parameter;

[0039] Extracting reference characteristic values ​​from the reference parameters, obtaining location information of the characteristic parameters, and searching for missing locations of characteristic values ​​in the characteristic parameters according to the location information;

[0040] Acquire a filling method according to the missing position of the eigenvalue, and fill the missing position of the eigenvalue with the reference eigenvalue according to the filling method to obtain a new data list;

[0041] The characteristic parameters in the new data list are executed to obtain target data, where the target data is used for product prediction.

[0042] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0043] Obtaining a data list, wherein the data list includes characteristic parameters;

[0044] When a characteristic parameter in the data list has a missing characteristic value, obtaining a reference parameter corresponding to the characteristic parameter;

[0045] Extracting reference characteristic values ​​from the reference parameters, obtaining location information of the characteristic parameters, and searching for missing locations of characteristic values ​​in the characteristic parameters according to the location information;

[0046] Acquire a filling method according to the missing position of the eigenvalue, and fill the missing position of the eigenvalue with the reference eigenvalue according to the filling method to obtain a new data list;

[0047] The characteristic parameters in the new data list are executed to obtain target data, where the target data is used for product prediction.

[0048] The above-mentioned data processing method, device, computer equipment and storage medium obtain a data list, the data list contains characteristic parameters, when the characteristic parameters in the data list have missing characteristic values, obtain reference parameters corresponding to the characteristic parameters, extract reference characteristic values ​​in the reference parameters, and obtain positioning information of the characteristic parameters, find the missing position of the characteristic value in the characteristic parameters according to the positioning information, obtain a filling method according to the missing position of the characteristic value, and fill the reference characteristic value to the missing position of the characteristic value according to the filling method to obtain a new data list, execute the characteristic parameters in the new data list to obtain target data, and the target data is used for product prediction. By filling the characteristic parameters with missing characteristic values ​​to obtain a new data list, since the characteristic parameters with missing characteristic values ​​are filled, the efficiency of data processing can be improved when data processing is performed according to the characteristic parameters without missing characteristic values. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 An application scenario diagram of a data processing method in an embodiment;

[0050] Figure 2 is a flow chart of a data processing method in one embodiment;

[0051] Figure 3 is a structural block diagram of a data processing device in one embodiment;

[0052] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0054] The data processing method provided in this application can be applied to Figure 1 In the application environment shown. The application environment includes a computer device 110. The computer device 110 can obtain a data list, and the data list contains characteristic parameters. When there is a missing characteristic value in the characteristic parameter in the data list, the computer device 110 can obtain a reference parameter corresponding to the characteristic parameter. The computer device 110 can extract the reference characteristic value in the reference parameter, and obtain the positioning information of the characteristic parameter, and find the missing position of the characteristic value in the characteristic parameter according to the positioning information. The computer device 110 can obtain a filling method according to the missing position of the characteristic value, and fill the reference characteristic value to the missing position of the characteristic value according to the filling method to obtain a new data list. The computer device 110 can execute the characteristic parameters in the new data list to obtain target data, and the target data can be used for product prediction. Among them, the computer device 110 can be but not limited to various personal computers, laptops, smart phones, tablet computers and other devices.

[0055] In one embodiment, Figure 2 As shown, a data processing method is provided, comprising the following steps:

[0056] Step 202, obtaining a data list, wherein the data list includes characteristic parameters.

[0057] A computer device may store multiple data lists. The data list may be obtained from a database, or may be a data list selected by a user through a computer device. The data list may contain multiple feature parameters, and the feature parameters may contain feature labels and feature values. Among them, feature labels may be labels such as name, age, and telephone number; feature values ​​may correspond to feature labels one by one, for example, when the feature label is age, the corresponding feature value may be 20 years old. Feature labels and feature values ​​may constitute feature parameters, for example, the feature parameter may be age 20 years old.

[0058] Step 204: when there is a missing characteristic value in a characteristic parameter in the data list, obtain a reference parameter corresponding to the characteristic parameter.

[0059] There may be multiple feature parameters in the data list. After obtaining the data list, the computer device may verify each feature parameter in the data list respectively, so as to determine whether there are feature parameters with missing feature values ​​in the data list. Missing feature values ​​means that the feature label in the feature parameter does not have a corresponding feature value. For example, when the feature parameter is age, it means that the feature parameter only contains a feature label but no feature value, that is, there is a missing feature value. The reference parameter contains a reference feature label and a reference feature value. When the reference feature label in the reference parameter does not have a corresponding reference feature value, the reference parameter stores a missing feature value.

[0060] The reference parameters may be stored in a database, and the feature parameters corresponding to the reference parameters means that the feature tags in the feature parameters correspond to the reference feature tags in the reference parameters.

[0061] When a characteristic parameter has a missing characteristic value, the computer device can search for a reference parameter corresponding to the characteristic parameter in the database. Specifically, the computer device can search for a reference parameter in the database where the corresponding reference characteristic tag is located according to the characteristic tag in the characteristic parameter. For example, if the characteristic parameter obtained by the computer device is age and there is a missing characteristic value, the computer device can search for a reference parameter in the database whose reference characteristic tag is age.

[0062] Step 206: extract the reference characteristic value in the reference parameter, obtain the positioning information of the characteristic parameter, and search for the missing position of the characteristic value in the characteristic parameter according to the positioning information.

[0063] After the computer device finds the reference parameter corresponding to the characteristic parameter, it can extract the reference characteristic value in the reference parameter. For example, the reference parameter found by the computer device is the age of 20 years old, and the computer device can extract the reference characteristic value of 20 years old. The positioning information of the characteristic parameter can be used to locate the position where the characteristic value is missing in the characteristic parameter. The positioning information of the characteristic parameter can be a file path, or it can be information such as a characteristic identifier corresponding to the characteristic parameter, which is not limited here. The computer device can find the position where the characteristic value is missing in the characteristic parameter based on the acquired positioning information of the characteristic parameter.

[0064] Step 208, obtaining a filling method according to the missing position of the eigenvalue, and filling the missing position of the eigenvalue with the reference eigenvalue according to the filling method to obtain a new data list.

[0065] The new data list may store feature parameters that do not have missing feature values. When the feature parameters acquired by the computer device do not have missing feature values, the computer device may use the acquired data list as a new data list. Specifically, the filling method of the feature value may include filling with a default value, a mean, and a mode, and the computer device may store a pre-set filling method. Different missing feature value positions may correspond to different filling methods.

[0066] The computer device can fill the extracted reference feature value into the missing feature value position according to the obtained filling method. Specifically, the computer device can use the extracted reference feature value as the feature value of the feature parameter to fill the missing feature value position. After the computer device fills the feature parameter with the feature value, a new data list can be obtained.

[0067] Step 210, executing the characteristic parameters in the new data list to obtain target data, the target data is used for product prediction.

[0068] After the computer device fills in the feature parameters with missing feature values, the feature parameters in the new data list obtained are all feature parameters without missing feature values. The computer device can execute the feature parameters in the new data list. Specifically, the computer device can input the feature tree in the data list into the prediction model to obtain the target data. The computer device can obtain the prediction result of the product according to the target data.

[0069] In this embodiment, the computer device uses a data list, which contains characteristic parameters. When there is a missing characteristic value in the characteristic parameter in the data list, the reference parameter corresponding to the characteristic parameter is obtained, the reference characteristic value in the reference parameter is extracted, and the positioning information of the characteristic parameter is obtained. The missing position of the characteristic value in the characteristic parameter is found according to the positioning information, and the filling method is obtained according to the missing position of the characteristic value, and the reference characteristic value is filled into the missing position of the characteristic value according to the filling method to obtain a new data list, and the characteristic parameters in the new data list are executed to obtain target data, and the target data is used for product prediction. By filling the characteristic parameters with missing characteristic values ​​to obtain a new data list, since the characteristic parameters with missing characteristic values ​​are filled, the efficiency of data processing can be improved when data processing is performed according to the characteristic parameters without missing characteristic values.

[0070] In one embodiment, a data processing method provided may also include a process of obtaining location information of feature parameters, specifically including: extracting keywords in the feature parameters; obtaining a keyword list, the keyword list being used to record the correspondence between the keywords and the keyword location information; searching for keyword location information corresponding to the keywords according to the keyword list; and generating location information of the feature parameters according to the keyword location information.

[0071] The feature parameter may include a keyword, wherein the keyword included in the feature parameter may be a feature tag. For example, when the feature parameter is age 20 years old, the keyword included may be age; when the feature parameter is name Zhang San, the keyword included may be name.

[0072] The keyword list may record the correspondence between the keyword and the keyword position information, and the keyword list may be stored in a computer device. The keyword position information may be used to indicate the storage path of the keyword, and each keyword may correspond to a unique keyword position information.

[0073] After obtaining the characteristic parameters, the computer device can extract the keywords in the characteristic parameters. For example, if the characteristic parameter obtained by the computer device is age 20, the computer device can further extract the keyword in the characteristic parameters as age. The computer device can obtain a stored keyword list, search for keywords in the keyword list, and then obtain the keyword position information according to the correspondence between the keywords recorded in the keyword list and the keyword position information.

[0074] The keyword location information can be used to indicate the storage path of the keyword, and the keyword is in the feature parameter, that is, as long as the storage path of the keyword is found, the storage path of the feature parameter can be found, and then the feature parameter can be found. The computer device can further find the storage path of the feature parameter based on the acquired keyword location information, and the computer device can generate the location information of the feature parameter based on the storage path of the feature parameter, so as to find the feature parameter based on the location information of the feature parameter.

[0075] In this embodiment, the computer device extracts keywords from the feature parameters to obtain a keyword list, the keyword list is used to record the correspondence between the keywords and the keyword position information, and the keyword position information corresponding to the keywords is searched according to the keyword list, and the location information of the feature parameters is generated according to the keyword position information. Since the correspondence between the keywords and the keyword position information is recorded in the keyword list, the computer device can obtain the keyword position information according to the extracted keywords, and then generate the location information of the feature parameters, which can improve the accuracy of the generated location information of the feature parameters.

[0076] In one embodiment, a data processing method provided may also include a process of determining whether a characteristic value is missing, specifically including: obtaining an input first characteristic value corresponding to a characteristic parameter; searching for the characteristic parameter in a database, and obtaining a second characteristic value corresponding to the characteristic parameter from the database; when the first characteristic value is different from the second characteristic value, there is a missing characteristic value in the characteristic parameter.

[0077] There are many cases of missing feature values. Most of them are because users did not enter relevant information when registering, or because new feature parameters were introduced due to system upgrades, resulting in the new feature parameters not matching the feature parameters in the encoder, thus causing the missing feature values.

[0078] The first characteristic value may be a characteristic value in a characteristic parameter acquired by a computer device; the second characteristic value may be a characteristic value in a characteristic parameter stored in the computer device. The first characteristic value may be input by a user through a computer device. When the user does not input the first characteristic value through the computer device, the first characteristic value may be none. The database may be used to store characteristic parameters and second characteristic values ​​corresponding to the characteristic parameters. The characteristic parameters and second characteristic values ​​stored in the database may be pre-input.

[0079] The computer device can determine whether there is a missing characteristic value. Specifically, the computer device can obtain the first characteristic value in the input characteristic parameter, and the computer device can search the characteristic parameter in the database, so as to obtain the second characteristic value corresponding to the characteristic parameter in the database. The computer device can compare the obtained first characteristic value with the obtained second characteristic value to obtain a comparison result. When the comparison result obtained by the computer device is that the first characteristic value is different from the second characteristic value, it indicates that there is a missing characteristic value in the characteristic parameter. Among them, when the first characteristic value is none, the computer device cannot match the second characteristic value that is the same as the first characteristic value in the database, that is, there is a missing characteristic value in the characteristic parameter.

[0080] When there are multiple characteristic parameters obtained, the computer device can respectively obtain the first characteristic value corresponding to each characteristic parameter. At the same time, the computer device can respectively obtain the second characteristic value corresponding to each characteristic parameter from the database, and then compare the first characteristic value and the second characteristic value respectively, so as to obtain the result of whether there are missing characteristic values ​​for each characteristic parameter.

[0081] In this embodiment, the computer device obtains the input first characteristic value corresponding to the characteristic parameter, searches for the characteristic parameter in the database, and obtains the second characteristic value corresponding to the characteristic parameter from the database. When the first characteristic value is different from the second characteristic value, the characteristic parameter has a missing characteristic value. When using the characteristic parameter and the prediction model for data prediction, if the characteristic parameter has a missing characteristic value, it will seriously affect the data prediction result of the prediction model. The computer device compares the input first characteristic value with the stored second characteristic value to determine whether the characteristic parameter has a missing characteristic value, which can avoid the situation where the characteristic parameter used for execution has a missing characteristic value, thereby improving the accuracy of data processing.

[0082] In one embodiment, a data processing method provided may also include a process of determining a position where a feature value is missing, specifically including: obtaining a feature parameter identifier in the positioning information, and searching for feature parameters based on the feature parameter identifier; obtaining a feature value position corresponding to the feature parameter, and determining a position where the feature value is missing based on the feature value position.

[0083] The characteristic parameter identifier can be used to distinguish different characteristic parameters. The characteristic parameter identifier can be represented by numbers, letters, or characters, which are not limited here. After obtaining the location information of the characteristic parameter, the computer device can obtain the characteristic parameter identifier from the location information, and then find the characteristic parameter according to the characteristic parameter identifier.

[0084] Since the characteristic parameter includes a characteristic label and a characteristic value, the computer device finds the characteristic parameter with a missing characteristic value according to the characteristic parameter identifier. After finding the characteristic parameter, the computer device can obtain the characteristic value position when the characteristic value exists in the characteristic parameter, and the computer device can use the found characteristic value position as the characteristic value missing position.

[0085] In this embodiment, the computer device obtains the characteristic parameter identifier in the positioning information, searches for the characteristic parameter according to the characteristic parameter identifier, obtains the characteristic value position corresponding to the characteristic parameter, and determines the characteristic value missing position according to the characteristic value position. The computer device searches for the corresponding characteristic value position according to the characteristic parameter identifier, and then determines the characteristic value missing position, thereby improving the accuracy of the found characteristic value missing position.

[0086] In one embodiment, a data processing method provided may also include a process of configuring reference characteristic values ​​for reference parameters, specifically including: obtaining data configuration instructions; wherein the data configuration instructions are used to configure reference characteristic values ​​for reference parameters; obtaining input reference characteristic values, and searching for reference parameters according to the data configuration instructions; establishing a correspondence between reference characteristic values ​​and reference parameters, and configuring reference characteristic values ​​for reference parameters according to the correspondence.

[0087] The computer device may configure a reference characteristic value for a reference parameter. Specifically, the computer device may detect a data configuration instruction, wherein the data configuration instruction is used to configure a reference characteristic value for a reference parameter. The data configuration instruction may be generated by a user through a computer device, for example, a user may click a control in a computer device interface to trigger the generation of a data configuration instruction, or a user may press a button in a computer device to generate a data configuration instruction. The data configuration instruction may include a reference parameter identifier, which may be used to distinguish different reference parameters.

[0088] After the computer device obtains the data configuration instruction, it can display the characteristic value configuration interface. The computer device can obtain the input reference characteristic value through the characteristic value configuration interface. The computer device can extract the reference parameter identifier in the data configuration instruction, and find the reference characteristic tag in the reference parameter according to the extracted reference parameter identifier. The computer device can establish a corresponding relationship between the obtained reference characteristic value and the found reference parameter. For example, the reference characteristic tag found by the computer device according to the reference parameter identifier contained in the data configuration instruction is age, and the input reference characteristic value obtained by the computer device is 20 years old. The computer device can establish a corresponding relationship between age and 20 years old. The computer device can configure the obtained input reference characteristic value to the found reference parameter according to the established corresponding relationship.

[0089] In this embodiment, the computer device obtains a data configuration instruction, wherein the data configuration instruction is used to configure a reference characteristic value for a reference parameter, obtains an input reference characteristic value, searches for the reference parameter according to the data configuration instruction, establishes a corresponding relationship between the reference characteristic value and the reference parameter, and configures the reference characteristic value for the reference parameter according to the corresponding relationship. The computer device configures the reference characteristic value for the reference parameter by establishing a corresponding relationship between the reference characteristic value and the reference parameter, and when filling the characteristic value of the characteristic parameter, the reference characteristic value to be filled can be quickly found, thereby improving the efficiency of filling the characteristic value.

[0090] In one embodiment, a data processing method provided may also include a process of extracting parameter characteristic values ​​from reference parameters, specifically including: searching for reference characteristic values ​​corresponding to the reference parameters according to a corresponding relationship; and extracting the reference characteristic values ​​from the reference parameters when the reference parameters are configured with reference characteristic values.

[0091] After obtaining the reference parameter corresponding to the characteristic parameter, the computer device can determine whether the reference parameter has a missing characteristic value, that is, whether the reference parameter contains a reference characteristic value. The reference parameter may be configured with a corresponding reference characteristic value or may not be configured with a corresponding reference characteristic value. When the reference parameter is not configured with a corresponding reference characteristic value, the reference parameter has a missing characteristic value. When the reference parameter has a missing characteristic value, the reference characteristic value corresponding to the reference parameter is none.

[0092] The computer device can find the reference characteristic value corresponding to the reference parameter according to the corresponding relationship between the reference parameter and the reference characteristic value. The computer device can determine whether the reference characteristic value corresponding to the reference parameter found is not absent. When the judgment result obtained by the computer device is that the reference characteristic value corresponding to the reference parameter is not absent, it means that the reference parameter is configured with a reference characteristic value, and the computer device can extract the reference characteristic value from the reference parameter. For example, the reference parameter obtained by the computer device is age 20 years old. The computer device can determine that the reference characteristic value in the reference parameter is age 20 years old is 20 years old, that is, the reference parameter is configured with a reference characteristic value, and the computer device can extract the reference characteristic value in the reference parameter is age 20 years old as 20 years old.

[0093] In this embodiment, the computer device searches for the reference characteristic value corresponding to the reference parameter according to the corresponding relationship, and extracts the reference characteristic value in the reference parameter when the reference parameter is configured with the reference characteristic value. The computer device extracts the reference characteristic value in the reference parameter according to the corresponding relationship, and since the corresponding relationship is a pre-established corresponding relationship between the reference parameter and the reference characteristic value, the accuracy of the extracted reference characteristic value can be improved.

[0094] In one embodiment, a data processing method provided may also include a process of searching for missing feature values. The computer device may obtain the feature category corresponding to the feature parameter, and search for the corresponding encoder according to the feature category, thereby obtaining the missing feature value. Specifically, the computer device may extract the feature identifier in the feature parameter, and the feature identifier may be used to distinguish different feature categories. The computer device may search for the feature category corresponding to the feature parameter according to the feature identifier. The computer device may search for the encoder corresponding to the feature category, and find the missing feature value from the encoder. The feature category may be divided into user features, product features, and context features, etc., and the computer device may find the corresponding feature category according to the feature identifier. For example, the computer device may extract the parameter ftype in the filled feature parameter, and the parameter ftype may be used to identify the feature category. The value range of ftype is 0, 1, 2. The computer device may identify the feature category according to the number ftype, where 0 represents user features, 1 represents product features, and 2 represents context features.

[0095] In this embodiment, the computer device can obtain the feature category corresponding to the feature parameter by extracting the feature identifier in the filled feature parameter, and find the corresponding encoder according to the feature category, thereby finding the missing feature value, which can improve the efficiency of finding the missing feature value.

[0096] In one embodiment, the computer device may store predefined dimensions of feature parameters and feature types of feature parameters. Specifically, the computer device may obtain configuration information for feature parameters input by the user, wherein the configuration information may include the dimensions of feature parameters and feature types of feature parameters. The computer device may generate a configuration file based on the input configuration information, and the computer device may write the generated configuration file into the encoder. Among them, the dimension of the feature parameter may be the length corresponding to the feature parameter, for example, the dimension corresponding to the age feature may be 1, and for another example, when 10 product feature parameters are clicked, the dimension of the product feature parameter is 10. Among them, the feature type may be a data type, and the data type may be divided into a floating point data type float, a double-precision floating point type double, a signed integer type int, a string type string, a Boolean type bool, and the like.

[0097] In one embodiment, a data processing method provided may also include a process of obtaining a filling method, specifically including: obtaining selection information corresponding to a missing position of a feature value, the selection information being divided into first selection information and second selection information; when the selection information is the first selection information, obtaining a filling method for automatic filling; when the selection information is the second selection information, obtaining a filling method for passive filling.

[0098] The selection information may be generated by the user triggering a selection button or a selection control in the computer device. The selection information may be divided into first selection information and second selection information, wherein the first selection information may be used to indicate the information of the automatic filling method selected by the user by triggering the computer device; the second selection information may be used to indicate the information of the passive filling method selected by the user by triggering the computer device. The selection information corresponding to different feature value missing positions may be different.

[0099] The computer device can obtain the corresponding selection information according to the missing position of the characteristic value, and judge the obtained selection information to obtain a judgment result. When the judgment result obtained by the computer device is that the selection information is the first selection information, the computer device can obtain the filling method of automatic filling; when the judgment result obtained by the computer device is that the selection information is the second selection information, the computer device can obtain the filling method of passive filling.

[0100] In this embodiment, the computer device obtains the selection information corresponding to the missing position of the feature value, and the selection information is divided into the first selection information and the second selection information. When the selection information is the first selection information, the automatic filling method is obtained, and when the selection information is the second selection information, the passive filling method is obtained. The computer device obtains the filling method according to the selection information corresponding to the missing position of the feature value, which can improve the accuracy of the obtained filling method.

[0101] In one embodiment, a data processing method provided may further include a process of obtaining a new data list, specifically including: when the filling mode is an automatic filling mode, automatically copying the reference feature value to the feature value missing position to obtain a new data list.

[0102] When the filling mode obtained by the computer device is the automatic filling mode, the computer device can automatically copy the reference characteristic value to the position where the characteristic value is missing, thereby obtaining a new data list, wherein the characteristic parameters in the new data list are all characteristic parameters without missing characteristic values.

[0103] In this embodiment, the computer device improves the efficiency of feature value filling by automatically copying the reference feature value to the feature value missing position.

[0104] In another embodiment, a data processing method provided may also include a process of obtaining a new data list, specifically including: when the filling method is a passive filling method, obtaining an editing instruction corresponding to the passive filling method; editing the reference feature value according to the editing instruction to obtain an edited reference feature value; filling the edited reference feature value to the missing position of the feature value to obtain a new data list.

[0105] The editing instruction can be used to edit the reference characteristic value. The editing instruction can be generated when the computer device detects that the filling mode is a passive filling mode, or can be generated by the user triggering the computer device.

[0106] When the filling method obtained by the computer device is a passive filling method, the computer device can obtain an editing instruction corresponding to the passive filling method. The computer device can parse the editing instruction, thereby editing the reference characteristic value according to the parsing result. For example, the editing instruction parsed by the computer device is to modify the reference characteristic value, and the computer device can modify the reference characteristic value to obtain a modified reference characteristic value. The computer device can fill the edited reference characteristic value into the missing position of the characteristic value, thereby obtaining a new data list.

[0107] It should be understood that although Figure 2 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0108] In one embodiment, Figure 3 As shown, a data processing device is provided, including: a data list acquisition module 310, a reference parameter acquisition module 320, a feature value missing position acquisition module 330, a feature value filling module 340 and a parameter execution module 350, wherein:

[0109] The data list module 310 is used to obtain a data list, and the data list includes characteristic parameters.

[0110] The reference parameter acquisition module 320 is used to acquire the reference parameter corresponding to the characteristic parameter when there is a missing characteristic value of the characteristic parameter in the data list.

[0111] The feature value missing position acquisition module 330 is used to extract the reference feature value in the reference parameter, obtain the positioning information of the feature parameter, and find the feature value missing position in the feature parameter according to the positioning information.

[0112] The eigenvalue filling module 340 is used to obtain a filling method according to the missing position of the eigenvalue, and fill the reference eigenvalue to the missing position of the eigenvalue according to the filling method to obtain a new data list.

[0113] The parameter execution module 350 is used to execute the characteristic parameters in the new data list to obtain target data, and the target data is used for product prediction.

[0114] In one embodiment, the feature value missing position acquisition module 330 is also used to extract keywords in the feature parameters; obtain a keyword list, the keyword list is used to record the correspondence between the keywords and the keyword position information; according to the keyword list, search for the keyword position information corresponding to the keywords; and generate the positioning information of the feature parameters according to the keyword position information.

[0115] In one implementation, the feature value missing position acquisition module 330 is also used to obtain the feature parameter identifier in the positioning information, and search for the feature parameter according to the feature parameter identifier; obtain the feature value position corresponding to the feature parameter, and determine the feature value missing position according to the feature value position.

[0116] In one embodiment, the feature value filling module 340 is also used to obtain selection information corresponding to the missing position of the feature value, and the selection information is divided into first selection information and second selection information; when the selection information is the first selection information, the automatic filling method is obtained; when the selection information is the second selection information, the passive filling method is obtained.

[0117] In one embodiment, the feature value filling module 340 is further used to automatically copy the reference feature value to the feature value missing position to obtain a new data list when the filling mode is the automatic filling mode.

[0118] In one embodiment, the feature value filling module 340 is also used to obtain the editing instructions corresponding to the passive filling method when the filling method is a passive filling method; edit the reference feature value according to the editing instruction to obtain the edited reference feature value; fill the edited reference feature value to the missing position of the feature value to obtain a new data list.

[0119] For the specific definition of the data prediction device, please refer to the definition of the data prediction method above, which will not be repeated here. Each module in the above-mentioned data prediction device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0120] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a data prediction method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0121] Those skilled in the art will understand that Figure 4The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0122] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0123] Get the data list, which contains characteristic parameters;

[0124] When there is a missing characteristic value for a characteristic parameter in the data list, obtain a reference parameter corresponding to the characteristic parameter;

[0125] Extracting reference characteristic values ​​from the reference parameters, obtaining location information of the characteristic parameters, and finding the missing position of the characteristic values ​​in the characteristic parameters according to the location information;

[0126] Obtain a filling method according to the missing position of the eigenvalue, and fill the reference eigenvalue to the missing position of the eigenvalue according to the filling method to obtain a new data list;

[0127] Execute the feature parameters in the new data list to obtain the target data, which is used for product prediction.

[0128] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0129] Get the data list, which contains characteristic parameters;

[0130] When there is a missing characteristic value for a characteristic parameter in the data list, obtain a reference parameter corresponding to the characteristic parameter;

[0131] Extracting reference characteristic values ​​from the reference parameters, obtaining location information of the characteristic parameters, and finding the missing position of the characteristic values ​​in the characteristic parameters according to the location information;

[0132] Obtain a filling method according to the missing position of the eigenvalue, and fill the reference eigenvalue to the missing position of the eigenvalue according to the filling method to obtain a new data list;

[0133] Execute the feature parameters in the new data list to obtain the target data, which is used for product prediction.

[0134] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database 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. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0135] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, 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.

[0136] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A data processing method, the method comprising: Obtaining a data list, wherein the data list includes characteristic parameters; Obtaining an input first characteristic value corresponding to the characteristic parameter, obtaining a second characteristic value corresponding to the characteristic parameter from a database, when the first characteristic value is different from the second characteristic value, there is a missing characteristic value of the characteristic parameter in the data list, and obtaining a reference parameter corresponding to the characteristic parameter; Extracting reference feature values ​​from the reference parameters, and extracting keywords from the feature parameters; Obtaining a keyword list, wherein the keyword list is used to record the corresponding relationship between the keywords and the keyword position information; According to the keyword list, searching for keyword location information corresponding to the keyword, wherein the keyword location information indicates a storage path of the keyword; Searching for a storage path of the characteristic parameter according to the keyword position information, and generating location information of the characteristic parameter according to the storage path of the characteristic parameter; Finding a missing position of a characteristic value in the characteristic parameter according to the positioning information; Acquire a filling method according to the selection information corresponding to the missing position of the eigenvalue, and fill the reference eigenvalue to the missing position of the eigenvalue according to the filling method to obtain a new data list; The characteristic parameters in the new data list are executed to obtain target data, where the target data is used for product prediction.

2. The method according to claim 1, characterized in that The executing the characteristic parameters in the new data list to obtain target data, wherein the target data is used for product prediction, comprises: Inputting the characteristic parameters in the new data list into the prediction model to obtain target data; A prediction result for the product is obtained according to the target data.

3. The method according to claim 1, characterized in that The positioning information includes a characteristic parameter identifier, and the characteristic parameter identifier is used to distinguish different characteristic parameters; The searching for a missing position of a characteristic value in the characteristic parameter according to the positioning information includes: Obtaining a characteristic parameter identifier in the positioning information, and searching for a characteristic parameter according to the characteristic parameter identifier; Acquire a feature value position corresponding to the feature parameter, and determine the feature value missing position according to the feature value position.

4. The method according to claim 1, characterized in that The obtaining of a filling method according to the missing position of the characteristic value includes: Acquire selection information corresponding to the missing position of the feature value, wherein the selection information is divided into first selection information and second selection information; When the selection information is the first selection information, obtaining an automatic filling method; When the selection information is the second selection information, a passive filling method is acquired.

5. The method according to claim 4, characterized in that The step of filling the reference characteristic value to the characteristic value missing position according to the filling method to obtain a new data list includes: When the filling mode is an automatic filling mode, the reference characteristic value is automatically copied to the position where the characteristic value is missing to obtain a new data list.

6. The method according to claim 4, characterized in that The step of filling the reference characteristic value to the characteristic value missing position according to the filling method to obtain a new data list also includes: When the filling mode is a passive filling mode, obtaining an editing instruction corresponding to the passive filling mode; Edit the reference characteristic value according to the editing instruction to obtain an edited reference characteristic value; The edited reference eigenvalues ​​are filled into the missing positions of the eigenvalues ​​to obtain a new data list.

7. A data processing device, characterized in that: The device comprises: A data list acquisition module is used to acquire a data list, wherein the data list includes characteristic parameters; A reference parameter acquisition module, used to acquire an input first characteristic value corresponding to the characteristic parameter, acquire a second characteristic value corresponding to the characteristic parameter from a database, and when the first characteristic value is different from the second characteristic value, there is a missing characteristic value of the characteristic parameter in the data list, and acquire a reference parameter corresponding to the characteristic parameter; A feature value missing position acquisition module, used to extract reference feature values ​​in the reference parameters and to extract keywords in the feature parameters; Obtaining a keyword list, wherein the keyword list is used to record the corresponding relationship between the keywords and the keyword position information; According to the keyword list, searching for keyword location information corresponding to the keyword, wherein the keyword location information indicates a storage path of the keyword; Searching for a storage path of the characteristic parameter according to the keyword position information, and generating location information of the characteristic parameter according to the storage path of the characteristic parameter; Finding a missing position of a characteristic value in the characteristic parameter according to the positioning information; A feature value filling module, used for obtaining a filling method according to the selection information corresponding to the feature value missing position, and filling the reference feature value into the feature value missing position according to the filling method to obtain a new data list; The parameter execution module is used to execute the characteristic parameters in the new data list to obtain target data, and the target data is used for product prediction.

8. The device according to claim 7, characterized in that The feature value missing position acquisition module is also used to extract keywords in the feature parameters; obtain a keyword list, which is used to record the correspondence between keywords and keyword position information; according to the keyword list, search for keyword position information corresponding to the keyword; and generate the positioning information of the feature parameters according to the keyword position information.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

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