Data analysis method and device, equipment and storage medium

Abstract

The invention is suitable for the technical field of data analysis, and provides a data analysis method, device and equipment and a storage medium, and the method comprises the following steps: carrying out feature variable extraction on each case in a database; inputting the feature variables into a variable attribute library for matching, determining a feature attribute corresponding to each feature variable, and obtaining feature information of each case according to a plurality of feature attributes; classifying all the feature information based on the action result, analyzing the feature information in each class, and determining action portrait information of each class; and receiving a feature attribute screening instruction input by a user, retaining feature information meeting conditions, and analyzing the retained feature information to obtain action prediction and intervention information. According to the invention, internal relations and potential laws between cases can be revealed, action portrait information is determined, and working personnel can make more accurate and effective strategies for different types of actions.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a data analysis method, device, equipment and storage medium. Background Art

[0002] In current legal practice, data processing and analysis of legal cases mostly rely on traditional manual review and statistical methods, which are particularly inefficient and error-prone when processing massive amounts of data. Databases related to legal cases contain a large amount of case information, which covers a number of aspects, such as the personal background, motivation, means, and results of actions of specific people. This information is of great significance for understanding action patterns, predicting action trends, and formulating effective action intervention strategies. However, existing data processing methods can often only perform simple classification and statistics on cases, and it is difficult to deeply explore the internal connections and potential laws between cases. In addition, due to the large amount of data, manual analysis is not only time-consuming and laborious, but also prone to missing key information, resulting in inaccurate and incomplete analysis results. At the same time, most existing analysis methods lack personalized action portrait construction, and cannot provide targeted predictions and intervention suggestions for different types of actions. Therefore, it is necessary to provide a data analysis method, device, equipment, and storage medium to solve the above problems. Summary of the invention

[0003] In view of the deficiencies in the prior art, the object of the present invention is to provide a data analysis method, device, equipment and storage medium to solve the problems existing in the above-mentioned background technology.

[0004] The present invention is implemented in a data analysis method, the method comprising the following steps:

[0005] Extract characteristic variables from each case in the database, including specific person's personality, gender, age, education, living environment, action motivation, action means and action results;

[0006] Input the characteristic variables into the variable attribute library for matching, determine the characteristic attributes corresponding to each characteristic variable, and obtain the characteristic information of each case based on several characteristic attributes;

[0007] Classify all feature information based on the action results, analyze the feature information in each category, and determine the action profile information of each category;

[0008] Receive the feature attribute screening instructions input by the user, retain the feature information that meets the conditions, analyze the retained feature information, and obtain action prediction and intervention information.

[0009] As a further solution of the present invention: the step of extracting characteristic variables for each case in the database specifically includes:

[0010] The database is used to obtain basic information, action records, family background, economic status and social relations of specific people in each case;

[0011] The basic information is extracted to obtain gender, age and education level, and the action records are extracted to obtain action motivation, action means and action results;

[0012] Integrate family background, economic status and social relations to obtain living environment;

[0013] Extract the character description sentences and the specific character behavior description sentences, analyze the character description sentences and the specific character behavior description sentences, and obtain the specific character personality.

[0014] As a further solution of the present invention: the step of inputting the feature variables into the variable attribute library for matching and determining the feature attributes corresponding to each feature variable specifically includes:

[0015] Input the specific content of the feature variable into the corresponding description area in the variable attribute library for text matching. Each description area corresponds to a feature attribute.

[0016] Determine the description area with the highest matching degree with the feature variable, and output the feature attribute corresponding to the description area.

[0017] As a further solution of the present invention: the step of analyzing the characteristic information in each category to determine the action portrait information of each category specifically includes:

[0018] Analyze all feature information in each category and calculate the proportion of each feature attribute in each feature variable;

[0019] Arrange each characteristic attribute in each characteristic variable in descending order according to the proportion value, analyze the characteristic attributes in each arrangement, and determine the action profile attributes;

[0020] All action portrait attributes are summarized to obtain action portrait information of each category.

[0021] As a further solution of the present invention: the step of analyzing the characteristic attributes in each arrangement to determine the action portrait attributes specifically includes:

[0022] The proportion values ​​corresponding to the characteristic attributes in the arrangement are accumulated one by one in order. After each accumulation, the accumulated value is calculated until the accumulated value is greater than the proportion threshold, and then the accumulation stops;

[0023] Retrieve the feature attributes involved in the accumulation and the corresponding proportion values, and determine whether the difference between two adjacent proportion values ​​is greater than a preset proportion interval;

[0024] When it does not exist, all retrieved feature attributes are determined to be action portrait attributes; when it exists, the feature attribute corresponding to the largest proportion value among the differences in the proportion values ​​is determined, and the feature attribute and the feature attributes before the arrangement are determined to be action portrait attributes.

[0025] As a further solution of the present invention: the step of analyzing the retained feature information to obtain action prediction and intervention information specifically includes:

[0026] Partially delete characteristic variables in the retained characteristic information based on the characteristic attribute screening instruction, and update the retained characteristic information;

[0027] Obtaining potential profile information based on the updated feature information, and determining action prediction information based on the action results in the potential profile information;

[0028] Action intervention information is generated based on the specific character, living environment, action motivation and action means in the potential portrait information to obtain action prediction and intervention information.

[0029] Another object of the present invention is to provide a data analysis device, the device comprising:

[0030] A feature variable extraction module is used to extract feature variables from each case in the database. The feature variables include a specific person's personality, gender, age, education, living environment, action motivation, action means and action results;

[0031] The feature information determination module is used to input the feature variables into the variable attribute library for matching, determine the feature attributes corresponding to each feature variable, and obtain the feature information of each case based on a number of feature attributes;

[0032] The action profile information module is used to classify all feature information based on the action results, analyze the feature information in each category, and determine the action profile information of each category;

[0033] The action prediction and intervention module is used to receive the feature attribute screening instructions input by the user, retain the feature information that meets the conditions, analyze the retained feature information, and obtain action prediction and intervention information.

[0034] As a further solution of the present invention: the feature variable extraction module includes:

[0035] A relevant information extraction unit, used to obtain basic information, action records, family background, economic status and social relations of specific persons in each case through the database;

[0036] An action record extraction unit is used to extract features from basic information to obtain gender, age and education level, and to extract features from action records to obtain action motivations, action means and action results;

[0037] The living environment determination unit is used to integrate family background, economic status and social relations to obtain the living environment;

[0038] The specific character determination unit is used to extract character description sentences and specific character behavior description sentences, analyze the character description sentences and specific character behavior description sentences, and obtain the specific character character.

[0039] The present invention also aims to provide a computer device, comprising a memory, a processor, and a computer device program stored in the memory and executable on the processor, wherein the processor implements the data parsing method when executing the computer device program.

[0040] Another object of the present invention is to provide a storage medium, which includes a stored program, and when the program is running, controls the device where the storage medium is located to execute the data parsing method.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] The present invention can significantly improve the speed and accuracy of data processing by extracting characteristic variables from each case in the database, inputting the characteristic variables into the variable attribute library for matching, and determining the characteristic attributes corresponding to each characteristic variable; by obtaining the characteristic information of each case through the characteristic attributes, classifying and analyzing all the characteristic information, it can reveal the internal connection and potential laws between the cases, and determine the action portrait information of each category, which helps the staff to formulate more accurate and effective strategies for different types of actions. In addition, the characteristic information of all cases will be screened according to the characteristic attribute screening instructions to obtain action prediction and intervention information, providing a more scientific basis for action prediction and intervention. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A flowchart of a data analysis method.

[0044] Figure 2 This is a flowchart for extracting characteristic variables for each case in a data analysis method.

[0045] Figure 3 A flowchart for determining a characteristic attribute corresponding to each characteristic variable in a data analysis method.

[0046] Figure 4A flowchart for determining action profile information of each category in a data analysis method.

[0047] Figure 5 A flowchart for determining action profile attributes in a data analysis method.

[0048] Figure 6 A flowchart for obtaining action prediction and intervention information in a data analysis method.

[0049] Figure 7 The figure is a structural diagram of a data analysis device. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0051] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0052] like Figure 1 As shown, an embodiment of the present invention provides a data parsing method, the method comprising the following steps:

[0053] S100, extracting characteristic variables from each case in the database, wherein the characteristic variables include a specific person's personality, gender, age, education, living environment, action motivation, action means and action result;

[0054] S200, inputting the characteristic variables into the variable attribute library for matching, determining the characteristic attributes corresponding to each characteristic variable, and obtaining characteristic information of each case according to the plurality of characteristic attributes;

[0055] S300, classifying all feature information based on the action results, analyzing the feature information in each category, and determining action profile information of each category;

[0056] S400, receiving a feature attribute screening instruction input by a user, retaining feature information that meets the conditions, analyzing the retained feature information, and obtaining action prediction and intervention information.

[0057] It should be noted that the existing data processing methods can only perform simple classification and statistics of cases, and it is difficult to deeply explore the internal connections and potential laws between cases. At the same time, most of the existing analysis methods lack personalized action portrait construction and cannot provide targeted predictions and intervention suggestions for different types of actions. The embodiments of the present invention are intended to solve the above problems.

[0058] In the embodiment of the present invention, feature variables will be automatically extracted for each case in the database, and the feature variables include specific character, gender, age, education, living environment, action motivation, action means and action results, which can significantly improve the speed and accuracy of data processing and reduce the cost and error rate of manual review. Then the feature variables will be input into the variable attribute library for matching, and the feature attributes corresponding to each feature variable will be determined. For example, the feature attribute corresponding to the feature variable of education is primary education, secondary education or higher education, and the feature attribute corresponding to the feature variable of specific character is sanguine type, choleric type, phlegmatic type or melancholic type. The feature information of each case is obtained according to several feature attributes. Then all feature information will be classified according to the action results. The feature attributes corresponding to the action results in each category are the same. Through the classification and analysis of feature information, the internal connection and potential laws between cases can be revealed, providing a more scientific basis for action prediction and intervention, and the feature information in each category is analyzed to determine the action portrait information of each category, which helps the staff to formulate more accurate and effective strategies for different types of actions. In addition, the embodiment of the present invention also supports users to input characteristic attribute filtering instructions, which are used to determine one or more characteristic attributes. For example, the content of the characteristic attribute filtering instructions is secondary education, male, and choleric type. Then, the characteristic information of all cases will be filtered according to the characteristic attribute filtering instructions, and the characteristic information that meets the conditions will be retained. The retained characteristic information will be analyzed to obtain action prediction and intervention information, thereby improving the pertinence and effectiveness of action prediction and intervention.

[0059] like Figure 2 As shown, as a preferred embodiment of the present invention, the step of extracting characteristic variables for each case in the database specifically includes:

[0060] S101, obtain basic information, action records, family background, economic status and social relations of specific persons in each case through the database;

[0061] S102, extracting features from basic information to obtain gender, age and education level, and extracting features from action records to obtain action motivation, action means and action results;

[0062] S103, integrating family background, economic status and social relations to obtain living environment;

[0063] S104, extracting the character description sentences and the specific character behavior description sentences, analyzing the character description sentences and the specific character behavior description sentences, and obtaining the specific character character.

[0064] In the embodiment of the present invention, the basic information, action records, family background, economic status and social relations of the specific person in each case are firstly directly obtained through the database, which are clearly recorded in the case information. Then, the basic information is feature extracted to obtain gender, age and education level, the action records are feature extracted to obtain action motivation, action means and action results, and the three aspects of family background, economic status and social relations are summarized and integrated to obtain the living environment. Finally, it is also necessary to extract personality description sentences and specific character behavior description sentences based on natural language processing (NLP) technology, and analyze them to obtain the specific character personality.

[0065] like Figure 3 As shown, as a preferred embodiment of the present invention, the step of inputting the feature variables into the variable attribute library for matching and determining the feature attributes corresponding to each feature variable specifically includes:

[0066] S201, input the specific content of the feature variable into the corresponding description area in the variable attribute library for text matching, each description area corresponds to a feature attribute;

[0067] S202, determining a description area having the highest matching degree with the feature variable, and outputting a feature attribute corresponding to the description area.

[0068] In the embodiment of the present invention, several variable attribute libraries are established in advance, each characteristic variable corresponds to a variable attribute library, the variable attribute library includes several description areas, each description area corresponds to a characteristic attribute, for example, the variable attribute library corresponding to the characteristic variable of a specific character personality includes four description areas, the characteristic attributes corresponding to the four description areas are respectively sanguine type, choleric type, phlegmatic type or melancholic type, and the specific content of the description area corresponding to the phlegmatic type is: low sensitivity, high tolerance, less external expression, emotional stability, slow but flexible reaction speed, good at restraining oneself, steady and practical, comprehensive consideration of problems, quiet and silent, stable attention and not easy to transfer, and relatively introverted. The specific content of the characteristic variable is input into the corresponding description area in the variable attribute library for text matching, and then the description area with the highest matching degree with the characteristic variable is determined, and the characteristic attribute corresponding to the description area is output, so that the characteristic attribute corresponding to each characteristic variable can be determined.

[0069] like Figure 4 As shown, as a preferred embodiment of the present invention, the step of analyzing the characteristic information in each category and determining the action portrait information of each category specifically includes:

[0070] S301, analyzing all feature information in each category, and calculating the proportion of each feature attribute in each feature variable;

[0071] S302, arranging each characteristic attribute in each characteristic variable in descending order according to the proportion value, analyzing the characteristic attributes in each arrangement, and determining the action profile attribute;

[0072] S303: Summarize all action portrait attributes to obtain action portrait information of each category.

[0073] In an embodiment of the present invention, in order to determine the action portrait information of each category, all feature information in each category is analyzed, the proportion of each feature attribute in each feature variable is calculated, and then each feature attribute in each feature variable is arranged in descending order according to the proportion. For example, the arrangement corresponding to a specific character personality is: choleric type, sanguine type, phlegmatic type and melancholic type. Then, the feature attributes in each arrangement are analyzed to determine the action portrait attributes. Finally, the action portrait attributes in all arrangements are summarized to obtain the action portrait information of each category.

[0074] like Figure 5 As shown, as a preferred embodiment of the present invention, the step of analyzing the characteristic attributes in each arrangement to determine the action portrait attributes specifically includes:

[0075] S3021, the proportion values ​​corresponding to the characteristic attributes in the arrangement are accumulated one by one in order, and after each accumulation, the accumulated value is calculated until the accumulated value is greater than the proportion threshold, and then the accumulation is stopped;

[0076] S3022, retrieve the characteristic attributes involved in the accumulation and the corresponding proportion values, and determine whether the difference between two adjacent proportion values ​​is greater than a preset proportion interval;

[0077] S3023, when it does not exist, determine that all retrieved feature attributes are action portrait attributes; when it exists, determine the feature attribute corresponding to the largest proportion value among the differences in the proportion values, and determine that the feature attribute and the feature attributes before arrangement are action portrait attributes.

[0078] In the embodiment of the present invention, in order to determine the action portrait attribute, the proportion values ​​corresponding to the characteristic attributes in the arrangement are accumulated one by one in order. After each accumulation, the accumulated value is calculated until the accumulated value is greater than the ratio threshold, and the accumulation is stopped. For example, if a certain arrangement is: characteristic attribute three (42%), characteristic attribute four (37%), characteristic attribute two (9%), characteristic attribute one (8%) and characteristic attribute five (4%), and the ratio threshold is 80%, then the accumulation will stop after 42%+37%+9%. Then, the characteristic attributes involved in the accumulation and the corresponding proportion values ​​are retrieved to determine whether the difference between two adjacent proportion values ​​is greater than the preset ratio interval. If not, all the retrieved characteristic attributes are determined to be action portrait attributes; if so, the characteristic attribute corresponding to the largest proportion value in the difference of the proportion values ​​is determined. For example, if the preset ratio interval is 25%, the difference between the proportion values ​​of 37% and 9% is greater than the preset ratio interval, then the characteristic attributes and the characteristic attributes before the arrangement are determined to be action portrait attributes, that is, characteristic attribute three and characteristic attribute four are action portrait attributes.

[0079] like Figure 6 As shown, as a preferred embodiment of the present invention, the step of analyzing the retained feature information to obtain action prediction and intervention information specifically includes:

[0080] S401, partially deleting feature variables in the retained feature information based on the feature attribute screening instruction, and updating the retained feature information;

[0081] S402, obtaining potential portrait information according to the updated feature information, and determining action prediction information according to the action results in the potential portrait information;

[0082] S403, generating action intervention information according to the specific character, living environment, action motivation and action means in the potential portrait information, and obtaining action prediction and intervention information.

[0083] In the embodiment of the present invention, the characteristic variables in the retained characteristic information will be partially deleted according to the characteristic attribute screening instruction. For example, if the content of the characteristic attribute screening instruction is secondary education, male and choleric type, the specific character, gender and education related information in each case characteristic information will be deleted, and the retained characteristic information will be updated. Then, the potential portrait information is obtained according to all the updated characteristic information. The method for obtaining the potential portrait information is similar to the method for obtaining the action portrait attribute, except that the action results will be classified when the action portrait attribute is determined. The action results will not be classified here. The specific steps are: calculate the proportion value of each characteristic attribute in each characteristic variable, arrange each characteristic attribute in each characteristic variable in descending order according to the proportion value, analyze the characteristic attributes in each arrangement, determine the potential portrait attribute, and summarize all the potential portrait attributes to obtain the potential portrait information. Then, the action prediction information will be determined according to the action result in the potential portrait information, and the action intervention information will be generated according to the specific character, living environment, action motivation and action means in the potential portrait information, thereby improving the pertinence and effectiveness of action prediction and intervention, and providing strong support for related work.

[0084] like Figure 7 As shown, an embodiment of the present invention further provides a data parsing device, the device comprising:

[0085] The feature variable extraction module 100 is used to extract feature variables for each case in the database, wherein the feature variables include a specific person's personality, gender, age, education, living environment, action motivation, action means and action results;

[0086] The feature information determination module 200 is used to input the feature variables into the variable attribute library for matching, determine the feature attributes corresponding to each feature variable, and obtain the feature information of each case according to a number of feature attributes;

[0087] The action portrait information module 300 is used to classify all feature information based on the action results, analyze the feature information in each category, and determine the action portrait information of each category;

[0088] The action prediction and intervention module 400 is used to receive a feature attribute screening instruction input by a user, retain feature information that meets the conditions, analyze the retained feature information, and obtain action prediction and intervention information.

[0089] As a preferred embodiment of the present invention, the feature variable extraction module 100 includes:

[0090] A relevant information extraction unit, used to obtain basic information, action records, family background, economic status and social relations of specific persons in each case through the database;

[0091] An action record extraction unit is used to extract features from basic information to obtain gender, age and education level, and to extract features from action records to obtain action motivations, action means and action results;

[0092] The living environment determination unit is used to integrate family background, economic status and social relations to obtain the living environment;

[0093] The specific character determination unit is used to extract character description sentences and specific character behavior description sentences, analyze the character description sentences and specific character behavior description sentences, and obtain the specific character character.

[0094] An embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer device program stored in the memory and executable on the processor, wherein the processor implements the data parsing method when executing the computer device program.

[0095] An embodiment of the present invention further provides a storage medium, wherein the storage medium includes a stored program, and when the program is executed, the device where the storage medium is located is controlled to execute the data parsing method.

[0096] The above only describes in detail the preferred embodiments of the present invention, which is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0097] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0098] 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 program can be stored in a non-volatile computer-readable storage medium. When the 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 may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may 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).

[0099] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the disclosure in the specification and examples. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. A data analysis method, characterized in that: The method comprises the following steps: Extract characteristic variables from each case in the database, including specific person's personality, gender, age, education, living environment, action motivation, action means and action results; Input the characteristic variables into the variable attribute library for matching, determine the characteristic attributes corresponding to each characteristic variable, and obtain the characteristic information of each case based on several characteristic attributes; Classify all feature information based on the action results, analyze the feature information in each category, and determine the action profile information of each category; Receive the feature attribute screening instructions input by the user, retain the feature information that meets the conditions, analyze the retained feature information, and obtain action prediction and intervention information.

2. The data analysis method according to claim 1, characterized in that: The step of extracting characteristic variables from each case in the database specifically includes: The database is used to obtain basic information, action records, family background, economic status and social relations of specific people in each case; The basic information is extracted to obtain gender, age and education level, and the action records are extracted to obtain action motivation, action means and action results; Integrate family background, economic status and social relations to obtain living environment; Extract the character description sentences and the specific character behavior description sentences, analyze the character description sentences and the specific character behavior description sentences, and obtain the specific character personality.

3. The data analysis method according to claim 1, characterized in that: The step of inputting the feature variables into the variable attribute library for matching and determining the feature attributes corresponding to each feature variable specifically includes: Input the specific content of the feature variable into the corresponding description area in the variable attribute library for text matching. Each description area corresponds to a feature attribute. Determine the description area with the highest matching degree with the feature variable, and output the feature attribute corresponding to the description area.

4. The data analysis method according to claim 1, characterized in that: The step of analyzing the characteristic information in each category to determine the action profile information of each category specifically includes: Analyze all feature information in each category and calculate the proportion of each feature attribute in each feature variable; Arrange each characteristic attribute in each characteristic variable in descending order according to the proportion value, analyze the characteristic attributes in each arrangement, and determine the action profile attributes; All action portrait attributes are summarized to obtain action portrait information of each category.

5. The data analysis method according to claim 4, characterized in that: The step of analyzing the characteristic attributes in each arrangement to determine the action portrait attributes specifically includes: The proportion values ​​corresponding to the characteristic attributes in the arrangement are accumulated one by one in order. After each accumulation, the accumulated value is calculated until the accumulated value is greater than the proportion threshold, and then the accumulation stops; Retrieve the feature attributes involved in the accumulation and the corresponding proportion values, and determine whether the difference between two adjacent proportion values ​​is greater than a preset proportion interval; When it does not exist, all retrieved feature attributes are determined to be action portrait attributes; when it exists, the feature attribute corresponding to the largest proportion value among the differences in the proportion values ​​is determined, and the feature attribute and the feature attributes before the arrangement are determined to be action portrait attributes.

6. The data analysis method according to claim 1, characterized in that: The step of analyzing the retained feature information to obtain action prediction and intervention information specifically includes: Partially delete characteristic variables in the retained characteristic information based on the characteristic attribute screening instruction, and update the retained characteristic information; Obtaining potential profile information based on the updated feature information, and determining action prediction information based on the action results in the potential profile information; Action intervention information is generated based on the specific character, living environment, action motivation and action means in the potential portrait information to obtain action prediction and intervention information.

7. A data analysis device, characterized in that: The device comprises: A feature variable extraction module is used to extract feature variables from each case in the database. The feature variables include a specific person's personality, gender, age, education, living environment, action motivation, action means and action results; The feature information determination module is used to input the feature variables into the variable attribute library for matching, determine the feature attributes corresponding to each feature variable, and obtain the feature information of each case based on a number of feature attributes; The action profile information module is used to classify all feature information based on the action results, analyze the feature information in each category, and determine the action profile information of each category; The action prediction and intervention module is used to receive the feature attribute screening instructions input by the user, retain the feature information that meets the conditions, analyze the retained feature information, and obtain action prediction and intervention information.

8. The data analysis device according to claim 7, characterized in that: The feature variable extraction module includes: A relevant information extraction unit, used to obtain basic information, action records, family background, economic status and social relations of specific persons in each case through the database; An action record extraction unit is used to extract features from basic information to obtain gender, age and education level, and to extract features from action records to obtain action motivations, action means and action results; The living environment determination unit is used to integrate family background, economic status and social relations to obtain the living environment; The specific character determination unit is used to extract character description sentences and specific character behavior description sentences, analyze the character description sentences and specific character behavior description sentences, and obtain the specific character character.

9. A computer device, characterized in that: The method comprises a memory, a processor and a computer device program stored in the memory and executable on the processor, wherein the processor implements the data parsing method according to any one of claims 1 to 6 when executing the computer device program.

10. A storage medium, characterized in that: The storage medium includes a stored program, and when the program is executed, the device where the storage medium is located is controlled to execute the data parsing method according to any one of claims 1 to 6.

Images