Method, system and readable storage medium for generating a table of all case elements

By clustering and structuring historical case data, factor information templates are generated, the inefficiency caused by the complexity of legal relationships in case processing is solved, and case analysis is improved and data standardization is achieved.

CN114444460BActive Publication Date: 2024-11-22刘志坚
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210090674.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-01-26
Publication Date
2024-11-22
Estimated Expiration
2042-01-26

AI Technical Summary

Technical Problem

In case handling, the complexity of multiple legal relationships leads to inefficiency, insufficient display of key information, which affects the clarification of the case.

Method used

By obtaining historical case data, extracting feature vectors for clustering, generating feature information templates, and storing them in a database, visualizing and data structured case entity relationships.

Benefits of technology

Improve case analysis capabilities, help clarify case matters, and provide structured key factor data by manually or automatically filling element information templates to assist in handling complex legal relationships.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114444460B_ABST
    Figure CN114444460B_ABST
Patent Text Reader

Abstract

The present invention discloses a method, system and readable storage medium for generating a table of elements of the entire case, wherein the method comprises: obtaining a historical case data set, and extracting feature vectors from the data set; clustering based on the feature vectors to obtain element values ​​of the extraction model of the data set; using a plurality of the element values ​​to form an element information template, and storing the element information template in a preset database; extracting and compiling the element information template to obtain an element table file and outputting it to a user end. The present invention can be analyzed based on historical data to obtain a type distinction of key elements of the case, and can form element information templates based on different elements for users to manually fill in, and can also perform keyword recognition and automatic filling based on data information fed back by users, thereby improving the case analysis capability, and can visualize the entity relationships in the case, structure and standardize the key element data, and assist judges in clarifying the case.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of case document technology, and more specifically, to a method, system and readable storage medium for generating a full case element table. Background Art

[0002] The cause of action indicates the specific legal relationship of the case. Sometimes, multiple legal relationships will be tried together. The original lawsuit and the counterclaim may be one cause of action or two. This requires clear expression when preparing the documents.

[0003] Therefore, for different cases, the complexity of the relationship will often affect the process of case judgment, resulting in inefficiency. At the same time, different people have different degrees of understanding of different cases, and their control of key points is also different. At present, there are still gaps in the display of the basic framework and key information of different cases. This is an obstacle to clarifying the case and needs to be solved urgently. Summary of the invention

[0004] In view of the above problems, the purpose of the present invention is to provide a method, system and readable storage medium for generating a full case cause element table, which can be analyzed based on historical data to obtain the type distinction of key elements of the case, visualize the entity relationships in the case, structure and standardize the key element data, and assist in clarifying the case.

[0005] The first aspect of the present invention provides a method for generating a full case element table, comprising the following steps:

[0006] Obtaining a historical case data set and extracting feature vectors from the data set;

[0007] Performing clustering based on the feature vectors to obtain element values ​​of an extraction model of the data set;

[0008] Utilizing a plurality of said element values ​​to form an element information template, and storing said element information template in a preset database;

[0009] The element information template is extracted and compiled to obtain an element table file and output it to the user end.

[0010] In this solution, the method further comprises:

[0011] Acquire the data packet of the element table file fed back by the user terminal;

[0012] Extracting the corresponding element value and target material based on the data packet;

[0013] The element values ​​of the data packet and the target material are stored in the database using a constellation model to update the database.

[0014] In this solution, the method further comprises:

[0015] Obtaining a data packet fed back by a certain user terminal to obtain the corresponding element value;

[0016] Filling the element information template based on the element value fed back by a certain user terminal;

[0017] and matching the target materials in the database based on the element values, wherein the target materials include litigation materials and evidence materials;

[0018] The corresponding element information template, the litigation materials and the evidence materials are output to a corresponding user terminal.

[0019] In this solution, clustering is performed based on the feature vector to obtain the element value of the extraction model of the data set, specifically:

[0020] Acquire the historical case data set, extract and vectorize basic information of each case to obtain the feature vector;

[0021] Performing k-means clustering on the feature vectors, and distinguishing the repeated feature vectors according to case types, so as to obtain the extraction model;

[0022] The corresponding different element values ​​are obtained based on the differentiated feature vectors.

[0023] In this solution, the extraction and compilation of the element information template to obtain the element table file and output it to the user end is specifically as follows:

[0024] Compiling the element information template to obtain an element extraction formula;

[0025] Based on the extraction result of the element extraction formula, the extracted element information is structured by compiling the code, including generating an Excel table and / or outputting an API interface.

[0026] In this solution, the method further includes obtaining a target element rule base based on the element value, specifically:

[0027] Performing big data analysis on the historical case data set to obtain the correlation between the format of the judgment and the location;

[0028] Extracting rules and keywords in the corresponding judgment based on the mutual relationship to form a judgment template, and then obtaining an initial element rule library;

[0029] The initial element rule base is iteratively updated using the case information in the historical case data set to complete the information, thereby obtaining the target element rule base.

[0030] The second aspect of the present invention further provides a system for generating a full case element table, comprising a memory and a processor, wherein the memory comprises a full case element table generation method program, and when the full case element table generation method program is executed by the processor, the following steps are implemented:

[0031] Obtaining a historical case data set and extracting feature vectors from the data set;

[0032] Performing clustering based on the feature vectors to obtain element values ​​of an extraction model of the data set;

[0033] Utilizing a plurality of said element values ​​to form an element information template, and storing said element information template in a preset database;

[0034] The element information template is extracted and compiled to obtain an element table file and output it to the user end.

[0035] In this solution, the method further comprises:

[0036] Acquire the data packet of the element table file fed back by the user terminal;

[0037] Extracting the corresponding element value and target material based on the data packet;

[0038] The element values ​​of the data packet and the target material are stored in the database using a constellation model to update the database.

[0039] In this solution, the method further comprises:

[0040] Obtaining a data packet fed back by a certain user terminal to obtain the corresponding element value;

[0041] Filling the element information template based on the element value fed back by a certain user terminal;

[0042] and matching the target materials in the database based on the element values, wherein the target materials include litigation materials and evidence materials;

[0043] The corresponding element information template, the litigation materials and the evidence materials are output to a corresponding user terminal.

[0044] In this solution, clustering is performed based on the feature vector to obtain the element value of the extraction model of the data set, specifically:

[0045] Acquire the historical case data set, extract and vectorize basic information of each case to obtain the feature vector;

[0046] Performing k-means clustering on the feature vectors, and distinguishing the repeated feature vectors according to case types, so as to obtain the extraction model;

[0047] The corresponding different element values ​​are obtained based on the differentiated feature vectors.

[0048] In this solution, the extraction and compilation of the element information template to obtain the element table file and output it to the user end is specifically as follows:

[0049] Compiling the element information template to obtain an element extraction formula;

[0050] Based on the extraction result of the element extraction formula, the extracted element information is structured by compiling the code, including generating an Excel table and / or outputting an API interface.

[0051] In this solution, the method further includes obtaining a target element rule base based on the element value, specifically:

[0052] Performing big data analysis on the historical case data set to obtain the correlation between the format of the judgment and the location;

[0053] Extracting rules and keywords in the corresponding judgment based on the mutual relationship to form a judgment template, and then obtaining an initial element rule library;

[0054] The initial element rule base is iteratively updated using the case information in the historical case data set to complete the information, thereby obtaining the target element rule base.

[0055] The third aspect of the present invention provides a computer-readable storage medium, which includes a machine-readable program for a method for generating a full case cause element table. When the program for generating a full case cause element table is executed by a processor, the steps of a method for generating a full case cause element table as described in any one of the above items are implemented.

[0056] The present invention discloses a method, system and readable storage medium for generating a full case cause element table, which can be analyzed based on historical data to obtain the type distinction of key elements of the case, and can form element information templates according to different elements for users to fill in manually, and can also perform keyword recognition and automatic filling according to data information fed back by users, thereby improving the case cause analysis capability, visualizing the entity relationships in the case, structuring and standardizing the key element data, and assisting in clarifying the case. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 A flowchart of a method for generating a full case element table according to the present invention is shown;

[0058] Figure 2 A block diagram of a system for generating a full case element table according to the present invention is shown. DETAILED DESCRIPTION

[0059] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0060] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0061] Figure 1 A flowchart of a method for generating a full case element table of the present application is shown.

[0062] like Figure 1 As shown, the present application discloses a method for generating a full case element table, comprising the following steps:

[0063] S102, obtaining a historical case data set, and extracting a feature vector from the data set;

[0064] S104, performing clustering based on the feature vector to obtain element values ​​of the extraction model of the data set;

[0065] S106, using a plurality of the element values ​​to form an element information template, and storing the element information template in a preset database;

[0066] S108, extracting and compiling the element information template to obtain an element table file and outputting it to the user end.

[0067] It should be noted that by extracting the case information in the historical case data set, the feature vector of the data set can be obtained, and multiple feature vectors can be clustered using k-means to obtain the extraction model for the data set. Correspondingly, the feature vector of the extraction model extracted is the element value, and multiple element values ​​are combined to obtain the element information template, which is stored in the database and waits for call. At the same time, the element information template is compiled into an Excel table, that is, the element table file, to be output to the user end.

[0068] According to an embodiment of the present invention, the method further includes:

[0069] Acquire the data packet of the element table file fed back by the user terminal;

[0070] Extracting the corresponding element value and target material based on the data packet;

[0071] The element values ​​of the data packet and the target material are stored in the database using a constellation model to update the database.

[0072] It should be noted that the case import user end can select different case types according to its own needs, and then call different factor information extraction formulas generated by machine learning according to the different types selected by the user, and extract factors from the data packets of the factor table file submitted by the user, and create a constellation model with the case information, factor information and corresponding case-related materials through fact tables and dimension tables and save them in the database.

[0073] According to an embodiment of the present invention, the method further includes:

[0074] Obtaining a data packet fed back by a certain user terminal to obtain the corresponding element value;

[0075] Filling the element information template based on the element value fed back by a certain user terminal;

[0076] and matching the target materials in the database based on the element values, wherein the target materials include litigation materials and evidence materials;

[0077] The corresponding element information template, the litigation materials and the evidence materials are output to a corresponding user terminal.

[0078] It should be noted that, taking a certain user terminal as the user terminal, it needs to extract a type of case for analysis. Accordingly, based on the element value fed back by the user terminal, the corresponding element information template and the litigation materials and the evidence materials are matched, and the keywords extracted from the element value fed back by the user terminal are compared with the basic information stored in the database to extract the litigation materials and the evidence materials related to the element value fed back by the user terminal, where the evidence materials include but are not limited to loan process instructions, loan contracts, personal credit authorization letters, face recognition and electronic signatures, personal loan confirmation letters, loan flow lists to personal accounts, personal loan business loan account statements, personal loan business customer repayment lists, interest and penalty interest calculation method descriptions, loan early maturity notices, attorney fees, defendant identity certificates, etc. to obtain data sets.

[0079] According to an embodiment of the present invention, clustering is performed based on the feature vector to obtain the element value of the extraction model of the data set, specifically:

[0080] Acquire the historical case data set, extract and vectorize basic information of each case to obtain the feature vector;

[0081] Performing k-means clustering on the feature vectors, and distinguishing the repeated feature vectors according to case types, so as to obtain the extraction model;

[0082] The corresponding different element values ​​are obtained based on the differentiated feature vectors.

[0083] It should be noted that the historical case data set obtained includes lawyer's practice certificates, lawyer's letters, power of attorney, lawsuits, evidence materials, etc. The basic information of each case in the data set is vectorized and used as the feature vector. The feature vector is clustered by k-means to obtain the repeated element information in the historical information. These element information are extracted and distinguished according to the type of case. After clustering, the extraction model corresponding to the data set will be generated, which can also be used as a feature information extraction model. Accordingly, the element information distinguished by case type, that is, the feature vector, obtains the corresponding different element values.

[0084] It is worth mentioning that the steps of the k-means algorithm are: first (randomly) select the initial centers of K clusters, then for any sample point, calculate its distance to the K cluster centers, and classify the sample point into the cluster with the smallest distance center, and iterate n times. In each iteration, use the mean and other methods to update the center point (center of mass) of each cluster. Finally, for the K cluster centers, after iteratively updating using the above steps, if the position point changes very little (a threshold can be set), it is considered to have reached a stable state and the iteration ends. Different color labels can be selected for different cluster blocks and cluster centers.

[0085] According to an embodiment of the present invention, extracting and compiling the element information template to obtain an element table file and outputting it to the user terminal is specifically as follows:

[0086] Compiling the element information template to obtain an element extraction formula;

[0087] Based on the extraction result of the element extraction formula, the extracted element information is structured by compiling the code, including generating an Excel table and / or outputting an API interface.

[0088] It should be noted that the element extraction formula is obtained by compiling the element information template, that is, the element information repeatedly appearing in various types of cases is obtained through machine learning methods. Then, these element information are integrated to form the element information template for various types of cases. After this fixed template is determined, these element information are generated into an excel table in the form of compiled code for output to the client, or an API interface is output for system docking with banks and financial institutions. For example, in a certain type of case in the historical information, element information such as name, age, and gender appear multiple times. Through the k-means clustering process, this data will be captured, and then the captured element information is integrated together to form the information template to be output. These element information will be stored in the database, and then the element information stored in the database will be extracted and compiled into an excel file. Among them, the element extraction formula is a formula of the prior art selected by those skilled in the art according to actual needs, and will not be elaborated in this invention one by one.

[0089] It is worth mentioning that for machine learning, it includes supervised learning and unsupervised learning, and the formula for extracting the element information is also generated by machine learning.

[0090] According to an embodiment of the present invention, the method further includes obtaining a target element rule base based on the element values, specifically:

[0091] Perform big data analysis on the historical case data set to obtain the mutual relationship between the judgment format and the location;

[0092] Extract the rules and keywords in the corresponding judgment based on the mutual relationship to form a judgment template, and then obtain an initial element rule base;

[0093] Use the case information in the historical case data set to iteratively update the initial element rule base to complete the information and obtain the target element rule base.

[0094] It should be noted that through big data analysis of several same-type cases and similar-type cases, it can be obtained that there is a certain degree of connection between the format, location, and time of the judgment, that is, the mutual relationship. By summarizing the mutual relationship, the rules and key phrases of the judgment are obtained to obtain a judgment template that can be compatible with different types of cases, forming an initial element rule base, and iteratively supplementing the information in the initial element base through the different number of cases in the historical case data set to obtain the target element rule base. Among them, the mutual relationship is the corresponding relationship between the judgment format, location, and time. For example: Time: "2020 / 12 / 10"; Location: ## Province ## Market; The judgment format is the content of the judgment.

[0095] It is worth mentioning that before the case is imported into the Excel table generated on the user side, it also includes: obtaining the attribute information of the case submitter to complete the Excel table.

[0096] It should be noted that, for the element information template, different submitters may apply for different data in the template. Accordingly, the difference lies in the attribute information of the submitter, such as identity information, position information, and the like.

[0097] It is worth mentioning that the method further includes sorting based on the characteristic values ​​in the element values, specifically:

[0098] Obtaining a characteristic value of a sorting element in the element value;

[0099] Classification is performed based on the feature values ​​of the sorting elements, wherein the priority of the case degree feature value is higher than the case time feature value.

[0100] It should be noted that when the user terminal calls the cases in the database, there may be multiple matching results. When sorting based on the multiple case information obtained by matching, they are first sorted in chronological order based on the time feature value, and then sorted based on the level of the degree feature value. For example, the time value of case A lags behind that of case B, but the level of case A is high. Accordingly, when displayed to the user terminal, case A is ranked before case B.

[0101] Figure 2 A block diagram of a system for generating a full case element table according to the present invention is shown.

[0102] like Figure 2 As shown, the present invention discloses a system for generating a full case element table, including a memory and a processor, wherein the memory includes a full case element table generation method program, and when the full case element table generation method program is executed by the processor, the following steps are implemented:

[0103] Obtaining a historical case data set and extracting feature vectors from the data set;

[0104] Performing clustering based on the feature vectors to obtain element values ​​of an extraction model of the data set;

[0105] Utilizing a plurality of said element values ​​to form an element information template, and storing said element information template in a preset database;

[0106] The element information template is extracted and compiled to obtain an element table file and output it to the user end.

[0107] It should be noted that by extracting the case information in the historical case data set, the feature vector of the data set can be obtained, and multiple feature vectors can be clustered using k-means to obtain the extraction model for the data set. Correspondingly, the feature vector of the extraction model extracted is the element value, and multiple element values ​​are combined to obtain the element information template, which is stored in the database and waits for call. At the same time, the element information template is compiled into an Excel table, that is, the element table file, to be output to the user end.

[0108] According to an embodiment of the present invention, the method further includes:

[0109] Acquire the data packet of the element table file fed back by the user terminal;

[0110] Extracting the corresponding element value and target material based on the data packet;

[0111] The element values ​​of the data packet and the target material are stored in the database using a constellation model to update the database.

[0112] It should be noted that the case import user end can select different case types according to its own needs, and then call different factor information extraction formulas generated by machine learning according to the different types selected by the user, and extract factors from the data packets of the factor table file submitted by the user, and create a constellation model with the case information, factor information and corresponding case-related materials through fact tables and dimension tables and save them in the database.

[0113] According to an embodiment of the present invention, the method further includes:

[0114] Obtaining a data packet fed back by a certain user terminal to obtain the corresponding element value;

[0115] Filling the element information template based on the element value fed back by a certain user terminal;

[0116] and matching the target materials in the database based on the element values, wherein the target materials include litigation materials and evidence materials;

[0117] The corresponding element information template, the litigation materials and the evidence materials are output to a corresponding user terminal.

[0118] It should be noted that, taking a certain user terminal as the user terminal, it needs to extract a type of case for analysis. Accordingly, based on the element value fed back by the user terminal, the corresponding element information template and the litigation materials and the evidence materials are matched, and the keywords extracted from the element value fed back by the user terminal are compared with the basic information stored in the database to extract the litigation materials and the evidence materials related to the element value fed back by the user terminal, where the evidence materials include but are not limited to loan process instructions, loan contracts, personal credit authorization letters, face recognition and electronic signatures, personal loan confirmation letters, loan flow lists to personal accounts, personal loan business loan account statements, personal loan business customer repayment lists, interest and penalty interest calculation method descriptions, loan early maturity notices, attorney fees, defendant identity certificates, etc. to obtain data sets.

[0119] According to an embodiment of the present invention, clustering is performed based on the feature vector to obtain the element value of the extraction model of the data set, specifically:

[0120] Acquire the historical case data set, extract and vectorize basic information of each case to obtain the feature vector;

[0121] Performing k-means clustering on the feature vectors, and distinguishing the repeated feature vectors according to case types, so as to obtain the extraction model;

[0122] The corresponding different element values ​​are obtained based on the differentiated feature vectors.

[0123] It should be noted that the historical case data set obtained includes lawyer's practice certificates, lawyer's letters, power of attorney, lawsuits, evidence materials, etc. The basic information of each case in the data set is vectorized and used as the feature vector. The feature vector is clustered by k-means to obtain the repeated element information in the historical information. These element information are extracted and distinguished according to the type of case. After clustering, the extraction model corresponding to the data set will be generated, which can also be used as a feature information extraction model. Accordingly, the element information distinguished by case type, that is, the feature vector, obtains the corresponding different element values.

[0124] It is worth mentioning that the steps of the k-means algorithm are: first (randomly) select the initial centers of K clusters, then for any sample point, calculate its distance to the K cluster centers, and classify the sample point into the cluster with the smallest distance center, and iterate n times. In each iteration, use the mean and other methods to update the center point (center of mass) of each cluster. Finally, for the K cluster centers, after iteratively updating using the above steps, if the position point changes very little (a threshold can be set), it is considered to have reached a stable state and the iteration ends. Different color labels can be selected for different cluster blocks and cluster centers.

[0125] According to an embodiment of the present invention, extracting and compiling the element information template to obtain an element table file and outputting it to the user terminal is specifically as follows:

[0126] Compiling the element information template to obtain an element extraction formula;

[0127] Based on the extraction result of the element extraction formula, the extracted element information is structured by compiling the code, including generating an Excel table and / or outputting an API interface.

[0128] It should be noted that the element information template is compiled to obtain the element extraction formula, that is, the element information that appears repeatedly in various types of cases is obtained through a machine learning method, and then these element information are integrated to form the element information template for each type of case. After this fixed template is determined, these element information are generated into an excel table by compiling the code to output it to the user end, or output an API interface for system docking with banks and financial institutions; for example, in a certain type of case in the historical information, the name, age, gender and other element information appear multiple times, and this data will be captured through the k-means clustering process, and then the captured element information will be integrated together to input the information template, and these element information will be put into the database, and then they will be extracted and compiled into an excel file based on the element information stored in the database, wherein the element extraction formula is a formula of the prior art selected by technicians in this field according to actual needs, and the present invention will not go into details one by one.

[0129] It is worth mentioning that machine learning includes supervised learning and unsupervised learning, wherein the formula for extracting element information is also generated by machine learning.

[0130] According to an embodiment of the present invention, the method further includes obtaining a target element rule base based on the element value, specifically:

[0131] Performing big data analysis on the historical case data set to obtain the correlation between the format of the judgment and the location;

[0132] Extract the corresponding rules and keywords in the judgment documents based on the mutual relationship to form a judgment document template, and then obtain an initial element rule base;

[0133] Use the case information in the historical case dataset to iteratively update the initial element rule base to complete the information and obtain the target element rule base.

[0134] It should be noted that through big data analysis of a number of same-type cases and similar-type cases, it can be obtained that there is a certain degree of connection between the format, location, and time of the judgment document, that is, the mutual relationship. Through the mutual relationship, the rules and key phrases of the judgment document are summarized to obtain a judgment document template that can be compatible with different types of cases, forming an initial element rule base, and iteratively complementing the information in the initial element base through the different numbers of cases in the historical case dataset to obtain the target element rule base. Among them, the mutual relationship is the corresponding relationship between the judgment document format, location, and time. For example: Time: "2020 / 12 / 10"; Location: ## Province ## Market; The judgment document format is the content of the judgment document.

[0135] It is worth mentioning that before generating the excel table of the case import user terminal, it also includes: obtaining the attribute information of the case submitter to complete the excel table.

[0136] It should be noted that for the element information template, the data in the template applied by different submitters are different. Correspondingly, the differences lie in the attribute information of the submitters, such as identity information, position information, etc.

[0137] It is worth mentioning that the method also includes sorting based on the characteristic values in the element values, specifically:

[0138] Obtain the sorting element characteristic values in the element values;

[0139] Classify based on the sorting element characteristic values, where the priority of the case degree characteristic value is higher than that of the case time characteristic value.

[0140] It should be noted that when the user terminal calls the cases in the database, the matching results may be multiple. When sorting based on the multiple case information obtained by matching, first sort based on the time characteristic value in chronological order, and then sort based on the level of the degree characteristic value. For example, the time value of case A lags behind that of case B, but the degree of case A is high. Correspondingly, when displayed to the user terminal, the sorting of case A is before that of case B.

[0141] The third aspect of the present invention provides a computer-readable storage medium, which includes a method program for generating a full case cause element table. When the method program for generating a full case cause element table is executed by a processor, the steps of a method for generating a full case cause element table as described in any one of the above items are implemented.

[0142] The present invention discloses a method, system and readable storage medium for generating a full case cause element table, which can be analyzed based on historical data to obtain the type distinction of key elements of the case, and can form element information templates according to different elements for users to fill in manually, and can also perform keyword recognition and automatic filling according to data information fed back by users, thereby improving the case cause analysis capability, visualizing the entity relationships in the case, structuring and standardizing the key element data, and assisting in clarifying the case.

[0143] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0144] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0145] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0146] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0147] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. A method for generating a table of all case elements, It is characterized in that The following steps are involved: Obtaining a historical case data set and extracting feature vectors from the data set; Performing clustering based on the feature vectors to obtain element values ​​of an extraction model of the data set; Utilizing a plurality of said element values ​​to form an element information template, and storing said element information template in a preset database; Extracting and compiling the element information template to obtain an element table file and outputting it to the user end; The clustering is performed based on the feature vector to obtain the element value of the extraction model of the data set, specifically: Acquire the historical case data set, extract and vectorize basic information of each case to obtain the feature vector; Performing k-means clustering on the feature vectors, and distinguishing the repeated feature vectors according to case types, so as to obtain the extraction model; Obtaining corresponding different element values ​​based on the distinguished feature vectors; The extracting and compiling of the element information template to obtain the element table file and outputting it to the user terminal is specifically as follows: Compiling the element information template to obtain an element extraction formula; Based on the extraction result of the element extraction formula, the extracted element information is structured by compiling the code, including generating an Excel table and / or outputting an API interface; The method further includes, when the user terminal calls the cases in the database and sorts the cases based on the matched multiple case information, sorting the cases based on the feature values ​​in the element values, specifically: Obtaining a characteristic value of a sorting element in the element value; Sorting is performed based on the characteristic values ​​of the sorting elements, wherein the priority of the case degree characteristic value is higher than the case time characteristic value.

2. A method for generating a full case element table according to claim 1, It is characterized in that The method further comprises: Acquire the data packet of the element table file fed back by the user terminal; Extracting the corresponding element value and target material based on the data packet; The element values ​​of the data packet and the target material are stored in the database using a constellation model to update the database.

3. A method for generating a full case element table according to claim 2, It is characterized in that The method further comprises: Obtaining a data packet fed back by a certain user terminal to obtain the corresponding element value; Matching the element information template based on the element value fed back by a certain user terminal; and matching the target materials in the database based on the element values, wherein the target materials include litigation materials and evidence materials; The corresponding element information template, the litigation materials and the evidence materials are output to a corresponding user terminal.

4. A method for generating a full case element table according to claim 1, It is characterized in that The method further includes obtaining a target element rule base based on the element value, specifically: Performing big data analysis on the historical case data set to obtain the correlation between the format of the judgment and the location; Extracting rules and keywords in the corresponding judgment based on the mutual relationship to form a judgment template, and then obtaining an initial element rule library; The initial element rule base is iteratively updated using the case information in the historical case data set to complete the information, thereby obtaining the target element rule base.

5. A system for generating a table of all case elements, It is characterized in that The invention comprises a memory and a processor, wherein the memory comprises a method program for generating a table of elements of a full case, and when the method program for generating a table of elements of a full case is executed by the processor, the following steps are implemented: Obtaining a historical case data set and extracting feature vectors from the data set; Performing clustering based on the feature vectors to obtain element values ​​of an extraction model of the data set; Utilizing a plurality of said element values ​​to form an element information template, and storing said element information template in a preset database; Extracting and compiling the element information template to obtain an element table file and outputting it to the user end; The clustering is performed based on the feature vector to obtain the element value of the extraction model of the data set, specifically: Acquire the historical case data set, extract and vectorize basic information of each case to obtain the feature vector; Performing k-means clustering on the feature vectors, and distinguishing the repeated feature vectors according to case types, so as to obtain the extraction model; Obtaining corresponding different element values ​​based on the distinguished feature vectors; The extracting and compiling of the element information template to obtain the element table file and outputting it to the user terminal is specifically as follows: Compiling the element information template to obtain an element extraction formula; Based on the extraction result of the element extraction formula, the extracted element information is structured by compiling the code, including generating an Excel table and / or outputting an API interface; The method further includes, when the user terminal calls the cases in the database and sorts the cases based on the matched multiple case information, sorting the cases based on the feature values ​​in the element values, specifically: Obtaining a characteristic value of a sorting element in the element value; Sorting is performed based on the characteristic values ​​of the sorting elements, wherein the priority of the case degree characteristic value is higher than the case time characteristic value.

6. A system for generating a full case element table according to claim 5, It is characterized in that The method further includes obtaining a target element rule base based on the element value, specifically: Performing big data analysis on the historical case data set to obtain the correlation between the format of the judgment and the location; Extracting rules and keywords in the corresponding judgment based on the mutual relationship to form a judgment template, and then obtaining an initial element rule library; The initial element rule base is iteratively updated using the case information in the historical case data set to complete the information, thereby obtaining the target element rule base.

7. A computer-readable storage medium, It is characterized in that The computer-readable storage medium includes a method program for generating a full case cause element table. When the method program for generating a full case cause element table is executed by a processor, the steps of a method for generating a full case cause element table as described in any one of claims 1 to 4 are implemented.