CN112288604B - Judicial case data processing method and device, electronic equipment and readable storage medium - Google Patents

Judicial case data processing method and device, electronic equipment and readable storage medium Download PDF

Info

Publication number
CN112288604B
CN112288604B CN202011299393.2A CN202011299393A CN112288604B CN 112288604 B CN112288604 B CN 112288604B CN 202011299393 A CN202011299393 A CN 202011299393A CN 112288604 B CN112288604 B CN 112288604B
Authority
CN
China
Prior art keywords
lawyer
case
target
judicial
processed
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011299393.2A
Other languages
Chinese (zh)
Other versions
CN112288604A (en
Inventor
赵墨林
张敏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An International Smart City Technology Co Ltd
Original Assignee
Ping An International Smart City Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ping An International Smart City Technology Co Ltd filed Critical Ping An International Smart City Technology Co Ltd
Priority to CN202011299393.2A priority Critical patent/CN112288604B/en
Publication of CN112288604A publication Critical patent/CN112288604A/en
Application granted granted Critical
Publication of CN112288604B publication Critical patent/CN112288604B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/18—Legal services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • G06F18/24155—Bayesian classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/24323—Tree-organised classifiers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/40—Document-oriented image-based pattern recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Economics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Strategic Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Development Economics (AREA)
  • Quality & Reliability (AREA)
  • Technology Law (AREA)
  • Primary Health Care (AREA)
  • Educational Administration (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Probability & Statistics with Applications (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to data processing, and discloses a judicial case data processing method, which comprises the following steps: establishing lawyer portraits for various lawyers; establishing lawyer groups corresponding to the dimension combination labels, and distributing the lawyers to the lawyer groups with different grades corresponding to the dimension combination labels according to the evaluation results; calculating a first characteristic sequence of the judicial cases to be processed, and determining a target case level based on the first characteristic sequence; and determining a target lawyer group corresponding to the to-be-processed judicial case based on the target dimension combination label, determining a target lawyer group in the target lawyer group corresponding to the to-be-processed judicial case based on the target case grade, and transmitting a list of a preset number of lawyers in the target lawyer group to the client based on the evaluation result. The invention also provides a judicial case data processing device, electronic equipment and a readable storage medium. The invention improves the accuracy and the efficiency of judicial case data processing.

Description

Judicial case data processing method and device, electronic equipment and readable storage medium
Technical Field
The present invention relates to the field of data processing, and in particular, to a method and apparatus for processing judicial case data, an electronic device, and a readable storage medium.
Background
Along with the progress of science and technology, intelligent recommendation/distribution is more and more widely applied in people's life, for example, intelligent distribution of judicial cases to proper lawyers is performed, at present, similarity comparison is usually performed between a to-be-processed case and a history case in a case library, a lawyer corresponding to the history case with highest similarity is used as a target lawyer of the to-be-processed case, however, the mode does not consider the good field of lawyers, so that the matching degree between the case and the lawyer is not high enough, the distribution accuracy is low, and meanwhile, the distribution efficiency of the case is low due to comparison with each history case in the case library. Therefore, there is a need for a judicial case data processing method to improve case distribution accuracy and distribution efficiency.
Disclosure of Invention
In view of the foregoing, it is necessary to provide a judicial case data processing method, which aims to improve the accuracy and efficiency of judicial case data processing.
The judicial case data processing method provided by the invention comprises the following steps:
Acquiring basic information of each historical referee document in a first database and each lawyer in a second database, and establishing lawyer portraits for each lawyer based on the historical referee text and the basic information, wherein the lawyer portraits comprise a plurality of dimension combination tags of the lawyer and evaluation results corresponding to the dimension combination tags;
Establishing lawyer groups corresponding to the dimension combination labels, and distributing the lawyers to lawyer groups with different grades of the lawyer groups corresponding to the dimension combination labels according to the evaluation result;
Analyzing a judicial case data processing request sent by a user based on a client, acquiring a to-be-processed judicial case and a target dimension combination tag carried in the judicial case data processing request, calculating a first feature sequence of the to-be-processed judicial case based on a preset feature set, and inputting the first feature sequence into a trained case grade identification model to obtain a target case grade of the to-be-processed judicial case;
And determining a target lawyer group corresponding to the to-be-processed judicial case based on the target dimension combination label, determining a target lawyer group in the target lawyer group corresponding to the to-be-processed judicial case based on the target case grade, and transmitting a list of a preset number of lawyers in the target lawyer group to the client based on the evaluation result.
Optionally, the creating a lawyer portrait for each lawyer based on the history referee text and the basic information includes:
Performing OCR (optical character recognition) on the historical referee document to obtain referee document text, and determining lawyers corresponding to the referee document text;
Taking the set of basic information corresponding to each lawyer and judge document text as the information set of each lawyer;
matching the first keyword set with the basic information in the information set to obtain first target keywords of all lawyers;
Matching the second keyword set with the judge document text in the information set to obtain second target keywords of all lawyers;
and determining lawyer portraits of all lawyers based on the first target keywords and the second target keywords, randomly combining the first target keywords and the second target keywords to obtain a plurality of dimension combination labels corresponding to all lawyers, and determining evaluation results corresponding to all dimension combination labels.
Optionally, the calculating the first feature sequence of the to-be-processed judicial case based on the preset feature set includes:
word segmentation is carried out on the case information of the judicial cases to be processed to obtain a word set;
Determining feature values of all features in the preset feature set based on the word set;
splicing the characteristic values to obtain a first sequence;
Converting the discrete data in the first sequence into numerical data to obtain a second sequence;
and carrying out normalization processing on the second sequence to obtain a first characteristic sequence of the to-be-processed judicial case.
Optionally, the training process of the case rank identification model includes:
Calculating a second feature sequence corresponding to each history referee document in the first database based on the preset feature set;
calculating a real risk value corresponding to each history referee document;
And inputting the second characteristic sequence into a case grade identification model to obtain predicted risk scores corresponding to the historical referee documents, and determining weight parameters of the case grade identification model by minimizing loss values between the predicted risk scores and the real risk scores to obtain a trained case grade identification model.
Optionally, after the list of the preset number of attorneys in the target lawyer group is sent to the client based on the evaluation result, the method further includes:
Determining whether each index of the multiple indexes of the judicial case to be processed is normal or not based on the multiple indexes and the case information of the judicial case to be processed, generating an abnormal report when any index is abnormal, and sending the abnormal report to the client.
Optionally, the calculation formula of the loss value is:
wherein loss (q i,pi) is a loss value between the predicted risk score and the real risk score of the ith historical referee document, q i is the predicted risk score of the ith historical referee document, p i is the real risk score of the ith historical referee document, and c is the total number of the historical referee documents.
In order to solve the above problems, the present invention also provides a judicial case data processing apparatus, including:
The portrait module is used for acquiring basic information of each historical referee document in the first database and each lawyer in the second database, and establishing a lawyer portrait for each lawyer based on the historical referee text and the basic information, wherein the lawyer portrait comprises a plurality of dimension combination labels of the lawyer and evaluation results corresponding to the dimension combination labels;
The distribution module is used for establishing lawyer groups corresponding to the dimension combination labels, and distributing the lawyers to the lawyer groups with different grades of the lawyer groups corresponding to the dimension combination labels according to the evaluation result;
The analysis module is used for analyzing a judicial case data processing request sent by a user based on a client, acquiring a to-be-processed judicial case and a target dimension combination label carried in the judicial case data processing request, calculating a first feature sequence of the to-be-processed judicial case based on a preset feature set, and inputting the first feature sequence into a trained case grade identification model to obtain a target case grade of the to-be-processed judicial case;
The determining module is used for determining a target lawyer group corresponding to the judicial case to be processed based on the target dimension combination label, determining a target lawyer group in the target lawyer group corresponding to the judicial case to be processed based on the target case grade, and sending a list of a preset number of lawyers in the target lawyer group to the client based on the evaluation result.
Optionally, the creating a lawyer portrait for each lawyer based on the history referee text and the basic information includes:
Performing OCR (optical character recognition) on the historical referee document to obtain referee document text, and determining lawyers corresponding to the referee document text;
Taking the set of basic information corresponding to each lawyer and judge document text as the information set of each lawyer;
matching the first keyword set with the basic information in the information set to obtain first target keywords of all lawyers;
Matching the second keyword set with the judge document text in the information set to obtain second target keywords of all lawyers;
and determining lawyer portraits of all lawyers based on the first target keywords and the second target keywords, randomly combining the first target keywords and the second target keywords to obtain a plurality of dimension combination labels corresponding to all lawyers, and determining evaluation results corresponding to all dimension combination labels.
In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores a judicial case data processing program executable by the at least one processor, the judicial case data processing program being executable by the at least one processor to enable the at least one processor to perform the judicial case data processing method described above.
In order to solve the above problems, the present invention also provides a computer-readable storage medium having stored thereon a judicial case data processing program executable by one or more processors to implement the above judicial case data processing method.
Compared with the prior art, the method and the device have the advantages that firstly, the lawyer portrait is built for each lawyer based on the basic information of the history referee document and the lawyers, the lawyer portrait comprises a plurality of dimension combination labels of the lawyers and evaluation results corresponding to the dimension combination labels, and the related information of each lawyer can be quickly known through the built lawyer portrait; then, establishing lawyer groups corresponding to the dimension combination labels, distributing the lawyers to lawyer groups of different grades of the lawyer groups corresponding to the dimension combination labels according to the evaluation result, establishing corresponding lawyer groups for each dimension combination label, and distributing the lawyers to the lawyer groups of different grades, so that the matching of subsequent cases can be facilitated; finally, inputting the first feature sequence of the judicial case to be processed into a trained case grade identification model to obtain a target case grade of the case to be processed, determining a target lawyer group based on a target dimension combination label carried in a judicial case data processing request, enabling a user demand to be more matched with the target lawyer group, improving lawyer matching accuracy, determining a target lawyer group in the target lawyer group based on the target case grade, and enabling part of lawyer groups in the target lawyer group to be removed rapidly. Therefore, the invention improves the accuracy and the efficiency of processing the judicial case data.
Drawings
FIG. 1 is a flow chart of a method for processing judicial case data according to an embodiment of the present invention;
FIG. 2 is a schematic block diagram of a judicial case data processing apparatus according to an embodiment of the present invention;
Fig. 3 is a schematic structural diagram of an electronic device for implementing a judicial case data processing method according to an embodiment of the present invention;
the achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that the description of "first", "second", etc. in this disclosure is for descriptive purposes only and is not to be construed as indicating or implying a relative importance or implying an indication of the number of technical features being indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not within the scope of protection claimed in the present invention.
The invention provides a judicial case data processing method. Referring to fig. 1, a flow chart of a method for processing judicial case data according to an embodiment of the invention is shown. The method may be performed by an electronic device, which may be implemented in software and/or hardware.
In this embodiment, the judicial case data processing method includes:
s1, acquiring basic information of each historical referee document in a first database and each lawyer in a second database, and establishing lawyer portraits for each lawyer based on the historical referee text and the basic information, wherein the lawyer portraits comprise a plurality of dimension combination labels of the lawyer and evaluation results corresponding to the dimension combination labels.
In this embodiment, the creating a lawyer portrait for each lawyer based on the history referee text and the basic information includes:
A1, performing OCR (optical character recognition) on the historical referee document to obtain referee document text, and determining lawyers corresponding to the referee document text;
A2, taking the set of basic information corresponding to each lawyer and the judge document text as the information set of each lawyer;
a3, matching the first keyword set with the basic information in the information set to obtain first target keywords of all lawyers;
A4, matching the second keyword set with the judge document text in the information set to obtain second target keywords of all lawyers;
A5, determining lawyer portraits of all lawyers based on the first target keywords and the second target keywords, randomly combining the first target keywords and the second target keywords to obtain a plurality of dimension combination labels corresponding to all the lawyers, and determining evaluation results corresponding to all the dimension combination labels.
Because the referee document is in an image format, OCR (optical character recognition) is needed to be carried out on the referee document to obtain a referee document text, the referee document text comprises case information, lawyer information, evidence information and judgment information, and the judgment information comprises case type, judge information, opponent lawyer information, case union, case handling region (province, city and district), court level, and trial program to obtain the case involved amount, judgment amount, property security duration, rechecking case-setting duration and the like with the finest granularity.
The basic information of the lawyers includes the level of lawyers, the field of adequacy, the time of practise (full-time lawyer's practical years), the academic, credit investigation conditions, the information of the law of residence, the job title, the result of the examination of the lawyers, etc.
The first keyword set is a set of indexes corresponding to basic information of lawyers (namely, a level of the lawyers, a good field, a time of practise (a full-time lawyer practice period), a academic calendar, a credit situation, information of a place law, a job title and a result of evaluating the lawyers) and the second keyword set is a set of indexes corresponding to decision information. Matching each index with basic information of lawyers and judge document text to obtain first and second target keywords, for example, the level of lawyer 1 is third-level lawyer, the field of law suit is civil lawyer, the time of practice is … … years, and the first target keywords of lawyer 1 are: third-level lawyers, civil lawsuits and practical years … … are matched respectively, a first target keyword and a second target keyword corresponding to each lawyer can be obtained, the first target keyword and the second target keyword are combined at will, and a plurality of dimension combination labels corresponding to each lawyer can be obtained.
The evaluation result corresponding to each dimension combination label is a score corresponding to each dimension combination label, and the determining the evaluation result corresponding to each dimension combination label includes:
And determining a target score corresponding to each dimension in each dimension combination label according to a predetermined keyword and score mapping relation table, and calculating the score corresponding to each dimension combination label based on a predetermined weight corresponding to each dimension and the target score.
And S2, establishing lawyer groups corresponding to the dimension combination labels, and distributing the lawyers to lawyer groups with different grades of the lawyer groups corresponding to the dimension combination labels according to the evaluation result.
For example, if the dimension combination corresponding to the dimension combination tag 1 is a fifth-level lawyer, a civil lawsuit, and a practitioner for 10 years, all lawyers satisfying the dimension combination are assigned to the lawyer group corresponding to the dimension combination tag 1, then the lawyers are ranked according to the order of the scores (i.e., the evaluation results) corresponding to the dimension combination from high to low, the lawyers in the lawyers are assigned to the lawyers of different levels according to the ranking results, for example, 90 lawyers in the lawyers corresponding to the dimension combination tag 1 can be divided into three levels of lawyers according to the scores, 30 lawyers in each level of lawyers can be classified into an expert group, a second level can be an excellent lawyer group, and a third level can be a common lawyer group.
S3, analyzing a judicial case data processing request sent by a user based on a client, acquiring a to-be-processed judicial case and a target dimension combination tag carried in the judicial case data processing request, calculating a first feature sequence of the to-be-processed judicial case based on a preset feature set, and inputting the first feature sequence into a trained case grade identification model to obtain a target case grade of the to-be-processed judicial case.
The target dimension combination label is a dimension combination input by a user, for example, a lawyer expected by the user meets the following conditions: civil litigation, shenzhen, two-trial and practitioner for 10 years, the target dimension combination label is the civil litigation, shenzhen, two-trial and practitioner for 10 years.
The calculating the first feature sequence of the judicial case to be processed based on the preset feature set comprises:
B1, word segmentation is carried out on the case information of the judicial case to be processed to obtain a word set;
B2, determining characteristic values of all the characteristics in the preset characteristic set based on the word set;
In this embodiment, the preset feature set includes: case type (case by + litigation stage/procedure), number of case involved, case jurisdiction, case target valuation, case difficulty level.
The difficulty level of the case is comprehensively determined according to the type of the case (case is formed by + litigation stage/program), the number of case participants, the jurisdiction of the case and the evaluation of the case targets, for example, the difficulty level of the second-trial case is higher than that of the first-trial case; counter charge, the difficulty of litigation cases of a plurality of parties or additional third parties is higher; large case targets, greater case difficulty related to various legal relationships, etc.
For example, if the words in the word set description region are Chongqing, the feature value of the case jurisdiction in the feature set is preset to be Chongqing.
B3, splicing the characteristic values to obtain a first sequence;
in this embodiment, the splicing order of each feature in the preset feature set is preset.
B4, converting the discrete data in the first sequence into numerical data to obtain a second sequence;
In this embodiment, the one-hot encoding is used to convert the discrete data into the numerical data, so that the distance between the subsequent features is calculated more reasonably, for example, the feature value of the case jurisdiction can be converted as follows (Beijing: 1, shanghai: 2, guangzhou: 3, shenzhen: 4).
And B5, performing normalization processing on the second sequence to obtain a first characteristic sequence of the judicial case to be processed.
The obtained first feature sequence is input into a trained case grade identification model, risk scores of the judicial cases to be processed can be output, target grades corresponding to the judicial cases to be processed can be determined according to risk score intervals corresponding to the case grades (high, medium and low), in the embodiment, the case grade identification model is a naive Bayesian model, and in other embodiments, the case grade identification model can also be a random forest model or a support vector machine model.
The training process of the case grade identification model comprises the following steps:
C1, calculating a second feature sequence corresponding to each history referee document in the first database based on the preset feature set;
c2, calculating a real risk value corresponding to each historical referee document;
According to the embodiment, the real risk scores of each historical referee document are calculated according to preset risk parameters, wherein the preset risk parameters comprise: judgment results, importance of legal rules, disputed focus, evidence flaw condition, jurisdictional court area and hierarchy.
The calculation formula of the real risk score is as follows:
pi＝a1*bi-1+a2*bi-2+…+an*bi-n
Wherein p i is the true risk score of the i-th history referee, b i-1 is the first parameter value of the i-th history referee, a 1 is the weight parameter of the first parameter, b i-2 is the second parameter value of the i-th history referee, a 2 is the weight parameter of the second parameter, b i-n is the n-th parameter value of the i-th history referee, and a n is the weight parameter of the n-th parameter.
And C3, inputting the second characteristic sequence into a case grade identification model to obtain predicted risk scores corresponding to the historical referee documents, and determining weight parameters of the case grade identification model by minimizing loss values between the predicted risk scores and the real risk scores to obtain a trained case grade identification model.
The calculation formula of the loss value is as follows:
wherein loss (q i,pi) is a loss value between the predicted risk score and the real risk score of the ith historical referee document, q i is the predicted risk score of the ith historical referee document, p i is the real risk score of the ith historical referee document, and c is the total number of the historical referee documents.
S4, determining a target lawyer group corresponding to the judicial case to be processed based on the target dimension combination label, determining a target lawyer group in the target lawyer group corresponding to the judicial case to be processed based on the target case grade, and transmitting a list of a preset number of lawyers in the target lawyer group to the client based on the evaluation result.
In the embodiment, the lawyer group corresponding to the target dimension combination label is used as the target lawyer group corresponding to the legal case to be processed, so that lawyers in the target lawyer group are more matched with the user requirements, and the lawyer matching accuracy is higher; according to the target case grade, a target lawyer group in a target lawyer group corresponding to the to-be-processed judicial case can be determined, for example, if the target case grade is high, a private lawyer group in the target lawyer group is taken as the target lawyer group, and part of lawyer groups in the target lawyer group can be removed, so that the judicial case data processing efficiency is higher; and then ordering lawyers in the target lawyers according to the evaluation results (namely scores) corresponding to the target dimension combination labels, and sending a list of a preset number (for example 5) of lawyers to the client.
In this embodiment, after transmitting the list of the preset number of attorneys in the target attorney group to the client based on the evaluation result, the method further includes:
Determining whether each index of the multiple indexes of the judicial case to be processed is normal or not based on the multiple indexes and the case information of the judicial case to be processed, generating an abnormal report when any index is abnormal, and sending the abnormal report to the client.
The index comprises: case timeliness, case evidence validity, case jurisdiction uniqueness, and the like. When the case timeliness is less than the timeliness threshold (e.g., 2 months), the case timeliness is considered abnormal; when case evidence includes evidence of disputes (e.g., blogs or other network evidence that is difficult to prove in time), the case evidence is considered to be abnormally valid; when the jurisdiction of the case is not unique (the case involves multiple regions), the case jurisdiction is considered to be unusual.
According to the judicial case data processing method provided by the embodiment of the invention, first, a lawyer portrait is established for each lawyer based on the basic information of the history judge document and the lawyers, the lawyer portrait comprises a plurality of dimension combination labels of the lawyers and evaluation results corresponding to the dimension combination labels, and the related information of each lawyer can be rapidly known through the established lawyer portrait; then, establishing lawyer groups corresponding to the dimension combination labels, distributing the lawyers to lawyer groups of different grades of the lawyer groups corresponding to the dimension combination labels according to the evaluation result, establishing corresponding lawyer groups for each dimension combination label, and distributing the lawyers to the lawyer groups of different grades, so that the matching of subsequent cases can be facilitated; finally, inputting the first feature sequence of the judicial case to be processed into a trained case grade identification model to obtain a target case grade of the case to be processed, determining a target lawyer group based on a target dimension combination label carried in a judicial case data processing request, enabling a user demand to be more matched with the target lawyer group, improving lawyer matching accuracy, determining a target lawyer group in the target lawyer group based on the target case grade, and enabling part of lawyer groups in the target lawyer group to be removed rapidly. Therefore, the invention improves the accuracy and the efficiency of processing the judicial case data.
Fig. 2 is a schematic block diagram of a judicial case data processing apparatus according to an embodiment of the present invention.
The judicial case data processing apparatus 100 of the present invention may be installed in an electronic device. Depending on the functions implemented, the judicial case data processing apparatus 100 may include a portrayal module 110, an assignment module 120, a parsing module 130, and a determination module 140. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
And the portrait module 110 is configured to obtain basic information of each history referee document in the first database and each lawyer in the second database, and establish a lawyer portrait for each lawyer based on the history referee text and the basic information, where the lawyer portrait includes a plurality of dimension combination tags of the lawyer and evaluation results corresponding to the dimension combination tags.
In this embodiment, the creating a lawyer portrait for each lawyer based on the history referee text and the basic information includes:
A1, performing OCR (optical character recognition) on the historical referee document to obtain referee document text, and determining lawyers corresponding to the referee document text;
A2, taking the set of basic information corresponding to each lawyer and the judge document text as the information set of each lawyer;
a3, matching the first keyword set with the basic information in the information set to obtain first target keywords of all lawyers;
A4, matching the second keyword set with the judge document text in the information set to obtain second target keywords of all lawyers;
A5, determining lawyer portraits of all lawyers based on the first target keywords and the second target keywords, randomly combining the first target keywords and the second target keywords to obtain a plurality of dimension combination labels corresponding to all the lawyers, and determining evaluation results corresponding to all the dimension combination labels.
Because the referee document is in an image format, OCR (optical character recognition) is needed to be carried out on the referee document to obtain a referee document text, the referee document text comprises case information, lawyer information, evidence information and judgment information, and the judgment information comprises case type, judge information, opponent lawyer information, case union, case handling region (province, city and district), court level, and trial program to obtain the case involved amount, judgment amount, property security duration, rechecking case-setting duration and the like with the finest granularity.
The basic information of the lawyers includes the level of lawyers, the field of adequacy, the time of practise (full-time lawyer's practical years), the academic, credit investigation conditions, the information of the law of residence, the job title, the result of the examination of the lawyers, etc.
The first keyword set is a set of indexes corresponding to basic information of lawyers (namely, a level of the lawyers, a good field, a time of practise (a full-time lawyer practice period), a academic calendar, a credit situation, information of a place law, a job title and a result of evaluating the lawyers) and the second keyword set is a set of indexes corresponding to decision information. Matching each index with basic information of lawyers and judge document text to obtain first and second target keywords, for example, the level of lawyer 1 is third-level lawyer, the field of law suit is civil lawyer, the time of practice is … … years, and the first target keywords of lawyer 1 are: third-level lawyers, civil lawsuits and practical years … … are matched respectively, a first target keyword and a second target keyword corresponding to each lawyer can be obtained, the first target keyword and the second target keyword are combined at will, and a plurality of dimension combination labels corresponding to each lawyer can be obtained.
The evaluation result corresponding to each dimension combination label is a score corresponding to each dimension combination label, and the determining the evaluation result corresponding to each dimension combination label includes:
And determining a target score corresponding to each dimension in each dimension combination label according to a predetermined keyword and score mapping relation table, and calculating the score corresponding to each dimension combination label based on a predetermined weight corresponding to each dimension and the target score.
And the allocation module 120 is configured to establish a lawyer group corresponding to each dimension combination label, and allocate each lawyer to a lawyer group with different grades of the lawyer group corresponding to each dimension combination label according to the evaluation result.
For example, if the dimension combination corresponding to the dimension combination tag 1 is a fifth-level lawyer, a civil lawsuit, and a practitioner for 10 years, all lawyers satisfying the dimension combination are assigned to the lawyer group corresponding to the dimension combination tag 1, then the lawyers are ranked according to the order of the scores (i.e., the evaluation results) corresponding to the dimension combination from high to low, the lawyers in the lawyers are assigned to the lawyers of different levels according to the ranking results, for example, 90 lawyers in the lawyers corresponding to the dimension combination tag 1 can be divided into three levels of lawyers according to the scores, 30 lawyers in each level of lawyers can be classified into an expert group, a second level can be an excellent lawyer group, and a third level can be a common lawyer group.
The analyzing module 130 is configured to analyze a judicial case data processing request sent by a user based on a client, obtain a to-be-processed judicial case and a target dimension combination tag carried in the judicial case data processing request, calculate a first feature sequence of the to-be-processed judicial case based on a preset feature set, and input the first feature sequence into a trained case class identification model to obtain a target case class of the to-be-processed judicial case.
The target dimension combination label is a dimension combination input by a user, for example, a lawyer expected by the user meets the following conditions: civil litigation, shenzhen, two-trial and practitioner for 10 years, the target dimension combination label is the civil litigation, shenzhen, two-trial and practitioner for 10 years.
The calculating the first feature sequence of the judicial case to be processed based on the preset feature set comprises:
B1, word segmentation is carried out on the case information of the judicial case to be processed to obtain a word set;
B2, determining characteristic values of all the characteristics in the preset characteristic set based on the word set;
In this embodiment, the preset feature set includes: case type (case by + litigation stage/procedure), number of case involved, case jurisdiction, case target valuation, case difficulty level.
The difficulty level of the case is comprehensively determined according to the type of the case (case is formed by + litigation stage/program), the number of case participants, the jurisdiction of the case and the evaluation of the case targets, for example, the difficulty level of the second-trial case is higher than that of the first-trial case; counter charge, the difficulty of litigation cases of a plurality of parties or additional third parties is higher; large case targets, greater case difficulty related to various legal relationships, etc.
For example, if the words in the word set description region are Chongqing, the feature value of the case jurisdiction in the feature set is preset to be Chongqing.
B3, splicing the characteristic values to obtain a first sequence;
in this embodiment, the splicing order of each feature in the preset feature set is preset.
B4, converting the discrete data in the first sequence into numerical data to obtain a second sequence;
In this embodiment, the one-hot encoding is used to convert the discrete data into the numerical data, so that the distance between the subsequent features is calculated more reasonably, for example, the feature value of the case jurisdiction can be converted as follows (Beijing: 1, shanghai: 2, guangzhou: 3, shenzhen: 4).
And B5, performing normalization processing on the second sequence to obtain a first characteristic sequence of the judicial case to be processed.
The obtained first feature sequence is input into a trained case grade identification model, risk scores of the judicial cases to be processed can be output, target grades corresponding to the judicial cases to be processed can be determined according to risk score intervals corresponding to the case grades (high, medium and low), in the embodiment, the case grade identification model is a naive Bayesian model, and in other embodiments, the case grade identification model can also be a random forest model or a support vector machine model.
The training process of the case grade identification model comprises the following steps:
C1, calculating a second feature sequence corresponding to each history referee document in the first database based on the preset feature set;
c2, calculating a real risk value corresponding to each historical referee document;
According to the embodiment, the real risk scores of each historical referee document are calculated according to preset risk parameters, wherein the preset risk parameters comprise: judgment results, importance of legal rules, disputed focus, evidence flaw condition, jurisdictional court area and hierarchy.
The calculation formula of the real risk score is as follows:
pi＝a1*bi-1+a2*bi-2+…+an*i-n
Wherein p i is the true risk score of the i-th history referee, b i-1 is the first parameter value of the i-th history referee, a 1 is the weight parameter of the first parameter, b i-2 is the second parameter value of the i-th history referee, a 2 is the weight parameter of the second parameter, b i-n is the n-th parameter value of the i-th history referee, and a n is the weight parameter of the n-th parameter.
And C3, inputting the second characteristic sequence into a case grade identification model to obtain predicted risk scores corresponding to the historical referee documents, and determining weight parameters of the case grade identification model by minimizing loss values between the predicted risk scores and the real risk scores to obtain a trained case grade identification model.
The calculation formula of the loss value is as follows:
wherein loss (q i,pi) is a loss value between the predicted risk score and the real risk score of the ith historical referee document, q i is the predicted risk score of the ith historical referee document, p i is the real risk score of the ith historical referee document, and c is the total number of the historical referee documents.
The determining module 140 is configured to determine, based on the target dimension combination tag, a target law group corresponding to the judicial case to be processed, determine, based on the target case level, a target law group in the target law group corresponding to the judicial case to be processed, and send, based on the evaluation result, a list of a preset number of attorneys in the target law group to the client.
In the embodiment, the lawyer group corresponding to the target dimension combination label is used as the target lawyer group corresponding to the legal case to be processed, so that lawyers in the target lawyer group are more matched with the user requirements, and the lawyer matching accuracy is higher; according to the target case grade, a target lawyer group in a target lawyer group corresponding to the to-be-processed judicial case can be determined, for example, if the target case grade is high, a private lawyer group in the target lawyer group is taken as the target lawyer group, and part of lawyer groups in the target lawyer group can be removed, so that the judicial case data processing efficiency is higher; and then ordering lawyers in the target lawyers according to the evaluation results (namely scores) corresponding to the target dimension combination labels, and sending a list of a preset number (for example 5) of lawyers to the client.
In this embodiment, after transmitting the list of the preset number of attorneys in the target attorney group to the client based on the evaluation result, the method further includes:
Determining whether each index of the multiple indexes of the judicial case to be processed is normal or not based on the multiple indexes and the case information of the judicial case to be processed, generating an abnormal report when any index is abnormal, and sending the abnormal report to the client.
The index comprises: case timeliness, case evidence validity, case jurisdiction uniqueness, and the like. When the case timeliness is less than the timeliness threshold (e.g., 2 months), the case timeliness is considered abnormal; when case evidence includes evidence of disputes (e.g., blogs or other network evidence that is difficult to prove in time), the case evidence is considered to be abnormally valid; when the jurisdiction of the case is not unique (the case involves multiple regions), the case jurisdiction is considered to be unusual.
Fig. 3 is a schematic structural diagram of an electronic device for implementing a judicial case data processing method according to an embodiment of the present invention.
The electronic device 1 is a device capable of automatically performing numerical calculation and/or information processing in accordance with a preset or stored instruction. The electronic device 1 may be a computer, a server group formed by a single network server, a plurality of network servers, or a cloud formed by a large number of hosts or network servers based on cloud computing, wherein the cloud computing is one of distributed computing, and is a super virtual computer formed by a group of loosely coupled computer sets.
In the present embodiment, the electronic device 1 includes, but is not limited to, a memory 11, a processor 12, and a network interface 13, which are communicably connected to each other via a system bus, and the memory 11 stores therein a judicial case data processing program 10, the judicial case data processing program 10 being executable by the processor 12. Fig. 3 shows only the electronic device 1 with components 11-13 and the judicial case data processing program 10, it being understood by those skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1 and may include fewer or more components than shown, or may combine certain components, or a different arrangement of components.
Wherein the storage 11 comprises a memory and at least one type of readable storage medium. The memory provides a buffer for the operation of the electronic device 1; the readable storage medium may be a non-volatile storage medium such as flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the readable storage medium may be an internal storage unit of the electronic device 1, such as a hard disk of the electronic device 1; in other embodiments, the nonvolatile storage medium may also be an external storage device of the electronic device 1, such as a plug-in hard disk provided on the electronic device 1, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD), or the like. In this embodiment, the readable storage medium of the memory 11 is generally used to store an operating system and various application software installed in the electronic device 1, for example, code of the judicial case data processing program 10 in one embodiment of the present invention. Further, the memory 11 may be used to temporarily store various types of data that have been output or are to be output.
Processor 12 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 12 is typically used to control the overall operation of the electronic device 1, such as performing control and processing related to data interaction or communication with other devices, etc. In this embodiment, the processor 12 is configured to execute the program code or process data stored in the memory 11, for example, execute the judicial case data processing program 10.
The network interface 13 may comprise a wireless network interface or a wired network interface, the network interface 13 being used for establishing a communication connection between the electronic device 1 and a client (not shown).
Optionally, the electronic device 1 may further comprise a user interface, which may comprise a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device 1 and for displaying a visual user interface.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The judicial case data processing program 10 stored in the memory 11 of the electronic device 1 is a combination of instructions that, when executed in the processor 12, can implement:
Acquiring basic information of each historical referee document in a first database and each lawyer in a second database, and establishing lawyer portraits for each lawyer based on the historical referee text and the basic information, wherein the lawyer portraits comprise a plurality of dimension combination tags of the lawyer and evaluation results corresponding to the dimension combination tags;
Establishing lawyer groups corresponding to the dimension combination labels, and distributing the lawyers to lawyer groups with different grades of the lawyer groups corresponding to the dimension combination labels according to the evaluation result;
Analyzing a judicial case data processing request sent by a user based on a client, acquiring a to-be-processed judicial case and a target dimension combination tag carried in the judicial case data processing request, calculating a first feature sequence of the to-be-processed judicial case based on a preset feature set, and inputting the first feature sequence into a trained case grade identification model to obtain a target case grade of the to-be-processed judicial case;
And determining a target lawyer group corresponding to the to-be-processed judicial case based on the target dimension combination label, determining a target lawyer group in the target lawyer group corresponding to the to-be-processed judicial case based on the target case grade, and transmitting a list of a preset number of lawyers in the target lawyer group to the client based on the evaluation result.
Specifically, the specific implementation method of the processor 12 to the judicial case data processing program 10 described above may refer to the description of the related steps in the corresponding embodiment of fig. 1, which is not repeated herein. It should be emphasized that, to further ensure the privacy and security of the above-mentioned judicial cases to be processed, the above-mentioned judicial cases to be processed may also be stored in a node of a blockchain.
Further, the modules/units integrated in the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. The computer readable medium may be nonvolatile or nonvolatile. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
The computer readable storage medium stores the judicial case data processing program 10, where the judicial case data processing program 10 may be executed by one or more processors, and the specific implementation of the computer readable storage medium is substantially the same as the embodiments of the judicial case data processing method described above, and is not described herein.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The blockchain (Blockchain), essentially a de-centralized database, is a string of data blocks that are generated in association using cryptographic methods, each of which contains information from a batch of network transactions for verifying the validity (anti-counterfeit) of its information and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the system claims can also be implemented by means of software or hardware by means of one unit or means. The terms second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.

Claims (6)

1. A method for judicial case data processing, the method comprising:
acquiring basic information of each historical referee document in a first database and each lawyer in a second database, and establishing lawyer portraits for each lawyer based on the historical referee documents and the basic information, wherein the lawyer portraits comprise a plurality of dimension combination tags of the lawyer and evaluation results corresponding to the dimension combination tags;
Establishing lawyer groups corresponding to the dimension combination labels, and distributing the lawyers to lawyer groups with different grades of the lawyer groups corresponding to the dimension combination labels according to the evaluation result;
Analyzing a judicial case data processing request sent by a user based on a client, acquiring a to-be-processed judicial case and a target dimension combination tag carried in the judicial case data processing request, calculating a first feature sequence of the to-be-processed judicial case based on a preset feature set, and inputting the first feature sequence into a trained case grade identification model to obtain a target case grade of the to-be-processed judicial case;
Determining a target lawyer group corresponding to the to-be-processed judicial case based on the target dimension combination label, determining a target lawyer group in the target lawyer group corresponding to the to-be-processed judicial case based on the target case grade, and transmitting a list of a preset number of lawyers in the target lawyer group to the client based on the evaluation result;
Wherein, based on the history referee document and the basic information, a lawyer portrait is established for each lawyer, including: performing OCR (optical character recognition) on the historical referee document to obtain referee document text, and determining lawyers corresponding to the referee document text; taking the set of basic information corresponding to each lawyer and judge document text as the information set of each lawyer; matching the first keyword set with the basic information in the information set to obtain first target keywords of all lawyers; matching the second keyword set with the judge document text in the information set to obtain second target keywords of all lawyers; determining lawyer portraits of all lawyers based on the first target keywords and the second target keywords, randomly combining the first target keywords and the second target keywords to obtain a plurality of dimension combination labels corresponding to all lawyers, and determining evaluation results corresponding to all dimension combination labels;
The calculating the first feature sequence of the judicial case to be processed based on the preset feature set comprises the following steps: word segmentation is carried out on the case information of the judicial cases to be processed to obtain a word set; determining feature values of all features in the preset feature set based on the word set; splicing the characteristic values to obtain a first sequence; converting the discrete data in the first sequence into numerical data to obtain a second sequence; performing normalization processing on the second sequence to obtain a first characteristic sequence of the judicial case to be processed;
The training process of the case grade identification model comprises the following steps: calculating a second feature sequence corresponding to each history referee document in the first database based on the preset feature set; calculating a real risk value corresponding to each history referee document; and inputting the second characteristic sequence into a case grade identification model to obtain predicted risk scores corresponding to the historical referee documents, and determining weight parameters of the case grade identification model by minimizing loss values between the predicted risk scores and the real risk scores to obtain a trained case grade identification model.
2. The judicial case data processing method according to claim 1, wherein after transmitting a list of a preset number of attorneys in the target set of attorneys to the client based on the evaluation result, the method further comprises:
Determining whether each index of the multiple indexes of the judicial case to be processed is normal or not based on the multiple indexes and the case information of the judicial case to be processed, generating an abnormal report when any index is abnormal, and sending the abnormal report to the client.
3. The judicial case data processing method according to claim 1, wherein the calculation formula of the loss value is:
Wherein, For the loss value between the predicted risk score and the true risk score of the i-th historical referee document,For the predicted risk score of the i-th historic referee document,The true risk score of the i-th historical referee document and c the total number of the historical referee documents.
4. A judicial case data processing apparatus for implementing the judicial case data processing method according to any one of claims 1 to 3, the apparatus comprising:
The portrait module is used for acquiring basic information of each historical referee document in the first database and each lawyer in the second database, and establishing a lawyer portrait for each lawyer based on the historical referee documents and the basic information, wherein the lawyer portrait comprises a plurality of dimension combination tags of the lawyer and evaluation results corresponding to the dimension combination tags;
The distribution module is used for establishing lawyer groups corresponding to the dimension combination labels, and distributing the lawyers to the lawyer groups with different grades of the lawyer groups corresponding to the dimension combination labels according to the evaluation result;
The analysis module is used for analyzing a judicial case data processing request sent by a user based on a client, acquiring a to-be-processed judicial case and a target dimension combination label carried in the judicial case data processing request, calculating a first feature sequence of the to-be-processed judicial case based on a preset feature set, and inputting the first feature sequence into a trained case grade identification model to obtain a target case grade of the to-be-processed judicial case;
The determining module is used for determining a target lawyer group corresponding to the judicial case to be processed based on the target dimension combination label, determining a target lawyer group in the target lawyer group corresponding to the judicial case to be processed based on the target case grade, and sending a list of a preset number of lawyers in the target lawyer group to the client based on the evaluation result.
5. An electronic device, the electronic device comprising:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores a judicial case data processing program executable by the at least one processor to enable the at least one processor to perform the judicial case data processing method of any one of claims 1 to 3.
6. A computer readable storage medium having stored thereon a judicial case data processing program executable by one or more processors to implement the judicial case data processing method of any of claims 1 to 3.
CN202011299393.2A 2020-11-19 2020-11-19 Judicial case data processing method and device, electronic equipment and readable storage medium Active CN112288604B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011299393.2A CN112288604B (en) 2020-11-19 2020-11-19 Judicial case data processing method and device, electronic equipment and readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011299393.2A CN112288604B (en) 2020-11-19 2020-11-19 Judicial case data processing method and device, electronic equipment and readable storage medium

Publications (2)

Publication Number Publication Date
CN112288604A CN112288604A (en) 2021-01-29
CN112288604B true CN112288604B (en) 2024-07-02

Family

ID=74398035

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011299393.2A Active CN112288604B (en) 2020-11-19 2020-11-19 Judicial case data processing method and device, electronic equipment and readable storage medium

Country Status (1)

Country Link
CN (1) CN112288604B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113704600A (en) * 2021-06-18 2021-11-26 诺正集团股份有限公司 Information processing method, device and equipment based on data interaction and storage medium
CN113344433A (en) * 2021-06-28 2021-09-03 平安信托有限责任公司 Product matching method and device, electronic equipment and readable storage medium
CN113779969A (en) * 2021-09-16 2021-12-10 平安国际智慧城市科技股份有限公司 Case information processing method, device, equipment and medium based on artificial intelligence
CN114358983A (en) * 2021-12-27 2022-04-15 北京金堤科技有限公司 Lawyer recommendation method and device and readable storage medium
CN117610990B (en) * 2023-11-13 2024-06-28 中国通信建设集团有限公司数智科创分公司 Intelligent judicial case quality evaluation system and method based on big data

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107563912A (en) * 2017-08-29 2018-01-09 广东蔚海数问大数据科技有限公司 A kind of lawyer recommends method and system
CN110175233A (en) * 2019-03-07 2019-08-27 平安科技（深圳）有限公司 Method, apparatus, computer installation and the storage medium of target subject portrait analysis

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9836436B2 (en) * 2010-08-05 2017-12-05 Thomson Reuters Global Resources Unlimited Company Systems, methods, software and interfaces for performing enhanced document processing and document outlining
US20200202466A1 (en) * 2018-12-21 2020-06-25 II Kenneth N. Sortedahl Litigation management

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107563912A (en) * 2017-08-29 2018-01-09 广东蔚海数问大数据科技有限公司 A kind of lawyer recommends method and system
CN110175233A (en) * 2019-03-07 2019-08-27 平安科技（深圳）有限公司 Method, apparatus, computer installation and the storage medium of target subject portrait analysis

Also Published As

Publication number Publication date
CN112288604A (en) 2021-01-29

Similar Documents

Publication Publication Date Title
CN112288604B (en) Judicial case data processing method and device, electronic equipment and readable storage medium
CN112182224A (en) Referee document abstract generation method and device, electronic equipment and readable storage medium
WO2022160442A1 (en) Answer generation method and apparatus, electronic device, and readable storage medium
CN112860737B (en) Data query method and device, electronic equipment and readable storage medium
CN113946690A (en) Potential customer mining method and device, electronic equipment and storage medium
CN111639706A (en) Personal risk portrait generation method based on image set and related equipment
CN112597135A (en) User classification method and device, electronic equipment and readable storage medium
CN113178071A (en) Driving risk level identification method and device, electronic equipment and readable storage medium
TW201531991A (en) A computational device for data management and decision
CN113837631A (en) Employee evaluation method and device, electronic device and readable storage medium
CN113065947A (en) Data processing method, device, equipment and storage medium
CN116578696A (en) Text abstract generation method, device, equipment and storage medium
CN113656586B (en) Emotion classification method, emotion classification device, electronic equipment and readable storage medium
CN113657546B (en) Information classification method, device, electronic equipment and readable storage medium
CN113157890B (en) Intelligent question-answering method and device, electronic equipment and readable storage medium
CN114581177B (en) Product recommendation method, device, equipment and storage medium
CN113240325B (en) Data processing method, device, equipment and storage medium
CN113706252B (en) Product recommendation method and device, electronic equipment and storage medium
CN113269179B (en) Data processing method, device, equipment and storage medium
CN115577983A (en) Enterprise task matching method based on block chain, server and storage medium
CN112561500B (en) Salary data generation method, device, equipment and medium based on user data
TW201539217A (en) A document analysis system, document analysis method and document analysis program
CN111861227A (en) User recommendation method and device based on membership analysis, electronic equipment and medium
CN113312482A (en) Question classification method and device, electronic equipment and readable storage medium
CN113064984A (en) Intention recognition method and device, electronic equipment and readable storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant