CN111222308A - Case decision book generation method and device and electronic equipment - Google Patents
Case decision book generation method and device and electronic equipment Download PDFInfo
- Publication number
- CN111222308A CN111222308A CN201911300477.0A CN201911300477A CN111222308A CN 111222308 A CN111222308 A CN 111222308A CN 201911300477 A CN201911300477 A CN 201911300477A CN 111222308 A CN111222308 A CN 111222308A
- Authority
- CN
- China
- Prior art keywords
- case
- data
- target
- litigation
- judgment
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000012545 processing Methods 0.000 claims abstract description 35
- 238000007405 data analysis Methods 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims description 26
- 238000012937 correction Methods 0.000 claims description 15
- 238000010801 machine learning Methods 0.000 claims description 13
- 230000015654 memory Effects 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 5
- 238000005111 flow chemistry technique Methods 0.000 abstract description 6
- 230000008569 process Effects 0.000 description 21
- 206010039203 Road traffic accident Diseases 0.000 description 15
- 238000010586 diagram Methods 0.000 description 6
- 230000004044 response Effects 0.000 description 4
- 230000002349 favourable effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 210000001503 joint Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000012015 optical character recognition Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000003999 initiator Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Technology Law (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A case judgment generation method is disclosed, which is applied to an auxiliary judgment system and used for receiving litigation data corresponding to a target case; the litigation data at least comprises litigation data submitted by the original reports and the reports and court trial record data; performing data analysis on the litigation data to obtain case element data corresponding to the target case; wherein the case element data indicates case critical features of the target case; inputting the case element data into a case trial model obtained by training for data processing to obtain prejudgment data corresponding to the target case; and generating case judgment books corresponding to the target cases based on the prejudgment data and the case element data, so that the case judgment books are quickly and automatically generated, and the case flow processing and case judging efficiencies are improved.
Description
Technical Field
The present application relates to the field of computer application technologies, and in particular, to a case decision generating method, an apparatus, an electronic device, and a machine-readable storage medium.
Background
The prosecution refers to a legal document which is requested to do a lawsuit from a court of law because citizens or legal persons are infringed by their own legal interests. Depending on the nature and purpose of litigation, the appetitive states may include civil appetitive states, administrative appetitive states, criminal self-appetitive states, and the like.
The answer form refers to a legal document which is reported to answer and dispute the content of the appeal form according to facts and laws within the legal time limit. The answer form is a right legally given to the party of the case in the state of being reported, which has the freedom to handle the answer form, and can answer or silence. The answer form is favorable for protecting the right and the legal right of the bulletin; the method is favorable for the court to judge the fact of the court on the basis of comprehensively knowing the case and make correct judgment.
The case judgment is a legal document written by a court after the case judgment is finished. For example, case decisions may include civil decisions, criminal decisions, administrative decisions, criminal incidental civil decisions, and the like.
Disclosure of Invention
The application provides a case judgment generation method, which is applied to an auxiliary trial system and comprises the following steps:
receiving litigation data corresponding to the target case; the litigation data at least comprises litigation data submitted by the original reports and the reports and court trial record data;
performing data analysis on the litigation data to obtain case element data corresponding to the target case; wherein the case element data indicates case critical features of the target case;
inputting the case element data into a case trial model obtained by training for data processing to obtain prejudgment data corresponding to the target case;
and generating case judgment books corresponding to the target cases based on the prejudgment data and the case element data.
Optionally, the performing data analysis on the litigation data to obtain case element data corresponding to the target case includes:
performing semantic analysis on the litigation data to obtain a plurality of feature data indicating case features of the target case;
screening the characteristic data to obtain key data indicating the case key characteristics of the target case;
and generating a key data set based on the obtained key data, wherein the key data set is used as case element data corresponding to the target case.
Optionally, the performing semantic analysis on the litigation data to obtain a plurality of feature data indicating case features of the target case includes:
carrying out data processing on the litigation data to obtain textual litigation data;
and performing semantic analysis on the obtained textual litigation data to obtain a plurality of feature data indicating case features of the target case.
Optionally, after obtaining the prejudgment data corresponding to the target case, the method further includes:
outputting the prejudgment data corresponding to the target case to the user so that the user can update the prejudgment data.
Optionally, the generating a case decision corresponding to the target case based on the prejudgment data and the case element data includes:
receiving data update of the user on the prejudgment data, inputting the updated prejudgment data to the case judgment model again for data processing, and obtaining prejudgment correction data corresponding to the target case;
and generating case judgment books corresponding to the target cases based on the prejudgment correction data and the case element data.
Optionally, after generating the case decision corresponding to the target case, the method further includes:
searching in a preset historical case library based on the case element data to obtain a historical case similar to the case of the target case;
and outputting the historical case judgment corresponding to the historical case to the user so that the user corrects the case judgment corresponding to the target case based on the historical case judgment.
Optionally, the case trial model is a machine learning model obtained by training litigation data associated with a time sequence based on historical cases.
Optionally, the case trial model is a machine learning model constructed based on an LSTM neural network.
The present application further provides a case decision making apparatus, which is applied to an auxiliary trial system, the apparatus comprising:
the receiving module is used for receiving litigation data corresponding to the target case; the litigation data at least comprises litigation data submitted by the original reports and the reports and court trial record data;
the analysis module is used for carrying out data analysis on the litigation data to obtain case element data corresponding to the target case; wherein the case element data indicates case critical features of the target case;
the processing module is used for inputting the case element data into a case trial model obtained by training for data processing to obtain prejudgment data corresponding to the target case;
and the generating module is used for generating a case judgment book corresponding to the target case based on the prejudgment data and the case element data.
Optionally, the analysis module further:
performing semantic analysis on the litigation data to obtain a plurality of feature data indicating case features of the target case;
screening the characteristic data to obtain key data indicating the case key characteristics of the target case;
and generating a key data set based on the obtained key data, wherein the key data set is used as case element data corresponding to the target case.
Optionally, the analysis module further:
carrying out data processing on the litigation data to obtain textual litigation data;
and performing semantic analysis on the obtained textual litigation data to obtain a plurality of feature data indicating case features of the target case.
Optionally, after obtaining the prejudgment data corresponding to the target case, the processing module further:
outputting the prejudgment data corresponding to the target case to the user so that the user can update the prejudgment data.
Optionally, based on the prejudgment data and the case element data, the generating module further:
receiving data update of the user on the prejudgment data, inputting the updated prejudgment data to the case judgment model again for data processing, and obtaining prejudgment correction data corresponding to the target case;
and generating case judgment books corresponding to the target cases based on the prejudgment correction data and the case element data.
Optionally, after generating the case decision corresponding to the target case, the generating module further:
searching in a preset historical case library based on the case element data to obtain a historical case similar to the case of the target case;
and outputting the historical case judgment corresponding to the historical case to the user so that the user corrects the case judgment corresponding to the target case based on the historical case judgment.
Optionally, the case trial model is a machine learning model obtained by training litigation data associated with a time sequence based on historical cases.
Optionally, the case trial model is a machine learning model constructed based on an LSTM neural network.
The application also provides an electronic device, which comprises a communication interface, a processor, a memory and a bus, wherein the communication interface, the processor and the memory are mutually connected through the bus;
the memory stores machine-readable instructions, and the processor executes the method by calling the machine-readable instructions.
With the above embodiments, based on receiving litigation data corresponding to a target case; carrying out data analysis on the litigation data to obtain case element data corresponding to the target case; and inputting the case element data into a case trial model for data processing to obtain prejudgment data, and generating a case judgment book corresponding to the target case based on the prejudgment data and the case element data, so that the case judgment book is quickly and automatically generated, and the case flow processing and case trial efficiency is improved.
Drawings
FIG. 1 is a schematic diagram of a case decision process provided by an exemplary embodiment;
FIG. 2 is a flow chart of a case decision making method provided by an exemplary embodiment;
FIG. 3 is a hardware block diagram of an electronic device provided by an exemplary embodiment;
fig. 4 is a block diagram of a case decision generating apparatus according to an exemplary embodiment.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
In order to make those skilled in the art better understand the technical solutions in the embodiments of the present specification, the following briefly describes the related art for generating case judgment specifications related to the embodiments of the present specification.
Referring to fig. 1, fig. 1 is a schematic diagram of a case decision process according to an embodiment of the present disclosure.
The case decision process as shown in fig. 1 includes: setting up a case, trial and error in a court and declaring a case; the participating objects involved in the case include: original notice, quilt notice and court.
As shown in fig. 1, during the process of filing, the original may initiate a litigation request to the court (step S1 shown in fig. 1); after the court determines that the litigation request of the original report meets the requirements of the proposal, the proposal is carried out; the court obtains the prosecution data (step S2 shown in fig. 1); further, the court sends a case citation to the notice (step S3 shown in fig. 1); and obtaining the reported litigation data (step S4 shown in fig. 1).
As shown in FIG. 1, in the process of trial in the court, the court-summoning foreigners, the announcements and the persons (such as lawyers or witnesses) related to the case are judged, the court trial and the current trial are carried out, and all data (such as evidences, testimonials and answer processes) of the process during the court trial are saved as a court trial record (step S5 shown in FIG. 1).
As shown in fig. 1, after the trial of the court is completed, the case judgment is manually written by the judge through case inference analysis, and the case is declared according to the case judgment (step S6 shown in fig. 1), so that the case declaration is completed, and usually, the judge is declared and called in the court.
Based on the scenario of case judgment process shown in fig. 1, on one hand, the information interaction, collection and arrangement in the original report, the reported report and the trial process are all processed manually, so that the problem of low case flow processing efficiency exists, and on the other hand, the problem of large case judgment scale and standard difference possibly exists due to different individual experience of judges.
On the basis of the case judgment process shown above, the present specification aims to provide a technical solution for conducting case judgment based on an auxiliary judgment system and automatically generating a case judgment.
When the method is realized, the auxiliary judging system receives litigation data corresponding to the target case; the litigation data at least comprises litigation data submitted by the original reports and the reports and court trial record data.
Further, the auxiliary judging system performs data analysis on the litigation data to obtain case element data corresponding to the target case; wherein the case element data is key data indicating case key features of the target case; inputting case element data into a case trial model obtained by training for data processing to obtain prejudgment data corresponding to a target case; and generating case judgment books corresponding to the target cases based on the prejudgment data and the case element data.
In the above technical solution, based on receiving litigation data corresponding to a target case; carrying out data analysis on the litigation data to obtain case element data corresponding to the target case; and inputting the case element data into a case trial model for data processing to obtain prejudgment data, and generating a case judgment book corresponding to the target case based on the prejudgment data and the case element data, so that the case judgment book is quickly and automatically generated, and the case flow processing and case trial efficiency is improved.
The present specification is described below with reference to specific embodiments and specific application scenarios.
Referring to fig. 2, fig. 2 is a flowchart of a case judgment generation method provided in an embodiment of the present disclosure, the method is applied to an auxiliary judgment system, and the method performs the following steps:
And step 206, inputting the case element data into a case trial model obtained by training for data processing to obtain prejudgment data corresponding to the target case.
And 208, generating a case judgment book corresponding to the target case based on the prejudgment data and the case element data.
In the present specification, the auxiliary trial system refers to any type of machine or machine cluster for assisting court to collect case information and make a trial on a case.
For example, in practical applications, the auxiliary judgment system may be a local machine or a local machine cluster for assisting a court to collect case information and judge cases, or a cloud machine or a local machine cluster for assisting a court to collect case information and judge cases.
In the present specification, the above-mentioned target cases may include any type of legal cases.
For example, in practical applications, the target cases may include civil cases, criminal cases, administrative cases, and the like.
In the present specification, the litigation data includes litigation data corresponding to the target case; the litigation data at least comprises litigation data submitted by the original reports and the reports and court trial record data.
For example, in practical applications, the litigation data may include litigation data such as a starting form and evidence submitted in the original report, litigation data such as a response form and evidence submitted in the report, and court trial entry data for all information during the trial process recorded at the court trial.
In the present specification, the auxiliary judgment system receives the litigation data corresponding to the target case.
For example, in practical applications, the auxiliary trial system may receive the litigation data corresponding to the target case through a web page or APP software.
In the process of receiving the litigation data, the auxiliary trial system may collect data contents and formats conforming to the legal regulations of the target case from the original report and the reported subject in the form of a web page or APP software. Therefore, the case flow processing efficiency is greatly improved.
For example, the target case may be a civil case of a traffic accident dispute, and in the process of receiving the litigation data, the auxiliary trial system may collect, from the original report and the noticed report, an appeal form, a response form, various evidences based on file formats such as text, pictures, and videos, and the like, which meet the civil law of the target case, in a form of a web page, APP software, or the like.
Of course, in practical applications, the auxiliary trial system may also collect court trial record data and the like of the target case, which meet the civil law, from a court (court clerk).
In the present specification, the case element data is key data indicating key features of the target case.
For example, in practical applications, the case element data may include key data indicating a case type of the target case; the case element data may further include key data indicating original complaints and core complaints of the target case; the case element data can also comprise key data indicating the original evidence and the important evidence of the defended evidence of the target case; the case element data may further include key data indicating important contents in the court trial transcript data of the target case.
In the present specification, upon receiving the litigation data, the auxiliary judging system performs data analysis on the litigation data to obtain the case element data corresponding to the target case; wherein the case element data indicates case key features of the target case.
In one embodiment, the auxiliary judgment system performs semantic analysis on the litigation data to obtain a plurality of feature data indicating case features of the target case.
For example: the auxiliary judging system can perform semantic analysis on the litigation data to obtain a plurality of feature data indicating case features of the target case; the feature data may include a plurality of keywords indicating the case features of the target case and values corresponding to the keywords, respectively.
In one embodiment, the auxiliary judging system performs data processing on the litigation data to obtain the textual litigation data, in the process of performing semantic analysis on the litigation data to obtain a plurality of feature data indicating case features of the target case.
For example, in practical applications, the litigation data may include text data such as a prosecution form, a quiz form, and a text court trial record, and the litigation data may include non-textual data such as a picture or a video of the original or the submitted notice, and data such as a text trial record. The auxiliary judgment system may perform data processing on the litigation data based on an OCR (Optical Character Recognition) algorithm, a voice Recognition algorithm, and an image and video Recognition algorithm, and perform Recognition processing on the litigation data including any one or more of a picture, a voice, and a video, respectively, to obtain textual litigation data.
In the present specification, the auxiliary judgment system may perform semantic analysis on the obtained textual litigation data to obtain a plurality of feature data indicating case features of the target case.
Taking a target case as a civil case of the traffic accident dispute for example, the auxiliary judging system may perform semantic analysis on the obtained textual litigation data based on an NLP (Natural Language Processing) algorithm to obtain a plurality of feature data indicating case features of the civil case of the traffic accident dispute; the characteristic data of the target case may include all semantically identifiable keywords and corresponding values thereof in a text after the textualization corresponding to the court trial record data, the complaint state, the answer state, the original evidence, the defended evidence and the court trial record data of the case characteristic of the civil case indicating that the target case is a traffic accident dispute.
In the present specification, the key data refers to data indicating a case key feature of the target case, among a plurality of feature data of case features of the target case.
Continuing the example above, the key characteristic data may include a medical reimbursement amount claim of the original report indicating the case key characteristics of the target case, a paid medical expense invoice slip submitted by the original report, a paid medical expense invoice slip submitted by the subject report, a receipt, an insurance reimbursement policy record, and the like. When the method is implemented, the key feature data can be saved based on a JSON (JavaScript Object Notation) format.
In the present specification, after the semantic analysis of the litigation data is performed to obtain a plurality of feature data indicating the case feature of the target case, the auxiliary judgment system performs data screening on the plurality of feature data to obtain the key data.
Continuing to illustrate in the above example, the auxiliary trial system performs data screening on a plurality of feature data (all semantically identifiable keywords and corresponding values) of the civil case indicating that the case feature of the target case is a traffic accident dispute, and obtains key data indicating the case key feature of the target case, for example, the key data may include { "original reported identity information": original defended identification number }, { "medical compensation amount appeal of original defending in appeal": amount X, evidence 1 of a paid medical expense invoice slip submitted for original: amount B1, proof of original submission of invoice document for spent medical costs 2 ": the amount B2. "proof N of the invoice document of the expended medical expense submitted by the original: amount BN }, { "amount of medical compensation providable by the notice in answer form": amount Y, { "evidence 1 of reimbursed medical expense invoice document submitted by the notice": amount P1, "proof of reimbursed medical expense invoice document submitted by notice 2": the amount P2, an "proof N of the invoice document for reimbursed medical fees submitted by the notice": amount PN, and { "court trial record information": original court trial speech word record } and the like.
In this specification, the case element data may include all key data obtained by the auxiliary judgment system performing data analysis on the litigation data.
For example, the case element data may include key data obtained by the auxiliary judgment system performing data analysis on litigation data submitted by a source, may include key data obtained by the auxiliary judgment system performing data analysis on litigation data submitted by a subject, and may include key data obtained by the auxiliary judgment system performing data analysis on court history data.
In the present specification, the auxiliary trial system may further generate a key data set based on the obtained key data as case element data corresponding to the target case.
Continuing the example above, the auxiliary judging system collects all the key data obtained by performing data analysis on the litigation data to generate a key data set as case element data corresponding to the target case.
In the present specification, the case history is a case that has been judged similarly to the case of the target case in the case history library of the auxiliary judgment system.
Taking the target case as a civil case of the traffic accident dispute, for example, the historical case may include a plurality of civil cases of the traffic accident dispute, which have been judged and are similar to the case of the target case, in the historical case library of the auxiliary judging system.
In the present specification, the case trial model is a machine learning model that is mounted in the auxiliary trial system and is used to simulate legal logics such as case analysis, inference, case judgment, and the like performed by a judge.
In one embodiment, the case trial model is a machine learning model obtained by training based on litigation data related to the existence timing of the historical cases.
Taking a target case as a civil case of the traffic accident dispute for example, wherein the case judging model is obtained by training litigation data corresponding to a plurality of historical civil cases of the traffic accident dispute which are similar to the case of the target case and have completed judgment; the litigation data of each historical civil case may include original reports, litigation data submitted by the reports and court trial record data corresponding to the historical case and having time sequence correlation.
In one embodiment, the case trial model is a machine learning model constructed based on an LSTM neural network.
For example, in practical applications, the auxiliary trial system may vectorize litigation data associated with the existence timing sequence of the history case, and input the vectorized litigation data to a machine model constructed based on an LSTM (Long Short-Term Memory) neural network for training, so as to complete training of model parameters of the machine model.
In this specification, the prejudgment data refers to a machine judgment result output by the auxiliary judgment system and corresponding to the case of the target case, a judgment process and a judgment conclusion.
Taking a target case as a civil case of a traffic accident dispute for example, the prejudgment data may include a machine judgment result output by the auxiliary judgment system and corresponding to the civil case of the traffic accident dispute; the judgment result may include the reason of the civil case, the trial process and the trial conclusion of the traffic accident dispute.
In the present specification, after the case element data is obtained, the auxiliary judgment system inputs the case element data to the case judgment model and performs data processing to obtain the prejudgment data.
Continuing the example following the example above, the case element data described above may include { "original advertised identity information": original defended identification number }, { "medical compensation amount appeal of original defending in appeal": amount X, evidence 1 of a paid medical expense invoice slip submitted for original: amount B1, proof of original submission of invoice document for spent medical costs 2 ": the amount B2. "proof N of the invoice document of the expended medical expense submitted by the original: amount BN }, { "amount of medical compensation providable by the notice in answer form": amount Y, { "evidence 1 of reimbursed medical expense invoice document submitted by the notice": amount P1, "proof of reimbursed medical expense invoice document submitted by notice 2": the amount P2, an "proof N of the invoice document for reimbursed medical fees submitted by the notice": amount PN, and { "court trial record information": original reported court trial uttered word records }, the auxiliary trial system inputs the case element data into the case trial model for data processing to obtain pre-decision data corresponding to the target case; the pre-judgment data can include the reasons of the civil case of the traffic accident dispute, the judging process and the judging conclusion (such as whether the original claim compensation amount in the complaint or the automatically generated judgment claim compensation amount is supported).
In one embodiment, after obtaining the prejudgment data corresponding to the target case, the auxiliary trial system outputs the prejudgment data corresponding to the target case to a user so that the user updates the prejudgment data.
Continuing with the above example, the prejudgment data includes an automatically generated determined compensation amount of 10 ten thousand yuan, and after the prejudgment data corresponding to the target case is obtained, the auxiliary judging system outputs the prejudgment data corresponding to the target case to a judge (that is, a user of the auxiliary judging system), so that the judge can perform data update on the prejudgment data, for example, after a court agreement, if the determined compensation amount of 15 ten thousand yuan is more appropriate than 10 ten thousand yuan, the judge can update the prejudgment data output by the auxiliary judging system to 15 ten thousand yuan, and submit the updated prejudgment data to the auxiliary judging system.
Of course, in practical applications, in the case trial process based on the auxiliary trial system, the judge may modify the pre-judgment data many times and submit the pre-judgment data to the auxiliary trial system, so that the auxiliary trial system performs data processing on the case based on the updated pre-judgment data and the trial model many times to complete machine trial. Therefore, the case judging efficiency is greatly improved.
In the present specification, the auxiliary trial system may further generate a case judgment book corresponding to the target case based on the prejudgment data and the case element data.
For example, in practical applications, the auxiliary trial system may generate case judgment documents corresponding to the target cases based on the prejudgment data (which may include the case and trial process and trial conclusion corresponding to the target cases) and the case element data (which may include identity information of the original defendant, key data in the court trial record, and key data in the appeal and answer forms).
In one embodiment, in the process of generating a case judgment rule corresponding to the target case based on the prejudged data and the case element data, the auxiliary judging system receives data update of the prejudged data by a user, and inputs the updated prejudged data into the case judging model again for data processing to obtain prejudged corrected data corresponding to the target case; and generating a case judgment book corresponding to the target case based on the prejudgment correction data and the case element data.
Continuing to take the example, the auxiliary judging system receives data update of the judge data by a judge, and inputs the updated judge data into the case judging model again for data processing to obtain judge correction data corresponding to the target case; based on a judgment template corresponding to the target case and legally stipulated, the case element data (such as identity information of an original defendant, key data in an original defendant evidence, key data in a court trial record and key data in a appeal form and a response form) are transmitted; and filling the prejudgment correction data (including case information, a judging process and a judging conclusion, for example) into the judgment case template so as to generate a case judgment case corresponding to the target case.
In one embodiment, after a case decision corresponding to the target case is generated, the auxiliary trial system searches a preset history case library based on the case element data to obtain a history case similar to the case of the target case.
Then, continuing the example, the auxiliary trial system may search, in a preset history case library, for the keyword or value (for example, including the identity information of the original defended, the key data in the original defended evidence, the key data in the court trial record, and the key data in the appeal and answer forms) of the case element data corresponding to the target case, to obtain a history case similar to the case of the civil case in which the target case is a traffic accident dispute.
In this specification, the auxiliary trial system may further output the historical case judgment corresponding to the historical case to a user, so that the user may correct the case judgment corresponding to the target case based on the historical case judgment.
Continuing to illustrate the example, the auxiliary judging system outputs the historical case judgment books corresponding to the historical cases with similar cases of the civil cases with the target cases being traffic accident disputes to the judge, so that the judge corrects the case judgment books corresponding to the target cases based on the historical case judgment books.
In this specification, after the user completes the correction of the case judgment corresponding to the target case, the auxiliary trial and judgment system may finally generate the case judgment corresponding to the target case.
For example, in practical applications, after a judge completes the correction of the case judgment corresponding to the target case, the auxiliary judging system may finally generate the case judgment corresponding to the target case; the specific format of the case judgment book can comprise case title, case number, original reported information, trial pass information, original report appeal information, reported and answered information, case routing information, evidence affirmation information, court affirmation fact information, court deeming information, judgment result information and the like.
In the above technical solution, based on receiving litigation data corresponding to a target case; carrying out data analysis on the litigation data to obtain case element data corresponding to the target case; and inputting the case element data into a case trial model for data processing to obtain prejudgment data, and generating a case judgment book corresponding to the target case based on the prejudgment data and the case element data, so that the case judgment book is quickly and automatically generated, and the case flow processing and case trial efficiency is improved.
Corresponding to the embodiment of the method, the application also provides an embodiment of a case judgment generation device.
Corresponding to the above method embodiments, the present specification also provides an embodiment of a case decision making apparatus. The embodiment of the case decision generation device of the present specification can be applied to electronic devices. The device embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. Taking a software implementation as an example, as a logical device, the device is formed by reading, by a processor of the electronic device where the device is located, a corresponding computer program instruction in the nonvolatile memory into the memory for operation. From a hardware aspect, as shown in fig. 3, a hardware structure diagram of an electronic device in which a case decision making apparatus of this specification is located is shown, except for a processor, a memory, a network interface, and a nonvolatile memory shown in fig. 3, the electronic device in which the apparatus is located in the embodiment may also include other hardware generally according to an actual function of the electronic device, which is not described again.
Fig. 4 is a block diagram of a case decision making apparatus shown in an exemplary embodiment of the present specification.
Referring to fig. 4, the case decision generating apparatus 40 can be applied to the electronic device shown in fig. 3, and the apparatus is applied to an auxiliary trial system, and the apparatus includes:
the receiving module 401 receives litigation data corresponding to the target case; the litigation data at least comprises litigation data submitted by the original reports and the reports and court trial record data;
an analysis module 402, configured to perform data analysis on the litigation data to obtain case element data corresponding to the target case; wherein the case element data indicates case critical features of the target case;
the processing module 403 is configured to input the case element data into a case trial model obtained through training for data processing, so as to obtain prejudgment data corresponding to the target case;
a generating module 404, configured to generate a case decision book corresponding to the target case based on the prejudgment data and the case element data.
In this embodiment, the analysis module 402 further:
performing semantic analysis on the litigation data to obtain a plurality of feature data indicating case features of the target case;
screening the characteristic data to obtain key data indicating the case key characteristics of the target case;
and generating a key data set based on the obtained key data, wherein the key data set is used as case element data corresponding to the target case.
In this embodiment, the analysis module 402 further:
carrying out data processing on the litigation data to obtain textual litigation data;
and performing semantic analysis on the obtained textual litigation data to obtain a plurality of feature data indicating case features of the target case.
In this embodiment, after obtaining the anticipation data corresponding to the target case, the processing module 403 further:
outputting the prejudgment data corresponding to the target case to the user so that the user can update the prejudgment data.
In this embodiment, based on the prejudgment data and the case element data, the generating module 404 further:
receiving data update of the user on the prejudgment data, inputting the updated prejudgment data to the case judgment model again for data processing, and obtaining prejudgment correction data corresponding to the target case;
and generating case judgment books corresponding to the target cases based on the prejudgment correction data and the case element data.
In this embodiment, after generating the case decision corresponding to the target case, the generating module 404 further:
searching in a preset historical case library based on the case element data to obtain a historical case similar to the case of the target case;
and outputting the historical case judgment corresponding to the historical case to the user so that the user corrects the case judgment corresponding to the target case based on the historical case judgment.
In this embodiment, the case trial model is a machine learning model obtained by training litigation data associated with the existence timing sequence of a historical case.
In this embodiment, the case trial model is a machine learning model constructed based on the LSTM neural network.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, wherein the modules described as separate parts may or may not be physically separate, and the parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the application. One of ordinary skill in the art can understand and implement it without inventive effort.
The apparatuses, modules or modules illustrated in the above embodiments may be implemented by a computer chip or an entity, or by an article with certain functions. A typical implementation device is a computer, which may take the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email messaging device, game console, tablet computer, wearable device, or a combination of any of these devices.
Corresponding to the method embodiment, the present specification also provides an embodiment of an electronic device. The electronic equipment can be applied to a distributed service system, wherein the distributed service system comprises a plurality of test databases, a service subsystem in butt joint with a flow initiator, and an identification subsystem in butt joint with the test databases; the electronic device includes: a processor and a memory for storing machine executable instructions; wherein the processor and the memory are typically interconnected by an internal bus. In other possible implementations, the device may also include an external interface to enable communication with other devices or components.
In this embodiment, the processor is caused to:
receiving litigation data corresponding to the target case; the litigation data at least comprises litigation data submitted by the original reports and the reports and court trial record data;
performing data analysis on the litigation data to obtain case element data corresponding to the target case; wherein the case element data indicates case critical features of the target case;
inputting the case element data into a case trial model obtained by training for data processing to obtain prejudgment data corresponding to the target case;
and generating case judgment books corresponding to the target cases based on the prejudgment data and the case element data.
In this embodiment, the processor is caused to:
performing semantic analysis on the litigation data to obtain a plurality of feature data indicating case features of the target case;
screening the characteristic data to obtain key data indicating the case key characteristics of the target case;
and generating a key data set based on the obtained key data, wherein the key data set is used as case element data corresponding to the target case.
In this embodiment, the processor is caused to:
carrying out data processing on the litigation data to obtain textual litigation data;
and performing semantic analysis on the obtained textual litigation data to obtain a plurality of feature data indicating case features of the target case.
In this embodiment, after obtaining the prejudged data corresponding to the target case, by reading and executing the machine executable instructions stored in the memory and corresponding to the control logic generated by the case decision, the processor is caused to:
outputting the prejudgment data corresponding to the target case to the user so that the user can update the prejudgment data.
In this embodiment, the processor is caused to:
receiving data update of the user on the prejudgment data, inputting the updated prejudgment data to the case judgment model again for data processing, and obtaining prejudgment correction data corresponding to the target case;
and generating case judgment books corresponding to the target cases based on the prejudgment correction data and the case element data.
In this embodiment, after generating the case decision corresponding to the target case, the processor is caused to:
searching in a preset historical case library based on the case element data to obtain a historical case similar to the case of the target case;
and outputting the historical case judgment corresponding to the historical case to the user so that the user corrects the case judgment corresponding to the target case based on the historical case judgment.
In this embodiment, the case trial model is a machine learning model obtained by training litigation data associated with the existence timing sequence of a historical case:
in this embodiment, the case trial model is a machine learning model constructed based on the LSTM neural network.
Other embodiments of the present disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This specification is intended to cover any variations, uses, or adaptations of the specification following, in general, the principles of the specification and including such departures from the present disclosure as come within known or customary practice within the art to which the specification pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the specification being indicated by the following claims.
It will be understood that the present description is not limited to the precise arrangements described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present description is limited only by the appended claims.
The above description is only a preferred embodiment of the present disclosure, and should not be taken as limiting the present disclosure, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the present disclosure should be included in the scope of the present disclosure.
Claims (11)
1. A case judgment generation method is applied to an auxiliary trial system and comprises the following steps:
receiving litigation data corresponding to the target case; the litigation data at least comprises litigation data submitted by the original reports and the reports and court trial record data;
performing data analysis on the litigation data to obtain case element data corresponding to the target case; wherein the case element data indicates case critical features of the target case;
inputting the case element data into a case trial model obtained by training for data processing to obtain prejudgment data corresponding to the target case;
and generating case judgment books corresponding to the target cases based on the prejudgment data and the case element data.
2. The method of claim 1, wherein the analyzing the litigation data to obtain case element data corresponding to the target case comprises:
performing semantic analysis on the litigation data to obtain a plurality of feature data indicating case features of the target case;
screening the characteristic data to obtain key data indicating the case key characteristics of the target case;
and generating a key data set based on the obtained key data, wherein the key data set is used as case element data corresponding to the target case.
3. The method of claim 2, the semantically analyzing the litigation data to obtain feature data indicative of case features of the target case, comprising:
carrying out data processing on the litigation data to obtain textual litigation data;
and performing semantic analysis on the obtained textual litigation data to obtain a plurality of feature data indicating case features of the target case.
4. The method according to claim 1, further comprising, after obtaining prejudice data corresponding to the target case:
outputting the prejudgment data corresponding to the target case to the user so that the user can update the prejudgment data.
5. The method of claim 1, wherein generating case decisions corresponding to the target case based on the prejudice data and the case element data comprises:
receiving data update of the user on the prejudgment data, inputting the updated prejudgment data to the case judgment model again for data processing, and obtaining prejudgment correction data corresponding to the target case;
and generating case judgment books corresponding to the target cases based on the prejudgment correction data and the case element data.
6. The method of claim 5, after generating case decisions corresponding to the target case, further comprising:
searching in a preset historical case library based on the case element data to obtain a historical case similar to the case of the target case;
and outputting the historical case judgment corresponding to the historical case to the user so that the user corrects the case judgment corresponding to the target case based on the historical case judgment.
7. The method of claim 1, the case trial model being a machine learning model trained based on litigation data for which there is a chronological association of historical cases.
8. The method of claim 1, the case trial model being a machine learning model constructed based on an LSTM neural network.
9. A case decision making apparatus applied to an auxiliary trial system, the apparatus comprising:
the receiving module is used for receiving litigation data corresponding to the target case; the litigation data at least comprises litigation data submitted by the original reports and the reports and court trial record data;
the analysis module is used for carrying out data analysis on the litigation data to obtain case element data corresponding to the target case; wherein the case element data indicates case critical features of the target case;
the processing module is used for inputting the case element data into a case trial model obtained by training for data processing to obtain prejudgment data corresponding to the target case;
and the generating module is used for generating a case judgment book corresponding to the target case based on the prejudgment data and the case element data.
10. An electronic device comprises a communication interface, a processor, a memory and a bus, wherein the communication interface, the processor and the memory are connected with each other through the bus;
the memory has stored therein machine-readable instructions, the processor executing the method of any of claims 1 to 8 by calling the machine-readable instructions.
11. A machine readable storage medium having stored thereon machine readable instructions which, when invoked and executed by a processor, carry out the method of any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911300477.0A CN111222308A (en) | 2019-12-17 | 2019-12-17 | Case decision book generation method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911300477.0A CN111222308A (en) | 2019-12-17 | 2019-12-17 | Case decision book generation method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111222308A true CN111222308A (en) | 2020-06-02 |
Family
ID=70827816
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911300477.0A Pending CN111222308A (en) | 2019-12-17 | 2019-12-17 | Case decision book generation method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111222308A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111695874A (en) * | 2020-06-09 | 2020-09-22 | 山东交通学院 | Judicial judgment auxiliary system, method, equipment and storage medium |
| CN111797246A (en) * | 2020-09-08 | 2020-10-20 | 共道网络科技有限公司 | Court trial method and device, electronic equipment and machine-readable storage medium |
| CN112966072A (en) * | 2021-03-11 | 2021-06-15 | 暨南大学 | Case prediction method and device, electronic device and storage medium |
| CN116595950A (en) * | 2023-03-06 | 2023-08-15 | 华院计算技术(上海)股份有限公司 | Method, system, equipment and medium for generating decision book |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107562938A (en) * | 2017-09-21 | 2018-01-09 | 重庆工商大学 | A kind of law court intelligently tries method |
| CN108596360A (en) * | 2018-03-16 | 2018-09-28 | 北京中科闻歌科技股份有限公司 | A kind of judgement prediction technique and system based on machine learning |
| CN109213864A (en) * | 2018-08-30 | 2019-01-15 | 广州慧睿思通信息科技有限公司 | Criminal case anticipation system and its building and pre-judging method based on deep learning |
| CN109241285A (en) * | 2018-08-29 | 2019-01-18 | 东南大学 | A kind of device of the judicial decision in a case of auxiliary based on machine learning |
| JP6469919B1 (en) * | 2018-05-09 | 2019-02-13 | 株式会社Ｌｅｇａｌｓｃａｐｅ | Judgment sentence database creation method, judgment sentence database search method, sentence creation method, judgment sentence database creation apparatus, judgment sentence database retrieval apparatus, sentence creation apparatus, judgment sentence database creation program, judgment sentence database retrieval program, And sentence creation program |
| CN109377000A (en) * | 2018-09-21 | 2019-02-22 | 安徽和信科技发展有限责任公司 | A kind of litigation risk assessment device of artificial intelligence technology |
| CN109815467A (en) * | 2018-12-20 | 2019-05-28 | 广州恒巨信息科技有限公司 | A kind of Judicial mediation document intelligent generation method, system and device |
| CN110175605A (en) * | 2019-05-27 | 2019-08-27 | 北京市律典通科技有限公司 | Electronics trial data processing method and device based on element formula |
-
2019
- 2019-12-17 CN CN201911300477.0A patent/CN111222308A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107562938A (en) * | 2017-09-21 | 2018-01-09 | 重庆工商大学 | A kind of law court intelligently tries method |
| CN108596360A (en) * | 2018-03-16 | 2018-09-28 | 北京中科闻歌科技股份有限公司 | A kind of judgement prediction technique and system based on machine learning |
| JP6469919B1 (en) * | 2018-05-09 | 2019-02-13 | 株式会社Ｌｅｇａｌｓｃａｐｅ | Judgment sentence database creation method, judgment sentence database search method, sentence creation method, judgment sentence database creation apparatus, judgment sentence database retrieval apparatus, sentence creation apparatus, judgment sentence database creation program, judgment sentence database retrieval program, And sentence creation program |
| CN109241285A (en) * | 2018-08-29 | 2019-01-18 | 东南大学 | A kind of device of the judicial decision in a case of auxiliary based on machine learning |
| CN109213864A (en) * | 2018-08-30 | 2019-01-15 | 广州慧睿思通信息科技有限公司 | Criminal case anticipation system and its building and pre-judging method based on deep learning |
| CN109377000A (en) * | 2018-09-21 | 2019-02-22 | 安徽和信科技发展有限责任公司 | A kind of litigation risk assessment device of artificial intelligence technology |
| CN109815467A (en) * | 2018-12-20 | 2019-05-28 | 广州恒巨信息科技有限公司 | A kind of Judicial mediation document intelligent generation method, system and device |
| CN110175605A (en) * | 2019-05-27 | 2019-08-27 | 北京市律典通科技有限公司 | Electronics trial data processing method and device based on element formula |
Non-Patent Citations (2)
| Title |
|---|
| 叶胜男;李波;: "人工智能介质下的审判范式", no. 31, pages 51 - 55 * |
| 康云云;彭敦陆;陈章;刘丛;: "ED-GAN:基于改进生成对抗网络的法律文本生成模型", no. 05, pages 2020 - 1025 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111695874A (en) * | 2020-06-09 | 2020-09-22 | 山东交通学院 | Judicial judgment auxiliary system, method, equipment and storage medium |
| CN111695874B (en) * | 2020-06-09 | 2023-08-11 | 山东交通学院 | Judicial decision auxiliary system, judicial decision auxiliary method, judicial decision auxiliary equipment and storable medium |
| CN111797246A (en) * | 2020-09-08 | 2020-10-20 | 共道网络科技有限公司 | Court trial method and device, electronic equipment and machine-readable storage medium |
| CN112966072A (en) * | 2021-03-11 | 2021-06-15 | 暨南大学 | Case prediction method and device, electronic device and storage medium |
| CN116595950A (en) * | 2023-03-06 | 2023-08-15 | 华院计算技术(上海)股份有限公司 | Method, system, equipment and medium for generating decision book |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20240078386A1 (en) | Methods and systems for language-agnostic machine learning in natural language processing using feature extraction | |
| CN111222308A (en) | Case decision book generation method and device and electronic equipment | |
| US20140308650A1 (en) | Evaluation control | |
| CN111898643B (en) | Semantic matching method and device | |
| CN109325146B (en) | Video recommendation method and device, storage medium and server | |
| JP6232607B1 (en) | Patent requirement conformity prediction device and patent requirement conformity prediction program | |
| US11720615B2 (en) | Self-executing protocol generation from natural language text | |
| US20130091143A1 (en) | Bigram suggestions | |
| JP6308708B1 (en) | Patent requirement conformity prediction device and patent requirement conformity prediction program | |
| US20210264208A1 (en) | Systems and methods for domain agnostic document extraction with zero-shot task transfer | |
| CN110377631B (en) | Case information processing method, device, computer equipment and storage medium | |
| CN110048995B (en) | Method and device for confirming content of multimedia protocol and electronic equipment | |
| Beall | Scientific soundness and the problem of predatory journals | |
| CN110059178A (en) | Problem distributing method and device | |
| CN113128228A (en) | Voice instruction recognition method and device, electronic equipment and storage medium | |
| Schraagen et al. | Evaluation of Named Entity Recognition in Dutch online criminal complaints | |
| JPWO2011018867A1 (en) | Information classification apparatus, information classification method, and program | |
| CN111753616A (en) | Wrong question collection method and learning equipment | |
| CN113343248A (en) | Vulnerability identification method, device, equipment and storage medium | |
| CN116775639A (en) | Data processing method, storage medium and electronic device | |
| US20220335387A1 (en) | Method and system for configuring user onboarding in a financial organization | |
| CN113609271B (en) | Knowledge graph-based service processing method, device, equipment and storage medium | |
| CN111382290B (en) | Document picture processing method and device | |
| CN112988957B (en) | Case pre-judgment result generation method and device and electronic equipment | |
| CN114153939A (en) | Text recognition method and device |
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 |