CN111695874B - Judicial decision auxiliary system, judicial decision auxiliary method, judicial decision auxiliary equipment and storable medium - Google Patents
Judicial decision auxiliary system, judicial decision auxiliary method, judicial decision auxiliary equipment and storable medium Download PDFInfo
- Publication number
- CN111695874B CN111695874B CN202010516668.7A CN202010516668A CN111695874B CN 111695874 B CN111695874 B CN 111695874B CN 202010516668 A CN202010516668 A CN 202010516668A CN 111695874 B CN111695874 B CN 111695874B
- Authority
- CN
- China
- Prior art keywords
- dispute
- book
- litigation
- judgment
- decision
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 53
- 238000012549 training Methods 0.000 claims description 38
- 230000011218 segmentation Effects 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000006698 induction Effects 0.000 claims 2
- 230000019771 cognition Effects 0.000 abstract 1
- 230000001737 promoting effect Effects 0.000 abstract 1
- 238000012360 testing method Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000012937 correction Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000001939 inductive effect Effects 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 239000012141 concentrate Substances 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000011478 gradient descent method Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 230000003340 mental effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 235000016709 nutrition Nutrition 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000008719 thickening Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
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
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Technology Law (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention is applicable to the technical field of computers, and provides a judicial decision assistance system, a judicial decision assistance method, judicial decision assistance equipment and a storable medium, wherein the judicial decision assistance method comprises the following steps: the litigation element acquisition unit is used for acquiring litigation elements of the decision book manuscript; the dispute feature determining unit is used for determining the dispute feature according to the litigation elements and a preset litigation element-dispute feature recognition model established based on the convolutional neural network; and the judgment book revising unit is used for carrying out information identification on the corresponding position of the judgment book manuscript according to the dispute characteristics so as to assist a user to revise the judgment book manuscript. The invention utilizes a litigation element-dispute feature recognition model established according to the convolutional neural network and a large number of judgment book samples, so that the corresponding dispute features can be determined directly through the related litigation elements extracted in the judgment book pre-manuscript, thereby helping judicial personnel to quickly obtain the dispute points of the corresponding cases, overcoming the cognition limitation and subjective randomness and promoting the identification of the evidence of the cases to accord with objective facts.
Description
Technical Field
The invention belongs to the technical field of computers, and particularly relates to a judicial decision auxiliary system, a method, equipment and a storable medium.
Background
The judgment books refer to books written by law according to judgment, including civil judgment books, criminal judgment books, administrative judgment books and criminal attendant civil judgment books. In order to improve the quality of litigation documents, the form of the decision book is often characterized by standardization, innovation, openness, law and accuracy, and especially, the highest court also prepares various standard and practical judicial decision document patterns; in addition, innovation refers to the characteristic of adapting to the change of cases, and changes are made on the document making method to strengthen the rational content of judicial judgment.
It follows that existing judicial decisions present the problem of ignoring the public's ubiquitous disputes.
Disclosure of Invention
The embodiment of the invention aims to provide a judicial judgment auxiliary system, which aims to solve the problem that the existing judicial judgment ignores the common disputes of the public.
The embodiment of the invention is realized in such a way that a judicial decision auxiliary system comprises a dispute feature determining unit, a litigation element acquiring unit communicated with the dispute feature determining unit and a decision revision unit;
The litigation element acquisition unit is used for acquiring litigation elements of the judgment book manuscript;
the dispute feature determining unit is used for determining dispute features according to the litigation elements and a preset litigation element-dispute feature recognition model established based on a convolutional neural network; the litigation element-dispute feature recognition model established based on the convolutional neural network is generated through training of the convolutional neural network by a plurality of pre-collected judgment book samples; and
and the judgment book revising unit is used for carrying out information identification on the corresponding position of the judgment book manuscript according to the dispute characteristics so as to assist a user to revise the judgment book manuscript and obtain a revised judgment book.
Another object of an embodiment of the present invention is to provide a judicial decision assistance method, including:
acquiring litigation elements of a manuscript of a judgment book;
determining a dispute feature according to the litigation elements and a preset litigation element-dispute feature recognition model established based on a convolutional neural network; the litigation element-dispute feature recognition model established based on the convolutional neural network is generated through training of the convolutional neural network by a plurality of pre-collected judgment book samples;
And according to the dispute characteristics, carrying out information identification on the corresponding position of the manuscript of the judgment book so as to assist a user to revise the manuscript of the judgment book and obtain a revised judgment book.
Another object of an embodiment of the invention is a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the judicial decision assistance method.
Another object of an embodiment of the present invention is a computer-readable storage medium, on which a computer program is stored, which when being executed by a processor, causes the processor to perform the steps of the judicial decision assistance method.
According to the judicial decision auxiliary system provided by the embodiment of the invention, litigation elements are obtained in a decision book manuscript so as to determine dispute characteristics according to the litigation elements and a preset litigation element-dispute characteristic recognition model established based on a convolutional neural network; and further, information identification is carried out on the corresponding position of the manuscript of the judgment book through the dispute characteristics so as to assist a user to revise the manuscript of the judgment book and obtain a revised judgment book. Because the preset litigation element-dispute feature recognition model is generated through training a plurality of pre-collected judgment book samples through a convolutional neural network, the method can be used for expressing an implicit relation between the litigation element and the dispute feature; therefore, the invention utilizes the litigation element-dispute feature recognition model established according to the convolutional neural network and a large amount of decision book sample data, so that the corresponding dispute feature can be directly determined through the related litigation elements extracted in the decision book manuscript, and the judicial personnel can be helped to quickly obtain the dispute points of the corresponding cases.
Drawings
FIG. 1 is a block diagram of a judicial decision assistance system according to an embodiment of the present invention;
FIG. 2 is a block diagram of another judicial decision assistance system according to an embodiment of the present invention;
FIG. 3 is a block diagram of an identification model generating unit according to an embodiment of the present invention;
FIG. 4 is a block diagram of still another judicial decision assistance system according to an embodiment of the present invention;
fig. 5 is a block diagram of a decision searching unit according to an embodiment of the present invention;
fig. 6 is a block diagram of another decision searching unit according to an embodiment of the present invention;
FIG. 7 is a flowchart of an implementation of a judicial decision assistance method according to an embodiment of the present invention;
fig. 8 is a flowchart of another judicial decision assistance method according to an embodiment of the present invention.
Description of the embodiments
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.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. 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 or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, etc. may be used in embodiments of the present invention to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another.
In order to solve the problem that judicial decisions neglect common disputes in the public in the prior art, the embodiment of the invention provides a judicial decision auxiliary system, which is used for acquiring litigation elements in a decision book manuscript so as to determine dispute characteristics according to the litigation elements and a preset litigation element-dispute characteristic recognition model established based on a convolutional neural network; and further, information identification is carried out on the corresponding position of the manuscript of the judgment book through the dispute characteristics so as to assist a user to revise the manuscript of the judgment book and obtain a revised judgment book. Because the preset litigation element-dispute feature recognition model is generated through training a plurality of pre-collected judgment book samples through a convolutional neural network, the method can be used for expressing an implicit relation between the litigation element and the dispute feature; therefore, the invention utilizes the litigation element-dispute feature recognition model established according to the convolutional neural network and a large amount of decision book sample data, so that the corresponding dispute feature can be directly determined through the related litigation elements extracted in the decision book manuscript, and the judicial personnel can be helped to quickly obtain the dispute points of the corresponding cases.
In order to further describe the technical means and effects adopted by the present invention for achieving the intended purpose, the following detailed description is given of the specific embodiments, structures, features and effects according to the present invention with reference to the accompanying drawings and preferred embodiments.
Fig. 1 shows a block diagram of a judicial decision assistance system according to an embodiment of the present invention, and for convenience of explanation, only the portions relevant to the embodiment of the present invention are shown, and the details are as follows:
in the embodiment of the invention, the judicial decision assistance system comprises a dispute feature determining unit 102, a litigation element acquiring unit 101 and a decision revision unit 103, wherein the litigation element acquiring unit 101 and the decision revision unit 103 are communicated with the dispute feature determining unit 102.
The litigation element obtaining unit 101 is configured to obtain litigation elements of the decision book manuscript.
In the embodiment of the invention, the preliminary manuscript of the judgment book is a preliminary manuscript or a draft of the judgment book obtained according to the case condition, such as the preliminary manuscript of the judgment book obtained by analyzing and reasoning the complaint, the debate, the court trial writing and the related evidence through browsing the case by common relevant judicial personnel, or the preliminary manuscript of the judgment book obtained by automatically matching related similar judgment books in a database according to the case condition through some intelligent systems so as to analyze and infer the similar judgment books, which is not particularly limited by the invention.
In the embodiment of the invention, litigation elements include, but are not limited to, a case-by-element and a result element, wherein the case-by-element refers to a result that a party generates disputes on legal relations, and what disputes are generated based on what legal relations; the result element is the corresponding judgment result of the case.
The dispute feature determining unit 102 is configured to determine a dispute feature according to the litigation element and a preset litigation element-dispute feature recognition model established based on a convolutional neural network.
In the embodiment of the invention, the litigation element-dispute feature recognition model established based on the convolutional neural network is generated through training of the convolutional neural network by a plurality of pre-collected judgment book samples. The method comprises the steps of obtaining a plurality of judgment book samples, carrying out text extraction on each corresponding judicial dispute focus and litigation element in each judgment book sample, carrying out clustering processing on the extracted text to form labels related to the judicial dispute focus and the litigation element, dividing the labels into a training group, a testing group and a simulation group, carrying out scrambling and normalization processing on data of the training group and the testing group, and then carrying out convolutional neural network training to generate a litigation element-litigation feature recognition model.
The decision revision unit 103 is configured to identify information on a corresponding position of the decision pre-draft according to the dispute feature, so as to assist a user in revising the decision pre-draft to obtain a revised decision.
In the embodiment of the invention, when the dispute characteristics are identified, dispute identification is carried out at the corresponding text position in the text content of the pre-manuscript of the corresponding judgment book, and meanwhile, an applicable reference judgment rule corresponding to the dispute focus is provided at the identification position, wherein the applicable reference judgment rule is used for being referred by judicial staff to assist the judicial staff in revising the pre-manuscript of the judgment book, the specific identification mode can be in the forms of symbol identification, color distinction, font thickening distinction and the like, and the specific identification mode can be set according to actual conditions and is not limited.
In a preferred embodiment of the present invention, the decision revision unit further involves a document correction module, so that in addition to dispute identification at a corresponding text position in the decision pre-draft text content, the decision pre-draft text content is further audited by the document correction module in combination with the content in the litigation request of the party, so as to avoid errors in the decision.
According to the judicial decision auxiliary system provided by the embodiment of the invention, litigation elements are obtained in a decision book manuscript so as to determine dispute characteristics according to the litigation elements and a preset litigation element-dispute characteristic recognition model established based on a convolutional neural network; and further, information identification is carried out on the corresponding position of the manuscript of the judgment book through the dispute characteristics so as to assist a user to revise the manuscript of the judgment book and obtain a revised judgment book. Because the preset litigation element-dispute feature recognition model is generated through training a plurality of pre-collected judgment book samples through a convolutional neural network, the method can be used for expressing an implicit relation between the litigation element and the dispute feature; therefore, the invention utilizes the litigation element-dispute feature recognition model established according to the convolutional neural network and a large amount of decision book sample data, so that the corresponding dispute feature can be directly determined through the related litigation elements extracted in the decision book manuscript, and the judicial personnel can be helped to quickly obtain the dispute points of the corresponding cases.
Fig. 2 shows a block diagram of another judicial decision assistance system according to an embodiment of the present invention, and for convenience of explanation, only a portion related to the embodiment of the present invention is shown, and the remaining embodiments are similar to the above embodiments, except that:
In an embodiment of the present invention, the judicial decision assistance system further comprises an identification model generating unit 201.
The recognition model generating unit 201 is configured to generate a preset litigation element-dispute feature recognition model through training of a convolutional neural network by using a plurality of pre-collected decision book samples.
In the embodiment of the invention, as shown in fig. 3, the recognition model generating unit 201 includes a sample collecting module 301, a litigation element obtaining module 302, a dispute feature determining module 303, a loss difference calculating module 304, a loss difference judging module 305, a model adjusting module 306, and a model determining module 307.
The sample collection module 301 is configured to collect a plurality of samples of a decision book carrying a target dispute feature.
The litigation element obtaining module 302 is configured to obtain litigation elements of the plurality of decision book samples and target dispute characteristics.
The dispute feature determining module 303 is configured to determine a first dispute feature of the first decision book sample according to a first litigation element of the first decision book sample and a convolutional neural network model including variable parameters.
In an embodiment of the present invention, the structure of the convolutional neural network model includes an input layer, a plurality of convolutional layers, a plurality of pooling layers, at least one fully-connected layer, and an output layer, where variable parameters exist in the plurality of convolutional layers and the plurality of fully-connected layers.
In the embodiment of the invention, when the variable parameters in the convolution layers and the full connection layers are changed, the dispute characteristics of the output are different for the same litigation element input.
The loss difference calculation module 304 is configured to calculate a first loss difference between the first dispute feature and a target dispute feature corresponding to the first decision book sample.
In an embodiment of the present invention, the loss difference between the first dispute feature and the target dispute feature corresponding to the first decision book sample may be calculated by a loss function, such as a Mean Absolute Error (MAE) and a Mean Square Error (MSE) of a commonly used loss function.
The loss difference judging module 305 is configured to judge whether the loss differences of the plurality of decision book samples meet a preset condition.
The model adjustment module 306 is configured to adjust variable parameters in the convolutional neural network model when it is determined that the loss differences of the plurality of decision book samples do not meet the preset conditions, and return to the step of determining the first dispute feature of the first decision book sample according to the first litigation element of the first decision book sample and the convolutional neural network model containing the variable parameters.
In the embodiment of the present invention, the variable parameters in the convolutional neural network model may be adjusted according to a random gradient descent method, or a momentum random gradient descent method, or a back propagation algorithm, but after the variable parameters are adjusted, the method returns to the step of determining the first dispute feature of the first decision book sample according to the first litigation element of the first decision book sample and the convolutional neural network model containing the variable parameters, and the loss difference is recalculated.
The model determining module 307 is configured to determine, when it is determined that the loss differences of the plurality of decision book samples meet preset conditions, the current convolutional neural network model containing the variable parameters as a preset litigation element-dispute feature recognition model established based on the convolutional neural network.
In the embodiment of the invention, in order to acquire a litigation element-dispute feature recognition model, namely, acquire an implicit relation between a litigation element and a corresponding dispute feature, a plurality of decisions carrying target dispute features are required to be taken as samples, loss differences between the corresponding dispute features of the outputted decision samples and the corresponding target dispute features are calculated under the current litigation element-dispute feature recognition model, and variable parameters in the litigation element-dispute feature recognition model are continuously fed back and adjusted until the loss differences between the corresponding dispute features of the outputted decision samples and the corresponding target dispute features meet preset conditions under a certain litigation element-dispute feature recognition model, and at the moment, the litigation element-dispute feature recognition model is the required preset litigation element-dispute feature recognition model established based on a convolutional neural network.
Fig. 4 shows a block diagram of still another judicial decision assistance system according to an embodiment of the present invention, and for convenience of explanation, only a portion related to the embodiment of the present invention is shown, and the remaining embodiments are similar except that:
in the embodiment of the present invention, the judicial decision assistance system further includes a decision-book searching unit 402, a description element obtaining unit 401 in communication with the decision-book searching unit 402, and a decision-book pre-draft generating unit 403; the decision document pre-draft generation unit 403 communicates with the litigation element acquisition unit 101.
The description element obtaining unit 401 is configured to obtain a description element of a case to be processed.
In the embodiment of the invention, the description elements of the case to be processed comprise but are not limited to evidence elements and fact elements, wherein the evidence elements refer to various elements for guaranteeing the authenticity, validity and legality of the provided evidence, such as elements of complete content, legal program and the like, and specifically comprise time, place, figures, time course and the like; the fact factors include, but are not limited to, case type, case profile such as time, place, person, accident form, liability assignment results, victim profile, related contact profile, and loss situation, such as profile related to accident occurrence in motor vehicle traffic accident liability disputes case type (time, place, party, hit vehicle, collision mode), liability assignment results of traffic police department, victim profile (age, living situation, house, occupation, victim situation, etc.), other reimbursement entitlement profile (age, living situation, house, occupation, etc.), relationship between other reimbursement entitlement and victim, property loss situation (medical fee, follow-up medical fee, miswork fee, hospitality food subsidy fee, mental harm pacifying fee, traffic fee, nutritional fee, death or disabled reimbursement fee, caretaker living fee, disability aid fee, etc.), traffic liability situation of third party (insured person, insurance carrier name), relationship between motor vehicle user and other obligations (actual relationship with the vehicle owner, reimbursement, etc.).
In the embodiment of the invention, the method for extracting the description element in the case to be processed refers to extracting the plain text data from the case described by natural language, removing other semantic noise, screening the plain text data by utilizing evidence elements and trigger words related to the fact elements which are trained by a large number of samples in advance, and completing the extraction of the description element.
The decision book searching unit 402 is configured to search a plurality of decision books corresponding to the description elements in a preset database.
In the embodiment of the invention, the preset database is a corpus containing a large number of judgment books, including but not limited to a Chinese referee document network; the related labeling of the description elements can be carried out according to each judgment book structure in the database, the labeled judgment books are further divided into a training group, a test group and a simulation group, the data of the training group and the test group are subjected to scrambling and normalization processing, so that initial values, weights and thresholds of a pre-constructed language neural network model are determined, and further basic parameters such as training functions, minimum algebra, learning rate, target errors, hidden layer number and the like of the neural network are determined; calculating training residual errors of the training set and the testing set, when the error of the mean value and the variance of the error distribution of the training set and the testing set does not exceed a preset threshold value, finishing training, otherwise, returning to the previous step, changing the basic parameters of the training function, and continuing training; the trained language model is utilized to directly obtain the corresponding related decision book through the description element.
In a preferred embodiment of the present invention, a plurality of decision books corresponding to the description elements are searched in a preset database, and are sequentially arranged according to the matching degree, and the decision books with the matching degree exceeding a certain threshold are used as the decision books with high association degree with the description elements.
The decision book pre-manuscript generating unit 403 is configured to perform inductive analysis processing on the plurality of decision books, and combine a preset decision book text template to generate a decision book pre-manuscript corresponding to the to-be-processed case.
In the embodiment of the invention, legal requirements applicable to the case to be processed are judged according to the obtained information such as the judgment book set, the examination time, the effective time and the like with high relevance, and meanwhile, a preset judgment book text template is combined to generate a judgment book pre-manuscript of the case to be processed; of course, the automatically generated manuscript of the judgment book aims at some cases with high repeatability and limited technical content, the cases occupy a relatively large amount, and the method is beneficial to a judge to release from a large amount of repeated works without technical content, so that more time and energy are spent on concentrating the cases.
According to the judicial judgment auxiliary system provided by the embodiment of the invention, the description elements are acquired from the to-be-processed case, so that a plurality of corresponding judgment books are searched in the preset database according to the description elements, the judgment books are subjected to inductive analysis processing, and a preset judgment book text template is combined to generate a judgment book manuscript corresponding to the to-be-processed case; the invention is beneficial to the relief of the judge from a large number of repeated works without technical content, has more time and energy to concentrate on the case and achieves the effect of improving the accuracy of the specific pointing clause of the applicable law in the judgment.
Fig. 5 shows a block diagram of a decision-making lookup unit according to an embodiment of the present invention, and for convenience of explanation, only the portions relevant to the embodiment of the present invention are shown, which is described in detail below:
in the embodiment of the present invention, the decision searching unit 402 includes a word segmentation module 501 and a first decision searching module 502.
The word segmentation module 501 is configured to perform word segmentation on the description element, and obtain a word segmentation result.
In the embodiment of the invention, the extracted description element corresponds to the search text information of the decision book, the word segmentation processing is carried out on the description element, namely the text data is segmented into a plurality of word forms, the word segmentation result can be obtained by carrying out the word segmentation processing on the description element, or a bargain word segmentation method can be used, and specifically, the description element is fully segmented, so that a basic word element represented by an adjacent linked list is generated. In addition, the word segmentation mode of the text can be various word segmentation methods of the text, and can also be NGram representation taking Chinese characters as units, and the invention is not limited to the word segmentation mode.
In a preferred embodiment of the present invention, some non-significant terms in the word segmentation result obtained after the word segmentation process is performed on the description element may be further subjected to system automatic filtering or artificial filtering, and may be ignored when calculating the similarity probability as described below.
The first decision searching module 502 is configured to search, in a preset database, a plurality of decisions having a similarity with the word segmentation result reaching a preset probability threshold.
In the embodiment of the invention, the description elements often comprise information with multiple dimensions, word segmentation results obtained through word segmentation processing also relate to information with different dimensions, and matching similar judgment books should be performed in a preset database according to the corresponding dimensions.
Fig. 6 shows a block diagram of another decision-making lookup unit according to an embodiment of the present invention, and for convenience of explanation, only the portions related to the embodiment of the present invention are shown in detail as follows:
in the embodiment of the present invention, the decision book searching unit 402 includes an association element obtaining module 601 and a second decision book searching module 602.
The related element obtaining module 601 is configured to obtain related elements with the same meaning as the description element.
In the embodiment of the invention, the associated elements with the same meaning as the description elements can be alternative words such as synonyms and paraphraseology, or associated vocabulary information which can be determined by networking, and the like, and the invention is not particularly limited.
The second decision book searching module 602 is configured to search a plurality of decision books corresponding to the association element in a preset database.
Fig. 7 shows a flow of implementation of a judicial decision assistance method according to an embodiment of the present invention, and for convenience of explanation, only the portions relevant to the embodiment of the present invention are shown, which are described in detail below:
in step S701, litigation elements of the decision book manuscript are acquired.
In the embodiment of the invention, the preliminary manuscript of the judgment book is a preliminary manuscript or a draft of the judgment book obtained according to the case condition, such as the preliminary manuscript of the judgment book obtained by analyzing and reasoning the complaint, the debate, the court trial writing and the related evidence through browsing the case by common relevant judicial personnel, or the preliminary manuscript of the judgment book obtained by automatically matching related similar judgment books in a database according to the case condition through some intelligent systems so as to analyze and infer the similar judgment books, which is not particularly limited by the invention.
In the embodiment of the invention, litigation elements include, but are not limited to, a case-by-element and a result element, wherein the case-by-element refers to a result that a party generates disputes on legal relations, and what disputes are generated based on what legal relations; the result element is the corresponding judgment result of the case.
In step S702, a dispute feature is determined according to the litigation elements and a preset litigation element-dispute feature recognition model established based on a convolutional neural network.
In the embodiment of the invention, the litigation element-dispute feature recognition model established based on the convolutional neural network is generated through training of the convolutional neural network by a plurality of pre-collected judgment book samples. The method comprises the steps of obtaining a plurality of judgment book samples, carrying out text extraction on each corresponding judicial dispute focus and litigation element in each judgment book sample, carrying out clustering processing on the extracted text to form labels related to the judicial dispute focus and the litigation element, dividing the labels into a training group, a testing group and a simulation group, carrying out scrambling and normalization processing on data of the training group and the testing group, and then carrying out convolutional neural network training to generate a litigation element-litigation feature recognition model.
In step S703, according to the dispute feature, information identification is performed on the corresponding position of the pre-script of the decision, so as to assist the user in revising the pre-script of the decision, and a revised decision is obtained.
In the embodiment of the invention, when the dispute characteristics are identified, dispute identification is carried out at the corresponding text position in the text content of the pre-manuscript of the corresponding judgment book, and meanwhile, an applicable reference judgment rule corresponding to the dispute focus is provided at the identification position, wherein the applicable reference judgment rule is used for being referred by judicial staff to assist the judicial staff in revising the pre-manuscript of the judgment book, the specific identification mode can be in the forms of symbol identification, color distinction, font thickening distinction and the like, and the specific identification mode can be set according to actual conditions and is not limited.
In a preferred embodiment of the present invention, the decision revision unit further involves a document correction module, so that in addition to dispute identification at a corresponding text position in the decision pre-draft text content, the decision pre-draft text content is further audited by the document correction module in combination with the content in the litigation request of the party, so as to avoid errors in the decision.
According to the judicial decision auxiliary method provided by the embodiment of the invention, litigation elements are obtained in a decision book manuscript so as to determine dispute characteristics according to the litigation elements and a preset litigation element-dispute characteristic identification model established based on a convolutional neural network; and further, information identification is carried out on the corresponding position of the manuscript of the judgment book through the dispute characteristics so as to assist a user to revise the manuscript of the judgment book and obtain a revised judgment book. Because the preset litigation element-dispute feature recognition model is generated through training a plurality of pre-collected judgment book samples through a convolutional neural network, the method can be used for expressing an implicit relation between the litigation element and the dispute feature; therefore, the invention utilizes the litigation element-dispute feature recognition model established according to the convolutional neural network and a large amount of decision book sample data, so that the corresponding dispute feature can be directly determined through the related litigation elements extracted in the decision book manuscript, and the judicial personnel can be helped to quickly obtain the dispute points of the corresponding cases.
Fig. 8 shows a flow chart of another judicial decision assistance method according to an embodiment of the present invention, and for convenience of explanation, only the portions relevant to the embodiment of the present invention are shown, and the details are as follows:
in step S801, description elements of a case to be processed are acquired.
In the embodiment of the invention, the description elements of the case to be processed comprise but are not limited to evidence elements and fact elements, wherein the evidence elements refer to various elements for guaranteeing the authenticity, validity and legality of the provided evidence, such as elements of complete content, legal program and the like, and specifically comprise time, place, figures, time course and the like; the fact factors include, but are not limited to, case type, case profile such as time, place, person, accident form, liability assignment results, victim profile, related contact profile, and loss situation, such as profile related to accident occurrence in motor vehicle traffic accident liability disputes case type (time, place, party, hit vehicle, collision mode), liability assignment results of traffic police department, victim profile (age, living situation, house, occupation, victim situation, etc.), other reimbursement entitlement profile (age, living situation, house, occupation, etc.), relationship between other reimbursement entitlement and victim, property loss situation (medical fee, follow-up medical fee, miswork fee, hospitality food subsidy fee, mental harm pacifying fee, traffic fee, nutritional fee, death or disabled reimbursement fee, caretaker living fee, disability aid fee, etc.), traffic liability situation of third party (insured person, insurance carrier name), relationship between motor vehicle user and other obligations (actual relationship with the vehicle owner, reimbursement, etc.).
In the embodiment of the invention, the method for extracting the description element in the case to be processed refers to extracting the plain text data from the case described by natural language, removing other semantic noise, screening the plain text data by utilizing evidence elements and trigger words related to the fact elements which are trained by a large number of samples in advance, and completing the extraction of the description element.
In step S802, a plurality of decision books corresponding to the description elements are searched in a preset database.
In the embodiment of the invention, the preset database is a corpus containing a large number of judgment books, including but not limited to a Chinese referee document network; the related labeling of the description elements can be carried out according to each judgment book structure in the database, the labeled judgment books are further divided into a training group, a test group and a simulation group, the data of the training group and the test group are subjected to scrambling and normalization processing, so that initial values, weights and thresholds of a pre-constructed language neural network model are determined, and further basic parameters such as training functions, minimum algebra, learning rate, target errors, hidden layer number and the like of the neural network are determined; calculating training residual errors of the training set and the testing set, when the error of the mean value and the variance of the error distribution of the training set and the testing set does not exceed a preset threshold value, finishing training, otherwise, returning to the previous step, changing the basic parameters of the training function, and continuing training; the trained language model is utilized to directly obtain the corresponding related decision book through the description element.
In a preferred embodiment of the present invention, a plurality of decision books corresponding to the description elements are searched in a preset database, and are sequentially arranged according to the matching degree, and the decision books with the matching degree exceeding a certain threshold are used as the decision books with high association degree with the description elements.
In step S803, the plurality of decision books are subjected to inductive analysis processing, and a preset decision book text template is combined to generate a decision book manuscript corresponding to the to-be-processed case.
In the embodiment of the invention, legal requirements applicable to the case to be processed are judged according to the obtained information such as the judgment book set, the examination time, the effective time and the like with high relevance, and meanwhile, a preset judgment book text template is combined to generate a judgment book pre-manuscript of the case to be processed; of course, the automatically generated manuscript of the judgment book aims at some cases with high repeatability and limited technical content, the cases occupy a relatively large amount, and the method is beneficial to a judge to release from a large amount of repeated works without technical content, so that more time and energy are spent on concentrating the cases.
According to the judicial judgment auxiliary method provided by the embodiment of the invention, the description elements are acquired from the to-be-processed case, so that a plurality of corresponding judgment books are searched in the preset database according to the description elements, the judgment books are subjected to inductive analysis processing, and a preset judgment book text template is combined to generate a judgment book manuscript corresponding to the to-be-processed case; the invention is beneficial to the relief of the judge from a large number of repeated works without technical content, has more time and energy to concentrate on the case and achieves the effect of improving the accuracy of the specific pointing clause of the applicable law in the judgment.
In one embodiment, a computer device is presented, the computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
acquiring litigation elements of a manuscript of a judgment book;
determining a dispute feature according to the litigation elements and a preset litigation element-dispute feature recognition model established based on a convolutional neural network; the litigation element-dispute feature recognition model established based on the convolutional neural network is generated through training of the convolutional neural network by a plurality of pre-collected judgment book samples;
and according to the dispute characteristics, carrying out information identification on the corresponding position of the manuscript of the judgment book so as to assist a user to revise the manuscript of the judgment book and obtain a revised judgment book.
In one embodiment, a computer readable storage medium is provided, having a computer program stored thereon, which when executed by a processor causes the processor to perform the steps of:
acquiring litigation elements of a manuscript of a judgment book;
determining a dispute feature according to the litigation elements and a preset litigation element-dispute feature recognition model established based on a convolutional neural network; the litigation element-dispute feature recognition model established based on the convolutional neural network is generated through training of the convolutional neural network by a plurality of pre-collected judgment book samples;
And according to the dispute characteristics, carrying out information identification on the corresponding position of the manuscript of the judgment book so as to assist a user to revise the manuscript of the judgment book and obtain a revised judgment book.
It should be understood that, although the steps in the flowcharts of the embodiments of the present application are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in various embodiments may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
Those skilled in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by a computer program for instructing relevant hardware, where the program may be stored in a non-volatile computer readable storage medium, and where the program, when executed, may include processes in the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (7)
1. A judicial decision assistance system, which is characterized by comprising a dispute feature determining unit, a litigation element acquiring unit communicated with the dispute feature determining unit and a decision revision unit;
The litigation element acquisition unit is used for acquiring litigation elements of the judgment book manuscript;
the dispute feature determining unit is used for determining dispute features according to the litigation elements and a preset litigation element-dispute feature recognition model established based on a convolutional neural network; the litigation element-dispute feature recognition model established based on the convolutional neural network is generated through training of the convolutional neural network by a plurality of pre-collected judgment book samples; and
the decision book revising unit is used for carrying out information identification on the corresponding position of the decision book manuscript according to the dispute characteristics so as to assist a user to revise the decision book manuscript and obtain revised decision books;
the judicial decision auxiliary system also comprises a decision book searching unit, a description element acquisition unit communicated with the decision book searching unit and a decision book pre-draft generation unit; the decision book pre-manuscript generating unit is communicated with the litigation element acquiring unit;
the description element acquisition unit is used for acquiring the description element of the case to be processed; the method for extracting the description elements in the case to be processed refers to extracting plain text data from the case described by natural language through a natural language extraction technology, removing other semantic noise, screening the plain text data by utilizing evidence elements and fact element related trigger words which are trained by a large number of samples in advance, and completing the extraction of the description elements;
The judgment book searching unit is used for searching a plurality of judgment books corresponding to the description elements in a preset database; and
the judgment book pre-manuscript generating unit is used for carrying out induction analysis processing on the plurality of judgment books and generating a judgment book pre-manuscript corresponding to the to-be-processed case by combining a preset judgment book text template;
the decision book searching unit comprises:
the associated element acquisition module is used for acquiring associated elements with the same word meaning as the description element; and
and the second judgment book searching module is used for searching a plurality of judgment books corresponding to the association factors in a preset database.
2. The judicial decision assistance system according to claim 1, further comprising an identification model generation unit;
the recognition model generation unit is used for generating a preset litigation element-dispute feature recognition model through convolutional neural network training through a plurality of pre-collected judgment book samples.
3. The judicial decision assistance system according to claim 2, wherein the recognition model generating unit comprises:
the sample acquisition module is used for acquiring a plurality of judgment book samples carrying target dispute characteristics;
The litigation element acquisition module is used for acquiring litigation elements and target dispute characteristics of the plurality of judgment book samples;
the dispute feature determining module is used for determining a first dispute feature of the first decision book sample according to the first litigation element of the first decision book sample and a convolution neural network model containing variable parameters;
a loss difference calculation module, configured to calculate a first loss difference between the first dispute feature and a target dispute feature corresponding to the first decision book sample;
the loss difference judging module is used for judging whether the loss differences of the plurality of judgment book samples meet preset conditions or not;
the model adjustment module is used for adjusting variable parameters in the convolutional neural network model when the loss difference of the plurality of decision book samples does not meet the preset condition, and returning to the step of determining the first dispute characteristics of the first decision book samples according to the first litigation factors of the first decision book samples and the convolutional neural network model containing the variable parameters; and
and the model determining module is used for determining the current convolution neural network model containing the variable parameters as a preset litigation element-dispute feature recognition model established based on the convolution neural network when the loss difference of the plurality of judgment book samples meets a preset condition.
4. The judicial decision assistance system of claim 1, wherein the decision book lookup unit comprises:
the word segmentation module is used for carrying out word segmentation processing on the description elements to obtain word segmentation results; and
the first judgment book searching module is used for searching a plurality of judgment books with similarity reaching a preset probability threshold value with the word segmentation result in a preset database.
5. A judicial decision assistance method, comprising:
acquiring litigation elements of a manuscript of a judgment book;
determining a dispute feature according to the litigation elements and a preset litigation element-dispute feature recognition model established based on a convolutional neural network; the litigation element-dispute feature recognition model established based on the convolutional neural network is generated through training of the convolutional neural network by a plurality of pre-collected judgment book samples;
according to the dispute characteristics, information identification is carried out on the corresponding position of the judgment manuscript so as to assist a user in revising the judgment manuscript and obtain a revised judgment book;
the judicial decision assistance method further comprises:
acquiring description elements of a case to be processed; the method for extracting the description elements in the case to be processed refers to extracting plain text data from the case described by natural language through a natural language extraction technology, removing other semantic noise, screening the plain text data by utilizing evidence elements and fact element related trigger words which are trained by a large number of samples in advance, and completing the extraction of the description elements;
Searching a plurality of judgment books corresponding to the description elements in a preset database;
and carrying out induction analysis processing on the plurality of judgment books, and generating a judgment book manuscript corresponding to the to-be-processed case by combining a preset judgment book text template.
6. A computer device comprising a memory and a processor, the memory having stored therein a computer program which, when executed by the processor, causes the processor to perform the steps of the judicial decision assistance method of claim 5.
7. A computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, which when executed by a processor causes the processor to perform the steps of the judicial decision assistance method of claim 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010516668.7A CN111695874B (en) | 2020-06-09 | 2020-06-09 | Judicial decision auxiliary system, judicial decision auxiliary method, judicial decision auxiliary equipment and storable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010516668.7A CN111695874B (en) | 2020-06-09 | 2020-06-09 | Judicial decision auxiliary system, judicial decision auxiliary method, judicial decision auxiliary equipment and storable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111695874A CN111695874A (en) | 2020-09-22 |
| CN111695874B true CN111695874B (en) | 2023-08-11 |
Family
ID=72479873
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010516668.7A Active CN111695874B (en) | 2020-06-09 | 2020-06-09 | Judicial decision auxiliary system, judicial decision auxiliary method, judicial decision auxiliary equipment and storable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111695874B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115188013B (en) * | 2022-09-14 | 2023-06-30 | 泰豪信息技术有限公司 | Risk prevention and control method, system, storage medium and equipment for decision book |
| CN115796285B (en) * | 2023-02-13 | 2023-05-09 | 上海百事通法务信息技术有限公司浙江分公司 | Litigation case pre-judging method and device based on engineering model and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018113498A1 (en) * | 2016-12-23 | 2018-06-28 | 北京国双科技有限公司 | Method and apparatus for retrieving legal knowledge |
| CN110738032A (en) * | 2018-07-03 | 2020-01-31 | 北京国双科技有限公司 | method and device for generating judgment sections of official paperwork institute |
| CN110858353A (en) * | 2018-08-17 | 2020-03-03 | 阿里巴巴集团控股有限公司 | Method and system for obtaining case referee result |
| CN110968688A (en) * | 2018-09-30 | 2020-04-07 | 北京国双科技有限公司 | Judicial data processing method and system |
| CN111143550A (en) * | 2019-11-27 | 2020-05-12 | 浙江大学 | Method for automatically identifying dispute focus based on hierarchical attention neural network model |
| CN111222308A (en) * | 2019-12-17 | 2020-06-02 | 共道网络科技有限公司 | Case decision book generation method and device and electronic equipment |
-
2020
- 2020-06-09 CN CN202010516668.7A patent/CN111695874B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018113498A1 (en) * | 2016-12-23 | 2018-06-28 | 北京国双科技有限公司 | Method and apparatus for retrieving legal knowledge |
| CN110738032A (en) * | 2018-07-03 | 2020-01-31 | 北京国双科技有限公司 | method and device for generating judgment sections of official paperwork institute |
| CN110858353A (en) * | 2018-08-17 | 2020-03-03 | 阿里巴巴集团控股有限公司 | Method and system for obtaining case referee result |
| CN110968688A (en) * | 2018-09-30 | 2020-04-07 | 北京国双科技有限公司 | Judicial data processing method and system |
| CN111143550A (en) * | 2019-11-27 | 2020-05-12 | 浙江大学 | Method for automatically identifying dispute focus based on hierarchical attention neural network model |
| CN111222308A (en) * | 2019-12-17 | 2020-06-02 | 共道网络科技有限公司 | Case decision book generation method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111695874A (en) | 2020-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112380840B (en) | Text error correction method, device, equipment and medium | |
| CN107818138B (en) | Case law regulation recommendation method and system | |
| CN109992664B (en) | Dispute focus label classification method and device, computer equipment and storage medium | |
| US8014604B2 (en) | OCR of books by word recognition | |
| CN110188346B (en) | Intelligent research and judgment method for network security law case based on information extraction | |
| CN111695874B (en) | Judicial decision auxiliary system, judicial decision auxiliary method, judicial decision auxiliary equipment and storable medium | |
| CN111191442B (en) | Similar problem generation method, device, equipment and medium | |
| CN106933802B (en) | Multi-data-source-oriented social security entity identification method and device | |
| CN115952292A (en) | Multi-label classification method, device and computer readable medium | |
| CN116150651A (en) | AI-based depth synthesis detection method and system | |
| CN109710756B (en) | Document genre classification system and method based on semantic role labeling | |
| CN114662477A (en) | Stop word list generating method and device based on traditional Chinese medicine conversation and storage medium | |
| CN112989830B (en) | Named entity identification method based on multiple features and machine learning | |
| CN113761192A (en) | Text processing method, text processing device and text processing equipment | |
| CN111782821A (en) | Method and device for predicting medical hotspots based on FM model and computer equipment | |
| CN109635289B (en) | Entry classification method and audit information extraction method | |
| CN113705443A (en) | Palm print image identification method comprehensively utilizing knowledge graph and depth residual error network | |
| CN114283429A (en) | Material work order data processing method, device, equipment and storage medium | |
| CN110928987B (en) | Legal provision retrieval method and related equipment based on neural network hybrid model | |
| CN114036289A (en) | Intention identification method, device, equipment and medium | |
| CN113255343A (en) | Semantic identification method and device for label data, computer equipment and storage medium | |
| CN113468366A (en) | Music automatic labeling method | |
| CN112765993A (en) | Semantic parsing method, system, device and readable storage medium | |
| CN113268566B (en) | Question and answer pair quality evaluation method, device, equipment and storage medium | |
| CN111192149B (en) | Nuclear insurance result data generation 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |