CN110795566A - Case recommendation method, device and equipment and computer-readable storage medium - Google Patents
Case recommendation method, device and equipment and computer-readable storage medium Download PDFInfo
- Publication number
- CN110795566A CN110795566A CN201910883521.9A CN201910883521A CN110795566A CN 110795566 A CN110795566 A CN 110795566A CN 201910883521 A CN201910883521 A CN 201910883521A CN 110795566 A CN110795566 A CN 110795566A
- Authority
- CN
- China
- Prior art keywords
- case
- knowledge graph
- knowledge
- dispute focus
- similarity
- 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 51
- 238000004590 computer program Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000013507 mapping Methods 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 8
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 9
- 239000013598 vector Substances 0.000 description 7
- 238000000605 extraction Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a case recommendation method, a case recommendation device and a computer readable storage medium, wherein the method comprises the following steps: acquiring case judgment data of a target case, determining a model based on a preset dispute focus, and determining the dispute focus of the target case according to the case judgment data; constructing a first knowledge graph of the target case according to the case data and the dispute focus; determining a candidate case set to be recommended from a prestored case judging library according to the dispute focus; acquiring a second knowledge graph corresponding to each candidate case in the candidate case set, and calculating the similarity between the first knowledge graph and each second knowledge graph; and determining the same case and case from the candidate case set according to the similarity between the first knowledge graph and each second knowledge graph. The application relates to data analysis and a knowledge graph, and can accurately determine the case of the same case and the same judgment.
Description
Technical Field
The present application relates to the field of data analysis technologies, and in particular, to a case recommendation method, apparatus, device, and computer-readable storage medium.
Background
At present, the dispute focus of a case usually represents the whole case, so a judge needs to determine the dispute focus according to an original appeal, an informed dialect and evidence items provided by both parties, and the case can be finalized by solving the dispute focus, and the fact elements, evidences, laws and regulations and the like need to be considered in the dispute focus, but the fact elements, the evidences and laws and regulations are complex, the same dispute focus can be generated, but the case judgment result is different, and the judge is not convenient for the judge to determine the case.
In order to solve the problems, when a judge examines a case, the judge refers to similar cases which are judged previously so as to effectively standardize and limit the free judgment right, thereby ensuring that the laws and the applications of similar cases are basically unified, the judgment scales are basically the same, and the case judgment results are basically consistent. However, the cases that have been tried before are many, it takes much time to find similar cases, and judges subjectively determine the logical relationship between cases, and the case situation of the found similar cases may not be suitable for the case of the current trial, which affects the case efficiency. Therefore, how to accurately determine the same case and the same case of a case, ensure the same case and the same judgment, and improve the case judgment efficiency is a problem to be solved urgently at present.
Disclosure of Invention
The application mainly aims to provide a case recommendation method, a case recommendation device, case recommendation equipment and a computer readable storage medium, aiming at accurately determining the same case and the same case judgment of a case, ensuring the same case and the same judgment and improving the case judgment efficiency.
In a first aspect, the present application provides a case recommendation method, including the steps of:
acquiring case judgment data of a target case, determining a model based on a preset dispute focus, and determining the dispute focus of the target case according to the case judgment data;
constructing a first knowledge graph of the target case according to the case data and the dispute focus;
determining a candidate case set to be recommended from a prestored case judging library according to the dispute focus;
acquiring a second knowledge graph corresponding to each candidate case in the candidate case set, and calculating the similarity between the first knowledge graph and each second knowledge graph;
and determining the same case and case from the candidate case set according to the similarity between the first knowledge graph and each second knowledge graph.
In a second aspect, the present application further provides a case recommending apparatus, including:
the dispute focus determining module is used for acquiring case judgment data of the target case, determining a model based on a preset dispute focus and determining the dispute focus of the target case according to the case judgment data;
the map construction module is used for constructing a first knowledge map of the target case according to the case data and the dispute focus;
the candidate case determining module is used for determining a candidate case set to be recommended from a prestored case judging library according to the dispute focus;
the calculation module is used for acquiring a second knowledge graph corresponding to each candidate case in the candidate case set and calculating the similarity between the first knowledge graph and each second knowledge graph;
and the case determining module is used for determining the same case and case from the candidate case set according to the similarity between the first knowledge graph and each second knowledge graph.
In a third aspect, the present application further provides a computer device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program, when executed by the processor, implements the steps of the case recommendation method as described above.
In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, where the computer program, when being executed by a processor, implements the steps of the case recommendation method as described above.
The application provides a case recommendation method, a case recommendation device, case recommendation equipment and a computer readable storage medium, wherein a model is determined based on a dispute focus, the dispute focus of a target case can be accurately determined according to case decision data, a knowledge graph of the target case is constructed according to the case decision data and the dispute focus, a candidate case set to be recommended is determined according to the dispute focus, then the similarity between the knowledge graph of the target case and the knowledge graph corresponding to each candidate case is calculated, and the case with the same case and the same judgment can be accurately determined according to the similarity between the knowledge graph of the target case and the knowledge graph corresponding to each candidate case.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flowchart of a case recommendation method according to an embodiment of the present application;
FIG. 2 is a schematic illustration of a knowledge graph in an embodiment of the present application;
FIG. 3 is a schematic flowchart of another case recommendation method according to an embodiment of the present application;
FIG. 4 is a schematic block diagram of a case recommending apparatus according to an embodiment of the present application;
FIG. 5 is a schematic block diagram of another case recommending apparatus provided in the embodiments of the present application;
fig. 6 is a block diagram schematically illustrating a structure of a computer device according to an embodiment of the present application.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The flow diagrams depicted in the figures are merely illustrative and do not necessarily include all of the elements and operations/steps, nor do they necessarily have to be performed in the order depicted. For example, some operations/steps may be decomposed, combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
The embodiment of the application provides a case recommendation method, a case recommendation device, computer equipment and a computer readable storage medium. The case recommendation method can be applied to a server, and the server can be a single server or a server cluster consisting of a plurality of servers.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a flowchart illustrating a case recommendation method according to an embodiment of the present application.
As shown in fig. 1, the case recommendation method includes steps S101 to S105.
Step S101, obtaining case judging data of a target case, determining a model based on a preset dispute focus, and determining the dispute focus of the target case according to the case judging data.
The method comprises the steps that case parties upload case judging data such as complaint request texts, debt texts and evidence information of unapproved cases to a server through terminal equipment, or the case parties submit the case judging data such as the complaint request texts, the debt texts and the evidence information of the unapproved cases to a court in an offline mode, staff of the court uploads the case judging data submitted by the case parties to the server through the terminal equipment, and the server stores the case judging data of the unapproved cases.
The case data includes complaint text including both the original information and the complaint points, complaint text including the defended information and the complaint points, and evidence information including, but not limited to, literature information, material evidence information, audiovisual material, witness testimonials, party statements, and appraisal conclusions. The evidence attribute refers to the characteristic attribute of the evidence, such as whether the evidence is a debt or not, and the signature of the borrower exists.
When a triggered co-case recommending instruction is monitored, determining an unrejuted case needing to be recommended as a co-case according to the co-case recommending instruction, recommending the unrejuted case as a target case, and then acquiring case judging data of the target case. The method comprises the steps that a trigger mode of the same case recommendation instruction comprises real-time trigger and timing trigger, wherein the real-time trigger is to acquire a case number of an undetermined case needing to recommend the same case from a case same case recommendation request and trigger the same case recommendation instruction containing the case number when the same case recommendation request sent by terminal equipment is monitored; and setting a timing task for the server by timing triggering, acquiring a case number from the case recommendation queue at regular time through the timing task, and triggering a case reasoning instruction containing the case number.
Specifically, the server extracts original complaint request information, reported dialectical information and evidence information from the case data; determining a preset number of candidate dispute focuses and an output probability value of each candidate dispute focus based on a preset dispute focus determination model according to original appeal information, reported dialectical information and evidence information; and taking the candidate dispute focus with the maximum output probability value as the dispute focus of the target case. The server stores a first regular expression for extracting original complaint request information and a second regular expression for extracting the reported dialectical information, the original complaint request information can be extracted from the case data through the first regular expression, and the reported dialectical information can be extracted from the case data through the second regular expression.
The evidence information extraction method specifically comprises the following steps: extracting evidence sentences and evidence items in each evidence sentence from the case data through an evidence item extraction model; and determining an evidence category of each evidence item and an evidence attribute of each evidence category, and taking each evidence item, the evidence category of each evidence item and the evidence attribute of each evidence category as evidence information.
In an embodiment, the evidence type is determined in a specific manner as follows: acquiring an evidence large class of an evidence item and each evidence small class under the evidence large class from a preset evidence classification table, calculating the similarity between the evidence item and an evidence keyword corresponding to each evidence small class under the evidence large class through a similarity formula, and determining the evidence small class with the maximum similarity as the evidence class of the evidence item. It should be noted that the evidence classification table may be set based on actual situations, and the present application is not limited to this.
In an embodiment, the evidence attribute is determined in a specific manner as follows: for each type of evidence, traversing the case data and determining the context information of each type of evidence; inquiring a mapping relation table of pre-stored evidence attributes and evidence keywords, acquiring a target evidence statement containing the evidence keywords from the context information of each type of evidence, and acquiring an evidence attribute group corresponding to the target evidence statement; after the target evidence statement and the evidence attribute group are spliced, a similarity calculation model is input, the similarity between each evidence attribute in the evidence attribute group and the target evidence statement is calculated, and the evidence attribute with the highest similarity is used as the evidence attribute of the corresponding evidence category, so that the evidence attribute of each evidence category is obtained. It should be noted that the mapping relationship table between the evidence attribute and the evidence keyword may be set based on actual situations, and this is not specifically limited in this application.
The evidence item extraction model is obtained by training sample data based on manual labeling through an AutoNER (Auto Named Entity Recognition), the AutoNER model is embedded by using word vectors trained aiming at the sanction document, the automatic remote labeling data accuracy is too low, so that the model is abandoned and the manually labeled data is used for training, the accuracy of the manually labeled sample data is higher, and in addition, in order to prevent overfitting, a data enhancement method is adopted during training, namely, no more than 3 words in evidence sentences are replaced randomly and/or the sequence of the words in the evidence sentences is changed. The similarity calculation model is obtained by retraining a pre-training model of the BERT model based on legal corpora, reducing an encoder module (a coding module) of the BERT model to 3 layers, adjusting the length of a sentence, and accordingly achieving optimization in time. The AutoNER model is a model which can automatically mark data and train named entity recognition without manual marking, and the BERT model is the first deep, bidirectional and unsupervised language representation model.
And S102, constructing a first knowledge graph of the target case according to the case data and the dispute focus.
Specifically, basic case knowledge information and evidence knowledge information are extracted from case data, a dispute focus, the basic case knowledge information and the evidence knowledge information are used as case knowledge information of a target case, then, legal knowledge matched with the case knowledge information is obtained from a preset legal knowledge base, and a knowledge graph of the target case is constructed according to the case knowledge information and the legal knowledge and recorded as a first knowledge graph.
The knowledge graph construction mode specifically comprises the following steps: the method comprises the steps of taking the law in the law knowledge and the original report, the defendant, the appeal viewpoint, the dialectical viewpoint, the dispute focus, the fact elements and the evidence in case knowledge information as entity nodes of a knowledge graph, obtaining the relation and the attribute (the specific values of the original report, the defendant, the appeal viewpoint, the dialectical viewpoint, the dispute focus, the fact elements, the evidence and the law) between each entity node from the law knowledge and the case knowledge information, and then constructing the knowledge graph of the target case based on the relation between the entity nodes and the attribute of the entity nodes.
Referring to fig. 2, fig. 2 is a schematic diagram of a knowledge graph in an embodiment of the present application, and as shown in fig. 2, entity nodes of the knowledge graph are an original announcement, an announced announcement, an appealing view, a dialectical view, a dispute focus, a fact element, an evidence, and a law enforcement, and the fact element includes a small element 1, a small element 2, and a small element 3, where the small element 1 corresponds to the law enforcement 1, the small element 2 corresponds to the law enforcement 2, and the small element 3 corresponds to the law enforcement 3.
And S103, determining a candidate case set to be recommended from a prestored case judging library according to the dispute focus.
The server also determines a candidate case set to be recommended from a prestored case judging library according to the dispute focus of the target case, namely traversing a prestored knowledge graph of all judged cases in the case judging library, acquiring the judged cases including the dispute focus in the knowledge graph, collecting each acquired judged case to form a judged case set, and taking the judged case set as the candidate case set to be recommended.
The server stores a knowledge graph of the judged cases, the knowledge graph is recorded as a second knowledge graph, case knowledge information and legal knowledge information are stored in the knowledge graph of the cases, the case knowledge information comprises basic case knowledge, dispute focus knowledge, fact element knowledge and evidence knowledge, the basic case knowledge comprises but is not limited to litigation persons, litigation companies, litigation participant relations, original reports, complaint opinions and dialectical opinions, the dispute focus knowledge comprises dispute focuses, and the evidence knowledge comprises evidence items, evidence categories and evidence attributes. The evidence attribute refers to the characteristic attribute of the evidence, such as whether the evidence is a debt or not, and the signature of the borrower exists. Each original appeal has at least one fact such as "a requests B to pay back" that "a borrows B and B does not.
The following explains the construction method of the knowledge graph of the judged case by taking the judged case as an example. Specifically, a decision document of the decided case is obtained, case knowledge extraction is carried out on the decision document, structured case knowledge information and law bar knowledge information of the decided case are obtained, and then a knowledge graph of the decided case is constructed according to the case knowledge information and the law bar knowledge information. The judgment document comprises a character relation part, a case origin part, an examination passing part, a fact part and a judgment reason and basis part. The character relation part comprises the basic situation of the party, the basic situation of the entrusted litigation agent and the litigation status of the party; the case origin part comprises the complaint information and the dialectical information, the trial pass part is recorded in the court trial, the fact part comprises the litigation request, the fact and the reason of the original complaint, the fact and the reason of the alleged complaint and the fact and evidence according to the law, the reason and the evidence part comprise the relationship between the evidence and the dispute focus and the relationship between the judgment evidence and the legal provision.
Step S104, acquiring a second knowledge graph corresponding to each candidate case in the candidate case set, and calculating the similarity between the first knowledge graph and each second knowledge graph.
After determining the candidate case set, the server acquires a second knowledge graph corresponding to each candidate case in the candidate case set, and calculates the similarity between the first knowledge graph and each second knowledge graph. It should be noted that the similarity between the first knowledge graph and each second knowledge graph is the similarity between the target case and each candidate case.
In one embodiment, the server obtains first case knowledge information from the first knowledge graph, and obtains respectively corresponding second case knowledge information from each second knowledge graph; and calculating the similarity between the first knowledge graph and each second knowledge graph according to the first case knowledge information and each second case knowledge information. The first case knowledge information comprises attribute information and relationship information of each entity node in the first knowledge graph, and the second knowledge information comprises attribute information and relationship information of each entity node in the second knowledge graph.
In one embodiment, the server calculates target similarity between each entity node in the first knowledge graph and the corresponding entity node in each second knowledge graph according to the first case knowledge information and each second case knowledge information; and calculating the similarity between the first knowledge graph and each second knowledge graph according to the preset coefficient and each target similarity corresponding to each entity node in the first knowledge graph.
Taking a second knowledge graph as an example to explain the calculation of the target similarity, specifically, acquiring the attribute information and/or relationship information of each first entity node from the first case knowledge information, and acquiring the attribute information and/or relationship information of each second entity node from the second case knowledge information; calculating a first similarity between each first entity node and the corresponding second entity node according to the attribute information of each first entity node and the attribute information of each second entity node; and/or calculating a second similarity between each first entity node and the corresponding second entity node according to the relationship information of each first entity node and the relationship information of each second entity node; and taking the first similarity and/or the second similarity between each first entity node and the corresponding second entity node as the target similarity between each entity node in the first knowledge graph and the corresponding entity node in each second knowledge graph.
The attribute information is attributes of entity nodes in the knowledge graph, such as specific parameters of entity nodes of a dispute focus, fact elements, evidence and the like, the relationship information is relationship information between the entity nodes in the knowledge graph, such as a relationship between the dispute focus and the fact elements, semantic similarity between cases can be obtained through the attribute information, and logical similarity between cases can be obtained through the relationship information. The reliability and accuracy of the similarity can be improved.
When the target similarity is the first similarity and the second similarity, the calculation method of the similarity between the first knowledge graph and the second knowledge graph specifically comprises the following steps: after multiplying each first similarity by the corresponding first weight coefficient, accumulating to obtain a first target similarity between the first knowledge graph and the second knowledge graph; after each second similarity is multiplied by the corresponding second weight coefficient, accumulating to obtain a second target similarity between the first knowledge graph and the second knowledge graph; and calculating the sum of the similarity of the first target and the similarity of the second target, and taking the sum of the similarity of the first target and the similarity of the second target as the similarity between the first knowledge graph and the second knowledge graph. The semantic and logical similarity between cases can be comprehensively considered through the attribute information and the relationship information, and the reliability and accuracy of the similarity are further improved.
It should be noted that the first weight coefficient and the second weight coefficient may be set based on actual situations, the first weight coefficient of each entity node may be the same or different, and the second weight coefficient of each entity node may be the same or different, and the present application is not limited specifically.
And S105, determining the same case and the same case from the candidate case set according to the similarity between the first knowledge graph and each second knowledge graph.
Specifically, the similarity between the first knowledge graph and each second knowledge graph is used as the similarity between the target case and each candidate case in the candidate case set, each candidate case in the candidate case set is ranked according to the sequence of the similarity, the candidate case with the highest ranking is used as the same case identical judging case, and the candidate case with the highest similarity is used as the same case identical judging case.
The case recommendation method provided in the above embodiment may be based on the dispute focus determination model, may accurately determine the dispute focus of the target case according to the case data, construct the knowledge graph of the target case according to the case data and the dispute focus, determine the candidate case set to be recommended according to the dispute focus, then calculate the similarity between the knowledge graph of the target case and the knowledge graph corresponding to each candidate case, and may accurately determine the cases with the same case and the same judgment according to the similarity between the knowledge graph of the target case and the knowledge graph corresponding to each candidate case.
Referring to fig. 3, fig. 3 is a schematic flow chart of another case recommendation method according to an embodiment of the present application.
As shown in fig. 3, the case recommendation method includes steps S201 to 206.
Step S201, obtaining case decision data of a target case, determining a model based on a preset dispute focus, and determining the dispute focus of the target case according to the case decision data.
When a triggered co-case recommending instruction is monitored, determining an unrejuted case needing to be recommended as a co-case according to the co-case recommending instruction, recommending the unrejuted case as a target case, and then acquiring case judging data of the target case.
Specifically, the server extracts original complaint request information, reported dialectical information and evidence information from the case data; determining a preset number of candidate dispute focuses and an output probability value of each candidate dispute focus based on a preset dispute focus determination model according to original appeal information, reported dialectical information and evidence information; and taking the candidate dispute focus with the maximum output probability value as the dispute focus of the target case.
Step S202, constructing a first knowledge graph of the target case according to the case data and the dispute focus.
Specifically, basic case knowledge information and evidence knowledge information are extracted from case data, a dispute focus, the basic case knowledge information and the evidence knowledge information are used as case knowledge information of a target case, then, legal knowledge matched with the case knowledge information is obtained from a preset legal knowledge base, and a knowledge graph of the target case is constructed according to the case knowledge information and the legal knowledge and recorded as a first knowledge graph.
And step S203, calculating the similarity between the dispute focus and the dispute focus of each judged case in the prestored judged case library.
The server calculates the similarity between the dispute focus of the target case and the dispute focus of each judged case in the prestored judged case library, namely, encodes each word in the dispute focus of the target case to obtain a first vector, encodes each word in the dispute focus of each judged case to obtain a corresponding second vector, calculates the cosine similarity between the first vector and each second vector, and takes the cosine similarity between the first vector and each second vector as the similarity between the dispute focus of the target case and the dispute focus of each judged case.
In one embodiment, the server counts the total number of cases of the cases already judged, and determines the number of concurrent threads according to the total number of cases, namely, obtains a pre-stored mapping relation table between the number of cases and the number of concurrent threads, and queries the mapping relation table to obtain the number of concurrent threads corresponding to the total number of cases; and calling a corresponding number of idle threads in a preset thread pool according to the number of concurrent threads to calculate the similarity between the dispute focus and the dispute focus of each judged case. It should be noted that the mapping relationship table between the number of cases and the number of concurrent threads and the number of threads in the thread pool may be set based on actual situations, which is not specifically limited in this application. The similarity calculation speed can be improved by simultaneously calculating the similarity between the dispute focus and the dispute focus of each judged case through a plurality of threads.
And S204, determining a candidate case set to be recommended from a prestored case judging library according to the similarity between the dispute focus and the dispute focus of each judged case.
After the similarity between the dispute focus of the target case and the dispute focus of each judged case is obtained through calculation, each judged case with the similarity larger than a preset similarity threshold value is written into a preset candidate case blank set to form a candidate case set to be recommended. It should be noted that the similarity threshold may be set based on actual situations, and this is not specifically limited in this application.
Step S205, a second knowledge graph corresponding to each candidate case in the candidate case set is obtained, and the similarity between the first knowledge graph and each second knowledge graph is calculated.
After determining the candidate case set, the server acquires a second knowledge graph corresponding to each candidate case in the candidate case set, and calculates the similarity between the first knowledge graph and each second knowledge graph. It should be noted that the similarity between the first knowledge graph and each second knowledge graph is the similarity between the target case and each candidate case.
And S206, determining the same case and the same case from the candidate case set according to the similarity between the first knowledge graph and each second knowledge graph.
Specifically, the similarity between the first knowledge graph and each second knowledge graph is used as the similarity between the target case and each candidate case in the candidate case set, each candidate case in the candidate case set is ranked according to the sequence of the similarity, the candidate case with the highest ranking is used as the same case identical judging case, and the candidate case with the highest similarity is used as the same case identical judging case.
According to the case recommendation method provided by the embodiment, the candidate case set to be recommended can be accurately determined through the similarity between the dispute focus of the target case and the dispute focus of each judged case, and meanwhile, cases similar to the target case can be further accurately determined based on the similarity between the knowledge graph of the target case and the knowledge graph of each candidate case, so that the same case judgment is ensured, and the case judgment efficiency is improved.
Referring to fig. 4, fig. 4 is a schematic block diagram of a case recommending apparatus according to an embodiment of the present application.
As shown in fig. 4, the case recommendation apparatus 300 includes: a dispute focus determination module 301, a graph construction module 302, a candidate case determination module 303, a calculation module 304, and a case determination module 305.
The dispute focus determining module 301 is configured to obtain case decision data of a target case, determine a dispute focus of the target case according to the case decision data based on a preset dispute focus determining model;
the map construction module 302 is configured to construct a first knowledge map of the target case according to the case data and the dispute focus;
a candidate case determining module 303, configured to determine a candidate case set to be recommended from a prestored case decision library according to the dispute focus;
a calculating module 304, configured to obtain a second knowledge graph corresponding to each candidate case in the candidate case set, and calculate a similarity between the first knowledge graph and each second knowledge graph;
a case determining module 305, configured to determine the same case and case from the candidate case set according to the similarity between the first knowledge graph and each second knowledge graph.
In one embodiment, the dispute focus determining module 301 is further configured to extract original complaint request information, debated dialect information, and evidence information from the case data; determining a preset number of candidate dispute focuses and an output probability value of each candidate dispute focus based on a preset dispute focus determination model according to the original complaint request information, the reported dialectical information and the evidence information; and taking the candidate dispute focus with the maximum output probability value as the dispute focus of the target case.
In one embodiment, the calculation module 304 is further configured to obtain first case knowledge information from the first knowledge-graph, and obtain respectively corresponding second case knowledge information from each of the second knowledge-graphs; and calculating the similarity between the first knowledge graph and each second knowledge graph according to the first case knowledge information and each second case knowledge information.
In one embodiment, the calculating module 304 is further configured to calculate a target similarity between each entity node in the first knowledge-graph and a corresponding entity node in each second knowledge-graph according to the first case knowledge information and each second case knowledge information;
and calculating the similarity between the first knowledge graph and each second knowledge graph according to the preset coefficient corresponding to each entity node in the first knowledge graph and each target similarity.
Referring to fig. 5, fig. 5 is a schematic block diagram of another case recommending apparatus according to an embodiment of the present application.
As shown in fig. 5, the case recommendation apparatus 400 includes: a dispute focus determination module 401, a graph construction module 402, a first calculation module 403, a candidate case determination module 404, a second calculation module 405, and a case determination module 406.
The dispute focus determination module 401 is configured to obtain case decision data of a target case, determine a dispute focus of the target case according to the case decision data based on a preset dispute focus determination model;
the map construction module 402 is configured to construct a first knowledge map of the target case according to the case data and the dispute focus;
a first calculating module 403, configured to calculate similarity between the dispute focus and a dispute focus of each pre-stored decided case in the case decision library;
a candidate case determining module 404, configured to determine a candidate case set to be recommended from a prestored case decision library according to a similarity between the dispute focus and a dispute focus of each decided case;
a second calculating module 405, configured to obtain a second knowledge graph corresponding to each candidate case in the candidate case set, and calculate a similarity between the first knowledge graph and each second knowledge graph;
and the case determining module 406 is configured to determine the same case and case from the candidate case set according to the similarity between the first knowledge graph and each second knowledge graph.
In an embodiment, the first calculating module 403 is further configured to count the total number of cases judged and determine a concurrent thread number according to the total number of cases; and calling a corresponding number of idle threads in a preset thread pool according to the number of concurrent threads to calculate the similarity between the dispute focus and the dispute focus of each pre-stored judged case in the case judgment library.
In an embodiment, the first calculating module 403 is further configured to obtain a mapping relationship table between a pre-stored case quantity and a concurrent thread quantity, query the mapping relationship table, and obtain the concurrent thread quantity corresponding to the case quantity.
It should be noted that, as will be clear to those skilled in the art, for convenience and brevity of description, the specific working processes of the above-described apparatus and each module and unit may refer to the corresponding processes in the foregoing case recommendation method embodiment, and are not described herein again.
The apparatus provided by the above embodiments may be implemented in the form of a computer program, which can be run on a computer device as shown in fig. 6.
Referring to fig. 6, fig. 6 is a schematic block diagram illustrating a structure of a computer device according to an embodiment of the present disclosure. The computer device may be a server.
As shown in fig. 6, the computer device includes a processor, a memory, and a network interface connected by a system bus, wherein the memory may include a nonvolatile storage medium and an internal memory.
The non-volatile storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause a processor to perform any of the case recommendation methods.
The processor is used for providing calculation and control capability and supporting the operation of the whole computer equipment.
The internal memory provides an environment for running a computer program on the non-volatile storage medium, which when executed by the processor causes the processor to perform any of the case recommendation methods.
The network interface is used for network communication, such as sending assigned tasks and the like. Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
It should be understood that the Processor may be a Central Processing Unit (CPU), and the Processor may be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, etc. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Wherein, in one embodiment, the processor is configured to execute a computer program stored in the memory to implement the steps of:
acquiring case judgment data of a target case, determining a model based on a preset dispute focus, and determining the dispute focus of the target case according to the case judgment data;
constructing a first knowledge graph of the target case according to the case data and the dispute focus;
determining a candidate case set to be recommended from a prestored case judging library according to the dispute focus;
acquiring a second knowledge graph corresponding to each candidate case in the candidate case set, and calculating the similarity between the first knowledge graph and each second knowledge graph;
and determining the same case and case from the candidate case set according to the similarity between the first knowledge graph and each second knowledge graph.
In one embodiment, the processor, when implementing a predetermined dispute focus determination model based on the scenario data to determine the dispute focus of the target case, is configured to implement:
extracting original complaint request information, reported dialectical information and evidence information from the case data;
determining a preset number of candidate dispute focuses and an output probability value of each candidate dispute focus based on a preset dispute focus determination model according to the original complaint request information, the reported dialectical information and the evidence information;
and taking the candidate dispute focus with the maximum output probability value as the dispute focus of the target case.
In one embodiment, the processor, in effecting calculating the similarity between the first knowledge-graph and each of the second knowledge-graphs, is operable to effect:
acquiring first case knowledge information from the first knowledge graph, and acquiring respectively corresponding second case knowledge information from each second knowledge graph;
and calculating the similarity between the first knowledge graph and each second knowledge graph according to the first case knowledge information and each second case knowledge information.
In one embodiment, the processor, in effecting calculating a similarity between the first knowledge-graph and each of the second knowledge-graphs based on the first case knowledge information and each of the second case knowledge information, is configured to effect:
calculating target similarity between each entity node in the first knowledge graph and the corresponding entity node in each second knowledge graph according to the first case knowledge information and each second case knowledge information;
and calculating the similarity between the first knowledge graph and each second knowledge graph according to the preset coefficient corresponding to each entity node in the first knowledge graph and each target similarity.
Wherein in another embodiment the processor is adapted to run a computer program stored in the memory to implement the steps of:
acquiring case judgment data of a target case, determining a model based on a preset dispute focus, and determining the dispute focus of the target case according to the case judgment data;
constructing a first knowledge graph of the target case according to the case data and the dispute focus;
calculating the similarity between the dispute focus and the dispute focus of each judged case in a prestored case judgment case library;
determining a candidate case set to be recommended from a prestored case judging library according to the similarity between the dispute focus and the dispute focus of each judged case;
acquiring a second knowledge graph corresponding to each candidate case in the candidate case set, and calculating the similarity between the first knowledge graph and each second knowledge graph;
and determining the same case and case from the candidate case set according to the similarity between the first knowledge graph and each second knowledge graph.
In one embodiment, the processor, in performing calculating the similarity between the dispute focus and the dispute focus of each decided case in the pre-stored case-resolved library, is configured to perform:
counting the total number of cases of the case-judged cases, and determining the number of concurrent processes according to the total number of cases;
and calling a corresponding number of idle threads in a preset thread pool according to the number of concurrent threads to calculate the similarity between the dispute focus and the dispute focus of each pre-stored judged case in the case judgment library.
In one embodiment, the processor, in effecting determining the number of concurrent threads based on the total number, is configured to effect:
and acquiring a mapping relation table between the pre-stored case quantity and the concurrent thread quantity, and inquiring the mapping relation table to acquire the concurrent thread quantity corresponding to the total case quantity.
It should be noted that, as will be clear to those skilled in the art, for convenience and brevity of description, the specific working process of the computer device described above may refer to the corresponding process in the foregoing case recommendation method embodiment, and is not described herein again.
Embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, where the computer program includes program instructions, and a method implemented when the program instructions are executed may refer to the embodiments of the case recommendation method of the present application.
The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, for example, a hard disk or a memory of the computer device. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the computer device.
It is to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present 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 in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments. While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A case recommendation method is characterized by comprising the following steps:
acquiring case judgment data of a target case, determining a model based on a preset dispute focus, and determining the dispute focus of the target case according to the case judgment data;
constructing a first knowledge graph of the target case according to the case data and the dispute focus;
determining a candidate case set to be recommended from a prestored case judging library according to the dispute focus;
acquiring a second knowledge graph corresponding to each candidate case in the candidate case set, and calculating the similarity between the first knowledge graph and each second knowledge graph;
and determining the same case and case from the candidate case set according to the similarity between the first knowledge graph and each second knowledge graph.
2. The case recommendation method according to claim 1, wherein said determining a dispute focus of said target case according to said case data based on a preset dispute focus determination model comprises:
extracting original complaint request information, reported dialectical information and evidence information from the case data;
determining a preset number of candidate dispute focuses and an output probability value of each candidate dispute focus based on a preset dispute focus determination model according to the original complaint request information, the reported dialectical information and the evidence information;
and taking the candidate dispute focus with the maximum output probability value as the dispute focus of the target case.
3. A case recommendation method according to claim 1, wherein said calculating a similarity between said first knowledge-graph and each said second knowledge-graph comprises:
acquiring first case knowledge information from the first knowledge graph, and acquiring respectively corresponding second case knowledge information from each second knowledge graph;
and calculating the similarity between the first knowledge graph and each second knowledge graph according to the first case knowledge information and each second case knowledge information.
4. A case recommendation method according to claim 3, wherein said calculating a similarity between said first knowledge-graph and each said second knowledge-graph based on said first case knowledge information and each said second case knowledge information comprises:
calculating target similarity between each entity node in the first knowledge graph and the corresponding entity node in each second knowledge graph according to the first case knowledge information and each second case knowledge information;
and calculating the similarity between the first knowledge graph and each second knowledge graph according to the preset coefficient corresponding to each entity node in the first knowledge graph and each target similarity.
5. A case recommendation method according to any one of claims 1 to 4, wherein said determining a candidate case set to be recommended from a pre-stored case-judged library according to said dispute focus comprises:
calculating the similarity between the dispute focus and the dispute focus of each judged case in a prestored case judgment case library;
and determining a candidate case set to be recommended from a prestored case judging library according to the similarity between the dispute focus and the dispute focus of each judged case.
6. The case recommendation method according to claim 5, wherein said calculating the similarity between said dispute focus and the dispute focus of each decided case in the pre-stored decided case library comprises:
counting the total number of cases of the case-judged cases, and determining the number of concurrent processes according to the total number of cases;
and calling a corresponding number of idle threads in a preset thread pool according to the number of concurrent threads to calculate the similarity between the dispute focus and the dispute focus of each pre-stored judged case in the case judgment library.
7. A case recommendation method according to claim 6, characterized in that said determining a number of concurrent threads according to said total number comprises:
and acquiring a mapping relation table between the pre-stored case quantity and the concurrent thread quantity, and inquiring the mapping relation table to acquire the concurrent thread quantity corresponding to the total case quantity.
8. A case recommending apparatus, characterized in that said case recommending apparatus comprises:
the dispute focus determining module is used for acquiring case judgment data of the target case, determining a model based on a preset dispute focus and determining the dispute focus of the target case according to the case judgment data;
the map construction module is used for constructing a first knowledge map of the target case according to the case data and the dispute focus;
the candidate case determining module is used for determining a candidate case set to be recommended from a prestored case judging library according to the dispute focus;
the calculation module is used for acquiring a second knowledge graph corresponding to each candidate case in the candidate case set and calculating the similarity between the first knowledge graph and each second knowledge graph;
and the case determining module is used for determining the same case and case from the candidate case set according to the similarity between the first knowledge graph and each second knowledge graph.
9. A computer arrangement, characterized in that the computer arrangement comprises a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program, when executed by the processor, carries out the steps of the case recommendation method as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, having a computer program stored thereon, wherein the computer program, when being executed by a processor, carries out the steps of the case recommendation method according to any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910883521.9A CN110795566A (en) | 2019-09-18 | 2019-09-18 | Case recommendation method, device and equipment and computer-readable storage medium |
| PCT/CN2020/093108 WO2021051865A1 (en) | 2019-09-18 | 2020-05-29 | Case recommendation method and device, apparatus, and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910883521.9A CN110795566A (en) | 2019-09-18 | 2019-09-18 | Case recommendation method, device and equipment and computer-readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110795566A true CN110795566A (en) | 2020-02-14 |
Family
ID=69427290
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910883521.9A Pending CN110795566A (en) | 2019-09-18 | 2019-09-18 | Case recommendation method, device and equipment and computer-readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110795566A (en) |
| WO (1) | WO2021051865A1 (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110019655A (en) * | 2017-07-21 | 2019-07-16 | 北京国双科技有限公司 | Precedent case acquisition methods and device |
| CN111814477A (en) * | 2020-07-06 | 2020-10-23 | 重庆邮电大学 | Dispute focus discovery method and device based on dispute focus entity and terminal |
| CN112487146A (en) * | 2020-12-02 | 2021-03-12 | 重庆邮电大学 | Legal case dispute focus acquisition method and device and computer equipment |
| WO2021051865A1 (en) * | 2019-09-18 | 2021-03-25 | 平安科技（深圳）有限公司 | Case recommendation method and device, apparatus, and computer readable storage medium |
| CN112632224A (en) * | 2020-12-29 | 2021-04-09 | 天津汇智星源信息技术有限公司 | Case recommendation method and device based on case knowledge graph and electronic equipment |
| CN113468323A (en) * | 2021-06-01 | 2021-10-01 | 成都数之联科技有限公司 | Dispute focus category and similarity judgment method, dispute focus category and similarity judgment system, dispute focus category and similarity judgment device and dispute focus category and similarity judgment recommendation method |
| CN114428848A (en) * | 2021-12-29 | 2022-05-03 | 航天科工网络信息发展有限公司 | Intelligent class case pushing method and system based on incidence relation |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113011789A (en) * | 2021-04-23 | 2021-06-22 | 集美大学 | Overwater dangerous chemical accident emergency aid decision-making method, terminal equipment and storage medium |
| CN113901781B (en) * | 2021-09-15 | 2024-04-26 | 昆明理工大学 | Similar case matching method integrating segment coding and affine mechanism |
| CN116910277B (en) * | 2023-09-13 | 2024-02-27 | 之江实验室 | Knowledge graph construction method, resource searching method, computer equipment and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108009299A (en) * | 2017-12-28 | 2018-05-08 | 北京市律典通科技有限公司 | Law tries method and device for business processing |
| CN108241621A (en) * | 2016-12-23 | 2018-07-03 | 北京国双科技有限公司 | The search method and device of legal knowledge |
| US20180218011A1 (en) * | 2017-02-02 | 2018-08-02 | Kensho Technologies, Inc. | Content Search Engine |
| CN108694178A (en) * | 2017-04-06 | 2018-10-23 | 北京国双科技有限公司 | A kind of method and device for recommending judicial cognizance |
| CN110209828A (en) * | 2018-02-12 | 2019-09-06 | 北大方正集团有限公司 | Case querying method and case inquiry unit, computer equipment and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100429054B1 (en) * | 1999-09-29 | 2004-05-03 | 주식회사 온빛시스템 | Automated intelligent item recommending system |
| CN107133276A (en) * | 2017-04-12 | 2017-09-05 | 安徽富驰信息技术有限公司 | A kind of judicial class case searching system and its search method |
| US10491952B2 (en) * | 2017-06-16 | 2019-11-26 | The Directv Group, Inc. | Scalable calculation of the similarity content graph |
| CN108280149A (en) * | 2018-01-04 | 2018-07-13 | 东南大学 | A kind of doctor-patient dispute class case recommendation method based on various dimensions tag along sort |
| CN110795566A (en) * | 2019-09-18 | 2020-02-14 | 平安科技（深圳）有限公司 | Case recommendation method, device and equipment and computer-readable storage medium |
-
2019
- 2019-09-18 CN CN201910883521.9A patent/CN110795566A/en active Pending
-
2020
- 2020-05-29 WO PCT/CN2020/093108 patent/WO2021051865A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108241621A (en) * | 2016-12-23 | 2018-07-03 | 北京国双科技有限公司 | The search method and device of legal knowledge |
| US20180218011A1 (en) * | 2017-02-02 | 2018-08-02 | Kensho Technologies, Inc. | Content Search Engine |
| CN108694178A (en) * | 2017-04-06 | 2018-10-23 | 北京国双科技有限公司 | A kind of method and device for recommending judicial cognizance |
| CN108009299A (en) * | 2017-12-28 | 2018-05-08 | 北京市律典通科技有限公司 | Law tries method and device for business processing |
| CN110209828A (en) * | 2018-02-12 | 2019-09-06 | 北大方正集团有限公司 | Case querying method and case inquiry unit, computer equipment and storage medium |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110019655A (en) * | 2017-07-21 | 2019-07-16 | 北京国双科技有限公司 | Precedent case acquisition methods and device |
| WO2021051865A1 (en) * | 2019-09-18 | 2021-03-25 | 平安科技（深圳）有限公司 | Case recommendation method and device, apparatus, and computer readable storage medium |
| CN111814477A (en) * | 2020-07-06 | 2020-10-23 | 重庆邮电大学 | Dispute focus discovery method and device based on dispute focus entity and terminal |
| CN111814477B (en) * | 2020-07-06 | 2022-06-21 | 重庆邮电大学 | Dispute focus discovery method and device based on dispute focus entity and terminal |
| CN112487146A (en) * | 2020-12-02 | 2021-03-12 | 重庆邮电大学 | Legal case dispute focus acquisition method and device and computer equipment |
| CN112632224A (en) * | 2020-12-29 | 2021-04-09 | 天津汇智星源信息技术有限公司 | Case recommendation method and device based on case knowledge graph and electronic equipment |
| CN112632224B (en) * | 2020-12-29 | 2023-01-24 | 天津汇智星源信息技术有限公司 | Case recommendation method and device based on case knowledge graph and electronic equipment |
| CN113468323A (en) * | 2021-06-01 | 2021-10-01 | 成都数之联科技有限公司 | Dispute focus category and similarity judgment method, dispute focus category and similarity judgment system, dispute focus category and similarity judgment device and dispute focus category and similarity judgment recommendation method |
| CN114428848A (en) * | 2021-12-29 | 2022-05-03 | 航天科工网络信息发展有限公司 | Intelligent class case pushing method and system based on incidence relation |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021051865A1 (en) | 2021-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110795566A (en) | Case recommendation method, device and equipment and computer-readable storage medium | |
| CN110825879B (en) | Decide a case result determination method, device, equipment and computer readable storage medium | |
| CN110825880A (en) | Case winning rate determining method, device, equipment and computer readable storage medium | |
| CN108491529B (en) | Information recommendation method and device | |
| US11429834B1 (en) | Neural-based agent assistance interface for providing answers based on a query vector | |
| CN109597874B (en) | Information recommendation method, device and server | |
| CN109325121B (en) | Method and device for determining keywords of text | |
| CN107545505B (en) | Method and system for identifying insurance financing product information | |
| CN113407677B (en) | Method, apparatus, device and storage medium for evaluating consultation dialogue quality | |
| CN111079029A (en) | Sensitive account detection method, storage medium and computer equipment | |
| US9417854B1 (en) | Functional use-case generation | |
| CN112579781B (en) | Text classification method, device, electronic equipment and medium | |
| CN110837732B (en) | Method and device for identifying intimacy between target persons, electronic equipment and storage medium | |
| CN112163415A (en) | User intention identification method and device for feedback content and electronic equipment | |
| CN110634018A (en) | Feature depiction method, recognition method and related device for lost user | |
| AU2019290658B2 (en) | Systems and methods for identifying and linking events in structured proceedings | |
| CN113010664A (en) | Data processing method and device and computer equipment | |
| Kaci et al. | From NL preference expressions to comparative preference statements: A preliminary study in eliciting preferences for customised decision support | |
| CN114297357B (en) | Question-answer model construction method and device based on quantum computation and electronic equipment | |
| US20240086433A1 (en) | Interactive tool for determining a headnote report | |
| CN117216650A (en) | Target object risk behavior early warning method and related equipment | |
| JP5368953B2 (en) | Advanced guidance recommendation method, program and device | |
| CN117836775A (en) | Apparatus, system, and method for intelligent determination of conversational intent | |
| CN113392181A (en) | Text relevance determining method and device, electronic equipment and medium | |
| CN117370649A (en) | Resource recommendation method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40019329 Country of ref document: HK |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |