CN116304078A - Legal case applicable legal condition recommendation method and device - Google Patents
Legal case applicable legal condition recommendation method and device Download PDFInfo
- Publication number
- CN116304078A CN116304078A CN202211724843.7A CN202211724843A CN116304078A CN 116304078 A CN116304078 A CN 116304078A CN 202211724843 A CN202211724843 A CN 202211724843A CN 116304078 A CN116304078 A CN 116304078A
- Authority
- CN
- China
- Prior art keywords
- legal
- case
- applicable
- target
- legal case
- 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 44
- 238000004590 computer program Methods 0.000 claims description 25
- 238000000605 extraction Methods 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 7
- 238000003062 neural network model Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 12
- 238000012545 processing Methods 0.000 description 9
- 239000000872 buffer Substances 0.000 description 4
- 238000013507 mapping Methods 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000007787 solid Substances 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
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/194—Calculation of difference between files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services; Handling legal documents
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a method and a device for recommending applicable legal conditions, wherein the method comprises the following steps: extracting characteristics of the text information of the target legal case to obtain the case characteristics of the target legal case; matching the case characteristics of the target legal case with a pre-established legal case applicable law knowledge graph to obtain a plurality of legal case applicable law to be matched; the legal case applicable legal condition knowledge graph comprises different legal case applicable legal conditions and corresponding legal case situation characteristics; calculating the case characteristics of the target legal case and the similarity between the case characteristics of the legal case corresponding to each legal case applicable rule to be matched; and taking the applicable legal rules of the legal cases to be matched, which have the similarity exceeding a preset value, as the applicable legal rules of the target legal cases, and sending out notification information carrying the applicable legal rules of the target legal cases. The method and the device are used for improving the efficiency and accuracy of applicable legal condition recommendation.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a method and a device for recommending applicable legal cases.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
At present, the intelligent court construction is continuously promoted, intelligent auxiliary supporting capability is built, and the intelligent court construction is a natural requirement for intelligent judgment.
In the case approval process, a judge needs to be based on facts, laws are standard, a large number of related laws and regulations are often consulted, the case fact analysis is combined to ensure the fairness and sense of judgment, and in fact, the consulting process often takes a large amount of time for case approval.
The main stream mode at present supports keyword retrieval laws and regulations, namely, the corresponding regulations are pushed according to the matching of the text of the to-be-processed case and keywords in the laws and regulations, but the mode increases the possibility of mismatching of the text of the case description and the corresponding regulations. The semantic relation among related keywords in the case description text is not beneficial to determining, so that the case to be processed can be matched with other types of regulations, and the possibility of mismatching between the case description text and the corresponding regulations is increased.
Disclosure of Invention
The embodiment of the invention provides a legal case applicable legal case recommendation method, which is used for improving the efficiency and accuracy of legal case applicable legal case recommendation, and comprises the following steps:
extracting characteristics of the text information of the target legal case to obtain the case characteristics of the target legal case;
matching the case characteristics of the target legal case with a pre-established legal case applicable law knowledge graph to obtain a plurality of legal case applicable law to be matched; the legal case applicable legal condition knowledge graph comprises different legal case applicable legal conditions and corresponding legal case situation characteristics;
calculating the case characteristics of the target legal case and the similarity between the case characteristics of the legal case corresponding to each legal case applicable rule to be matched;
and taking the applicable legal rules of the legal cases to be matched, which have the similarity exceeding a preset value, as the applicable legal rules of the target legal cases, and sending out notification information carrying the applicable legal rules of the target legal cases.
The embodiment of the invention also provides a legal case applicable legal case recommendation device, which is used for improving the efficiency and accuracy of legal case applicable legal case recommendation, and comprises the following steps:
the feature extraction module is used for extracting features of the text information of the target legal case to obtain the case characteristics of the target legal case;
the knowledge map matching module is used for matching the case characteristics of the target legal case with a pre-established legal case applicable law knowledge map to obtain a plurality of legal case applicable law to be matched; the legal case applicable legal condition knowledge graph comprises different legal case applicable legal conditions and corresponding legal case situation characteristics;
the similarity calculation module is used for calculating the similarity between the case characteristics of the target legal case and the legal case characteristics corresponding to each legal case applicable rule to be matched;
and the notification module is used for taking the applicable legal rules of the legal cases to be matched, which have the similarity exceeding a preset value, as the applicable legal rules of the target legal cases and sending notification information carrying the applicable legal rules of the target legal cases.
The embodiment of the invention also provides computer equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the applicable legal case recommendation method when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the applicable legal case recommendation method when being executed by a processor.
The embodiment of the invention also provides a computer program product, which comprises a computer program, and the computer program realizes the applicable legal case recommendation method when being executed by a processor.
In the embodiment of the invention, the text information of the target legal case is subjected to feature extraction to obtain the case condition features of the target legal case; matching the case characteristics of the target legal case with a pre-established legal case applicable law knowledge graph to obtain a plurality of legal case applicable law to be matched; the legal case applicable legal condition knowledge graph comprises different legal case applicable legal conditions and corresponding legal case situation characteristics; calculating the case characteristics of the target legal case and the similarity between the case characteristics of the legal case corresponding to each legal case applicable rule to be matched; the applicable legal case law of the to-be-matched legal case with the similarity exceeding the preset value is used as the applicable legal case of the target legal case, and notification information carrying the applicable legal case of the target legal case is sent out, so that the purposes of automatically pushing the applicable legal case of the target legal case by text information of the target legal case through establishing a knowledge graph and calculating the similarity are achieved, the problem that only keyword retrieval law is supported in the prior art to easily cause mismatching of a case description text and a corresponding rule is solved, efficiency and accuracy of recommending the applicable legal case are improved, legal rule reference can be provided for law and law interpretation, and intelligent auxiliary support is provided for intelligent trial.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
FIG. 1 is a schematic flow chart of a legal case applicable legal case recommendation method in an embodiment of the invention;
FIG. 2 is a specific example diagram of a legal case applicable legal case recommendation method in an embodiment of the present invention;
FIG. 3 is a specific example diagram of a legal case applicable legal case recommendation method in an embodiment of the present invention;
FIG. 4 is a specific example diagram of a legal case applicable legal case recommendation method in an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of a legal case applicable legal case recommendation device according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a computer device for applicable legal case recommendation in an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present invention and their descriptions herein are for the purpose of explaining the present invention, but are not to be construed as limiting the invention.
The term "and/or" is used herein to describe only one relationship, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist together, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.
In the description of the present specification, the terms "comprising," "including," "having," "containing," and the like are open-ended terms, meaning including, but not limited to. Reference to the terms "one embodiment," "a particular embodiment," "some embodiments," "for example," etc., means that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. The sequence of steps involved in the embodiments is used to schematically illustrate the practice of the present application, and is not limited thereto and may be appropriately adjusted as desired.
The data acquisition, storage, use, processing and the like in the technical scheme meet the relevant regulations of national laws and regulations.
The main stream mode at present supports keyword retrieval laws and regulations, namely, the corresponding regulations are pushed according to the matching of the text of the to-be-processed case and keywords in the laws and regulations, but the mode increases the possibility of mismatching of the text of the case description and the corresponding regulations. The semantic relation among related keywords in the case description text is not beneficial to determining, so that the case to be processed can be matched with other types of regulations, and the possibility of mismatching between the case description text and the corresponding regulations is increased.
In order to solve the above problems, an embodiment of the present invention provides a legal case applicable legal case recommendation method, for improving efficiency and accuracy of legal case applicable legal case recommendation, as shown in fig. 1, the method includes:
step 101: extracting characteristics of the text information of the target legal case to obtain the case characteristics of the target legal case;
step 102: matching the case characteristics of the target legal case with a pre-established legal case applicable law knowledge graph to obtain a plurality of legal case applicable law to be matched; the legal case applicable legal condition knowledge graph comprises different legal case applicable legal conditions and corresponding legal case situation characteristics;
step 103: calculating the case characteristics of the target legal case and the similarity between the case characteristics of the legal case corresponding to each legal case applicable rule to be matched;
step 104: and taking the applicable legal rules of the legal cases to be matched, which have the similarity exceeding a preset value, as the applicable legal rules of the target legal cases, and sending out notification information carrying the applicable legal rules of the target legal cases.
In the embodiment of the invention, the text information of the target legal case is subjected to feature extraction to obtain the case condition features of the target legal case; matching the case characteristics of the target legal case with a pre-established legal case applicable law knowledge graph to obtain a plurality of legal case applicable law to be matched; the legal case applicable legal condition knowledge graph comprises different legal case applicable legal conditions and corresponding legal case situation characteristics; calculating the case characteristics of the target legal case and the similarity between the case characteristics of the legal case corresponding to each legal case applicable rule to be matched; the applicable legal case law of the to-be-matched legal case with the similarity exceeding the preset value is used as the applicable legal case of the target legal case, and notification information carrying the applicable legal case of the target legal case is sent out, so that the purposes of automatically pushing the applicable legal case of the target legal case by text information of the target legal case through establishing a knowledge graph and calculating the similarity are achieved, the problem that only keyword retrieval law is supported in the prior art to easily cause mismatching of a case description text and a corresponding rule is solved, efficiency and accuracy of recommending the applicable legal case are improved, legal rule reference can be provided for law and law interpretation, and intelligent auxiliary support is provided for intelligent trial.
When the method is specifically implemented, firstly, feature extraction is carried out on text information of the target legal case, and the case characteristics of the target legal case are obtained.
In one embodiment, feature extraction is performed on text information of a target legal case to obtain a case feature of the target legal case, including:
based on a deep learning SKE algorithm, text extraction and text classification are carried out on the text information of the target legal cases, so that the text information of the target legal cases in different categories is obtained;
and extracting the characteristics of the text information of the target legal cases in different categories to obtain the case characteristics of the target legal cases.
In one embodiment, descriptive text of case facts may be obtained first, text mining and information extraction are performed on the descriptive text of case facts using natural language processing (Natural Language Processing, NLP), important information is located from the document, and a minimum set of terms in units of elements, that is, a set of case features of a target legal case, is generated.
For example, obtaining text data of a case description to obtain a data set containing case elements may include: and extracting case description text characteristic data based on a deep learning SKE method, classifying the extracted data according to part of speech, word meaning, syntax and fact knowledge, and reserving case characteristic elements, namely case elements.
In the above embodiment, it may be realized that the case is taken as coordinates, and the minimum entry set of the text containing the case element is obtained after integrating the case fact description related elements.
In specific implementation, after characteristic extraction is carried out on text information of a target legal case to obtain case characteristics of the target legal case, the case characteristics of the target legal case are matched with a pre-established legal case applicable law knowledge graph to obtain a plurality of legal case applicable law to be matched; the legal case applicable legal condition knowledge graph comprises different legal case applicable legal conditions and corresponding legal case situation characteristics.
In the embodiment, the mapping relation between the extracted case elements and laws and regulations can be established based on a unidirectional language model of a transducer, namely, modeling the input text from left to right.
In one embodiment, further comprising:
establishing a legal case applicable legal rule knowledge graph according to the legal case applicable legal rule historical data; the legal case applicable legal provision history data comprises: legal case applicable legal rules corresponding to the case characteristics of different historical legal cases.
In the above embodiment, the mapping relationship between the case elements and the matching laws of the case is established through the knowledge graph, and the law and regulation data set with the characteristics of the case is established by deep learning and mining the association between the laws and the case elements and between the upper laws and the lower laws based on the knowledge graph of the case facts elements.
In specific implementation, after the case characteristics of the target legal case are matched with the pre-established legal case applicable law pattern to obtain a plurality of legal case applicable law to be matched, calculating the similarity between the case characteristics of the target legal case and the case characteristics of the legal case corresponding to each legal case applicable law to be matched.
In the embodiment, first, the underlying logic of the related legal system can be definitely deduced, and the association relation of a plurality of case elements is set as the precondition of the corresponding legal system; extracting the case characteristics of the input case description information to obtain case elements, and then calculating the similarity between the case elements and the existing case elements in the database.
In one embodiment, calculating the case characteristics of the target legal case and the similarity between the case characteristics of the legal case corresponding to each legal case applicable legal rule to be matched includes:
for each legal case to be matched the applicable legal rules,
inputting the case characteristics of the target legal case and the legal case characteristics corresponding to the legal case applicable legal rules to be matched into a pre-trained GPT model to obtain the case characteristics of the target legal case and the similarity between the case characteristics of the legal case corresponding to each legal case applicable legal rules to be matched; the GPT model includes a multi-head attention structure, a layer normalization structure, and a fully connected layer structure.
For example, the case feature extraction may be performed on the input case description information to obtain a case element, and then similarity calculation is performed between the case element and an existing case element in the database, as shown in fig. 2.
In fig. 2, the similarity calculation task may be composed of two pieces of text, but unlike the text implication task, there is no sequential relationship between the two pieces of text that participate in the similarity calculation.
Examples of the assumed similarity calculation are respectively:
it will be entered into the GPT in the form of two corresponding hidden layer representations, as follows:
and finally, adding the two hidden layer representations, predicting the similarity through a full-connection layer, and finally obtaining the similarity of the case elements in the two texts.
In one embodiment, the similarity of the case fact description text to the plurality of legal requirements may be determined by a Pre-trained (GPT) model. Therefore, the context semantics of the case facts can be combined to perform different granularity rule matching, and the accuracy of the recommendation of the related laws is improved on the premise of guaranteeing the recommendation efficiency of the related laws of the case.
In order to improve the recommendation accuracy of the laws and improve the recommendation efficiency, the multi-layer attention mechanism in the transducer neural network model adopted by the embodiment of the invention is further optimized. As shown in fig. 3, the structure of the GPT model provided by the present invention specifically includes: multi-head attention, layer normalization, fully connected layer, layer normalized mode. In the pre-training stage, the GPT trains a language model based on deep convertors by using large-scale data, and has mastered the general semantic representation of the text. The purpose of the next Fine-tuning is to perform domain adaptation according to the characteristics of the Downstream task (Downstream task) on the basis of the general semantic representation, so that the domain adaptation is more compatible with the form of the Downstream task, and a better application effect of the Downstream task is obtained.
In order to further improve the accuracy of legal recommendation, the recommendation method provided by the invention further comprises similarity calculation, wherein two sections of texts respectively contain different tasks, the sequence limitation between the two sections of texts participating in the similarity calculation is eliminated, the two sections of texts are input into the GPT to obtain two corresponding hidden layer case elements, finally the two hidden layer elements are added, the similarity is predicted through a full-connection layer, and finally the accurate pushing of the relevant legal of the fusion case element is realized.
The embodiment of the invention can accurately match the corresponding legal regulation method according to the case facts, and aims to automatically push the relevant legal strips accurately matched according to the case facts, provide legal regulation reference for the judge of the judge officer and provide intelligent auxiliary support for intelligent judgment.
In specific implementation, after calculating the case characteristics of the target legal case and the similarity between the case characteristics of the legal case corresponding to each legal case applicable law of the legal case to be matched, the similarity exceeding a preset value, is used as the applicable law of the target legal case, and notification information carrying the applicable law of the target legal case is sent out.
In one embodiment, in the calculation result of the similarity, if the calculation result of the similarity is greater than or equal to the probability threshold, a law corresponding to the probability is reserved; and if the similarity calculation result is smaller than the probability threshold value, deleting a French corresponding to the probability.
In one embodiment, further comprising:
inputting the case characteristics of the target legal case into a legal case applicable legal rule recognition model to obtain a neural network judgment result of the target legal case applicable legal rule; the legal case applicable legal condition recognition model is obtained by training a Transformer neural network model through legal case applicable legal condition historical data; the legal case applicable legal provision history data comprises: legal case applicable legal rules corresponding to the case characteristics of different historical legal cases;
the legal case applicable law of the to-be-matched, the similarity of which exceeds a preset value, is used as the applicable law of the target legal case, and the method comprises the following steps:
matching the applicable legal rules of the target legal cases with the neural network judgment results of the applicable legal rules of the target legal cases;
after successful matching, the legal case applicable law of the to-be-matched, the similarity of which exceeds a preset value, is used as the applicable law of the target legal case.
In the above embodiment, a neural network model of a Transformer may be established, where the neural network model of the Transformer uses case fact elements as a set input, and uses probability that each case fact element matches a relevant law as an output.
The embodiment of the invention can enable the computer to understand the case content and analyze the case content by utilizing the deep neural network, and intelligently recommend the case related laws to the judge.
A specific embodiment is given below to illustrate a specific application of the method of the present invention, and in this embodiment, as shown in fig. 4, the following steps may be included:
s1, integrating related elements of case fact description by taking a case as coordinates to obtain a minimum entry set of text containing the case elements;
s2, establishing a mapping relation between the case elements and the matching laws of the case by using a knowledge graph, and establishing a law and regulation data set with the characteristics of the case by using the knowledge graph of the case fact elements as a basis and performing deep learning to mine the association between the laws and the case elements and between the upper laws and the lower laws;
s3, defining underlying logic for pushing out relevant laws, and setting association relations of a plurality of case elements as pre-conditions for pushing out corresponding laws; extracting the case characteristics of the input case description information to obtain case elements, and then calculating the similarity between the case elements and the existing case elements in the database;
and S4, pushing out the relevant law closest to the case fact description according to the matching degree between the case elements and the law through a Pre-trained (GPT) model.
As described above, the present embodiment can accurately match the corresponding legal regulation method according to the case facts, so as to automatically push the relevant legal strips accurately matched according to the case facts, provide legal regulation references for the legal officer's case, and provide intelligent auxiliary support for intelligent judgment.
Of course, it is to be understood that other variations of the above detailed procedures are also possible, and all related variations should fall within the protection scope of the present invention.
In the embodiment of the invention, the text information of the target legal case is subjected to feature extraction to obtain the case condition features of the target legal case; matching the case characteristics of the target legal case with a pre-established legal case applicable law knowledge graph to obtain a plurality of legal case applicable law to be matched; the legal case applicable legal condition knowledge graph comprises different legal case applicable legal conditions and corresponding legal case situation characteristics; calculating the case characteristics of the target legal case and the similarity between the case characteristics of the legal case corresponding to each legal case applicable rule to be matched; the applicable legal case law of the to-be-matched legal case with the similarity exceeding the preset value is used as the applicable legal case of the target legal case, and notification information carrying the applicable legal case of the target legal case is sent out, so that the purposes of automatically pushing the applicable legal case of the target legal case by text information of the target legal case through establishing a knowledge graph and calculating the similarity are achieved, the problem that only keyword retrieval law is supported in the prior art to easily cause mismatching of a case description text and a corresponding rule is solved, efficiency and accuracy of recommending the applicable legal case are improved, legal rule reference can be provided for law and law interpretation, and intelligent auxiliary support is provided for intelligent trial.
The embodiment of the invention also provides a legal case applicable legal case recommending device, which is expressed in the following embodiment. Because the principle of the device for solving the problem is similar to that of the applicable legal rules recommending method of the legal cases, the implementation of the device can be referred to the implementation of the applicable legal rules recommending method of the legal cases, and the repetition is not repeated.
The embodiment of the invention also provides a legal case applicable legal case recommendation device, which is used for improving the efficiency and accuracy of legal case applicable legal case recommendation, as shown in fig. 5, and comprises the following steps:
the feature extraction module 501 is configured to perform feature extraction on text information of a target legal case to obtain a case feature of the target legal case;
the knowledge map matching module 502 is configured to match the case characteristics of the target legal case with a pre-established legal case applicable legal case knowledge map, so as to obtain a plurality of legal case applicable legal cases to be matched; the legal case applicable legal condition knowledge graph comprises different legal case applicable legal conditions and corresponding legal case situation characteristics;
a similarity calculating module 503, configured to calculate similarity between the case characteristics of the target legal case and the legal case characteristics corresponding to each legal case applicable rule to be matched;
the notification module 504 is configured to take the applicable legal rules of the legal case to be matched, which have similarity exceeding a preset value, as the applicable legal rules of the target legal case, and send out notification information carrying the applicable legal rules of the target legal case.
In one embodiment, the feature extraction module is specifically configured to:
based on a deep learning SKE algorithm, text extraction and text classification are carried out on the text information of the target legal cases, so that the text information of the target legal cases in different categories is obtained;
and extracting the characteristics of the text information of the target legal cases in different categories to obtain the case characteristics of the target legal cases.
In one embodiment, further comprising:
the knowledge graph building module is used for:
establishing a legal case applicable legal rule knowledge graph according to the legal case applicable legal rule historical data; the legal case applicable legal provision history data comprises: legal case applicable legal rules corresponding to the case characteristics of different historical legal cases.
In one embodiment, the similarity calculation module is specifically configured to:
inputting the case characteristics of the target legal case and the legal case characteristics corresponding to the legal case applicable legal case to be matched into a pre-trained GPT model aiming at each legal case applicable legal case to be matched, so as to obtain the similarity between the case characteristics of the target legal case and the legal case characteristics corresponding to each legal case applicable legal case to be matched; the GPT model includes a multi-head attention structure, a layer normalization structure, and a fully connected layer structure.
In one embodiment, further comprising:
the neural network model building module is used for:
inputting the case characteristics of the target legal case into a legal case applicable legal rule recognition model to obtain a neural network judgment result of the target legal case applicable legal rule; the legal case applicable legal condition recognition model is obtained by training a Transformer neural network model through legal case applicable legal condition historical data; the legal case applicable legal provision history data comprises: legal case applicable legal rules corresponding to the case characteristics of different historical legal cases;
the notification module is specifically configured to:
matching the applicable legal rules of the target legal cases with the neural network judgment results of the applicable legal rules of the target legal cases;
after successful matching, the legal case applicable law of the to-be-matched, the similarity of which exceeds a preset value, is used as the applicable law of the target legal case.
The embodiment of the invention provides a computer device for realizing all or part of contents in the applicable legal condition recommendation method of the legal condition, which specifically comprises the following contents:
a processor (processor), a memory (memory), a communication interface (Communications Interface), and a bus; the processor, the memory and the communication interface complete communication with each other through the bus; the communication interface is used for realizing information transmission between related devices; the computer device may be a desktop computer, a tablet computer, a mobile terminal, or the like, and the embodiment is not limited thereto. In this embodiment, the computer device may be implemented with reference to an embodiment of the method for implementing legal case applicable legal case recommendation and an embodiment of the apparatus for implementing legal case applicable legal case recommendation, and the contents thereof are incorporated herein and are not repeated here.
Fig. 6 is a schematic block diagram of a system configuration of a computer device 1000 according to an embodiment of the present application. As shown in fig. 6, the computer device 1000 may include a central processor 1001 and a memory 1002; the memory 1002 is coupled to the central processor 1001. Notably, this fig. 6 is exemplary; other types of structures may also be used in addition to or in place of the structures to implement telecommunications functions or other functions.
In one embodiment, applicable legal case recommendation functionality may be integrated into the central processor 1001.
The central processor 1001 may be configured to control, among other things, the following:
extracting characteristics of the text information of the target legal case to obtain the case characteristics of the target legal case;
matching the case characteristics of the target legal case with a pre-established legal case applicable law knowledge graph to obtain a plurality of legal case applicable law to be matched; the legal case applicable legal condition knowledge graph comprises different legal case applicable legal conditions and corresponding legal case situation characteristics;
calculating the case characteristics of the target legal case and the similarity between the case characteristics of the legal case corresponding to each legal case applicable rule to be matched;
and taking the applicable legal rules of the legal cases to be matched, which have the similarity exceeding a preset value, as the applicable legal rules of the target legal cases, and sending out notification information carrying the applicable legal rules of the target legal cases.
In another embodiment, the applicable legal rules recommending device of the legal case may be configured separately from the central processing unit 1001, for example, the applicable legal rules recommending device of the legal case may be configured as a chip connected to the central processing unit 1001, and the applicable legal rules recommending function of the legal case is implemented under the control of the central processing unit.
As shown in fig. 6, the computer device 1000 may further include: a communication module 1003, an input unit 1004, an audio processor 1005, a display 1006, a power supply 1007. It is noted that the computer device 1000 need not include all of the components shown in FIG. 6; in addition, the computer device 1000 may further include components not shown in fig. 6, to which reference is made to the prior art.
As shown in fig. 6, the central processor 1001, sometimes also referred to as a controller or operational control, may include a microprocessor or other processor device and/or logic device, and the central processor 1001 receives input and controls the operation of the various components of the computer device 1000.
The memory 1002 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information about failure may be stored, and a program for executing the information may be stored. And the central processor 1001 can execute the program stored in the memory 1002 to realize information storage or processing, and the like.
The input unit 1004 provides input to the central processor 1001. The input unit 1004 is, for example, a key or a touch input device. The power supply 1007 is used to provide power to the computer device 1000. The display 1006 is used for displaying display objects such as images and characters. The display may be, for example, but not limited to, an LCD display.
The memory 1002 may be a solid state memory such as Read Only Memory (ROM), random Access Memory (RAM), SIM card, and the like. But also a memory which holds information even when powered down, can be selectively erased and provided with further data, an example of which is sometimes referred to as EPROM or the like. Memory 1002 may also be some other type of device. Memory 1002 includes a buffer memory 1021 (sometimes referred to as a buffer). The memory 1002 may include an application/function storage 1022, the application/function storage 1022 for storing application programs and function programs or for executing a flow of operations of the computer apparatus 1000 by the central processor 1001.
The memory 1002 may also include a data store 1023, the data store 1023 for storing data such as contacts, digital data, pictures, sounds, and/or any other data used by a computer device. The driver store 1024 of the memory 1002 can include various drivers for the computer device for communication functions and/or for performing other functions of the computer device (e.g., messaging applications, address book applications, etc.).
The communication module 1003 is a transmitter/receiver 1003 that transmits and receives signals via an antenna 1008. A communication module (transmitter/receiver) 1003 is coupled to the central processor 1001 to provide an input signal and receive an output signal, which may be the same as in the case of a conventional mobile communication terminal.
Based on different communication technologies, a plurality of communication modules 1003, such as a cellular network module, a bluetooth module, and/or a wireless lan module, etc., may be provided in the same computer device. The communication module (transmitter/receiver) 1003 is also coupled to a speaker 1009 and a microphone 1010 via an audio processor 1005 to provide audio output via the speaker 1009 and to receive audio input from the microphone 1010 to implement usual telecommunications functionality. The audio processor 1005 may include any suitable buffers, decoders, amplifiers and so forth. In addition, an audio processor 1005 is also coupled to the central processor 1001 so that sound can be recorded locally through the microphone 1010 and so that sound stored locally can be played through the speaker 1009.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the applicable legal case recommendation method when being executed by a processor.
The embodiment of the invention also provides a computer program product, which comprises a computer program, and the computer program realizes the applicable legal case recommendation method when being executed by a processor.
In the embodiment of the invention, the text information of the target legal case is subjected to feature extraction to obtain the case condition features of the target legal case; matching the case characteristics of the target legal case with a pre-established legal case applicable law knowledge graph to obtain a plurality of legal case applicable law to be matched; the legal case applicable legal condition knowledge graph comprises different legal case applicable legal conditions and corresponding legal case situation characteristics; calculating the case characteristics of the target legal case and the similarity between the case characteristics of the legal case corresponding to each legal case applicable rule to be matched; the applicable legal case law of the to-be-matched legal case with the similarity exceeding the preset value is used as the applicable legal case of the target legal case, and notification information carrying the applicable legal case of the target legal case is sent out, so that the purposes of automatically pushing the applicable legal case of the target legal case by text information of the target legal case through establishing a knowledge graph and calculating the similarity are achieved, the problem that only keyword retrieval law is supported in the prior art to easily cause mismatching of a case description text and a corresponding rule is solved, efficiency and accuracy of recommending the applicable legal case are improved, legal rule reference can be provided for law and law interpretation, and intelligent auxiliary support is provided for intelligent trial.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. The applicable legal case recommendation method is characterized by comprising the following steps of:
extracting characteristics of the text information of the target legal case to obtain the case characteristics of the target legal case;
matching the case characteristics of the target legal case with a pre-established legal case applicable law knowledge graph to obtain a plurality of legal case applicable law to be matched; the legal case applicable legal condition knowledge graph comprises different legal case applicable legal conditions and corresponding legal case situation characteristics;
calculating the case characteristics of the target legal case and the similarity between the case characteristics of the legal case corresponding to each legal case applicable rule to be matched;
and taking the applicable legal rules of the legal cases to be matched, which have the similarity exceeding a preset value, as the applicable legal rules of the target legal cases, and sending out notification information carrying the applicable legal rules of the target legal cases.
2. The method of claim 1, wherein extracting features from the text information of the target legal case to obtain the case features of the target legal case comprises:
based on a deep learning SKE algorithm, text extraction and text classification are carried out on the text information of the target legal cases, so that the text information of the target legal cases in different categories is obtained;
and extracting the characteristics of the text information of the target legal cases in different categories to obtain the case characteristics of the target legal cases.
3. The method as recited in claim 1, further comprising:
establishing a legal case applicable legal rule knowledge graph according to the legal case applicable legal rule historical data; the legal case applicable legal provision history data comprises: legal case applicable legal rules corresponding to the case characteristics of different historical legal cases.
4. The method of claim 1, wherein calculating similarities between case characteristics of the target legal case and case characteristics of legal cases corresponding to each legal case applicable legal case to be matched comprises:
inputting the case characteristics of the target legal case and the legal case characteristics corresponding to the legal case applicable legal case to be matched into a pre-trained GPT model aiming at each legal case applicable legal case to be matched, so as to obtain the similarity between the case characteristics of the target legal case and the legal case characteristics corresponding to each legal case applicable legal case to be matched; the GPT model includes a multi-head attention structure, a layer normalization structure, and a fully connected layer structure.
5. The method as recited in claim 1, further comprising:
inputting the case characteristics of the target legal case into a legal case applicable legal rule recognition model to obtain a neural network judgment result of the target legal case applicable legal rule; the legal case applicable legal condition recognition model is obtained by training a Transformer neural network model through legal case applicable legal condition historical data; the legal case applicable legal provision history data comprises: legal case applicable legal rules corresponding to the case characteristics of different historical legal cases;
the legal case applicable law of the to-be-matched, the similarity of which exceeds a preset value, is used as the applicable law of the target legal case, and the method comprises the following steps:
matching the applicable legal rules of the target legal cases with the neural network judgment results of the applicable legal rules of the target legal cases;
after successful matching, the legal case applicable law of the to-be-matched, the similarity of which exceeds a preset value, is used as the applicable law of the target legal case.
6. An applicable legal case recommendation device, comprising:
the feature extraction module is used for extracting features of the text information of the target legal case to obtain the case characteristics of the target legal case;
the knowledge map matching module is used for matching the case characteristics of the target legal case with a pre-established legal case applicable law knowledge map to obtain a plurality of legal case applicable law to be matched; the legal case applicable legal condition knowledge graph comprises different legal case applicable legal conditions and corresponding legal case situation characteristics;
the similarity calculation module is used for calculating the similarity between the case characteristics of the target legal case and the legal case characteristics corresponding to each legal case applicable rule to be matched;
and the notification module is used for taking the applicable legal rules of the legal cases to be matched, which have the similarity exceeding a preset value, as the applicable legal rules of the target legal cases and sending notification information carrying the applicable legal rules of the target legal cases.
7. The apparatus of claim 6, wherein the feature extraction module is specifically configured to:
based on a deep learning SKE algorithm, text extraction and text classification are carried out on the text information of the target legal cases, so that the text information of the target legal cases in different categories is obtained;
and extracting the characteristics of the text information of the target legal cases in different categories to obtain the case characteristics of the target legal cases.
8. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 5 when executing the computer program.
9. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program which, when executed by a processor, implements the method of any of claims 1 to 5.
10. A computer program product, characterized in that the computer program product comprises a computer program which, when executed by a processor, implements the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211724843.7A CN116304078A (en) | 2022-12-30 | 2022-12-30 | Legal case applicable legal condition recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211724843.7A CN116304078A (en) | 2022-12-30 | 2022-12-30 | Legal case applicable legal condition recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116304078A true CN116304078A (en) | 2023-06-23 |
Family
ID=86813866
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211724843.7A Pending CN116304078A (en) | 2022-12-30 | 2022-12-30 | Legal case applicable legal condition recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116304078A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117609487A (en) * | 2024-01-19 | 2024-02-27 | 武汉百智诚远科技有限公司 | Legal provision quick retrieval method and system based on artificial intelligence |
-
2022
- 2022-12-30 CN CN202211724843.7A patent/CN116304078A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117609487A (en) * | 2024-01-19 | 2024-02-27 | 武汉百智诚远科技有限公司 | Legal provision quick retrieval method and system based on artificial intelligence |
| CN117609487B (en) * | 2024-01-19 | 2024-04-09 | 武汉百智诚远科技有限公司 | Legal provision quick retrieval method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103280216B (en) | Improve the speech recognition device the relying on context robustness to environmental change | |
| CN111241237B (en) | Intelligent question-answer data processing method and device based on operation and maintenance service | |
| CN110164435A (en) | Audio recognition method, device, equipment and computer readable storage medium | |
| US11899675B2 (en) | Machine reading comprehension system for answering queries related to a document | |
| CN110930980B (en) | Acoustic recognition method and system for Chinese and English mixed voice | |
| CN110956956A (en) | Voice recognition method and device based on policy rules | |
| CN108447471A (en) | Audio recognition method and speech recognition equipment | |
| CN103970791B (en) | A kind of method, apparatus for recommending video from video library | |
| CN111428010A (en) | Man-machine intelligent question and answer method and device | |
| CN111832308B (en) | Speech recognition text consistency processing method and device | |
| CN102073704A (en) | Text classification processing method, system and equipment | |
| CN111159358A (en) | Multi-intention recognition training and using method and device | |
| CN113722438A (en) | Sentence vector generation method and device based on sentence vector model and computer equipment | |
| CN111651586B (en) | Rule template generation method, rule template generation device and rule template generation medium for text classification | |
| CN116304078A (en) | Legal case applicable legal condition recommendation method and device | |
| CN113342948A (en) | Intelligent question and answer method and device | |
| CN112632248A (en) | Question answering method, device, computer equipment and storage medium | |
| CN111178081A (en) | Semantic recognition method, server, electronic device and computer storage medium | |
| CN112734565B (en) | Fluidity coverage prediction method and device | |
| CN113011195A (en) | Recommendation system effect enhancement method and device based on pre-training language model | |
| CN112580335B (en) | Method and device for disambiguating polyphone | |
| CN113220828A (en) | Intention recognition model processing method and device, computer equipment and storage medium | |
| CN117056481A (en) | Cloud service industry dialogue help system based on large model technology and implementation method | |
| CN111143529A (en) | Method and equipment for carrying out conversation with conversation robot | |
| CN111428487A (en) | Model training method, lyric generation method, device, electronic equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |