CN113297376A - Legal case risk point identification method and system based on meta-learning - Google Patents
Legal case risk point identification method and system based on meta-learning Download PDFInfo
- Publication number
- CN113297376A CN113297376A CN202110559632.1A CN202110559632A CN113297376A CN 113297376 A CN113297376 A CN 113297376A CN 202110559632 A CN202110559632 A CN 202110559632A CN 113297376 A CN113297376 A CN 113297376A
- Authority
- CN
- China
- Prior art keywords
- meta
- legal
- legal case
- classified
- learning
- 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 54
- 239000013598 vector Substances 0.000 claims abstract description 70
- 238000000605 extraction Methods 0.000 claims abstract description 19
- 230000006698 induction Effects 0.000 claims abstract description 17
- 230000008569 process Effects 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 230000001537 neural effect Effects 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 2
- 230000009466 transformation Effects 0.000 claims description 2
- 230000002457 bidirectional effect Effects 0.000 claims 1
- 238000004590 computer program Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 238000005259 measurement Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012549 training 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
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- 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—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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Technology Law (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure provides a legal case risk point identification method and system based on meta-learning, which are used for acquiring text descriptions of legal cases to be classified; constructing a meta-learning task according to the legal case text description to be classified and the legal case text description of the known risk points; obtaining feature vectors of the legal case text descriptions to be classified and the legal case text descriptions in the meta-learning task support set according to the legal case text descriptions to be classified and the legal case text descriptions in the meta-learning task support set and a preset feature extraction model; obtaining a class representative vector of each class of risks according to the feature vectors of the text descriptions of the legal cases in the meta-learning task support set and a preset induction model; obtaining the probability of various risks of the legal cases to be classified according to the feature vectors of the text description of the legal cases to be classified and the class representative vectors of each class of risks; the method adopts the idea of meta-learning, and improves the classification precision of the risk points of the legal cases.
Description
Technical Field
The disclosure relates to the technical field of natural language processing and small sample classification, in particular to a legal case risk point identification method and system based on meta-learning.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
At present, various legal cases are continuously emerged, and the classification of case risk points is taken as a key part of the construction of an intelligent court, so that the wide attention is drawn.
The inventor finds that the risk point classification of the cases is generally carried out in a deep model training classifier mode under the traditional condition, but the overfitting phenomenon is serious under the condition that the samples are small, and the classification accuracy is influenced.
Disclosure of Invention
In order to overcome the defects of the prior art, the method and the system for identifying the risk points of the legal case based on the meta-learning are provided, the method and the system are suitable for the conditions of more types and fewer types of classification samples of the legal risk points based on the thought of the meta-learning, and the classification precision is improved; through meta-learning, the experience of processing risk point classification can be effectively learned, and efficient and accurate classification can be realized for new risk points appearing in the future.
In order to achieve the purpose, the following technical scheme is adopted in the disclosure:
the first aspect of the disclosure provides a legal case risk point identification method based on meta-learning.
A legal case risk point identification method based on meta-learning comprises the following processes:
acquiring the text description of the legal cases to be classified;
constructing a meta-learning task according to the legal case text description to be classified and the legal case text description of the known risk points;
obtaining feature vectors of the legal case text descriptions to be classified and the legal case text descriptions in the meta-learning task support set according to the legal case text descriptions to be classified and the legal case text descriptions in the meta-learning task support set and a preset feature extraction model;
obtaining a class representative vector of each class of risks according to the feature vectors of the text descriptions of the legal cases in the meta-learning task support set and a preset induction model;
and obtaining the probability of various risks of the legal cases to be classified according to the characteristic vector of the text description of the legal cases to be classified and the class representative vector of each class of risks.
A second aspect of the present disclosure provides a system for identifying risk points of legal cases based on meta-learning.
A system for identifying risk points of legal cases based on meta-learning, comprising:
a data acquisition module configured to: acquiring the text description of the legal cases to be classified;
a task construction module configured to: constructing a meta-learning task according to the legal case text description to be classified and the legal case text description of the known risk points;
a feature extraction module configured to: obtaining feature vectors of the legal case text descriptions to be classified and the legal case text descriptions in the meta-learning task support set according to the legal case text descriptions to be classified and the legal case text descriptions in the meta-learning task support set and a preset feature extraction model;
a summarization module configured to: obtaining a class representative vector of each class of risks according to the feature vectors of the text descriptions of the legal cases in the meta-learning task support set and a preset induction model;
a risk point prediction module configured to: and obtaining the probability of various risks of the legal cases to be classified according to the characteristic vector of the text description of the legal cases to be classified and the class representative vector of each class of risks.
A third aspect of the present disclosure provides a computer-readable storage medium having stored thereon a program which, when executed by a processor, implements the steps in the meta-learning based legal case risk point identification method according to the first aspect of the present disclosure.
A fourth aspect of the present disclosure provides an electronic device, including a memory, a processor, and a program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps in the method for identifying risk points of legal cases based on meta learning according to the first aspect of the present disclosure.
Compared with the prior art, the beneficial effect of this disclosure is:
1. according to the method, the system, the medium or the electronic equipment, the legal case description to be classified is input into the feature extraction model to obtain the feature vector of the legal case description to be classified and the legal case description of the known risk point, the feature vector of the legal case description of the known risk point is input into the induction module to obtain the most representative risk representative vector, and the feature vector of the legal case description to be classified and the risk representative vector are subjected to similarity measurement, so that more accurate prediction of risks existing in the classified legal cases is achieved.
2. The method, the system, the medium or the electronic equipment are suitable for the conditions of multiple types and few types of legal risk point classification samples based on the thought of meta-learning, and the classification precision is improved; through meta-learning, the experience of processing risk point classification can be effectively learned, and efficient and accurate classification can be realized for new risk points appearing in the future.
Advantages of additional aspects of the disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the disclosure.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and are not to limit the disclosure.
Fig. 1 is a schematic flowchart of a legal case risk point identification method based on meta learning according to embodiment 1 of the present disclosure.
Detailed Description
The present disclosure is further described with reference to the following drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
Example 1:
as shown in fig. 1, an embodiment 1 of the present disclosure provides a method for identifying risk points of legal cases based on meta learning, including the following processes:
s101: obtaining legal case description to be classified;
s102: constructing a meta-learning task by the legal case description to be classified and the legal case description of the known risk points;
s103, inputting the legal case description to be classified and the legal case description in the meta-learning task support set into a feature extraction model to obtain the feature vectors of the legal case description to be classified and the legal case description in the meta-learning task support set;
s104: inputting the feature vectors described by the legal cases in the meta-learning task support set into a generalization module to obtain class representative vectors of each class of risks;
s105: based on the feature vector of the legal case description to be classified and the class representative vector of each class of risks, the probability that the legal case to be classified has various risks is obtained.
In S101, obtaining the legal case description to be classified specifically includes the following processes:
obtaining legal case description to be classified;
describing the legal cases to be classified, and deleting characters and symbols without practical significance;
and converting the processed legal case description to be classified into word combinations through word segmentation.
It can be understood that the deletion of the words that have no practical meaning to the matching judicial case documents refers to: characters such as numbers, punctuation marks, virtual words without practical significance and the like are removed by text preprocessing means.
It can be understood that converting the processed legal case description to be classified into a word combination through word segmentation means: the legal case description is cut into individual words by Chinese word segmentation algorithm, and expressed as a combined sequence of words x ═ x (x) in sequence1,x2,...,xT)。
In S102, the legal case description to be classified and the legal case description construction element learning task of the known risk point specifically include the following processes:
taking the treated legal case description to be classified as a query set of a meta-learning task, sampling from the legal case description of known risk points, randomly extracting N types of risk points, and randomly extracting K different samples from each type of risk to form a support set of the meta-learning task; the two are combined to construct a meta-learning task.
In S103, the feature extraction process of the feature extraction model includes:
the two-way LSTM model performs feature extraction on the description of the legal case, uses two-way LSTM coding, and obtains an implicit vector h by splicing forward coding and reverse codingt;
Increasing the weight of words which have great influence on semantic information through an attention mechanism to obtain a feature vector described by a legal case;
further, the attention mechanism process is to obtain h through a multilayer perceptron and a tanh activation functiontThe vector of the semantic features of the sentence is obtained after weighting.
In S104, the induction process of the induction module includes:
obtaining a sample feature vector of each type of the support set;
and (3) carrying out iterative induction on all sample feature vectors in each class in the support set for a certain number of times through a dynamic routing algorithm to obtain class feature representation.
In particular, assume eijS denotes the jth vector supporting class i in the set S, ciClass representation vector representing class i obtained by calculation, and in a generalization module, all samples in a support set share a transformation matrix WSAnd bias bsTransforming to capture key semantic information between the low-level features and the high-level features, and expressing the prediction value of each vector in the support set as:
wherein, square represents a nonlinear squeezing function, and the vector direction is unchanged and the vector magnitude is compressed through the square function.
Further, in the dynamic routing process, a link parameter b is setiIs dynamically modified during routing, is uniformly set to 0 in the first iteration, and b is set toiD is obtained by one-time softmaxi。
All sample prediction vectors in class i in the support set S will be supportedAt a weight diThe weighted sum is obtained to obtain the candidate vector of each classWill be provided withObtaining a class representative vector c through a square functioni。
Further, by ciTo update the link parameter biThe update function is represented as:
in S105, the classification process includes:
the vector e in the query set Q obtained by the feature extraction moduleqAnd class-feature representation in the support set obtained in the induction module ciInputting a network of neural tensors to measure eqAnd ciThe similarity between them;
inputting the result obtained by the neural tensor network into a full-connection network, and obtaining a query set vector e through a sigmoid activation functionqAnd a class vector c supporting class i in the setiThe relevance score of (a).
Most of the existing legal case risk point identification methods select a depth frame to train a classifier on data of known risk points, and input the legal case description to be classified into the classifier to obtain a classification result; in reality, however, the case samples of each risk point are often small, and the classification method is not enough to train an accurate classifier. In the embodiment, the legal case risk point identification method based on meta-learning constructs a large number of tasks by repeatedly sampling cases to train the feature extraction module, obtains the most representative class representative vector of each class of risk through the induction module, identifies the risk points of the legal cases through a measurement mode, and can more accurately obtain the classification result.
The embodiment adopts the thought of meta-learning, is suitable for the current situation that the legal risk point classification samples are various in types and few in categories, and the meta-learning can effectively learn the experience of processing the risk point classification, and can efficiently classify new risk points appearing in the future.
Table 1 is a simulation experiment of the disclosed method, which is measured with classification accuracy. The data set used by the task is a legal case risk point data set constructed by TIME laboratories of software college of Shandong university, the data set comprises about 200 different risk points, and positive and negative samples of each risk point are about 6 respectively.
Compared with the prior art, the method adopts the meta-learning method, so that the overfitting phenomenon is greatly reduced, and the accuracy of identifying the risk points of the legal case is improved.
Table 1: accuracy comparison of the present disclosure with other algorithms
Example 2:
the embodiment 2 of the present disclosure provides a legal case risk point identification system based on meta-learning, including:
a data acquisition module configured to: acquiring the text description of the legal cases to be classified;
a task construction module configured to: constructing a meta-learning task according to the legal case text description to be classified and the legal case text description of the known risk points;
a feature extraction module configured to: obtaining feature vectors of the legal case text descriptions to be classified and the legal case text descriptions in the meta-learning task support set according to the legal case text descriptions to be classified and the legal case text descriptions in the meta-learning task support set and a preset feature extraction model;
a summarization module configured to: obtaining a class representative vector of each class of risks according to the feature vectors of the text descriptions of the legal cases in the meta-learning task support set and a preset induction model;
a risk point prediction module configured to: and obtaining the probability of various risks of the legal cases to be classified according to the characteristic vector of the text description of the legal cases to be classified and the class representative vector of each class of risks.
It should be noted here that the above-mentioned acquisition module, task construction module, feature extraction module, induction module and risk point prediction correspond to steps S101 to S105 in the first embodiment, and the above-mentioned modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the contents disclosed in the first embodiment. It should be noted that the modules described above as part of a system may be implemented in a computer system such as a set of computer-executable instructions.
In the foregoing embodiments, the descriptions of the embodiments have different emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
The proposed system can be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the above-described modules is merely a logical functional division, and in actual implementation, there may be other divisions, for example, multiple modules may be combined or integrated into another system, or some features may be omitted, or not executed.
Example 3:
embodiment 3 of the present disclosure provides a computer-readable storage medium on which a program is stored, which when executed by a processor, implements the steps in the method for identifying a risk point of a legal case based on meta learning according to embodiment 1 of the present disclosure.
Example 4:
the embodiment 4 of the present disclosure provides an electronic device, which includes a memory, a processor, and a program stored in the memory and executable on the processor, and when the processor executes the program, the steps in the method for identifying risk points of legal cases based on meta learning according to embodiment 1 of the present disclosure are implemented.
As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure 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, optical storage, and the like) having computer-usable program code embodied therein.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams 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.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Claims (10)
1. A legal case risk point identification method based on meta-learning is characterized in that: the method comprises the following steps:
acquiring the text description of the legal cases to be classified;
constructing a meta-learning task according to the legal case text description to be classified and the legal case text description of the known risk points;
obtaining feature vectors of the legal case text descriptions to be classified and the legal case text descriptions in the meta-learning task support set according to the legal case text descriptions to be classified and the legal case text descriptions in the meta-learning task support set and a preset feature extraction model;
obtaining a class representative vector of each class of risks according to the feature vectors of the text descriptions of the legal cases in the meta-learning task support set and a preset induction model;
and obtaining the probability of various risks of the legal cases to be classified according to the characteristic vector of the text description of the legal cases to be classified and the class representative vector of each class of risks.
2. The meta-learning based legal case risk point identification method of claim 1, wherein:
the method for acquiring the legal case text description to be classified comprises the following steps:
acquiring the text description of the legal cases to be classified;
describing the legal case characters to be classified, and deleting characters and symbols without practical significance;
and converting the processed legal case text description to be classified into word combinations through word segmentation.
3. The meta-learning based legal case risk point identification method of claim 1, wherein:
constructing a meta-learning task according to the legal case textual description to be classified and the legal case textual descriptions of the known risk points, comprising the following processes:
and taking the processed legal case text description to be classified as a query set of the meta-learning task, sampling from the legal case description of the known risk points, randomly extracting N types of risk points, randomly extracting K different samples from each type of risk to form a support set of the meta-learning task, and combining the two to construct the meta-learning task.
4. The meta-learning based legal case risk point identification method of claim 1, wherein:
a feature extraction process for a feature extraction model, comprising:
using bidirectional LSTM coding, and splicing forward coding and backward coding to obtain an implicit vector;
through an attention mechanism and by combining the obtained implicit vectors, the weight of the words with large influence on semantic information is increased, and the feature vectors described by the legal case are obtained.
5. The meta-learning based legal case risk point identification method of claim 1, wherein:
the induction process of the preset induction model comprises the following processes:
obtaining a sample feature vector of each type of the support set;
and (4) carrying out iterative induction on all sample feature vectors in each class in the support set through a dynamic routing algorithm for preset times to obtain class representative vectors.
6. The meta-learning based legal case risk point identification method of claim 5, wherein:
obtaining a predicted value of each vector in the support set class i according to the transformation matrix, the offset and a preset squeezing function;
linking parameter b in dynamic routing processiIs dynamically modified during routing, biObtaining the weight d after one time of softmaxi;
All sample prediction vectors in class i in the support set are weighted by diAnd (4) calculating the weighted sum to obtain a candidate vector of each class, and enabling the candidates to be adjacent to each other to obtain a class representative vector through a square function.
7. The meta-learning based legal case risk point identification method of claim 1, wherein:
inputting the characteristic vector of the legal case text description in the meta-learning task support set and the class representative vector in the support set obtained in the induction model into a neural tensor network;
and inputting the result obtained by the neural tensor network into a full-connection network, and obtaining a correlation score between the two vectors through a sigmoid activation function.
8. A legal case risk point identification system based on meta-learning is characterized in that: the method comprises the following steps:
a data acquisition module configured to: acquiring the text description of the legal cases to be classified;
a task construction module configured to: constructing a meta-learning task according to the legal case text description to be classified and the legal case text description of the known risk points;
a feature extraction module configured to: obtaining feature vectors of the legal case text descriptions to be classified and the legal case text descriptions in the meta-learning task support set according to the legal case text descriptions to be classified and the legal case text descriptions in the meta-learning task support set and a preset feature extraction model;
a summarization module configured to: obtaining a class representative vector of each class of risks according to the feature vectors of the text descriptions of the legal cases in the meta-learning task support set and a preset induction model;
a risk point prediction module configured to: and obtaining the probability of various risks of the legal cases to be classified according to the characteristic vector of the text description of the legal cases to be classified and the class representative vector of each class of risks.
9. A computer-readable storage medium, on which a program is stored, which program, when being executed by a processor, carries out the steps of the meta learning based legal case risk point identification method according to any one of claims 1-7.
10. An electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor implements the steps of the meta learning based legal case risk point identification method of any one of claims 1-7 when executing the program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110559632.1A CN113297376A (en) | 2021-05-21 | 2021-05-21 | Legal case risk point identification method and system based on meta-learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110559632.1A CN113297376A (en) | 2021-05-21 | 2021-05-21 | Legal case risk point identification method and system based on meta-learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113297376A true CN113297376A (en) | 2021-08-24 |
Family
ID=77323723
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110559632.1A Pending CN113297376A (en) | 2021-05-21 | 2021-05-21 | Legal case risk point identification method and system based on meta-learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113297376A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116663877A (en) * | 2023-05-31 | 2023-08-29 | 中咨海外咨询有限公司 | Whole process engineering consultation project risk management method |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109783604A (en) * | 2018-12-14 | 2019-05-21 | 平安科技(深圳)有限公司 | Information extracting method, device and computer equipment based on a small amount of sample |
CN111737552A (en) * | 2020-06-04 | 2020-10-02 | 中国科学院自动化研究所 | Method, device and equipment for extracting training information model and acquiring knowledge graph |
-
2021
- 2021-05-21 CN CN202110559632.1A patent/CN113297376A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109783604A (en) * | 2018-12-14 | 2019-05-21 | 平安科技(深圳)有限公司 | Information extracting method, device and computer equipment based on a small amount of sample |
CN111737552A (en) * | 2020-06-04 | 2020-10-02 | 中国科学院自动化研究所 | Method, device and equipment for extracting training information model and acquiring knowledge graph |
Non-Patent Citations (2)
Title |
---|
徐彤彤: ""基于双向长效注意力特征表达的少样本文本分类模型研究"", 《数据分析与知识发现》 * |
马欣睿: ""基于基元特征分析的图像识别算法研究"", 《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116663877A (en) * | 2023-05-31 | 2023-08-29 | 中咨海外咨询有限公司 | Whole process engineering consultation project risk management method |
CN116663877B (en) * | 2023-05-31 | 2024-02-02 | 中咨海外咨询有限公司 | Whole process engineering consultation project risk management method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108170736B (en) | Document rapid scanning qualitative method based on cyclic attention mechanism | |
CN109766277B (en) | Software fault diagnosis method based on transfer learning and DNN | |
CN105868184B (en) | A kind of Chinese personal name recognition method based on Recognition with Recurrent Neural Network | |
CN106445919A (en) | Sentiment classifying method and device | |
CN112711953A (en) | Text multi-label classification method and system based on attention mechanism and GCN | |
CN113344206A (en) | Knowledge distillation method, device and equipment integrating channel and relation feature learning | |
CN113010683B (en) | Entity relationship identification method and system based on improved graph attention network | |
CN112052684A (en) | Named entity identification method, device, equipment and storage medium for power metering | |
CN110347791B (en) | Topic recommendation method based on multi-label classification convolutional neural network | |
Yan et al. | Data augmentation for deep learning of judgment documents | |
CN112434164B (en) | Network public opinion analysis method and system taking topic discovery and emotion analysis into consideration | |
CN113220865B (en) | Text similar vocabulary retrieval method, system, medium and electronic equipment | |
CN113128233B (en) | Construction method and system of mental disease knowledge map | |
CN112667782A (en) | Text classification method, device, equipment and storage medium | |
CN115952292B (en) | Multi-label classification method, apparatus and computer readable medium | |
CN114416979A (en) | Text query method, text query equipment and storage medium | |
CN111639185B (en) | Relation information extraction method, device, electronic equipment and readable storage medium | |
CN111709225B (en) | Event causal relationship discriminating method, device and computer readable storage medium | |
CN112100377A (en) | Text classification method and device, computer equipment and storage medium | |
CN114048729A (en) | Medical document evaluation method, electronic device, storage medium, and program product | |
CN117501283A (en) | Text-to-question model system | |
CN114528835A (en) | Semi-supervised specialized term extraction method, medium and equipment based on interval discrimination | |
CN115659947A (en) | Multi-item selection answering method and system based on machine reading understanding and text summarization | |
CN114881173A (en) | Resume classification method and device based on self-attention mechanism | |
CN114818718A (en) | Contract text recognition method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210824 |