Case text-based judgment rule knowledge extraction method and system

Abstract

The invention relates to a rule atlas construction method taking case texts as knowledge sources, which mainly aims at judgment documents of criminal, civil, administrative first-examination, second-examination and reexamination cases of court trials, and according to service content characteristics of the judgment documents, judgment document making specifications, judgment document semi-structured characteristics, and composition characteristics and type characteristics of legal rules, the invention designs an information model of a judgment rule atlas, provides a method for constructing legal terms, a classification method for identifying rules and a method for identifying rule types, finally realizes construction of the judgment rule atlas, outputs an XML structured document, a computer system can effectively utilize the judgment rules existing in the case text to carry out legislation, law enforcement and judicial application, and plays a role in the fields of judgment document error correction, judgment document quality evaluation, case quality supervision, judicial case handling law article pushing and the like.

Description

technical field [0001] The invention relates to the technical field of legal knowledge engineering, in particular to a method and system for extracting knowledge of adjudication rules based on case texts. Background technique [0002] Legal rules are codes of conduct that specifically stipulate people's legal rights, legal obligations and corresponding legal consequences in a certain structural form. Legal rules are generally expressed in the form of natural language in the text of laws and regulations, but based on the requirements of legislative technology of laws and regulations, the expression of legal rules in the text of laws and regulations is general and abstract, which is equivalent to the existence of ontology. It is necessary to perform operational mapping and reasoning of legal terms in legal rules for specific scenarios, especially in the process of judicial adjudication, in order to clarify the legal reasoning process of the current case, it is necessary to fur...

AI Technical Summary

Problems solved by technology

The invention solves the problem that the data in the existing legal database is incomplete and cannot directly obtain the referee rules

[0007] Compared with the construction of the legal rule map, the above four patents have the disadvantages of: (1) the lack of a targeted solution for the natural language scene of the legal rules contained in the judgment document; (2) the generalized legal The knowledge map emphasizes the relational system of knowledge, and lacks the knowledge representation form of the core "rules" of legal field knowledge; (3) is a general method, which is applicable to the construction of simple legal knowledge maps, based on text context Short-distance semantic associations are used to form graphs, but there is no further methodological design for the construction of complex knowledge graphs; (4) graph construction for local text semantics cannot support reasoning between multiple graphs to build new Map, because it is difficult to realize the relationship between multiple legal rules to construct a secondary map; (5) There is no control mechanism for the extraction rate and accuracy rate for each type of knowledge map; (6) Feature machine learning module Using algorithms such as random forests and support vector machines to train and learn legal knowledge features does not make good use of the industry characteristics of legal knowledge features, and its training effect is difficult to achieve high-precision indicators

Images