Cyber-safety act case intelligent studying and judging method based on information extraction

Abstract

The invention discloses a cyber-safety act case intelligent studying and judging method based on information extraction. The method comprises the following steps: (1) knowledge map construction: constructing a cyber-safety act knowledge map from three aspects of event concepts, event entities and legal provision; (2) case information extraction: extracting illegal events, illegal subjects, illegalobjects and other event entities from the network security method case text, and performing event concept linking in a network security method knowledge map; and (3) legal provision retrieval: integrating the structured retrieval based on the knowledge graph and the unstructured retrieval based on semantic matching to obtain legal provisions which can be used for studying and judging the cyber-safety act case. According to the method, the cyber-safety act case is understood based on information extraction, so that the method can more accurately obtain the structured information of the case, and the knowledge graph is adopted to represent the related knowledge of the cyber-safety act, so that the method can more accurately make study and judgment on the case.

Description

technical field [0001] The invention relates to data mining and knowledge graph technology, and in particular relates to an intelligent research and judgment method for legal cases. Background technique [0002] Judgment of legal cases is a very serious matter, so the current intelligent research and judgment system for legal cases basically only provides judgment assistance, rather than giving final judgments. The main ways that the intelligent research and judgment system of legal cases provides judgment assistance include: recommendation of similar cases, prediction of sentencing, matching of legal provisions, etc. Among them, the matching of legal provisions can find the legal provisions that best match the legal case from a large number of legal provisions, and has the most direct guiding value for the judgment of legal cases. [0003] Existing legal clause matching methods are mainly based on semantic analysis technology, using keyword extraction, word vector, sentenc...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the shortcomings of the existing matching methods of legal provisions that cannot be applied to the situation of insufficient training samples and poor matching performance, a method for intelligent research and judgment of network security law cases based on information extraction is invented, which is based on information extraction. Understanding legal cases, so that the method can obtain the structured information of the case more accurately, and use the knowledge graph to represent the relevant knowledge of network security law, so that the method can make more accurate research and judgment on the case

Images