A multi-user case retrieval system based on multi-dimensional semantic joint modeling

Abstract

The present invention relates to a multi-user case retrieval system based on multi-dimensional semantic joint modeling, including a knowledge building module: extracting information from existing judgment documents, building a judgment document database, and generating a judgment document portrait database and case-participant portrait database ;Element identification module: use the element feature extraction model to extract the element features of the text provided by the user, and use it to extract the user character features of the consulting user; matching query module: aim at the element features extracted in the element identification module and propose the user character features Query and match in the portrait database of referee documents and the portrait database of case participants generated by the knowledge building module respectively. The technical solution provided by the present invention can be applied to the retrieval needs of ordinary people for legal cases, and to a certain extent, satisfies the requirements of retrieval accuracy, and improves whether lawyers or ordinary people have corresponding similar judgment documents when searching for similar cases or searching according to their own circumstances. search accuracy.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a multi-user case retrieval system based on multi-dimensional semantic joint modeling. Background technique [0002] With the advent of the information age, the channels for people to obtain information have become more extensive, and at the same time, the requirements for the quality of the obtained information have also been raised, especially in the field of legal case retrieval. [0003] At present, when people encounter legal disputes, they tend to search for relevant cases on the Internet first, and check the judgments. However, most of the case retrieval systems on the market are based on keyword retrieval methods, which cannot fully capture the main target of users' attention; Secondly, most case retrieval systems are aimed at users with legal expertise, and ordinary people cannot relate to these retrieval systems well; even retrieval systems that involve specific...

AI Technical Summary

Problems solved by technology

[0003] At present, when people encounter legal disputes, they tend to go to the Internet to find relevant cases and check the judgments. However, most of the case retrieval systems on the market are based on keyword retrieval methods, which cannot fully capture the main target of users' attention; Secondly, most case retrieval systems are aimed at users with legal expertise, and ordinary people cannot relate to these retrieval systems well; even retrieval systems that involve specific semantic analysis can only capture shallow semantics and cannot mine The user's deep information, so the retrieval accuracy of this type of method is low

Images