Category prediction method and device based on theme information

Abstract

The invention provides a category prediction method and device based on theme information. The method is applicable to criminal name prediction of legal documents and includes, on the basis of the hierarchical neural network, describing the overall association between each vocabulary in each sentence and the case text according to the theme information of the case description text, determining theimportance of each sentence through the theme information, performing weighted summation to obtain semantic vector representation of the case description text, and inputting the semantic vector representation into a classifier to predict a criminal name corresponding to the case. According to the method, key words and sentences in the case description text are mined by using theme information, and more effective semantic vector representation of the case description text can be obtained, so that a better effect is achieved on low-frequency criminal name prediction.

Description

technical field [0001] The invention belongs to the technical field of text classification, in particular to a category prediction method and device based on subject information. Background technique [0002] In recent years, the informatization construction of courts has been continuously improved. As of December 2018, China Judgment Documents Network has collected and published more than 59 million judgment documents. The use of artificial intelligence technology to analyze, summarize and utilize these judicial big data has become a hot research topic topic. [0003] Charge prediction is to predict reasonable charges based on the description of the case in the judgment document, which can be used for sentencing and conviction before trial, and can also be used for evaluation of trial fairness after trial, which is conducive to realizing "same case with same sentence" and ensuring fairness and justice. [0004] Crime prediction is essentially a text category prediction pro...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the shortcomings of the above-mentioned prior art, the purpose of the present invention is to provide a category prediction method and device based on topic information, which is used to describe the semantic relevance between each semantic unit in the description of the case and the whole case, and to identify important words and sentences. Solve the problems of lack of semantics and the inability to predict low-frequency crimes in the current text classification method, and improve the degree of judicial intelligence

Images