Judicial fact finding generation method and device based on deep neural network, and medium

Abstract

The invention discloses a judicial fact finding generation method and device based on a deep neural network, and a medium. According to the method, features of court trial record text data in a dialogue form are extracted by utilizing a hierarchical sequence model, and vectorized representation of a word level, a sentence level and a dialogue level is obtained; then, the fact element classification task and the missing fact ascertaining task are taken as auxiliary tasks, and a fact ascertaining scene conforming to judicial program logic is constructed under a multi-task learning framework; finally, the feature extraction results are linked and combined, and a judicial fact finding result meeting court trial records is generated by means of an attention mechanism-based Seq2Seq model under amulti-task learning framework. According to the method, the deep sequence learning model is applied to judicial fact finding automatic generation, and compared with a common text generation algorithm, modeling and auxiliary text generation are carried out on factual key information in legal documents, factual elements in original texts are effectively reserved, and controllability and interpretability of the generation model are guaranteed.

Description

technical field [0001] The present invention relates to the field of intelligent judicial auxiliary processing, in particular to a method for extracting and maintaining the dialogue structure information and relevant fact element features of court trial transcripts, and completing the ascertainment and generation of judicial facts. Background technique [0002] Using natural language processing technology to assist in intelligent judicial auxiliary processing is a key technology with practical application significance, and it is also a key field for the application of natural language processing technology. Correspondingly, natural language processing-assisted text understanding and text generation has become a hot spot in the interdisciplinary field of computer science and law. [0003] In the traditional text generation algorithm based on deep learning, it is generally realized by using the sequence-to-sequence framework composed of encoder-decoder. The model extracts the...

AI Technical Summary

Problems solved by technology

However, this generation method ignores the distinction between the key elements in the text and other texts, and in the decoding process of generating the target text, it is easy to accumulate larger errors with the length of the decoding sequence, resulting in unsatisfactory generation results

Therefore, traditional methods are generally difficult to obtain generation results containing key information, and cannot provide reasonable explanations for the results

Images