A method and device for realizing element identification in judicial documents

Abstract

The embodiment of the present application discloses a method and a device for realizing element identification in a judicial document. Specifically, the judicial document to be identified is first subjected to sentence-by-sentence processing, a plurality of sentences delineated by the judicial document to be identified are obtained, and at the same time, the sentence to be identified is obtained. Identify the causes of action included in judicial documents. Then, the text features of each sentence are extracted, and the text features of each sentence are input into the element recognition model corresponding to the pre-generated case, so as to obtain the first element label corresponding to each sentence. Because the identification method provided by the embodiment of the present application can fully learn the text features of the second target sentence, and is no longer limited by fixed sentences and complex sentence patterns, it can be applied to judicial documents with complex semantics. Moreover, the pre-trained element recognition model is generated by training sentences as a unit, so that the element label corresponding to each sentence in the judicial document can be obtained, and the accuracy of element recognition can be improved.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular to a method and device for realizing element identification in judicial documents. Background technique [0002] In the judicial field, various types of judicial documents are usually involved, such as judgments and rulings, and the content of such judicial documents is usually relatively long. For some complex cases, it takes a lot of energy and time for court workers to quickly capture key information points of the case from judicial documents, which brings great work pressure to court workers. [0003] In the prior art, in order to facilitate court workers to quickly obtain element information from judicial documents, some judicial documents are manually sampled, keywords are extracted from the judicial documents, and then the element information is identified from the judicial documents by the keyword method. However, this method requires manual op...

AI Technical Summary

Problems solved by technology

However, this method requires manual operations such as viewing, recording, and calculation, and it is difficult to achieve large-scale statistics. There are usually a large number of colloquial expressions of the parties in judicial documents, and the method of identifying elements through keywords cannot adapt to complex semantics. documents, resulting in inaccurate identification of elements in judicial documents

Images