Similar case matching method based on semantic similarity

Abstract

The invention discloses a case matching method based on semantic similarity, and the method comprises the following steps: obtaining a case word vector through the training of a Word2Vec model, and automatically extracting features from training data, i.e., extracting the features as one part of the model, thereby neglecting the particularity of a case text. According to the method, the keywords of the case are automatically extracted on the basis of the case word vector, and through converting multiple examples into a single example, a plurality of keyword vectors are converted into fisher vectors of the cases to perform semantic similarity calculation, so that a common user can obtain similar cases only by inputting case description or judgment documents, and the usability of the methodis greatly enhanced.

Description

technical field [0001] The invention is a case matching method based on semantic similarity, which belongs to the field of legal artificial intelligence. Background technique [0002] With the advent of the information age, the amount of information that human beings come into contact with every day is increasing, gradually moving from the age of information scarcity to the age of information overload, how to obtain effective information from it is particularly important. At present, various legal databases have stored a large amount of electronic data. Since the database can only do simple case classification, it is time-consuming and laborious to query similar cases through the database. How to quickly and efficiently search for similar cases from a large number of legal cases is a work worth exploring. With the development of Internet technology, there are already some legal case retrieval technologies related to machine learning. These technologies will search similar c...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problem that ordinary users cannot effectively extract keywords in legal documents and traditional semantic similarity algorithms require manual definition and feature extraction, the present invention proposes a case word vector model based on Word2Vec, and automatically extracts and describes cases on this basis keywords, convert multiple examples into single examples, and convert multiple keyword vectors into fisher vectors describing the case for semantic similarity calculation. The main process includes the case word vector generation process and the semantic similarity calculation method based on the case word vector

Images