Determination and punishment recommendation method based on legal knowledge graph and related equipment

Abstract

The invention provides a determination and punishment recommendation method based on a legal knowledge graph and related equipment. The method comprises the following steps: in response to a received text description of an illegal case, based on an illegal behavior label tree, performing multi-label classification on the text description by using a multi-label attention mechanism of a deep learning algorithm to predict an illegal behavior category label corresponding to the illegal case; performing matching and reasoning calculation on the basis of a punishment regulation knowledge graph according to the illegal behavior category label so as to determine punishment clause information and an illegal property label corresponding to the illegal case; and outputting the punishment clause information and the illegal property label as a recommendation determination result of the illegal case. According to the method provided by the invention, legal information is automatically extracted from existing related files and cases, a set of knowledge graphs of related fields is established, and a relatively reasonable judicial decision is given based on the graphs, so that assistance is provided for judicial agencies to judge cases.

Description

technical field [0001] The present disclosure relates to the technical field of knowledge graphs, in particular to a qualitative measurement recommendation method and related equipment based on legal knowledge graphs. Background technique [0002] The construction of the legal knowledge graph is an indispensable basic project for the realization of smart justice. In recent years, the judicial field has actively used advanced technologies such as big data, cloud computing, and artificial intelligence to effectively improve the efficiency of case handling, assist judicial management, and serve the masses in litigation, which has greatly promoted the acceleration of judicial modernization. The legal knowledge map is based on the application scenario, extracts the entities in the relevant fields of laws and regulations, the relationship and attributes between entities, constructs logical relationships, and forms a structured knowledge expression. Based on the legal knowledge ma...

AI Technical Summary

Problems solved by technology

Traditional legal argumentation is mainly done manually, and the quality of the argument depends entirely on the argumentation ability and knowledge reserve of the legal argumentator. As a natural person, the argumentator has limitations in value orientation, knowledge structure, etc., and the decisions he makes are often subject to restrictions. The influence of subjective factors

Images