Legal reasoning proposition representation method, legal event reasoning method and electronic equipment based on the three-level theory

Abstract

The present invention provides a legal reasoning proposition representation method based on the three-level theory, a legal event reasoning method, and an electronic device, wherein the method includes: obtaining a preset legal event graph; The corresponding reasoning representation framework expresses legal propositions on the legal event graph; uses the three-level theory to express the legal propositions probabilistically. Since the path of prediction is generated based on the reasoning of the three-level theory of law, the prediction can be fully interpreted, for example, it can explain clearly the situation of the establishment of the legality proposition of the elements and the probability of supporting it, and then provide prediction and evidence support for legal decision-making .

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a representation method for legal reasoning propositions based on the three-level theory, a legal event reasoning method and electronic equipment. Background technique [0002] Reasoning is a very important and challenging task in the field of natural language processing. Its purpose is to use existing knowledge and inference techniques to make judgments on unseen input information. Machine reasoning requires heuristics and strategies, which are usually done by knowledgeable domain experts. This process is where machine reasoning becomes difficult for businesses to scale, as it requires a lot of expert human labor to accomplish the strategy. [0003] Machine reasoning works best in deterministic scenarios. That is, to determine if something is true, or if it will happen. Machine Reasoning has good applications in tasks such as common sense question answering, fact detect...

AI Technical Summary

Problems solved by technology

3. The above reasoning research is based on data observation, such as support rate, winning and losing rate, etc. There is no in-depth research on the atomicity of reasoning, and the focus is on how to let the machine learn the correlation between input and output

[0005] At present, most of the existing reasoning research mainly relies on the output results of the machine algorithm model, and the interpretation of the results is very lacking. The results that are not explained according to legal causal reasoning are difficult to be accepted and recognized.

Images