Law reasoning proposition representation method based on three-level theory, law event reasoning method and electronic equipment

Abstract

The invention provides a legal reasoning proposition representation method based on a three-level theory, a legal event reasoning method and electronic equipment. The method comprises steps of obtaining a preset legal event atlas; based on knowledge types in the legal event graph, utilizing an inference representation framework corresponding to the knowledge types to carry out legal proposition representation on the legal event graph; and performing probabilistic representation on the legal proposition by using a three-level theory. As the predicted path is generated based on legal three-leveltheory reasoning, the prediction can have sufficient interpretability, for example, the condition that a legal proposition is established and the probability of supporting the legal proposition can be explained clearly, and then prediction and evidence support are provided for legal decisions.

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