Case recommendation method and system based on collaborative filtering recommendation algorithm

Abstract

The invention discloses a case recommendation method and system based on a collaborative filtering recommendation algorithm. The method comprises the following steps: S1, user input; s2, performing similarity calculation on the user options to discover nearest neighbors; s3, calculating and generating a recommendation data set according to the user similarity; and S4, constructing and utilizing labels to recommend similar cases to the user. The method has the beneficial effects that by applying a collaborative filtering algorithm and improving the collaborative filtering algorithm, the accuracy of recommended cases can be improved, and after a user selects an input item, irrelevance, basic relevance and very relevance can be selected according to the cases recommended by the system, so that the understanding degree of the user on the cases can be effectively improved, and the professional limitation of right protection of people is reduced; meanwhile, according to the method, an existing recommendation algorithm is improved, whether similar input exists or not can be directly judged according to options of the user, and even the same input is found, so that data matrix construction in the existing algorithm is reduced, and efficiency and recommendation accuracy are improved.

Description

technical field [0001] The present invention relates to the field of information recommendation, in particular to a method and system for case recommendation based on a collaborative filtering recommendation algorithm. Background technique [0002] With the in-depth development of law popularization work and the enhancement of people's legal awareness, more people choose to use legal weapons to protect their legitimate rights and interests when encountering various disputes. Therefore, the courts accept more and more cases. Due to the increasing number of trial cases, various law-related search websites provide search and query services for public judgment documents. Various typical cases serve as guiding cases. However, it still requires a lot of detailed reading by the staff before it is possible to draw similar judgment references, which takes a lot of time. However, the use of keyword-based matching technology to implement the recommendation of public interest litigati...

AI Technical Summary

Problems solved by technology

[0004] For the problems in related technologies, no effective solutions have been proposed yet

Images