Case push method, device, electronic equipment and medium based on artificial intelligence

Abstract

The invention relates to artificial intelligence, and provides an artificial intelligence-based case push method, device, electronic equipment and media. This method can extract cases to be processed and preliminary screening cases, obtain and preprocess case texts, obtain and analyze target texts, obtain target features and determine feature vectors, semantically analyze target texts, obtain semantic vectors to be processed, obtain and pre-screen cases Calculate the similarity between each word vector and the feature vector for the corresponding word vector and the primary screening semantic vector to obtain the first similarity, and calculate the similarity between each primary screening semantic vector and the semantic vector to be processed to obtain the second similarity , determine the weights of the first similarity and the second similarity, calculate the weighted sum of the first similarity and the second similarity, obtain the score, push the preliminary screening case according to the score, and push the case accurately. In addition, the present invention also relates to block chain technology, and the multiple word vectors and the multiple preliminary screening semantic vectors are stored in the block chain.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to an artificial intelligence-based case push method, device, electronic equipment and media. Background technique [0002] In order to facilitate the judge or the person in charge of the case to have a more in-depth and systematic understanding of each case, a similar case recommendation method is produced, that is, through the pre-processed documents of the pending case and the dispute focus information summarized by the user, from the past judgment documents Find the judgment documents that are highly relevant to the pending case and recommend them to the user as a reference for case judgment. [0003] The inventors of the present application found in the research that the current similar case recommendation method usually uses algorithms such as TF-IDF and BM25 to calculate the text similarity between the preceding documents and the past judgment document...

AI Technical Summary

Problems solved by technology

[0003] The inventors of the present application found in the research that the current similar case recommendation method usually uses algorithms such as TF-IDF and BM25 to calculate the text similarity between the preceding documents and the past judgment documents. However, because such algorithms set the weight of words to Because it is anti-correlated with word frequency, the word weight of this type of algorithm is not suitable for cases in legal scenarios. At the same time, through simple weighted matching of keywords, the semantic understanding of the case to be processed is lost, resulting in the inability to accurately determine the relationship between the case to be processed and Similarity of past judgment documents

Images