Case Recommendation Algorithm of Discipline Inspection and Supervision based on Knowledge Graph

In view of work problems in the field of disciplinary and supervision such as the large number of cases, the complexity of the content of the documents, the large workload of data compilation, and the low efficiency of conviction and sentencing, intelligent recommendation of similar cases is an important measure to alleviate this situation. In order to improve the accuracy and interpretability of similar case recommendation, based on the constructed laws and regulations knowledge graph of disciplinary inspection and supervision and the disciplinary case dataset, an intelligent recommendation algorithm for similar cases that integrates the characteristics of the legal knowledge graph of disciplinary inspection and supervision is proposed. The method constructs a keyword dictionary of legal elements that map the keywords in the case text with the entities in the knowledge graph, and merges the knowledge features of the matched legal entities with the feature vectors of the original case text so that enhances the representation of legal knowledge characteristics corresponding to disciplinary. Experiments with several machine learning methods and deep learning methods show that the proposed method has a certain improvement in F-score.