Research On Case Discrimination Algorithm Based On Text Analysis

With the rapid development of natural language processing technology under the branch of artificial intelligence and the vigorous implementation of smart court by the State Council,intelligent judicial assistants has become a new application of natural language processing in the judicial field.Judicial assistants can alleviate the phenomenon of "more cases and fewer people" in the current judicial field,assist judges and lawyers to deal with cases to a certain extent,and relieve the pressure of judicial practitioners.Let the information construction achievements of "smart court" effectively serve the people.Currently,rich content can be mined in the judicial field,and it has a lot of valuable internal contact information.The text classification method based on word vector and deep neural network implements statistical classification of judicial documents,but it can not achieve the inherent logical interpretation of judicial cases.Although the method based on statistical learning can get satisfactory results,it can not give a convincing explanation.This is often unacceptable in the judicial field where there is rigorous logic.The purpose of this article is to analyze the judicial decision documents of criminal cases,propose and construct the semantic logic tree of judicial texts,and mine the event tree through the deep forest.Judicial documents are divided into several sub-tree fragments by sentence segmentation,and each sub-tree fragment is analyzed by dependency syntax to obtain core subject-predicate-object triples.TF-IDF algorithm is used to calculate the weights of triples,and get the core sub-event sequence,and use pruning algorithm to construct the max heap.The designed triple encoding algorithm realizes max heap vectorization of event tree,and embedded deep forest algorithm to realize classification discrimination of judicial text event tree.Finally,it can automatically distinguish between allegations in judicial cases and recommend similar documents.The model based on event tree can associate many important knowledge in judicial cases and judge cases automatically by calculating the weight of relevant knowledge,and display the relevant knowledge of the final judgment in a visual way.The experimental results show that the proposed event tree construction method combined with the deep forest algorithm can greatly improve the logical interpretation and accuracy of judicial text.