A transfer learning and deep learning-based citizen mediation case classification system and method

Abstract

The invention relates to a transfer learning and deep learning-based citizen mediation case classification system and method. The system comprises a data acquisition module, a feature extraction module, a feature transfer module and a network training module, and is simple in structure and wide in application range; The method comprises the steps of constructing a character vector matrix, performing auxiliary data vectorization processing, performing vectorization processing on the citizen mediation data, inputting the vectorized auxiliary data into a neural network, extracting auxiliary datafeatures, migrating the extracted auxiliary data features into the vectorized citizen mediation data, and training a classification model. According to the method, all texts can be effectively converted, low-frequency words cannot be ignored, dimension reduction is obvious, the training speed is high, and follow-up online iterative optimization is facilitated; And meanwhile, the difference betweenthe people's mediation field and the auxiliary field is solved, and the individual requirements of the specific field are met.

Description

technical field [0001] The present invention relates to the technical field of data processing and classification, in particular to a system and method for classifying people's mediation cases based on transfer learning and deep learning. Background technique [0002] At present, my country mediates more than 9 million disputes every year, but there are only more than 20 types of existing disputes. With the development of economy and society, the number of cases increases and the types of cases show diversification. How to quickly and accurately resolve cases Classifying and adding new types of cases in a timely manner to improve the efficiency of mediation work is a serious problem faced by the people's mediation work. The current types of people's mediation cases have the following shortcomings: 1. The number of existing types of cases is too small to cover all disputes; 2. It is not possible to distinguish new types of disputes from existing types of disputes in time; 3. E...

AI Technical Summary

Problems solved by technology

The current types of people's mediation cases have the following shortcomings: 1. The number of existing types of cases is too small to cover all disputes; 2. It is not possible to distinguish new types of disputes from existing types of disputes in time; 3. Existing types of disputes suddenly The item is not detailed and cannot accurately reflect the main points of the dispute

However, this method is in the vertical field, and it is difficult to expand the corpus according to external auxiliary data.

Images