An ICT System Fault Analysis Technology Based on Text Classification and Image Recognition

Abstract

Due to the increasing complexity of power grid, SGCC hopes to have a computer-aided decision-making scheme for ICT system fault identification. This paper proposes an ICT fault analysis technology which integrates text classification and image recognition. It aims to solve the problem that only relying on the knowledge reserve and personal experience of a single staff member is often unable to analyze and judge the fault of power grid system. In this paper, the main work is as follows: first, preprocess the ICT fault report data to get more easily recognized structured data by computer; second, build a text recognition model to classify the text content; then build an image recognition model to classify the image content; finally, integrating the text and image classification based on the above content, linear regression is applied to the weight parameters to improve the accuracy and reliability of the classification results. According to the test results of comprehensive test data, the accuracy of the method is good and it can be used as a reliable scheme test.