Mathematical problem concept type prediction service provision method using neural network-based machine translation and mascorpus (Math Corpus)

摘要

PROBLEM TO BE SOLVED: To provide a method for providing a mathematical problem concept type prediction service using neural network-based machine translation and a mass corpus. SOLUTION: The mathematical problem concept type prediction service providing system has a stage where a mathematical text problem is input, a stage where the mathematical text problem is separated into text and an image by using natural language processing and image processing, and a separated text. Is analyzed using morphological analysis and individual name recognition based on the mass corpus, and the image is analyzed using object recognition and semantic analysis to extract mathematical terms. The stage of filtering, extracting and compressing conceptual type candidates based on the translated mathematical terms, the step of analyzing the mathematically translated mathematical terms to classify them into the established cases and terms, the neural network infrastructure machine. This includes the stage of classifying the conceptual types of mathematical text problems by analyzing the syntax patterns based on the definitions of the already set calculation problem patterns, text problem patterns, and illustrated problem patterns using translation. [Selection diagram] FIG. 7