Research on the Key Technologies of Relation Extraction from Quality Text for Industrial Manufacturing

Relation extraction of quality reports in industrial manufacturing industries such as automobiles and machinery is of great significance to the research of quality knowledge graph and quality question answering system of the industry. However, there is no available public dataset for relation extraction of quality reports, and there are few pieces of research on relation extraction of Chinese quality reports. For the above problems, this paper constructs a professional dataset for relation extraction and proposes a Chinese-based Piecewise Convolutional Neural Networks (C-PCNN) for the relation extraction of quality reports. To be more specific, this paper first collects quality reports in the field of industrial manufacturing and makes corresponding professional labels to construct a professional dataset. Then this paper learns a developed PCNN model based on Chinese characteristics by this constructed dataset, and finally this paper applies it to relation extraction in Chinese quality reports. Experimental results on the constructed dataset show that the accuracy, recall, and F1 values of the C-PCNN are 0.8234, 0.8076, 0.8154 respectively, better than PCNN and RNN, indicating the feasibility and effectiveness of the method. This research has practical significance for personnel engaged in the manufacturing industry.