Financial reimbursement document listing account subject matching degree verification method and system

• Main Authors: JEON HO-KYUNG, CHEN YONGLI, ZHAO WENBING
• Format: Patent
• Language: Chinese; English
• Published: 04.07.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a financial reimbursement bill listing account subject matching degree verification method and system, belongs to the technical field of natural language recognition, and aims to solve the technical problem of how to excavate the internal relation between a reimbursement bill business abstract and a financial listing account subject, realize accurate recognition of the financial listing account subject matching degree and improve the recognition efficiency. According to the technical scheme, the method specifically comprises the following steps that historical statement data are selected, financial listing account subject short text core word extraction and short text classification are achieved, and training samples are sorted out; carrying out abstract analysis on the training samples based on an NLP technology, and realizing feature extraction of listing account subjects through service abstracts; performing convolutional neural network classification training, and outputting a trai