Invoice false decline risk assessment method based on keyword extraction and rapid text classification

• Main Authors: JIN YUZE, ZHOU HONGLI
• Format: Patent
• Language: Chinese; English
• Published: 05.01.2021
• 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 an invoice false-decline risk assessment method based on keyword extraction and rapid text classification. The method comprises the steps of 1, establishing a value-added tax invoice sample database of a to-be-assessed region; 2, combining the commodity codes of which the similarity is not less than a threshold value into a commodity category, and selecting a set commoditycategory CA; 3, forming a forward keyword set SET, and positively putting the SET into a bag-of-words model ModelCA; 4, forming a reverse keyword set SET reverse, updating a forward keyword set SET forward, and updating a bag-of-words model ModelCA; 5, obtaining a final bag-of-word model ModelCA; 6, inputting a total value-added tax invoice in a to-be-assessed time period of the to-be-assessed region; 7, screening out invoices of the commodity class CA by utilizing the final word bag model ModelCA in the step 5, and judging whether a purchaser taxpayer uses the invoices for deduction of the output tax amount; and 8, p