基于文本分析的货物运输发票异常判断方法和装置
By segmenting and preprocessing freight transport invoices, and combining waybill attributes and Bayesian prior information, an invoice classification and recognition model is used to solve the problem of low efficiency in cargo information identification and anomaly judgment in existing technologies, thus achieving efficient and accurate invoice anomaly judgment.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- YONGLI SHUZHI (BEIJING) TECH CO LTD
- Filing Date
- 2022-12-21
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies cannot quickly and accurately identify target cargo information in freight invoices and determine information anomalies, resulting in low efficiency in the judgment process.
The freight invoices are segmented and preprocessed using text analysis methods. Combined with waybill attributes, an invoice classification and recognition model is used to extract the type of goods and identify anomalies. Bayesian prior information and credit information are integrated to improve the accuracy and efficiency of recognition.
It achieves accurate regional text recognition on freight transport invoices, improving the accuracy and efficiency of freight invoice text judgment and enabling rapid identification and judgment of invoice anomalies.
Smart Images
Figure CN115862042B_ABST