Fraud identification method and device
By converting the text to be identified into a vector representation, querying the vector library and extracting key features, and using the information recognition model for fraud identification, it solves the problem that traditional methods are difficult to deal with the new fraud model, and achieves higher recognition accuracy and adaptability.
CN119484699APending Publication Date: 2025-02-18BEIJING UNIV OF POSTS & TELECOMM
View PDF 0 Cites -1 Cited by
Patent Information
- Application Number
- CN202411502885.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-25
- Publication Date
- 2025-02-18
AI Technical Summary
Technical Problem
Traditional fraud identification methods are difficult to cope with the ever-changing new fraud models, and the recognition effect is limited.
Method used
By converting the text to be identified into a vector representation, the pre-constructed vector library is queryed, key features are extracted, and the information recognition model is used for identification, improving the accuracy and adaptability of fraud identification.
Benefits of technology
It improves the accuracy of identifying telecommunications fraud, can identify new types of fraud methods, and enhances the risk prevention and control capabilities of telecommunications fraud.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN119484699A_ABST
Abstract
The embodiment of the invention provides a fraud recognition method and device. The fraud recognition method comprises the steps that a to-be-recognized text is converted into a to-be-recognized vector representation according to a preset vector conversion method; according to the to-be-identified vector representation, querying a pre-constructed vector library to obtain a target vector representation most similar to the to-be-identified vector representation; extracting at least one key feature from the target vector representation; and inputting each key feature and the to-be-identified file into a pre-constructed information identification model, and outputting an information identification result by using the information identification model. According to the method provided by the invention, the accuracy of identifying telecommunication fraud can be improved, and continuously changing novel fraud modes can be identified.
Need to check novelty before this filing date? Find Prior Art