Identity verification system and method based on voiceprint recognition
A voiceprint recognition and voiceprint technology, which is applied in the field of identity verification system based on voiceprint recognition, can solve the problem of time-consuming identity verification
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0031] Example one
[0032] The identity verification system based on voiceprint recognition includes the client, server and back-end terminal. The client is the Huawei P40 mobile phone used by the customer. The server is a Dell EMC PowerEdge T30 micro-tower server, and the back-end terminal is a Lenovo all-in-one computer; figure 1 As shown, the server includes an input module, a database, a processing module, and an output module. The input module is used to obtain the current voiceprint model sent by the client during a call; the database is used to pre-store the sample voiceprint model of the client; The module is used to receive the current voiceprint model and process the current voiceprint model according to the sample voiceprint model. If the current voiceprint model does not match the sample voiceprint model, the first warning message will be generated; otherwise, the verification message will be generated ; Output module, used to send the first alarm information and the...
Example Embodiment
[0042] Example two
[0043] Compared with the first embodiment, the only difference is that the database is also used to store the voiceprint models of blacklisted users; the processing module is used to determine the current voiceprint model according to the blacklisted voiceprint model. If the voiceprint model is the same, the second alarm information is generated. Specifically, since customer B is judged to maliciously use the identity of another person to apply for credit business, the voiceprint model of customer B is stored in the database as a blacklist; it is convenient for subsequent identification and matching of the voiceprint model to obtain the result The second warning message is "This user is a blacklisted user, and is suspected of defrauding customers, please be alert!", the auditor will conduct further identity verification and verification.
Example Embodiment
[0044] Example three
[0045] Compared with the first embodiment, the only difference is that the input module is also used to obtain the short message data of the user side; the preprocessing module is also used to filter the short message data in the user side and extract the keyword information in the short message data , Extract the short message data whose keywords include finance or credit to generate the target to be verified; the processing module is also used for semantic analysis of the target to be verified. When the result of the semantic analysis is a positive result, it is recorded as a positive one; otherwise , It is recorded as minus one point; the output module is also used to receive the standard scores pre-stored in the database, and calculate the scores according to the semantic analysis results to obtain score information; if the score information is less than the first preset threshold, mark the user as high Risk users, and send user information to the user ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap