Voiceprint extraction method, core network element, electronic device and storage medium

Abstract

Embodiments of the present invention provide a voiceprint extraction method, a network element of a core network, electronic equipment, and a storage medium. The method includes that the network element of the core network receives the first call signaling sent by the sending end, the first call signaling includes a calling number and a called number carrying a fraud identification mark, and the fraud identification mark is that the sending end judges that the calling number is suspected Added after the fraudulent phone number; according to the fraudulent identification mark, the call traffic corresponding to the first call signaling and the pre-received call signaling is sent to the aggregation end office for the voiceprint extraction system to collect through the link of the aggregation end office The first call signaling and call traffic, and extract the voiceprint according to the first call signaling and call traffic. According to the method, the core network element routes the first call signaling and call traffic to a designated convergent end office according to the fraud identification mark, so as to realize single-point collection of the first call signaling and call traffic, and according to the first call Extract voiceprints from signaling and call traffic to improve the efficiency of voiceprint extraction.

Description

technical field [0001] The embodiment of the present invention relates to the field of communication technology, in particular to a voiceprint extraction method, a core network element, an electronic device and a storage medium. Background technique [0002] Telephone fraud refers to the criminal activity of deceiving the trust of the victim by calling the victim. It is characterized by the fact that the suspect leaves less evidence, and the suspect’s voice is an important evidence in the process of telephone fraud. [0003] After conducting in-depth and detailed analysis and research, it was found that the most effective weapon to detect phone fraud is to identify criminal suspects through voiceprints. Voiceprint refers to inputting the voice of a person into a voice analyzer for analysis to obtain the distribution waveform of the voice. Voiceprint recognition is a technology that automatically identifies the identity of the speaker based on the waveform. [0004] The way...

AI Technical Summary

Problems solved by technology

[0007] In the massive call traffic at the carrier level, most of the calls are normal user behaviors, and only a very small part are phone fraud behaviors. The massive traffic data of the billion level is collected in full, and then the suspected fraudulent calls are filtered to extract the suspected fraudulent numbers. voiceprint, high cost and low efficiency

Images