CN-122027163-A - Biological feature recognition method and device based on acoustic wave of auditory canal

CN122027163ACN 122027163 ACN122027163 ACN 122027163ACN-122027163-A

Abstract

The application discloses a biological feature recognition method and device based on auditory canal sound waves, relates to the technical field of biological recognition, and mainly aims to solve the problem of poor accuracy of existing fingerprint and face identification. The method comprises the steps of responding to a signature request of a user, indicating earphone equipment to send sound wave signals, wherein the sound wave signals comprise random numbers, obtaining reflected sound wave signals, determining voiceprint hash values of the reflected sound wave signals, generating a composite digital signature based on the voiceprint hash values and the random numbers after the voiceprint hash values are subjected to in-vivo verification, and carrying out signature verification based on the composite digital signature to obtain a biological feature recognition result.

Inventors

Yan Panjie
Xu Dinghang
CHENG RONG
XIE ZONGXIAO

Assignees

中金金融认证中心有限公司

Dates

Publication Date: 20260512
Application Date: 20260104

Claims (10)

1. A method for identifying biological characteristics based on acoustic waves of an ear canal, comprising: Responding to a signature request of a user, and indicating the earphone equipment to send an acoustic wave signal, wherein the acoustic wave signal comprises a random number; acquiring a reflected sound wave signal and determining a voiceprint hash value of the reflected sound wave signal; And after the voiceprint hash value is subjected to in-vivo verification, generating a composite digital signature based on the voiceprint hash value and the random number, and performing signature verification based on the composite digital signature to obtain a biological feature recognition result.
2. The method of claim 1, wherein before the instructing the headset device to transmit the acoustic wave signal, the method further comprises: And indicating the earphone equipment to record the acoustic meatus signal, and performing hash value conversion on the acoustic meatus signal to obtain a standard acoustic meatus hash value.
3. The method according to claim 2, wherein the method further comprises: Determining the similarity between the voiceprint hash value and a standard auditory canal hash value; and if the similarity is greater than a preset similarity threshold, determining that the voiceprint hash value passes the in-vivo verification.
4. The method of claim 1, wherein the determining the voiceprint hash value of the reflected acoustic wave signal comprises: And extracting the reflection spectrum characteristics of the reflected sound wave signals, and performing hash value calculation based on the reflection spectrum characteristics to obtain voiceprint hash values.
5. The method of claim 1, wherein the generating a composite digital signature based on the voiceprint hash value and the random number comprises: splicing the voiceprint hash value, the signature Wen Haxi value and the random number to obtain a spliced hash value; and carrying out digital signature on the spliced hash value based on a security private key to obtain the composite digital signature.
6. The method of claim 5, wherein the performing signature verification based on the composite digital signature, obtaining a biometric result comprises: Transmitting the composite digital signature to a verifier so that the verifier decrypts based on a public key, wherein the verifier obtains the standard auditory canal hash value in an authorized mode and then compares and verifies the decrypted hash value; and receiving a biological characteristic recognition result fed back by the verifier.
7. The method of claim 6, wherein before the instructing the headset device to transmit the acoustic wave signal, the method further comprises: Generating a random number; Obtaining a document to be signed, and performing hash value calculation on the document to be signed to obtain a signature Wen Haxi value; the method further comprises the steps of: and synthesizing an electronic signature file based on the composite digital signature, and outputting the biological characteristic recognition result and the electronic signature file to complete biological characteristic recognition.
8. A biological feature recognition device based on acoustic waves of an ear canal, comprising: the sending module is used for responding to a signature request of a user and indicating the earphone equipment to send an acoustic wave signal, wherein the acoustic wave signal comprises a random number; The determining module is used for acquiring the reflected sound wave signal and determining a voiceprint hash value of the reflected sound wave signal; And the generation module is used for generating a composite digital signature based on the voiceprint hash value and the random number after the voiceprint hash value is subjected to living body verification, and carrying out signature verification based on the composite digital signature to obtain a biological characteristic recognition result.
9. A computer readable storage medium having stored thereon a computer program/instruction which when executed by a processor performs the steps of the method of claim 1.
10. A computer device comprising a memory, a processor and a computer program stored on the memory, characterized in that the processor executes the computer program to carry out the steps of the method of claim 1.

Description

Biological feature recognition method and device based on acoustic wave of auditory canal Technical Field The application relates to the technical field of biological identification, in particular to a biological feature identification method and device based on acoustic waves of an auditory canal. Background The biological recognition technology is to closely combine a computer with high-tech means such as optics, acoustics, a biological sensor, a biological statistics principle and the like, and utilize the inherent physiological characteristics of a human body (such as fingerprints, facial images, irises and the like) and behavioral characteristics (such as handwriting, sound, gait and the like) to identify the identity of the person. With the rapid development of intelligent technology, in identification and authentication of identity features, fingerprint and face authentication based on image recognition and voiceprint authentication based on signal analysis can be adopted, but fingerprint and face authentication are easy to make false images and biological features are easy to leak, voiceprint authentication is easy to be influenced by environmental noise, and authentication accuracy between users with small sound variability is low, so that a biological feature recognition method is needed to solve the problems. Disclosure of Invention In view of the above, the application provides a biological feature recognition method and device based on acoustic waves of auditory meatus, which mainly aims to solve the problem of poor accuracy of the existing fingerprint and face identification. According to one aspect of the present application, there is provided a biological feature recognition method based on acoustic waves of an ear canal, comprising: Responding to a signature request of a user, and indicating the earphone equipment to send an acoustic wave signal, wherein the acoustic wave signal comprises a random number; acquiring a reflected sound wave signal and determining a voiceprint hash value of the reflected sound wave signal; And after the voiceprint hash value is subjected to in-vivo verification, generating a composite digital signature based on the voiceprint hash value and the random number, and performing signature verification based on the composite digital signature to obtain a biological feature recognition result. Further, before the instructing the earphone device to transmit the acoustic wave signal, the method further includes: And indicating the earphone equipment to record the acoustic meatus signal, and performing hash value conversion on the acoustic meatus signal to obtain a standard acoustic meatus hash value. Further, the method further comprises: Determining the similarity between the voiceprint hash value and a standard auditory canal hash value; and if the similarity is greater than a preset similarity threshold, determining that the voiceprint hash value passes the in-vivo verification. Further, the determining the voiceprint hash value of the reflected acoustic wave signal includes: And extracting the reflection spectrum characteristics of the reflected sound wave signals, and performing hash value calculation based on the reflection spectrum characteristics to obtain voiceprint hash values. Further, the generating a composite digital signature based on the voiceprint hash value and the random number includes: splicing the voiceprint hash value, the signature Wen Haxi value and the random number to obtain a spliced hash value; and carrying out digital signature on the spliced hash value based on a security private key to obtain the composite digital signature. Further, the step of performing signature verification based on the composite digital signature to obtain a biometric feature recognition result includes: Transmitting the composite digital signature to a verifier so that the verifier decrypts based on a public key, wherein the verifier obtains the standard auditory canal hash value in an authorized mode and then compares and verifies the decrypted hash value; and receiving a biological characteristic recognition result fed back by the verifier. Further, before the instructing the earphone device to transmit the acoustic wave signal, the method further includes: Generating a random number; Obtaining a document to be signed, and performing hash value calculation on the document to be signed to obtain a signature Wen Haxi value; the method further comprises the steps of: and synthesizing an electronic signature file based on the composite digital signature, and outputting the biological characteristic recognition result and the electronic signature file to complete biological characteristic recognition. According to another aspect of the present application, there is provided an ear canal acoustic wave-based biometric identification device comprising: the sending module is used for responding to a signature request of a user and indicating the earphone equipment to send