Voiceprint-based identity authentication method and device

Abstract

The embodiment of the present specification discloses a voiceprint-based identity authentication method, in which a random code is generated by a smart glasses end and a server in each voiceprint-based identity authentication link, the smart glasses end plays verification audio constructed according to the locally generated random code, and then the verification audio is collected and uploaded to the server. After the server decodes the verification audio, the consistency between the received random code and the random code generated by the server is verified to realize the authentication of the user identity. In the entire voiceprint-based identity authentication link, the random code is not transmitted, the verification audio generated based on the random code is also random, and the verification audio is transmitted through playing and collecting, thereby limiting the distance to the attacker, and the security is improved. The voiceprint-based identity authentication device described in the embodiment of the present specification also has the beneficial effects described above.

Description

Technical Field

[0001] This invention relates to the field of identity authentication technology, and in particular to a voiceprint-based identity authentication method and apparatus. Background Technology

[0002] Currently, voiceprint authentication technology in smart glasses relies on traditional acoustic features and one-way authentication processes. However, due to their open sound field design, smart glasses are vulnerable to attacks at multiple stages of the voiceprint transmission link. For example, the physical interface between the microphone module and the processing chip may be subject to side-channel attacks, the voiceprint features may be intercepted and replayed during transmission to the authentication server, and the local voiceprint template may be physically extracted and reverse-cloned. Summary of the Invention

[0003] One or more embodiments of this specification provide a voiceprint-based identity authentication method and apparatus that can effectively resist voiceprint injection attacks during the voiceprint verification process of smart glasses.

[0004] Firstly, a voiceprint-based identity authentication method is provided, applicable to smart glasses, the method comprising:

[0005] In response to the user's identity verification request, the smart glasses generate a first random code. At the same time, the smart glasses send an identity verification request to the server to trigger the server to generate a second random code. The first random code and the second random code are generated in the same way.

[0006] The smart glasses generate and play the verification audio based on the first random code.

[0007] The smart glasses collect and play the verification audio and upload it to the server, so that the server can decode the verification audio to obtain the first random code, and determine whether the user has passed the identity authentication by comparing the consistency of the first random code and the second random code.

[0008] As an alternative implementation of the method described in the first aspect, the verification audio is ultrasonic audio.

[0009] As an optional implementation of the method described in the first aspect, the smart glasses terminal generates verification audio based on the first random code, specifically including:

[0010] The smart glasses terminal randomly assigns an audio frequency to each character in the first random code;

[0011] Generate sub-audio frequencies based on the audio frequencies;

[0012] The sub-audio is concatenated according to the order of characters in the first random code to obtain the verification audio.

[0013] Specifically, the server decodes the verification audio to obtain the first random code, which includes:

[0014] The server decodes the verification audio according to a pre-agreed decoding method with the smart glasses to obtain the first random code.

[0015] As an optional implementation of the method described in the first aspect, the smart glasses terminal includes smart glasses, which include a first response module, a first audio generation module, a first audio playback module, and a first audio acquisition module;

[0016] The first response module is configured to generate the first random code in response to the user's identity verification request; at the same time, it sends the identity verification request to the server.

[0017] The first audio generation module is configured to generate the verification audio based on the first random code;

[0018] The first audio playback module is configured to play the verification audio;

[0019] The first audio acquisition module is configured to acquire the verification audio being played and upload it to the server.

[0020] As an optional implementation of the method described in the first aspect, the smart glasses end includes smart glasses and a smart terminal;

[0021] The smart glasses are configured to, in response to the user's identity verification request, send a random code generation request to the smart terminal; and simultaneously, send the identity verification request to the server.

[0022] The smart terminal is configured to generate the first random code in response to the random code generation request, and to generate and play the verification audio based on the first random code.

[0023] The smart glasses are also configured to collect the verification audio played by the smart terminal and upload it to the server.

[0024] Secondly, a voiceprint-based identity authentication device is provided, suitable for smart glasses, including:

[0025] The second response module is configured to generate a first random code in response to a user's authentication request, and simultaneously send an authentication request to the server to trigger the server to generate a second random code; the first random code and the second random code are generated in the same way;

[0026] The second audio generation module is configured to generate verification audio based on the first random code;

[0027] The second audio playback module is configured to play the verification audio.

[0028] The second audio acquisition module is configured to acquire the verification audio being played and upload it to the server, so that the server can decode the verification audio to obtain the first random code, and determine whether the user has passed the identity authentication by comparing the consistency of the first random code and the second random code.

[0029] As an optional implementation of the apparatus described in the second aspect, the audio generation module is specifically used to generate ultrasonic audio based on the first random code as the verification audio.

[0030] As an optional embodiment of the apparatus described in the second aspect, the audio generation module is specifically used for:

[0031] Randomly assign an audio frequency to each character in the first random code;

[0032] Generate sub-audio frequencies based on the audio frequencies;

[0033] The sub-audio is concatenated according to the order of characters in the first random code to obtain the verification audio.

[0034] Specifically, the audio generation module generates the verification audio using an encoding method pre-agreed with the server; the server is specifically used to decode the verification audio using a corresponding decoding method to obtain the first random code.

[0035] Thirdly, a smart glasses system is provided, including the aforementioned voiceprint-based identity authentication device.

[0036] Fourthly, a smart glasses system is provided, including: smart glasses and a smart terminal;

[0037] The smart glasses are configured to, in response to a user's identity verification request, send a random code generation request to the smart terminal; simultaneously, send an identity verification request to the server; thereby triggering the server to generate a second random code.

[0038] The smart terminal is configured to generate a first random code in response to the random code generation request, and to generate and play a verification audio based on the first random code; the first random code and the second random code are generated in the same way.

[0039] The smart glasses are also configured to collect the verification audio played by the smart terminal and upload it to the server, so that the server can decode the verification audio to obtain the first random code, and determine whether the user has passed the identity authentication by comparing the consistency of the first random code and the second random code.

[0040] As an optional implementation of the system described in the fourth aspect, the smart terminal is specifically used to generate ultrasonic audio based on the first random code as the verification audio.

[0041] As an optional implementation of the system described in the fourth aspect, the smart terminal is specifically used for:

[0042] Randomly assign an audio frequency to each character in the first random code;

[0043] Generate sub-audio frequencies based on the audio frequencies;

[0044] The sub-audio is concatenated according to the order of characters in the first random code to obtain the verification audio.

[0045] Specifically, in the aforementioned smart glasses system, the smart terminal generates the verification audio using an encoding method pre-agreed with the server; the server is specifically used to decode the verification audio using a corresponding decoding method to obtain the first random code.

[0046] The beneficial effects of the voiceprint-based identity authentication method described in the embodiments of this specification are as follows:

[0047] In each voiceprint-based identity authentication step, the smart glasses and the server generate a random code. The smart glasses play a verification audio constructed based on the locally generated random code and then collect the verification audio and upload it to the server. After decoding the verification audio, the server verifies the consistency between the received random code and the random code generated by the server to authenticate the user's identity.

[0048] Throughout the voiceprint-based authentication process, the random code is stored separately on the smart glasses and the server and is not transmitted. This makes it difficult for external attacks to obtain the random code, thus improving its security.

[0049] Furthermore, the verification audio generated based on the random code is also random during each authentication process, and the verification audio is transmitted through playback and capture, which sets a distance limit for attackers, thereby further improving security.

[0050] In summary, in the above-mentioned voiceprint-based authentication methods, the random code and verification audio are difficult to forge and predict, thus effectively resisting voiceprint injection attacks.

[0051] The voiceprint-based identity authentication device, smart glasses, and smart glasses system described in the embodiments of this specification also have the aforementioned beneficial effects. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 An exemplary schematic diagram of a voiceprint-based identity authentication system described in an embodiment of this specification is shown.

[0054] Figure 2 An exemplary flowchart of a voiceprint-based identity authentication method described in an embodiment of this specification is shown.

[0055] Figure 3 An exemplary schematic diagram of a waveform structure for verifying audio is shown in an embodiment of this specification.

[0056] Figure 4 A schematic diagram of the structure of a smart glasses terminal 11 as described in an embodiment of this specification is shown as an example.

[0057] Figure 5 An exemplary schematic diagram of a voiceprint-based identity authentication device provided in an embodiment of this specification is shown. Detailed Implementation

[0058] First, it should be noted that the terminology used in the embodiments of this invention is for the purpose of describing specific embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” used in the embodiments of this invention and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0059] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments in this specification, and not all of the embodiments. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0060] It should be noted that the steps of the corresponding methods are not necessarily performed in the order shown and described in this specification in other embodiments. In some other embodiments, the methods may include more or fewer steps than described in this specification. Furthermore, a single step described in this specification may be broken down into multiple steps in other embodiments; and multiple steps described in this specification may be combined into a single step in other embodiments.

[0061] Existing voiceprint authentication technologies rely on traditional acoustic features (such as MFCC and fundamental frequency) and one-way authentication processes. However, smart glasses have unique risks due to their open sound field design (such as bone conduction and temple microphones), for example:

[0062] Hardware link vulnerability: The physical interface (such as the 2S bus) between the microphone module and the processing chip of smart glasses may be attacked by bypass, through electromagnetic injection or malicious firmware to tamper with the voiceprint data stream.

[0063] Transport layer exposure: When smart glasses transmit voiceprint features to the cloud identity verification server, if end-to-end encryption (such as the national cryptographic algorithm SM9) is not used, it may be intercepted and replayed by man-in-the-middle attacks.

[0064] Vulnerability in storage: If the local voiceprint template of smart glasses only uses general encrypted storage (such as AES-256) without hardware security element (SE) isolation, it is easy to be physically extracted and reverse cloned.

[0065] In summary, with the advancement of deepfake technology, attackers can record / steal users' voiceprints and inject them directly into the voiceprint authentication link of smart glasses through linking methods. Existing voiceprint authentication solutions are insufficient to resist voiceprint attacks.

[0066] In view of this, one or more embodiments of this specification propose a voiceprint-based identity authentication method and apparatus, which can effectively resist voiceprint injection attacks during the voiceprint verification process of smart glasses.

[0067] The voiceprint-based identity authentication method and apparatus described in one or more embodiments of this specification will be further described in detail below with reference to the accompanying drawings and specific embodiments. However, this detailed description does not constitute a limitation on the embodiments of this specification.

[0068] Please refer to Figure 1 , Figure 1 A voiceprint-based identity authentication system is proposed for one or more embodiments of this specification. For example... Figure 1 As shown, the system includes: smart glasses terminal 11 and server terminal 12.

[0069] The smart glasses 11 and the server 12 are connected via a communication link, which can be a wired network or a wireless network. For example, the smart glasses 11 can establish a communication connection with the server 12 using communication methods such as WIFI, Bluetooth, or infrared. Alternatively, the smart glasses 11 can also establish a communication connection with the server 12 via a mobile network, where the mobile network standard can be any of 2G (GSM), 2.5G (GPRS), 3G (WCDMA, TD-SCDMA, CDMA2000, UTMS), 4G (LTE), 4G+ (LTE+), WiMax, etc.

[0070] The server 12 can be any device, equipment, platform, or cluster of devices with computing and processing capabilities. In this embodiment, the implementation form of the server 12 is not limited. For example, the server 12 can be a single server or a server cluster composed of multiple servers. The server 12 can also be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system.

[0071] In the aforementioned voiceprint-based identity authentication system, the smart glasses terminal 11 generates and collects verification audio and uploads it to the server terminal 12. The server terminal 12 then verifies the verification audio uploaded by the smart glasses terminal 11 to verify the user's identity.

[0072] In conjunction with the aforementioned voiceprint-based identity authentication system, one or more embodiments of this specification provide a voiceprint-based identity authentication method applicable to smart glasses terminal 11. Please refer to... Figure 2 , Figure 2 A flowchart illustrating a voiceprint-based identity authentication method is shown, such as... Figure 2 As shown, the method includes steps S200 to S204.

[0073] S200: In response to the user's identity verification request, the smart glasses terminal 11 generates a first random code. At the same time, the smart glasses terminal 11 sends an identity verification request to the server 12 to trigger the server 12 to generate a second random code.

[0074] The aforementioned smart glasses terminal 11 and server terminal 12 must use the same random code generation method to generate the first random code and the second random code, ensuring that the generated first random code and the second random code are consistent. This random code generation method can be pre-deployed in the smart glasses terminal 11 and server terminal 12. Furthermore, the specific algorithm program for this random code generation method can be deployed in a trusted environment within the smart glasses terminal 11 and server terminal 12.

[0075] In some implementations, a timestamp-based random code generation algorithm H can be pre-deployed on the smart glasses 11 and the server 12.

[0076] When the smart glasses terminal 11 receives a user's identity verification request, it obtains the current timestamp T1 and uses a random code generation algorithm H to generate a first random code H(T1) based on T1. Simultaneously, the smart glasses terminal 11 sends an identity verification request to the server 12, including a timestamp T2, where T2 = T1. After receiving the identity verification request from the smart glasses terminal 11, the server 12 uses the random code generation algorithm H to generate a second random code H(T2) based on T2.

[0077] It should be noted that the above-mentioned random code generation method can be selected and set according to requirements, and this embodiment does not impose any restrictions on it.

[0078] S202: The smart glasses terminal 11 generates and plays the verification audio based on the first random code.

[0079] In some implementations, the smart glasses terminal 11 can generate an ultrasonic audio signal based on a first random code as the aforementioned verification audio. Since ultrasonic waves are inaudible to the human ear, this verification audio will not affect the user experience during playback.

[0080] Specifically, when generating the verification audio, the smart glasses terminal 11 can randomly assign an audio frequency to each character in the first random code, and then generate a sub-audio for each character using that audio frequency; finally, all the sub-audio are concatenated according to the order of the characters in the first random code to obtain the verification audio.

[0081] The following uses ultrasound as an example to explain in detail how the above verification audio is generated.

[0082] In one implementation, if the first random code is 223, then when generating the verification audio, each character in the first random code can first be represented by a 4-bit binary number, where "2" is represented as "0010" and "3" as "0011". Next, for each character, a frequency is randomly assigned to the "0" and "1" in its binary representation. For example, ... Figure 3As shown, 20100 Hz can represent "1" and 20000 Hz can represent "0". Therefore, the ultrasonic audio sequence corresponding to "2" is: 20000 Hz, 20000 Hz, 20100 Hz, 20000 Hz; the ultrasonic audio sequence corresponding to "3" is: 20000 Hz, 20000 Hz, 20100 Hz, 20100 Hz. The ultrasonic audio sequence corresponding to the first random code 223 is: 20000 Hz, 20000 Hz, 20100 Hz, 20000 Hz, 20000 Hz, 20000 Hz, 20100 Hz, 20000 Hz, 20000 Hz, 20100 Hz, 20100 Hz.

[0083] It should be noted that the specific method for generating verification audio based on the first random code can be set according to requirements, and this embodiment does not impose any restrictions on it.

[0084] S204: The smart glasses terminal 11 collects and plays the verification audio and uploads it to the server 12, so that the server 12 can decode the verification audio to obtain the first random code, and determine whether the user has passed the identity authentication by comparing the consistency of the first random code and the second random code.

[0085] The smart glasses terminal 11 and the server terminal 12 need to agree on the encoding and decoding methods of the verification audio in advance so that the server terminal 12 can successfully complete the decoding after receiving the verification audio uploaded by the smart glasses terminal 11 to obtain the first random code.

[0086] Next, server 12 compares the first random code with the second random code generated locally. If they match, server 12 determines that the user has passed authentication and sends a verification success message to smart glasses 11. If they do not match, server 12 determines that the user has failed authentication and sends a verification failure message to smart glasses 11.

[0087] In the specific implementation of the above method, the smart glasses terminal 11 can be a standalone smart glasses, the internal structure of which is as follows: Figure 4 As shown, it includes a first response module 401, a first audio generation module 402, a first audio playback module 403, and a first audio acquisition module 404.

[0088] The first response module 401 is configured to generate a first random code in response to a user's identity verification request; at the same time, it sends an identity verification request to the server 12 to trigger the server to generate a second random code.

[0089] The first audio generation module 402 is configured to generate verification audio based on the first random code.

[0090] The first audio playback module 403 is configured to play verification audio.

[0091] The first audio acquisition module 404 is configured to acquire the verification audio to be played and upload it to the server 12.

[0092] In the specific implementation of the above method, the smart glasses terminal 11 can also be divided into smart glasses and smart terminal. The smart terminal can be configured with an APP that matches the smart glasses to implement the corresponding steps in the above voiceprint-based identity authentication method.

[0093] The smart glasses are configured to initiate a random code generation request to the smart terminal 12 in response to the user's identity verification request; at the same time, the identity verification request is initiated to the server 12 to trigger the server 12 to generate a second random code.

[0094] The smart terminal is configured to generate a first random code in response to a random code generation request, and to generate and play a verification audio based on the first random code.

[0095] The smart glasses are also configured to collect the verification audio played by the smart terminal and upload it to the server 12, so that the server 12 can decode the verification audio to obtain the first random code, and determine whether the user has passed the identity authentication by comparing the consistency of the first random code and the second random code.

[0096] In summary, regardless of whether the smart glasses terminal 11 is implemented through a single smart glasses or through a combination of smart glasses and a smart terminal, the first random code is not transmitted after it is generated. The verification audio is collected by the user's own smart glasses and uploaded to the server 12.

[0097] Corresponding to the aforementioned voiceprint-based authentication method, one or more embodiments of this specification propose a voiceprint-based authentication device suitable for smart glasses terminal 11. For example... Figure 5 As shown, the voiceprint-based identity authentication device includes:

[0098] The second response module 501 is configured to generate a first random code in response to a user's identity verification request, and at the same time, send an identity verification request to the server 12 to trigger the server 12 to generate a second random code.

[0099] The second audio generation module 502 is configured to generate verification audio based on the first random code.

[0100] The second audio playback module 503 is configured to play verification audio.

[0101] The second audio acquisition module 504 is configured to acquire and play verification audio and upload it to the server 12, so that the server 12 can decode the verification audio to obtain the first random code, and determine whether the user has passed the identity authentication by comparing the consistency of the first random code and the second random code.

[0102] For the second response module 501 described above, both the second response module 501 and the server 12 must use the same random code generation method to generate the first random code and the second random code, ensuring that the generated first random code and the second random code are consistent. This random code generation method can be pre-deployed in the second response module 501 and the server 12. Furthermore, the specific algorithm program for this random code generation method can be deployed in a trusted environment within the second response module 501 and the server 12.

[0103] In some implementations, a timestamp-based random code generation algorithm H may be pre-deployed in the second response module 501 and the server 12.

[0104] When the second response module 501 receives a user's identity verification request, it obtains the current timestamp T1 and uses the random code generation algorithm H to generate a first random code H(T1) based on T1. Simultaneously, the second response module 501 sends an identity verification request to the server 12, carrying a timestamp T2, where T2 = T1. After receiving the identity verification request from the second response module 501, the server 12 uses the random code generation algorithm H to generate a second random code H(T2) based on T2.

[0105] It should be noted that the above-mentioned random code generation method can be selected and set according to requirements, and this embodiment does not impose any restrictions on it.

[0106] Regarding the second audio generation module 502 described above, in some embodiments, the second audio generation module 502 can generate an ultrasonic audio segment as the verification audio based on the first random code. Since the human ear cannot hear ultrasonic waves, this verification audio will not affect the user experience when played.

[0107] Specifically, when generating the verification audio, the second audio generation module 502 can randomly assign an audio frequency to each character in the first random code, and then generate a sub-audio for each character using the audio frequency; finally, all the sub-audio are concatenated according to the order of the characters in the first random code to obtain the verification audio.

[0108] In one implementation, assuming the first random code is 223, the second audio generation module 502, when generating the verification audio, can first represent each character in the first random code using a 4-bit binary representation, where "2" is represented as "0010" and "3" as "0011". Then, for each character, the second audio generation module 502 randomly assigns a frequency to the "0" and "1" in its binary representation. For example, ... Figure 3 As shown, 20100 Hz can represent "1" and 20000 Hz can represent "0". Therefore, the ultrasonic audio sequence corresponding to "2" is: 20000 Hz, 20000 Hz, 20100 Hz, 20000 Hz; the ultrasonic audio sequence corresponding to "3" is: 20000 Hz, 20000 Hz, 20100 Hz, 20100 Hz. The ultrasonic audio sequence corresponding to the first random code 223 is: 20000 Hz, 20000 Hz, 20100 Hz, 20000 Hz, 20000 Hz, 20000 Hz, 20100 Hz, 20100 Hz, 20000 Hz, 20000 Hz, 20000 Hz, 20100 Hz, 20100 Hz.

[0109] It should be noted that the specific method for generating verification audio based on the first random code can be set according to requirements, and this embodiment does not impose any restrictions on it.

[0110] The second audio generation module 502 and the server 12 need to agree in advance on the encoding and decoding methods of the verification audio so that the server 12 can successfully complete the decoding to obtain the first random code after receiving the verification audio uploaded by the second audio generation module 502.

[0111] The second audio playback module 503 described above can be implemented using a player, which plays the verification audio in the near field.

[0112] The second audio acquisition module 504 described above can be implemented using the microphone array of the smart glasses terminal 11.

[0113] Corresponding to the aforementioned voiceprint-based identity authentication device, one or more embodiments of this specification propose a smart glasses that apply the aforementioned voiceprint-based identity authentication device to implement the aforementioned voiceprint-based identity authentication method.

[0114] Corresponding to the above-described voiceprint-based identity authentication method, one or more embodiments of this specification propose a smart glasses system, including: smart glasses and a smart terminal, wherein the smart terminal may deploy an app for the smart glasses to implement the corresponding steps in the above-described voiceprint-based identity authentication method.

[0115] The smart glasses are configured to initiate a random code generation request to the smart terminal in response to the user's identity verification request; at the same time, they initiate an identity verification request to the server 12 to trigger the server 12 to generate a second random code.

[0116] The smart terminal is configured to generate a first random code in response to a random code generation request, and to generate and play a verification audio based on the first random code.

[0117] The smart glasses are also configured to collect the verification audio played by the smart terminal and upload it to the server 12, so that the server 12 can decode the verification audio to obtain the first random code, and determine whether the user has passed the identity authentication by comparing the consistency of the first random code and the second random code.

[0118] Optionally, the smart terminal can be used to generate ultrasonic audio based on the first random code as verification audio.

[0119] Optionally, the smart terminal can be used to: randomly assign an audio frequency to each character in the first random code; generate a sub-audio based on the audio frequency; and concatenate the sub-audio according to the order of the characters in the first random code to obtain the verification audio.

[0120] Optionally, the smart terminal needs to agree on the encoding and decoding of the verification audio with the server 12 in advance, so that the server 12 can use the corresponding decoding method to decode the received verification audio and obtain the first random code.

[0121] It is understood that the structures illustrated in the embodiments of this specification do not constitute a specific limitation on the system of the embodiments of this specification. In other embodiments of the specification, the above system may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0122] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the apparatus embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0123] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0124] It should be noted that the above examples are merely specific embodiments of the present invention, and the present invention is obviously not limited to the above embodiments, with many similar variations. All modifications that can be directly derived or conceived by those skilled in the art from the content disclosed in this invention should fall within the protection scope of this invention.

Claims

1. A voiceprint-based identity authentication method suitable for a smart glasses end, the method comprising: in response to a user's identity verification request, the smart glasses end obtains a current timestamp T1, generates a first random code according to T1 using a random code generation algorithm, and simultaneously initiates an identity verification request to a server and carries a timestamp T2, T2=T1, in the identity verification request to trigger the server to generate a second random code according to T2 using a random code generation algorithm; the smart glasses end randomly assigns an audio frequency to each character in the first random code; generates a sub-audio according to the audio frequency; splices the sub-audio according to the order of characters in the first random code to obtain a verification audio and plays the verification audio; the verification audio is an ultrasonic audio; the smart glasses end collects the played verification audio and uploads it to the server, so that the server decodes the verification audio according to a pre-agreed decoding manner with the smart glasses end to obtain the first random code, and determines whether the user passes the identity authentication by comparing the consistency of the first random code and the second random code. 2.The method of claim 1, wherein the smart glasses end comprises a smart glasses, and the smart glasses comprises a first response module, a first audio generation module, a first audio playing module and a first audio collection module; the first response module is configured to generate the first random code in response to the user's identity verification request, and simultaneously initiate the identity verification request to the server; the first audio generation module is configured to generate the verification audio based on the first random code; the first audio playing module is configured to play the verification audio; the first audio collection module is configured to collect the played verification audio and upload it to the server. 3.The method of claim 1, wherein the smart glasses end comprises a smart glasses and a smart terminal; the smart glasses is configured to initiate a random code generation request to the smart terminal in response to the user's identity verification request, and simultaneously initiate the identity verification request to the server; the smart terminal is configured to generate the first random code in response to the random code generation request, and generate the verification audio based on the first random code and play the verification audio; the smart glasses is further configured to collect the verification audio played by the smart terminal and upload it to the server. 4.A voiceprint-based identity authentication device suitable for a smart glasses end, comprising: a second response module configured to obtain a current timestamp T1 in response to a user's identity verification request, generate a first random code according to T1 using a random code generation algorithm, and simultaneously initiate an identity verification request to a server and carry a timestamp T2, T2=T1, in the identity verification request to trigger the server to generate a second random code according to T2 using a random code generation algorithm. a second audio generation module configured to randomly assign an audio frequency to each character in the first random code, generate a sub-audio according to the audio frequency, splice the sub-audios according to the order of the characters in the first random code to obtain a verification audio, and play the verification audio; the verification audio is an ultrasonic audio; a second audio collection module configured to collect the played verification audio and upload the verification audio to the server, so that the server decodes the verification audio according to a decoding manner agreed with the smart glasses in advance to obtain the first random code, and determines whether the user passes the identity authentication by comparing the consistency of the first random code and the second random code.

5. A smart glasses comprising the identity authentication device of claim 4.

6. A smart eyewear system, comprising: a smart glasses and a smart terminal; the smart glasses are configured to, in response to a user's identity verification request, obtain a current timestamp T1, initiate a random code generation request to the smart terminal, and at the same time, initiate an identity verification request to the server and carry a timestamp T2 in the identity verification request, T2=T1, to trigger the server to generate a second random code according to T2 using a random code generation algorithm; the smart terminal is configured to, in response to the random code generation request, generate a first random code according to T1 using a random code generation algorithm, and randomly assign an audio frequency to each character in the first random code, generate a sub-audio according to the audio frequency, splice the sub-audios according to the order of the characters in the first random code to obtain a verification audio, and play the verification audio; the verification audio is an ultrasonic audio; the smart glasses are also configured to collect the verification audio played by the smart terminal and upload the verification audio to the server, so that the server decodes the verification audio according to a decoding manner agreed with the smart glasses in advance to obtain the first random code, and determines whether the user passes the identity authentication by comparing the consistency of the first random code and the second random code.

Images