Identity identification method, identity identification device, electronic equipment and storage medium

Abstract

This application discloses an identity recognition method, an identity recognition device, an electronic device, and a storage medium. The identity recognition method includes acquiring user information of a user logging into a virtual scene; acquiring an identity identifier corresponding to the user information when the user information is successfully verified; acquiring the user's verification audio information; encoding the identity identifier into the verification audio information to obtain encoded audio information; and sending the encoded audio information to the verification platform of the virtual scene, so that the verification platform can recognize the user's identity based on the identity identifier carried in the encoded audio information. This method enables the verification platform of the virtual scene to recognize the user's identity based on the identity identifier carried in the encoded audio information, which avoids the low success rate of user identity recognition caused by the verification platform of the virtual scene relying on voice identity recognition based on encoded audio information, thus improving the success rate of user identity recognition in virtual scenes.

Description

Technical Field

[0001] This application relates to the field of identity recognition technology, and more specifically, to an identity recognition method, an identity recognition device, an electronic device, and a storage medium. Background Technology

[0002] Virtual Reality (VR) technology is a brand-new practical technology that emerged in the 20th century. VR technology encompasses computer science, electronic information, and simulation technology. Its basic implementation method is to use computers to simulate virtual scenes (e.g., the metaverse) to give people a sense of immersion in the environment.

[0003] In virtual environments, users can perform various activities just like in the real world, and even transcend the real world itself. However, the need for user identification still exists in virtual environments, such as voice identification.

[0004] However, in virtual environments, in order to protect user privacy, the voices emitted by users are all altered. When it is necessary to perform voice identification on users, it is impossible to identify users based on their voices, resulting in a low success rate for user identification in virtual environments. Summary of the Invention

[0005] In view of the above problems, this application proposes an identity recognition method, identity recognition device, electronic device and storage medium, which enables the verification platform in a virtual scene to recognize the user's identity based on the identity identifier carried by the encoded audio information. This avoids the low success rate of user identity recognition caused by the verification platform in the virtual scene relying on voice identity recognition based on the encoded audio information, and improves the success rate of user identity recognition in the virtual scene.

[0006] In a first aspect, embodiments of this application provide an identity recognition method, comprising: obtaining user information of a user logging into a virtual scene; when the user information is successfully verified, obtaining an identity identifier corresponding to the user information; obtaining the user's verification audio information; encoding the identity identifier into the verification audio information to obtain encoded audio information; and sending the encoded audio information to the verification platform of the virtual scene, so that the verification platform can recognize the user's identity based on the identity identifier carried in the encoded audio information.

[0007] Secondly, embodiments of this application provide an identity recognition device, including a first acquisition module, a second acquisition module, a third acquisition module, an encoding module, and a sending module. The first acquisition module is used to acquire user information of a user logging into a virtual scene; the second acquisition module is used to acquire an identity identifier corresponding to the user information when the user information is successfully verified; the third acquisition module is used to acquire the user's verification audio information; the encoding module is used to encode the identity identifier into the verification audio information to obtain encoded audio information; and the sending module is used to send the encoded audio information to the verification platform of the virtual scene, so that the verification platform can identify the user's identity based on the identity identifier carried in the encoded audio information.

[0008] Thirdly, embodiments of this application provide an electronic device including a memory; one or more processors coupled to the memory; and one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more application programs are configured to perform the identity recognition method as provided in the first aspect above.

[0009] Fourthly, embodiments of this application provide a computer-readable storage medium storing program code, which can be invoked by a processor to execute the identity recognition method provided in the first aspect above.

[0010] The solution provided in this application obtains user information when logging into a virtual scene. When the user information is successfully verified, it obtains the identity identifier corresponding to the user information and the user's verification audio information. The identity identifier is encoded into the verification audio information, and the encoded audio information is sent to the verification platform of the virtual scene. This allows the verification platform to identify the user based on the identity identifier carried in the encoded audio information. This solution enables the verification platform of the virtual scene to identify the user based on the identity identifier carried in the encoded audio information, avoiding the low success rate of user identification caused by the verification platform of the virtual scene relying on voice identification based on encoded audio information. This improves the success rate of user identification in the virtual scene. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This illustration shows a scenario diagram of the identity recognition system provided in an embodiment of this application.

[0013] Figure 2 A flowchart illustrating an identity recognition method provided in an embodiment of this application is shown.

[0014] Figure 3 This illustration shows another flowchart of the identity recognition method provided in an embodiment of this application.

[0015] Figure 4 A structural block diagram of an identity recognition device provided in an embodiment of this application is shown.

[0016] Figure 5 A structural block diagram of an electronic device provided in an embodiment of this application is shown.

[0017] Figure 6 This application illustrates a computer-readable storage medium for storing or carrying program code that implements the identity recognition method provided in the embodiments of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0019] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0020] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0021] In the description of this application, it should be noted that the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0022] Virtual Reality (VR) technology is a brand-new practical technology that emerged in the 20th century. VR technology encompasses computer science, electronic information, and simulation technology. Its basic implementation method is to use computers to simulate virtual scenes (e.g., the metaverse) to give people a sense of immersion in the environment.

[0023] In virtual environments, users still perceive the world through their senses, such as sight and hearing, which are the same as in the physical world. Furthermore, the need for user identification still exists in virtual environments, such as voice identification.

[0024] However, in virtual environments, in order to protect user privacy, the voices emitted by users are all altered. When it is necessary to perform voice identification on users, it is impossible to identify users based on their voices, resulting in a low success rate for user identification in virtual environments.

[0025] To address the aforementioned issues, the inventors, after extensive research, proposed the identity recognition method, identity recognition device, electronic device, and storage medium provided in the embodiments of this application. This enables the verification platform in a virtual scene to recognize users' identities based on the identity identifier carried by the encoded audio information. This avoids the low success rate of user identity recognition caused by the verification platform in the virtual scene relying on voice identity recognition based on encoded audio information, thereby improving the success rate of user identity recognition in virtual scenes.

[0026] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0027] Please see Figure 1 This illustration shows an application scenario diagram of the identity recognition system provided in the embodiments of this application, which may include a terminal device 100. The terminal device 100 can be used to collect user information of users logging into virtual scenarios. The user information may include voiceprint information, fingerprint information, face information, iris information, and ID card information, etc.

[0028] Terminal device 100 can be a head-mounted display device, mobile phone, PDA (Personal Digital Assistant), tablet PC (Tablet Personal Computer), laptop computer, smartwatch, smart bracelet, etc.

[0029] The terminal device 100 may include an information acquisition module 110, a processor 120, a display device 130, and a memory 140. The information acquisition module 110, the display device 130, and the memory 140 are all connected to the processor 120.

[0030] The information collection module 110 can be used to collect user information and send the collected user information to the processor 120. The information collection module 110 may include a voiceprint collection module, a fingerprint collection module, a face image collection module, an iris collection module, and an ID card information collection module, etc. The type of information collection module 110 is not limited here, and it can be set according to actual needs.

[0031] The processor 120 can be used to generate a virtual scene 200 (e.g., a metaverse verification platform), and can generate scene data corresponding to the virtual scene 200 (e.g., identity recognition data of the metaverse verification platform) based on the user information collected by the information acquisition module 110, input the scene data into the corresponding virtual scene 200, and send the virtual scene 200 to the display device 130.

[0032] Processor 120 may include any suitable type of general-purpose microprocessor, general-purpose digital signal processor, special-purpose microprocessor, special-purpose digital signal processor, or microcontroller. Processor 120 may be configured to receive data and / or signals sent by information acquisition module 110; processor 120 may also be configured to receive data and / or signals from various components of the system via, for example, a network; processor 120 may also process data and / or signals to determine one or more operating conditions in the system.

[0033] For example, the processor 120 can generate identity recognition data for the verification platform of the virtual scene 200 based on the user information received from the information acquisition module 110, and input the identity recognition data into the generated verification platform of the virtual scene 200; the processor 120 can also generate identity recognition data for the verification platform of the virtual scene 200 based on pre-stored user information, and input the identity recognition data into the verification platform of the virtual scene 200; the processor 120 can also receive user data sent by a smart terminal or computer through a network, generate identity recognition data for the verification platform of the virtual scene 200 based on the received user information, and input the identity recognition data into the verification platform of the virtual scene 200.

[0034] The network can be ZigBee, Bluetooth (BT), Wi-Fi, Thread, LoRa, Low-Power Wide-Area Network (LPWAN), infrared, Narrow Band Internet of Things (NB-IoT), Controller Area Network (CAN), Digital Living Network Alliance (DLNA), Wide Area Network (WAN), Local Area Network (LAN), Metropolitan Area Network (MAN), and Wireless Personal Area Network (WPAN), etc.

[0035] The display device 130 can be used to receive the virtual scene 200 sent by the processor 120 and display the received virtual scene 200.

[0036] The memory 140 can be used to store software programs and modules. The processor 120 executes various functional applications and data processing by running the software programs and modules stored in the memory 140. The memory 140 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.

[0037] The display device 130 and information acquisition module 110 of the terminal device 100 can be connected to a smart device having a storage function of a memory 140 and a processing function of a processor 120. It is understood that the processing performed by the processor 120 in the above embodiment is performed by the processor 120 of the smart device, and the data stored in the memory 140 in the above embodiment is stored in the memory 140 of the smart device.

[0038] In this embodiment, the terminal device 100 may further include a communication module, which can be communicatively connected to the processor 120. The communication module can be used for communication between the terminal device 100 and other terminals.

[0039] Please see Figure 2The diagram illustrates a flowchart of an identity recognition method provided in one embodiment of this application. In specific embodiments, the identity recognition method can be applied to, for example... Figure 1 The terminal device 100 in the identity recognition system shown below will be used as an example to illustrate the following. Figure 2 The process shown is described in detail. The identity recognition method may include steps S110 to S150.

[0040] Step S110: Obtain user information for the user logging into the virtual scene.

[0041] In this embodiment, virtual users in the virtual scene are one-to-one bound to users in the real world. Users can create corresponding virtual users in the virtual scene using user information. The terminal device may include an information collection module. When a user logs into the virtual scene using the terminal device, the information collection module can obtain the user information of the user who logged into the virtual scene. The user information may include voiceprint information, fingerprint information, facial information, iris information, and ID card information, etc. The virtual scene can be a metaverse.

[0042] In some implementations, user information can be voiceprint information; the information acquisition module can be a voiceprint acquisition module, which can be used to collect the user's voice data and obtain the corresponding voiceprint information based on the collected voice data. The voiceprint acquisition module can detect the sound data of the surrounding environment of the terminal device. When it detects sound data containing login keywords (for example, sound data containing the keywords "login to virtual scene", or sound data containing the keywords "login" and "virtual scene"), it can collect the sound data and analyze the collected sound data to obtain the corresponding voiceprint information, which is the user's voiceprint information for logging into the virtual scene.

[0043] In some implementations, user information can be fingerprint information; the information acquisition module can be a fingerprint acquisition module, which can be used to acquire the user's fingerprint image and obtain the corresponding fingerprint information based on the acquired fingerprint image. When a user logs into a virtual scene, they can input a fingerprint image into the fingerprint acquisition module. The fingerprint acquisition module can acquire the fingerprint image input by the user and analyze the acquired fingerprint image to obtain the corresponding fingerprint information, which is the fingerprint information for the user to log into the virtual scene.

[0044] In some implementations, user information can be facial information; the information acquisition module can be a facial image acquisition module, which can be used to acquire the user's facial image and obtain the corresponding facial information based on the acquired facial image. When a user logs into the virtual scene, they can touch the facial image acquisition module. The facial image acquisition module responds to the user's touch, acquires the user's facial image, analyzes the acquired facial image, and obtains the corresponding facial information, which is the user's facial information for logging into the virtual scene.

[0045] In some implementations, user information can be iris information; the information acquisition module can be an iris acquisition module, which can be used to acquire the user's iris image and obtain the corresponding iris information based on the acquired iris image. When a user logs into the virtual scene, they can touch the iris acquisition module. The iris acquisition module responds to the user's touch, acquires the user's iris image, analyzes the acquired iris image, and obtains the corresponding iris information, which is the iris information of the user logging into the virtual scene.

[0046] In some implementations, user information can be ID card information; the information collection module can be an ID card information collection module equipped with a Radio Frequency Identification (RFID) chip, which can automatically read the ID card information from the ID card. When a user logs into the virtual scene, the user can place their ID card in the ID card information collection module, and the RFID chip will read the corresponding ID card information, which is the user's ID card information for logging into the virtual scene.

[0047] In some implementations, the terminal device may further include a processor and a memory. The processor is connected to the information acquisition module and the memory. The memory pre-stores pre-stored user information, which is associated with virtual users in the virtual scene. After acquiring user information for logging into the virtual scene, the information acquisition module can send the user information to the processor. The processor receives and responds to the user information, matches it with the pre-stored user information retrieved from the memory, obtains a matching degree, and determines whether the user is a preset user based on the matching degree, obtaining a determination result. Based on the determination result, it determines whether the user information verification is successful. The determination result includes a first result indicating that the user is a preset user and a second result indicating that the user is not a preset user.

[0048] When the information matching degree is greater than or equal to the information matching degree threshold, the first result is obtained and the user information verification is confirmed to be successful; when the information matching degree is less than the information matching degree threshold, the second result is obtained and the user information verification is confirmed to be failed.

[0049] In one implementation, user information can be voiceprint information, pre-stored user information can be pre-stored voiceprint information, information matching degree can be voiceprint matching degree, and information matching degree threshold can be voiceprint matching degree threshold. After acquiring the voiceprint information of the user logging into the virtual scene, the voiceprint acquisition module can send the voiceprint information to the processor. The processor receives and responds to the voiceprint information, matches the voiceprint information with the pre-stored voiceprint information retrieved from the memory, obtains the voiceprint matching degree, determines whether the user is a preset user based on the voiceprint matching degree, obtains the determination result, and determines whether the voiceprint information verification is successful based on the determination result.

[0050] When the voiceprint matching degree is greater than or equal to the voiceprint matching degree threshold, the first result is obtained and the voiceprint information verification is confirmed to be successful; when the voiceprint matching degree is less than the voiceprint matching degree threshold, the second result is obtained and the voiceprint information verification is confirmed to be unsuccessful.

[0051] In one implementation, user information can be fingerprint information, pre-stored user information can be pre-stored fingerprint information, information matching degree can be fingerprint matching degree, and information matching degree threshold can be fingerprint matching degree threshold. After acquiring the fingerprint information of the user logging into the virtual scene, the fingerprint acquisition module can send the fingerprint information to the processor. The processor receives and responds to the fingerprint information, matches the fingerprint information with the pre-stored fingerprint information obtained from the memory, obtains the fingerprint matching degree, determines whether the user is the preset user based on the fingerprint matching degree, obtains the determination result, and determines whether the fingerprint information verification is successful based on the determination result.

[0052] When the fingerprint matching degree is greater than or equal to the fingerprint matching degree threshold, the first result is obtained, and the fingerprint information is confirmed to be successfully verified; when the fingerprint matching degree is less than the fingerprint matching degree threshold, the second result is obtained, and the fingerprint information is confirmed to be unverified.

[0053] In one implementation, user information can be facial information, pre-stored user information can be pre-stored facial information, information matching degree can be facial matching degree, and information matching degree threshold can be facial matching degree threshold. After acquiring the facial information of the user logging into the virtual scene, the facial image acquisition module can send the facial information to the processor. The processor receives and responds to the facial information, matches the facial information with the pre-stored facial information retrieved from the memory, obtains the facial matching degree, and determines whether the user is the preset user based on the facial matching degree, obtains the determination result, and determines whether the facial information verification is successful based on the determination result.

[0054] When the face matching degree is greater than or equal to the face matching degree threshold, the first result is obtained, and the face information verification is confirmed to be successful; when the face matching degree is less than the face matching degree threshold, the second result is obtained, and the face information verification is confirmed to be unsuccessful.

[0055] In one implementation, user information can be iris information, pre-stored user information can be pre-stored iris information, information matching degree can be iris matching degree, and information matching degree threshold can be iris matching degree threshold. After acquiring the iris information of the user logging into the virtual scene, the iris acquisition module can send the iris information to the processor. The processor receives and responds to the iris information, matches the iris information with the pre-stored iris information retrieved from the memory, obtains the iris matching degree, determines whether the user is the preset user based on the iris matching degree, obtains the determination result, and determines whether the iris information verification is successful based on the determination result.

[0056] When the iris matching degree is greater than or equal to the iris matching degree threshold, the first result is obtained, and the iris information verification is confirmed to be successful; when the iris matching degree is less than the iris matching degree threshold, the second result is obtained, and the iris information verification is confirmed to be unsuccessful.

[0057] In one implementation, user information can be ID card information, pre-stored user information can be pre-stored ID card information, information matching degree can be ID card information matching degree, and information matching degree threshold can be ID card information matching degree threshold. After obtaining the ID card information of the user logging into the virtual scene, the ID card information collection module can send the ID card information to the processor. The processor receives and responds to the ID card information, matches the ID card information with the pre-stored ID card information obtained from the memory, obtains the ID card information matching degree, determines whether the user is the preset user based on the ID card information matching degree, obtains the determination result, and determines whether the ID card information verification is successful based on the determination result.

[0058] When the matching degree of the ID card information is greater than or equal to the ID card information matching degree threshold, the first result is obtained and the ID card information verification is confirmed to be successful; when the matching degree of the ID card information is less than the ID card information matching degree threshold, the second result is obtained and the ID card information verification is confirmed to be failed.

[0059] Step S120: When the user information is successfully verified, obtain the identity identifier corresponding to the user information.

[0060] In this embodiment, the memory pre-stores identity identifiers associated with a preset user. The processor can verify the user information based on the user information. When the user information is successfully verified, it indicates that the user is the preset user, and an identity identifier retrieval instruction corresponding to the preset user can be sent to the memory. The memory receives and responds to the identity identifier retrieval instruction, sending the pre-stored identity identifier associated with the preset user to the processor. The processor receives the identity identifier returned by the memory and uses it as the identity identifier corresponding to the user information. The identity identifier may include voiceprint encoding, fingerprint encoding, face encoding, iris encoding, and ID card encoding, etc.

[0061] In some implementations, user information can be voiceprint information, identity identifier can be voiceprint encoding, and identity identifier acquisition instruction can be voiceprint encoding acquisition instruction. The processor can perform voiceprint recognition on the user based on the voiceprint information to obtain the voiceprint recognition result. When the user is determined to be a preset user based on the voiceprint recognition result, the processor can send the voiceprint encoding acquisition instruction corresponding to the preset user to the memory. The memory receives and responds to the voiceprint encoding acquisition instruction, and sends the pre-stored voiceprint encoding associated with the preset user to the processor. The processor receives the voiceprint encoding returned by the memory and uses it as the voiceprint encoding corresponding to the voiceprint information.

[0062] In some implementations, user information can be fingerprint information, identity identification can be fingerprint code, and identity identification acquisition instruction can be fingerprint code acquisition instruction. The processor can perform fingerprint recognition on the user based on the fingerprint information, obtain the fingerprint recognition result, and when the user is determined to be a preset user based on the fingerprint recognition result, it can send a fingerprint code acquisition instruction corresponding to the preset user to the memory. The memory receives and responds to the fingerprint code acquisition instruction, and sends the pre-stored fingerprint code associated with the preset user to the processor. The processor receives the fingerprint code returned by the memory and uses it as the fingerprint code corresponding to the fingerprint information.

[0063] In some implementations, user information can be facial information, identity identifier can be a face code, and identity identifier acquisition instruction can be a face code acquisition instruction. The processor can perform facial recognition on the user based on the facial information, obtain the facial recognition result, and when the user is determined to be a preset user based on the facial recognition result, it can send a face code acquisition instruction corresponding to the preset user to the memory. The memory receives and responds to the face code acquisition instruction, sending the pre-stored face code associated with the preset user to the processor. The processor receives the face code returned by the memory and uses it as the face code corresponding to the facial information.

[0064] In some implementations, user information can be iris information, identity identification can be iris encoding, and identity identification acquisition instructions can be iris encoding acquisition instructions. The processor can perform iris recognition on the user based on the iris information to obtain the iris recognition result. When the iris recognition result determines that the user is a preset user, it can send an iris encoding acquisition instruction corresponding to the preset user to the memory. The memory receives and responds to the iris encoding acquisition instruction, sending the pre-stored iris encoding associated with the preset user to the processor. The processor receives the iris encoding returned by the memory and uses it as the iris encoding corresponding to the iris information.

[0065] In some implementations, user information can be ID card information, identity identifier can be ID card code, and identity identifier acquisition instruction can be ID card code acquisition instruction. The processor can perform ID card recognition on the user based on the ID card information, obtain ID card recognition result, and when the user is determined to be a preset user based on the ID card recognition result, it can send an ID card code acquisition instruction corresponding to the preset user to the memory. The memory receives and responds to the ID card code acquisition instruction, and sends the pre-stored ID card code associated with the preset user to the processor. The processor receives the ID card code returned by the memory and uses it as the ID card code corresponding to the ID card information.

[0066] Step S130: Obtain the user's verification audio information.

[0067] In this embodiment of the application, when the verification platform in the virtual scene needs to perform voice identity recognition on the user, the processor can obtain the user's verification audio information. The verification audio information is the audio information obtained by changing the voice of the verification information input by the user. This can avoid the leakage of user privacy when using the verification audio information corresponding to the user's voiceprint information to perform voice identity recognition on the verification platform in the virtual scene, thereby improving the protection of user privacy in the virtual scene.

[0068] Specifically, the processor can send a prompt message to the user's associated designated terminal to prompt the user to send the corresponding verification information to the information collection module. When the user sends the verification information to the information collection module, the information collection module receives and responds to the verification information and sends the verification information to the processor. The processor receives and responds to the verification information and converts the verification information into corresponding verification audio information. The verification information may include voice verification information and text verification information. The verification audio information is the audio information corresponding to preset voiceprint information that is different from the user's voiceprint information.

[0069] The specified terminal can be a mobile terminal (e.g., mobile phone, PDA, tablet PC, laptop, smartwatch, smart bracelet, etc.) or a fixed terminal (e.g., desktop computer, projector, smart TV, smart control panel, etc.), etc., without limitation.

[0070] In some implementations, the verification information can be voice verification information, the prompt information can be voice verification prompt information, the information acquisition module can be a voiceprint acquisition module, the voiceprint acquisition module can be used to acquire the voice verification information issued by the user, and the memory stores a pre-trained audio conversion model, which can be used to convert the voice verification information into verification audio information corresponding to the preset voiceprint information.

[0071] The processor can send voice verification prompts to the user's associated designated terminal to prompt the user to send the corresponding voice verification information to the voiceprint acquisition module. When the user issues voice verification information within the perception range of the voiceprint acquisition module, the voiceprint acquisition module can collect the voice verification information issued by the user and send the collected voice verification information to the processor. The processor receives and responds to the voice verification information, inputs the voice verification information into the audio conversion model obtained from the memory, the audio conversion model receives and responds to the voice verification information, converts the voice verification information into verification audio information corresponding to the preset voiceprint information, and outputs the verification audio information to the processor. The processor receives the verification audio information output by the audio conversion model.

[0072] The audio conversion model can be a Convolutional Neural Network (CNN) model, a Deep Belief Network (DBN) model, a Stacked Auto Encoder Network (SAE) model, a Recurrent Neural Network (RNN) model, a Deep Neural Network (DNN) model, a Long Short-Term Memory (LSTM) network model, or a Gated Recurring Unit (GRU) model, etc. The type of audio conversion model is not limited here, and can be set according to actual needs.

[0073] In some implementations, the verification information can be voice verification information, the prompt information can be voice verification prompt information, the information acquisition module can be a voiceprint acquisition module, the voiceprint acquisition module can be used to collect the voice verification information issued by the user, and the memory pre-stores preset voiceprint information.

[0074] The processor can send voice verification prompts to the user's associated designated terminal to prompt the user to send the corresponding voice verification information to the voiceprint acquisition module. When the user issues voice verification information within the perception range of the voiceprint acquisition module, the voiceprint acquisition module can collect the voice verification information issued by the user and send the collected voice verification information to the processor. The processor receives and responds to the voice verification information, analyzes the voice verification information to obtain the corresponding text verification information, and synthesizes the preset voiceprint information obtained from the memory with the text verification information to obtain the corresponding verification audio information.

[0075] In some implementations, the verification information can be text verification information, the prompt information can be text verification prompt information, the information acquisition module can be a text acquisition module, the text acquisition module can be used to acquire the text verification information input by the user, and the memory stores a pre-trained audio conversion model, the audio conversion model can be used to convert the text verification information into verification audio information corresponding to the preset voiceprint information.

[0076] The processor can send text verification prompts to the user's associated designated terminal to prompt the user to input the corresponding text verification information in the text acquisition module. When the user inputs text verification information in the text acquisition module (for example, by pressing a button on the operation panel of the text acquisition module or by handwriting on the operation panel of the text acquisition module), the text acquisition module can acquire the text verification information input by the user and send the acquired text verification information to the processor. The processor receives and responds to the text verification information, inputs the text verification information into the audio conversion model obtained from the memory, the audio conversion model receives and responds to the text verification information, converts the text verification information into verification audio information corresponding to the preset voiceprint information, and outputs the verification audio information to the processor. The processor receives the verification audio information output by the audio conversion model.

[0077] Step S140: Encode the identity identifier into the verification audio information to obtain the encoded audio information.

[0078] In this embodiment of the application, in order to protect the user privacy in the virtual scene, the verification audio information obtained by the processor is audio information that has been processed by voice changing, which makes it impossible for the verification platform of the virtual scene to identify the user based on the verification audio information. Therefore, the processor can encode the identity identifier into the verification audio information to obtain the corresponding encoded audio information, so that the verification platform can identify the user based on the encoded audio information, thereby improving the success rate of the verification platform of the virtual scene in identifying the user.

[0079] In some implementations, the processor can analyze the verification audio information to obtain a preset frequency band for the verification audio information, and encode the identity identifier into the preset frequency band for the verification audio information to obtain encoded audio information. The preset frequency band can be a frequency range outside the human hearing range (20 Hz - 20000 Hz), for example, 0-20 Hz; the preset frequency band can also be a frequency range within the human hearing range, for example, 100-200 Hz, etc., and is not limited here.

[0080] Specifically, the processor can analyze the verification audio information, obtain the preset frequency band of the verification audio information, and divide the preset frequency band into multiple frequency ranges corresponding to the number of identification bits of the identity identifier according to the number of identification bits of the identity identifier. Each frequency range corresponds to an identification code of the identity identifier, and the amplitude value corresponding to each frequency range is updated to the identification code of the corresponding identity identifier to obtain the encoded audio information.

[0081] In one implementation, the identity identifier can be a voiceprint code, the identifier bit length can be the same as the voiceprint code bit length, and the identifier code can be a voiceprint identifier code. The processor can divide a preset frequency band into multiple frequency ranges corresponding to the voiceprint code bit length, with each frequency range corresponding to a voiceprint identifier code, and update the amplitude value corresponding to each frequency range to the corresponding voiceprint identifier code, thereby obtaining encoded audio information.

[0082] In one implementation, the identification can be a fingerprint code, the number of digits can be the number of digits in the fingerprint code, and the identification code can be the fingerprint identification code. The processor can divide a preset frequency band into multiple frequency ranges corresponding to the number of digits in the fingerprint code, with each frequency range corresponding to a fingerprint identification code, and update the amplitude value corresponding to each frequency range to the fingerprint identification code of the corresponding fingerprint code, thereby obtaining encoded audio information.

[0083] In one implementation, the identity identifier can be a face code, the identifier length can be the face code length, and the identifier code is a face identifier code. The processor can divide a preset frequency band into multiple frequency ranges corresponding to the face code length, each frequency range corresponding to a face identifier code, and update the amplitude value corresponding to each frequency range to the corresponding face identifier code, thereby obtaining encoded audio information.

[0084] In one implementation, the identification can be an iris code, the number of digits of the identification can be the same as the number of iris codes, and the identification code can be an iris identification code. The processor can divide a preset frequency band into multiple frequency ranges corresponding to the number of iris codes, each frequency range corresponding to an iris identification code, and update the amplitude value corresponding to each frequency range to the corresponding iris identification code, thereby obtaining encoded audio information.

[0085] In one implementation, the identification identifier can be an ID card code, the identifier length can be the same as the ID card code length, and the identifier code can be the ID card identifier code. The processor can divide a preset frequency band into multiple frequency ranges corresponding to the ID card code length, with each frequency range corresponding to an ID card identifier code, and update the amplitude value corresponding to each frequency range to the corresponding ID card identifier code, thereby obtaining encoded audio information.

[0086] In some implementations, the audio conversion model can also be used to convert an identity identifier into identifier audio information corresponding to preset voiceprint information. The processor can input the identity identifier into the audio conversion model retrieved from memory. The audio conversion model receives and responds to the identity identifier, converts the identity identifier into identifier audio information corresponding to preset voiceprint information, and outputs the identifier audio information to the processor. The processor receives the identifier audio information output by the audio conversion model and fuses the identifier audio information with the verification audio information to generate corresponding encoded audio information.

[0087] In one implementation, the identity identifier can be a voiceprint encoding, and the identifier audio information can be first identifier audio information. The audio conversion model can also be used to convert the voiceprint encoding into first identifier audio information corresponding to preset voiceprint information. The processor can input the voiceprint encoding into the audio conversion model obtained from the memory. The audio conversion model receives and responds to the voiceprint encoding, converts the voiceprint encoding into first identifier audio information of preset voiceprint information, and outputs the first identifier audio information to the processor. The processor receives the first identifier audio information output by the audio conversion model and fuses the first identifier audio information with the verification audio information to generate corresponding encoded audio information.

[0088] In one implementation, the identification identifier can be a fingerprint code, and the identification audio information can be second identification audio information. The audio conversion model can also be used to convert the fingerprint code into second identification audio information corresponding to preset voiceprint information. The processor can input the fingerprint code into the audio conversion model obtained from the memory. The audio conversion model receives and responds to the fingerprint code, converts the fingerprint code into second identification audio information of preset voiceprint information, and outputs the second identification audio information to the processor. The processor receives the second identification audio information output by the audio conversion model and fuses the second identification audio information with the verification audio information to generate corresponding encoded audio information.

[0089] In one implementation, the identity identifier can be a face code, and the identifier audio information can be third identifier audio information. The audio conversion model can also be used to convert the face code into third identifier audio information corresponding to preset voiceprint information. The processor can input the face code into the audio conversion model obtained from the memory. The audio conversion model receives and responds to the face code, converts the face code into third identifier audio information of preset voiceprint information, and outputs the third identifier audio information to the processor. The processor receives the third identifier audio information output by the audio conversion model and fuses the third identifier audio information with the verification audio information to generate the corresponding encoded audio information.

[0090] In one implementation, the identity identifier can be an iris code, and the identifier audio information can be fourth identifier audio information. The audio conversion model can also be used to convert the iris code into fourth identifier audio information corresponding to preset voiceprint information. The processor can input the iris code into the audio conversion model retrieved from memory. The audio conversion model receives and responds to the iris code, converts the iris code into fourth identifier audio information of preset voiceprint information, and outputs the fourth identifier audio information to the processor. The processor receives the fourth identifier audio information output by the audio conversion model and fuses the fourth identifier audio information with the verification audio information to generate the corresponding encoded audio information.

[0091] In one implementation, the identity identifier can be an ID card code, and the identifier audio information can be fifth identifier audio information. The audio conversion model can also be used to convert the ID card code into fifth identifier audio information corresponding to preset voiceprint information. The processor can input the ID card code into the audio conversion model obtained from the memory. The audio conversion model receives and responds to the ID card code, converts the ID card code into fifth identifier audio information of preset voiceprint information, and outputs the fifth identifier audio information to the processor. The processor receives the fifth identifier audio information output by the audio conversion model and merges the fifth identifier audio information with the verification audio information to generate the corresponding encoded audio information.

[0092] In one application scenario, the identification can be a national ID card code, for example: 14092374801237463718. The ID card code has 20 digits, and the preset frequency band can be 20Hz. The processor can divide the preset frequency band into 20 frequency ranges based on the 20-digit ID card code: 0-1Hz, 1-2Hz, 2-3Hz, 3-4Hz, 4-5Hz, 5-6Hz, 6-7Hz, 7-8Hz, 8-9Hz, 9-10Hz, 10-11Hz, 11-12Hz, 12-13Hz, 13-14Hz, 14-15Hz, 15-16Hz, 16-17Hz, 17-18Hz, 18-19Hz, and 19-20Hz. The order of these frequency ranges corresponds to the order of the ID card identification code. The processor can update the amplitude value corresponding to each frequency range to the corresponding ID card identification code in the following manner to obtain the encoded audio information.

[0093] Update the amplitude value corresponding to the 0-1Hz frequency range to 1;

[0094] Update the amplitude value corresponding to the 1-2Hz frequency range to 4;

[0095] Update the amplitude value corresponding to the 2-3Hz frequency range to 0;

[0096] Update the amplitude value corresponding to the 3-4Hz frequency range to 9;

[0097] Update the amplitude value corresponding to the 4-5Hz frequency range to 2;

[0098] Update the amplitude value corresponding to the 5-6Hz frequency range to 3;

[0099] Update the amplitude value corresponding to the 6-7Hz frequency range to 7;

[0100] Update the amplitude value corresponding to the 7-8Hz frequency range to 4;

[0101] Update the amplitude value corresponding to the 8-9Hz frequency range to 8;

[0102] Update the amplitude value corresponding to the 9-10Hz frequency range to 0;

[0103] Update the amplitude value corresponding to the 10-11Hz frequency range to 1;

[0104] Update the amplitude value corresponding to the 11-12Hz frequency range to 2;

[0105] Update the amplitude value corresponding to the 12-13Hz frequency range to 3;

[0106] Update the amplitude value corresponding to the 13-14Hz frequency range to 7;

[0107] Update the amplitude value corresponding to the 14-15Hz frequency range to 4;

[0108] Update the amplitude value corresponding to the 15-16Hz frequency range to 6;

[0109] Update the amplitude value corresponding to the 16-17Hz frequency range to 3;

[0110] Update the amplitude value corresponding to the 17-18Hz frequency range to 7;

[0111] Update the amplitude value corresponding to the 18-19Hz frequency range to 1;

[0112] Update the amplitude value corresponding to the 19-20Hz frequency range to 8.

[0113] Step S150: Send the encoded audio information to the verification platform of the virtual scene so that the verification platform can identify the user based on the identity identifier carried in the encoded audio information.

[0114] In this embodiment, after encoding the identity identifier into the verification audio information, the processor can send the encoded audio information to the verification platform of the virtual scene. The verification platform of the virtual scene receives and responds to the encoded audio information, decodes the encoded audio information to obtain the corresponding identity identifier, and matches the identity identifier with the pre-stored identity identifier to obtain the identity identifier matching degree. Based on the identity identifier matching degree, it can determine whether the user's identity recognition is successful. This realizes that the verification platform of the virtual scene can recognize the user's identity based on the identity identifier carried in the encoded audio information, which can avoid the low recognition success rate of the user's identity recognition caused by the verification platform of the virtual scene performing voice identity recognition based on the encoded audio information, and improve the recognition success rate of the user's identity recognition in the virtual scene.

[0115] When the identity matching degree is greater than or equal to the identity matching degree threshold, the user's identity is determined to be successfully identified; when the identity matching degree is less than the identity matching degree threshold, the user's identity is determined to be unidentified.

[0116] The solution provided in this application obtains user information when logging into a virtual scene. When the user information is successfully verified, it obtains the identity identifier corresponding to the user information and the user's verification audio information. The identity identifier is encoded into the verification audio information, and the encoded audio information is sent to the verification platform of the virtual scene. This allows the verification platform to identify the user based on the identity identifier carried in the encoded audio information. This solution enables the verification platform of the virtual scene to identify the user based on the identity identifier carried in the encoded audio information, avoiding the low success rate of user identification caused by the verification platform of the virtual scene relying on voice identification based on encoded audio information. This improves the success rate of user identification in the virtual scene.

[0117] Please see Figure 3 This illustrates a flowchart of an identity recognition method provided in another embodiment of this application. In specific embodiments, the identity recognition method can be applied to, for example... Figure 1 The terminal device 100 in the identity recognition system shown below will be used as an example to illustrate the following. Figure 3 The process shown is described in detail, and the identity recognition method may include steps S210 to S280.

[0118] Step S210: Obtain user information for the user logging into the virtual scene.

[0119] Step S220: When the user information is successfully verified, obtain the identity identifier corresponding to the user information.

[0120] Step S230: Obtain the voice verification information input by the user.

[0121] In this embodiment, steps S210, S220 and S230 can be referred to the corresponding steps in the foregoing embodiments, and will not be repeated here.

[0122] Step S240: Determine if a pre-trained audio conversion model exists.

[0123] In this embodiment, after obtaining the user-input voice verification information, the processor can determine whether a pre-trained audio conversion model exists. Specifically, the processor can analyze the voice verification information to obtain the corresponding voice information, match the voice information with a pre-stored conversion model to obtain the model matching degree, and determine whether a pre-trained audio conversion model exists based on the model matching degree. The voice information may include at least one of timbre information, speech rate information, and pause duration.

[0124] If the model matching degree is greater than or equal to the model matching degree threshold, it is determined that a pre-trained audio conversion model exists, and the pre-stored conversion model corresponding to the model matching degree is identified as the audio conversion model; if the model matching degree is less than the model matching degree threshold, it is determined that no pre-trained audio conversion model exists.

[0125] The pre-stored conversion model can be a Convolutional Neural Network (CNN) model, a Deep Belief Network (DBN) model, a Stacked AutoEncoder Network (SAE) model, a Recurrent Neural Network (RNN) model, a Deep Neural Network (DNN) model, a Long Short-Term Memory (LSTM) network model, or a Gated Recurring Unit (GRU) model, etc. The type of pre-stored conversion model is not limited here, and can be set according to actual needs.

[0126] In some implementations, the speech information can be timbre information, the model matching degree can be timbre matching degree, and the model matching degree threshold can be timbre matching degree threshold. The processor can analyze the speech verification information to obtain timbre information, match the timbre information with a pre-stored conversion model to obtain timbre matching degree, and determine whether a pre-trained audio conversion model exists based on the timbre matching degree. When the timbre matching degree is greater than or equal to the timbre matching degree threshold, it is determined that a pre-trained audio conversion model exists, and the pre-stored conversion model corresponding to the timbre matching degree is identified as the audio conversion model; when the timbre matching degree is less than the timbre matching degree threshold, it is determined that no pre-trained audio conversion model exists.

[0127] In some implementations, the speech information can be timbre information, speech rate information, and pause duration; the model matching degree can be the speech matching degree; and the model matching degree threshold can be the speech matching degree threshold. The processor can analyze the speech verification information to obtain timbre information, speech rate information, and pause duration, and match the timbre information, speech rate information, and pause duration with a pre-stored conversion model to obtain the speech matching degree. Based on the speech matching degree, it can determine whether a pre-trained audio conversion model exists. When the speech matching degree is greater than or equal to the speech matching degree threshold, it is determined that a pre-trained audio conversion model exists, and the pre-stored conversion model corresponding to that speech matching degree is identified as the audio conversion model. When the speech matching degree is less than the speech matching degree threshold, it is determined that no pre-trained audio conversion model exists.

[0128] Step S250: When it is determined that there is no pre-trained audio conversion model, obtain the target text information corresponding to the speech verification information.

[0129] In this embodiment, when the processor determines that there is no pre-trained audio conversion model, it can match the voice verification information with the pre-stored sound information to obtain the pre-stored sound information that matches the voice verification information, and obtain the pre-stored text information corresponding to the pre-stored sound information that matches the voice verification information. The pre-stored text information can be used as the target text information corresponding to the voice verification request, thereby realizing the sound matching of the voice verification information and ensuring the accuracy of the voice verification information.

[0130] The sound information can include timbre information and pitch information; the pre-stored sound information can be pre-stored sound information associated with timbre information and pitch information, such as Mandarin sound information, dialect sound information, English sound information, etc.; the type of sound information and pre-stored sound information is not limited here, and can be set according to actual needs.

[0131] Specifically, the processor can match the sound information with the pre-stored sound information to obtain the sound matching degree. When the sound matching degree is greater than or equal to the sound matching degree threshold, it determines that the pre-stored sound information corresponding to the sound matching degree is the pre-stored sound information that matches the voice verification information. It can also obtain the pre-stored text information corresponding to the pre-stored sound information and use the pre-stored text information as the target text information corresponding to the voice verification information.

[0132] Step S260: Synthesize preset voiceprint information and target text information to obtain verification audio information.

[0133] In this embodiment, the processor can synthesize preset voiceprint information and target text information to obtain corresponding verification audio information, thus ensuring the accuracy of the verification audio information.

[0134] Step S270: Encode the identity identifier into the verification audio information to obtain the encoded audio information.

[0135] Step S280: Send the encoded audio information to the verification platform of the virtual scene so that the verification platform can identify the user based on the identity identifier carried in the encoded audio information.

[0136] In this embodiment, steps S270 and S280 can be referred to the corresponding steps in the foregoing embodiments, and will not be repeated here.

[0137] The solution provided in this embodiment obtains user information when logging into a virtual scene. When the user information is successfully verified, it obtains the identity identifier corresponding to the user information and the user's input voice verification information. It then determines whether a pre-trained audio conversion model exists. If no pre-trained audio conversion model exists, it obtains the target text information corresponding to the voice verification information and synthesizes the preset voiceprint information and the target text information to obtain verification audio information. The identity identifier is encoded into the verification audio information, and the encoded audio information is sent to the verification platform of the virtual scene. This allows the verification platform to identify the user based on the identity identifier carried in the encoded audio information. This achieves user identification based on the identity identifier carried in the encoded audio information, avoiding the low success rate of user identification caused by voice identification based on encoded audio information in the virtual scene verification platform, thus improving the success rate of user identification in the virtual scene.

[0138] Furthermore, when it is determined that there is no pre-trained audio conversion model, the verification audio information is obtained by acquiring the target text corresponding to the voice verification information and synthesizing the preset voiceprint information and the target text information, thus ensuring the accuracy of the verification audio information and improving the user experience.

[0139] Please see Figure 4 This illustrates an embodiment of an identity recognition device 300 provided in this application, which can be applied to, for example... Figure 1 The terminal device 100 in the identity recognition system shown below will be used as an example to illustrate the following. Figure 4 The identity recognition device 300 shown will be described in detail. The identity recognition device 300 may include a first acquisition module 310, a second acquisition module 320, a third acquisition module 330, an encoding module 340, and a sending module 350.

[0140] The first acquisition module 310 can be used to acquire user information of the user who logs into the virtual scene; the second acquisition module 320 can be used to acquire the identity identifier corresponding to the user information when the user information is successfully verified; the third acquisition module 330 can be used to acquire the user's verification audio information; the encoding module 340 can be used to encode the identity identifier into the verification audio information to obtain the encoded audio information; the sending module 350 can be used to send the encoded audio information to the verification platform of the virtual scene so that the verification platform can identify the user's identity based on the identity identifier carried in the encoded audio information.

[0141] In some implementations, the encoding module 340 may include an analysis unit and an encoding unit update unit.

[0142] The analysis unit can be used to analyze the verification audio information and obtain the preset frequency band of the verification audio information; the encoding unit can be used to encode the identity identifier into the preset frequency band of the verification audio information and obtain the encoded audio information.

[0143] In some implementations, the encoding unit may include a partitioning subunit and an updating subunit.

[0144] The division subunit can be used to divide the preset frequency band into multiple frequency ranges corresponding to the number of identifier bits of the identity identifier, and each frequency range corresponds to an identifier code of the identity identifier; the update subunit can be used to update the amplitude value corresponding to each frequency range to the corresponding identifier code to obtain coded audio information.

[0145] In some implementations, the third acquisition module 330 may include a first acquisition unit and a conversion unit.

[0146] The first acquisition unit can be used to acquire user-input verification information, including voice verification information and / or text verification information; the conversion unit can be used to convert the verification information into verification audio information.

[0147] In some implementations, the verification information is voice verification information, and the conversion unit may include a first input subunit and a first receiving subunit.

[0148] The first input subunit can be used to input the voice verification information into a pre-trained audio conversion model, which converts the voice verification information into verification audio information corresponding to the preset voiceprint information; the first receiving subunit can be used to receive the verification audio information output by the audio conversion model.

[0149] In some implementations, the verification information is text verification information, and the conversion unit may further include a second input subunit and a second receiving subunit.

[0150] The second input subunit can be used to input text verification information into a pre-trained audio conversion model, which converts the text verification information into verification audio information corresponding to preset voiceprint information; the second receiving subunit can be used to receive the verification audio information output by the audio conversion model.

[0151] In some implementations, the user information is voiceprint information, and the first acquisition module 310 may include a second acquisition unit.

[0152] The second acquisition unit can be used to acquire the voiceprint information of the user logging into the virtual scene.

[0153] In some implementations, the second acquisition module 320 may include an identification unit and a third acquisition unit.

[0154] The identification unit can be used to identify a user's voiceprint based on the voiceprint information; the third acquisition unit can be used to acquire the identity identifier associated with the preset user when the user is determined to be a preset user based on the voiceprint recognition result.

[0155] The solution provided in this application obtains user information when logging into a virtual scene. When the user information is successfully verified, it obtains the identity identifier corresponding to the user information and the user's verification audio information. The identity identifier is encoded into the verification audio information, and the encoded audio information is sent to the verification platform of the virtual scene. This allows the verification platform to identify the user based on the identity identifier carried in the encoded audio information. This solution enables the verification platform of the virtual scene to identify the user based on the identity identifier carried in the encoded audio information, avoiding the low success rate of user identification caused by the verification platform of the virtual scene relying on voice identification based on encoded audio information. This improves the success rate of user identification in the virtual scene.

[0156] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For device embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to in the descriptions of the method embodiments. Any processing method described in the method embodiments can be implemented in the device embodiments through corresponding processing modules, and will not be elaborated upon further in the device embodiments.

[0157] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0158] Please see Figure 5 This illustrates a functional block diagram of an electronic device 400 provided in another embodiment of this application. The electronic device 400 may include one or more components such as a memory 410, a processor 420, and one or more application programs, wherein the one or more application programs may be stored in the memory 410 and configured to be executed by one or more processors 420, and the one or more application programs are configured to perform the methods as described in the foregoing method embodiments.

[0159] The memory 410 may include random access memory (RAM) or read-only memory (ROM). The memory 410 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 410 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (e.g., obtaining user information, verifying user information, obtaining an identity identifier, obtaining verification audio information, encoding verification audio information, obtaining encoded audio information, sending encoded audio information, identity recognition, analyzing verification audio information, obtaining a preset frequency band, encoding a preset frequency band, dividing a preset frequency band, updating amplitude, inputting verification information, obtaining verification information, converting verification information, inputting voice verification information to an audio extraction model, receiving verification audio information output by the audio extraction model, inputting text verification information to an audio conversion model, converting text verification information to verification audio information, receiving verification audio information output by the audio conversion model, obtaining voiceprint information, voiceprint recognition, determining a user as a preset user, and obtaining an identity identifier associated with a preset user, etc.), and instructions for implementing the various method embodiments described below. The storage data area can also store data created by the electronic device 400 during use (such as user information, identity identifier, verification audio information, encoded audio information, verification platform of virtual scene, preset frequency band, frequency range, identification code, amplitude, verification information, voice verification information, text verification information, audio extraction model, text verification information, preset voiceprint information, audio conversion model, voiceprint information, and preset user).

[0160] Processor 420 may include one or more processing cores. Processor 420 connects to various parts within the electronic device 400 using various interfaces and lines, and performs various functions and processes data of the electronic device 400 by running or executing instructions, programs, code sets, or instruction sets stored in memory 410, and by calling data stored in memory 410. Optionally, processor 420 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). Processor 420 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 420 and may be implemented separately using a communication chip.

[0161] Please refer to Figure 6 This diagram illustrates a structural block diagram of a computer-readable storage medium provided in an embodiment of this application. The computer-readable storage medium 500 stores program code 510, which can be called by a processor to execute the methods described in the above method embodiments.

[0162] The computer-readable storage medium 500 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium 500 includes a non-transitory computer-readable storage medium. The computer-readable storage medium 500 has storage space for program code 510 that performs any of the method steps described above. This program code can be read from or written to one or more computer program products. The program code 510 may be compressed, for example, in a suitable form.

[0163] The solution provided in this application obtains user information when logging into a virtual scene. When the user information is successfully verified, it obtains the identity identifier corresponding to the user information and the user's verification audio information. The identity identifier is encoded into the verification audio information, and the encoded audio information is sent to the verification platform of the virtual scene. This allows the verification platform to identify the user based on the identity identifier carried in the encoded audio information. This solution enables the verification platform of the virtual scene to identify the user based on the identity identifier carried in the encoded audio information, avoiding the low success rate of user identification caused by the verification platform of the virtual scene relying on voice identification based on encoded audio information. This improves the success rate of user identification in the virtual scene.

[0164] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. An identity recognition method, characterized by, The method comprises: obtaining user information of a user logging into a virtual scene; when the user information is verified successfully, obtaining an identity corresponding to the user information; obtaining verification audio information of the user, the verification audio information being audio information obtained by performing voice processing on verification information input by the user; encoding the identity into the verification audio information to obtain encoded audio information: analyzing the verification audio information to obtain a preset frequency band of the verification audio information, dividing the preset frequency band into a plurality of frequency ranges corresponding to a number of identity bits of the identity, the number of frequency ranges being consistent with the number of identity bits, each frequency range corresponding to an identity code of the identity; updating the value of the amplitude corresponding to each frequency range to the corresponding identity code to obtain encoded audio information, the preset frequency band being a frequency range outside the human hearing range; sending the encoded audio information to a verification platform of the virtual scene to enable the verification platform to identify the identity of the user according to the identity carried by the encoded audio information.

2. The identity recognition method of claim 1, wherein, The method comprises: obtaining verification information input by the user, the verification information comprising voice verification information and / or text verification information; analyzing the voice verification information to obtain corresponding voice information, matching the voice information with a pre-stored conversion model to obtain a model matching degree, and determining whether there is a pre-trained audio conversion model according to the model matching degree; when the model matching degree is greater than or equal to a model matching degree threshold, it is determined that there is a pre-trained audio conversion model, and the pre-stored conversion model corresponding to the model matching degree is determined as the audio conversion model to convert the verification information into verification audio information through the audio conversion model; when the model matching degree is less than the model matching degree threshold, it is determined that there is no pre-trained audio conversion model, the voice verification information is matched with pre-stored sound information to obtain pre-stored sound information matched with the voice verification information, pre-stored text information corresponding to the pre-stored sound information matched with the voice verification information is obtained, and the pre-stored text information is taken as target text information corresponding to the voice verification request, preset voiceprint information and the target text information are synthesized to obtain verification audio information.

3. The identity recognition method of claim 2, wherein, The verification information is voice verification information, and the conversion of the verification information into verification audio information comprises: inputting the voice verification information into a pre-trained audio conversion model, the audio conversion model being used to convert the voice verification information into verification audio information corresponding to preset voiceprint information; receiving verification audio information output by the audio conversion model.

4. The identity recognition method of claim 2, wherein, The verification information is text verification information, and the conversion of the verification information into verification audio information comprises: inputting the text verification information into a pre-trained audio conversion model, the audio conversion model being used to convert the text verification information into verification audio information corresponding to preset voiceprint information; receiving the verification audio information output by the audio conversion model.

5. The identity recognition method according to any one of claims 1 to 4, characterized in that, The user information is voiceprint information, and the obtaining of the user information of the user logging into the virtual scene comprises: Acquire voiceprint information of a user logging into a virtual scene; When the user information is verified successfully, acquire an identity corresponding to the user information, including: According to the voiceprint information, perform voiceprint recognition on the user; When it is determined according to the voiceprint recognition result that the user is a preset user, acquire an identity associated with the preset user.

6. An identity recognition apparatus characterized by comprising: Including: A first acquisition module is configured to acquire user information of a user logging into a virtual scene; A second acquisition module is configured to, when the user information is verified successfully, acquire an identity corresponding to the user information; A third acquisition module is configured to acquire verification audio information of the user, the verification audio information being audio information obtained by performing voice conversion on verification information input by the user; An encoding module is configured to encode the identity into the verification audio information to obtain encoded audio information: analyze the verification audio information to obtain a preset frequency band of the verification audio information, divide the preset frequency band into a plurality of frequency ranges corresponding to a number of identity bits of the identity, the number of the frequency ranges being consistent with the number of the identity bits, each frequency range corresponding to an identity code of the identity, and update a value of an amplitude corresponding to each frequency range to a corresponding identity code to obtain encoded audio information, the preset frequency band being a frequency range outside a human hearing range; A sending module is configured to send the encoded audio information to a verification platform of the virtual scene, so that the verification platform performs identity recognition on the user according to the identity carried by the encoded audio information.

7. An electronic device, comprising: Including: A memory; One or more processors coupled to the memory; One or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more application programs are configured to perform the identity recognition method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores program codes, and the program codes can be called and executed by the processor to perform the identity recognition method according to any one of claims 1 to 5.

Images