User identity identification method, storage medium and electronic device

Abstract

This application discloses a user identity recognition method, storage medium, and electronic device, relating to the field of smart home technology. By inputting user voice data into a voice voiceprint recognition model to obtain voice recognition information, voice recognition of the user voice data is achieved, providing reference information for user identity recognition. If the target user identification information cannot be determined based on the voice recognition information, one or a combination of pre-stored user profile information, device information, recent conversation information, user group information, and voice recognition information is input into the user identity recognition model to achieve user identity recognition based on information from multiple dimensions, ultimately determining the target user identification information and improving the accuracy of user identity recognition.

Description

Technical Field

[0001] The present application relates to the field of smart home technology, and in particular to a user identity identification method, storage medium, and electronic device. Background Art

[0002] In the smart home sector, voice dialogue systems have become essential. When users engage in multi-round conversations across multiple devices, accurate user identification is fundamental to all interactions. Existing technologies rely solely on voice and voiceprint features for identity recognition, with low accuracy. This is especially true when background noise interference or unclear user speech creates a high error rate, leading to ineffective multi-round conversations across multiple devices and a poor user experience.

[0003] Therefore, proposing an identity recognition method to achieve accurate user identity recognition is an important current research direction. Summary of the Invention

[0004] The present application provides a user identity recognition method, a storage medium, and an electronic device to solve the defect of high error rate of identity recognition in the prior art and realize accurate user identity recognition.

[0005] This application provides a user identity identification method, including:

[0006] Get user voice data;

[0007] Inputting the user voice data into a voice voiceprint recognition model to obtain voice recognition information;

[0008] If the target user identification information cannot be determined based on the voice recognition information, a combination of one or more of the pre-stored user portrait information, device information, recent conversation information, user group information and the voice recognition information is input into the user identity recognition model to determine the target user identification information.

[0009] According to a user identity recognition method provided by the present application, the voice recognition information includes a confidence level that the current user is a pending user, the current user's gender information, and the current user's age information, or a combination of the two.

[0010] The step of inputting the user voice data into a voice voiceprint recognition model to obtain voice recognition information includes:

[0011] The user voice data is input into a voice voiceprint recognition model, and one or more of the following information is output: the confidence level that the current user is the pending user, the current user's gender information, and the current user's age information.

[0012] According to a user identity identification method provided by this application, the method further includes:

[0013] In a case where the confidence level is greater than a confidence level threshold, the user identification information corresponding to the pending user is determined as the target user identification information.

[0014] According to a user identity recognition method provided by the present application, the voice recognition information includes the confidence level that the current user is the pending user, the current user's gender information, and the current user's age information;

[0015] The step of inputting one or a combination of pre-stored user portrait information, device information, recent conversation information, user group information, and the voice recognition information into a user identity recognition model to determine target user identification information includes:

[0016] Performing similarity matching in a preset user database corresponding to the user portrait information based on the user identity recognition model, the confidence level, the current user gender information, and the current user age information to determine initial user identification information, where the initial user identification information is user identification information with a similarity greater than a similarity threshold;

[0017] Target user identification information is determined according to the initial user identification information.

[0018] According to a user identity identification method provided by the present application, after determining the initial user identification information, the method further includes:

[0019] Determining recent user identification information based on the recent conversation information;

[0020] The initial user identification information is corrected according to the recent user identification information to determine target user identification information.

[0021] According to a user identification method provided by this application, the recent user identification information includes time information;

[0022] The correcting the initial user identification information according to the recent user identification information to determine the target user identification information includes:

[0023] Determine, based on the time information, a plurality of candidate user identification information within a preset time period from the recent user identification information;

[0024] In a case where the plurality of candidate user identification information are consistent, the candidate user identification information is determined as the target user identification information.

[0025] According to a user identity identification method provided by this application, the method further includes:

[0026] In the case that the initial user identification information cannot be determined, temporary user identification information is generated according to the device information and the user group information, and the temporary user identification information is determined as the target user identification information.

[0027] The present application also provides a user identity recognition device, comprising:

[0028] Acquisition module, used to obtain user voice data;

[0029] A speech recognition module, configured to input the user's speech data into a speech voiceprint recognition model to obtain speech recognition information;

[0030] The user identity recognition module is used to input the pre-stored user portrait information, device information, recent conversation information, user group information and the voice recognition information into the user identity recognition model to determine the target user identification information when the target user identification information cannot be determined based on the voice recognition information.

[0031] The present application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute any of the above-mentioned user identity recognition methods through the computer program.

[0032] The present application also provides a computer-readable storage medium, which includes a stored program, wherein the program is executed to implement any of the user identity identification methods described above when it is run.

[0033] The present application also provides a computer program product, comprising a computer program, which implements any of the above-mentioned user identity identification methods when executed by a processor.

[0034] The user identification method, storage medium, and electronic device provided in this application utilize voice recognition information obtained by inputting user voice data into a voice and voiceprint recognition model. This allows for voice recognition of the user's voice data, providing reference information for user identification. If the target user's identification information cannot be determined based on the voice recognition information, pre-stored user profile information, device information, recent conversation information, user group information, and voice recognition information are input into the user identification model to identify the user based on multiple dimensions of information. Ultimately, the target user's identification information is determined, thereby improving the accuracy of user identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0037] Figure 1 Schematic diagram of a hardware environment for a user identification method according to an embodiment of the present application;

[0038] Figure 2 This is a flowchart of the user identification method provided by this application;

[0039] Figure 3 This is a schematic diagram of the user identification process provided by this application;

[0040] Figure 4 This is a schematic diagram of the structure of the user identity recognition device provided by this application;

[0041] Figure 5 It is a structural diagram of the electronic device provided in this application. DETAILED DESCRIPTION

[0042] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0043] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0044] According to one aspect of the embodiment of the present application, a user identification method is provided. The user identification method is widely used in smart home (Smart Home), smart home, smart home device ecology, smart residential (Intelligence House) ecology and other whole-house intelligent digital control application scenarios. Optionally, in this embodiment, the above user identification method can be applied to Figure 1 In the hardware environment shown in FIG. 1 , which is composed of a terminal device 102 and a server 104. Figure 1 As shown, the server 104 is connected to the terminal device 102 via a network, and can be used to provide services (such as application services, etc.) for the terminal or the client installed on the terminal. A database can be set up on the server or independently of the server to provide data storage services for the server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data computing services for the server 104.

[0045] The aforementioned network may include, but is not limited to, at least one of the following: a wired network and a wireless network. The aforementioned wired network may include, but is not limited to, at least one of the following: a wide area network, a metropolitan area network, and a local area network. The aforementioned wireless network may include, but is not limited to, at least one of the following: Wi-Fi (Wireless Fidelity) and Bluetooth. The terminal device 102 may be, but is not limited to, a PC, a mobile phone, a tablet computer, a smart air conditioner, a smart range hood, a smart refrigerator, a smart oven, a smart stove, a smart washing machine, a smart water heater, a smart washing machine, a smart dishwasher, a smart projection device, a smart TV, a smart clothes drying rack, smart curtains, smart audio and video, a smart socket, a smart speaker, a smart fresh air device, smart kitchen and bathroom equipment, smart bathroom equipment, a smart sweeping robot, a smart window cleaning robot, a smart mopping robot, a smart air purifier, a smart steamer, a smart microwave oven, a smart kitchen treasure, a smart purifier, a smart water dispenser, a smart door lock, etc.

[0046] This application provides a user identification method, such as Figure 2 Shown, including:

[0047] S21. Obtain user voice data;

[0048] S22, inputting the user voice data into a voice voiceprint recognition model to obtain voice recognition information;

[0049] S23. When the target user identification information cannot be determined based on the voice recognition information, a combination of one or more of the pre-stored user portrait information, device information, recent conversation information, and user group information and the voice recognition information are input into the user identity recognition model to determine the target user identification information.

[0050] Specifically, through the voice voiceprint recognition model, the voiceprint in the user's voice data can be recognized to obtain voice recognition information, which is used to represent some basic information of the user in the voice, including but not limited to the confidence that the identity of the user in the user's voice corresponds to the target user in the user database, the gender and age of the user in the user's voice, and other information.

[0051] Optionally, you can try to determine the target user identification information based on the voice recognition information. If the target user identification information cannot be determined based on the voice recognition information, you can call the user portrait information, device information, recent conversation information, user group information that has been entered and saved in advance, and the previously determined voice recognition information, input the user identity recognition model, and determine the target user identification information.

[0052] User portrait information can be label information defined for the user based on the user's historical conversation records and historical behavior records, such as label information of behavioral habits such as interests, hobbies, dietary preferences, waking up and sleeping times, or information such as the user's gender and age.

[0053] The device information may be parameters related to the device currently acquiring the user voice data, including but not limited to information such as the device ID, device name, and device model.

[0054] Recent conversation information may be conversation record information within a preset round or a preset time period, including but not limited to information such as the field to which the conversation content belongs, the intention of the conversation, and the time of the conversation.

[0055] The user group information may be association information of a plurality of preset users, such as information representing a plurality of users registered as a family unit.

[0056] In an embodiment of the present application, by inputting user voice data into a voice voiceprint recognition model, voice recognition information is obtained, and voice recognition of the user voice data is realized, providing reference information for user identity recognition; when the target user identification information cannot be determined based on the voice recognition information, the user identity recognition model is input based on a combination of one or more of the pre-stored user portrait information, device information, recent conversation information, user group information and voice recognition information, to realize user identity recognition based on information of multiple dimensions, and finally determine the target user identification information, thereby improving the accuracy of user identity recognition.

[0057] According to the user identity recognition method provided by this application, the voice recognition information includes a confidence level that the current user is the target user, the user's gender information, and the current user's age information, or a combination of the two. Step S22 includes:

[0058] S221: Input the user voice data into a voice voiceprint recognition model, and output one or more of the following information: confidence that the current user is the target user, gender information of the current user, and age information of the current user.

[0059] Specifically, a voiceprint recognition model can be used to analyze user voice data and determine the confidence level that the current user in the voice is a candidate user in a preset user database, as well as the current user's gender and age information. The confidence level indicates the degree of overlap between the current user and the candidate user. A higher confidence level indicates that the current user's identity is closer to the target user's identity.

[0060] In this embodiment, a voiceprint recognition model is used to analyze user voice data to obtain a confidence level, the current user's gender information, and the current user's age information, or a combination of these. The confidence level indicates the degree of identity overlap between the current user and the user to be determined. The confidence level, the current user's gender information, and the current user's age information can vividly describe the current user's characteristics and profile, facilitating subsequent accurate user identification.

[0061] According to the user identity identification method provided by this application, the method further includes:

[0062] S24: When the confidence level is greater than a confidence threshold, determine the user identification information corresponding to the pending user as target user identification information.

[0063] Specifically, the confidence level describes the degree of overlap between the current user's identity and the identities of the pending users in the user database. A higher confidence level indicates a closer match between the current user's identity and the pending user's identity. A confidence threshold can be set based on actual needs. If the confidence level exceeds the threshold, the current user's identity can be determined to be the identity of the pending user corresponding to the confidence level, and the user identification information corresponding to the pending user can be determined as the target user identification information.

[0064] In one example, a confidence threshold is set at 90%. After inputting user voice data into the voice voiceprint recognition model, the confidence level that the current user in the output voice is pending user A is 95%, and the confidence level that the current user is pending user B is 20%. This indicates that there is a 95% probability that the current user in the voice is pending user A and a 20% probability that the current user is pending user B. Since the 95% confidence level that the current user is pending user A is greater than the set confidence threshold of 90%, the user identification information corresponding to pending user A can be determined as the target user identification information, indicating that the current user is determined to be pending user A.

[0065] In an embodiment of the present application, a confidence threshold is used to describe the degree of identity overlap between the current user and the pending user. The confidence threshold is set. When the confidence is greater than the confidence threshold, the identity of the current user can be directly determined to be the identity of the pending user corresponding to the confidence, and the identification information corresponding to the pending user can be determined as the target user identification information, thereby realizing rapid user identity identification.

[0066] According to the user identity recognition method provided by this application, the voice recognition information includes the confidence level that the current user is the pending user, the current user's gender information, and the current user's age information; step S23 includes:

[0067] S231. Performing similarity matching in a preset user database corresponding to the user portrait information using the user identity recognition model based on the user portrait information, the confidence level, the current user gender information, and the current user age information to determine initial user identification information, where the initial user identification information is user identification information with a similarity greater than a similarity threshold.

[0068] S232: Determine the initial user identification information as target user identification information.

[0069] Specifically, the user profile of the current user can be represented by the confidence level, the current user's gender information, and the current user's age information. The user identification information in the preset user database corresponds to pre-stored user profile information. Similarity matching is performed in the preset user database using the pre-stored user profile information and the user profile of the current user represented by the confidence level, the current user's gender information, and the current user's age information. The similarity corresponding to each user identification information in the user database is calculated. User identification information with a similarity greater than a similarity threshold is determined as initial user identification information, and the initial user identification information is determined as target user identification information.

[0070] In this embodiment of the application, similarity matching is performed in a pre-set user database based on user profile information, confidence level, current user gender information, and current user age information to determine initial user identification information and achieve preliminary recognition of the current user's identity. To improve recognition accuracy, the preliminary recognition results are verified with recent conversation information to further determine the target user's identification information, thereby improving the accuracy of user identification.

[0071] According to a user identity identification method provided by this application, after step S231, the method further includes:

[0072] S233, determining recent user identification information based on the recent conversation information;

[0073] S234: Correct the initial user identification information according to the recent user identification information to determine target user identification information.

[0074] Specifically, based on the initial user identification information and recent conversation information, the initial user identification information can be further verified from the perspective of recent conversations to determine the target user identification information. Based on the recent conversation information, the corresponding user identification information in the recent conversation can be determined. The initial user identification information can be corrected using the recent user identification information to obtain the accurate target user identification.

[0075] Furthermore, the recent user identification information includes time information, and step S234 includes:

[0076] S235. Determine, based on the time information, a plurality of candidate user identification information within a preset time period from the recent user identification information;

[0077] S236: When the plurality of candidate user identification information are consistent, determine the candidate user identification information as the target user identification information.

[0078] Specifically, in one example, the preset time period is set in advance to the 10 seconds before the current moment. Assuming that the recent conversation information includes information related to five rounds of conversation, one every three seconds, within the last 15 seconds, and based on the recent conversation information, the recent user identification information corresponding to the five rounds of conversation within the last 15 seconds is determined to be ABBBB in chronological order, then the multiple candidate user identification information within the preset time period is the last three BBBs. The consistency of the multiple candidate user identification information indicates that user B has been in the conversation for the most recent period (preset time period), and the target user identification information at the current moment is most likely B. If the initial user identification information determined this time is B, it is consistent with the candidate user identification information and does not require correction. B is directly determined as the target user identification information. If the initial user identification information determined this time is A, the candidate user identification information B replaces the initial user identification information A, and B is determined as the target user identification information, thereby correcting the user identification information based on the recent conversation information and improving recognition accuracy.

[0079] In an embodiment of the present application, in order to improve the accuracy of recognition, multiple candidate user identifications in a short period of time are determined in the recent user identification information through the time information in the recent conversation information. When the multiple candidate user identification information in the short period of time is consistent, it can be determined that there is a deviation error in this recognition, and the recognition result of this time is corrected. The candidate user identification information that best fits the actual scenario is determined as the target user identification information, thereby correcting the preliminary recognition result.

[0080] According to a user identity identification method provided by this application, the method further includes:

[0081] S237: If the initial user identification information cannot be determined, generate temporary user identification information according to the device information and the user group information, and determine the temporary user identification information as the target user identification information.

[0082] Specifically, when calculating the similarity corresponding to each user identification information in the user database, if there is no user identification information with a similarity greater than the similarity threshold, that is, if the initial user identification information cannot be determined, temporary user identification information can be generated based on the device information and user group information, and the temporary user identification information can be determined as the target user identification information. For example, a new ID is formed by combining the device ID and the user group ID, and this is used as the target user identification information.

[0083] In an embodiment of the present application, when it is impossible to preliminarily identify the current user identity based on the determined initial user identification information, temporary user identification information can be generated as the target user identification information through device information and user group information to establish a temporary user identity, making user identity identification more complete.

[0084] In an example based on the above embodiments, Figure 3 As shown, voice voiceprint identity recognition is performed based on the user voice data. When the confidence level is greater than the confidence threshold, the target user identification information can be directly identified. Otherwise, when the target user identification information cannot be directly identified, user identity recognition is performed based on voice recognition information, user portrait information, device information, recent conversation information and user group information to determine the target user identification information.

[0085] The user identity identification device provided in the present application is described below. The user identity identification device described below and the user identity identification method described above can be referenced to each other.

[0086] This application also provides a user identity identification device, such as Figure 4 Shown, including:

[0087] An acquisition module 41 is used to acquire user voice data;

[0088] The speech recognition module 42 is used to input the user speech data into the speech voiceprint recognition model to obtain speech recognition information;

[0089] The user identity recognition module 43 is used to input a combination of one or more of the pre-stored user portrait information, device information, recent conversation information, user group information and the voice recognition information into a user identity recognition model to determine the target user identification information when the target user identification information cannot be determined based on the voice recognition information.

[0090] In an embodiment of the present application, by inputting user voice data into a voice voiceprint recognition model, voice recognition information is obtained, and voice recognition of the user voice data is realized, providing reference information for user identity recognition; when the target user identification information cannot be determined based on the voice recognition information, the user identity recognition model is input based on a combination of one or more of the pre-stored user portrait information, device information, recent conversation information, user group information, and voice recognition information, to realize user identity recognition based on information from multiple dimensions, and finally determine the target user identification information, thereby improving the accuracy of user identity recognition.

[0091] According to the user identity recognition device provided by the present application, the voice recognition information includes one or more of the following information: the confidence level that the current user is the pending user, the current user's gender information, and the current user's age information;

[0092] The speech recognition module 42 is specifically configured to input the user speech data into a speech voiceprint recognition model, and output one or more of the following information: the confidence level that the current user is the pending user, the current user's gender information, and the current user's age information.

[0093] According to the user identity recognition device provided by the present application, the user identity recognition module 43 is further configured to: when the confidence level is greater than a confidence level threshold, determine that the user identification information corresponding to the target user is the target user identification information.

[0094] According to the user identification device provided by the present application, the voice recognition information includes the confidence level that the current user is the pending user, the current user's gender information, and the current user's age information; the user identification unit 43 is specifically configured to:

[0095] Performing similarity matching in a preset user database corresponding to the user portrait information based on the user identity recognition model, the confidence level, the current user gender information, and the current user age information to determine initial user identification information, where the initial user identification information is user identification information with a similarity greater than a similarity threshold;

[0096] The initial user identification information is determined as the target user identification information.

[0097] According to the user identity recognition device provided by this application, the user identity recognition unit 43 is further configured to:

[0098] Determining recent user identification information based on the recent conversation information;

[0099] The initial user identification information is corrected according to the recent user identification information to determine target user identification information.

[0100] According to the user identification device provided by this application, the recent user identification information includes time information;

[0101] The user identification unit 43 is specifically configured to:

[0102] Determine, based on the time information, a plurality of candidate user identification information within a preset time period from the recent user identification information;

[0103] In a case where the plurality of candidate user identification information are consistent, the candidate user identification information is determined as the target user identification information.

[0104] According to the user identity recognition device provided by this application, the user identity recognition unit 43 is further configured to:

[0105] In the case that the initial user identification information cannot be determined, temporary user identification information is generated according to the device information and the user group information, and the temporary user identification information is determined as the target user identification information.

[0106] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5 As shown, the electronic device may include: a processor 510, a communications interface 520, a memory 530, and a communication bus 540, wherein the processor 510, the communications interface 520, and the memory 530 communicate with each other via the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute a user identification method, which includes: obtaining user voice data; inputting the user voice data into a voice voiceprint recognition model to obtain voice recognition information; and if the target user identification information cannot be determined based on the voice recognition information, inputting one or more of the pre-stored user portrait information, device information, recent conversation information, and user group information, as well as the voice recognition information, into the user identification model to determine the target user identification information.

[0107] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0108] On the other hand, the present application also provides a computer program product, which includes a computer program, and the computer program can be stored on a computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the user identity identification method provided by the above methods, which method includes: obtaining user voice data; inputting the user voice data into a voice voiceprint recognition model to obtain voice recognition information; when the target user identification information cannot be determined based on the voice recognition information, inputting a combination of one or more of the pre-stored user portrait information, device information, recent conversation information, and user group information and the voice recognition information into the user identity recognition model to determine the target user identification information.

[0109] On the other hand, the present application also provides a computer-readable storage medium, which includes a stored program, wherein the program executes the user identity identification method provided by the above methods when it is run, and the method includes: obtaining user voice data; inputting the user voice data into a voice voiceprint recognition model to obtain voice recognition information; when the target user identification information cannot be determined based on the voice recognition information, inputting a combination of one or more of the pre-stored user portrait information, device information, recent conversation information, and user group information and the voice recognition information into the user identity recognition model to determine the target user identification information.

[0110] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0111] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0112] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A user identification method, characterized in that: include: Get user voice data; Inputting the user voice data into a voice voiceprint recognition model to obtain voice recognition information; If the target user identification information cannot be determined based on the voice recognition information, one or a combination of pre-stored user portrait information, device information, recent conversation information, user group information, and the voice recognition information are input into the user identity recognition model to determine the target user identification information; The speech recognition information includes the confidence level of the current user being the pending user, the current user's gender information, and the current user's age information; The step of inputting one or a combination of pre-stored user portrait information, device information, recent conversation information, user group information, and the voice recognition information into a user identity recognition model to determine target user identification information includes: Performing similarity matching in a preset user database corresponding to the user portrait information based on the user identity recognition model, the confidence level, the current user gender information, and the current user age information to determine initial user identification information, where the initial user identification information is user identification information with a similarity greater than a similarity threshold; Determine the target user identification information according to the initial user identification information; After determining the initial user identification information, the method further includes: Determining recent user identification information based on the recent conversation information; Correcting the initial user identification information according to the recent user identification information to determine target user identification information; The method further comprises: In the case that the initial user identification information cannot be determined, temporary user identification information is generated according to the device information and the user group information, and the temporary user identification information is determined as the target user identification information.

2. The user identification method according to claim 1, characterized in that: The speech recognition information includes one or more of the following information: the confidence level that the current user is the pending user, the gender information of the current user, and the age information of the current user; The step of inputting the user voice data into a voice voiceprint recognition model to obtain voice recognition information includes: The user voice data is input into a voice voiceprint recognition model, and one or more of the following information is output: the confidence level that the current user is the pending user, the current user's gender information, and the current user's age information.

3. The user identification method according to claim 2, characterized in that: The method further comprises: In a case where the confidence level is greater than a confidence level threshold, the user identification information corresponding to the pending user is determined as the target user identification information.

4. The user identification method according to claim 1, characterized in that: The recent user identification information includes time information; The correcting the initial user identification information according to the recent user identification information to determine the target user identification information includes: Determine, based on the time information, a plurality of candidate user identification information within a preset time period from the recent user identification information; In a case where the plurality of candidate user identification information are consistent, the candidate user identification information is determined as the target user identification information.

5. A user identification device, characterized in that: include: Acquisition module, used to obtain user voice data; A speech recognition module, configured to input the user's speech data into a speech voiceprint recognition model to obtain speech recognition information; A user identification module is configured to input one or a combination of pre-stored user portrait information, device information, recent conversation information, and user group information, as well as the voice recognition information, into a user identification model to determine the target user identification information if the target user identification information cannot be determined based on the voice recognition information; The speech recognition information includes the confidence level of the current user being the pending user, the current user's gender information, and the current user's age information; The user identification module is used to input one or a combination of pre-stored user profile information, device information, recent conversation information, user group information, and the voice recognition information into the user identification model to determine the target user identification information, specifically for: Performing similarity matching in a preset user database corresponding to the user portrait information based on the user identity recognition model, the confidence level, the current user gender information, and the current user age information to determine initial user identification information, where the initial user identification information is user identification information with a similarity greater than a similarity threshold; Determine the target user identification information according to the initial user identification information; The user identification module is further configured to: determine recent user identification information based on the recent conversation information; correct the initial user identification information based on the recent user identification information to determine target user identification information; The user identification module is further configured to: if the initial user identification information cannot be determined, generate temporary user identification information according to the device information and the user group information, and determine the temporary user identification information as the target user identification information.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 3 when executed.

7. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 3 through the computer program.

Images