Voiceprint unlocking method, electronic equipment, chip, storage medium and program product

Abstract

The invention discloses a voiceprint unlocking method, electronic equipment, a chip, a storage medium and a program product, and relates to the technical field of electronic equipment, and the voiceprint unlocking method comprises the following steps: when the electronic equipment is in a function limited state, obtaining an unlocking voice; wherein the function limited state comprises function limitation of a system service in the electronic equipment or function limitation of an application in the electronic equipment. And if the electronic equipment obtains the unlocking voices of at least two users within the first duration, voiceprint recognition is performed on the unlocking voices of the users, and the predicted age of each user is determined. And if the predicted ages of two users in the at least two users meet the unlocking condition, the electronic equipment quits the function limited state. In the scheme, at least two users participate in voiceprint unlocking, so that the problem of poor supervision when a single user performs unlocking by himself / herself is avoided, and a mutual supervision effect can be achieved; and the two users who perform voiceprint unlocking are users whose ages meet the unlocking condition, so that the reliability of voiceprint unlocking can be further improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of electronic devices, and in particular to a voiceprint unlocking method, electronic device, chip, storage medium, and program product. Background Art

[0002] With the development of electronic devices, in order to prevent minors from using electronic devices for a long time, youth mode (also known as underage mode) is set for some usage scenarios of electronic devices. Youth mode is a network protection mechanism that can provide a limited, safe, and healthy network environment for minors. When the youth mode is turned on for an electronic device, all or part of the functions in the usage scenario of the electronic device will be locked, and the locked functions will be unavailable.

[0003] After exiting the youth mode, that is, unlocking the youth mode, all or part of the functions of the electronic device are updated from a locked state to an unlocked state, thereby enabling the use of corresponding functions of the electronic device in the locked state.

[0004] Existing youth mode unlocking methods, such as digital password verification, are easily cracked, resulting in the failure of the youth mode's supervisory function. Therefore, a more reliable youth mode unlocking method is urgently needed. Summary of the invention

[0005] The embodiments of the present application provide a voiceprint unlocking method, electronic device, chip, storage medium and program product. When releasing the limited function state of the electronic device, at least two users participate in the voiceprint unlocking, avoiding the problem of poor supervision when a single user unlocks the device by himself, and playing a role of mutual supervision. Both users who perform voiceprint unlocking are users whose ages meet the unlocking conditions, which can further improve the reliability of voiceprint unlocking. In addition, the voiceprint unlocking method in this solution is used to identify users of different age groups, and determines whether to perform voiceprint unlocking by age. It is not necessary to register the voiceprint in advance to establish a voiceprint identity database for identity verification. While simplifying the voiceprint unlocking process, it avoids the limitation of voiceprint unlocking with registered voiceprints.

[0006] In order to achieve the above-mentioned purpose, the embodiments of the present application adopt the following technical solutions.

[0007] In a first aspect, a voiceprint unlocking method is provided, the method comprising: When the electronic device is in a limited function state, the unlocking voice is obtained.

[0008] The function-restricted state includes the function-restricted system service in the electronic device or the function-restricted application in the electronic device.

[0009] If the electronic device obtains unlocking voices of at least two users within the first time period, voiceprint recognition is performed on the unlocking voices of each user to determine the predicted age of each user.

[0010] If the predicted ages of two of the at least two users meet the unlocking condition, the electronic device exits the function-restricted state.

[0011] In this application, when releasing the restricted function state of the electronic device, at least two users participate in voiceprint unlocking, which avoids the problem of poor supervision when a single user unlocks the device by himself, and can play a role of mutual supervision. The two users who perform voiceprint unlocking are both users whose ages meet the unlocking conditions, which can further improve the reliability of voiceprint unlocking. In addition, the voiceprint unlocking method in this solution is used to identify users of different age groups, and determines whether to perform voiceprint unlocking by age. There is no need to register voiceprints in advance to establish a voiceprint identity database for identity verification. While simplifying the voiceprint unlocking process, it avoids the limitations of voiceprint unlocking with registered voiceprints.

[0012] In a possible implementation manner of the first aspect, the predicted ages of the two users satisfy the unlocking condition, including: The age difference between the predicted ages of the two users is greater than or equal to the difference threshold.

[0013] Alternatively, the predicted age of one of the two users is within a first age range, and the predicted age of the other of the two users is within a second age range; the first age range does not overlap with the second age range.

[0014] In this application, the ages of the two users meet the unlocking conditions, which means that there is an adult and a minor among the two users. Considering that the electronic device is in a functionally restricted state, it includes the case for minors as well as the case for adults. When performing voiceprint unlocking, ensuring that at least one minor and at least one adult are present to participate in the unlocking can achieve the purpose of mutual supervision of voiceprint unlocking. Regardless of whether the electronic device is in a functionally restricted state and is targeted at adults or minors, the reliability of voiceprint unlocking is improved to a certain extent. Especially for some unlocking scenarios that require protection of privacy information, it can further ensure that the device is unlocked under mutual supervision to reduce the risk of privacy leakage.

[0015] In another possible implementation manner of the first aspect, the method further includes: When the electronic device is in a function-restricted state, if a first unlocking voice of a first user is acquired within a first time period, a first prompt message is output, wherein the first prompt message is used to prompt users whose ages meet the unlocking condition to participate in the unlocking.

[0016] If the electronic device receives a second unlocking voice of the second user within the second time period, the electronic device performs voiceprint recognition on the second unlocking voice to determine the predicted age of the second user.

[0017] If the predicted age of the first user and the predicted age of the second user satisfy the unlocking condition, the electronic device exits the function-restricted state.

[0018] In the present application, for the situation where the electronic device may only receive the unlocking voice of one user within the first period of time, the electronic device can output a prompt message to prompt the user that other users whose ages meet the unlocking conditions are needed to participate in the unlocking. This can more intuitively express to the user the requirement that at least two users work together to perform voiceprint unlocking. The voiceprint unlocking by at least two users has the effect of joint supervision, making the unlocking of the electronic device in a function-restricted state more reliable.

[0019] In another possible implementation manner of the first aspect, the electronic device includes multiple function-restricted states, and the function-restricted states correspond to target users of age groups with unlocking authority.

[0020] The method further includes: When the electronic device is in a function-restricted state, if a third unlocking voice of a third user is obtained within a first time period, and the third user is determined to be a target user corresponding to the function-restricted state based on the predicted age of the third user, the electronic device exits the function-restricted state.

[0021] In this application, each functionally restricted state corresponds to a target user of the age group with unlocking authority. For example, when the electronic device is a smart TV, and the smart TV is in a functionally restricted state in the youth mode, the user targeted by the functionally restricted state is a minor, and the target user of the functionally restricted state is an adult. For example, when the electronic device is a private device of a minor, if the electronic device is in a functionally restricted state, and the user targeted by the functionally restricted state is another adult, then the target user of the functionally restricted state is the owner of the electronic device (a minor).

[0022] In the present application, for the situation where the electronic device may only receive the unlocking voice of one user within the first period of time, if the electronic device determines that the one user is a target user in a functionally restricted state, the electronic device directly performs voiceprint unlocking, which can improve the efficiency of voiceprint unlocking, save the time of voiceprint unlocking, and further optimize the limitation that two users must participate in voiceprint unlocking in some special scenarios.

[0023] In another possible implementation manner of the first aspect, the method further includes: If the electronic device determines the target user corresponding to the non-functionally restricted state of the third user based on the predicted age of the third user, the electronic device outputs the second prompt information, wherein the second prompt information is used to prompt the target user who needs to match the age to participate in unlocking.

[0024] If the electronic device receives the fourth unlocking voice of the fourth user within the third time period, the electronic device performs voiceprint recognition on the fourth unlocking voice to determine the predicted age of the fourth user.

[0025] If the predicted age of the third user and the predicted age of the fourth user satisfy the unlocking condition, the electronic device exits the function-restricted state.

[0026] In the present application, for the situation where the electronic device may only receive the unlocking voice of one user within the first time period, if the electronic device determines that the one user is not the target user of the functionally restricted state, the electronic device outputs a prompt message to prompt the user that other users whose ages meet the unlocking conditions are required to participate in the unlocking. This can more intuitively express to the user the requirement that at least two users work together to perform voiceprint unlocking. The voiceprint unlocking by at least two users has the effect of joint supervision, making the unlocking of the electronic device in the functionally restricted state more reliable.

[0027] In another possible implementation manner of the first aspect, the electronic device includes multiple function-restricted states, and the function-restricted states correspond to target users of age groups with unlocking authority.

[0028] The method further includes: When the electronic device is in a limited function state, if a fifth unlocking voice of a fifth user is obtained within a first time period, and the fifth user is determined to be a target user corresponding to the limited function state based on the predicted age of the fifth user, the electronic device performs security verification on the fifth user. The security verification includes password verification.

[0029] When the fifth user passes the security verification, the electronic device exits the function-restricted state.

[0030] In the present application, when the electronic device receives only one user's unlocking voice within the first time period, and determines that the one user is a target user in a functionally restricted state, the electronic device can further perform security verification on the target user in a functionally restricted state, and when the security verification is passed, the electronic device performs voiceprint unlocking. Since the target user is a user with unlocking authority in a functionally restricted state, the electronic device determines that the user corresponding to the unlocking voice is the target user, and when the target user passes the security verification, the electronic device performs voiceprint unlocking, further improving the reliability of unlocking the electronic device in a functionally restricted state.

[0031] In another possible implementation manner of the first aspect, the method further includes: When the electronic device is in a function-restricted state, the electronic device obtains the question voice of the sixth user in response to the interactive unlocking operation.

[0032] The electronic device performs voiceprint recognition on the questioning voice to determine the predicted age of the sixth user.

[0033] If the predicted age of the sixth user is within the first age range, the electronic device performs content recognition on the question voice to obtain a first question content corresponding to the question voice.

[0034] If the electronic device receives the answering voice of the seventh user within the fourth time period, the electronic device performs content recognition on the answering voice to obtain the first answering content.

[0035] If the first answer content matches the first question content, the electronic device exits the function-restricted state.

[0036] In this application, in the interactive unlocking mode, the voice of the parent whose age is predicted to be in the first age range is used as the question voice, and the voice of another user is used as the answer voice. Based on the question voice and the answer voice, voiceprint unlocking in the interactive unlocking mode can be performed. While performing voiceprint unlocking, different types of knowledge can be learned in a relaxed and pleasant atmosphere, which can also effectively enhance communication between parents and children, reduce children's resistance to the youth mode (the functional limited state of electronic devices), and improve the user experience.

[0037] In another possible implementation manner of the first aspect, after the electronic device receives the answering voice of the seventh user within the fourth time period, the method further includes: The electronic device performs voiceprint recognition on the answering voice to determine the predicted age of the seventh user.

[0038] The electronic device performs content recognition on the answering voice to obtain the first answer content, including: If the predicted age of the seventh user is within the second age range, the electronic device performs content recognition on the answering voice to obtain the first answering content.

[0039] In this application, in the interactive unlocking mode, users participating in voiceprint unlocking include parents whose predicted age is in the first age range and children whose predicted age is in the second age range. When unlocking, the interacting parents and children can learn different types of knowledge in a relaxed and pleasant atmosphere, which can also effectively enhance communication between parents and children, reduce children’s resistance to the youth mode (the functional restricted state of electronic devices), and improve the user experience.

[0040] In another possible implementation manner of the first aspect, the method further includes: When the electronic device is in a function-restricted state, the electronic device obtains the question voice of the eighth user in response to the interactive unlocking operation.

[0041] The electronic device performs content recognition on the question voice and obtains a second question content corresponding to the question voice.

[0042] If the electronic device receives the ninth user's answer voice within the fifth time period, the electronic device performs content recognition on the answer voice to obtain the second answer content.

[0043] The electronic device performs voiceprint recognition on the question voice and the answer voice respectively to determine the predicted age of the eighth user and the predicted age of the ninth user.

[0044] When the second question content matches the second answer content, and the predicted age of the eighth user and the predicted age of the ninth user meet the unlocking condition, the electronic device exits the function-restricted state.

[0045] Among them, the predicted age of the eighth user and the predicted age of the ninth user meet the unlocking conditions, including: the age difference between the predicted age of the eighth user and the predicted age of the ninth user is greater than or equal to the difference threshold; or, the predicted age of the eighth user is in the first age range.

[0046] In this application, the electronic device does not need to specifically distinguish which user is an adult, and the voice corresponding to the adult is the question voice, and which user is a minor, and the voice corresponding to the minor is the answer voice. In this embodiment, the electronic device only needs to determine that the predicted ages of two people meet the unlocking conditions, that is, an adult and a minor, and at the same time, the content corresponding to the voices of the two users matches, and the function-restricted state can be exited. In actual underlying calculations, some data processing steps of electronic devices can be reduced, and the efficiency of voiceprint unlocking of electronic devices can be improved.

[0047] In another possible implementation manner of the first aspect, the method further includes: The electronic device displays a question-and-answer interface; the question-and-answer interface includes fields related to the question content.

[0048] In the present application, the electronic device can display a question-and-answer interface to make the question-and-answer interaction in the interactive unlocking mode more intuitive and enhance the interactive fun between users.

[0049] In another possible implementation manner of the first aspect, the method further includes: The electronic device displays an interactive unlocking interface, wherein the interactive unlocking interface includes a first control and a second control.

[0050] If the electronic device receives an interactive unlocking operation acting on the first control, the electronic device executes a step of acquiring the question voice of the sixth user, or executes a step of acquiring the question voice of the eighth user.

[0051] If the electronic device receives a direct unlocking operation acting on the second control, the step of the electronic device acquiring the unlocking voice is executed.

[0052] In this application, the electronic device can perform voiceprint unlocking in different unlocking modes by displaying different controls. This includes direct voiceprint unlocking mode and interactive voiceprint unlocking mode. Different voiceprint unlocking modes can be applied to the current unlocking scenarios. For example, when there is plenty of time, you can act on the first control to perform voiceprint unlocking in interactive voiceprint unlocking mode, which can increase the fun of the voiceprint unlocking process; when you want to directly perform voiceprint unlocking, you can act on the second control to perform direct unlocking operation, which can shorten the time of voiceprint unlocking.

[0053] In another possible implementation of the first aspect, the electronic device performs voiceprint recognition on each user's unlocking voice to determine the predicted age of each user, including: The electronic device inputs each user's unlocking voice into the voiceprint recognition model for feature extraction and age classification to determine the predicted age of each user.

[0054] In this application, the electronic device uses the voiceprint recognition model to extract features and classify age, and the voiceprint recognition model can be used to identify different age stages. The voiceprint recognition model in this case is not used for voiceprint identity verification, and the entire solution does not involve voiceprint registration, which can avoid the limitations of the voiceprint registration method for voiceprint verification and the complexity of the process.

[0055] In a second aspect, an electronic device is provided, which includes an audio acquisition device, a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of any one of the methods described in the first aspect.

[0056] In a third aspect, a computer-readable storage medium is provided, wherein instructions are stored in the computer-readable storage medium, and when the computer program / instructions are executed by a processor, the steps of the method described in any one of the first aspects are implemented.

[0057] In a fourth aspect, a computer program product comprising instructions is provided, including a computer program / instructions, which, when executed by a processor, implements the steps of any one of the methods described in the first aspect.

[0058] In a fifth aspect, an embodiment of the present application provides a chip, the chip including a processor, the processor being used to call a computer program in a memory to execute a method as described in any one of the methods in the first aspect.

[0059] It can be understood that the beneficial effects that can be achieved by the electronic device described in the second aspect, the computer-readable storage medium described in the third aspect, the computer program product described in the fourth aspect, and the chip described in the fifth aspect provided above can refer to the beneficial effects in the first aspect and any possible design method thereof, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 A flow chart of a voiceprint unlocking method based on voiceprint identity authentication; Figure 2 A flow chart of a voiceprint unlocking method provided in an embodiment of the present application; Figure 3 A flowchart of another voiceprint unlocking method provided in an embodiment of the present application; Figure 4 A schematic diagram of a scenario of voiceprint unlocking of an electronic device provided in an embodiment of the present application; Figure 5 A schematic diagram of a scenario of voiceprint unlocking of another electronic device provided in an embodiment of the present application; Figure 6 A schematic diagram of a scenario of voiceprint unlocking of another electronic device provided in an embodiment of the present application; Figure 7 A schematic diagram of a scenario of voiceprint unlocking of another electronic device provided in an embodiment of the present application; Figure 8 A schematic diagram of a scenario of voiceprint unlocking of another electronic device provided in an embodiment of the present application; Fig. 9 A schematic diagram of a scenario of voiceprint unlocking of another electronic device provided in an embodiment of the present application; Fig.10 A schematic diagram of a flow chart of voiceprint unlocking including an interactive unlocking mode provided in an embodiment of the present application; Fig.11 A schematic diagram of a scenario of voiceprint unlocking of another electronic device provided in an embodiment of the present application; Fig.12 A schematic diagram of a scene of a display interface of a smart TV provided in an embodiment of the present application; Fig.13 Interface diagrams of several interactive unlocking interfaces provided in embodiments of the present application; Fig.14 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application; Fig.15 A schematic diagram of the structure of another electronic device provided in an embodiment of the present application; Fig.16A schematic diagram of the structure of a chip system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] In the description of the embodiments of the present application, the terms used in the following embodiments are only for the purpose of describing specific embodiments, and are not intended to be used as limitations on the present application. As used in the specification and the appended claims of the present application, the singular expressions "a", "said", "above", "the" and "this" are intended to also include expressions such as "one or more", unless there is a clear contrary indication in the context. It should also be understood that in the following embodiments of the present application, "at least one", "one or more" refer to one or more (including two). The term "and / or" is used to describe the association relationship of associated objects, indicating that three relationships can exist; for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0062] References to "one embodiment" or "some embodiments" etc. described in this specification mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Thus, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways. The term "connection" includes direct connection and indirect connection, unless otherwise specified. "First" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated.

[0063] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0064] With the development of electronic devices, in order to prevent minors from becoming addicted to electronic devices, youth mode (also known as underage mode) is set for electronic devices. Youth mode is a network protection mechanism that aims to provide a limited, safe, and healthy network environment for minors. When youth mode is turned on for an electronic device, the electronic device is in a limited function state, all or specified functions of the electronic device are locked, and the locked functions are unavailable, and the usage time is also limited.

[0065] In one example, when the electronic device is a mobile phone, the operating system of the mobile phone has a youth mode. When the mobile phone turns on the youth mode, the specified functions provided by the operating system of the mobile phone are in a locked state. Specifically, the specified function can be a networking function. When the mobile phone turns on the youth mode, the networking function of the mobile phone is in a locked state. In another example, when the electronic device is a mobile phone, the application of the mobile phone has a youth mode. When the youth mode of the application is turned on, all or specified functions of the application are in a locked state. Specifically, the application can be a social application, a video application, a game application, etc. For example, when the youth mode of the game application is turned on, the usage time of the game application is changed from unlimited to limited time, and the pull-up payment function of the game application is in a locked state. In another example, when the electronic device is a smart TV, the smart TV has a youth mode. When the youth mode of the smart TV is turned on, all or part of the functions of the smart TV are in a locked state. Specifically, the specified function can be a networking function. When the youth mode of the smart TV is turned on, the networking state of the smart TV is in a locked state, and the smart TV cannot connect to the Internet.

[0066] Similar to the youth mode, the child lock mode also has the effect of limiting all or specified functions. The original intention of setting the child lock mode is to prevent children from accidentally touching the electronic device and causing the electronic device to malfunction, or to prevent children from being injured by accidental touch. The child lock mode is usually used in smart home devices. Smart home devices such as smart TVs, smart washing machines, smart ovens, and smart water dispensers can all be set with a child lock mode. In one example, when the smart home device is a smart washing machine, when the child lock mode of the smart TV is turned on, all function buttons of the smart washing machine are in a locked state to prevent children from accidentally touching the function buttons and getting injured or causing the washing machine equipment to malfunction.

[0067] When the youth mode or child lock mode is turned on for an electronic device, all or specified functions of the electronic device can be locked. This state of function restriction is hereinafter referred to as the electronic device being in a function restricted state. When an electronic device is in a function restricted state, it can be used to ensure that teenagers use the electronic device without supervision. When an adult uses an electronic device or an adult accompanies a teenager to use an electronic device, the youth mode or child lock mode can be exited, and the electronic device exits the function restricted state, and the corresponding function of the electronic device is updated to the use state. The operations of exiting the function restricted state involved in this embodiment, such as exiting the youth mode or child lock mode, etc., can be collectively referred to as the unlocking operation.

[0068] There are many common implementation methods for unlocking electronic devices. In one example, the electronic device can be unlocked by a digital password. Specifically, when the electronic device is in a limited function state, the electronic device can output a password verification interface in response to the user's unlocking operation. After receiving the digital password input by the user, the electronic device verifies the digital password input by the user, and if the verification is successful, the electronic device exits the limited function state.

[0069] The specific implementation method of this unlocking operation has certain limitations. For example, when unlocking electronic devices through digital passwords, the digital password setting rules are relatively simple. In some cases, teenagers can easily crack the digital passwords and cancel the youth mode by themselves without parental permission, which makes the supervision of the youth mode ineffective and unable to play an effective supervision effect. In some other aspects, digital passwords are easy to forget, and retrieving the digital password to cancel the youth mode may cause complicated operation procedures.

[0070] Alternatively, in another example, a common unlocking operation of an electronic device includes an unlocking operation of the electronic device by verifying the user's identity through voiceprint. Specifically, when the electronic device is in a limited function state, the electronic device responds to the user's unlocking operation and performs voiceprint recognition on the unlocking audio input by the user. When the user identity corresponding to the unlocking audio is confirmed to be a legitimate user in the voiceprint registration database based on the voiceprint registration database, the electronic device exits the limited function state.

[0071] Figure 1 A flow chart of a voiceprint unlocking method based on voiceprint identity authentication is given. Figure 1 ,This method includes two stages, the first stage is the user voiceprint registration ,stage, and the second stage is the user voiceprint unlocking ,stage.

[0072] The process of user voiceprint registration includes: Step 1: The electronic device collects the registration audio of the user to be registered.

[0073] Voiceprint registration has certain requirements for the registered audio to ensure the validity and integrity of the user's voiceprint data corresponding to the registered audio. For example, the duration of the registered audio is required to be greater than a preset duration; or the content of the registered audio is required to include specific repeated phrases or sentences, etc.

[0074] Step 2: The electronic device performs voiceprint recognition on the registered audio and extracts a standard feature vector corresponding to the registered audio.

[0075] The standard feature vector represents the voiceprint feature vector of the user to be registered. The electronic device can use the voiceprint recognition model to perform voiceprint recognition to obtain the standard feature vector corresponding to the registration audio.

[0076] After obtaining the standard feature vector corresponding to the registration audio, the electronic device can store the standard feature vector of the registration audio in the voiceprint database. After multiple users register voiceprints, the voiceprint database includes standard feature vectors corresponding to multiple users. The multiple standard feature vectors in the voiceprint database are used to match and verify the user identity during the voiceprint unlocking stage.

[0077] The process of user voiceprint unlocking includes: Step 3: When the electronic device receives the user's unlocking instruction, it obtains the user's unlocking audio.

[0078] Step 4: The electronic device performs voiceprint recognition on the unlocking audio and extracts a test feature vector corresponding to the unlocking audio.

[0079] Step 5: The electronic device calculates the similarity between the test feature vector and each standard feature vector in the voiceprint database.

[0080] If there is a standard feature vector in the voiceprint database whose similarity is greater than the similarity threshold, the electronic device responds to the user's unlocking instruction and performs a corresponding unlocking operation.

[0081] If there is a standard feature vector in the voiceprint database with a similarity greater than the similarity threshold, it means that the test feature vector matches the standard feature vector, and the test feature vector and the corresponding user may be the user corresponding to the matched standard feature vector. That is, the user corresponding to the unlocking audio has registered the voiceprint, and the standard feature vector corresponding to the user already exists in the voiceprint registration database. The user's identity authentication is passed, and the electronic device can respond to the user's unlocking instruction and execute the unlocking operation of the electronic device.

[0082] Specifically, in some examples, if application A of an electronic device is in youth mode, then the electronic device may perform a corresponding unlocking operation to unlock application A, so that application A is in normal mode and all functions are in an unlocked state. If system service B of an electronic device is in a locked state, then the electronic device may perform a corresponding unlocking operation to unlock system service B, so that system service B of the electronic device is in an unlocked state and can be used by all users. If the electronic device is in a locked state, for example, the electronic device is in a standby locked state, a screen-off locked state, etc., then the electronic device may perform a corresponding unlocking operation to unlock the electronic device, so that the electronic device is in an unlocked state, and all services and functions provided by the electronic device can be used by all users.

[0083] On the contrary: if there is no standard feature vector with a similarity greater than the similarity threshold in the voiceprint database, the electronic device does not respond to the user's unlocking instruction.

[0084] If there is no standard feature vector with a similarity greater than the similarity threshold in the voiceprint database, it means that the test feature vector does not match any standard feature vector in the voiceprint database, the test feature vector and the corresponding user have not been registered for voiceprint, and there is no standard feature vector corresponding to the user in the voiceprint registration database, and the user's identity verification fails. In this case, the electronic device may not respond to the user's unlocking instruction and keep the electronic device locked.

[0085] Depend on Figure 1 It can be seen from the specific process of the commonly used voiceprint unlocking method shown that if the user has not registered the voiceprint in advance, there is no standard feature vector corresponding to the user in the voiceprint database, and the user cannot pass the identity authentication of voiceprint recognition and cannot unlock the electronic device. This method that requires voiceprint registration in advance makes the process of voiceprint unlocking complicated and limits the users who can be unlocked. In addition, the matching of voiceprint feature vectors requires a relatively reliable voiceprint recognition model. If the reliability of the voiceprint recognition model is not high, the accuracy of the voiceprint feature vector extracted by the voiceprint recognition model is low, and the accuracy of matching the voiceprint feature vector is also relatively low. It is possible to mistakenly match the voiceprint corresponding to the false audio (such as audio generated by artificial intelligence or audio with imitation of timbre) as a registered voiceprint, thereby performing the unlocking operation for the false audio, reducing the reliability and accuracy of the unlocking operation.

[0086] Based on this, a reliable and effective unlocking method is urgently needed to solve the problem of poor supervision under the above unlocking operation.

[0087] The embodiment of the present application provides a voiceprint unlocking method. When the electronic device is in a limited function state, when the electronic device receives the unlocking voice, the electronic device can perform voiceprint recognition on the unlocking voice to determine the user age corresponding to the unlocking voice. If the unlocking voice contains the unlocking voices of at least two users, and the user ages corresponding to the unlocking voices of the two users meet the unlocking conditions, the electronic device exits the limited function state. In this solution, the electronic device exits the limited function state, and at least two users whose user ages meet the unlocking conditions are required to participate in the unlocking, which avoids the problem of poor supervision when a single user removes the limited function state by himself. The participation of at least two users in the unlocking can play a role in mutual supervision, further improving the reliability of exiting the limited function state. In addition, the voiceprint unlocking method in this solution can identify users of different age groups, and determine whether to perform voiceprint unlocking based on the user's age. In this solution, there is no need to register the voiceprint in advance to establish a voiceprint identity database for identity authentication, which simplifies the voiceprint unlocking process while avoiding the limitation that the electronic device cannot be unlocked without voiceprint registration.

[0088] The following describes the voiceprint unlocking method provided by the embodiments of the present application through specific embodiments. Figure 2 A flow chart of a voiceprint unlocking method provided in this embodiment is given, including: S101, when the electronic device is in a function-restricted state, the electronic device obtains an unlocking voice.

[0089] Among them, the electronic device being in a functionally restricted state includes the electronic device's application being in a functionally restricted state, the electronic device's system service being in a functionally restricted state, or the entire electronic device being in a functionally restricted state. Among them, from another dimension, being in a functionally restricted state can also include all functions being in an authorized state, or some functions being in a restricted state. In this way, a variety of functionally restricted states of electronic devices are formed.

[0090] In one example, a functionally restricted state of an electronic device may be that an application of the electronic device is in youth mode. When an application is in youth mode, all or part of the functions of the application are locked. Specifically, when the application is a social application, the social application is in youth mode, the payment function and publishing function of the social application are locked, and the usage time of the social application is limited.

[0091] In another example, a functionally limited state of an electronic device may be that the electronic device is in youth mode. When the electronic device is in youth mode, some system services provided by the electronic device, or some applications deployed in the electronic device are in a locked state. For example, when the electronic device is in youth mode, the networking function and payment function of the electronic device are in a locked state, and the social applications, communication applications, video applications, game applications, etc. deployed in the electronic device are in a locked state.

[0092] In another example, a functionally limited state of an electronic device may be that the electronic device is in a child lock mode. When the electronic device is in the child lock mode, all or part of the system services provided by the electronic device are in a locked state. For example, when the electronic device is a smart washing machine, the electronic device is in the child lock mode, and all system services of the electronic device are in a locked state.

[0093] When the electronic device is in a certain function-restricted state, the electronic device can perform voiceprint unlocking based on the user's unlocking voice.

[0094] In this embodiment, the unlocking voice is a voice for exiting the limited function state, and the unlocking voice contains keywords related to unlocking. The keywords that need to be contained in the unlocking voice corresponding to each limited function state may be different. For example, when the electronic device is in youth mode, the unlocking voice may be an unlocking voice containing keywords such as "exit youth mode". When the electronic device is in child lock mode, the unlocking voice may contain an unlocking voice with keywords such as "exit child lock mode".

[0095] There are many ways for the electronic device to determine that the acquired voice is the unlocking voice corresponding to the function-limited state of the electronic device.

[0096] In one example, the electronic device can perform content recognition on the received voice. If the voice contains keywords corresponding to exiting the restricted function state, the electronic device determines that the voice is the unlocking voice, and the electronic device determines and responds to the voiceprint unlocking based on the unlocking voice.

[0097] In another example, before obtaining the unlocking voice, the electronic device may receive an unlocking operation triggered by the user. If the electronic device obtains any voice of two users within a preset time after receiving the unlocking operation. The electronic device can still perform a voiceprint unlocking operation based on the two arbitrary voices. That is to say, even if at least one of the arbitrary voices of the two users does not contain keywords related to unlocking, under the premise that the unlocking operation has been received, the arbitrary voices of the two users can be used as voices with the function of triggering voiceprint unlocking, so that the electronic device uses the method provided in this embodiment to perform voiceprint unlocking. For example, when the electronic device is in the youth mode, if the electronic device receives the voices of two users within a preset time after receiving the exit operation of the youth mode by the user through a preset gesture operation or function item operation. The electronic device can make a judgment and response to voiceprint unlocking based on the voices of the two users. Alternatively, when the electronic device receives the exit operation of the youth mode, it can output a prompt message of "input unlocking voice", and the electronic device determines the acquired voice as a voice for unlocking, and makes a judgment and response to voiceprint unlocking based on the unlocking voice.

[0098] Alternatively, in other feasible implementations, the electronic device may also obtain the unlocking voice in other ways, and this implementation does not limit the specific way of obtaining the unlocking voice.

[0099] S102: If the electronic device obtains unlocking voices of at least two users within the first time period, the electronic device performs voiceprint recognition on the unlocking voices of the respective users to determine the predicted age of the respective users.

[0100] The first duration may be a preset shorter duration. Specifically, the first duration may be 1 minute, 2 minutes, 3 minutes, etc.

[0101] In this embodiment, the electronic device can perform speaker recognition on the unlocking voice acquired within the first time period, and preliminarily determine the number of speakers (users) of the unlocking voice. Thus, the electronic device can respond with a corresponding voiceprint unlocking method based on the number of speakers corresponding to the unlocking voice.

[0102] Specifically, the electronic device may determine the number of speakers of the unlocking voice received within the first time period in a variety of ways. In a feasible embodiment, if the electronic device obtains a segment of unlocking voice within the first time period, the segment of unlocking voice may include the voices of one or more users. In this case, the electronic device may use voiceprint detection technology and separation technology to separate the voiceprints of the users contained in the unlocking voice, thereby determining the number of users contained in a segment of unlocking voice. Among them, the voiceprint detection and separation technology can be implemented using traditional voiceprint detection technology and separation technology, and this embodiment does not limit the specific implementation method. After performing speaker recognition of the unlocking voice in the above manner, if the electronic device determines that the unlocking voices of two or more users are obtained, the electronic device performs voiceprint recognition on the unlocking voice of each user based on the unlocking voice corresponding to each user after separation, and determines the predicted age of the user corresponding to each unlocking voice.

[0103] In another feasible embodiment, the electronic device may successively obtain multiple unlocking voices within the first time period, each of which includes the unlocking voice of one user, and the electronic device may use voiceprint detection technology to identify whether the user corresponding to each unlocking voice is from the same user. When the electronic device determines that the multiple unlocking voices are from two or more different users, the electronic device performs voiceprint recognition on the unlocking voice of each user respectively, and determines the predicted age of the user corresponding to each unlocking voice. The voiceprint detection technology here can also be implemented using traditional voiceprint detection technology. This embodiment does not limit the specific method for identifying whether the speakers of multiple unlocking voices are the same speaker.

[0104] Electronic devices can use voiceprint extraction technology and age classification technology to perform voiceprint recognition on each user's unlocking voice and determine the predicted age of each user.

[0105] In this embodiment, for each user's corresponding unlocking voice, the electronic device can use a voiceprint feature extraction method to extract the voiceprint feature vector corresponding to the unlocking voice. Exemplarily, the electronic device can extract features of different dimensions such as mel-frequency cepstral coefficients (MFCC), linear prediction cepstral coefficients (LPCC), short-time zero-crossing rate, short-time energy spectrum, and pitch period corresponding to the unlocking voice. These features can reflect the acoustic characteristics of each person's voice, and the acoustic characteristics also contain information related to the voiceprint and age. For example, as people age, their vocal cords will change, thereby affecting the timbre, pitch and other characteristics of the voice, and these features will be reflected in the extracted voiceprint feature vector. Based on this, after extracting the voiceprint feature vector of the unlocking voice, the voiceprint feature vector can be classified by age based on the age classification technology to determine the predicted age of the user corresponding to the voiceprint feature vector.

[0106] In a specific implementation, the electronic device may use a preset voiceprint recognition model to perform voiceprint recognition of the unlocking voice to determine the predicted age of the user corresponding to the unlocking voice. The voiceprint recognition model may include at least a feature extraction network and an age classification network.

[0107] The feature extraction network is used to extract voiceprint features from the unlocking voice input to the voiceprint recognition model, and obtain the voiceprint feature vector corresponding to the unlocking voice. The voiceprint feature vector output by the feature extraction network is used as the input of the age classification network. The age classification network can classify the voiceprint feature vector by age and determine the predicted age corresponding to the voiceprint feature vector. The age classification network can be based on a common classification network such as a classification network based on traditional machine learning or a classification network based on deep learning.

[0108] In the specific implementation method of determining the predicted age of the user corresponding to the unlocking voice based on the voiceprint recognition model, the accuracy of age classification can be improved by training the voiceprint recognition model.

[0109] Specifically, the voiceprint recognition model can be trained through a large number of sample voices marked with age information. The age information can be divided into multiple age stages, such as children, teenagers, adults, and adults. The number of divided age stages can be determined according to actual conditions. The higher the fine-grained requirements for age classification, the more age stages can be divided. In the training process based on sample voices, the voiceprint recognition model can learn the differences and regularities of voice features of different age groups. During the training process, the voiceprint recognition model will continuously adjust the model parameters to improve the recognition accuracy of age. In this embodiment, the training method for the voiceprint recognition model can adopt a conventional model training method, for example, the voiceprint recognition model is trained through sample voices until the loss value is less than a loss threshold, and a trained voiceprint recognition model is obtained. Alternatively, the voiceprint recognition model is trained through sample voices until the number of model training times reaches a threshold, and a trained voiceprint recognition model is obtained. This embodiment does not elaborate on the specific process of model training.

[0110] The voiceprint recognition model in this embodiment is used to determine the predicted age of the user corresponding to the unlocking voice, and does not perform user identity verification for the unlocking voice. Based on this, the voiceprint recognition model in this embodiment is not used for voiceprint registration.

[0111] In some other optional implementations, before training the voiceprint recognition model based on the sample speech, data preprocessing may be performed on the collected sample speech. Exemplarily, data preprocessing may include operations such as framing, windowing, and pre-emphasis on the sample speech. The specific implementation of data preprocessing may refer to common data preprocessing methods, and this embodiment does not limit it.

[0112] S103: If the predicted ages of two of the at least two users meet the unlocking condition, the electronic device exits the function-restricted state.

[0113] After the electronic device performs voiceprint recognition on the unlocking voices of multiple users and obtains the predicted age of the user corresponding to each unlocking voice, the voiceprint unlocking can be determined based on the predicted age of each user and the unlocking condition. If the predicted age of two users meets the unlocking condition, the electronic device exits the function-restricted state.

[0114] In this embodiment, the unlocking condition includes a condition requiring the predicted ages of the two users.

[0115] In one example, the predicted ages of the two users satisfying the unlocking condition includes that the age difference between the predicted ages of the two users is greater than or equal to an age difference threshold.

[0116] The age difference between the predicted ages of the two users is greater than or equal to the age difference threshold, which can indicate to a certain extent that at least one of the two users is an adult.

[0117] In one scenario, when exiting a restricted function state, such as exiting a youth mode or exiting a child lock mode, it is necessary to ensure that at least one adult is present to supervise the electronic device exiting the restricted function state, making voiceprint unlocking more effective. Considering that the unlocking condition is intended to determine whether at least one adult is present, the age difference threshold in this embodiment can be a natural number greater than or equal to 18. The specific value can be determined according to actual conditions and is not limited in this embodiment.

[0118] For example, the age difference threshold is 18 (in years, the unit description is omitted in the following embodiments). After voiceprint recognition, it is determined that the predicted age of user A is 12, and the predicted age of user B is 38. The age difference between the predicted age of user A and the predicted age of user B is 26, which is greater than the age difference threshold of 20. It is determined that the predicted ages of user A and user B meet the unlocking condition.

[0119] In another example, the predicted ages of two users satisfying the unlocking condition include the predicted age of one user being in a first age range and the predicted age of the other user being in a second age range. The first age range and the second age range are two non-overlapping age ranges.

[0120] In a specific example, considering that the unlocking condition is intended to determine whether at least one adult is present, the first age range can represent the age range corresponding to adults, for example, the first age range can be (20,50); the second age range can be represented as the age range corresponding to adults, for example, the second age range can be (2,17). The specific value ranges of the first age range and the second age range can be determined according to actual conditions, and this embodiment does not limit this.

[0121] For example, after voiceprint recognition, it is determined that the predicted age of user A is 12, and the predicted age of this user is in the second age range; the predicted age of user B is 38, and the predicted age of this user is in the first age range. It is determined that the predicted age of user A and the predicted age of user B meet the unlocking condition.

[0122] In some other scenarios, for example, when the electronic device is a private device of user C, the electronic device is in a restricted state. If user D wants to release the restricted state of the electronic device, the consent of user C is required. When user C is a minor, the purpose of unlocking the condition is to determine that at least one minor is present. In other words, when an adult uses voiceprint to unlock the electronic device in use, the owner of the electronic device (minor) needs to participate in the unlocking; adults cannot use voiceprint to unlock the electronic device without the consent of the owner of the electronic device (minor), which improves the reliability of voiceprint unlocking and, to a certain extent, protects the privacy of the owner of the electronic device (minor) from being easily leaked. Among them, when the electronic device is a private device of a certain user, the electronic device is in a restricted state, which may be that some applications containing privacy information are in a restricted state, or system services containing privacy information are in a restricted state, etc.

[0123] Based on the unlocking conditions provided in this embodiment, the determination of voiceprint unlocking in this scenario can also be performed. For example, in the specific process of determining the unlocking conditions, the electronic device can further determine that at least one of the two users is a minor. Then, the unlocking condition can be that the age difference between the predicted ages of the two users is greater than or equal to the age difference threshold, and the predicted age of the user with the younger predicted age is less than an age threshold. For example, the age threshold is 18.

[0124] Specifically, the age difference threshold is 18, and the predicted age of user D is 38 and the predicted age of user C is 12 after voiceprint recognition. The predicted age of user C, who is predicted to be younger, is less than the age threshold of 18, and the age difference between the predicted age of user D and the predicted age of user C is greater than or equal to the age difference threshold of 18. At this time, the electronic device can determine that the predicted ages of user C and user D meet the unlocking condition in this scenario. For example, the predicted age of user E is 20 and the predicted age of user F is 40 after voiceprint recognition. The predicted age of user E, who is predicted to be younger, is greater than the age threshold of 18. In this case, even if the age difference between the predicted age of user E and the predicted age of user F is greater than or equal to the age difference threshold of 18, the electronic device will determine that the predicted ages of user C and user D do not meet the unlocking condition in this scenario. In this scenario where a minor is the owner of the electronic device, the voiceprint unlocking supervision of the minor present is played, making the voiceprint unlocking more effective.

[0125] Figure 3 A flow chart of another voiceprint unlocking method provided by this embodiment is given. Figure 3As shown, if the electronic device receives a child's unlocking voice, the child's predicted age can be determined by performing voiceprint recognition and age prediction on the unlocking voice; if the electronic device receives a parent's unlocking voice, the parent's predicted age can be obtained by performing voiceprint recognition and age prediction on the unlocking voice. The electronic device compares and determines the age difference based on the child's predicted age and the parent's predicted age to obtain a determination result. When the age difference between the child's predicted age and the parent's predicted age is greater than or equal to the age difference threshold, it is determined that the child and the parent meet the unlocking condition of the electronic device, and the electronic device exits the limited function state.

[0126] In addition, the unlocking condition may also include that the predicted age of one of the two users is within a first age range, and the predicted age of the other user is within a second age range. When the first age range represents the age range corresponding to adults, and the second age range represents the age range corresponding to minors, the judgment on whether the unlocking condition is met in the scenario where the minor is the owner of the electronic device is similar to the judgment on whether the unlocking condition is met when exiting the function-restricted state of the electronic device, and will not be elaborated here.

[0127] In some optional embodiments, regardless of whether the user's predicted age meets the unlocking conditions, the electronic device can store the received user's unlocking voice in a designated storage space, and the unlocking voice stored in the designated storage space can be viewed by the relevant user. In some subsequent cases that may involve privacy leakage verification or unlocking verification, the unlocking voice stored in the designated storage space can be retrieved for unlocking backtracking. The unlocking voices stored in this embodiment can be used as supporting data in other subsequent scenarios, which can further improve the security and privacy protection of voiceprint unlocking.

[0128] The voiceprint unlocking method based on the unlocking condition in this embodiment can be applied to a variety of different scenarios. When the unlocking condition is met, the purpose of at least two users working together to unlock the voiceprint is achieved. Whether it is for minors or adults, it has a joint supervision effect, making the unlocking of the electronic device in the limited function state more reliable. In addition, compared with the traditional voiceprint verification identity unlocking method, the voiceprint unlocking method provided in this embodiment does not require the user to register the voiceprint in advance to establish a voiceprint identity database for identity authentication. Users of electronic devices can switch freely, which simplifies the voiceprint unlocking process while avoiding the limitation that the electronic device cannot be unlocked without voiceprint registration, and improves the flexibility and convenience of users to unlock the electronic device.

[0129] The following uses some specific usage scenarios to illustrate the above Figure 2 and Figure 3 Provided voiceprint unlocking method.

[0130] In one example, the electronic device is a smart TV. The smart TV has a youth mode. When the youth mode of the smart TV is turned on, some functions of the smart TV will be in a restricted state. For example, the Internet TV function provided by the smart TV will be in a restricted state. In this embodiment, turning on the youth mode of the smart TV can be understood as a restricted state in which the Internet TV application is restricted; accordingly, when the smart TV exits the youth mode, it can be understood as releasing the restricted state of the Internet TV application.

[0131] Combined with this application scenario, Figure 4 A schematic diagram of a scenario of voiceprint unlocking of an electronic device is given.

[0132] When the smart TV turns on the youth mode, the smart TV is in a limited function state. In one example, if the smart TV receives an operation triggered by the user to exit the youth mode, such as Figure 4 As shown, the smart TV can display prompt information on the display screen to prompt the user to input the unlocking voice.

[0133] The smart TV obtains the unlocking voice, performs speaker recognition on the obtained unlocking voice, and separates the unlocking voice 1 corresponding to user 1 and the unlocking voice 2 corresponding to user 2. The smart TV performs voiceprint recognition on the unlocking voice 1 to determine the predicted age 1 of user 1 corresponding to the unlocking voice 1; and performs voiceprint recognition on the unlocking voice 2 to determine the predicted age 2 of user 2 corresponding to the unlocking voice 2. The smart TV performs voiceprint recognition to determine the predicted age of the user corresponding to the unlocking voice, which can be referred to the above S102 and will not be described in detail here.

[0134] In a specific example, if the predicted age 1 is 12 and the predicted age 2 is 30, the unlocking condition is that the age difference between the predicted ages of the two users is greater than or equal to the age difference threshold, where the age difference threshold is 18. The smart TV determines that the age difference (18) between the predicted age 1 and the predicted age 2 is equal to the age difference threshold (18), and the unlocking condition of the smart TV is met, and the smart TV exits the youth mode. In an example, the smart TV can output a prompt message for prompting the user that the youth mode has been exited.

[0135] In this embodiment, when the smart TV turns on the youth mode, the duration and content of TV viewing by minors can be restricted. When the youth mode of the smart TV is released, two users need to participate in voiceprint unlocking. In particular, when one of the two users is a minor, the minor and the adult need to participate in voiceprint unlocking, which realizes voiceprint unlocking under the supervision of adults, making the voiceprint unlocking method more reliable, and effectively preventing minors from releasing the youth mode of the smart TV without the supervision of adults and watching inappropriate content. In addition, since smart TVs are more likely to be used by multiple users, multiple users may include users with high frequency of use (such as family members) and users with low frequency of use (such as visitors). If a conventional voiceprint verification identity unlocking method is used, the visitor needs to re-register the voiceprint before voiceprint verification unlocking can be performed. In this embodiment, since voiceprint-based identity authentication is not performed, the user does not need to register the voiceprint. Whether the user who releases the limited state of the smart TV function is a user with high frequency of use or a user with low frequency of use, when the predicted age meets the unlocking condition, the voiceprint unlocking process can be performed, which greatly simplifies the voiceprint unlocking process. In addition, due to the significant age difference between adults and minors, the method of judging whether the unlocking conditions are met based on the age difference between the users' predicted ages is relatively easy to implement and will not cause excessive computing power problems for smart TVs (electronic devices).

[0136] In another example, the electronic device is a mobile phone. When the owner of the mobile phone is a minor, when the gallery application of the mobile phone is in a locked state, the voiceprint unlocking method provided in this embodiment can be used to unlock the phone.

[0137] Combined with this application scenario, Figure 5 A schematic diagram of another scenario of voiceprint unlocking of an electronic device is given.

[0138] When the Gallery app of a mobile phone is locked, if the mobile phone receives an operation triggered by the user to open the Gallery app, such as Figure 5 As shown, the mobile phone can display the lock interface of the gallery application on the display screen and output a prompt message for prompting the user to input an unlocking voice.

[0139] The mobile phone obtains the unlocking voice, performs speaker recognition on the unlocking voice, and separates the unlocking voice 3 corresponding to user 3 and the unlocking voice 4 corresponding to user 4. The mobile phone performs voiceprint recognition on the unlocking voice 3 to determine the predicted age 3 of user 3 corresponding to the unlocking voice 3; and performs voiceprint recognition on the unlocking voice 4 to determine the predicted age 4 of user 4 corresponding to the unlocking voice 4. The process of the mobile phone performing voiceprint recognition to determine the predicted age of the user corresponding to the unlocking voice can be referred to the above S102, which will not be described in detail here.

[0140] In a specific example, if the predicted age 3 is 14, the predicted age 4 is 37, and the age difference threshold is 18, the age threshold is 18. The unlocking condition is that the age difference between the predicted ages of the two users is greater than or equal to the age difference threshold, where the age difference threshold is 18. The smart TV determines that the age difference (23) between the predicted age 3 and the predicted age 4 is greater than the age difference threshold (18), and the smaller predicted age 3 is less than the age threshold (18), and the unlocking condition of the mobile phone's gallery application is met, and the mobile phone exits the gallery application from the restricted function state. In an example, the smart TV can directly display the main interface of the gallery application.

[0141] In this embodiment, the mobile phone of a minor includes the privacy of the minor, for example, the gallery application of the mobile phone contains the private pictures or videos of the minor. When the gallery application of the mobile phone is in a restricted function state, it can restrict other people (such as adults) from privately viewing the content of the gallery application without the consent of the minor. When unlocking the gallery application, two users including the minor (the owner of the device) need to participate in voiceprint unlocking together, which realizes voiceprint unlocking with the consent of the minor (the owner of the device) and under joint supervision, making the unlocking of the gallery application of the mobile phone more reliable, and effectively preventing adults from privately lifting the restricted function state of the gallery of the mobile phone without the consent of the minor (the owner of the device).

[0142] The above embodiments all provide embodiments of the voiceprint unlocking method when the electronic device receives the unlocking voices of two users. In some actual scenarios, the electronic device may first receive the unlocking voice of one user, and the electronic device may implement the voiceprint unlocking method in other further ways after receiving the unlocking voice of one user.

[0143] Combination Figure 6 A schematic diagram of another scenario of voiceprint unlocking of an electronic device is given to introduce another voiceprint unlocking method provided by this embodiment. Figure 6 Taking the electronic device as a smart TV as an example, the electronic device being in a limited function state includes the smart TV being in a youth mode, and the electronic device exiting the limited function state includes the smart TV exiting the youth mode. Specifically, it includes: S201, when the electronic device is in a function-restricted state, the electronic device obtains an unlocking voice.

[0144] In one example, if the smart TV receives an operation triggered by the user to exit the youth mode, the smart TV may display a prompt message on the display screen to prompt the user to input an unlocking voice. The specific method for the smart TV to obtain the unlocking voice may refer to the above S101 and Figure 3 The given embodiments are not described in detail here.

[0145] S202: If the electronic device obtains a first unlocking voice of a first user within a first time period, the electronic device outputs first prompt information.

[0146] The first prompt information is used to prompt users whose ages meet the unlocking conditions to participate in unlocking.

[0147] In this embodiment, a single user cannot perform voiceprint unlocking. If the electronic device only obtains the first unlocking voice of a first user within the first time period, the electronic device can output a prompt message to remind the first user that other users who meet the unlocking conditions are required to jointly unlock the device. The certain time period can be a relatively short time period such as 1 minute or 2 minutes.

[0148] In some specific implementations, the electronic device may output the audio corresponding to the first prompt information in the form of voice output; or the electronic device may display the first prompt information on a display interface.

[0149] In a specific implementation, after the electronic device obtains the first unlocking voice in S201, it may first perform voiceprint recognition on the first unlocking voice to determine the predicted age of the first user.

[0150] In the case where the electronic device first determines the predicted age of the first user, if the electronic device determines that the predicted age of the first user is less than the age threshold, the content of the first prompt information output by the electronic device can be further refined into prompt information about prompting that an adult is required to jointly participate in unlocking. Correspondingly, if the electronic device determines that the predicted age of the first user is greater than the age threshold, the content of the first prompt information output by the electronic device can be further refined into prompt information about prompting that relevant users are required to jointly participate in unlocking.

[0151] In another specific implementation, the electronic device may also simultaneously perform voiceprint recognition of the first unlocking voice and output the first prompt information. Alternatively, the electronic device first outputs the first prompt information and then performs voiceprint recognition of the first unlocking voice. In both cases, the content of the first prompt information output by the electronic device may include the need for other users whose ages meet the unlocking conditions to participate in the unlocking.

[0152] S203: If the electronic device receives a second unlocking voice of the second user within the second time period, the electronic device performs voiceprint recognition on the second unlocking voice to determine the predicted age of the second user.

[0153] The second duration may be a preset duration after receiving the unlocking voice of the first user. The second duration may be a shorter duration, for example, the second duration may be 30 seconds, 50 seconds, 1 minute, etc. In some other feasible settings, the second duration may also be the same as the first duration.

[0154] Within the second time period, the electronic device receives the second unlocking voice of the second user, which means that after being prompted by the first prompt information, the first user invites users who may meet the unlocking conditions to participate in the voiceprint unlocking operation of the electronic device.

[0155] If the electronic device obtains the second unlocking voice of the second user, the electronic device performs voiceprint recognition on the second unlocking voice to determine the predicted age of the second user. The specific method of the electronic device performing voiceprint recognition on the unlocking voice to determine the predicted age of the user corresponding to the unlocking voice can be referred to the implementation method provided in S102, which is not described here.

[0156] In some other cases, if the electronic device does not receive the second unlocking voice of the second user within the second time period, the electronic device can exit from the voiceprint unlocking environment and return to an environment where the electronic device is in a functionally restricted state.

[0157] S204: If the predicted age of the first user and the predicted age of the second user satisfy the unlocking condition, the electronic device exits the function-restricted state.

[0158] After the electronic device receives the second unlocking voice of the second user and performs voiceprint recognition to determine the predicted age of the second user, it can determine whether the unlocking conditions of the functionally restricted state of the electronic device are met based on the predicted age of the second user and the predicted age of the first user.

[0159] For example, in this embodiment, after obtaining the predicted age of the first user and the predicted age of the second user, the smart TV determines whether the unlocking condition of the youth mode of the smart TV is met based on the predicted age of the second user and the predicted age of the first user. The specific method of determining whether the unlocking condition is met and performing the corresponding operation can refer to the specific implementation provided in S103, which will not be described in detail here.

[0160] like Figure 6 As shown, when the predicted age of the second user and the predicted age of the first user meet the unlocking condition of the youth mode of the smart TV, the smart TV exits the youth mode.

[0161] In this embodiment, if the electronic device only receives the unlocking voice of one user within the first time period, the electronic device can output a first prompt message, prompting the first user that other users whose ages meet the unlocking conditions need to participate in voiceprint unlocking. By interacting with the user, the requirement that at least two users work together to perform voiceprint unlocking can be more intuitively expressed to the user. The voiceprint unlocking by at least two users has the effect of joint supervision, making the unlocking of the electronic device in a function-restricted state more reliable.

[0162] The electronic device being in a functionally restricted state may include multiple functionally restricted states, and each functionally restricted state corresponds to a target user of an age group with unlocking authority. For example, when the electronic device is a smart TV, when the smart TV is in a functionally restricted state in the youth mode, the user targeted by the functionally restricted state is a minor. For example, when the electronic device is a private device of a minor, if the electronic device is in a functionally restricted state, the user targeted by the functionally restricted state is other adults. Based on the age group of the user targeted by the functionally restricted state, the target user of an age group with unlocking authority corresponding to each functionally restricted state can be set. For example, when the smart TV is in a functionally restricted state in the youth mode, the target user of the functionally restricted state is an adult. For example, when the electronic device is a private device of a minor, when the private device is in a functionally restricted state, the target user of the functionally restricted state is the owner of the electronic device (minor).

[0163] The electronic device identifies the target user in a functionally restricted state, and can compare and determine the target user in the functionally restricted state with the obtained predicted age of the user. For example, when the smart TV is in a functionally restricted state in the youth mode, the target user is a user whose age is greater than the first scene threshold. Among them, the first scene threshold can be set to a natural number greater than 18, specifically, the first scene threshold can be 20. After receiving an unlocking voice of a user within a first time period, voiceprint recognition is performed on the unlocking voice to determine the predicted age of the user. If the predicted age of the user is greater than or equal to the first scene threshold, the user is considered to be the target user of the smart TV in the youth mode. Conversely, if the predicted age of the user is less than the first scene threshold, the user is considered not to be the target user of the smart TV in the youth mode.

[0164] Based on this actual situation, Figure 7 and Figure 8 A schematic diagram of another scenario of voiceprint unlocking of an electronic device is given. Figure 7 , Figure 8 and Figure 6 The scenario is the same as above, so I won’t go into details here.

[0165] like Figure 7 In one scenario shown, when the smart TV receives a third unlocking voice of a third user within a first time period, if it is determined that the third user is a target user of the smart TV in the youth mode, since the target user is a user with unlocking authority when the smart TV is in the youth mode, the smart TV can directly execute the voiceprint unlocking operation of exiting the youth mode. Figure 8In another scenario shown, when the smart TV receives a third unlocking voice of a third user within the first time period, if the smart TV determines that the third user is not the target user of the smart TV in the youth mode, the smart TV can execute the method provided in the above S202-S204 embodiments, and output a prompt message to prompt that other users whose ages meet the unlocking conditions need to participate in voiceprint unlocking. When the smart TV receives a fourth unlocking voice of a fourth user within the third time period, the fourth unlocking voice of the fourth user is recognized by voiceprint recognition to determine the predicted age of the fourth user. The smart TV determines the unlocking condition based on the predicted age of the third user and the predicted age of the fourth user. When the predicted age of the third user and the predicted age of the fourth user meet the unlocking condition of the electronic device function restricted state, the smart TV exits the youth mode and exits the function restricted state.

[0166] The third duration may be a shorter preset duration, for example, the third duration may be 30 seconds, 50 seconds, 1 minute, etc. In some feasible examples, the third duration may be equal to the second duration.

[0167] In this embodiment, the electronic device only receives the unlocking voice of one user within the first time period, and when it is determined that the one user is a target user in a functionally restricted state, the target user has the unlocking authority adapted to the functionally restricted state. The electronic device can directly perform voiceprint unlocking, which can improve the efficiency of voiceprint unlocking, save the time of voiceprint unlocking, and further optimize the limitation that two users must participate in voiceprint unlocking together in some special scenarios.

[0168] When the electronic device receives only one user's unlocking voice within the first time period and determines that the user is a target user in a limited function state, the electronic device directly performs voiceprint unlocking, which may cause the problem of misinterpretation of the lock in some scenarios. In order to further improve the reliability of voiceprint unlocking, in this embodiment, when the electronic device receives only one user's unlocking voice within the first time period and determines that the user is a target user in a limited function state, the electronic device can perform security verification on the user. Voiceprint unlocking is performed when the user passes the security verification.

[0169] Fig. 9 A schematic diagram of another scenario of voiceprint unlocking of an electronic device is given. Fig. 9 and Figure 6 The scenario is the same as above, so I won’t go into details here.

[0170] like Fig. 9As shown, when the smart TV receives a fifth unlocking voice of a fifth user within the first time period, if it is determined that the fifth user is a target user of the smart TV in the youth mode, the smart TV can perform security verification on the fifth user.

[0171] There are many ways for smart TVs to perform security verification. For example, security verification can be digital password verification. The smart TV can display the input interface of the digital password on the display screen and receive the digital password entered by the fifth user. When the digital password entered by the fifth user matches the registered password, it is determined that the fifth user has passed the security verification, and the smart TV exits the youth mode and the functionally restricted state. In some other feasible implementations, the smart TV can also perform security verification on the fifth application through the user identity. If the smart TV determines that the fifth user is a user with a registered voiceprint, it is determined that the fifth user has passed the security verification, and the smart TV exits the youth mode and the functionally restricted state. Security verification can also be security verification in other dimensions, and this embodiment does not limit the specific implementation methods of security verification.

[0172] If the smart TV determines that the fifth user is not the target user of the smart TV in youth mode, the smart TV can execute the method provided in the above S202-S204 embodiments, and output a prompt message to prompt other users whose ages meet the unlocking conditions to participate in voiceprint unlocking, which will not be elaborated here.

[0173] In this embodiment, when the electronic device receives only one user's unlocking voice within the first time period and determines that the one user is a target user in a functionally restricted state, the electronic device can further perform security verification on the target user in a functionally restricted state, and when the security verification is passed, the electronic device performs voiceprint unlocking. Since the target user is a user with unlocking authority in a functionally restricted state, the electronic device determines that the user corresponding to the unlocking voice is the target user, and when the target user passes the security verification, the electronic device performs voiceprint unlocking, further improving the reliability of unlocking the electronic device in a functionally restricted state.

[0174] In the above embodiments, various scenarios of voiceprint unlocking that require the participation of at least two persons are introduced. Since the at least two persons who participate in the voiceprint unlocking often involve minors, in order to increase the fun of minors participating in the voiceprint unlocking, in some scenarios, the electronic device may also provide multiple interactive unlocking modes to increase the fun and knowledge of the voiceprint unlocking process.

[0175] In some specific embodiments, for example, the electronic device can respond to the interactive unlocking operation and unlock the electronic device in a certain interactive unlocking mode. In the process of unlocking the functionally limited state in the interactive unlocking mode, the electronic device can obtain the question voice and answer voice input by different users to realize the interesting question and answer when the electronic device is released from the functionally limited state. The interactive unlocking mode refers to a mode of interesting verification through questioning and answering. Among them, the questioning and answering can be about the interaction of different types of content. The interaction of each type of content forms an interactive unlocking mode. For example, an interactive unlocking mode can be a mode of questioning and answering about poetry; for example, another interactive unlocking mode can be a mode of questioning and answering about mathematical operations; for example, another interactive unlocking mode can be a mode of questioning and answering about common sense dialogue. Different interactive unlocking modes correspond to different knowledge reserves. The electronic device can store the knowledge reserves corresponding to different interactive unlocking modes through a local database. Or, the knowledge reserves corresponding to different interactive unlocking modes can be stored in a cloud database, and the electronic device obtains the answers corresponding to the questions by accessing the cloud database, etc. The role of voiceprint unlocking in the interactive unlocking mode is to teach and entertain. Based on this purpose, the interactive unlocking mode can be any mode of enhancing the interaction with minors' education.

[0176] Fig.10 A flow chart of voiceprint unlocking including interactive unlocking mode is given. The voiceprint unlocking method includes: S301, when the electronic device is in a function-restricted state, the electronic device responds to an interactive unlocking operation and obtains a question voice of a sixth user.

[0177] The interactive unlocking operation is used to instruct the electronic device to turn on the interactive unlocking mode and perform voiceprint unlocking in the interactive unlocking mode. The interactive unlocking operation may be the electronic device receiving a user's voice command about "interactive unlocking"; or the interactive unlocking operation may also be the electronic device receiving a user's selection operation for the interactive unlocking mode. For example, the electronic device may display an operation control for selecting voiceprint unlocking in the interactive unlocking mode on the display interface, and upon receiving the user's operation on the operation control, perform voiceprint unlocking in the interactive unlocking mode to obtain the question voice of the sixth user.

[0178] Then, accordingly, if the user does not trigger the interactive unlocking operation, for example, the electronic device receives the user's selection of voiceprint unlocking in direct unlocking mode, then the electronic device adopts the following method: Figure 3-Figure 9 Any of the provided voiceprint unlocking methods can be used to directly unlock multiple people’s voiceprints.

[0179] S302, the electronic device performs voiceprint recognition on the questioning voice to determine the predicted age of the sixth user.

[0180] The specific method of performing voiceprint recognition on speech to obtain predicted age can refer to the above embodiment S102 or S203.

[0181] S303: If the predicted age of the sixth user is within the first age range, the electronic device performs content recognition on the question voice to obtain a first question content corresponding to the question voice.

[0182] In this embodiment, the first age interval may be an area greater than an age threshold. Exemplarily, the age threshold may be 18. The first age interval is used to indicate the age interval corresponding to adults. The predicted age of the sixth user is in the first age interval, which means that the sixth user may be an adult. When the user is an adult, the voice input by the user is used as a question voice. Question voice refers to a voice containing content keywords of a type corresponding to the interactive unlocking mode. The electronic device may perform content recognition on the voice of the sixth user, and determine that it is a question voice when the voice contains content keywords of a type corresponding to the interactive unlocking mode. At the same time, the electronic device performs content recognition on the question voice, and may obtain the first question content corresponding to the question voice. Among them, the electronic device may perform content recognition on the question voice using a system automatic voice recognition model, and specific reference may be made to S102 in the above embodiment.

[0183] For example, the interactive unlocking mode is a mode of asking and answering questions about poetry. When the question voice is "the moon shines brightly before the bed", the electronic device determines that the voice contains keywords related to poetry and determines that it is a question voice. At the same time, the electronic device performs content recognition on the question voice and obtains the first question content ("the moon shines brightly before the bed") corresponding to the question voice. For example, the interactive unlocking mode is a mode of asking and answering questions about mathematical operations. When the question voice is "What is 15+25 equal to?", the electronic device determines that the voice contains keywords related to mathematical operations and determines that it is a question voice. At the same time, the electronic device performs content recognition on the question voice and obtains the first question content corresponding to the question voice ("What is 15+25 equal to") For example, the interactive unlocking mode is a mode of questioning and answering about common sense dialogue. When the question voice is "Stop at a red light", the electronic device determines that the voice contains keywords related to common sense and determines that it is a question voice. At the same time, the electronic device performs content recognition on the question voice and obtains the first question content ("Stop at a red light") corresponding to the question voice. Optionally, in some embodiments, the electronic device may match the seventh user's answer content based on the first question content. Alternatively, the electronic device may first obtain standard answer content based on the first question content, and match the seventh user's answer content based on the standard answer content.

[0184] In some embodiments, S304: The electronic device obtains standard answer content based on the first question content.

[0185] In this embodiment, the electronic device may obtain the standard answer content corresponding to the first question content from a local database; or the electronic device may also access the cloud to obtain the standard answer content corresponding to the first question content from a cloud database.

[0186] For example, when the first question is "The moon shines brightly before the bed", the standard answer obtained by the electronic device may be "I wonder if it is frost on the ground". For example, when the first question is "What is 15+25 equal to?", the standard answer obtained by the electronic device may be "40". For example, when the first question is "Stop at a red light", the standard answer obtained by the electronic device may be "Go at a green light".

[0187] The standard answer content can be used as reference data to verify the correctness of the first answer content corresponding to the answer voice received by the electronic device.

[0188] In some feasible embodiments, the electronic device may detect whether the answer voice of the seventh user is received within a preset fourth time period while acquiring the standard answer content or after acquiring the standard answer content.

[0189] In other feasible embodiments, after obtaining the standard answer content, the electronic device may display all or part of the fields of the standard answer content on the display interface. When the electronic device displays all the fields of the standard answer content, the purpose of the electronic device is to provide the seventh user with a known knowledge for learning. The seventh user can read aloud the standard answer content to form an answer voice. When the electronic device displays part of the fields of the standard answer content, the purpose of the electronic device is to provide the seventh user with a question knowledge for learning. The seventh user can answer based on part of the fields of the standard answer content to form an answer voice. This embodiment does not limit whether to display the standard answer content, and whether to display all or part of the fields of the standard answer content.

[0190] S305: If the electronic device receives the answering voice of the seventh user within the fourth time period, it performs content recognition on the answering voice to obtain the first answering content.

[0191] The fourth duration may be a preset duration. In some feasible examples, the fourth duration may be equal to the third duration. After the electronic device receives the answering voice of the seventh user, the answering voice may be content recognized to obtain the first answering content corresponding to the answering voice. For example, the first answering content may be "It may be frost on the ground". For example, the first answering content may be "50". For example, the first answering content may be "Green light".

[0192] In some optional embodiments, the electronic device may also perform voiceprint recognition on the seventh user to obtain the predicted age of the seventh user. When the predicted age of the seventh user is less than the age threshold, the seventh user is considered to be a minor. When the seventh user is a minor, the minor's voice is used as the answer voice. The electronic device performs content recognition on the answer voice to obtain the first answer content, which can provide an interesting knowledge interaction scene for minors.

[0193] S306: The electronic device performs content matching based on the first question content and the first answer content to obtain a verification result.

[0194] In this embodiment, if S304 is not executed, the electronic device can directly match the first question content with the first answer content; or, after executing S304, the electronic device can match the first answer content with the standard answer content to obtain a verification result.

[0195] The following example illustrates the verification result obtained by matching the first answer content with the standard answer content.

[0196] For example, the first answer is "I suspect it is frost on the ground", and the standard answer is "I suspect it is frost on the ground". The first answer matches the standard answer, and the verification result may be passed.

[0197] For example, the first answer content is "50" and the standard answer content is "40". The first answer content does not match the standard answer content, and the verification result may be verification failure / failed verification.

[0198] For example, the first answer is "green light OK", and the standard answer is "green light OK". The first answer matches the standard answer, and the verification result may be passed.

[0199] If the verification result is passed, the electronic device can perform a voiceprint unlocking operation to exit the functionally restricted state of the electronic device. If the verification result is failed / failed, the electronic device can output a prompt message to prompt the seventh user to re-enter the answer voice. Alternatively, in other possible scenarios, if the number of times the first answer does not match the standard answer exceeds a threshold, the electronic device can output a prompt message refusing to exit the functionally restricted state. Alternatively, in other possible scenarios, the electronic device can output a prompt message to determine whether to unlock, and after receiving the operation to determine unlock, perform a voiceprint unlocking operation to exit the functionally restricted state of the electronic device.

[0200] In some other feasible practical application scenarios, when the electronic device is in a limited function state, it may receive the voices input by two users one after another. For example, the electronic device first receives the voice of the eighth user, and then receives the voice of the ninth user within the fifth time period. Here, the fifth time period may be a preset time period, and in some feasible examples, the fifth time period may be equal to the fourth time period.

[0201] In this embodiment, according to the conventional order of questions, the voice received first by the electronic device can be defaulted as the question voice, and the voice received later can be defaulted as the answer voice. The electronic device can perform voiceprint recognition on the two voices respectively to determine the predicted ages of the two users; in addition, the electronic device can also perform content recognition on the two voices respectively, and perform content matching based on the content corresponding to the two voices (question content and answer content).

[0202] In this scenario, when the question content matches the answer content and the predicted ages of the two users meet the unlocking conditions, the electronic device can exit the function-restricted state.

[0203] In this implementation, the electronic device does not need to specifically distinguish which user is an adult, whose corresponding voice is a questioning voice, and which user is a minor, whose corresponding voice is an answering voice. In this embodiment, the electronic device only needs to determine that the predicted ages of two people meet the unlocking conditions, that is, an adult and a minor, and at the same time, the content corresponding to the voices of the two users matches, to exit the restricted function state. In actual underlying calculations, some data processing steps of the electronic device can be reduced, improving the efficiency of voiceprint unlocking of the electronic device.

[0204] It is understandable that the purpose of question-and-answer interaction is to increase the fun of the voiceprint unlocking process. When the ages of the sixth user and the seventh user meet the unlocking conditions, the verification result of the first answer content and the standard answer content may not actually affect the result of whether to perform voiceprint unlocking.

[0205] In a specific embodiment, Fig.11 Given Fig.10 A scenario diagram of the voiceprint unlocking method provided. Fig.11 and Figure 6 The scenario is the same as above, so I won’t go into details here.

[0206] like Fig.11 As shown, when the smart TV is in youth mode, in one example, the smart TV responds to the interactive unlocking operation, which may be that the smart TV receives a user's voice command about "interactive unlocking"; or, it may be, Fig.11As shown, the smart TV can display an interactive unlocking interface on the display screen. Optionally, the interactive unlocking interface includes a first control. If the smart TV receives an operation of the user on the first control, the smart TV responds to the operation and unlocks the function-restricted state in an interactive unlocking mode.

[0207] If the smart TV does not receive any operation of the user on the first lock control within a certain period of time, the smart TV adopts the following method: Figure 3-Figure 9 The voiceprint unlocking method provided in any one of the embodiments is used to perform voiceprint unlocking. Alternatively, the interactive unlocking interface further includes a second control. When the smart TV receives the user's operation on the second control, the smart TV uses the following method: Figure 3-Figure 9 The voiceprint unlocking method provided in any one of the embodiments is used to unlock the voiceprint, which will not be described here.

[0208] like Fig.11 The voiceprint unlocking method in the interactive unlocking mode shown is illustrated by one of the above embodiments. When the smart TV is in a limited function state, a prompt message for prompting the user to ask questions can be displayed on the display interface. After receiving the voice of the sixth user, the smart TV performs voiceprint recognition on the voice, and after determining that the predicted age of the sixth user is in the first age range, the sixth user is used as the questioner in the interactive unlocking mode. The voice corresponding to the sixth user is used as the question voice. The smart TV performs content recognition on the question voice and obtains the question content corresponding to the question voice. Among them, the smart TV can perform content recognition on the question voice through the system automatic voice recognition model to obtain the question content corresponding to the question voice.

[0209] After the smart TV obtains the question content, the smart TV can query the standard answer content corresponding to the question content from the local interactive database or the cloud database. After the smart TV obtains the standard answer content, all or part of the fields of the standard answer content can be displayed on the display screen. The smart TV displays all or part of the fields of the standard answer content in order to obtain the seventh user's answer voice to the standard answer content. The smart TV performs content recognition on the answer voice to obtain the answer content of the answer voice. When the answer content matches the standard answer content, the voiceprint unlocking of the interactive unlocking mode of the electronic device is performed.

[0210] Or, in some other embodiments, such as Fig.11As shown, after the smart TV obtains the standard answer content, the electronic device can output a prompt message to read aloud the standard answer content. The prompt message contains the question content and the standard answer content. The answer voice generated when the seventh user reads aloud is obtained. The smart TV performs content recognition on the answer voice to obtain the answer content of the answer voice. In the case where the answer content contains the standard answer content, it can also be determined that the answer content matches the standard answer content, and the voiceprint unlocking of the interactive voiceprint unlocking scenario of the electronic device is performed.

[0211] Take the interactive unlocking mode as an example of a mode of questioning and answering about poetry. For example, the smart TV needs to access the cloud to obtain standard answer content, and a large number of poetry segments are stored in the cloud database. The smart TV performs content recognition on the question voice of the sixth user, and the first question content obtained is "Bright moonlight in front of the bed". The smart TV sends a query request carrying "Bright moonlight in front of the bed" to the cloud to obtain the standard answer content corresponding to "Bright moonlight in front of the bed". For example, the standard answer content is "Suspected to be frost on the ground". The smart TV can display the complete sentence of the standard answer content "Suspected to be frost on the ground" on the display screen, or the smart TV can display a partial sentence of the standard answer content "Suspected to be __ __ frost" on the display screen. The purpose of the smart TV displaying the complete sentence of the standard answer content "Suspected to be frost on the ground" is to enable the seventh user (such as a minor) to input the answer voice by reading the first answer content aloud. The purpose of the smart TV displaying the partial sentence of the standard answer content "Suspected to be frost on the ground" is to realize the knowledge test of the seventh user (such as a minor) on the standard answer content, and obtain the answer voice when the seventh user recites the complete sentence of the standard answer content.

[0212] The smart TV performs content recognition on the answer voice and obtains the answer content. If the answer content is "The moon shines brightly in front of the bed". The answer content matches the standard answer content, and the smart TV performs voiceprint unlocking in the interactive unlocking mode of the electronic device, and the smart TV exits the youth mode and the limited function state. If the answer content does not match the standard answer content, a prompt message can be output to prompt the seventh user to re-enter the answer voice. If the number of times that the answer content does not match the standard answer content exceeds a threshold, the smart TV can output a prompt message refusing to exit the youth mode.

[0213] Let's take a more specific example. Fig.12 Schematic diagram of a scene of a display interface of a smart TV shown in FIG. For example, when the smart TV is in youth mode, the interactive unlocking interface displayed is a "poetry dialogue interface". The poetry dialogue interface includes a first control and a second control of the "poetry dialogue" mode. When the smart TV receives the user's operation on the second control, the smart TV adopts the following method: Figure 3-Figure 9The voiceprint unlocking method provided by any one of the embodiments is used to perform voiceprint unlocking. When the smart TV receives the user's operation on the first control, the smart TV loads the automatic speech recognition model and displays a prompt message prompting the user to input a question voice on the display interface.

[0214] When the smart TV receives a voice question from a parent, it identifies the question and obtains the question content. For example, the question content is "The moon shines brightly before my bed". The smart TV uses the question content as the previous sentence of the poem (the question sentence) and sends a query request carrying the question content to the cloud to obtain the standard answer content returned by the cloud. The smart TV can display all or part of the fields of the standard answer content on the display interface to prompt the user to give a voice answer. For example, Fig.12 The smart TV obtains the minor's answer voice, performs content recognition on the answer voice, and uses the minor's answer as the answer content. The smart TV can match the standard answer content with the answer content, and if they match, a successful verification result can be determined. Fig.12 In the example of , after the verification is successful, the smart TV can exit the youth mode. Otherwise, it is determined that the verification has failed.

[0215] Fig.13 Several schematic diagrams of smart TV interactive unlocking interfaces are given. Fig.13 As shown in (a), after the smart TV obtains the standard answer content, it may not display the standard answer content. The smart TV may display the question information about the first question content in the interactive unlocking interface. For example, the question information of the first question content may be "What is the next sentence of the moonlight before the bed?" or, Fig.13 As shown in (b), after the smart TV obtains the standard answer content, the electronic device can output prompt information for reading aloud. The prompt information includes the first question content and the standard answer content.

[0216] In this embodiment, whether the answer of the minor is verified or not is not a strong basis for voiceprint unlocking. In essence, as long as there are two users whose ages meet the unlocking conditions participating in the voiceprint unlocking, the electronic device can be unlocked by voiceprint. For the interactive unlocking scenario, the purpose is to increase the fun of the unlocking process. Parents and children interact during the unlocking process and learn different types of knowledge in a relaxed and pleasant atmosphere. It can also effectively enhance communication between parents and children, reduce children’s resistance to the youth mode (the electronic device is in a functionally restricted state), and enhance the user experience. This embodiment does not limit the specific interactive implementation details.

[0217] It should be noted that the personal information used in the technical solution of this application is limited to information for which the individual's separate consent has been obtained, including but not limited to notifying and reminding the user to read the relevant user agreement (notification) and sign the agreement (authorization) including authorization of relevant user information before the user uses the function.

[0218] In the technical solutions disclosed in this application, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the relevant laws and regulations and do not violate public order and good morals.

[0219] The voiceprint unlocking method provided in the embodiment of the present application can be applied to electronic devices with a youth mode. Exemplarily, the electronic device can be a portable computer (such as a mobile phone), a tablet computer, a laptop computer, a personal computer (PC), a wearable electronic device (such as a smart watch), an augmented reality (AR) device, a virtual reality (VR) device, and the like. For example, when the electronic device is a mobile phone, the voiceprint unlocking method can be applied to unlocking the youth mode of the mobile phone (the device itself), or the voiceprint unlocking method can also be applied to unlocking the youth mode of each application / function with a youth mode in the mobile phone. Specifically, the voiceprint unlocking method can be applied to unlocking the youth mode of gallery applications, social applications, game applications, etc. in the mobile phone.

[0220] In addition, the child lock mode is similar to the youth mode, both of which are restrictions on the functions / partial functions of electronic devices. Therefore, the voiceprint unlocking method provided in the embodiment of the present application can also be applied to smart home devices with a child lock mode. For example, the smart home device can be a smart washing machine / dryer, a smart TV, a smart refrigerator, a smart oven, a smart dishwasher, a smart hanging iron, etc. The following embodiments do not specifically limit the specific form of the electronic device.

[0221] Fig.14 A schematic structural diagram of an electronic device 100 is shown.

[0222] The electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a sensor module 180, a display screen 194, etc.

[0223] It is to be understood that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may include more or fewer components than shown in the figure, or combine some components, or separate some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0224] The processor 110 may include one or more processing units, for example, the processor 110 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0225] The controller may be the nerve center and command center of the electronic device 100. The controller may generate an operation control signal according to the instruction operation code and the timing signal to complete the control of fetching and executing instructions.

[0226] The processor 110 may also be provided with a memory for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory may store instructions or data that the processor 110 has just used or cyclically used. If the processor 110 needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

[0227] In this embodiment, the processor 110 may serve as the execution body of the voiceprint unlocking method.

[0228] In some embodiments, the processor 110 may include one or more interfaces. The interface may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0229] It is understandable that the interface connection relationship between the modules illustrated in the embodiment of the present invention is only a schematic illustration and does not constitute a structural limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may also adopt different interface connection methods in the above embodiments, or a combination of multiple interface connection methods.

[0230] The charging management module 140 is used to receive charging input from a charger. The charger may be a wireless charger or a wired charger. In some wired charging embodiments, the charging management module 140 may receive charging input from a wired charger through the USB interface 130. In some wireless charging embodiments, the charging management module 140 may receive wireless charging input through a wireless charging coil of the electronic device 100. While the charging management module 140 is charging the battery 142, it may also power the electronic device through the power management module 141.

[0231] The power management module 141 is used to connect the battery 142, the charging management module 140 and the processor 110. The power management module 141 receives input from the battery 142 and / or the charging management module 140, and provides power to the processor 110, the internal memory 121, the external memory, the display screen 194 and the wireless communication module 160. The power management module 141 can also be used to monitor parameters such as battery capacity, battery cycle number, battery health status (leakage, impedance), etc. In some other embodiments, the power management module 141 can also be set in the processor 110. In other embodiments, the power management module 141 and the charging management module 140 can also be set in the same device.

[0232] The wireless communication function of the electronic device 100 can be implemented through the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modem processor and the baseband processor.

[0233] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals.

[0234] The mobile communication module 150 can provide solutions for wireless communications including 2G / 3G / 4G / 5G, etc., applied to the electronic device 100. The mobile communication module 150 can receive electromagnetic waves through the antenna 1, and filter, amplify, and process the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modulation and demodulation processor, and convert it into electromagnetic waves for radiation through the antenna 1. In some embodiments, at least some of the functional modules of the mobile communication module 150 can be set in the processor 110. In some embodiments, at least some of the functional modules of the mobile communication module 150 can be set in the same device as at least some of the modules of the processor 110.

[0235] The wireless communication module 160 can provide wireless communication solutions including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc., which are applied to the electronic device 100. The wireless communication module 160 can be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2, modulates the frequency of the electromagnetic wave signal and performs filtering processing, and sends the processed signal to the processor 110. The wireless communication module 160 can also receive the signal to be sent from the processor 110, modulate the frequency of it, amplify it, and convert it into electromagnetic waves for radiation through the antenna 2.

[0236] In some embodiments, the antenna 1 of the electronic device 100 is coupled to the mobile communication module 150, and the antenna 2 is coupled to the wireless communication module 160, so that the electronic device 100 can communicate with the network and other devices through wireless communication technology. The wireless communication technology may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC, FM, and / or IR technology. The GNSS may include a global positioning system (GPS), a global navigation satellite system (GLONASS), a Beidou navigation satellite system (BDS), a quasi-zenith satellite system (QZSS) and / or a satellite based augmentation system (SBAS).

[0237] In this embodiment, for example, Fig.10 and Fig.11 In the provided embodiment, the electronic device can send a first question to a cloud server through a wireless communication function to obtain a first answer corresponding to the first question, and perform a voiceprint unlocking operation in an interactive voiceprint unlocking scenario based on a matching result between the second answer and the first answer.

[0238] The electronic device 100 implements the display function through a GPU, a display screen 194, and an application processor. The GPU is a microprocessor for image processing, which connects the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 110 may include one or more GPUs that execute program instructions to generate or change display information.

[0239] The display screen 194 is used to display images, videos, etc. The display screen 194 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the electronic device 100 may include 1 or N display screens 194, where N is a positive integer greater than 1.

[0240] In this embodiment, the electronic device may display the first answer or a partial field of the first answer on the display screen.

[0241] In addition, when the user age corresponding to the user's voice data does not meet the unlocking conditions, the electronic device can display a prompt message on the display screen.

[0242] The external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100. The external memory card communicates with the processor 110 through the external memory interface 120 to implement a data storage function, such as storing music, video and other files in the external memory card.

[0243] The internal memory 121 can be used to store computer executable program codes, which include instructions. The processor 110 executes various functional applications and data processing of the electronic device 100 by running the instructions stored in the internal memory 121. The internal memory 121 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc. The data storage area may store data created during the use of the electronic device 100 (such as audio data, a phone book, etc.), etc. In addition, the internal memory 121 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc.

[0244] The electronic device 100 can implement audio functions through the audio module 170, speakers, microphones, and application processors, such as music playback, recording, etc. Optionally, the audio module 170 may also include other devices such as an earphone interface and a receiver.

[0245] The audio module 170 is used to convert digital audio information into analog audio signal output, and is also used to convert analog audio input into digital audio signals. The audio module 170 can also be used to encode and decode audio signals. In some embodiments, the audio module 170 can be arranged in the processor 110, or some functional modules of the audio module 170 can be arranged in the processor 110.

[0246] The speaker, also called a "speaker", is used to convert an audio electrical signal into a sound signal. The electronic device 100 can play audio through the speaker.

[0247] Microphone, also known as "microphone" or "microphone", is used to convert sound signals into electrical signals. Microphone can also be understood as an audio collection device.

[0248] In this embodiment, the electronic device can collect the sound signal input by the user through the microphone, and the audio module 170 converts the user's sound signal into an electrical signal, and digitizes the electrical signal to obtain a digital audio signal. The audio module 170 can send the digital audio signal to the processor 110. The processor 110 uses the voiceprint unlocking method provided in the embodiment of the present application to perform voiceprint recognition and other processing on the digital audio signal. Specifically, the processor 110 can perform voiceprint recognition on the digital audio signal through a preset voiceprint recognition model, the processor 110 can perform content recognition on the digital audio signal through an automatic voice recognition model, and so on. The processor 110 can also store the digital audio signal in a designated storage space.

[0249] Fig.15 A possible structural diagram of the electronic device involved in the above embodiments is shown. Fig.15 The electronic device 1500 shown includes a processing module 1501, an audio acquisition module 1502, and a storage module 1503. In some optional embodiments, the electronic device 1500 may further include a display module 1504.

[0250] The processing module 1501 may be a central processing unit (CPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The processor may include an application processor and a baseband processor. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0251] For example, the processing module 1501 may be as follows Fig.14 The processor 110 shown in FIG. 110; the audio acquisition module 1502 may be as follows Fig.14 The microphone in the audio module 170 shown; the storage module 1503 can be as follows Fig.14 The internal memory 121 shown; the display module 1504 can be as follows Fig.14 The electronic device provided in the embodiment of the present application can be Fig.14 An electronic device 100 is shown.

[0252] The present application also provides a chip system (eg, a system on a chip (SoC)), such as Fig.16 As shown, the chip system includes at least one processor 1601 and at least one interface circuit 1602. The processor 1601 and the interface circuit 1602 can be interconnected via lines. For example, the interface circuit 1602 can be used to receive signals from other devices (such as a memory of an electronic device). For another example, the interface circuit 1602 can be used to send signals to other devices (such as a processor 1601 or a camera of an electronic device). Exemplarily, the interface circuit 1602 can read instructions stored in the memory and send the instructions to the processor 1601. When the instructions are executed by the processor 1601, the electronic device can execute the various steps in the above embodiments. Of course, the chip system can also include other discrete devices, which are not specifically limited in the embodiments of the present application.

[0253] An embodiment of the present application also provides a computer-readable storage medium, which includes computer instructions. When the computer instructions are executed on the above-mentioned electronic device, the electronic device executes each function or step executed by the electronic device 100 in the above-mentioned method embodiment.

[0254] The embodiment of the present application further provides a computer program product, which, when executed on a computer, enables the computer to execute the functions or steps executed by the electronic device 100 in the above method embodiment. For example, the computer may be the above electronic device 100.

[0255] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0256] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0257] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0258] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0259] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0260] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application shall be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A voiceprint unlocking method, characterized in that: The method comprises: When the electronic device is in a function-restricted state, acquiring an unlocking voice; the function-restricted state includes function-restricted system services in the electronic device or function-restricted applications in the electronic device; If the electronic device obtains unlocking voices of at least two users within the first time period, performing voiceprint recognition on the unlocking voices of the respective users to determine the predicted age of the respective users; If the predicted ages of two users among the at least two users meet the unlocking condition, the electronic device exits the function-restricted state.

2. The method according to claim 1, characterized in that The predicted ages of the two users meet the unlocking conditions, including: The age difference between the predicted ages of the two users is greater than or equal to a difference threshold; Alternatively, the predicted age of one of the two users is within a first age range, and the predicted age of the other of the two users is within a second age range; the first age range does not overlap with the second age range.

3. The method according to claim 1 or 2, characterized in that: The method further comprises: When the electronic device is in the function-restricted state, if a first unlocking voice of a first user is acquired within the first time period, a first prompt message is output; the first prompt message is used to prompt a user whose age meets the unlocking condition to participate in unlocking; If the electronic device receives a second unlocking voice of the second user within the second time period, performing voiceprint recognition on the second unlocking voice to determine the predicted age of the second user; If the predicted age of the first user and the predicted age of the second user satisfy the unlocking condition, the electronic device exits the function-restricted state.

4. The method according to claim 1 or 2, characterized in that: The electronic device includes a plurality of function-restricted states, and the function-restricted states correspond to target users of age groups with unlocking authority; The method further comprises: When the electronic device is in the function-restricted state, if a third unlocking voice of a third user is obtained within the first time period, and the third user is determined to be a target user corresponding to the function-restricted state based on the predicted age of the third user, the electronic device exits the function-restricted state.

5. The method according to claim 4, characterized in that The method further comprises: If the electronic device determines, based on the predicted age of the third user, that the third user is not a target user corresponding to the functional restriction state, the electronic device outputs a second prompt message; the second prompt message is used to prompt the target user who needs to match the age to participate in unlocking; If the electronic device receives a fourth unlocking voice of a fourth user within a third time period, performing voiceprint recognition on the fourth unlocking voice to determine the predicted age of the fourth user; If the predicted age of the third user and the predicted age of the fourth user satisfy the unlocking condition, the electronic device exits the function-restricted state.

6. The method according to claim 1 or 2, characterized in that: The electronic device includes a plurality of function-restricted states, and the function-restricted states correspond to target users of age groups with unlocking authority; The method further comprises: When the electronic device is in the function-restricted state, if a fifth unlocking voice of a fifth user is acquired within the first time period, and the fifth user is determined to be a target user corresponding to the function-restricted state based on the predicted age of the fifth user, the electronic device performs security verification on the fifth user; the security verification includes password verification; When the fifth user passes the security verification, the electronic device exits the function-restricted state.

7. The method according to claim 1, characterized in that The method further comprises: When the electronic device is in the function-restricted state, the electronic device obtains a question voice of a sixth user in response to an interactive unlocking operation; The electronic device performs voiceprint recognition on the questioning voice to determine the predicted age of the sixth user; If the predicted age of the sixth user is within the first age range, the electronic device performs content recognition on the question voice to obtain a first question content corresponding to the question voice; If the electronic device receives the answering voice of the seventh user within the fourth time period, the electronic device performs content recognition on the answering voice to obtain the first answering content; If the first answer content matches the first question content, the electronic device exits the function-restricted state.

8. The method according to claim 7, characterized in that After the electronic device receives the seventh user's answer voice within the fourth time period, the method further includes: The electronic device performs voiceprint recognition on the answering voice to determine the predicted age of the seventh user; The electronic device performs content recognition on the answer voice to obtain first answer content, including: If the predicted age of the seventh user is within the second age range, the electronic device performs content recognition on the answering voice to obtain the first answering content.

9. The method according to claim 1, characterized in that: The method further comprises: When the electronic device is in the function-restricted state, the electronic device obtains a question voice of an eighth user in response to an interactive unlocking operation; The electronic device performs content recognition on the question voice to obtain a second question content corresponding to the question voice; If the electronic device receives the answering voice of the ninth user within the fifth time period, the electronic device performs content recognition on the answering voice to obtain the second answering content; The electronic device performs voiceprint recognition on the question voice and the answer voice respectively to determine the predicted age of the eighth user and the predicted age of the ninth user; When the second question content matches the second answer content, and the predicted age of the eighth user and the predicted age of the ninth user meet the unlocking condition, the electronic device exits the function-restricted state; Among them, the predicted age of the eighth user and the predicted age of the ninth user meet the unlocking condition, including: the age difference between the predicted age of the eighth user and the predicted age of the ninth user is greater than or equal to a difference threshold; or, the predicted age of the eighth user is in the first age range.

10. The method according to claim 7 or 9, characterized in that: The method further comprises: The electronic device displays a question-and-answer interface; the question-and-answer interface includes fields related to question content.

11. The method according to claim 7 or 9, characterized in that: The method further comprises: The electronic device displays an interactive unlocking interface; the interactive unlocking interface includes a first control and a second control; If the electronic device receives the interactive unlocking operation acting on the first control, the electronic device performs a step of acquiring the question voice of the sixth user, or the electronic device performs a step of acquiring the question voice of the eighth user; If the electronic device receives a direct unlocking operation acting on the second control, the step of the electronic device acquiring an unlocking voice is executed.

12. The method according to claim 1 or 2, characterized in that: The electronic device performs voiceprint recognition on the unlocking voice of each user to determine the predicted age of each user, including: The electronic device inputs the unlocking voice of each user into a voiceprint recognition model for feature extraction and age classification to determine the predicted age of each user.

13. An electronic device comprising an audio acquisition device, a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 12.

14. A chip comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to perform the steps of implementing the method according to any one of claims 1 to 12.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 12 are implemented.

16. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 12 are implemented.

Images