WO2017181610A1

WO2017181610A1 - Voice unlocking method and device

Info

Publication number: WO2017181610A1
Application number: PCT/CN2016/101055
Authority: WO
Inventors: 王蕊
Original assignee: 乐视控股（北京）有限公司; 乐视致新电子科技（天津）有限公司
Priority date: 2016-04-19
Filing date: 2016-09-30
Publication date: 2017-10-26
Also published as: CN105933765A

Abstract

Provided in the embodiments of the present invention are a voice unlocking method and device. The voice unlocking method comprises: acquiring, by means of a television client, a voice command from a user, extracting acoustic characteristic information from the voice command, and determining, according to the acoustic characteristic information, the user type of the user; determining whether the user type is identical to a preset user type; if the user type is identical to the preset user type, recognizing the voice command, and determining, according to the correlation between the voice command and a preset unlocking command, whether the voice command corresponds to the preset unlocking command; and if the determination result is yes, performing, according to the preset unlocking command, an unlocking operation corresponding to the preset unlocking command. Accordingly, further provided in the embodiments of the present invention is a voice unlocking device, which, according to the technical solutions provided in the embodiments of the present invention, determines the user type while acquiring the voice command, and performs the unlocking if the user type is identical to the preset user type, facilitating the unlocking operation while preventing users who do not satisfy the requirements from performing the operation.

Description

Voice unlocking method and device

cross reference

The present application is hereby incorporated by reference in its entirety in its entirety in its entirety in its entirety in its entirety in the the the the the the the the

Technical field

The embodiments of the present invention relate to the field of information interaction processing technologies, and in particular, to a voice unlocking method and apparatus.

Background technique

The control mode of the traditional TV is mainly based on the remote control. The infrared connection method makes the remote control and the TV connect, and generates commands by means of physical buttons, thereby realizing the user's control of the television. With the development of technology, the traditional television has Gradually moving towards the direction of Internet TV, no matter from the content of TV or the operation mode of TV, great changes have taken place. The traditional control method using remote control is somewhat troublesome.

At present, the content of TV is more and more rich, including content that is not suitable for young people. In order to prevent children from involving and watching too many multimedia content that is not suitable for young people, the usual practice is to turn on the TV and switch functions. Permission management, by setting a password to control the user to enter some application permissions, the user needs to set the password first, and reserve the mobile phone number for the loss of the password to retrieve, when booting or entering the locked application, Adjust the keyboard, and use the up, down, left and right direction keys to move the keyboard cursor to complete the password input to complete the password unlocking. The operation process is very cumbersome. When you forget the password, you need to send the short message to retrieve the password.

Therefore, based on the technical defects in the prior art, an interactive control scheme that is simple, quick and convenient, and capable of booting or entering a locked application through voice recognition technology is a technical problem to be solved currently.

Summary of the invention

The embodiment of the invention provides a voice unlocking method and device, which is used to solve the cumbersome manual operation of the keyboard when booting or entering a locked application when the power is turned on during the booting of the TV and the function switching. It also avoids the hassle of forgetting the password and needing to retrieve the password by sending a text message.

The embodiment of the invention further provides a voice unlocking electronic device, a non-transitory computer storage medium and a computer program product.

In view of this, an embodiment of the present invention provides a voice unlocking method, including:

Obtaining, by the television client, a voice instruction of the user, extracting acoustic feature information of the voice instruction, and determining a user type of the user according to the acoustic feature information;

Determining whether the user type is consistent with a preset user type;

And if the user type is consistent with the preset user type, the voice command is identified, and the voice command and the preset unlock command are determined according to a correspondence between the voice command and the preset unlock command. Whether it corresponds;

If the determination result is yes, the unlocking operation corresponding to the preset unlocking instruction is performed according to the preset unlocking instruction.

Correspondingly, the embodiment of the present invention further provides a voice unlocking apparatus, including: a television client, where the television client includes:

An acquiring module, configured to acquire a voice instruction of the user, extract acoustic characteristic information of the voice instruction, and determine a user type of the user according to the acoustic feature information;

a determining module, configured to determine whether the user type is consistent with a preset user type;

An identification module, configured to: if the user type is consistent with the preset user type, identify the voice instruction, and determine the voice instruction according to a correspondence between the voice instruction and the preset unlocking instruction Whether it corresponds to the preset unlock command;

And an execution module, configured to perform an unlocking operation corresponding to the preset unlocking instruction according to the preset unlocking instruction, if the determination result is yes.

Embodiments of the present invention also provide a non-transitory computer storage medium, which is stored in a computer executable The computer executable instructions are used to perform any of the above described voice unlocking methods of the present application.

An embodiment of the present invention provides a voice unlocking electronic device, including: at least one processor;

a memory communicatively coupled to the at least one processor; wherein

The memory stores instructions executable by the one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

Determining whether the user type is consistent with a preset user type;

Embodiments of the present invention also provide a computer program product, the computer program product comprising a computing program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions, when the program instructions are executed by a computer The computer is caused to perform any of the above-described voice unlocking methods of the present application.

The method and device for unlocking a voice provided by the embodiment of the present invention acquires the acoustic feature information in the voice command of the user, and determines the user type according to the acoustic feature information, and identifies the user type according to the preset user type. The user's voice command performs an unlocking operation corresponding to the preset unlocking command according to the correspondence between the voice command and the preset unlocking command, and solves the problem in the prior art that when the television is turned on and the function is switched, the rights management is performed. When the device is powered on or enters the locked application, the manual operation of the keyboard is cumbersome, and the trouble of forgetting the password to retrieve the password by sending the short message is avoided. The technical solution provided by the embodiment of the present invention facilitates the user to unlock the operation. At the same time, it can effectively prevent users who do not meet the requirements from performing inappropriate operations. When the unlocking operation is performed, the operation of the user is ensured to be simple, convenient, and convenient, and the user experience is improved.

DRAWINGS

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description of the drawings used in the embodiments or the prior art description will be briefly described below. Obviously, the drawings in the following description It is a certain embodiment of the present invention, and other drawings can be obtained from those skilled in the art without any creative work.

FIG. 1 is a flowchart of a method for unlocking a voice according to an embodiment of the present invention;

2 is a schematic structural diagram of an apparatus for unlocking a voice according to an embodiment of the present invention;

3 is a schematic structural diagram of an apparatus for preferentially unlocking a voice according to an embodiment of the present invention;

4 is a schematic diagram of an application scenario of a method for unlocking a voice according to an embodiment of the present invention;

FIG. 5 is a schematic structural diagram of an electronic device for unlocking a voice according to an embodiment of the present invention.

detailed description

The technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. It is a partial embodiment of the invention, and not all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

The traditional way of operating the TV with the remote control is very troublesome. In the interactive way, the appearance of voice control is another possibility of TV control, whether it is a cold start (the voice boot mode when the TV is off), or General TV control, voice can achieve full control of the terminal.

At present, the content of TV is more and more rich, including content that is not suitable for young people. In order to prevent children from involving and watching too many multimedia content that is not suitable for young people, the usual practice is to turn on the TV and switch functions. Permission management, by setting a password to control the user to enter some application permissions, the user needs to set the password first, and reserve the mobile phone number for the loss of the password to retrieve, when booting or entering the locked application, Tune up the keyboard and Move the keyboard cursor through the up, down, left and right direction keys to complete the password input to complete the password unlocking. The operation process is very cumbersome. When you forget the password, you need to send the short message to retrieve the password.

If you can use the voice recognition technology to boot or enter the unlocking operation of the locked application, you can save the cumbersome manual operation of the keyboard, and avoid the trouble of forgetting the password and need to send the text message to retrieve the password.

In view of the above, the embodiment of the present invention provides a method and an apparatus for unlocking a voice to solve the above problems. The following describes the embodiments of the present invention in detail with reference to the accompanying drawings and embodiments. The process of applying technical means to solve technical problems and achieve technical efficacy can be fully understood and implemented.

Embodiment 1

FIG. 1 is a flowchart of a method for unlocking a voice according to an embodiment of the present invention. Referring to FIG. 1 , an embodiment of the present invention provides a voice unlocking method, including:

Step S101: Acquire the user's voice instruction through the television client, extract the acoustic feature information of the voice instruction, and determine the user type of the user according to the acoustic feature information;

The generation of human speech is a complex physiological and physical process between the human language center and the vocal organs. The vocal organs used by people in speech--the tongue, teeth, throat, lungs, and nasal cavity are very different in size and shape. Therefore, the voiceprints of any two people are different. Because each person's vocal organs are different, therefore, according to the difference of voiceprints in human speech, the acoustic characteristics information can be extracted to distinguish different people. The sound or the judgment is whether the voice of the same person, the voice of the different person can distinguish the age, the gender, and the like of the person. The embodiment of the present invention is based on the above principle, and the TV client is used when the user uses the television client. After obtaining the voice instruction of the user, the user extracts the acoustic feature information in the voice instruction to determine the user type of the user, including but not limited to adults and children, and also includes a man, a woman, an elderly person, etc., after determining the type of the user, Step 102 is performed, and when the acoustic feature information of the voice instruction is extracted, the cloud service may be Extraction, and the extracted voiceprint information back to television client.

Step S102: determining whether the user type is consistent with the preset user type;

After determining the user type of the user, determining whether the user type is consistent with the preset user type, for example, the preset user type is an adult, and when the user type determined by step S101 is an adult, indicating the user type and the preset user type. If the user type is determined to be inconsistent with the preset user type, the user does not respond to the voice command or gives an error prompt.

Step S103: If the user type is consistent with the preset user type, the voice instruction is recognized, and according to the correspondence between the voice instruction and the preset unlocking instruction, determining whether the voice instruction corresponds to the preset unlocking instruction;

If the user type is consistent with the preset user type, indicating that the user is a user who can perform operations, the user's voice command is recognized, the recognized voice command is compared with the preset unlock command, and the voice command and the preset unlock are used according to the voice command and the preset unlocking command. Corresponding relationship between the instructions, when the voice command and the preset unlock command correspond to each other, the user's voice command is considered to be correct, and step S104 is performed. If the voice command does not correspond to the preset unlock command, the user voice command is considered incorrect, To respond, or to prompt an error message, the preset unlocking command is preset by the user. In the setting unlocking command interface, the user inputs any unlocking instruction, for example: "I am a parent", "I am an adult", "unlock" Etc., the input unlock command is saved to generate a preset unlock command, and different applications can set different or the same unlock command. For example, the user sets an unlock command for the boot application, the movie application, the game application, and the like, and the boot application setting is unlocked. The instruction is "I am a parent" and the unlocking command for the movie application is "I am big." "Man", the "I am an adult" of the game application, when the user wants to start the application or enter the movie application, the game application needs to perform an unlocking operation, and input a voice command consistent with the preset unlocking instruction to execute step S104.

Step S104: If the determination result is YES, the unlocking operation corresponding to the preset unlocking instruction is performed according to the preset unlocking instruction.

When the voice command input by the user and the preset unlock command correspond to each other, the unlocking operation is performed according to the preset unlocking command, thereby performing a power-on operation or entering the television application, and performing an unlocking operation according to the preset unlocking instruction, preferably, the embodiment of the present invention preferably And performing the unlocking operation corresponding to the preset unlocking instruction according to the preset unlocking instruction, further comprising:

When the TV client is in the off state, the power-on unlocking operation is performed according to the preset unlocking instruction, so that the television client is cold-started; or

When the TV client is in the power-on state, the application unlocking operation is performed according to the preset unlocking instruction, so as to unlock the application corresponding to the preset unlocking command and enter the application.

Specific example: Example 1: When the user is using the TV, the TV is turned off, but the TV is connected to the power supply. When the user inputs the voice command “I am a parent”, the TV obtains the voice command “I am a parent”. After that, the acoustic feature information in the user voice instruction is extracted, and the user type of the user is determined. When the determined user type is consistent with the preset user type “adult”, the “I am a parent” voice command and the preset unlock are used. The instruction compares, according to the correspondence between the voice command and the preset unlocking command, and judges that “I am a parent” is consistent with the preset unlocking instruction, the television performs an unlocking operation, starts up and starts, and completes the cold start of the television.

Example 2: When the user uses the TV movie application, the movie application is locked, and the lock screen is popped up. When the user inputs the voice command “I am an adult”, the TV obtains the voice command “I am an adult”. Extracting the acoustic feature information in the user voice command to determine the user type of the user. When the determined user type is consistent with the preset user type “adult”, the “I am an adult” voice command and the preset unlocking command are performed. In contrast, according to the correspondence between the voice command and the preset unlocking command, it is determined that "I am an adult" is consistent with the preset unlocking command, and then the television performs an unlocking operation and enters the movie application.

The method for unlocking a voice provided by the embodiment of the present invention acquires the acoustic feature information in the voice command of the user, and determines the user type according to the acoustic feature information. When the user type is consistent with the preset user type, the user is identified. The voice command performs an unlocking operation corresponding to the preset unlocking command according to the correspondence between the voice command and the preset unlocking command, and solves the problem that the prior art performs the power-on management when the television is turned on and the function is switched. When the user enters the locked application, the cumbersome manual operation of the keyboard is adjusted, and the trouble of forgetting the password to retrieve the password by sending the short message is avoided. The technical solution provided by the embodiment of the present invention can facilitate the unlocking operation of the user. Effectively avoiding users who do not meet the requirements to perform inappropriate operations, and ensuring the user's operation is simple and convenient when the unlocking operation is performed, thereby improving the user experience.

The embodiments of the present invention are described in detail below, and need to be described in the embodiments of the present invention. The examples are only for explaining the progress of the embodiments of the present invention, and are not intended to be unduly limited by the embodiments of the present invention. The examples are only some examples in the embodiments of the present invention, not all examples, and the technical fields to which the embodiments of the present invention are applied. Including but not limited to the field of smart terminals, such as televisions, mobile phones, etc., the field of transportation, such as the automotive field, and other technical fields with voice recognition capabilities.

For the step S101, when determining the user type, the embodiment of the present invention preferably determines the user type of the user according to the acoustic feature information, and further includes:

Extracting acoustic feature information of the voice instruction and comparing the similarity with the acoustic feature information pre-existing in the acoustic feature information library;

Obtaining acoustic feature information in an acoustic feature information base having a similarity greater than or equal to the similarity threshold;

The user type of the user is determined according to the acoustic feature information in the acquired acoustic feature information library.

After acquiring the user voice instruction, extracting the acoustic feature information in the voice command, and comparing the similarity with the acoustic feature in the acoustic feature information database, and comparing the acoustic feature information in the acoustic feature information base with the similarity greater than or equal to the similarity threshold Extracting, determining the user type of the user according to the acoustic feature information in the acquired acoustic feature information database.

The key condition for determining the user type of the user is that the acoustic feature information in the voice command and the acoustic feature information in the acoustic feature information database are greater than or equal to the similarity threshold, and the acoustic feature information base needs to be established in advance before the similarity comparison is performed. Preferably, the embodiment of the present invention compares the similarity with the acoustic feature information in the pre-existing acoustic feature information database, and further includes: establishing the acoustic feature information database, including: collecting at least two voice information, and extracting each acquired Acoustic feature information of the voice information, wherein the voice information includes voice information of the adult and voice information of the child;

According to the preset grouping strategy, the acoustic feature information of the collected voice information is divided into an adult group and a child group, and is stored in the acoustic feature information base.

When establishing the acoustic feature information base, it is necessary to collect the user's voice information, and collect voice information of at least two users. The voice information should include the voice information of the adult and the voice information of the child, and the acoustic features in the collected user voice information. Performing extraction, and grouping the acoustic feature information in the extracted user voice information according to a preset grouping strategy, and the preset grouping strategy is preset by the user. For example, the acoustic feature information extracted from the child's voice information is divided into a child group, the acoustic feature information extracted from the adult voice information is divided into an adult group, and the acoustic feature information extracted from the adult voice information may also be gender-based. Differently divided into a group of men, a group of women, etc., the acoustic feature information of the collected voice information is grouped according to a preset grouping strategy, and then saved to the acoustic feature information library for subsequent acoustic feature information in the voice command. Similarity comparison, it should be noted that the user voice information collected when the acoustic feature information base is established refers to the voice information input by the user, and the purpose is to extract the user's acoustic feature information, including but not limited to specific instructions, such as I want movies, I want to watch cartoons, etc., and other non-command voices that the user says, such as the weather is good, the mood is good, and so on.

After the acoustic feature information base is established, the user type can be determined. In the embodiment of the present invention, the user type of the user is determined according to the acoustic feature information in the acquired acoustic feature information database, including:

If the acquired acoustic feature information in the acoustic feature information database is included in the adult group, the user type is an adult;

If the acoustic feature information in the acquired acoustic feature information database is included in the child group, the user type is a child.

After obtaining the user voice instruction in the specific application, the acoustic feature information in the voice command is extracted, and the similarity is compared with the acoustic feature in the acoustic feature information database, and the similarity degree is greater than or equal to the similarity threshold in the acoustic feature information database. The acoustic feature information is extracted, and it is determined which acoustic group information in the extracted acoustic feature information database is included in the group of the acoustic feature information database, and if included in the adult group, the user type is an adult, if included in the child In the group, the user type is child, and so on, and in which group the acoustic feature information in the extracted acoustic feature information database is included, the user type belongs to which type.

Through the above method, the corresponding unlocking operation can be performed by the user's voice instruction, but for various reasons, the user's voice may not match the actual age, for example, the actual age is a child but the sound is like an adult, and the actual age is an adult voice image. Children, there is also a situation that may lead to misoperation, that is, there are now a lot of software that can change people's voices, such as entering a child's voice, processing it into an adult voice, or turning a man's voice into a woman. of Sound, such as the case described above, may be erroneously operated only by performing a corresponding unlocking operation according to the user's voice, so it is necessary to add some auxiliary measures such as face recognition or user authentication.

For the step S103, in the embodiment of the present invention, preferably, if the user type is consistent with the preset user type, the method further includes:

Performing face recognition on the user, acquiring facial feature information of the user, and determining the user type of the user according to the facial feature information of the user;

If the user type is consistent with the preset user type, the voice command is recognized.

After determining that the user type of the user is consistent with the preset user type according to the acoustic feature information, performing a face recognition operation on the user, determining a user type of the user by acquiring the face feature information of the user, and determining the user of the user according to the acoustic feature information. After the type is consistent with the preset user type, it is determined by the face recognition that the user type of the user is consistent with the preset user type, and the voice command of the user is recognized.

For example, the preset user type is an adult, and when it is determined by the acoustic feature information that the user type of the user is an adult, the user is recognized by the face, and when the face recognition is determined that the user type is an adult, the user voice instruction is performed. The recognition may be performed by using a front camera to identify the facial information of the user. The recognition may be performed in real time or according to a preset time period, so as to prevent the child from unlocking through the voice changer.

When the user uses a terminal such as a television, it can be used by several people together, but some application users do not want to share with others, and then need to perform identity verification when performing the unlocking operation. For the step S103, if the user type and the pre-step Set the user types to be consistent, including:

Performing user identity verification based on acoustic feature information;

When the user authentication is passed, the voice command is recognized.

After determining that the user type of the user is consistent with the preset user type according to the acoustic feature information, the user needs to be authenticated to determine whether the user who issued the voice instruction is an authorized user, and only the authorized user can perform related Unlocking operation,

In the embodiment of the present invention, preferably, based on the acoustic feature information, the authentication is performed. User authentication, further including:

The acoustic feature information is compared with the preset authorized acoustic feature information in the pre-existing acoustic feature information database, and if the similarity is greater than or equal to the similarity threshold, the user identity verification is passed.

Acquiring the voice instruction of the user, extracting the acoustic feature information in the collected user voice information, setting the acoustic feature information in the extracted user voice information to the authorized acoustic feature information, and saving the information to the acoustic feature information library, so as to Subsequent authentication.

Embodiment 2

2 is a schematic structural diagram of an apparatus for unlocking a voice according to an embodiment of the present invention, as shown in FIG. 2:

Accordingly, the embodiment of the present invention further provides a voice unlocking apparatus, including: a television client (not shown), and the television client includes:

The acquiring module 1 is configured to acquire a voice instruction of the user, extract acoustic characteristic information of the voice instruction, and determine a user type of the user according to the acoustic feature information;

The determining module 2 is configured to determine whether the user type is consistent with the preset user type;

The determining module 2 is coupled to the obtaining module 1. After the obtaining module 1 determines the user type of the user, the determining module 2 compares the user type with the preset user type, determines whether the two are consistent, and sends the determination result to the identifying module. 3.

The identification module 3 is configured to: if the user type is consistent with the preset user type, identify a voice instruction, and determine, according to a correspondence between the voice instruction and the preset unlocking instruction, whether the voice instruction corresponds to the preset unlocking instruction;

The identification module 3 is coupled to the determination module 2, and when the determination module 2 determines that the user type is consistent with the preset user type, the recognition module 3 recognizes the voice instruction of the user, and according to the correspondence between the voice instruction and the preset unlock instruction, It is determined whether the voice command corresponds to the preset unlock command, and the determination result is sent to the execution module 4.

The execution module 4 is configured to perform an unlocking operation corresponding to the preset unlocking instruction according to the preset unlocking instruction if the determination result is YES.

The execution module 4 is coupled to the identification module 3, and the execution module 4 receives the determination of the identification module 3. If the result of the determination is yes, the unlocking operation corresponding to the preset unlocking instruction is performed according to the preset unlocking instruction, for example, the preset unlocking command corresponds to the power-on unlocking, and then the power-on unlocking is performed, and the preset unlocking instruction is related to opening the movie application. Correspondingly, the movie application is unlocked and the movie application is opened.

The device for unlocking a voice provided by the embodiment of the present invention obtains the acoustic feature information in the voice command by acquiring the voice command of the user, and determines the user type according to the acoustic feature information, and determines whether the user type of the module 2 is related to the preset user type. In the case that the user type is consistent with the preset user type, the recognition module 3 recognizes the voice command of the user, and according to the correspondence between the voice command and the preset unlock command, the execution module 4 executes the preset unlock command. The corresponding unlocking operation solves the cumbersome operation of manually adjusting the keyboard when the power is turned on or the locked application is performed in the prior art for the power-on of the TV and the function switching, and the text message needs to be sent by the forgotten password. The technical solution provided by the embodiment of the present invention facilitates the user to unlock the operation and can effectively prevent the user who does not meet the requirement from performing an inappropriate operation, and ensures the operation of the user when performing the unlocking operation. Simple and convenient, it improves the user experience.

Preferably, the obtaining module 1 is further configured to:

FIG. 3 is a schematic structural diagram of an apparatus for preferentially unlocking a voice according to an embodiment of the present invention, as shown in FIG. 3:

Preferably, the method further includes: an establishing module 5, configured to: establish an acoustic feature information library, comprising: collecting at least two pieces of voice information, and extracting acoustic feature information of each collected voice information, wherein the voice information includes voice information of the adult and Children's voice information;

The establishing module 5 is coupled to the acquiring module 1 for establishing an acoustic feature information base for comparing the voiceprint feature information in the user voice command with the voiceprint feature information in the acoustic feature information database to determine the identity of the user. Types of.

Preferably, the obtaining module 1 is further configured to:

Preferably, the identification module 3 is further configured to:

After determining that the user type of the user is consistent with the preset user type according to the acoustic feature information, performing face recognition on the user, acquiring facial feature information of the user, and determining a user type of the user according to the facial feature information of the user;

In addition, preferably, the module 4 is executed, further for:

The apparatus shown in FIG. 2-3 can perform the method of the embodiment shown in FIG. 1. The method of the embodiment of the present invention corresponds to the features of the device, and can be referred to each other, and details are not described herein again.

Specific application scenarios:

The following is a more straightforward understanding of the technical solutions of the embodiments of the present invention by using the description of the application scenarios. The following scenarios are intended to illustrate the technical solutions of the embodiments of the present invention, and do not constitute an undue limitation of the embodiments of the present invention.

scene one

FIG. 4 is a schematic diagram of an application scenario of a method for unlocking a voice according to an embodiment of the present invention, as shown in FIG. 4:

Taking the use of a television as an example, the user presets the user type to an adult, and the user locks the application and powers on through the parent lock under the TV housekeeper menu.

When the user enters the locked application or powers on, the interface will pop up a lock screen that needs to type a password. The user sends a voice command “I am a parent”, according to the “I am a parent” voiceprint feature information, to determine the type of the user, for example Whether the voiceprint feature is a child, if it is, it will not be unlocked and stay on the lock screen. If not, the unlock operation will be performed.

Scene two

Still taking scene 1 as the background, when judging that the user type is adult, the front camera of the TV is turned on, the face recognition is performed on the user, and after the face recognition is determined that the user type is an adult, the unlock operation is performed, if the face is If the result of the recognition is a child, it will stay on the lock screen.

Scene three

Still taking scene 1 as the background, when judging that the type of the user is an adult, comparing the similarity of the voiceprint feature information in the extracted voice command with the acoustic feature information of the preset authorized in the pre-existing acoustic feature information library, if similar If the degree is greater than or equal to the similarity threshold, the user authentication passes, and the unlock operation is performed.

In summary, the technical solution provided by the embodiment of the present invention acquires the acoustic feature information in the voice command of the user, and determines the user type according to the acoustic feature information. When the user type is consistent with the preset user type, Identifying a voice command of the user, performing an unlocking operation corresponding to the preset unlocking command according to the correspondence between the voice command and the preset unlocking command, and solving the prior art, when performing rights management on the TV booting and function switching, When booting or entering a locked application, the manual operation of the keyboard is cumbersome, and the password is forgotten. The technical solution provided by the embodiment of the present invention facilitates the unlocking operation of the user, and can effectively prevent the user who does not meet the requirement from performing an inappropriate operation, and ensures the user when performing the unlocking operation. The operation is simple and convenient, and the user experience is improved.

FIG. 5 is a schematic structural diagram of an electronic device for unlocking a voice in an embodiment of the present invention. The device in this embodiment may be part of a voice unlocking server or a voice unlocking server, and the device may include:

One or more processors 501 and memory 502, one processor 501 is taken as an example in FIG.

The voice unlocked electronic device may further include: an input device 503 and an output device 504.

The processor 501, the memory 502, the input device 503, and the output device 504 can be connected by a bus or other means.

The memory 502 is used as a non-transitory computer readable storage medium, and can be used for storing non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the method for unlocking voice in the embodiment of the present invention. . The processor 501 executes various functional applications and data processing of the server by running non-transitory software programs, instructions, and modules stored in the memory 502, that is, a method for implementing voice unlocking in the above method embodiments.

The memory 502 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store data created according to usage of the voice unlocked device, and the like. Moreover, memory 502 can include high speed random access memory, and can also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 502 can optionally include memory remotely located relative to the processor 501 that can be connected to the processing device of the list item operation over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The input device 503 can receive the input digital or character information and generate a key signal input related to user settings and function control of the device for voice unlocking. Output device 504 can include a display device such as a display screen.

The one or more modules are stored in the memory 502 when the one or more When the processor 501 executes, the method of voice unlocking in any of the above method embodiments is performed.

The above product can perform the method provided by the embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the method provided by the embodiments of the present invention.

The electronic device of the embodiment of the invention exists in various forms, including but not limited to:

(1) Mobile communication devices: These devices are characterized by mobile communication functions and are mainly aimed at providing voice and data communication. Such terminals include: smart phones (such as iPhone), multimedia phones, functional phones, and low-end phones.

(2) Ultra-mobile personal computer equipment: This type of equipment belongs to the category of personal computers, has computing and processing functions, and generally has mobile Internet access. Such terminals include: PDAs, MIDs, and UMPC devices, such as the iPad.

(3) Portable entertainment devices: These devices can display and play multimedia content. Such devices include: audio, video players (such as iPod), handheld game consoles, e-books, and smart toys and portable car navigation devices.

(4) Server: A device that provides computing services. The server consists of a processor, a hard disk, a memory, a system bus, etc. The server is similar to a general-purpose computer architecture, but because of the need to provide highly reliable services, processing power and stability High reliability in terms of reliability, security, scalability, and manageability.

(5) Other electronic devices with data interaction functions.

Correspondingly, an embodiment of the present invention further provides a computer readable storage medium, where the program for executing the method of the foregoing embodiment is stored.

The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, ie may be located A place, or it can be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment. Those of ordinary skill in the art can understand and implement without deliberate labor.

Through the description of the above embodiments, those skilled in the art can clearly understand that the various embodiments can be implemented by means of software plus a necessary general hardware platform, and of course, by hardware. Based on such understanding, the above-described technical solutions may be embodied in the form of software products in essence or in the form of software products, which may be stored in a computer readable storage medium such as ROM/RAM, magnetic Discs, discs, etc., include instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to perform the methods described in various embodiments or portions of the embodiments.

It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and are not limited thereto; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that The technical solutions described in the foregoing embodiments are modified, or the equivalents of the technical features are replaced. The modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

A voice unlocking method, comprising:

Obtaining, by the television client, a voice instruction of the user, extracting acoustic feature information of the voice instruction, and determining a user type of the user according to the acoustic feature information;

Determining whether the user type is consistent with a preset user type;

And if the user type is consistent with the preset user type, the voice command is identified, and the voice command and the preset unlock command are determined according to a correspondence between the voice command and the preset unlock command. Whether it corresponds;

If the determination result is yes, the unlocking operation corresponding to the preset unlocking instruction is performed according to the preset unlocking instruction.
The method according to claim 1, wherein determining the user type of the user according to the acoustic feature information further comprises:

Extracting acoustic feature information of the voice instruction and comparing the similarity with the acoustic feature information pre-existing in the acoustic feature information library;

Acquiring the acoustic feature information in the acoustic feature information base with the similarity greater than or equal to the similarity threshold;

Determining the user type of the user based on the acquired acoustic feature information in the acoustic feature information library.
The method according to claim 2, wherein comparing the acoustic feature information in the pre-existing acoustic feature information database, the method further comprises: establishing the acoustic feature information database, comprising: collecting at least two voice information Extracting acoustic feature information of each of the collected voice information, wherein the voice information includes voice information of an adult and voice information of the child;

According to the preset grouping strategy, the collected acoustic feature information of the voice information is divided into an adult group and a child group, and stored in the acoustic feature information library.
The method according to claim 3, wherein determining the user type of the user according to the acquired acoustic feature information in the acoustic feature information database comprises:

If the acquired acoustic feature information in the acoustic feature information database is included in the adult group, the user type is an adult;

If the obtained acoustic feature information in the acoustic feature information database is included in the child group, the user type is a child.
The method according to claim 1, wherein if the user type is consistent with the preset user type, the method further includes:

Performing face recognition on the user, acquiring facial feature information of the user, and determining the user type of the user according to the facial feature information of the user;

If the user type is consistent with the preset user type, the voice instruction is recognized.
The method according to any one of claims 1-5, wherein the performing the unlocking operation corresponding to the preset unlocking instruction according to the preset unlocking instruction further comprises:

When the television client is in a shutdown state, performing a power-on unlocking operation according to the preset unlocking command to perform a cold booting of the television client; or

When the television client is in the power-on state, an application unlocking operation is performed according to the preset unlocking instruction, so as to unlock the application corresponding to the preset unlocking command and enter the application.
A voice unlocking device, comprising: a television client, wherein the television client comprises:

An acquiring module, configured to acquire a voice instruction of the user, extract acoustic characteristic information of the voice instruction, and determine a user type of the user according to the acoustic feature information;

a determining module, configured to determine whether the user type is consistent with a preset user type;

An identification module, configured to: if the user type is consistent with the preset user type, identify the voice instruction, and determine the voice instruction according to a correspondence between the voice instruction and the preset unlocking instruction Whether it corresponds to the preset unlock command;

And an execution module, configured to perform an unlocking operation corresponding to the preset unlocking instruction according to the preset unlocking instruction, if the determination result is yes.
The apparatus according to claim 7, wherein said acquisition module further And configured to: extract acoustic feature information of the voice instruction, and compare the similarity with the acoustic feature information in the pre-existing acoustic feature information base;

Acquiring the acoustic feature information in the acoustic feature information base with the similarity greater than or equal to the similarity threshold;

Determining the user type of the user based on the acquired acoustic feature information in the acoustic feature information library.
The apparatus according to claim 8, further comprising: an establishing module, configured to: establish the library of acoustic feature information, comprising: collecting at least two pieces of voice information, and extracting acoustics of each of the collected voice information Feature information, wherein the voice information includes voice information of an adult and voice information of a child;

According to the preset grouping strategy, the collected acoustic feature information of the voice information is divided into an adult group and a child group, and stored in the acoustic feature information library.
The device according to claim 9, wherein the obtaining module is further configured to:

If the acquired acoustic feature information in the acoustic feature information database is included in the adult group, the user type is an adult;

If the obtained acoustic feature information in the acoustic feature information database is included in the child group, the user type is a child.
The device according to claim 7, wherein the identification module is further configured to:

After determining that the user type of the user is consistent with the preset user type according to the acoustic feature information, performing face recognition on the user, acquiring facial feature information of the user, according to the user The face feature information determines the user type of the user;

If the user type is consistent with the preset user type, the voice instruction is recognized.
The device according to any one of claims 7-11, wherein the execution module is further configured to:

When the television client is in a shutdown state, performing a power-on unlocking operation according to the preset unlocking command to perform a cold booting of the television client; or

When the television client is in the power-on state, executing the application according to the preset unlocking instruction The unlocking operation is to unlock the application corresponding to the preset unlocking command and enter the application.
A voice unlocking electronic device, comprising:

At least one processor; and,

a memory communicatively coupled to the at least one processor; wherein

The memory stores instructions executable by the one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method of any of claims 1-6.
A non-transitory computer readable storage medium, wherein the non-transitory computer readable storage medium stores computer instructions for causing the computer to perform the method of any of claims 1-6 .
A computer program product comprising a computing program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions that, when executed by a computer, cause the computer to execute The method of any of claims 1-6.