A voice control device and control method for smart device and smart home

Abstract

The present invention discloses a voice control device and control method for smart devices and smart homes. For the voice control device end: in response to receiving the voice information currently input by the user, the target device is obtained according to the voice information; the authorization list corresponding to the target device is queried, and the authorization list includes the identity of the user who has the authority to voice control the target device; if the authorization list is not empty, the voiceprint recognition is performed on the voice information to obtain the target identity of the user to whom the current voiceprint belongs; if the target identity is included in the authorization list, a control instruction is sent to the target device, and the control instruction is used to instruct the target device to perform the operation corresponding to the voice information. The present application realizes personalized control of the voice authority of smart devices, thereby improving the security of smart home voice control.

Description

Technical Field

[0001] The present invention relates to the field of smart home technology, and in particular to a smart device, a voice control device for a smart home, and a control method. Background Art

[0002] In the smart home scene, users can control the working status of each smart device by voice, including smart TVs, smart refrigerators, smart air conditioners, smart door locks, smart lamps, etc. For example, voice control devices such as AI voice assistants can be configured in the home scene. AI voice assistants communicate with multiple smart devices through the Internet. If the user shouts "turn on the air conditioner" to the AI ​​voice assistant, the AI ​​voice assistant will send a control command to the smart air conditioner, which will automatically turn on after receiving the control command, eliminating the need for users to manually or remotely input the power-on operation, thereby improving the intelligence, convenience and user experience of the home system.

[0003] However, due to the randomness of voice input, anyone in the home scene can control smart devices by voice, which may pose a safety hazard, such as user A opening the door lock of the dressing room by voice without permission, or children controlling the microwave or oven to start high-temperature heating by voice, etc. Therefore, how to improve the security of smart home voice control is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0004] The present invention provides a voice control device and a control method for a smart device and a smart home, which identifies the user's voice control authority for a target device based on the voiceprint information carried in the voice information input by the user and a preset authorization list, and sends corresponding control instructions to the target device based on the authentication result, thereby improving the security of smart home voice control.

[0005] The first aspect of the embodiment provides a smart home voice control device, including:

[0006] A voice collector is used to collect voice information input by users;

[0007] A communicator, used to communicate with smart devices included in the home scene;

[0008] The controller is configured to execute:

[0009] In response to receiving the voice information currently input by the user, acquiring a target device according to the voice information;

[0010] Querying an authorization list corresponding to the target device, the authorization list including the identity of a user who has the authority to voice control the target device;

[0011] If the authorization list is not empty, perform voiceprint recognition on the voice information to obtain the target identity of the user to whom the current voiceprint belongs;

[0012] If the target identity is included in the authorization list, a control instruction is sent to the target device, where the control instruction is used to instruct the target device to execute an operation corresponding to the voice information.

[0013] The smart device provided by the second embodiment includes:

[0014] A communicator, used for communicating with a voice control device;

[0015] The controller is configured to execute:

[0016] Upon receiving a control instruction sent by the voice control device, executing a corresponding operation according to the control instruction;

[0017] Among them, the control instruction is that the voice control device obtains the target device and queries the authorization list corresponding to the target device according to the voice information input by the user, and is sent when the authorization list is not empty and the target identity obtained after voiceprint recognition of the voice information is included in the authorization list; the authorization list includes the identity of the user who has the authority to voice control the target device.

[0018] The third aspect of the embodiment provides a smart home voice control method, which is used for a voice control device, and includes:

[0019] In response to receiving the voice information currently input by the user, acquiring a target device according to the voice information;

[0020] Querying an authorization list corresponding to the target device, the authorization list including the identity of a user who has the authority to voice control the target device;

[0021] If the authorization list is not empty, perform voiceprint recognition on the voice information to obtain the target identity of the user to whom the current voiceprint belongs;

[0022] If the target identity is included in the authorization list, a control instruction is sent to the target device, where the control instruction is used to instruct the target device to execute an operation corresponding to the voice information.

[0023] The fourth aspect of the embodiment provides a smart home voice control method, which is used on a smart device, and includes:

[0024] When receiving a control instruction sent by a voice control device, performing a corresponding operation according to the control instruction;

[0025] Among them, the control instruction is that the voice control device obtains the target device and queries the authorization list corresponding to the target device according to the voice information input by the user, and is sent when the authorization list is not empty and the target identity obtained after voiceprint recognition of the voice information is included in the authorization list; the authorization list includes the identity of the user who has the authority to voice control the target device.

[0026] In the smart home system of the present application, the voice control device communicates with multiple smart devices. When receiving the voice information input by the user, the voice control device can parse and semantically recognize the voice information, so as to obtain the target device indicated by the voice information. For example, if the user shouts "turn on the TV" to the voice control device, the target device can be identified as the TV. The voice control device will maintain an authorization list corresponding to each smart device, and the authorization list includes the identity of users who have the authority to control smart devices by voice. For example, the authorization list corresponding to the TV is {Dad, Mom, Son}, then users with these three identities can voice control the working status of the TV, such as turning the TV on, off, switching channels, adjusting the volume, etc., while other users who are not on the authorization list cannot voice control the TV.

[0027] When the authorization list corresponding to the target device is not empty, the voice control device continues to perform voiceprint recognition on the voice information, and identifies the target identity of the current user through the voiceprint information. For example, if the target identity of the current user is identified as mom, and "mom" is included in the authorization list of the above-mentioned TV, the voice control device sends a control instruction to the target device to instruct the target device to perform the operation corresponding to the voice information, that is, to control the TV to automatically turn on. This application authenticates the user through voiceprint recognition and the authorization list maintained for each smart device, and only sends a control instruction to the target device when it is identified that the user has the authority to voice control the target device, otherwise the control instruction will not be sent, thereby realizing personalized control of the voice authority of the smart device, thereby improving the security of smart home voice control. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required to be accessed in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 A schematic diagram of a smart home voice control scenario is shown as an example;

[0030] Figure 2 The hardware configuration diagram of the voice control device 100 is exemplarily shown;

[0031] Figure 3 A schematic diagram exemplarily illustrates the principle of voice interaction;

[0032] Figure 4 The following is a schematic diagram of a setting page of the voice control device 100;

[0033] Figure 5 A schematic diagram exemplarily shows that the voice control device 100 displays a first registration prompt;

[0034] Figure 6 A schematic diagram exemplarily shows that the voice control device 100 displays a second registration prompt;

[0035] Figure 7 The following is a schematic diagram showing an exemplary display device list interface of the voice control device 100;

[0036] Figure 8 A schematic diagram of the authorization list setting interface when the authorization list is empty is exemplified;

[0037] Fig. 9 The following is a schematic diagram showing an example of an authorization list setting interface after a user clicks on a first add control;

[0038] Fig.10 The following is an example of a schematic diagram of the interface after the authorization list is set up;

[0039] FIG. 11( a ) is a schematic diagram showing an example of an authorization list setting interface having a verification authority function;

[0040] FIG11( b ) is a schematic diagram showing, by way of example, changes in the interface after clicking on the verification control in the interface of FIG11( a );

[0041] FIG11( c ) exemplarily shows a schematic diagram of the authorization list setting interface when the authority verification is passed;

[0042] FIG11( d ) exemplarily shows a schematic diagram of the authorization list setting interface when the authority verification fails;

[0043] Fig.12 A flow chart of a voice control method for a smart home is exemplified;

[0044] Fig.13 The schematic diagram exemplarily shows that the voice control device 100 displays the third registration prompt;

[0045] Fig.14 The figure exemplarily shows that the voice control device 100 displays the fourth registration prompt. DETAILED DESCRIPTION

[0046] In order to make the purpose and implementation method of the present application clearer, the exemplary implementation method of the present application will be clearly and completely described below in conjunction with the drawings in the exemplary embodiments of the present application. Obviously, the described exemplary embodiments are only part of the embodiments of the present application, rather than all the embodiments.

[0047] It should be noted that the brief description of terms in this application is only for the convenience of understanding the embodiments described below, and is not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their common and usual meanings.

[0048] The terms "first", "second", "third", etc. in the specification and claims of this application and the above drawings are used to distinguish similar or similar objects or entities, and do not necessarily mean to limit a specific order or sequence, unless otherwise noted. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances.

[0049] The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device comprising a list of components is not necessarily limited to all the components expressly listed but may include other components not expressly listed or inherent to such product or device.

[0050] The term "module" refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic or combination of hardware and / or software code that is capable of performing the functions associated with that element.

[0051] In some embodiments, Figure 1 The smart home voice control scenario is shown, which includes a voice control device 100 and N smart devices 200, N is greater than or equal to 1, the voice control device 100 communicates with the N smart devices 200 through a network, and the voice control device 100 is used to send control instructions to the smart device 200 according to the voice information input by the user, and the smart device 200 responds to the received control instructions and controls its functional components to perform operations that meet the user's intentions. For example, the user shouts "increase the volume of the TV" to the voice control device 100, and the voice control device 100 performs parsing processing such as recognition and semantic analysis on the voice information, and it can be obtained that the target device is a TV, and the user's intention is to increase the volume, then a control instruction for instructing it to increase the volume is sent to the TV, and the TV receives and responds to the control instruction, and controls the current power amplifier (such as its own speaker or external audio, etc.) to increase the volume value of the audio output. The working status of each smart device is controlled by voice, without the need for manual or remote control operation by the user, which improves the intelligence, convenience and user interaction experience of the smart home.

[0052] In an actual home scene, the smart devices 200 include but are not limited to smart TVs, smart refrigerators, smart air conditioners, smart door locks, smart lamps, smart kitchen appliances and other home appliances that support voice control. The location distribution of each smart device in the home scene and the hardware and software configuration are not limited, and the working status of each smart device is independently controlled.

[0053] In some embodiments, the voice control device 100 is directly facing the user side, and the voice control device 100 is, for example, an AI voice assistant, a conversational artificial intelligence system, or the like. The hardware configuration of the voice control device 100 is as follows: Figure 2 As shown, the voice control device may include at least a controller 110 and a voice collector 120, a communicator 130, a sound player 150, a memory 160 and a power supply 170 respectively connected to the controller 110. It should be noted that the voice control device is not limited to Figure 2 instead of examples, the corresponding hardware and modules can be adaptively configured according to actual functional requirements.

[0054] In some embodiments, the voice collector 120 is used to collect voice information input by the user and send the voice information to the controller 110. The voice collector 120 is, for example, a microphone.

[0055] In some embodiments, the communicator 130 is a component for communicating with the smart device 200, other external devices and / or servers according to various communication protocol types. The communicator 130 may include a Wifi module, a Bluetooth module, a wired Ethernet module, or other network communication protocol chips or near-field communication protocol chips, as well as at least one of an infrared receiver to achieve the sending and receiving of control instructions and data between the voice control device 100 and the smart device 200.

[0056] In some embodiments, the audio player 150 is used to output audio data according to the instructions of the controller 110, and to broadcast some prompt information to the user by voice, etc. The audio player 150 can be a built-in speaker of the voice control device 100, or an external amplifier device such as headphones, Bluetooth speakers, etc. connected in a wired or wireless manner through a USB interface, an HDMI interface or a Bluetooth module.

[0057] In some embodiments, the memory 160 is used to store various software control programs, as well as instructions for operating systems and application programs, and is also used to store content such as registration lists and authorization lists corresponding to various smart devices.

[0058] In some embodiments, the voice control device 100 further includes a display 140, which includes a display screen component for presenting images, and a driving component for driving image display, and is used to receive an image signal output from the controller 110, and display video content, image content, and a menu control interface component and a user control UI interface, etc. The display 140 can be at least one of a liquid crystal display, an OLED display, and a projection display, and can also be a projection device and a projection screen.

[0059] In some embodiments, the controller 110 controls the operation of the voice control device 100 and responds to the user's voice / UI operation by executing various software control programs stored in the memory 160. The controller 110 controls the overall operation of the voice control device 100. For example, in response to receiving a user command for selecting a UI object to be displayed on the display 140, the controller 110 can perform operations related to the object selected by the user command.

[0060] In some embodiments, the object may be any one of the selectable objects, such as a hyperlink, an icon or other operable controls. Operations related to the selected object include: displaying a page, document, image, etc. connected to the hyperlink, or executing a program corresponding to the icon.

[0061] In some embodiments, the user may input a user command through a graphical user interface (GUI) displayed on the display 140, and the user input interface receives the user input command through the graphical user interface (GUI). Alternatively, the user may input a user command through a specific sound or gesture, and the user input interface receives the user input command by recognizing the sound or gesture through a sensor.

[0062] In some embodiments, "user interface" is a medium interface for interaction and information exchange between an application or operating system and a user, which realizes the conversion between the internal form of information and the form acceptable to the user. A common form of user interface is a graphical user interface (GUI), which refers to a user interface related to computer operation displayed in a graphical manner. It can be an interface element such as an icon, window, or control displayed on a display screen of an electronic device, wherein a control may include at least one of icons, buttons, menus, tabs, text boxes, dialog boxes, status bars, navigation bars, widgets, and other visual interface elements.

[0063] In some embodiments, the voice control device 100 may be Figure 2 The overall control device shown is independent of each smart device and communicates and interacts with each smart device.

[0064] In some embodiments, the voice control device 100 can also be set in any smart device in the home scene in the form of a chip or module. This design enables the smart device to have not only its own general functions, but also the functions of the voice control device 100 and the programs configured to be executed, so that the smart device becomes a voice control device. In this embodiment, if the voice control device 100 is integrated with any smart device, the software and hardware configuration of the voice control device 100 can be adaptively modified and adjusted according to the software and hardware configuration of the smart device, and the software and hardware configuration of the voice control device 100 is not specifically limited.

[0065] In some embodiments, Figure 3 A schematic diagram of a speech recognition network architecture is provided. Figure 3 In the embodiment, the smart device is used to receive input voice information and output the processing result of the voice information. The voice recognition service device is an electronic device deployed with a voice recognition service, the semantic service device is an electronic device deployed with a semantic service, and the business service device is an electronic device deployed with a business service. The electronic devices here may include servers, computers, etc. The voice recognition service, semantic service (also referred to as a semantic engine) and business service here are web services that can be deployed on electronic devices, wherein the voice recognition service is used to recognize audio as text, the semantic service is used to perform semantic analysis on the text, and the business service is used to provide specific services such as the weather query service of Moji Weather, the music query service of QQ Music, etc. In some embodiments, Figure 3 In the illustrated architecture, there may be multiple physical service devices deployed with different business services, or one or more functional services may be integrated into one or more physical service devices.

[0066] In some embodiments, the following Figure 3 The process of processing the information input into the smart device by the architecture shown is described by way of example. Taking the information input into the smart device as a query statement input by voice as an example, the above process may include the following three processes:

[0067] A1: [Speech Recognition]

[0068] After receiving the query statement input by voice, the smart device may upload the audio of the query statement to the voice recognition service device, so that the voice recognition service device recognizes the audio as text through the voice recognition service and returns it to the smart device. In one embodiment, before uploading the audio of the query statement to the voice recognition service device, the smart device may perform denoising on the audio of the query statement, and the denoising process here may include steps such as removing echoes and environmental noise.

[0069] A2: [Semantic Understanding]

[0070] The smart device uploads the text of the query statement recognized by the speech recognition service to the semantic service device, so that the semantic service device performs semantic analysis on the text through the semantic service to obtain the business field, intent, etc. of the text.

[0071] A3: [Semantic Response]

[0072] The semantic service device sends a query instruction to the corresponding business service device according to the semantic parsing result of the text of the query statement to obtain the query result given by the business service. The intelligent device can obtain the query result from the semantic service device and output it. As an embodiment, the semantic service device can also send the semantic parsing result of the query statement to the intelligent device, so that the intelligent device can output the feedback statement in the semantic parsing result.

[0073] In some embodiments, the following Figure 3 The process of processing the information input into the smart device is described by way of example. Taking the information received by the smart device as voice information inputted through voice to control the target device as an example, the above process may include the following three processes:

[0074] B1: [Speech Recognition]

[0075] After receiving the voice information of the user performing voice control on the target device, the smart device can upload the audio of the voice information to the voice recognition service device, so that the voice recognition service device can recognize the audio as text through the voice recognition service and return it to the smart device. In one embodiment, before uploading the audio of the voice information to the voice recognition service device, the smart device can perform denoising on the audio of the voice information, and the denoising here can include steps such as removing echoes and environmental noise.

[0076] B2: [Semantic Understanding]

[0077] The smart device uploads the text corresponding to the voice information recognized by the voice recognition service to the semantic service device, so that the semantic service device performs semantic analysis on the text through the semantic service to obtain information such as the user's voice control intention and the controlled object (i.e., the target device described in this application) carried in the text.

[0078] B3: [Semantic Response]

[0079] The semantic service device sends the semantic analysis result of the text to the smart device. The smart device obtains the target device based on the semantic analysis result, queries the authorization list corresponding to the target device, and performs voiceprint recognition on the voice information input by the user when the authorization list is not empty, thereby obtaining the target identity of the user to whom the voiceprint belongs. When the target identity is included in the authorization list, it generates a control instruction based on the user's voice control intention indicated by the semantic analysis result, and sends the control instruction to the target device, thereby controlling the target device to perform the operation corresponding to the voice information.

[0080] It should be noted that Figure 3 The architecture shown is only an example and does not limit the scope of protection of this application. In the embodiments of this application, other architectures can also be used to implement similar functions. For example, all or part of the three processes can be completed by the smart device end, which will not be described in detail here. Among them, the control process of B1 to B3 can be executed by a voice control chip / module (having the function of voice control device 100) configured on a smart device end.

[0081] In some embodiments, Figure 3 The smart device shown can be a display device, such as a smart TV. The function of the voice recognition service device can be realized by the sound collector and controller set on the display device. The functions of the semantic service device and the business service device can be realized by the controller of the display device or by the server of the display device. It should be noted that smart devices are not limited to display devices, but can also include household appliances such as smart refrigerators, washing machines, and smart air conditioners.

[0082] In some embodiments, the controller 110 of the present application is mainly used to parse and process voice information, authenticate according to the authorization list of each smart device maintained by itself, and issue control instructions to the target device when it is determined that the current user identity is authorized.

[0083] In some embodiments, when the controller 110 receives voice information, it first recognizes the voice information, that is, converts the voice information into corresponding text information. Voice recognition mainly includes four links: feature extraction, language model, voiceprint model, and dictionary and decoding. In order to extract features more effectively, the collected sound signal can be preprocessed, that is, the voice signal to be analyzed is extracted from the original collected signal. Feature extraction is to convert the voice signal from the time domain to the frequency domain to provide a suitable feature vector for the voiceprint model; the voiceprint model calculates the voiceprint feature score of each feature vector according to the voiceprint characteristics, and finally outputs the voiceprint information. The voiceprint information is a sound wave spectrum carrying the user's gender, age and other biological sound characteristics. The voiceprint information of each person is different, so the user's identity can be accurately distinguished and identified through the voiceprint information; the voice model calculates the probability of the possible phrase sequence of the voice signal according to the relevant knowledge theory of linguistics, and finally decodes the phrase sequence according to the dictionary to obtain the converted text information. For example, the voice collector 120 collects the voice information A in the PCM (Pulse Code Modulation) format, and the text information converted after voice recognition is "turn on the air conditioner".

[0084] In some embodiments, the controller 110 performs semantic analysis based on the information in the text. The shortest path word segmentation algorithm is used to match the words contained in the text information, and then the shortest path composed of words is found to obtain the word segmentation result. For example, if the text information is "turn on the air conditioner", the word segmentation result is {turn on, air conditioner}. After the word segmentation is completed, a part-of-speech tagging algorithm based on HMM (HiddenMarkov Model) can be used to tag the part-of-speech of the word segmentation, and add business tags to obtain {turn on, turn on, actionOpen: smartHomeOpen|air conditioner, air conditioner, basicWord: shopKeys: deviceType}, where actionOpen represents the part-of-speech of the word as a verb, smartHomeOpen is the business tag of "turn on", representing the action used to start the smart home; basicWord represents the part-of-speech of the word as a noun, and shopKeys: deviceType is the business tag of "air conditioner", which is used to represent the device type of the controlled object as an air conditioner.

[0085] In some embodiments, after completing the text segmentation and part-of-speech tagging, a deep learning model based on a convolutional neural network can be used to analyze the user's voice control intention and locate the business. It can be determined that "turn on the air conditioner" belongs to the field of smart home control, and the generated control instructions are as follows:

[0086]

[0087]

[0088] From the above control instructions, it can be seen that the target device that the user wants to control by voice is the air conditioner. After the control instruction is sent to the air conditioner, the air conditioner responds to the control instruction and controls its own switch component to turn on, thereby completing the operation of turning on the air conditioner. It should be noted that voice analysis processing such as voice recognition, semantic analysis and voiceprint recognition can refer to relevant existing technologies, which will not be described in detail in this application, and is not limited to the algorithm provided in the embodiments of this application.

[0089] In some embodiments, the present application uses voiceprint recognition and authorization list for authentication, and sends control instructions to the target device when it is identified that the current user has the authority to voice control the target device. Figure 4 The setting page UI of the voice control device 100 shown in the figure includes an account registration control and an authorization setting control. After the user clicks the account registration control, the controller 110 receives the registration request input by the user and starts the guided registration process.

[0090] In some embodiments, the voice control device 100 first performs a first registration prompt, which may be in the form of voice or UI. Figure 5 Taking the first registration prompt in the UI form shown as an example, the display 140 displays prompt content for guiding the user to input preset voice information, such as "Please say 'I want to register'", that is, the preset voice information is "I want to register", and the user says "I want to register" toward the voice collector 120 of the voice control device 100, and the voice collector 120 collects the preset voice information and sends it to the controller 110. The controller 110 performs voiceprint recognition on the preset voice information to obtain the first voiceprint information.

[0091] In some embodiments, if the user does not speak according to the preset voice information specified in the first registration prompt, or the user does not make any sound, or the sound made by the user is not his original voice or is unclear, it may cause the voiceprint recognition to fail or deviate. Therefore, in order to improve the accuracy of the user's voiceprint account registration, two or more (that is, the preset number M is greater than 1) preset voice messages in different texts can be set.

[0092] For example, set the text of preset voice message 1 as "I want to register", the text of preset voice message 2 as "I am registering", and the text of preset voice message 3 as "I have completed registration". After the user clicks the account registration control, the UI interface first displays "Please say 'I want to register'". After the user says "I want to register" and the controller receives and recognizes preset voice message 1, it controls the display 140 to switch to display "Please say 'I am registering'", and so on. The user sequentially says the texts corresponding to the 3 preset voice messages. If the controller 110 recognizes that the inputs of the 3 preset voice messages are correct, it performs voiceprint recognition based on the 3 preset voice messages to obtain the first voiceprint information, and then gives a second registration prompt; otherwise, if the controller recognizes that the input of a certain preset voice message is incorrect currently, for example, preset voice message 3 is incorrect, it prompts the user "The information is incorrect. Please say 'I have completed registration' again" until the inputs of the 3 preset voice messages are all correct. In this embodiment, an example is given with the preset quantity M = 3. The value of the preset quantity M is not limited, but it should not be too large so as not to cause the voiceprint registration to take too long and affect the user experience.

[0093] In some embodiments, after obtaining the first voiceprint information, a second registration prompt is given. The second registration prompt can be in the form of voice or UI. Taking the second registration prompt in the form of UI shown as an example, the display 140 displays prompt content for guiding the user to input a first identity identifier corresponding to the first voiceprint information, such as "Please set a nickname". This nickname is the identity identifier used to represent the user to whom the first voiceprint information belongs, that is, the first identity identifier. The user can input the first identity identifier through voice / text. Since there may be homophonic characters with different meanings for the nickname text, such as "Fang" and "Fang", it is impossible to determine which specific character the homophone corresponds to when inputting the nickname by voice. Therefore, it is preferable to use text input. Referring to Figure 6 and in the second registration prompt interface, a text input field is set. When the user clicks on the text input field, the cursor automatically positions itself and the virtual keyboard automatically pops up. The user can customize and input their personal identity identifier through the virtual keyboard. The first identity identifier becomes the account name of the voiceprint account. The account name should ensure uniqueness, that is, multiple users cannot use the same account name, but must be one-to-one. After the user inputs the first identity identifier, they click the "Confirm Registration" control in the interface, and the registration is successful. The guided registration process ends, the second registration prompt interface exits, and it returns to the default main page. Figure 6

[0094] In some embodiments, to facilitate the management and maintenance of registered accounts, the controller 110 may create and store a registration list, which includes all currently registered account information, and the account information includes the corresponding relationship between the voiceprint information of the registered user and his / her identity identifier, such as {voiceprint information A, mother}, which indicates that the identity of the user to whom the voiceprint information A belongs is the mother in the family. For each newly added registration record of a voiceprint account, the corresponding relationship needs to be added to the registration list. For example, in the previous embodiment, after clicking the confirmation registration control, the corresponding relationship between the newly registered first voiceprint information and the first identity identifier is stored in the registration list.

[0095] In some embodiments, a certain registered account information can also be deleted from the registration list to cancel the registration. In addition, since the voiceprint information of each registered user cannot be changed, users are only supported to modify the identity in a certain account information, but it must be ensured that the identity before and after the modification still corresponds to the same user. For example, if the mother's name in the family is Li Moufang, then {voiceprint information A, mother} can be modified to {voiceprint information A, Li Moufang}.

[0096] In some embodiments, after the user enters the first identity identifier and clicks the confirmation registration control, the controller 110 obtains the first identity identifier, and then traverses the registration list to detect whether the first identity identifier exists in the registration list. If not, the display 140 is controlled to display a prompt message of successful registration and exit the registration process; on the contrary, if the first identity identifier exists in the registration list, it means that the same identity identifier has been registered by others before, and the controller 110 controls the display 140 to display a prompt message such as "This nickname has been registered, please change your nickname". After the user sees the prompt message, the identity identifier can be changed until the same identity identifier is not found in the registration list, and the registration is successful. This method can ensure the global uniqueness of the identity identifier in the registration list, so as to facilitate the subsequent accurate identification of the true identity of the voice user, thereby improving the accuracy of authentication.

[0097] The above embodiment provides a guided registration mode, which is a registration that the user actively implements according to the guidance, and is a perceptible registration. In other embodiments, an imperceptible registration mode may also be adopted, that is, when the user uses the voice control function, the controller 110 automatically identifies the voiceprint information, and automatically generates a unique identity for the voiceprint information at random, and automatically saves the corresponding relationship between the voiceprint information and the identity in the registration list, thereby realizing automatic registration of the voiceprint account without the user's perception.

[0098] In some embodiments, Figure 4 The authorization setting control on the page is the entry for setting the authorization list. After the user clicks the authorization setting control, the UI jumps to Figure 7 The device list interface shown in the figure displays a device list, which includes device information of all smart devices that are networked and communicate with the voice control device 100 and can be controlled by voice, and the device information includes at least one of the device type / name, MAC address, and IP address. Figure 7 In the example, the device list includes the names of smart TVs, smart air conditioners, washing machines, and smart lamps. It should be noted that since there may be more than one smart device of the same type in a home scene and they are distributed in different locations, taking smart lamps as an example, they can be refined into master bedroom lamps, bathroom lamps, kitchen lamps, living room lamps, etc., so that users can set up targeted authorization lists for smart devices in different locations. If the user has not set up an authorization list corresponding to smart device A, the authorization list of smart device A is empty; the user can select any smart device B that needs to be set up with an authorization list from the device list, and the UI interface will automatically jump to the authorization list setting interface corresponding to smart device B.

[0099] In some embodiments, taking setting the authorization list of a smart air conditioner as an example, Figure 8 The corresponding authorization list setting interface is shown. At this time, the authorization list is empty. The interface is provided with a first fill-in control and displays operation guidance information, such as "Please click + to set the authorization list of the air conditioner". After the user views the operation guidance information, he clicks the first fill-in control. Fig. 9 As shown, a registration list pop-up window will pop up automatically in the interface. Each account information in the registration list pop-up window has a corresponding selection control, and a select all control is set. If the user clicks the select all control, all account information in the registration list will be automatically selected; the user can also click the selection control corresponding to the voiceprint account to be authorized in the registration list pop-up window to select part of the account information. For example, Fig. 9 The identity set in the current registration list is {Dad, Mom, Xiao Ming, Fang Fang}, and the authorization list selected by the user is {Dad, Mom}, that is, the authorization list is a subset of the identity set. Then click the confirmation control in the registration list pop-up window, as shown below Fig.10 As shown, the identity identifiers of users who have the ability to voice control the air conditioner, namely, dad and mom, are filled in the authorization list setting interface. Dad and mom can control the working status of the air conditioner by voice, while Xiao Ming and Fang Fang are not authorized and cannot control the working status of the air conditioner by voice.

[0100] In some embodiments, reference Fig.10In the UI interface shown, when the authorization list is not empty, each identity in the authorization list has a corresponding delete control and a modify control, and a second add control is also provided in the interface. In response to the user clicking the delete control of the first target item in the authorization list, the controller 110 removes the identity A corresponding to the first target item from the authorization list, and the user corresponding to the identity A no longer has the authority to control the air conditioner by voice.

[0101] In some embodiments, in response to the user clicking on a certain modification control, the controller 110 may re-edit and modify the identity B corresponding to the modification control, and modify the identity B to the identity B′, then the registration list needs to simultaneously modify the identity B to the identity B′; similarly, if the user modifies the identity C to the identity C′ in the registration list, if the original identity C is included in the authorization list of P (P is greater than or equal to 1) smart devices, then the identity C in the P authorization lists needs to be synchronously modified to the identity C′. That is, no matter whether the user modifies a certain identity in the registration list or any authorization list, the corresponding identity needs to be synchronously modified and updated globally to ensure the consistency of the identity of the same registered user, and thus ensure the accuracy of subsequent authentication.

[0102] In some embodiments, the controller 110 automatically pops up a registration list pop-up window in response to the user clicking the second addition control. After selecting the newly added identity in the registration list in the aforementioned manner, Fig.10 The authorization list is updated. The authorization list can be empty or filled with at least one identity identifier, and each identity identifier must be globally unique. Regardless of whether the user clicks the first add control when the authorization list is empty, or the user clicks the second add control when the authorization list is not empty, the controller 110 receives the new operation input by the user and automatically displays the registration list in a pop-up window. The user selects at least one second target item in the registration list pop-up window, and the identity identifiers of these second target items are added to the authorization list.

[0103] In some embodiments, the authorization list setting interface also includes a return control. In response to the user clicking the return control, the controller 110 exits the authorization list setting interface of the current smart device and returns to the Figure 7 In the device list interface shown, users can continue to set or modify the authorization list of other smart devices in the device list according to actual needs. In this application, the registration list, device list and authorization list all support dynamic adjustment and update.

[0104] In some embodiments, the controller 110 may also maintain a list setting permission list, which records the identity identifiers that have the permission to set the authorization list of each smart device, such as adding the identity identifiers of the guardians in the family members to the list setting permission list, such as {Dad, Mom}. When the UI interface jumps to the authorization list setting interface, as shown in FIG11(a), the first add control / second add control, delete control and modify control in the authorization list setting interface are all in a prohibited response state. At this time, no matter which control the user triggers, the current authorization list cannot be changed. In addition, a verification control is added to the authorization list setting interface, and a prompt message is displayed to prompt the user to click the verification control to verify whether the authorization list has the permission to set the authorization list, such as "Please click 'Verify' to confirm whether you have the permission to set the authorization list". After the user views the prompt message, he clicks the verification control, as shown in FIG11(b). At this time, the interface switches the prompt message to "Please say 'I want to verify the permission'". After the user says the text "I want to verify the permission", the controller 110 performs voiceprint recognition according to the voice signal input by the user to determine the identity identifier of the user to whom the voiceprint belongs.

[0105] If its identity is included in the list setting permission list, the permission verification is passed, as shown in Figure 11(c), and the first add control / second add control, delete control and modify control are changed to a responsive state, so that the user can set or modify the authorization list by operating these controls, and a prompt message indicating successful permission verification is displayed, such as "Verification passed, please set the authorization list"; on the contrary, if its identity is not included in the list setting permission list, the permission verification is not passed, as shown in Figure 11(d), the first add control / second add control, delete control and modify control remain in a prohibited response state, and a prompt message is displayed to prompt the user that he does not have the permission to set the authorization list, such as "Verification failed, you do not have the permission to set the authorization list". By limiting the users who have the permission to set the authorization list in this way, the security risks caused by anyone being able to set the authorization list at will can be avoided, thereby further improving the security of smart home voice control.

[0106] In some embodiments, the list setting permission list is not fixed. For example, users with permission in the table can perform addition or deletion operations. For example, if a mother adds the registered "grandmother" to the list setting permission list, then after the grandmother verifies the permission in the authorization list setting interface, she can freely set or modify the authorization list.

[0107] It should be noted that the various prompt information and operation guidance information involved in this application can be in the form of voice broadcast and / or UI display, and this application does not limit it. The UI involved in this application, as well as the registration process and authorization list setting process based on the UI are only exemplary, and the actual design and application shall prevail. The UI process is not a limitation on the technical solution of this application.

[0108] In some embodiments, after the user presets the authorization list corresponding to each smart device, Fig.12 A voice control method for a smart home is shown. The execution subject of the method is the controller 110. The method includes the following program steps:

[0109] Step S1, in response to receiving voice information currently input by a user, obtaining a target device according to the voice information.

[0110] In some embodiments, after receiving the voice information, the controller 110 first performs voice recognition to convert the voice information into text information, then performs semantic analysis on the text information to obtain the word segmentation result, and performs part-of-speech tagging and adds business tags to the segmented words, and then uses a deep learning model based on a convolutional neural network to analyze the intention of the user's input voice and obtain the target device. The target device is the controlled object corresponding to the user's voice control, and the target device can be any type of smart device in the aforementioned device list.

[0111] Step S2, querying the authorization list corresponding to the target device.

[0112] The voice control device 100 maintains an authorization list corresponding to each smart device in the device list. After obtaining the target device, the authorization list corresponding to the target device can be queried according to the device name / type of the target device. The authorization list may be empty or not empty. When the authorization list is not empty, it includes at least one identity identifier of a user who has the authority to voice control the target device. The identity identifier is the nickname / account name that the user customizes when registering a voiceprint account.

[0113] Step S3, determine whether the authorization list is empty. If the authorization list is empty, execute step S9; otherwise, if the authorization list is not empty, execute step S4.

[0114] Step S4, performing voiceprint recognition on the voice information to obtain target voiceprint information.

[0115] In some embodiments, feature extraction is performed on voice information, and the time domain signal is converted into a frequency domain signal to provide a feature vector for the voiceprint model. The feature vector is input into the voiceprint model, and the voiceprint model performs voiceprint recognition based on the feature vector, and finally outputs target voiceprint information, which includes the voiceprint features of the user who is currently voice-controlling the target device.

[0116] Step S5, check whether the registration list includes the target voiceprint information. If the detection result is yes, execute step S6, otherwise execute step S9.

[0117] Referring to the description of the aforementioned UI part, the registration list stores the correspondence between the voiceprint information of registered users and their identity identifiers, so the user's identity can be directly identified through the voiceprint information and this correspondence.

[0118] In some embodiments, before executing step S5, it can be detected whether the registration list is empty. If the registration list is not empty, then continue to execute step S5; if the registration list is empty, that is, the registration list does not include any voiceprint information and its corresponding identity, then it is obviously impossible to include the target voiceprint information, then execute step S9.

[0119] Step S6: taking the identity in the registration list that has a corresponding relationship with the target voiceprint information as the target identity.

[0120] For example, the corresponding relationship set included in the registration list is {{voiceprint information A, Dad}, {voiceprint information B, Mom}, {voiceprint information C, Xiao Ming}, {voiceprint information D, Fang Fang}}. Voiceprint recognition is performed on the voice information of the user of the current voice-controlled target device to obtain the target voiceprint information. By comparing the target voiceprint information with the registration list, it is identified that the target voiceprint information is voiceprint information B. Then, according to the corresponding relationship of {voiceprint information B, Mom}, the target identity can be determined as "Mom".

[0121] Step S7, determining whether the target identity is included in the authorization list. If the authorization list includes the target identity, then executing step S8, otherwise executing step S9.

[0122] In some embodiments, after obtaining the target identity and the authorization list corresponding to the target device, the target identity is compared with the identities included in the authorization list one by one using an absolute string matching method. If the target identity is found in the authorization list, it means that the current user has the authority to control the target device by voice, and the comparison is stopped, and step S8 is executed; if the target identity is not found in the authorization list after traversing the authorization list, it means that the current user does not have the authority to control the target device by voice, and step S9 is executed.

[0123] Step S8: sending a control instruction to the target device.

[0124] The control instruction is used to instruct the target device to perform the operation corresponding to the voice information. For example, the text corresponding to the voice information input by the user is "turn on the TV", that is, the target device is the TV, and the voice control device 100 sends a control instruction to the TV. In response to the received control instruction, the TV controls the underlying controlled components to execute the boot program, so that the target device accurately completes the corresponding operation according to the user's voice control intention.

[0125] Step S9: No control instruction is sent to the target device, and the user is prompted that he does not have the authority to control the target device by voice.

[0126] In some embodiments, when the current user is identified as not having the authority to voice control the target device through the authorization list, the voice control device 100 does not send a control instruction to the target device, and the target device does not receive any control instruction, and the current working state remains unchanged, so that the voice control of the target device by the unauthorized user is invalid, thereby improving the security of smart home voice control. At the same time, the voice control device 100 controls the display 140 or the sound player 150 to display a text prompt message or broadcast a voice prompt message in the UI to prompt the current user that he does not have the authority to voice control the target device, so that the current user knows that he cannot voice control the target device because he is not authorized.

[0127] In some embodiments, the authorization list is used to specify the user identity that has the authority to voice control the target device. If the authorization list is empty, it means that no one has the authority to voice control the target device. When step S3 determines that the authorization list is empty, no control instructions are sent to the target device, and a text prompt message is displayed in the UI or a voice prompt message is broadcast to prompt that the current user does not have the authority to voice control the target device.

[0128] In some embodiments, after user M learns that he does not have the authority to control the target device by voice, if he wants to have the voice control authority, he can ask the user with the specified identity in the aforementioned list setting authority list to authorize him, for example, the list setting authority list includes {Dad, Mom}. If user M has not registered a voiceprint account before, first follow the aforementioned registration process to add the corresponding relationship between user M's own voiceprint information and identity identifier to the registration list. If the father or mother in the list setting authority list agrees to authorize, the father or mother will add the identity identifier of user M to the authorization list of the target device; if the father or mother does not agree to authorize, user M still does not have the authority to control the target device by voice.

[0129] In some embodiments, if user M has previously registered a voiceprint account, that is, the registration list stores the correspondence between user M's voiceprint information and identity identifier, then there is no need to register again. If the father or mother in the list setting permission list agrees to authorize, the father or mother will add the identity identifier of user M to the authorization list of the target device; if the father or mother does not agree to authorize, user M still does not have the authority to control the target device by voice.

[0130] In some embodiments, when it is detected in step S5 that the target voiceprint information is not included in the registration list, it means that the user of the current voice-controlled target device has not registered a voiceprint account before, that is, there is no corresponding relationship between the user's voiceprint information and the identity identifier in the registration list, and the actual identity of the user cannot be identified, and the authorized identity in the authorization list is selected from the registration list, so the unregistered user generally does not have the authority to voice-control the target device. Therefore, in this case, the voice control device 100 does not send a control instruction to the target device, and displays a text prompt message in the UI or broadcasts a voice prompt message to prompt the user that he does not have the authority to voice-control the target device.

[0131] In some embodiments, if the target voiceprint information is not included in the registration list in step S5, the voice control device 100 can temporarily store the target voiceprint information, and generate and add a random sequence identifier for the target voiceprint information, wherein the random sequence identifier is used to indicate that the target voiceprint information is in an unregistered state. That is, when user N has not registered a voiceprint account, he inputs voice information to control the working state of the target device. Since the voice control device 100 has obtained the voiceprint information of user N, it is not necessary to obtain the voiceprint information of user N by inputting the preset voice information in the aforementioned registration process, thereby improving the registration efficiency of user N and achieving quick registration.

[0132] In some embodiments, if the target voiceprint information is not included in the registration list in step S5, when the controller 110 detects the random sequence identifier carried by the target voiceprint information, a third registration prompt can be displayed in the UI or voice broadcast, and the third registration prompt is used to ask the user whether to register the target voiceprint information. Fig.13 An example of the UI displaying the third registration prompt is provided, in which a registration inquiry pop-up window is displayed on the UI interface, and inquiry information is displayed in the registration inquiry pop-up window. For example, the inquiry information is "You have not registered a voiceprint account yet, do you want to register immediately?" The registration inquiry pop-up window also has a register now control, a register later control, and a cancel control.

[0133] In some embodiments, after user N views the inquiry information, if the user clicks the "Register Immediately" control, the controller 110 receives the "Register Immediately" instruction input by user N and can provide a fourth registration prompt in the form of UI display or voice broadcast. The fourth registration prompt is used to guide user N to input a second identity identifier corresponding to their target voiceprint information. Since the controller 110 has already obtained the voiceprint information of user N, the link of collecting voiceprint information through preset voice messages is skipped. Instead, directly through the fourth registration prompt, user N is guided to input their custom identity identifier, that is, the second identity identifier named in this application. User N can speak the second identity identifier by voice or input it in text form through the electronic keyboard on the UI interface. Due to the situation of homophones with different characters, such as "xiao" and "xiaoxiao", as Fig.14 shown, it is more accurate to input the second identity identifier in text form manually.

[0134] In some embodiments, after the user inputs the second identity identifier and clicks the "Confirm Registration" control, the controller 110 performs a uniqueness determination based on the received second identity identifier and the registration list. If the second identity identifier is not included in the registration list, then the second identity identifier is unique. The random sequence identifier is deleted, and the corresponding relationship between the target voiceprint information of user N and the second identity identifier is stored in the registration list. Then, a registration success message is prompted, the registration inquiry pop-up window is closed, and the current registration process ends. Conversely, if the second identity identifier is included in the registration list, then the second identity identifier is not unique. The registration inquiry pop-up window switches to a prompt such as "This nickname has already been registered. Please change to another nickname." After the user views this prompt message, the user changes the second identity identifier one or more times until the changed second identity identifier meets the uniqueness condition.

[0135] In some embodiments, after user N views the inquiry information, if the user clicks the "Register Later" control, the current registration inquiry pop-up window is closed, and after a preset time interval, the registration inquiry pop-up window is displayed again. The preset time interval can be set according to the actual application. For example, the preset time interval is 6 hours, and this application does not make specific limitations.

[0136] In some embodiments, after user N views the inquiry information, if the user clicks the "Cancel" control, it means that the user does not want to register currently. The registration process is cancelled, the registration inquiry pop-up window is closed, and the temporarily stored target voiceprint information of user N and its random sequence identifier are deleted. Subsequently, if user N wants to register a voiceprint account, the registration process is completed according to the first registration prompt and the second registration prompt.

[0137] It should be noted that this technical solution mainly involves the authorization management link in smart home voice control, and does not limit other links in smart home and voice control. In addition, the UI and software and hardware configurations of the voice control device 100 can be set based on actual applications, not limited to the examples of this application.

[0138] Those skilled in the art can clearly understand that the technology in the embodiments of the present invention can be implemented by means of software plus a necessary general hardware platform. In a specific implementation, the present invention also provides a computer storage medium, which can store a program. When the computer storage medium is located in an intelligent device or a voice control device, the program may include a voice control method for a smart home configured at either end when executed. Among them, the computer storage medium may be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0139] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0140] For the convenience of explanation, the above description has been made in conjunction with specific embodiments. However, the above exemplary discussion is not intended to be exhaustive or limit the embodiments to the specific forms disclosed above. Based on the above teachings, various modifications and variations can be obtained. The selection and description of the above embodiments are to better explain the principles and practical applications, so that those skilled in the art can better use the embodiments and various different variations of the embodiments suitable for specific use considerations.

Claims

1. A voice control device for smart home, characterized in that: include: A voice collector is used to collect voice information input by users; A communicator, used to communicate with smart devices included in the home scene; The controller is configured to execute: In response to receiving the voice information currently input by the user, recognizing the voice information, and acquiring the target device according to the recognition result; Querying an authorization list corresponding to the target device, the authorization list including the identity of a user who has the authority to voice control the target device; If the authorization list is not empty, perform voiceprint recognition on the voice information to obtain the target identity of the user to whom the current voiceprint belongs; If the authorization list is empty, no control instruction is sent to the target device, and the user is prompted that he does not have the authority to control the target device by voice; If the target identity is included in the authorization list, sending the control instruction to the target device, the control instruction is used to instruct the target device to perform the operation corresponding to the voice information; If the target identity is not included in the authorization list, the control instruction is not sent to the target device, and the user is prompted that he does not have the authority to control the target device by voice.

2. The voice control device according to claim 1, characterized in that: The controller is also used to obtain the target identity of the user to whom the current voiceprint belongs in the following manner: Performing voiceprint recognition on the voice information to obtain target voiceprint information; Detecting whether the target voiceprint information is included in the registration list; wherein the registration list stores the corresponding relationship between the voiceprint information of registered users and their identity identifiers, and the authorized list is selected from the registration list; If it is detected that the target voiceprint information is included in the registration list, an identity identifier corresponding to the target voiceprint information is used as the target identity identifier.

3. The voice control device according to claim 2, characterized in that: The controller is also used to execute: If it is detected that the target voiceprint information is not included in the registration list, the control instruction is not sent to the target device, and the user is prompted that he does not have the authority to control the target device by voice; A random sequence identifier is generated for the target voiceprint information, where the random sequence identifier is used to indicate that the target voiceprint information is in an unregistered state.

4. The voice control device according to claim 2, characterized in that: The controller is also used to execute: In response to receiving a registration request input by a user, performing a first registration prompt, wherein the first registration prompt is used to guide the user to input preset voice information; If the preset voice information is received, voiceprint recognition is performed on the preset voice information to obtain first voiceprint information, and a second registration prompt is performed, where the second registration prompt is used to guide the user to enter a first identity identifier corresponding to the first voiceprint information; A first identity identifier input by a user is received, and a corresponding relationship between the first voiceprint information and the first identity identifier is stored in the registration list.

5. The voice control device according to claim 3, characterized in that: The controller is also used to execute: When the random sequence identifier is detected, a third registration prompt is performed, wherein the third registration prompt is used to ask the user whether to register the target voiceprint information; If an immediate registration instruction input by the user is received, a fourth registration prompt is performed, wherein the fourth registration prompt is used to guide the user to input a second identity identifier corresponding to the target voiceprint information; A second identity identifier input by a user is received, and a corresponding relationship between the target voiceprint information and the second identity identifier is stored in the registration list.

6. The voice control device according to claim 2, characterized in that: The controller is also used to execute: According to the user's deletion operation on the first target item in the authorization list, deleting the identity identifier corresponding to the first target item from the authorization list; Alternatively, upon receiving a new addition operation input by the user, displaying the registration list; According to a selection operation of a user on at least one second target item in the registration list, the second target item is added to the authorization list.

7. A smart device, characterized in that: include: A communicator, used for communicating with a voice control device; The controller is configured to execute: Upon receiving a control instruction sent by the voice control device, executing a corresponding operation according to the control instruction; Among them, the control instruction is sent by the voice control device after the voice control device identifies the voice information input by the user, obtains the target device according to the identification result and queries the authorization list corresponding to the target device, and the authorization list is not empty and the target identity obtained after voiceprint recognition of the voice information is included in the authorization list; if the authorization list is empty, the control instruction is not sent to the target device and the user is prompted that he does not have the authority to voice control the target device; the authorization list includes the identity of the user who has the authority to voice control the target device.

8. A voice control method for smart home, characterized in that: include: In response to receiving the voice information currently input by the user, recognizing the voice information, and acquiring the target device according to the recognition result; Querying an authorization list corresponding to the target device, the authorization list including the identity of a user who has the authority to voice control the target device; If the authorization list is not empty, perform voiceprint recognition on the voice information to obtain the target identity of the user to whom the current voiceprint belongs; If the authorization list is empty, no control instruction is sent to the target device, and the user is prompted that he does not have the authority to control the target device by voice; If the target identity is included in the authorization list, sending the control instruction to the target device, the control instruction is used to instruct the target device to perform the operation corresponding to the voice information; If the target identity is not included in the authorization list, the control instruction is not sent to the target device, and the user is prompted that he does not have the authority to control the target device by voice.

9. A voice control method for smart home, characterized in that: include: Upon receiving a control instruction sent by a voice control device, executing a corresponding operation according to the control instruction; The control instruction is sent when the voice control device obtains the target device according to the recognition result and queries the authorization list corresponding to the target device after recognizing the voice information input by the user and the target identity obtained after performing voiceprint recognition on the voice information is included in the authorization list; if the authorization list is empty, the control instruction is not sent to the target device and the user is prompted that he does not have the authority to control the target device by voice; The authorization list includes the identities of users who have the authority to voice control the target device.

Images