Voice control method and device
Through the analysis of voice commands and model interaction, control information is obtained to call control objects, the problem of insufficient flexibility in smart home control is solved, and higher flexibility and customized control is achieved.
Patent Information
- Application Number
- CN202411083518.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-07
- Publication Date
- 2024-12-03
AI Technical Summary
The prior art is difficult to achieve flexibility in smart home control, and users need to make a lot of settings in the control device to achieve voice control.
By analyzing the obtained voice commands, generating instruction information, and semantic disassembly based on the deployed model, obtaining control information, calling the corresponding control object to control the controlled device, if the user ID is included, the extended control information is obtained. If empty, obtain the default information or issue permission alarms, and self-learning and update the knowledge base based on operation instructions.
It improves the flexibility of smart home control, reduces the user's setting needs in the control device, and improves the level of customization and flexibility of control.
Smart Images

Figure CN119068875A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of communication technology, and in particular to a voice control method and device. Background Art
[0002] With the development of network technology, home appliances also have network functions, which makes it feasible to intelligently control home appliances. In order to achieve intelligent control, home appliances will first be connected to a control device that can provide internal and external data interaction, such as a home smart hub and router.
[0003] When implementing intelligent control, the control device receives the voice control command sent by the user, determines the execution device to be controlled according to the voice control command, and sends the control information obtained by parsing the voice control command to the execution device for execution. In the current implementation, the control device uses a complete matching method to determine the content of the control information to be executed, and a large number of settings need to be made in the control device. As users' demand for control flexibility increases, how to achieve control flexibility of smart homes is an urgent problem to be solved by those skilled in the art. Summary of the invention
[0004] In order to overcome the problems existing in the related art, this specification provides a voice control method and device.
[0005] According to a first aspect of an embodiment of this specification, a voice control method is provided, including:
[0006] Parse the acquired voice commands and generate command information;
[0007] Semantically decomposing the instruction information based on the deployed model to obtain control information, wherein the control information at least includes a control object identifier and control content;
[0008] The corresponding control object is called according to the control information to control the controlled device.
[0009] Optionally, the step of parsing the acquired voice command to generate command information further includes:
[0010] receiving a voice command, and performing voiceprint recognition according to the voice command;
[0011] If there is voiceprint information corresponding to the voice command, the acquired voice command is parsed to generate command information, wherein the command information includes a user identifier, and the control information also includes a user identifier.
[0012] Optionally, calling a corresponding control object according to the control information to control the controlled device includes:
[0013] The corresponding control object is called according to the control object identifier. If it is determined that the user identifier contained in the control information is not empty, the extended control information corresponding to the user identifier and the control object is obtained through the deployed knowledge base, and the controlled device is controlled according to the extended control information.
[0014] Optionally, the calling a corresponding control object according to the control information to control the controlled device further includes:
[0015] If it is determined that the user identifier included in the control information is empty, then obtaining default control information, and controlling the controlled device according to the default control information; or,
[0016] If it is determined that the user identifier included in the control information is empty, an authority alarm is issued.
[0017] Optionally, after calling the corresponding control object according to the control information to control the controlled device, the method further includes:
[0018] Obtaining an operation instruction from a user for the controlled device;
[0019] The operation instructions are self-learned based on the deployed model, and the knowledge base is updated according to the self-learning results.
[0020] According to a second aspect of the embodiments of this specification, a voice control device is provided, including:
[0021] A parsing unit, used to parse the acquired voice command and generate command information;
[0022] An acquisition unit, configured to semantically decompose the instruction information based on the deployed model to acquire control information, wherein the control information at least includes a control object identifier and control content;
[0023] The control unit is used to call the corresponding control object according to the control information to control the controlled device.
[0024] Optionally, the parsing unit further includes:
[0025] A receiving module, used to receive a voice command and perform voiceprint recognition according to the voice command;
[0026] The parsing module is used to parse the acquired voice command and generate command information if there is voiceprint information corresponding to the voice command, wherein the command information includes a user identifier and the control information also includes a user identifier.
[0027] Optionally, the control unit includes:
[0028] The first control module is used to call the corresponding control object according to the control object identifier. If it is determined that the user identifier contained in the control information is not empty, the extended control information corresponding to the user identifier and the control object is obtained through the deployed knowledge base, and the controlled device is controlled according to the extended control information.
[0029] Optionally, the control unit further includes:
[0030] The second control module is used to obtain default control information if it is determined that the user identifier included in the control information is empty, and control the controlled device according to the default control information; or, if it is determined that the user identifier included in the control information is empty, issue an authority alarm.
[0031] Optionally, the device further includes:
[0032] An operation acquisition unit, used to acquire an operation instruction of a user for the controlled device;
[0033] An updating unit is used to perform self-learning on the operation instruction based on the deployed model, and update the knowledge base according to the self-learning result.
[0034] According to a third aspect of the embodiments of this specification, a control device is provided, which is applied to a smart home system, and the control device is communicatively connected to a plurality of controlled devices;
[0035] The control device includes a transceiver, a processor, and a machine-readable storage medium, wherein the machine-readable storage medium stores machine-executable instructions that can be executed by the processor, and the processor is prompted by the machine-executable instructions to implement any of the method steps described above.
[0036] Optionally, a model is deployed on the control device, or the control device accesses the model through a communication connection.
[0037] Optionally, a knowledge base is deployed on the control device.
[0038] According to a fourth aspect of the embodiments of this specification, a smart home system is provided, comprising a plurality of controlled devices, a control device as described in any one of the above, and a network device that communicatively connects the controlled devices and the control devices.
[0039] The technical solutions provided by the embodiments of this specification may have the following beneficial effects:
[0040] In the embodiments of the present specification, the acquired voice commands are parsed, the acquired command information is interacted with the deployed model, the control information is acquired, and the control object to be called is confirmed based on the acquired control information, and the controlled device is controlled based on the control object. This allows the model to be combined with the smart home control process to reduce the settings that the user needs to perform in the control device, thereby improving the flexibility of smart home control.
[0041] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present specification. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the specification and, together with the description, serve to explain the principles of the specification.
[0043] Figure 1 The structure of a smart home system involved in this application is:
[0044] Figure 2 is a flow chart of a voice control method involved in this application;
[0045] Figure 3 It is a structural schematic diagram of a voice control device involved in the present application;
[0046] Figure 4 It is a structural schematic diagram of a control device involved in this application. DETAILED DESCRIPTION
[0047] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this specification. Instead, they are merely examples of devices and methods consistent with some aspects of this specification as detailed in the appended claims.
[0048] The terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit this specification. The singular forms "a", "the" and "the" used in this specification and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.
[0049] It should be understood that although the terms first, second, third, etc. may be used in this specification to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this specification, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".
[0050] like Figure 1 As shown, in a smart home system, a control device, several controlled devices and a network device may be deployed, and a communication connection is established between the control device and the controlled device based on the network device. In a smart home system, various sensors and input devices may be provided, such as temperature sensors, light sensors, cameras, microphones, etc. These sensors or input devices may be integrated into the controlled device or the control device.
[0051] The control device can be an independently set up intelligent center or integrated into network devices such as gateways.
[0052] The controlled device can be a single device, such as a cloud screen, audio, etc., or a device group consisting of multiple devices, such as a smart home that includes lights, curtains, etc.
[0053] Network devices can realize communication connections in smart home systems based on wired or wireless communications. For example, the network device can be a network composed of switches and routers. The router acts as a gateway to provide interaction with the external network, and the switch connects various controlled devices. Alternatively, the network can be an AC (Access Controller) and an AP (Access Point) that act as a gateway to provide interaction with the external network, and the AP can be used to connect controlled devices. In addition, the model can be deployed in the home network or in the external network. If deployed in the home network, it can be deployed in the control device or independent of the control device. If deployed in the external network, the control device needs to be able to interact with the model deployed in the external network through the network device. Figure 1 The model is deployed on the external network.
[0054] This application provides a voice control method, such as Figure 2 As shown, including:
[0055] S200: parse the acquired voice command to generate command information.
[0056] When users need to control smart homes, they can use voice to wake up the smart home service at home to control smart homes. For example, by interacting with the smart hub, they can issue voice commands to it, such as "turn on the lights and play a song."
[0057] After receiving the voice command, the intelligent hub can call the voice recognition interface to parse it, convert the voice command into text content, and generate command information based on the text content, such as json format. The intelligent hub can send the json format information and encapsulate it into a format that the model can recognize, such as prompt information, and then send the prompt information to the model for processing.
[0058] S201. Semantically decompose the instruction information based on the deployed model to obtain control information.
[0059] When a user issues a voice command, the purpose may be to control the operation of multiple controlled devices, that is, to control multiple control objects. For example, in the voice command "turn on the lights and then play a song", the lighting and audio can be controlled. Therefore, after the command information is input into the model, the model can parse the command information from the received prompt word information.
[0060] Since a command message may contain several control information, the model can semantically decompose the command message to obtain each control instruction contained therein. For example, the above voice command may contain two types of control information, namely, control for lighting and control for audio.
[0061] It should be noted that the control object refers to the client (agent) formed in the intelligent hub. The client can be understood as a control program for a type of controlled device in the intelligent hub. The client can manage the controlled devices belonging to the client. For example, the agent responsible for lighting control can manage lamps and curtains, and the agent responsible for music control can manage audio, etc., and can be set according to actual needs.
[0062] The client has an interface, and the intelligent center can exchange information by calling the interface, transmit the acquired control information to the corresponding client for processing and realize control of the controlled device.
[0063] The control information at least includes a control object identifier and control content. The control object identifier is used to mark the control object requiring the control information, and the control content is used to indicate a specific control method.
[0064] S202: Call a corresponding control object according to the control information to control the controlled device.
[0065] According to the control object identifier in the control information, the smart hub sends the control content to the various controlled devices corresponding to the control object, so that the corresponding controlled devices can perform smart home control. For example, the smart hub calls the lighting agent to turn on the lights in the living room, and calls the music agent to control the sound system to start playing.
[0066] Optionally, the step S200 of parsing the acquired voice command to generate command information further includes:
[0067] S200A: Receive a voice command, and perform voiceprint recognition according to the voice command.
[0068] When using the smart hub, the user's voiceprint information can be pre-set. When setting, the user can input voice through the smart home application, for example, repeat the voice of the wake-up word three times, so that the smart hub can record the user's voiceprint information and establish a corresponding relationship between the voiceprint information, user identification and the user name set by the user.
[0069] When the smart hub receives a user's voice command, it performs voiceprint recognition by calling the voiceprint recognition program in the smart hub, and matches the recognized voiceprint information with the stored correspondence to determine whether the user who inputs the voice command is an authorized user.
[0070] S200B: If there is voiceprint information corresponding to the voice command, the acquired voice command is parsed to generate command information.
[0071] If it is determined based on the voice command that there is corresponding voiceprint information, then the user who is making the voice input is determined to be a user with control authority. After determining that the user has control authority, the intelligent hub parses the voice command and generates command information. At this time, the command information includes a user ID, and the control information also includes a user ID. In this way, each control information can mark the user who issued the voice command, so that the model can perform self-learning based on the user's habits based on the user ID. All types of clients can determine the control method that the user is accustomed to based on the user ID carried in the received control information, thereby further improving the customization level of smart home control.
[0072] S200C: If there is voiceprint information corresponding to the voice command, it is prompted that the user does not have control authority for the smart home.
[0073] Optionally, the step S202, calling a corresponding control object according to the control information to control the controlled device, includes:
[0074] S202A. Call the corresponding control object according to the control object identifier. If it is determined that the user identifier included in the control information is not empty, obtain the extended control information corresponding to the user identifier and the control object through the deployed knowledge base, and control the controlled device according to the extended control information.
[0075] exist Figure 2 In the figure, the knowledge base deployed in the internal network is indicated by a dotted line. The knowledge base is connected to the AC, and the intelligent hub (and various clients deployed therein) can access the knowledge base through the AC. The control content corresponding to the control information is stored in the knowledge base. Since the control information carries the user identifier, the control content obtained from the knowledge base can reflect the user's control habits. For example, for the control information corresponding to the "play music" part of the voice command issued by user A, the knowledge base can determine the extended control information such as the music or music type that user A is accustomed to playing, and feed the extended control information back to the audio agent. For example, according to user A's habit, "play music" refers to the music in playlist A.
[0076] Alternatively, in response to a "turn on the lights" command issued by user A, the extended control information obtained through the knowledge base instructs the lighting agent to turn on the lights in the "living room" and "kitchen".
[0077] Of course, depending on the different control objects, the extended control information corresponding to each control information is different, and it can be set according to actual needs without any restriction.
[0078] Optionally, step S202, calling a corresponding control object according to the control information to control the controlled device, further includes:
[0079] S202B: If it is determined that the user identifier included in the control information is empty, obtain default control information, and control the controlled device according to the default control information.
[0080] If the intelligent hub finds that the user who issued the voice command does not have control authority when parsing the user's voice command, the intelligent hub can mark the user ID in the command information as empty without processing, indicating that the user does not have control authority.
[0081] At this time, the client can obtain the default control information in the intelligent hub according to the control information (or obtain the default control information from the knowledge base), and control the controlled device through the default control information.
[0082] Alternatively, S202C: if it is determined that the user identifier included in the control information is empty, then an authority alarm is issued.
[0083] In another case, for example, if the user sets a limit that people without permission cannot control the system, the smart hub will issue a permission warning to inform the user who is currently issuing the voice command that he or she does not have permission.
[0084] Optionally, after step S202, invoking a corresponding control object according to the control information to control the controlled device, the method further includes:
[0085] S203: Obtain an operation instruction from the user for the controlled device.
[0086] After controlling the controlled device through voice commands, the user may adjust the controlled device according to the current situation, such as adjusting the light brightness and modifying the playlist. These adjustments made to the controlled device can be called operation instructions, which can reflect the state that the user wants the smart home control to reach.
[0087] At this time, the intelligent center can obtain these operation instructions and send the operation instructions and user identification to the deployed model, conduct self-learning through the model, and adjust the user's control information.
[0088] S204: Perform self-learning on the operation instruction based on the deployed model, and update the knowledge base according to the self-learning result.
[0089] After the model performs self-learning based on the operating instructions, the intelligent center can update the knowledge base according to the self-learning results after obtaining the self-learning structure sent by the model, so that the knowledge base can reflect the user's latest control information.
[0090] Through the interaction between the deployed models and the knowledge base, in the process of smart home control, the knowledge base can obtain the user's latest control requirements and improve the flexibility of smart home control.
[0091] Correspondingly, the present application also provides a voice control device, such as Figure 3 As shown, including:
[0092] A parsing unit, used to parse the acquired voice command and generate command information;
[0093] An acquisition unit, configured to semantically decompose the instruction information based on the deployed model to acquire control information, wherein the control information at least includes a control object identifier and control content;
[0094] The control unit is used to call the corresponding control object according to the control information to control the controlled device.
[0095] Optionally, the parsing unit further includes:
[0096] A receiving module, used to receive a voice command and perform voiceprint recognition according to the voice command;
[0097] The parsing module is used to parse the acquired voice command and generate command information if there is voiceprint information corresponding to the voice command, wherein the command information includes a user identifier and the control information also includes a user identifier.
[0098] Optionally, the control unit includes:
[0099] The first control module is used to call the corresponding control object according to the control object identifier. If it is determined that the user identifier contained in the control information is not empty, the extended control information corresponding to the user identifier and the control object is obtained through the deployed knowledge base, and the controlled device is controlled according to the extended control information.
[0100] Optionally, the control unit further includes:
[0101] The second control module is used to obtain default control information if it is determined that the user identifier included in the control information is empty, and control the controlled device according to the default control information; or, if it is determined that the user identifier included in the control information is empty, issue an authority alarm.
[0102] Optionally, the device further includes:
[0103] An operation acquisition unit, used to acquire an operation instruction of a user for the controlled device;
[0104] An updating unit is used to perform self-learning on the operation instruction based on the deployed model, and update the knowledge base according to the self-learning result.
[0105] Correspondingly, the present application also provides a control device, such as Figure 4 As shown, it is applied to a smart home system, and the control device is communicatively connected to a number of controlled devices;
[0106] The control device includes a transceiver, a processor, and a machine-readable storage medium, wherein the machine-readable storage medium stores machine-executable instructions that can be executed by the processor, and the processor is prompted by the machine-executable instructions to implement any of the method steps described above.
[0107] Optionally, a model is deployed on the control device, or the control device accesses the model through a communication connection.
[0108] Optionally, a knowledge base is deployed on the control device.
[0109] Correspondingly, a smart home system is provided, such as Figure 1As shown, it includes several controlled devices, any of the control devices described above, and a network device that communicates and connects the controlled devices and the control devices.
[0110] The technical solutions provided by the embodiments of this specification may have the following beneficial effects:
[0111] In the embodiments of the present specification, the acquired voice commands are parsed, the acquired command information is interacted with the deployed model, the control information is acquired, and the control object to be called is confirmed based on the acquired control information, and the controlled device is controlled based on the control object. This allows the model to be combined with the smart home control process to reduce the settings that the user needs to perform in the control device, thereby improving the flexibility of smart home control.
[0112] The implementation process of the functions and effects of each module in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, which will not be repeated here.
[0113] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this specification. A person of ordinary skill in the art can understand and implement it without paying creative labor.
[0114] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0115] Those skilled in the art will readily appreciate other embodiments of the specification after considering the specification and practicing the invention claimed herein. The specification is intended to cover any variations, uses or adaptations of the specification that follow the general principles of the specification and include common knowledge or customary techniques in the art that are not claimed in the specification. The specification and examples are to be considered exemplary only, and the true scope and spirit of the specification are indicated by the following claims.
[0116] It should be understood that the present description is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present description is limited only by the appended claims.
[0117] The above description is only a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this specification should be included in the scope of protection of this specification.
Claims
1. A voice control method, characterized in that: include: Parse the acquired voice commands and generate command information; Semantically decomposing the instruction information based on the deployed model to obtain control information, wherein the control information at least includes a control object identifier and control content; The corresponding control object is called according to the control information to control the controlled device.
2. The method according to claim 1, characterized in that The step of parsing the acquired voice command to generate command information further includes: receiving a voice command, and performing voiceprint recognition according to the voice command; If there is voiceprint information corresponding to the voice command, the acquired voice command is parsed to generate command information, wherein the command information includes a user identifier, and the control information also includes a user identifier.
3. The method according to claim 2, characterized in that The controlling the controlled device by calling the corresponding control object according to the control information includes: The corresponding control object is called according to the control object identifier. If it is determined that the user identifier contained in the control information is not empty, the extended control information corresponding to the user identifier and the control object is obtained through the deployed knowledge base, and the controlled device is controlled according to the extended control information.
4. The method according to claim 3, characterized in that The controlling the controlled device by calling the corresponding control object according to the control information also includes: If it is determined that the user identifier included in the control information is empty, then obtaining default control information, and controlling the controlled device according to the default control information; or, If it is determined that the user identifier included in the control information is empty, an authority alarm is issued.
5. The method according to claim 3, characterized in that: After calling the corresponding control object according to the control information to control the controlled device, the method further includes: Obtaining an operation instruction from a user for the controlled device; The operation instructions are self-learned based on the deployed model, and the knowledge base is updated according to the self-learning results.
6. A voice control device, characterized in that: include: A parsing unit, used to parse the acquired voice command and generate command information; An acquisition unit, configured to semantically decompose the instruction information based on the deployed model to acquire control information, wherein the control information at least includes a control object identifier and control content; The control unit is used to call the corresponding control object according to the control information to control the controlled device.
7. A control device, characterized in that: Applied to a smart home system, the control device is communicatively connected to a number of controlled devices; The control device comprises a transceiver, a processor and a machine-readable storage medium, wherein the machine-readable storage medium stores machine-executable instructions that can be executed by the processor, and the processor is prompted by the machine-executable instructions to implement the method steps described in any one of claims 1-5.
8. The control device according to claim 7, characterized in that A model is deployed on the control device, or the control device accesses the model through a communication connection.
9. The control device according to claim 7, characterized in that: A knowledge base is deployed on the control device.
10. A smart home system, characterized in that: The invention comprises a plurality of controlled devices, a control device as described in any one of claims 7 to 9, and a network device for communication connecting the controlled devices and the control device.
