Voice control method, server, smart home system, and computer-readable storage medium

Abstract

The present application discloses a voice control method, server, smart home system, and computer-readable storage medium. The voice control method includes: obtaining voice recognition times for multiple terminal devices, where the recognition time refers to the time it takes for the terminal devices to acquire a voice signal and obtain a recognition result; determining a target recognition terminal device from the multiple terminal devices based on the voice recognition times of the multiple terminal devices; determining a controlled terminal device from the multiple terminal devices based on the recognition results of the target recognition terminal device; and transmitting the recognition results of the target recognition terminal device to the controlled terminal devices. The voice control method provided by the present application improves the accuracy and synchronization of voice recognition results and subsequent control operations.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and specifically designs a voice control method, a server, a smart home system, and a computer-readable storage medium. Background Art

[0002] With the advent of the intelligent era, there are more and more electrical terminal devices with voice control in the home. Voice control can bring more convenience, such as adjusting the shower water flow and water temperature through voice control when taking a shower, or adjusting the temperature and lighting brightness of the bathroom heater through voice control when using the toilet, without having to go to the terminal device or directly operate it with hands. However, there are various noises in the use environment of voice terminal devices, such as the terminal device itself that the user is about to control or the noise caused by the operation of other terminal devices in the same space, such as the sound of water flowing from the faucet, the sound of air flow when the bathroom heater is exhausting, or the sound of audio playing by the smart mirror. In these noisy environments, when the user speaks multiple times, it is possible that the terminal device has no response or responds infrequently, or acts incorrectly, or when multiple terminal devices work in conjunction, the terminal devices in the noisy area cannot respond synchronously.

[0003] Existing technologies solve the above problems by adding multi-point or array microphone sound recognition devices and high-speed main control operations to a single machine, conducting long-term training to establish models, and using targeted noise filtering algorithms to identify the corresponding noises. However, these dedicated algorithms generally have long cycles and the corresponding main control hardware application costs are high. Summary of the Invention

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the present application proposes a voice control method, a server, a smart home system, and a computer-readable storage medium.

[0005] A first aspect of the present application provides a voice control method, comprising:

[0006] Obtaining speech recognition time for multiple terminal devices, where the recognition time refers to the time taken by the terminal device from collecting the speech signal to obtaining the recognition result;

[0007] According to the speech recognition time of the plurality of terminal devices, a target recognition terminal device is determined from the plurality of terminal devices,

[0008] According to the identification result of the target identification terminal device, a controlled terminal device is determined from the plurality of terminal devices, and the identification result of the target identification terminal device is sent to the controlled terminal device.

[0009] In one embodiment, determining the target recognition terminal device from the plurality of terminal devices based on the speech recognition times of the plurality of terminal devices includes: comparing the speech recognition times of the plurality of terminal devices, and determining the terminal device with the shortest speech recognition time as the target recognition terminal device.

[0010] In one embodiment, the method of determining a controlled terminal device from a plurality of terminal devices based on an identification result of a target identification terminal device and sending the identification result of the target identification terminal device to the controlled terminal device includes: obtaining the identification result of the target identification terminal device, re-identifying the identification result of the target identification terminal device to obtain a final target identification result, determining a controlled terminal device from a plurality of terminal devices based on the final target identification result, and sending the final target identification result to the controlled terminal device.

[0011] In one embodiment, the voice control method further includes obtaining recognition result confidence scores of the plurality of the terminal devices, and determining a target recognition terminal device from the plurality of the terminal devices based on the voice recognition time and recognition result confidence scores of the plurality of the terminal devices.

[0012] In one embodiment, the voice control method further includes obtaining noise coefficients of the plurality of terminal devices, and determining a target recognition terminal device from the plurality of terminal devices based on the noise coefficients, voice recognition time and recognition result confidence scores of the plurality of terminal devices, wherein the noise coefficient is the ratio of the current operating sound pressure value of the terminal device to the maximum processing sound pressure value.

[0013] In one embodiment, the target recognition terminal device is determined from the multiple terminal devices based on the noise coefficients, speech recognition times and recognition result confidence scores of the multiple terminal devices, specifically including calculating the recognition result accuracy values Score=K*CL / (T*N) of the multiple terminal devices, and determining the terminal device with the largest recognition result accuracy value as the target recognition terminal device, wherein K is the weight factor of the corresponding terminal device, K=1 / (operating sound pressure value of the corresponding terminal device / total operating sound pressure values of multiple terminal devices), CL is the recognition result confidence score of the corresponding terminal device, T is the speech recognition time of the corresponding terminal device, in milliseconds, and N is the noise coefficient of the corresponding terminal device.

[0014] In one embodiment, obtaining the speech recognition times of the plurality of terminal devices includes:

[0015] Invoking the plurality of terminal devices to respectively recognize the voice signal to obtain the voice recognition times of the plurality of terminal devices;

[0016] If the noise coefficient of the terminal device is greater than a preset threshold, noise reduction processing is performed on the terminal device before calling the terminal device to recognize the voice signal.

[0017] In one embodiment, the terminal device is a water outlet terminal device, and the noise reduction process includes reducing the water flow rate.

[0018] In one embodiment, the terminal device is an air conditioning terminal device, and the noise reduction process includes reducing the wind speed.

[0019] In one embodiment, the terminal device is a sound playing terminal device, and the noise reduction processing includes reducing the volume.

[0020] The second aspect of the present application provides a server, which includes a processor and a memory, wherein the memory stores at least one program code, and the at least one program code is loaded by the processor and executes the voice control method described in the first aspect of the present invention.

[0021] The third aspect of the present application provides a smart home system, comprising a plurality of terminal devices and a server as described in the second aspect of the present application, wherein the plurality of terminal devices are communicatively connected to the server.

[0022] A fourth aspect of the present application provides a computer-readable storage medium, wherein the storage medium stores at least one program code, and the at least one program code is used to be executed by a processor to implement the voice control method as described in the first aspect of the present invention.

[0023] The fifth aspect of the present application provides a computer program product, which includes computer instructions, which are stored in a computer-readable storage medium. The processor of a computer terminal device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer terminal device performs the voice control method as described in the first aspect of the present application.

[0024] The voice control method provided in the embodiment of the present application determines the target recognition terminal device based on the voice recognition time, the recognition result confidence score, and the terminal device noise coefficient, determines the controlled terminal device based on the recognition result of the target recognition terminal device and controls the operation of the controlled terminal device, while discarding the voice signals collected by other terminal devices, thereby improving the accuracy and synchronization of the voice recognition results and subsequent control operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings that constitute a part of this application are used to provide further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute improper limitations on this application.

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0027] Figure 1 A flow chart of a voice control method provided in one embodiment of the present application;

[0028] Figure 2 A schematic diagram of an implementation environment provided for one embodiment of the present application;

[0029] Figure 3 A structural block diagram of part of a server provided in one embodiment of the present application;

[0030] Figure 4 A block diagram of a smart home system provided for one embodiment of the present application. DETAILED DESCRIPTION

[0031] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0032] The terms "including," "having," and any variations thereof mentioned in the description of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or terminal device that includes a series of steps or modules is not limited to the listed steps or modules, but may optionally include other steps or modules not listed, or may optionally include other steps or modules inherent to the process, method, product, or terminal device.

[0033] In the embodiments of the present application, the term "plurality" includes two or more.

[0034] Additionally, in the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" or "for example" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present concepts in a concrete manner.

[0035] With the advent of the intelligent era, there are more and more electrical terminal devices with voice control in the home. Voice control can bring more convenience, such as adjusting the shower water flow and water temperature through voice control when taking a shower, or adjusting the temperature and lighting brightness of the bathroom heater through voice control when using the toilet, without having to go to the terminal device or directly operate it with hands. However, there are various noises in the use environment of voice terminal devices, such as the terminal device itself that the user is about to control or the noise caused by the operation of other terminal devices in the same space, such as the sound of water flowing from the faucet, the sound of air flow when the bathroom heater is exhausting, or the sound of audio playing by the smart mirror. In these noisy environments, when the user speaks multiple times, it is possible that the terminal device has no response or responds infrequently, or acts incorrectly, or when multiple terminal devices work in conjunction, the terminal devices in the noisy area cannot respond synchronously.

[0036] To solve the above problem, this embodiment provides a voice control method, including:

[0037] S1. Obtaining speech recognition time for multiple terminal devices, where the recognition time refers to the time taken by the terminal device from collecting the speech signal to obtaining the recognition result;

[0038] S2, based on the voice recognition time of the plurality of terminal devices, determining the target recognition terminal device from the plurality of terminal devices;

[0039] S3. Determine a controlled terminal device from the plurality of terminal devices according to the identification result of the target identification terminal device, and send the identification result of the target identification terminal device to the controlled terminal device.

[0040] In some embodiments, determining the target recognition terminal device from the multiple terminal devices based on the speech recognition times of the multiple terminal devices includes: comparing the speech recognition times of the multiple terminal devices, and determining the terminal device with the shortest speech recognition time as the target recognition terminal device.

[0041] Please refer to Figure 2 , Figure 2 A schematic diagram of an implementation environment provided by an embodiment of the present application is shown. Figure 2 This embodiment is further described.

[0042] like Figure 2As shown, in the same space, there are three terminal devices: terminal device A, terminal device B, and terminal device C. Terminal devices A, B, and C are respectively a bathroom heater, a shower, and a bathroom mirror cabinet. All three terminal devices have voice control functions, and the bathroom mirror cabinet has an audio playback function. When a user issues a control voice command at a certain location, due to factors such as the different distances and orientations between the three terminal devices and the user, the different noises generated by the three terminal devices' own operation, and the varying degrees of interference of certain environmental noises on the voice collection of the three terminal devices, all three terminal devices may not successfully collect and correctly recognize the user's voice command. It is possible that terminal devices A and B may fail to successfully recognize the user's voice command, while terminal device C may successfully collect and correctly recognize it. In the technical context of local single-machine recognition and single-machine control, if the voice command issued by the user is to control terminal device A or terminal device B, the problem of terminal device A or terminal device B not responding or responding incorrectly may occur.

[0043] In this embodiment, the speech recognition times of three terminal devices are obtained, and the terminal device with the shortest speech recognition time is determined as the target recognition terminal device. For example, if the speech recognition time of terminal device A is 0.6 seconds, the speech recognition time of terminal device B is 0.4 seconds, and the speech recognition time of terminal device C is 0.2 seconds, terminal device C is determined as the target recognition terminal device. Based on the recognition result of terminal device C, the controlled terminal device is determined from terminal devices A, B, and C, and the recognition result of terminal device C is sent to the controlled terminal devices. For example, if the recognition result of terminal device C for the user command is "Control terminal device B to raise the water temperature to 50 degrees Celsius," terminal device B is determined to be the controlled terminal device based on the recognition result, and the recognition result is sent to terminal device B. For another example, if the recognition result of terminal device C for the user command is "Control terminal device C to turn on the light," terminal device C is determined to be the controlled terminal device based on the recognition result, and the recognition result of terminal device C is sent to terminal device C. Or the recognition result of terminal device C is to control terminal device A to turn on and adjust the water temperature of terminal device C to 50 degrees Celsius. At this time, terminal device C and terminal device A are determined as controlled terminal devices, and the recognition result is sent to terminal device C and terminal device A. After receiving the recognition result, terminal device A and terminal device C execute the corresponding operation of this terminal device.

[0044] Speech recognition time refers to the time it takes from collecting a speech signal to obtaining a recognition result. This duration is affected by factors such as the distance between the speech source and the terminal device and noise. A shorter speech recognition time generally indicates better speech signal acquisition quality and higher recognition accuracy. This embodiment first obtains the speech recognition times of multiple terminal devices and selects the terminal device with the shortest speech recognition time as the target recognition terminal device. This improves speech recognition accuracy and reduces the probability of a single terminal device failing to recognize, resulting in no response or an incorrect response. Furthermore, in the synchronous control of multiple terminal devices, if each terminal device independently recognizes a command and executes the corresponding operation, even if each terminal device successfully recognizes the command, the recognition time may vary due to factors such as the distance from the sound source and the degree of noise interference experienced by each terminal device. In this case, each terminal device may execute the action sequentially, resulting in poor synchronization. In this embodiment, the recognition result of the terminal device with the shortest recognition time is taken and sent to the relevant controlled terminal devices, allowing the relevant controlled terminal devices to execute the action synchronously, improving synchronization.

[0045] In some embodiments, the method of determining a controlled terminal device from a plurality of the terminal devices based on the identification result of the target terminal device, and sending the identification result of the target identification terminal device to the controlled terminal device, specifically includes: obtaining the identification result of the target identification terminal device, re-identifying the identification result of the target identification terminal device to obtain a final target identification result, determining a controlled terminal device from a plurality of the terminal devices based on the final target identification result, and sending the final target identification result to the controlled terminal device.

[0046] The recognition result obtained by the target recognition terminal device when recognizing the voice signal is obtained locally on the target recognition terminal device. The target recognition terminal device may be affected by factors such as external noise during local recognition. Therefore, in this embodiment, after obtaining the recognition result of the target recognition terminal device, it is re-recognized to improve the accuracy of the recognition result.

[0047] In some embodiments, the voice control method further includes obtaining recognition result confidence scores of the plurality of the terminal devices, and determining a target recognition terminal device from the plurality of the terminal devices based on the voice recognition time and recognition result confidence scores of the plurality of the terminal devices.

[0048] In actual scenarios, sometimes there may be incorrect recognition results for some words with the same or similar pronunciations. For example, when a user sends out "Arrow Wizard", it may be recognized as "Keyboard Wizard". Although the probability of this is low, it cannot be completely avoided. In this case, even if the corresponding terminal device takes the shortest time to obtain the recognition result, if it is adopted as the target recognition terminal device, it will cause the controlled device to respond inaccurately or not respond. Therefore, this embodiment further combines the confidence level to determine the target recognition terminal device to further improve the efficiency and accuracy of speech recognition.

[0049] In one of the embodiments, determining the target recognition terminal device from the multiple terminal devices based on the speech recognition time and the recognition result confidence scores of the multiple terminal devices specifically includes: determining the target terminal device based on the ratio of the confidence score to the speech recognition time, and determining the terminal device with the largest ratio of the confidence score to the speech recognition time as the target recognition terminal device.

[0050] In some embodiments, the voice control method further includes obtaining noise coefficients of the plurality of terminal devices, and determining a target recognition terminal device from the plurality of terminal devices based on the noise coefficients, voice recognition time, and recognition result confidence scores of the plurality of terminal devices, wherein the noise coefficient is the ratio of the current operating sound pressure value of the terminal device to the maximum processing sound pressure value.

[0051] Speech recognition itself is the semantic restoration of audio. In addition to the voice of the user, the audio also includes the ambient noise in the environment where the terminal device is located and the operating noise of the terminal device itself. These noises will be picked up together with the voice of the user. When these noises are too loud, some of the effective information of the audio will enter a saturated state, which may cause inaccurate recognition results. Therefore, in this embodiment, the target terminal device is determined in combination with the noise coefficient of the terminal device to avoid the risk of inaccurate recognition results caused by excessive noise in the terminal device, thereby further improving the accuracy of the speech recognition results.

[0052] In some embodiments, the target recognition terminal device is determined from the multiple terminal devices based on the noise coefficients, speech recognition time and recognition result confidence scores of the multiple terminal devices, specifically including calculating the recognition result accuracy value Score=K*CL / (T*N) of the multiple terminal devices, and determining the terminal device with the largest recognition result accuracy value as the target recognition terminal device, wherein K is the weight factor of the corresponding terminal device, K=1 / (operating sound pressure value of the corresponding terminal device / total operating sound pressure values of multiple terminal devices), CL is the recognition result confidence score of the corresponding terminal device, T is the speech recognition time of the corresponding terminal device, in milliseconds, and N is the noise coefficient of the corresponding terminal device.

[0053] In order to facilitate understanding of this embodiment, this embodiment is combined with Figure 2 The schematic diagram of the application scenario of the voice control method of this embodiment is further explained in FIG. There are three terminal devices in the same space: terminal device A, terminal device B, and terminal device C. At this time, the weight factor K of terminal device A is A =1 / (operating sound pressure value of terminal device A / total operating sound pressure value of terminal device A, terminal device B, and terminal device C), weight factor K of terminal device B B =1 / (operating sound pressure value of terminal device B / total operating sound pressure value of terminal devices A, B, and C), weight factor K of terminal device C c =1 / (operating sound pressure value of terminal device C / total operating sound pressure value of terminal devices A, B and C).

[0054] In some embodiments, obtaining the speech recognition time of the plurality of terminal devices includes:

[0055] Invoking the plurality of terminal devices to respectively recognize the voice signal to obtain the voice recognition times of the plurality of terminal devices;

[0056] If the noise coefficient of the terminal device is greater than a preset threshold, noise reduction processing is performed on the terminal device before calling the terminal device to recognize the voice signal.

[0057] like Figure 2 As shown, terminal device B is a shower head. If its noise coefficient is greater than a preset threshold, the shower head's water flow rate is reduced before the shower head is called to recognize voice signals. Terminal device A is a bathroom heater. If its noise coefficient is greater than a preset threshold, the heater's wind speed is reduced before the heater is called to recognize voice signals. Terminal device C is a bathroom mirror cabinet with audio playback function. If its noise coefficient is greater than a preset threshold, the audio playback volume is lowered before the heater is called to recognize voice signals.

[0058] An embodiment of the present application provides a server, which includes a processor and a memory, wherein the memory stores at least one program code, and the processor loads the at least one program code and executes the voice control method described in any of the above embodiments.

[0059] The server can be an independent physical server or a server cluster consisting of multiple physical servers.

[0060] A cluster or distributed system can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0061] Please refer to Figure 3 , Figure 3 The block diagram of the structure of part of the server 110 of one embodiment of the present application is shown. The server 110 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPUs) 2922 (for example, one or more processors) and memory 2932, and one or more storage media 2930 (for example, one or more mass storage devices) storing application programs 2942 or data 2944. Among them, the memory 2932 and the storage medium 2930 can be temporary storage or permanent storage. The program stored in the storage medium 2930 may include one or more modules (not shown in the figure), each module may include a series of instruction operations in the server 2900. Furthermore, the central processing unit 2922 can be configured to communicate with the storage medium 2930 to execute a series of instruction operations in the storage medium 2930 on the server 2900. The server 2900 may also include one or more power supplies 2926, one or more wired or wireless network interfaces 2950, one or more input / output interfaces 2958, and / or one or more operating systems 2941, such as Windows Server™, Mac OSX™, Unix™, Linux™, FreeBSD™, etc. The central processing unit 2922 in the server 2900 may be used to execute the voice control method of the embodiments of the present application.

[0062] An embodiment of the present application provides a smart home system, comprising a plurality of terminal devices and the server described in the above embodiment, wherein the plurality of terminal devices are communicatively connected to the server.

[0063] The terminal and the server may be connected directly or indirectly via wired or wireless communication, which is not limited in this application.

[0064] like Figure 4 As shown, Figure 4A framework diagram of a smart home system according to an embodiment of the present application is shown, including terminal device A, terminal device B, terminal device C and a server. Terminal device A, terminal device B and terminal device C have a voice recognition module to collect and recognize voice signals. The other three terminal devices also have a wireless module to communicate with the server to send information to the server or receive information sent by the server.

[0065] One embodiment of the present application provides a computer-readable storage medium, wherein the storage medium stores at least one program code, and the at least one program code is used to be executed by a processor to implement the voice control method as described in any of the above embodiments.

[0066] In this embodiment, the computer-readable storage medium may include: ROM, RAM, solid state drives (SSDs), or optical disks, etc. Among them, RAM may include resistance random access memory (ReRAM) and dynamic random access memory (DRAM).

[0067] One embodiment of the present application provides a computer program product, which includes computer instructions, which are stored in a computer-readable storage medium. A processor of a computer terminal device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer terminal device performs the voice control method described in any of the above embodiments.

[0068] Those skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or by a program to instruct the relevant hardware, and the program may be stored in a computer-readable storage medium, which may be a read-only memory, a disk, or an optical disk, etc.

[0069] The above description is merely an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A voice control method, characterized in that: include: Obtaining speech recognition time for multiple terminal devices, where the recognition time refers to the time taken by the terminal device from collecting the speech signal to obtaining the recognition result; According to the speech recognition time of the plurality of terminal devices, a target recognition terminal device is determined from the plurality of terminal devices, According to the identification result of the target identification terminal device, a controlled terminal device is determined from the plurality of terminal devices, and the identification result of the target identification terminal device is sent to the controlled terminal device.

2. A voice control method according to claim 1, characterized in that: Determining the target recognition terminal device from the plurality of terminal devices based on the speech recognition times of the plurality of terminal devices includes: comparing the speech recognition times of the plurality of terminal devices and determining the terminal device with the shortest speech recognition time as the target recognition terminal device.

3. A voice control method according to claim 1, characterized in that: The method of determining a controlled terminal device from a plurality of terminal devices based on an identification result of a target identification terminal device and sending the identification result of the target identification terminal device to the controlled terminal device includes: obtaining an identification result of the target identification terminal device, re-identifying the identification result of the target identification terminal device to obtain a final target identification result, determining a controlled terminal device from a plurality of terminal devices based on the final target identification result, and sending the final target identification result to the controlled terminal device.

4. A voice control method according to claim 1, characterized in that: The voice control method further includes obtaining recognition result confidence scores of the plurality of terminal devices, and determining a target recognition terminal device from the plurality of terminal devices based on the voice recognition times and recognition result confidence scores of the plurality of terminal devices.

5. A voice control method according to claim 4, characterized in that: The voice control method also includes obtaining noise coefficients of the multiple terminal devices, and determining a target recognition terminal device from the multiple terminal devices based on the noise coefficients, voice recognition time and recognition result confidence scores of the multiple terminal devices, wherein the noise coefficient is the ratio of the current operating sound pressure value of the terminal device to the maximum processed sound pressure value.

6. A voice control method according to claim 5, characterized in that: The method of determining a target recognition terminal device from a plurality of terminal devices based on the noise coefficients, speech recognition time and recognition result confidence scores of the plurality of terminal devices specifically includes calculating the recognition result accuracy values Score=K*CL / (T*N) of the plurality of terminal devices, and determining the terminal device with the largest recognition result accuracy value as the target recognition terminal device, wherein K is a weight factor of the corresponding terminal device, K=1 / (operating sound pressure value of the corresponding terminal device / total operating sound pressure values of the plurality of terminal devices), CL is the recognition result confidence score of the corresponding terminal device, T is the speech recognition time of the corresponding terminal device, in milliseconds, and N is the noise coefficient of the corresponding terminal device.

7. A voice control method according to claim 1, characterized in that: Obtaining the speech recognition times of the plurality of terminal devices includes: Calling multiple terminal devices to recognize voice signals respectively to obtain voice recognition time of multiple terminal devices; if the noise coefficient of the terminal device is greater than a preset threshold, performing noise reduction processing on the terminal device before calling the terminal device to recognize the voice signal.

8. A server, characterized in that: The method comprises a processor and a memory, wherein the memory stores at least one program code, and the processor loads and executes the voice control method according to any one of claims 1 to 7.

9. A smart home system, comprising a plurality of terminal devices and the server according to claim 8, wherein the plurality of terminal devices are communicatively connected to the server.

10. A computer-readable storage medium, characterized in that The storage medium stores at least one program code, and the at least one program code is used to be executed by a processor to implement the voice control method according to any one of claims 1 to 7.

Images