Equipment control method and device, equipment and storage medium

By collecting and combining voice information in the IoT device system and determining the manipulation probability in the control device, the problem of other devices being mismanaged when the user controls an IoT device is solved, and the precise execution of voice commands is achieved.

CN119763571APending Publication Date: 2025-04-04GREE ELECTRIC APPLIANCE INC OF ZHUHAI +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411916136.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-24
Publication Date
2025-04-04

AI Technical Summary

Technical Problem

When a user uses voice commands to control an IoT device, other IoT devices with the same voice commands may also be manipulated at the same time, resulting in unexpected device wake-up or operation.

Method used

By implementing the merging process of voice commands between the terminal device and the control device, voice information of the current terminal device and other terminal devices is collected, voice information is generated, and combined voice information is determined in the control device based on the operation probability.

Benefits of technology

It effectively avoids the problem that multiple IoT devices are controlled simultaneously under the same voice command, ensuring the accuracy of voice commands and the user's control intentions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119763571A_ABST
    Figure CN119763571A_ABST
Patent Text Reader

Abstract

The invention relates to an equipment control method and device, equipment and a storage medium. The method comprises the following steps: receiving combined sound information reported by at least one terminal device; according to each piece of received combined sound information, determining sound information respectively corresponding to a plurality of different terminal devices; wherein the multiple pieces of sound information correspond to the same voice instruction; when a preset control probability detection event is detected, determining a control probability corresponding to each terminal device according to the sound information corresponding to the plurality of terminal devices and the room position parameters corresponding to the plurality of terminal devices; and sending a preset execution permission instruction to the terminal equipment with the maximum control probability. According to the method, the execution permission instruction is sent to the terminal equipment with the maximum control probability, so that the terminal equipment with the maximum control probability executes the voice instruction, and the problem that the terminal equipment adopting the same voice instruction is awakened at the same time can be avoided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of Internet of Things, and in particular to a device control method, apparatus, device and storage medium. Background Art

[0002] With the rapid development of IoT technology, smart home systems are increasingly being used in life, office, public places and other application scenarios. In order to enable users to quickly control IoT devices in smart home systems, most device manufacturers will set up voice interfaces for IoT devices. Users can control IoT devices by speaking preset voice commands.

[0003] However, the voice interfaces between IoT devices are independent of each other and the voice commands used between different IoT devices may be the same. For example: IoT devices from the same manufacturer use the same wake-up word for wake-up. When a user speaks a voice command to one of the IoT devices, other IoT devices that use the voice command may also detect the voice command. This will cause the user to want to use a voice command to control an IoT device, and other IoT devices that use the same voice command will also be controlled at the same time. For example: multiple air-conditioning devices are set up in a home environment. The multiple air-conditioning devices are set up in different rooms and use the same wake-up word. When the user speaks the wake-up word in the living room, in addition to the air-conditioning in the living room being awakened, the air-conditioning closer to the living room will also be awakened at the same time. If the user does not want to wake up other air-conditioning, they still need to control other air-conditioning separately, which causes trouble for the user. Summary of the invention

[0004] The present application provides a device control method, apparatus, device and storage medium to solve the problem that when a user wants to use voice commands to control an IoT device, other IoT devices using the same voice commands can also be controlled simultaneously.

[0005] In view of the above technical problems, the technical solution of this application is solved by the following embodiments:

[0006] An embodiment of the present application provides a device control method, and the steps executed on the terminal device include: at the current terminal device, collecting sound information corresponding to the voice instructions for controlling the current terminal device; waiting to receive sound information corresponding to the voice instructions for controlling the other terminal devices sent by other terminal devices; wherein the voice instructions for controlling the current terminal device are the same as the voice instructions for controlling the other terminal devices; generating merged sound information based on the sound information collected at the current terminal device and the sound information received from the other terminal devices, and reporting the merged sound information to a preset control device; waiting to receive an execution permission instruction returned by the control device and executing the voice instruction upon receiving the execution permission instruction returned by the control device.

[0007] Among them, after the sound information corresponding to the voice instructions for controlling the current terminal device is collected, it also includes: sending a first broadcast message to a preset network environment; wherein the first broadcast message carries the sound information corresponding to the voice instructions for controlling the current terminal device; the waiting to receive the sound information corresponding to the voice instructions sent by other terminal devices for controlling the other terminal devices includes: waiting to receive a second broadcast message from the network environment; wherein the second broadcast message carries the sound information corresponding to the voice instructions for controlling the other terminal devices.

[0008] An embodiment of the present application also provides a device control method, in which the steps executed by the control device include: receiving merged sound information reported by at least one terminal device; determining the sound information corresponding to multiple different terminal devices respectively based on the received merged sound information; wherein the multiple sound information correspond to the same voice command; when it is detected that a preset control probability detection event is triggered, determining the control probability corresponding to each terminal device according to the sound information corresponding to the multiple terminal devices respectively and the room location parameters corresponding to the multiple terminal devices respectively; and sending a preset permission execution instruction to the terminal device with the highest control probability.

[0009] Among them, the sound information corresponding to multiple different terminal devices is determined based on the received each merged sound information, including: in each merged sound information, extracting the each sound information carried in the merged sound information and the terminal device information corresponding to each sound information; according to the terminal device information corresponding to each sound information, performing deduplication processing on each sound information to obtain the sound information corresponding to multiple different terminal devices.

[0010] Wherein, before the detection of the preset manipulation probability detection event being triggered, it also includes: triggering the manipulation probability detection event when it is detected that all the sound information storage locations corresponding to at least one of the merged sound information are occupied; wherein, each time a merged sound information is received, a preset number of multiple sound information storage locations are set corresponding to the merged sound information; each of the sound information extracted from the merged sound information and its corresponding terminal device information are stored in a sound information storage location; or, when a preset time length has passed since the first merged sound information was received, triggering the manipulation probability detection event.

[0011] Among them, the method of determining the control probability corresponding to each of the terminal devices according to the sound information respectively corresponding to the multiple terminal devices and the room location parameters respectively corresponding to the multiple terminal devices includes: for each of the terminal devices, obtaining the room location parameters corresponding to the terminal device, and obtaining the sound intensity and the sound angle from the sound information corresponding to the terminal device; normalizing the room location parameters, the sound intensity and the sound angle respectively; determining the initial control probability corresponding to the terminal device according to the room location parameters, the sound intensity and the sound angle after normalization; determining the control probability corresponding to the terminal device according to the initial control probability corresponding to the terminal device and the initial control probabilities corresponding to other terminal devices.

[0012] Among them, sending a preset permission execution instruction to the terminal device with the highest probability of control includes: if the combined sound information sent by the terminal device with the highest probability of control is received, directly sending the permission execution instruction to the terminal device with the highest probability of control; if the combined sound information sent by the terminal device with the highest probability of control is not received, determining the terminal device that reports the sound information of the terminal device with the highest probability of control, and forwarding the permission execution instruction to the terminal device with the highest probability of control through the terminal device.

[0013] The embodiment of the present application also provides a device control apparatus, which is arranged in a terminal device, and includes: a collection module, which is used to collect sound information corresponding to the voice instructions for controlling the current terminal device at the current terminal device; a first receiving module, which is used to wait for receiving sound information corresponding to the voice instructions for controlling the other terminal devices sent by other terminal devices; wherein the voice instructions for controlling the current terminal device are the same as the voice instructions for controlling the other terminal devices; a generation module, which is used to generate merged sound information based on the sound information collected at the current terminal device and the sound information received from the other terminal devices, and report the merged sound information to a preset control device; an execution module, which is used to wait for receiving an execution permission instruction returned by the control device And when receiving the execution permission instruction returned by the control device, execute the voice instruction; the device control device set in the control device includes: a second receiving module, used to receive the combined sound information reported by at least one terminal device; a first determination module, used to determine the sound information corresponding to multiple different terminal devices according to the received each combined sound information; wherein the multiple sound information corresponds to the same voice instruction; the second determination module is used to determine the control probability corresponding to each terminal device according to the sound information corresponding to the multiple terminal devices and the room location parameters corresponding to the multiple terminal devices when it is detected that a preset control probability detection event is triggered; a sending module is used to send a preset execution permission instruction to the terminal device with the highest control probability.

[0014] An embodiment of the present application also provides a device control device, comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; and at least one memory connected to the at least one bus, wherein the processor is configured to: execute a device control program stored in the memory to implement any of the above-mentioned device control methods executed on the terminal device, or to implement any of the above-mentioned device control methods executed on the terminal device.

[0015] An embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are executed to implement any of the above-mentioned device control methods executed on the terminal device, or to implement any of the above-mentioned device control methods executed on the terminal device.

[0016] The above technical solution provided by the embodiment of the present application has the following advantages over the prior art: the method provided by the embodiment of the present application can receive the combined sound information reported by at least one terminal device; determine the sound information corresponding to multiple different terminal devices according to each of the combined sound information received; wherein, multiple of the sound information corresponds to the same voice instruction; when a preset manipulation probability detection event is detected, determine the manipulation probability corresponding to each of the terminal devices according to the sound information corresponding to the multiple terminal devices and the room location parameters corresponding to the multiple terminal devices; send a preset permission execution instruction to the terminal device with the highest manipulation probability. In the embodiment of the present application, the sound information corresponding to multiple different terminal devices can be extracted from each of the combined sound information received, and the manipulation probability corresponding to each terminal device can be determined according to the sound information corresponding to the multiple terminal devices and the room location parameters corresponding to the multiple terminal devices. The manipulation probability is the probability of the terminal device executing the voice instruction, and then the permission execution instruction is sent to the terminal device with the highest manipulation probability, so that the terminal device with the highest manipulation probability executes the voice instruction, avoiding the problem of each terminal device using the same voice instruction being awakened at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0020] Figure 1 is a structural diagram of a device control system according to an embodiment of the present application;

[0021] Figure 2 is a schematic diagram of a device control system according to an embodiment of the present application;

[0022] Figure 3 is a flow chart of a device control method executed on a terminal device according to an embodiment of the present application;

[0023] Figure 4is a flow chart of a device control method executed on a control device according to an embodiment of the present application;

[0024] Figure 5 A flowchart of the steps of determining the sound information corresponding to different terminal devices according to an embodiment of the present application;

[0025] Figure 6 A schematic diagram of storing voice information and terminal device information according to an embodiment of the present application;

[0026] Figure 7 A flowchart of the steps of determining the manipulation probability according to an embodiment of the present application;

[0027] Figure 8 This is a structural diagram of a device control apparatus provided in a terminal device according to an embodiment of the present application;

[0028] Fig. 9 It is a structural diagram of a device control apparatus provided in a control device according to an embodiment of the present application;

[0029] Fig.10 It is a structural diagram of a device control device according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0031] The disclosure below provides many different embodiments or examples to realize the different structures of the present application. In order to simplify the disclosure of the present application, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present application. In addition, the present application can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0032] An embodiment of the present application provides a device control system. Figure 1 , which is a structural diagram of a device control system according to an embodiment of the present application.

[0033] In the device control system, a control device and a plurality of terminal devices ( Figure 1The control device and the plurality of terminal devices are in the same network environment. For example, the network environment is a home network environment.

[0034] Types of control devices include, but are not limited to: individually set control devices and designated IoT devices.

[0035] The types of terminal devices include, but are not limited to, IoT devices, such as air conditioners, refrigerators, televisions, washing machines, etc.

[0036] Furthermore, the voice commands used to control each terminal device are the same or different.

[0037] For example: Figure 2 In the schematic diagram of the device control system shown, device 1, device 2, device 3, device 4, device E and device F all use the same wake-up word for device wake-up. If the user speaks the wake-up word, device 1, device 2, device 3 and device 4 are close to the user and can detect the wake-up word spoken by the user, and then can match the preset voice wake-up instruction, that is to say: the voice wake-up instruction can be used to control device 1, device 2, device 3 and device 4, while device E and device F are far away from the user and cannot detect the wake-up word spoken by the user, that is to say: even if the user speaks the wake-up word corresponding to device E and device F, because the user is far away from device E and device F, the wake-up word spoken by the user cannot be detected by device E and device F, and the user cannot wake up device E and device F which are far away.

[0038] The control device is used to determine one of the terminal devices to execute the voice command when the same voice command is used to control multiple terminal devices.

[0039] The terminal device is used to collect the sound information corresponding to the voice instruction (voice information) when it detects that the voice information matches the preset voice instruction. For example, if a user wants to wake up the air conditioner, he can say the wake-up word "air conditioner". When he says "air conditioner", the voice instruction can be preliminarily matched, and the sound information emitted by the user can be collected.

[0040] Collect sound information corresponding to the voice instructions for controlling the terminal device at each terminal device; wait for receiving sound information corresponding to the voice instructions for controlling the other terminal devices sent by other terminal devices; wherein the voice instructions for controlling the terminal device are the same as the voice instructions for controlling the other terminal devices; generate merged sound information based on the sound information collected at the terminal device and the sound information received from the other terminal devices, and report the merged sound information to the control device; wait for receiving the permission to execute instruction returned by the control device and execute the voice instruction upon receiving the permission to execute instruction returned by the control device.

[0041] The control device is used to receive the combined sound information reported by at least one terminal device; determine the sound information corresponding to multiple different terminal devices based on the received combined sound information; wherein the multiple sound information corresponds to the same voice instruction; when it is detected that a preset control probability detection event is triggered, determine the control probability corresponding to each terminal device based on the sound information corresponding to the multiple terminal devices and the room location parameters corresponding to the multiple terminal devices; and send a preset execution permission instruction to the terminal device with the highest control probability.

[0042] In an embodiment of the present application, after a user issues a voice command, multiple terminal devices using the voice command collect sound information corresponding to the voice command and send it to a control device during the process of collecting the voice command. The control device determines which specific terminal device executes the voice command based on the sound information, and other terminal devices do not execute the voice command.

[0043] Furthermore, due to the poor network status of some terminal devices, the terminal devices may fail to complete the reporting of sound information. Therefore, each terminal device in the same network environment must not only report the sound information corresponding to the voice command, but also report the sound information of nearby terminal devices that also use the voice information, so that the control device can more comprehensively determine which specific terminal device executes the voice command.

[0044] In order to make the processing process of each node in the above-mentioned device control system clearer, the steps executed by the terminal device and the control device will be described below respectively.

[0045] According to an embodiment of the present application, a device control method executed in a terminal device is provided. Figure 3 , which is a flow chart of a device control method executed on a terminal device according to an embodiment of the present application.

[0046] Step S310: At the current terminal device, sound information corresponding to the voice command for controlling the current terminal device is collected.

[0047] The sound information includes: sound intensity and sound angle. Furthermore, the sound intensity and sound angle can be collected using a microphone built into the terminal device.

[0048] Sound intensity refers to the volume of the speaker's voice. For example, sound intensity is the number of decibels.

[0049] The sound angle refers to the angle of the speaker relative to the terminal device. The sound angle is the largest when the speaker is directly in front of the terminal device. For example, when the speaker is facing the terminal device, the sound angle is 90 degrees, and when the speaker is on the left and right sides of the terminal device, the sound angle is 0 degrees.

[0050] Specifically, voice information can be detected on the current terminal device, and when the detected voice information preliminarily matches a voice instruction, the sound information corresponding to the voice information can be collected. Alternatively, voice information and sound information corresponding to the voice information can be detected on the current terminal device, and after the voice information detection is completed, the voice instruction matching the voice information can be determined, and when it is determined that the voice information has a matching voice instruction, the collected sound information can be determined as the sound information corresponding to the voice instruction for controlling the current terminal device. Preliminary matching to a voice instruction refers to querying for a voice instruction that matches part of the currently input voice information. When the detected voice information preliminarily matches a voice instruction, the sound information corresponding to the voice information can be collected, thereby achieving the purpose of having a unique terminal device execute voice instructions without increasing the control response time, and without increasing the cost on the voice device side.

[0051] Furthermore, in order for other terminal devices to obtain the sound information collected by the current terminal, after collecting the sound information corresponding to the voice command used to control the current terminal device, a first broadcast message can be sent to a preset network environment; wherein the first broadcast message carries the sound information corresponding to the voice command used to control the current terminal device. The network environment is the network environment where the current terminal device, other terminal devices, and control devices are located. The first broadcast message can be sent to the preset network environment by wireless broadcasting. Wireless broadcasting methods include, but are not limited to, Bluetooth and WiFi.

[0052] Step S320, waiting to receive sound information corresponding to the voice instructions for controlling the other terminal devices sent by other terminal devices; wherein the voice instructions for controlling the current terminal device are the same as the voice instructions for controlling the other terminal devices.

[0053] Waiting to receive a second broadcast message from the network environment; wherein the second broadcast message carries sound information corresponding to the voice command for controlling the other terminal devices.

[0054] In the embodiment of the present application, starting from the sound information collected at the current terminal device, within a preset time length, waiting to receive the sound information corresponding to the voice command for controlling the other terminal device sent by other terminal devices. After the time length is over, stop receiving the sound information corresponding to the voice command for controlling the other terminal device sent by other terminal devices. The preset time length can be an empirical value or a value obtained through experiments.

[0055] Furthermore, due to the influence of environmental factors and the broadcast range, the current terminal device may not necessarily receive the second broadcast message sent by all other terminal devices. Therefore, the number of second broadcast messages received by each terminal device using the same voice command may be different, and further, each terminal device using the same voice command may receive the same or different sound information sent by other terminal devices.

[0056] Step S330: generating combined sound information according to the sound information collected by the current terminal device and the sound information received from the other terminal devices, and reporting the combined sound information to a preset control device.

[0057] The combined sound information is used to carry the sound information collected by the current terminal device and the sound information sent by other terminal devices.

[0058] The combined sound information includes at least: terminal device information of the current terminal device and sound information collected by the current terminal device, terminal device information of other terminal devices and sound information sent by other terminal devices.

[0059] In an embodiment of the present application, the current terminal device can adopt a point-to-point transmission method to report the generated combined sound information to the control device.

[0060] Step S340: Wait for receiving an execution permission instruction returned by the control device and execute the voice instruction when receiving the execution permission instruction returned by the control device.

[0061] The execution permission instruction is used to execute the voice instruction on the current terminal device.

[0062] In an embodiment of the present application, when the same voice command is used to control multiple terminal devices, the control device determines one of the multiple terminal devices to execute the voice command, and sends an execution permission instruction to the terminal device to execute the voice command.

[0063] In an embodiment of the present application, at the current terminal device, the sound information corresponding to the voice instruction for controlling the current terminal device is collected; the sound information corresponding to the voice instruction for controlling the other terminal device is waited for to be received from other terminal devices; wherein the voice instruction for controlling the current terminal device is the same as the voice instruction for controlling the other terminal devices; according to the sound information collected at the current terminal device and the sound information received from the other terminal devices, the merged sound information is generated and reported to the preset control device; the execution permission instruction returned by the control device is waited for and the execution permission instruction returned by the control device is received, and the current terminal device is controlled. In the embodiment of the present application, each terminal device using the same voice instruction reports the sound information collected by each terminal device to the control device respectively, so that the control device determines whether the terminal device can execute the voice information according to the sound information, and in order to avoid the problem that some terminal devices cannot report the sound information to the control device normally, the current terminal device needs to report not only the sound information collected by the current terminal device to the control device, but also the sound information collected by other terminal devices to the control device, so that the control device can more comprehensively determine one of the terminal devices that needs to execute the voice instruction, and avoid the problem that each terminal device using the same voice instruction is controlled at the same time.

[0064] Based on the above-mentioned device control method executed on the terminal device, the embodiment of the present application also provides a device control method executed on the control device. Figure 4 , which is a flow chart of a device control method executed on a control device according to an embodiment of the present application.

[0065] Step S410: receiving combined sound information reported by at least one terminal device.

[0066] The merged sound information includes at least: the terminal device information of the current terminal device (the reported terminal device) and the sound information collected by the current terminal device, the terminal device information of other terminal devices and the sound information sent by other terminal devices.

[0067] In an embodiment of the present application, since each terminal device using the same voice command is affected by the network status, its own setting location or its own settings, the control device may not be able to receive the combined sound information reported separately by all terminal devices using the same voice command.

[0068] Step S420: determining sound information corresponding to a plurality of different terminal devices respectively according to the received combined sound information; wherein the plurality of sound information correspond to the same voice command.

[0069] In each merged sound information, the terminal device information of the current terminal device (reported terminal device) carried in the merged sound information, the sound information collected at the current terminal device, the terminal device information of other terminal devices, and the sound information sent by other terminal devices are extracted to obtain the sound information corresponding to multiple different terminal devices.

[0070] Step S430, when it is detected that a preset manipulation probability detection event is triggered, the manipulation probability corresponding to each of the terminal devices is determined according to the sound information respectively corresponding to the plurality of terminal devices and the room location parameters respectively corresponding to the plurality of terminal devices.

[0071] The manipulation probability detection event refers to an event triggered when the control device needs to determine the manipulation probability corresponding to each terminal device.

[0072] The room location parameter is used to indicate the room number where the terminal device is located. The room location parameter corresponding to the terminal device can be pre-set in the control device and stored in a preset storage space, or can be pre-set and stored in the terminal device, or can be pre-set in the user terminal and sent to the cloud device for storage. In this way, for each terminal device, the room location parameter corresponding to the terminal device can be obtained in the storage space, or can be obtained from the terminal device, or can be obtained from the cloud device.

[0073] The control probability refers to the probability that the terminal device executes the voice command. The method for determining the control probability will be described later, so it will not be repeated here.

[0074] Step S440: Send a preset execution permission instruction to the terminal device with the highest manipulation probability.

[0075] The control probabilities corresponding to the various terminal devices are compared to determine the terminal device with the highest control probability, and the execution instruction is allowed to be sent to the terminal device with the highest control probability.

[0076] Furthermore, the execution permission instruction may be sent only to the terminal device with the highest probability of manipulation, or the execution permission instruction may be sent to the terminal device with the highest probability of manipulation and the execution prohibition instruction may be sent to other terminal devices. In this way, the terminal device that receives the execution permission instruction executes the voice instruction, and the terminal device that does not receive the execution permission instruction or receives the execution prohibition instruction prohibits the execution of the voice instruction.

[0077] In the embodiment of the present application, an execution permission instruction may be sent to the terminal device with the highest probability of manipulation based on the terminal device information corresponding to the terminal device with the highest probability of manipulation.

[0078] Furthermore, the execution permission instruction may be directly sent to the terminal device with the highest control probability according to the terminal device information corresponding to the terminal device with the highest control probability.

[0079] Furthermore, in order to avoid the problem that the terminal device with the highest probability of manipulation cannot communicate normally with the control device and cannot normally receive the execution permission instruction sent by the control device due to the network status, self-settings, etc. of the terminal device, it can be determined whether the combined sound information sent by the terminal device with the highest probability of manipulation has been received; if the combined sound information sent by the terminal device with the highest probability of manipulation has been received, the execution permission instruction is directly sent to the terminal device with the highest probability of manipulation; if the combined sound information sent by the terminal device with the highest probability of manipulation has not been received, the terminal device that reports the sound information of the terminal device with the highest probability of manipulation is determined, and the execution permission instruction is forwarded to the terminal device with the highest probability of manipulation through the terminal device. Among them, if the combined sound information sent by the terminal device with the highest probability of manipulation is received, it means that the control device and the terminal device with the highest probability of manipulation can communicate normally. If the combined sound information sent by the terminal device with the highest control probability is not received, but the sound information corresponding to the terminal device with the highest control probability can be obtained, it means that the control device and the terminal device with the highest control probability cannot communicate normally, but there are other terminal devices that can communicate normally with the terminal device with the highest control probability. The other terminal device is the terminal device that reports the combined sound information, and the combined sound information reported by the terminal device includes the sound information corresponding to the terminal device with the highest control probability.

[0080] In an embodiment of the present application, a combined sound information reported by at least one terminal device is received; sound information corresponding to a plurality of different terminal devices is determined based on each of the combined sound information received; wherein a plurality of the sound information corresponds to the same voice instruction; when a preset control probability detection event is detected, the control probability corresponding to each of the terminal devices is determined based on the sound information corresponding to the plurality of the terminal devices and the room location parameters corresponding to the plurality of the terminal devices; and a preset execution permission instruction is sent to the terminal device with the highest control probability. In the embodiment of the present application, sound information corresponding to a plurality of different terminal devices can be extracted from each of the combined sound information received; the control probability corresponding to each terminal device can be determined based on the sound information corresponding to the plurality of terminal devices and the room location parameters corresponding to the plurality of terminal devices; the control probability is the probability of the terminal device executing the voice instruction, and then the execution permission instruction is sent to the terminal device with the highest control probability, so that the terminal device with the highest control probability executes the voice instruction, thereby avoiding the problem of each terminal device using the same voice instruction being awakened at the same time.

[0081] In order to make the device control method executed by the control device of the present application easier to understand, the device control method executed by the control device of the present application will be further described below.

[0082] In an embodiment of the present application, the merged sound information reported by the terminal device can be received. After receiving the merged sound information reported by the terminal device, the sound information corresponding to multiple different terminal devices can be determined based on the received respective merged sound information.

[0083] like Figure 5 , which is a flowchart of the steps of determining the sound information corresponding to different terminal devices according to an embodiment of the present application.

[0084] Step S510: extracting, from each of the combined sound information, individual sound information carried in the combined sound information and terminal device information corresponding to each of the sound information.

[0085] For each merged sound information, after receiving the merged sound information, a preset number of multiple sound information storage locations are set for the merged sound information; each sound information extracted from the merged sound information and its corresponding terminal device information are stored in one of the sound information storage locations. The preset number is less than or equal to the number of terminal devices using the same voice command. The voice command is the voice command corresponding to each sound information in the merged sound information. For example: after receiving the merged sound information, the merged sound information is stored in n windows (sound information storage locations), and each window is used to store a sound information and its corresponding terminal device information.

[0086] When storing sound information and terminal device information correspondingly, the sound information and the terminal device information can be stored together in one of the sound information storage locations, or the corresponding terminal device information can be set in advance for each sound information storage location, and the sound information corresponding to the terminal device information is stored in the sound information storage location corresponding to the terminal device information.

[0087] Step S520: Deduplication processing is performed on each of the sound information according to the terminal device information corresponding to each of the sound information to obtain sound information corresponding to multiple different terminal devices.

[0088] Deduplication processing is used to retain only one sound information for each terminal device. Furthermore, after collecting sound information, the terminal device not only reports the sound information collected by itself, but also broadcasts the sound information to other terminal devices, so that the sound information collected by itself can be reported through other terminal devices. In this way, on the control device side, the sound information corresponding to the same terminal device reported from different channels is the same.

[0089] For example: Figure 6 As shown, it is a schematic diagram of the storage of sound information and terminal device information according to an embodiment of the present application. Devices using the same voice command include device 1, device 2, device 3 and device 4; after the user speaks the voice information, the control device successively receives the combined sound information reported by device 1, device 2 and device 4 respectively; the control device sets three sound information storage locations for the combined sound information reported by each terminal device; the control device extracts the sound information corresponding to device 1, the sound information corresponding to device 2 and the sound information corresponding to device 4 from the combined sound information reported by device 1, stores the device information and sound information corresponding to device 1 in the first sound information storage location, stores the device information and sound information corresponding to device 2 in the second sound information storage location and stores the device information and sound information corresponding to device 4 in the third sound information storage location. The control device extracts the sound information corresponding to device 2 and the sound information corresponding to device 3 from the combined sound information reported by device 2, stores the device information and sound information corresponding to device 2 in the first sound information storage position, and stores the device information and sound information corresponding to device 3 in the second sound information storage position; the control device extracts the sound information corresponding to device 4 and the sound information corresponding to device 1 from the combined sound information reported by device 4, stores the device information and sound information corresponding to device 4 in the first sound information storage position, and stores the device information and sound information corresponding to device 1 in the second sound information storage position. After deduplication of the sound information stored in each sound information storage position, the control device can obtain the device information and sound information corresponding to device 1, the device information and sound information corresponding to device 2, the device information and sound information corresponding to device 3, and the device information and sound information corresponding to device 4. Although the control device does not receive the combined sound information reported by device 3, the device information and sound information corresponding to device 3 can still be obtained through other terminal devices.

[0090] In an embodiment of the present application, in the process of determining the sound information corresponding to different terminal devices respectively, it is detected whether a manipulation probability detection event is triggered.

[0091] The control probability detection event refers to an event that currently requires the control probability of the terminal device corresponding to each sound information to be determined.

[0092] Specifically, before the detection of the preset manipulation probability detection event being triggered, the manipulation probability detection event is triggered when it is detected that all the sound information storage locations corresponding to at least one of the combined sound information are occupied; wherein, each time a combined sound information is received, a preset number of sound information storage locations are set for the combined sound information; each of the sound information extracted from the combined sound information and its corresponding terminal device information are stored in a sound information storage location; or, when a preset time length has passed since the first combined sound information was received, the manipulation probability detection event is triggered. The preset time length is the time length for waiting to receive sound information sent by other terminal devices. For example: the preset time length is half of the input time of the voice information corresponding to the voice instruction, such as: the time for the user to say the wake-up word "air conditioning equipment" is 1 second, then the preset time length is 0.5 seconds, so that after the control device determines the terminal device that can execute the voice instruction and sends the permission execution instruction to the terminal device, the terminal device has just collected all the voice information, and the terminal device can execute the voice instruction without delay, and the entire wake-up process can be done without the user's perception.

[0093] For example: Figure 6 In the embodiment, each combined sound information corresponds to three sound information storage locations. When it is detected that the three sound information storage locations corresponding to the combined sound information of device 1 are all filled with device information and sound information, a manipulation probability detection event is triggered.

[0094] In an embodiment of the present application, after detecting that a manipulation probability detection event is triggered, the manipulation probability corresponding to each of the terminal devices is determined based on the sound information corresponding to the multiple terminal devices and the room location parameters corresponding to the multiple terminal devices.

[0095] For each terminal device, you can refer to Figure 7 , determine the control probability corresponding to the terminal device. Among them, Figure 7 The figure is a flowchart of the steps of determining the manipulation probability according to an embodiment of the present application.

[0096] Step S710: For each of the terminal devices, obtain the room location parameters corresponding to the terminal device, and obtain the sound intensity and sound angle from the sound information corresponding to the terminal device.

[0097] In an embodiment of the present application, the room location parameters corresponding to the terminal device can be obtained from the storage space of the control device, or the room location parameters corresponding to the terminal device can be obtained from a cloud device.

[0098] Step S720, normalizing the room position parameter, the sound intensity and the sound angle respectively.

[0099] Obtain the room location parameters corresponding to each terminal device and cluster them according to the value (room number); determine the room location parameter with the largest number; if the room location parameter corresponding to the current terminal device, the normalized room location parameter of the current terminal device is 1; otherwise, it is 0. If the number of room location parameters of each terminal device is the same, for example, all are 1, then the normalized room location parameters of each terminal device are all 0.

[0100] The maximum sound intensity and the minimum sound intensity are obtained, and the sound intensity is normalized using the maximum sound intensity and the minimum sound intensity. The maximum sound intensity and the minimum sound intensity may be set values, or may be the maximum and minimum values ​​determined in the historical sound intensity. If the maximum sound intensity and the minimum sound intensity are the maximum and minimum values ​​determined in the historical sound intensity, then in the sound information corresponding to the terminal device, after obtaining the sound intensity and the sound intensity, the sound intensity of this time is recorded.

[0101] For example, the following formula can be used to normalize the sound intensity:

[0102]

[0103] in, is the normalized sound intensity, x i is the sound intensity, x min is the minimum sound intensity, x max is the maximum sound intensity, and i represents the i-th terminal device.

[0104] Get the maximum and minimum sound angles, and use them to normalize the sound angle. The maximum and minimum sound angles are both set values. For example, the maximum sound angle is set to 90 degrees, and the minimum sound angle is set to 0 degrees.

[0105] For example, the following formula can be used to normalize the sound angle:

[0106]

[0107] in, is the normalized sound angle, y i is the sound angle, y min is the minimum value of the sound angle, y max is the maximum value of the sound angle, and i represents the i-th terminal device.

[0108] Step S730, determining the initial control probability corresponding to the terminal device according to the normalized room position parameters, the sound intensity and the sound angle.

[0109] The initial control probability is the intermediate value when calculating the control probability. In the embodiment of the present application, the normalized room position parameter is positively correlated with the initial control probability, that is, the initial control probability when the normalized room position parameter is 1 is greater than the initial control probability when the normalized room position parameter is 0; the normalized sound intensity is positively correlated with the initial control probability, that is, the greater the normalized sound intensity, the greater the initial control probability, and the smaller the normalized sound intensity, the smaller the initial control probability; the normalized sound angle is positively correlated with the initial control probability, that is, the greater the normalized sound angle, the greater the initial control probability, and the smaller the normalized sound angle, the smaller the initial control probability.

[0110] For example, the initial control probability can be calculated using the following formula:

[0111]

[0112] Among them, h i is the initial control probability corresponding to the i-th terminal device; is the normalized room position parameter; is the normalized sound intensity, is the normalized sound intensity; a1, a2, b1, b2, c and d are preset parameter values ​​respectively. The values ​​of a1, a2, b1, b2, c and d can be the same or different.

[0113] Step S740, determining the control probability corresponding to the terminal device according to the initial control probability corresponding to the terminal device and the initial control probabilities corresponding to other terminal devices.

[0114] After determining the initial operation probabilities corresponding to the respective terminal devices, a softmax function may be called to enable the softmax function to calculate the manipulation probability corresponding to each terminal device using the initial operation probabilities corresponding to the respective terminal devices.

[0115] For example, the following softmax function is used to calculate the control probability corresponding to each terminal device:

[0116]

[0117] Among them, softmax(h i ) represents the control probability corresponding to the i-th terminal device; n represents the number of sound information storage locations set for merging sound information.

[0118] In the embodiment of the present application, after determining the manipulation probabilities corresponding to each terminal device, the terminal device with the highest manipulation probability is determined, and an execution permission instruction is sent to the terminal device with the highest manipulation probability.

[0119] Specifically, before sending the execution permission instruction to the terminal device with the highest manipulation probability, it is necessary to determine the transmission path of the execution permission instruction. Furthermore, the transmission path of the execution permission instruction can be determined according to the terminal device that reports the combined sound information.

[0120] If the combined sound information sent by the terminal device with the highest control probability is received, the execution permission instruction is sent to the terminal device with the highest control probability. Figure 6 If device 1 is the terminal device with the highest probability of being controlled, and the control device receives the combined sound information reported by device 1, then the control device can communicate with device 1 and send an execution permission instruction to device 1.

[0121] If the combined sound information sent by the terminal device with the highest control probability is not received, the terminal device that reports the sound information of the terminal device with the highest control probability is determined, and the execution permission instruction is forwarded to the terminal device with the highest control probability through the terminal device. Figure 6 If device 3 is the terminal device with the highest probability of control, and the control device does not receive the combined sound information reported by device 3, then the control device cannot communicate with device 3. If the terminal device that reports the sound information of device 3 is device 2, then the control device can send an allow execution instruction to device 2, and instruct device 2 to forward the allow execution instruction to device 3.

[0122] The present application also provides a device control device provided in a terminal device. Figure 8 , which is a structural diagram of a device control apparatus provided in a terminal device according to an embodiment of the present application.

[0123] The device control device provided in the terminal device includes:

[0124] The collection module 810 is used to collect, at the current terminal device, sound information corresponding to the voice command used to control the current terminal device.

[0125] The first receiving module 820 is used to wait for receiving sound information corresponding to the voice instructions for controlling the other terminal devices sent by other terminal devices; wherein the voice instructions for controlling the current terminal device are the same as the voice instructions for controlling the other terminal devices.

[0126] The generating module 830 is used to generate combined sound information according to the sound information collected by the current terminal device and the sound information received from other terminal devices, and report the combined sound information to a preset control device.

[0127] The execution module 840 is used to wait for receiving the execution permission instruction returned by the control device and execute the voice instruction when receiving the execution permission instruction returned by the control device.

[0128] The functions of the device described in the embodiment of the present application have been described in the above method embodiment. Therefore, for any details not provided in the description of this embodiment, please refer to the relevant descriptions in the above embodiment and will not be repeated here.

[0129] The present application also provides a device control device provided in a control device. Fig. 9 , which is a structural diagram of a device control apparatus provided in a control device according to an embodiment of the present application.

[0130] The device control device provided in the control device includes:

[0131] The second receiving module 910 is used to receive combined sound information reported by at least one terminal device.

[0132] The first determination module 920 is used to determine the sound information corresponding to multiple different terminal devices according to the received combined sound information; wherein the multiple sound information corresponds to the same voice instruction.

[0133] The second determination module 930 is used to determine the control probability corresponding to each of the terminal devices according to the sound information corresponding to the multiple terminal devices and the room location parameters corresponding to the multiple terminal devices when a preset control probability detection event is detected to be triggered.

[0134] The sending module 940 is used to send a preset execution permission instruction to the terminal device with the highest manipulation probability.

[0135] The functions of the device described in the embodiment of the present application have been described in the above method embodiment. Therefore, for any details not provided in the description of this embodiment, please refer to the relevant descriptions in the above embodiment and will not be repeated here.

[0136] The present application also provides a device control device, such as Fig.10 , which is a structural diagram of a device control device according to an embodiment of the present application.

[0137] The device control device includes: a processor 1010, a communication interface 1020, a memory 1030 and a communication bus 1040. The processor 1010, the communication interface 1020 and the memory 1030 communicate with each other through the communication bus 1040.

[0138] The memory 1030 is used to store computer programs.

[0139] In one embodiment of the present application, the processor 1010, when executing the program stored on the memory 1030, implements the device control method provided by any of the aforementioned method embodiments and executed on the terminal device, including: at the current terminal device, collecting sound information corresponding to the voice instructions for controlling the current terminal device; waiting to receive sound information corresponding to the voice instructions for controlling the other terminal devices sent by other terminal devices; wherein the voice instructions for controlling the current terminal device are the same as the voice instructions for controlling the other terminal devices; generating merged sound information based on the sound information collected at the current terminal device and the sound information received from the other terminal devices, and reporting the merged sound information to a preset control device; waiting to receive an execution permission instruction returned by the control device and executing the voice instruction upon receiving the execution permission instruction returned by the control device.

[0140] Among them, after the sound information corresponding to the voice instructions for controlling the current terminal device is collected, it also includes: sending a first broadcast message to a preset network environment; wherein the first broadcast message carries the sound information corresponding to the voice instructions for controlling the current terminal device; the waiting to receive the sound information corresponding to the voice instructions sent by other terminal devices for controlling the other terminal devices includes: waiting to receive a second broadcast message from the network environment; wherein the second broadcast message carries the sound information corresponding to the voice instructions for controlling the other terminal devices.

[0141] In one embodiment of the present application, the processor 1010 is used to execute the program stored in the memory 1030 to implement the device control method provided by any of the aforementioned method embodiments and executed on the control device, including: receiving merged sound information reported by at least one terminal device; determining the sound information corresponding to multiple different terminal devices according to each of the received merged sound information; wherein the multiple sound information correspond to the same voice command; when it is detected that a preset control probability detection event is triggered, determining the control probability corresponding to each of the terminal devices according to the sound information corresponding to the multiple terminal devices and the room location parameters corresponding to the multiple terminal devices; and sending a preset permission execution instruction to the terminal device with the highest control probability.

[0142] Among them, the sound information corresponding to multiple different terminal devices is determined based on the received each merged sound information, including: in each merged sound information, extracting the each sound information carried in the merged sound information and the terminal device information corresponding to each sound information; according to the terminal device information corresponding to each sound information, performing deduplication processing on each sound information to obtain the sound information corresponding to multiple different terminal devices.

[0143] Wherein, before the detection of the preset manipulation probability detection event being triggered, it also includes: triggering the manipulation probability detection event when it is detected that all the sound information storage locations corresponding to at least one of the merged sound information are occupied; wherein, each time a merged sound information is received, a preset number of multiple sound information storage locations are set corresponding to the merged sound information; each of the sound information extracted from the merged sound information and its corresponding terminal device information are stored in a sound information storage location; or, when a preset time length has passed since the first merged sound information was received, triggering the manipulation probability detection event.

[0144] Among them, the method of determining the control probability corresponding to each of the terminal devices according to the sound information respectively corresponding to the multiple terminal devices and the room location parameters respectively corresponding to the multiple terminal devices includes: for each of the terminal devices, obtaining the room location parameters corresponding to the terminal device, and obtaining the sound intensity and the sound angle from the sound information corresponding to the terminal device; normalizing the room location parameters, the sound intensity and the sound angle respectively; determining the initial control probability corresponding to the terminal device according to the room location parameters, the sound intensity and the sound angle after normalization; determining the control probability corresponding to the terminal device according to the initial control probability corresponding to the terminal device and the initial control probabilities corresponding to other terminal devices.

[0145] Among them, sending a preset permission execution instruction to the terminal device with the highest probability of control includes: if the combined sound information sent by the terminal device with the highest probability of control is received, directly sending the permission execution instruction to the terminal device with the highest probability of control; if the combined sound information sent by the terminal device with the highest probability of control is not received, determining the terminal device that reports the sound information of the terminal device with the highest probability of control, and forwarding the permission execution instruction to the terminal device with the highest probability of control through the terminal device.

[0146] The embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the device control method performed on the terminal device as provided in any of the aforementioned method embodiments, or the steps of the device control method performed on the control device. Since the device control method performed on the terminal device and the device control method performed on the control device have been described in detail above, for the details not fully described in the description of this embodiment, please refer to the relevant descriptions in the aforementioned embodiments, and no further description will be given here.

[0147] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0148] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0149] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0150] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.

Claims

1. A device control method, characterized in that: The steps performed on the terminal device include: At the current terminal device, collecting sound information corresponding to the voice command used to control the current terminal device; Waiting to receive sound information corresponding to a voice instruction for controlling the other terminal device sent by other terminal devices; wherein the voice instruction for controlling the current terminal device is the same as the voice instruction for controlling the other terminal device; Generate combined sound information according to the sound information collected by the current terminal device and the sound information sent by the other terminal devices, and report the combined sound information to a preset control device; Wait for receiving the execution permission instruction returned by the control device and execute the voice instruction when receiving the execution permission instruction returned by the control device.

2. The method according to claim 1, characterized in that After the sound information corresponding to the voice command for controlling the current terminal device is collected, the method further includes: Sending a first broadcast message to a preset network environment; wherein the first broadcast message carries sound information corresponding to a voice command for controlling a current terminal device; The waiting to receive the sound information corresponding to the voice command sent by other terminal devices and used to control the other terminal devices includes: Waiting to receive a second broadcast message from the network environment; wherein the second broadcast message carries sound information corresponding to the voice command for controlling the other terminal devices.

3. A device control method, characterized in that: The steps performed in the control device include: Receiving combined sound information reported by at least one terminal device; Determine, according to each of the received combined sound information, sound information corresponding to a plurality of different terminal devices respectively; wherein the plurality of sound information corresponds to the same voice command; When it is detected that a preset manipulation probability detection event is triggered, determining the manipulation probability corresponding to each of the terminal devices according to the sound information respectively corresponding to the plurality of terminal devices and the room location parameters respectively corresponding to the plurality of terminal devices; A preset execution permission instruction is sent to the terminal device with the highest manipulation probability.

4. The method according to claim 3, characterized in that The step of determining the sound information corresponding to the plurality of different terminal devices respectively according to the received combined sound information includes: Extracting, from each of the combined sound information, each of the sound information carried in the combined sound information and the terminal device information corresponding to each of the sound information; According to the terminal device information corresponding to each of the sound information, deduplication processing is performed on each of the sound information to obtain sound information corresponding to multiple different terminal devices.

5. The method according to claim 3, characterized in that: Before the detection of a preset manipulation probability detection event being triggered, the method further includes: When it is detected that all the sound information storage locations corresponding to at least one of the combined sound information are occupied, the manipulation probability detection event is triggered; wherein, each time a combined sound information is received, a preset number of sound information storage locations are set for the combined sound information; each of the sound information extracted from the combined sound information and its corresponding terminal device information are stored in a sound information storage location; Alternatively, when a preset time length has passed since the first combined sound information was received, the manipulation probability detection event is triggered.

6. The method according to claim 3, characterized in that The determining, according to the sound information respectively corresponding to the plurality of terminal devices and the room location parameters respectively corresponding to the plurality of terminal devices, the control probability corresponding to each of the terminal devices comprises: For each of the terminal devices, obtain room location parameters corresponding to the terminal device, and obtain sound intensity and sound angle from the sound information corresponding to the terminal device; Normalizing the room position parameter, the sound intensity and the sound angle respectively; Determining an initial control probability corresponding to the terminal device according to the normalized room position parameter, the sound intensity, and the sound angle; The control probability corresponding to the terminal device is determined according to the initial control probability corresponding to the terminal device and the initial control probabilities corresponding to other terminal devices.

7. The method according to claim 3, characterized in that The sending a preset execution permission instruction to the terminal device with the highest manipulation probability includes: If the combined sound information sent by the terminal device with the highest control probability is received, directly sending the execution permission instruction to the terminal device with the highest control probability; If the combined sound information sent by the terminal device with the highest control probability is not received, the terminal device that reports the sound information of the terminal device with the highest control probability is determined, and the execution permission instruction is forwarded to the terminal device with the highest control probability through the terminal device.

8. A device control device, characterized in that: The device control device provided in the terminal device includes: A collection module, used to collect, at the current terminal device, sound information corresponding to a voice command used to control the current terminal device; A first receiving module, configured to wait for receiving sound information corresponding to a voice instruction for controlling the other terminal device sent by other terminal devices; wherein the voice instruction for controlling the current terminal device is the same as the voice instruction for controlling the other terminal device; A generating module, configured to generate combined sound information according to the sound information collected by the current terminal device and the sound information received and sent by the other terminal devices, and report the combined sound information to a preset control device; an execution module, configured to wait for receiving an execution permission instruction returned by the control device and execute the voice instruction upon receiving the execution permission instruction returned by the control device; The device control device provided in the control device includes: A second receiving module, used to receive combined sound information reported by at least one terminal device; A first determination module is used to determine the sound information corresponding to the plurality of different terminal devices respectively according to the received respective combined sound information; wherein the plurality of sound information corresponds to the same voice instruction; A second determination module is used to determine the control probability corresponding to each of the terminal devices according to the sound information respectively corresponding to the plurality of terminal devices and the room location parameters respectively corresponding to the plurality of terminal devices when detecting that a preset control probability detection event is triggered; The sending module is used to send a preset execution permission instruction to the terminal device with the highest manipulation probability.

9. A device control device, characterized in that: include: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor coupled to the at least one bus; At least one memory connected to the at least one bus, wherein the processor is configured to: execute a device control program stored in the memory to implement the device control method executed in the terminal device according to any one of claims 1 to 2, or to implement the device control method executed in the terminal device according to any one of claims 3 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed to implement the device control method executed on the terminal device according to any one of claims 1-2, or to implement the device control method executed on the terminal device according to any one of claims 3-7.