Equipment voice control method, device and system and electrical equipment

Abstract

The invention discloses an equipment voice control method, device and system and electrical equipment, and belongs to the field of voice equipment control. And when the electrical equipment receives the wake-up word, acquiring first wake-up information, then determining an arbitration strategy based on the connection condition with the control center, and determining whether to respond to wake-up based on the arbitration strategy and the first wake-up information. During offline arbitration, the electrical equipment determines whether to respond to awakening based on the voiceprint features, the awakening time, the sound source direction and the sound intensity, and during online arbitration, the control center determines the electrical equipment responding to awakening based on the connection time, the voiceprint features, the sound source direction and the sound intensity. According to the scheme of the invention, both offline arbitration and online arbitration can be realized, and quick judgment of the electrical equipment is not affected no matter whether the network is poor or not. In addition, during offline arbitration, control of a central device or a server is not needed, wake-up delay does not need to be introduced, the response speed is high, and response is accurate. And the use experience of the user is greatly improved.

Description

Technical Field

[0001] This application relates to the field of voice device control technology, and in particular, to a device voice control method, apparatus, system and electrical equipment. Background Technology

[0002] Smart voice devices offer convenient voice control capabilities. Through voice recognition technology, users can directly control home appliances with spoken commands without having to search for a remote control or operate them manually. This makes them especially suitable for the elderly, people with disabilities, and other special groups.

[0003] With the widespread deployment of smart voice devices in homes, offices, and other environments, it has become commonplace for users to use multiple voice terminals in the same space. In scenarios where multiple devices coexist, accurately and efficiently determining which device should respond to the user's voice commands is key to improving the voice interaction experience.

[0004] Existing proximity-based wake-up technologies typically rely on sound source localization and sound intensity, using inter-device communication and negotiation to determine the responding device. This approach generally requires devices to exchange wake-up information, sound source location, etc., after the user issues a wake-up word, before making a unified decision. This "negotiate first, respond later" strategy often requires central device or server control, increasing system complexity and introducing wake-up latency, affecting response speed. The problems of response conflicts or erroneous responses are particularly severe when there are many devices or poor network conditions. Summary of the Invention

[0005] To overcome the shortcomings of the prior art, this application provides a device voice control method, apparatus, system and electrical equipment to solve the problem that when the existing proximity wake-up technology adopts the strategy of "negotiation first, response later", it often requires central equipment or server control, which increases system complexity and introduces wake-up delay, affecting response speed. In particular, when there are many devices or the network is poor, the problem of response conflict or erroneous response is more serious.

[0006] The technical solution adopted by this application to solve its technical problem is: Firstly, a voice control method for an electrical device is provided, the control method comprising: Upon receiving a wake word, obtain the first wake-up information; Obtain the connection status with the control center, which is used to control multiple electrical devices on the same network; The arbitration strategy is determined based on the connection status, and the arbitration strategy includes offline arbitration and online arbitration; Whether to respond to the wake-up call is determined based on the first wake-up information and the arbitration strategy.

[0007] As an optional implementation of this application, the step of determining whether to respond to the wake-up based on the first wake-up information and the arbitration strategy includes: When the arbitration strategy is offline arbitration, the second wake-up information broadcast by other electrical devices located in the same network within a preset time window is obtained; Whether to respond to the wake-up call is determined based on the first wake-up information and the second wake-up information.

[0008] As an optional implementation of this application, the step of determining whether to respond to a wake-up call based on the first wake-up information and the second wake-up information includes: Determine whether the second voiceprint feature information in the second wake-up information is the same as the first voiceprint feature information in the first wake-up information; If they are the same, then compare the first wake-up time in the first wake-up information and the second wake-up time in the second wake-up information; If the second wake-up time is later than the first wake-up time, then it is determined not to respond to the wake-up, or it is determined to respond to the wake-up.

[0009] As an optional implementation of this application, it also includes: If any of the second wake-up times is earlier than the first wake-up time, then it is determined that no wake-up response will be given.

[0010] As an optional implementation of this application, it also includes: If there exists a second wake-up time that is the same as the first wake-up time, and there is no second wake-up time earlier than the first wake-up time, then whether to respond to the wake-up is determined based on the sound source direction and / or sound intensity in the first wake-up information and the second wake-up information.

[0011] As an optional implementation of this application, the step of determining whether to respond to the wake-up based on the first wake-up information and the arbitration strategy includes: When the arbitration strategy is online arbitration, the first wake-up information is sent to the control center so that the control center can determine whether to respond to the wake-up based on the first wake-up information.

[0012] As an optional implementation of this application, determining the arbitration strategy based on the connection status includes: Upon receiving the wake word, a request to establish a connection is sent to the control center; If the control center responds to the connection establishment request, the arbitration strategy is determined to be online arbitration; if the control center does not respond to the connection establishment request, the arbitration strategy is determined to be offline arbitration.

[0013] Secondly, a device voice control method is provided, applied in a control center, the control method comprising: Responding to a request from an electrical device to establish a connection, recording the connection time established with the electrical device, and receiving wake-up information from the electrical device; Candidate electrical devices are determined based on the voiceprint features in the wake-up information. The candidate electrical devices are those that receive the target wake-up word sent by the same user at the same time. The target electrical device is determined from the candidate electrical devices based on the connection time. Send a control command in response to the user's wake-up call to the target electrical device.

[0014] As an optional implementation of this application, determining the target electrical device among the candidate electrical devices based on the connection time includes: If there is only one candidate electrical device with the earliest connection time, then the candidate electrical device with the earliest connection time is determined as the target electrical device.

[0015] As an optional implementation of this application, determining the target electrical device among the candidate electrical devices based on the connection time includes: If there are only two candidate electrical devices with the earliest connection time, the target electrical device is determined based on the sound source direction and / or sound intensity in the wake-up information of the candidate electrical device with the earliest connection time.

[0016] Thirdly, a voice control device for electrical equipment is provided, the control device comprising: The wake-up information acquisition module is used to acquire the first wake-up information when a wake-up word is received; The connection status acquisition module is used to acquire the connection status with the control center, which is used to control multiple electrical devices in the same network; An arbitration strategy determination module is used to determine an arbitration strategy based on the connection status, wherein the arbitration strategy includes offline arbitration and online arbitration; The wake-up response determination module is used to determine whether to respond to the wake-up based on the first wake-up information and the arbitration strategy.

[0017] Fourthly, a device voice control apparatus is provided for use in a control center, the control apparatus comprising: A connection request and response module is used to respond to the request of the electrical device to establish a connection, record the connection time of establishing a connection with the electrical device, and receive the wake-up information of the electrical device; The candidate electrical device determination module is used to determine candidate electrical devices based on the voiceprint features in the wake-up information, wherein the candidate electrical devices are electrical devices that receive the target wake-up word sent by the same user at the same time. A target electrical device determination module is used to determine a target electrical device from the candidate electrical devices based on the connection time. The wake-up control command sending module is used to send control commands in response to user wake-up to the target electrical device.

[0018] Fifthly, a device voice control system is provided, comprising: At least one processor and at least one memory; The memory stores the executable instructions of the processor; The processor is configured to perform the device voice control method described in any of the preceding descriptions.

[0019] Sixthly, an electrical device is provided that applies the device voice control method described in any of the preceding claims.

[0020] Beneficial effects: This application provides a device voice control method, apparatus, system, and electrical equipment. When the electrical equipment receives a wake-up word, it acquires first wake-up information, then determines an arbitration strategy based on the connection status with the control center, and determines whether to respond to the wake-up based on the arbitration strategy and the first wake-up information. In offline arbitration, the electrical equipment determines whether to respond to the wake-up based on voiceprint characteristics, wake-up time, sound source direction, and sound intensity. In online arbitration, the control center determines the electrical equipment that should respond to the wake-up based on connection time, voiceprint characteristics, sound source direction, and sound intensity. This application's solution can perform both offline and online arbitration, and does not affect the electrical equipment's rapid judgment regardless of network conditions. Furthermore, offline arbitration does not require central equipment or server control, eliminates wake-up delay, and results in fast and accurate response, greatly improving the user experience. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a device voice control method for electrical equipment provided in an embodiment of this application; Figure 2 This is a flowchart of a device voice control method applied in a control center, provided by an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a device voice control device applied to electrical equipment, provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a voice control device for a control center provided in an embodiment of this application; Figure 5 This is a schematic diagram of a device voice control system provided in an embodiment of this application; Figure 6 This is a block diagram of a specific device voice control system provided in an embodiment of this application; Figure 7 This is a flowchart of an offline arbitration process provided in an embodiment of this application; Figure 8 This is a flowchart of an online arbitration process provided in an embodiment of this application. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be described in detail below with reference to the accompanying drawings and embodiments. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments of this application, all other implementation methods obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] Reference Figure 1 This application provides a device voice control method for electrical equipment, the control method comprising: S11: Upon receiving a wake-up word, obtain the first wake-up information; It is understandable that electrical devices receive sound through a microphone. If a user is detected to utter a wake-up word, the device obtains the first wake-up information, which includes voiceprint feature information, wake-up time information, sound intensity, and sound source direction.

[0025] The direction of the sound source is defined by using the front of the device as a baseline, and the angle between the line connecting the sound source and the device and the baseline is used as the direction. All other things being equal, the default setting is to minimize the angle and / or maximize the sound intensity of the device the user wants to control.

[0026] In addition, the first wake-up message needs to be sent to the network.

[0027] S12: Obtain the connection status with the control center, which is used to control multiple electrical devices in the same network; The control center, or central device, can be located in the cloud or on a server.

[0028] S13: Determine an arbitration strategy based on the connection status, the arbitration strategy including offline arbitration and online arbitration; The determination of the arbitration strategy based on the connection status includes: Upon receiving the wake word, a request to establish a connection is sent to the control center; If the control center responds to the connection establishment request, the arbitration strategy is determined to be online arbitration; if the control center does not respond to the connection establishment request, the arbitration strategy is determined to be offline arbitration.

[0029] S14: Determine whether to respond to the wake-up based on the first wake-up information and the arbitration strategy.

[0030] In one embodiment, determining whether to respond to a wake-up call based on the first wake-up information and the arbitration strategy includes: When the arbitration strategy is offline arbitration, the second wake-up information broadcast by other electrical devices in the same network within a preset time window is obtained; the purpose of setting the time window is to avoid confusion when the same user mentions the same wake-up word in different locations and at different times, and also to determine whether to respond as soon as possible and improve wake-up efficiency.

[0031] Whether to respond to the wake-up call is determined based on the first wake-up information and the second wake-up information.

[0032] As a preferred implementation of this application, the step of determining whether to respond to a wake-up call based on the first wake-up information and the second wake-up information includes: Determine whether the second voiceprint feature information in the second wake-up information is the same as the first voiceprint feature information in the first wake-up information; If they are the same, then compare the first wake-up time in the first wake-up information and the second wake-up time in the second wake-up information; If the second wake-up time is later than the first wake-up time, then it is determined not to respond to the wake-up, or it is determined to respond to the wake-up.

[0033] If the second voiceprint feature information in the second wake-up information is different from the first voiceprint feature information in the first wake-up information, then the judgment will not be continued and the corresponding second wake-up information will be deleted.

[0034] The initial voiceprint feature analysis is used to confirm whether it belongs to the same user. Only when it's the same user is it necessary to determine which device will be the final control device. If it's a different user, a different detection method is used.

[0035] In addition, it also includes: If any of the second wake-up times is earlier than the first wake-up time, then it is determined that no wake-up response will be given.

[0036] If there exists a second wake-up time that is the same as the first wake-up time, and there is no second wake-up time earlier than the first wake-up time, then whether to respond to the wake-up is determined based on the sound source direction and / or sound intensity in the first wake-up information and the second wake-up information.

[0037] It should be noted that, in this embodiment of the application, when comparing the second wake-up time with the first wake-up time, if the difference between the first wake-up time and the second wake-up time is less than or equal to a threshold, they are determined to be the same. If the difference between the first wake-up time and the second wake-up time is greater than the threshold, and the first wake-up time is earlier, the first wake-up time is determined to be earlier than the second wake-up time; if the difference between the first wake-up time and the second wake-up time is greater than the threshold, and the first wake-up time is later, the second wake-up time is determined to be earlier than the first wake-up time.

[0038] Specifically, the decision to respond to a wake-up call is based on the sound source direction and / or sound intensity in the first and second wake-up information. If the sound source direction is most positive and / or the sound intensity is greatest in the first wake-up information, then a wake-up call is initiated. Otherwise, no wake-up call is initiated.

[0039] The step of determining whether to respond to a wake-up call based on the first wake-up information and the arbitration strategy includes: When the arbitration strategy is online arbitration, the first wake-up information is sent to the control center so that the control center can determine whether to respond to the wake-up based on the first wake-up information.

[0040] Among them, the control center adopts such as Figure 2 The method shown determines whether to respond to a wake-up call. It includes: S21: Respond to the request from the electrical device to establish a connection, record the connection time of establishing a connection with the electrical device, and receive the wake-up information from the electrical device; The wake-up information includes the same content as the first wake-up information mentioned above, and will not be repeated here.

[0041] S22: Based on the voiceprint features in the wake-up information, determine the candidate electrical devices, which are electrical devices that receive the target wake-up word sent by the same user at the same time; Understandably, if there is only one candidate electrical device, then that candidate electrical device is directly identified as one.

[0042] S23: Determine the target electrical device from the candidate electrical devices based on the connection time.

[0043] The step of determining the target electrical device from the candidate electrical devices based on the connection time includes: If there is only one candidate electrical device with the earliest connection time, then the candidate electrical device with the earliest connection time is determined as the target electrical device.

[0044] The earlier the connection time, the earlier the wake word was received. Therefore, the candidate electrical device with the earliest connection time is selected as the target electrical device.

[0045] It should be noted that the connection time is determined based on the difference. If the difference is within a preset value, the connection time is considered to be the same.

[0046] If there are only two candidate electrical devices with the earliest connection time, the target electrical device is determined based on the sound source direction and / or sound intensity in the wake-up information of the candidate electrical device with the earliest connection time.

[0047] S24: Send a control command in response to user wake-up to the target electrical device.

[0048] It should be noted that any process or method description in the flowchart or otherwise described herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order according to the functions involved, as should be understood by those skilled in the art to which the embodiments of this application pertain.

[0049] Furthermore, in the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0050] The device voice control method provided in this application, when an electrical device receives a wake-up word, acquires first wake-up information, then determines an arbitration strategy based on the connection status with the control center, and determines whether to respond to the wake-up based on the arbitration strategy and the first wake-up information. In offline arbitration, the electrical device determines whether to respond to the wake-up based on voiceprint characteristics, wake-up time, sound source direction, and sound intensity. In online arbitration, the control center determines the electrical device that should respond to the wake-up based on connection time, voiceprint characteristics, sound source direction, and sound intensity. This application's solution can perform both offline and online arbitration, and does not affect the electrical device's rapid judgment regardless of network conditions. Furthermore, offline arbitration does not require central device or server control, does not introduce wake-up delay, and offers fast and accurate response, greatly improving the user experience.

[0051] Based on the same inventive concept, this application provides a device voice control device 30 for use in electrical equipment. The device voice control device 30 includes: The wake-up information acquisition module 31 is used to acquire first wake-up information when a wake-up word is received; It is understandable that electrical devices receive sound through a microphone. If a user is detected to utter a wake-up word, the device obtains the first wake-up information, which includes voiceprint feature information, wake-up time information, sound intensity, and sound source direction.

[0052] The direction of the sound source is defined by using the front of the device as a baseline, and the angle between the line connecting the sound source and the device and the baseline is used as the direction. All other things being equal, the default setting is to minimize the angle and / or maximize the sound intensity of the device the user wants to control.

[0053] In addition, the first wake-up message needs to be sent to the network.

[0054] The connection status acquisition module 32 is used to acquire the connection status with the control center, which is used to control multiple electrical devices in the same network; The control center, or central device, can be located in the cloud or on a server.

[0055] Arbitration strategy determination module 33 is used to determine an arbitration strategy based on the connection status, wherein the arbitration strategy includes offline arbitration and online arbitration; The determination of the arbitration strategy based on the connection status includes: Upon receiving the wake word, a request to establish a connection is sent to the control center; If the control center responds to the connection establishment request, the arbitration strategy is determined to be online arbitration; if the control center does not respond to the connection establishment request, the arbitration strategy is determined to be offline arbitration.

[0056] The wake-up response determination module 34 is used to determine whether to respond to the wake-up based on the first wake-up information and the arbitration strategy.

[0057] In one embodiment, determining whether to respond to a wake-up call based on the first wake-up information and the arbitration strategy includes: When the arbitration strategy is offline arbitration, the second wake-up information broadcast by other electrical devices in the same network within a preset time window is obtained; the purpose of setting the time window is to avoid confusion when the same user mentions the same wake-up word in different locations and at different times, and also to determine whether to respond as soon as possible and improve wake-up efficiency.

[0058] Whether to respond to the wake-up call is determined based on the first wake-up information and the second wake-up information.

[0059] As a preferred implementation of this application, the step of determining whether to respond to a wake-up call based on the first wake-up information and the second wake-up information includes: Determine whether the second voiceprint feature information in the second wake-up information is the same as the first voiceprint feature information in the first wake-up information; If they are the same, then compare the first wake-up time in the first wake-up information and the second wake-up time in the second wake-up information; If the second wake-up time is later than the first wake-up time, then it is determined not to respond to the wake-up, or it is determined to respond to the wake-up.

[0060] If the second voiceprint feature information in the second wake-up information is different from the first voiceprint feature information in the first wake-up information, then the judgment will not be continued and the corresponding second wake-up information will be deleted.

[0061] The initial voiceprint feature analysis is used to confirm whether it belongs to the same user. Only when it's the same user is it necessary to determine which device will be the final control device. If it's a different user, a different detection method is used.

[0062] In addition, it also includes: If any of the second wake-up times is earlier than the first wake-up time, then it is determined that no wake-up response will be given.

[0063] If there exists a second wake-up time that is the same as the first wake-up time, and there is no second wake-up time earlier than the first wake-up time, then whether to respond to the wake-up is determined based on the sound source direction and / or sound intensity in the first wake-up information and the second wake-up information.

[0064] It should be noted that, in this embodiment of the application, when comparing the second wake-up time with the first wake-up time, if the difference between the first wake-up time and the second wake-up time is less than or equal to a threshold, they are determined to be the same. If the difference between the first wake-up time and the second wake-up time is greater than the threshold, and the first wake-up time is earlier, the first wake-up time is determined to be earlier than the second wake-up time; if the difference between the first wake-up time and the second wake-up time is greater than the threshold, and the first wake-up time is later, the second wake-up time is determined to be earlier than the first wake-up time.

[0065] Specifically, the decision to respond to a wake-up call is based on the sound source direction and / or sound intensity in the first and second wake-up information. If the sound source direction is most positive and / or the sound intensity is greatest in the first wake-up information, then a wake-up call is initiated. Otherwise, no wake-up call is initiated.

[0066] The step of determining whether to respond to a wake-up call based on the first wake-up information and the arbitration strategy includes: When the arbitration strategy is online arbitration, the first wake-up information is sent to the control center so that the control center can determine whether to respond to the wake-up based on the first wake-up information.

[0067] The device voice control apparatus provided in this application, when an electrical device receives a wake-up word, acquires first wake-up information, then determines an arbitration strategy based on the connection status with the control center, and determines whether to respond to the wake-up based on the arbitration strategy and the first wake-up information. In offline arbitration, the electrical device determines whether to respond to the wake-up based on voiceprint characteristics, wake-up time, sound source direction, and sound intensity. In online arbitration, the control center determines the electrical device that should respond to the wake-up based on the connection time, voiceprint characteristics, sound source direction, and sound intensity. This application's solution can perform both offline and online arbitration, and does not affect the rapid judgment of the electrical device regardless of network conditions. Furthermore, offline arbitration does not require central device or server control, does not introduce wake-up delay, and offers fast and accurate response, greatly improving the user experience.

[0068] Based on the same inventive concept, this application provides an electrical device and applies the device control method for electrical devices provided in the above embodiments.

[0069] The electrical device provided in this application, by applying the device control method for electrical devices provided in the above embodiments, can obtain first wake-up information when the electrical device receives a wake-up word, and then determine an arbitration strategy based on the connection status with the control center. Based on the arbitration strategy and the first wake-up information, it then determines whether to respond to the wake-up. In offline arbitration, the electrical device determines whether to respond to the wake-up based on voiceprint characteristics, wake-up time, sound source direction, and sound intensity. In online arbitration, the control center determines the electrical device that responds to the wake-up based on the connection time, voiceprint characteristics, sound source direction, and sound intensity. This application's solution can perform both offline and online arbitration, and does not affect the rapid judgment of the electrical device regardless of network conditions. Furthermore, offline arbitration does not require central device or server control, does not introduce wake-up delay, and has a fast and accurate response speed, greatly improving the user experience.

[0070] Based on the same inventive concept, this application provides a device voice control device 40, applied in a control center, the device voice control device 40 comprising: The connection request and response module 41 is used to respond to the request of the electrical device to establish a connection, record the connection time of establishing a connection with the electrical device, and receive the wake-up information of the electrical device. The wake-up information includes the same content as the first wake-up information mentioned above, and will not be repeated here.

[0071] The candidate electrical device determination module 42 is used to determine candidate electrical devices based on the voiceprint features in the wake-up information, wherein the candidate electrical devices are electrical devices that receive the target wake-up word sent by the same user at the same time. Understandably, if there is only one candidate electrical device, then that candidate electrical device is directly identified as one.

[0072] The target electrical device determination module 43 is used to determine the target electrical device from the candidate electrical devices based on the connection time.

[0073] The step of determining the target electrical device from the candidate electrical devices based on the connection time includes: If there is only one candidate electrical device with the earliest connection time, then the candidate electrical device with the earliest connection time is determined as the target electrical device.

[0074] The earlier the connection time, the earlier the wake word was received. Therefore, the candidate electrical device with the earliest connection time is selected as the target electrical device.

[0075] It should be noted that the connection time is determined based on the difference. If the difference is within a preset value, the connection time is considered to be the same.

[0076] If there are only two candidate electrical devices with the earliest connection time, the target electrical device is determined based on the sound source direction and / or sound intensity in the wake-up information of the candidate electrical device with the earliest connection time.

[0077] The wake-up control command sending module 44 is used to send a control command in response to the user's wake-up to the target electrical device.

[0078] The device voice control apparatus provided in this application, when an electrical device receives a wake-up word, acquires first wake-up information, then determines an arbitration strategy based on the connection status with the control center, and determines whether to respond to the wake-up based on the arbitration strategy and the first wake-up information. In offline arbitration, the electrical device determines whether to respond to the wake-up based on voiceprint characteristics, wake-up time, sound source direction, and sound intensity. In online arbitration, the control center determines the electrical device that should respond to the wake-up based on the connection time, voiceprint characteristics, sound source direction, and sound intensity. This application's solution can perform both offline and online arbitration, and does not affect the rapid judgment of the electrical device regardless of network conditions. Furthermore, offline arbitration does not require central device or server control, does not introduce wake-up delay, and offers fast and accurate response, greatly improving the user experience.

[0079] Based on the same inventive concept, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the device voice control method provided in any of the above embodiments.

[0080] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0081] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0082] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0083] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0084] The computer-readable storage medium provided in this application embodiment stores a computer program, which, when executed by a processor, implements the steps of the device voice control method provided in any of the above embodiments. Thus, when an electrical device receives a wake-up word, it acquires first wake-up information, then determines an arbitration strategy based on the connection status with the control center, and determines whether to respond to the wake-up based on the arbitration strategy and the first wake-up information. In offline arbitration, the electrical device determines whether to respond to the wake-up based on voiceprint characteristics, wake-up time, sound source direction, and sound intensity. In online arbitration, the control center determines the electrical device that responds to the wake-up based on the connection time, voiceprint characteristics, sound source direction, and sound intensity. This application's solution can perform both offline and online arbitration, and does not affect the rapid judgment of the electrical device regardless of network conditions. Furthermore, offline arbitration does not require central device or server control, does not introduce wake-up delay, and has a fast and accurate response speed, greatly improving the user experience.

[0085] Based on the same inventive concept, such as Figure 5 As shown, this application also provides a device voice control system 50, including: At least one processor 51 and at least one memory 52; The memory stores the executable instructions of the processor; The processor is configured to execute the device voice control method provided in the above embodiments.

[0086] The device voice control system provided in this application stores executable instructions of the processor in a memory. When these instructions are executed, the processor can obtain first wake-up information when the electrical device receives a wake-up word, and then determine an arbitration strategy based on the connection status with the control center. Based on the arbitration strategy and the first wake-up information, it determines whether to respond to the wake-up. In offline arbitration, the electrical device determines whether to respond to the wake-up based on voiceprint characteristics, wake-up time, sound source direction, and sound intensity. In online arbitration, the control center determines the electrical device that responds to the wake-up based on the connection time, voiceprint characteristics, sound source direction, and sound intensity. This application's solution can perform both offline and online arbitration, and does not affect the rapid judgment of the electrical device regardless of network conditions. Furthermore, offline arbitration does not require central device or server control, does not introduce wake-up delay, and offers fast and accurate response, greatly improving the user experience.

[0087] To more clearly illustrate the proposed solution, such as Figure 6 As shown in the diagram, this application provides a specific block diagram of a device voice control system. The voice control system of this application is applicable to smart terminal devices that support voice wake-up and voice recognition functions, and mainly includes the following modules: Wake-up detection module: Listens to the user's voice and detects the wake word to initiate a device response; Voiceprint extraction module: Extracts the user's voiceprint features from the current speech for subsequent determination of whether it is the same user waking up; Sound source information extraction module: Analyzes the direction (azimuth) and intensity of the speech for nearby judgment; the azimuth is based on the front of the device, and each device calculates the azimuth of the sound source relative to itself; Information broadcasting / upload module: Used to send the extracted information to other devices or servers via broadcast (offline) or upload (online); Broadcast monitoring module (offline mode only): Monitors and caches broadcast information from other devices; Arbitration judgment module: Based on parameters such as voiceprint, wake-up time, direction, and intensity from the device and monitoring information, it determines whether to continue control; Control execution module: After being identified as a responding device, it continues to perform voice recognition and control operations; Server arbitration module (online mode only): used to receive requests from multiple devices and determine the nearest responding device.

[0088] The implementation process is as follows; like Figure 7 As shown: Offline arbitration process: When a device cannot connect to the cloud, the system implements a local arbitration mechanism of "wake-up from the nearest neighbor" within the local area network via BLE broadcast. The specific control process is as follows: Local wake-up detection: Each device continuously runs a wake-up detection module, constantly listening for wake-up words from the user. Once a wake-up event is detected, the following information is immediately extracted and cached: Voice feature summary (used to compare whether it is the same user) Wake-up timestamp Sound source direction and sound intensity Broadcast wake-up message Upon detecting a wake-up, the device immediately broadcasts its wake-up status and information via BLE, and declares that it is in the "wake-up identification process".

[0089] Listen and arbitrate locally The device enters the broadcast listening window at time T (e.g., 200ms), receives wake-up broadcast messages from nearby devices, and executes local arbitration logic: If a broadcast packet with the same voiceprint (from the same user) is detected: If this device wakes up earliest, it retains the right to perform identification. If the wake-up times are similar (e.g., ≤50ms), then compare the direction and intensity: If the device is oriented in the most positive direction and has the greatest strength, then the right to identify and execute is reserved; Otherwise, it will actively exit the recognition process and resume listening. If the voiceprints are inconsistent: it will be considered as multiple users waking up in parallel, and each device will independently enter its own speech recognition process.

[0090] like Figure 8 As shown, the online arbitration process is as follows: When devices connect to the cloud, the server collects and assesses the status of each device, enabling high-precision centralized arbitration, coordinating responses from multiple devices, and avoiding redundancy. Local wake-up and information upload are also supported. After detecting a wake-up event, the device collects the following information and uploads it to the server: Voice feature summary (used to compare whether it is the same user) Wake-up time Sound source direction and sound intensity After waking up, the system recognizes audio data (for subsequent speech recognition). Note: The uploaded audio for recognition and cloud arbitration are executed in parallel. After arbitration is completed, the server will indicate the invalid device and actively terminate the connection with it, without affecting the execution process of the valid device.

[0091] Cloud-based centralized arbitration After receiving the uploaded information, the server performs the following judgment process: Voiceprint comparison: to confirm whether it is the same user; Connection timing determination: If a device was connected earliest and the voiceprint matches, continue uploading and executing control. Other devices are disconnected from the cloud, terminating the recognition process. Direction and intensity determination (when wake-up times are close): The server compares the direction and intensity of the sound source from each device and selects the device that is closest to the sound source to continue executing the task. Other devices were disconnected from the cloud, terminating the identification process.

[0092] This application proposes a device voice control system based on proximity arbitration during the recognition phase. By determining the responding device during the recognition phase rather than the wake-up phase, the multi-round communication and response delay issues of traditional methods are effectively avoided, improving response efficiency and system stability.

[0093] The core innovations of this application's embodiments include: 1. Each device makes its own judgment completely autonomously, without the need for coordination from a central device. Each device independently extracts information (including voiceprint, sound source, intensity, wake-up timestamp, etc.) after being woken up, and completes the nearest judgment through only one broadcast or upload, avoiding multiple rounds of communication and interaction.

[0094] 2. Introduce voiceprint features for device screening. During the arbitration phase, voiceprints are compared to determine whether the wake-up command was initiated by the same user. Only devices with the same voiceprint are considered for subsequent control response, accurately identifying participating devices, avoiding false responses, and eliminating the need for user grouping settings.

[0095] The above-described solution has the following advantages: 1. Fast response: No need for multiple rounds of negotiation, the device only needs to broadcast once to complete the arbitration, which greatly reduces communication overhead and latency; 2. No central coordination required: Each device independently completes its decision-making logic, making system deployment more flexible and robust; 3. Precise voiceprint screening: Only devices belonging to the same user enter the arbitration process, significantly improving recognition accuracy and preventing false responses; 4. Automatic proximity control: The system automatically identifies the control equipment, eliminating the need for manual control group setup; It is compatible with various network scenarios: offline arbitration is suitable for local area network devices, while online arbitration is suitable for cloud services, and it has good scalability.

[0096] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0097] It should be noted that in the description of this application, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this application, unless otherwise stated, "a plurality of" means at least two.

[0098] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A device voice control method, characterized in that, The control method, applied to electrical equipment, includes: Upon receiving a wake word, obtain the first wake-up information; Obtain the connection status with the control center, which is used to control multiple electrical devices on the same network; The arbitration strategy is determined based on the connection status, and the arbitration strategy includes offline arbitration and online arbitration; Whether to respond to the wake-up call is determined based on the first wake-up information and the arbitration strategy.

2. The method according to claim 1, characterized in that: The step of determining whether to respond to a wake-up call based on the first wake-up information and the arbitration strategy includes: When the arbitration strategy is offline arbitration, the second wake-up information broadcast by other electrical devices located in the same network within a preset time window is obtained; Whether to respond to the wake-up call is determined based on the first wake-up information and the second wake-up information.

3. The method according to claim 2, characterized in that: The step of determining whether to respond to a wake-up call based on the first wake-up information and the second wake-up information includes: Determine whether the second voiceprint feature information in the second wake-up information is the same as the first voiceprint feature information in the first wake-up information; If they are the same, then compare the first wake-up time in the first wake-up information and the second wake-up time in the second wake-up information; If the second wake-up time is later than the first wake-up time, then it is determined not to respond to the wake-up, or it is determined to respond to the wake-up.

4. The method according to claim 3, characterized in that, Also includes: If any of the second wake-up times is earlier than the first wake-up time, then it is determined that no wake-up response will be given.

5. The method according to claim 3, characterized in that, Also includes: If there exists a second wake-up time that is the same as the first wake-up time, and there is no second wake-up time earlier than the first wake-up time, then whether to respond to the wake-up is determined based on the sound source direction and / or sound intensity in the first wake-up information and the second wake-up information.

6. The method according to claim 1, characterized in that: The step of determining whether to respond to a wake-up call based on the first wake-up information and the arbitration strategy includes: When the arbitration strategy is online arbitration, the first wake-up information is sent to the control center so that the control center can determine whether to respond to the wake-up based on the first wake-up information.

7. The method according to claim 1, characterized in that: The determination of the arbitration strategy based on the connection status includes: Upon receiving the wake word, a request to establish a connection is sent to the control center; If the control center responds to the connection establishment request, the arbitration strategy is determined to be online arbitration; if the control center does not respond to the connection establishment request, the arbitration strategy is determined to be offline arbitration.

8. A method for voice control of a device, characterized in that, The control method, applied in a control center, includes: Responding to a request from an electrical device to establish a connection, recording the connection time established with the electrical device, and receiving wake-up information from the electrical device; Candidate electrical devices are determined based on the voiceprint features in the wake-up information. The candidate electrical devices are those that receive the target wake-up word sent by the same user at the same time. The target electrical device is determined from the candidate electrical devices based on the connection time. Send a control command in response to the user's wake-up call to the target electrical device.

9. The method according to claim 8, characterized in that: The step of determining the target electrical device from the candidate electrical devices based on the connection time includes: If there is only one candidate electrical device with the earliest connection time, then the candidate electrical device with the earliest connection time is determined as the target electrical device.

10. The method according to claim 8, characterized in that: The step of determining the target electrical device from the candidate electrical devices based on the connection time includes: If there are only two candidate electrical devices with the earliest connection time, the target electrical device is determined based on the sound source direction and / or sound intensity in the wake-up information of the candidate electrical device with the earliest connection time.

11. A voice control device for an equipment, characterized in that, The control device, applied to electrical equipment, includes: The wake-up information acquisition module is used to acquire the first wake-up information when a wake-up word is received; The connection status acquisition module is used to acquire the connection status with the control center, which is used to control multiple electrical devices in the same network; An arbitration strategy determination module is used to determine an arbitration strategy based on the connection status, wherein the arbitration strategy includes offline arbitration and online arbitration; The wake-up response determination module is used to determine whether to respond to the wake-up based on the first wake-up information and the arbitration strategy.

12. A voice control device for an equipment, characterized in that, The control device, used in a control center, includes: A connection request and response module is used to respond to the request of the electrical device to establish a connection, record the connection time of establishing a connection with the electrical device, and receive the wake-up information of the electrical device; The candidate electrical device determination module is used to determine candidate electrical devices based on the voiceprint features in the wake-up information, wherein the candidate electrical devices are electrical devices that receive the target wake-up word sent by the same user at the same time. A target electrical device determination module is used to determine a target electrical device from the candidate electrical devices based on the connection time. The wake-up control command sending module is used to send control commands in response to user wake-up to the target electrical device.

13. A voice control system for a device, characterized in that, include: At least one processor and at least one memory; The memory stores the executable instructions of the processor; The processor is configured to perform the method of any one of claims 1-7 and / or claims 8-10.

14. An electrical appliance, characterized in that, The method described in any one of claims 1-7.

Images