Voice command processing method and device, storage medium and electronic device

Abstract

The present application provides a method and device for processing voice commands, a storage medium and an electronic device, and relates to the field of smart home / intelligent home technology, wherein the method comprises: obtaining multiple voice signals collected by multiple collection components on a smart device, wherein each of the multiple voice signals is a voice signal collected by one of the multiple collection components and corresponding to a voice control command issued by a target object; selecting a target voice signal from the multiple voice signals according to the signal characteristics of the multiple voice signals; and sending the energy value of the target voice signal to a server, so that the server determines whether the smart device responds to the voice control command according to the energy value of the target voice signal. Through the present application, the problem of poor accuracy of voice command execution caused by inaccurate energy value of the voice signal determined by the device in the voice command processing method in the related art is solved.

Description

Technical Field

[0001] The present application relates to the field of communications, and in particular, to a method and device for processing voice commands, a storage medium, and an electronic device. Background Art

[0002] At present, there can be multiple voice devices (i.e., smart devices with voice collection functions) in a home. After the user issues a voice command, a distributed voice control solution can be used to select the responding device for each voice device that receives the voice command. The distributed voice control solution can select the device closest to the user to respond based on the user's location, thus realizing local voice control.

[0003] Multiple voice collection components (receiving components, such as microphones) can be set in the voice device, and voice commands can be collected through the set voice collection components. After collecting multi-channel voice signals through multiple voice collection components, the energy value of one voice signal or voice signal collected by the preset fixed voice collection component can be transmitted to the cloud. The cloud makes a decision based on the energy values ​​sent by the multiple voice devices (the device with low energy will not be awakened, and the device with the highest energy will be awakened).

[0004] However, the energy value of the voice signal collected by the voice collection component will vary greatly due to the different placement of the voice device. For example, when the voice device is placed against a wall, if the voice signal collected by the voice collection component close to the wall is used to calculate the energy value of the voice device, the calculated energy value will be inaccurate due to the influence of wall reflection, resulting in inaccurate selection of the wake-up device, which in turn causes the voice command issued by the user to fail to be accurately executed.

[0005] It can be seen from this that the voice command processing method in the related art has the problem of poor accuracy in executing the voice command due to inaccurate energy value of the voice signal determined by the device. Summary of the invention

[0006] The embodiments of the present application provide a method and device for processing voice commands, a storage medium, and an electronic device, so as to at least solve the problem of poor accuracy of voice command execution caused by inaccurate energy value of the voice signal determined by the device in the voice command processing method in the related art.

[0007] According to one aspect of an embodiment of the present application, a method for processing voice commands is provided, comprising: acquiring multiple voice signals collected by multiple collection components on a smart device, wherein each of the multiple voice signals is a voice signal collected by one of the multiple collection components and corresponding to a voice control command issued by a target object; selecting a target voice signal from the multiple voice signals based on signal characteristics of the multiple voice signals; and sending an energy value of the target voice signal to a server, so that the server determines whether the smart device responds to the voice control command based on the energy value of the target voice signal.

[0008] In an exemplary embodiment, selecting a target voice signal from the multiple voice signals based on signal characteristics of the multiple voice signals includes: selecting a target acquisition component that is closest to the target object from the multiple acquisition components based on the signal characteristics of the multiple voice signals; determining a voice signal collected by the target acquisition component among the multiple voice signals as the target voice signal; or determining a voice signal with the largest energy value among the multiple voice signals as the target voice signal.

[0009] In an exemplary embodiment, selecting a target acquisition component that is closest to the target object from the multiple acquisition components based on signal characteristics of the multiple voice signals includes: determining object angle information of the target object based on signal characteristics of the multiple voice signals, wherein the object angle information is used to describe the relative angle between the target object and the smart device; selecting the target acquisition component from the multiple acquisition components based on the object angle information, wherein the target acquisition component is the acquisition component that is closest to the target object after the target object is projected onto the plane where the multiple acquisition components are located according to the relative angle.

[0010] In an exemplary embodiment, before selecting a target speech signal from the multiple speech signals based on the signal features of the multiple speech signals, the method further includes: performing an acoustic echo cancellation operation on the multiple speech signals to obtain the processed multiple speech signals; and performing signal feature extraction on each speech signal in the processed multiple speech signals to obtain the signal features of the multiple speech signals.

[0011] In an exemplary embodiment, before acquiring multiple voice signals collected by multiple collection components on the smart device, the method also includes: performing image collection on the target object through an image collection component on the smart device to obtain a target collection image; performing object recognition on the target collection image to obtain object position information of the target object, wherein the object position information is used to indicate the relative position of the target object and the smart device; and adjusting the collection angles of the multiple collection components for collecting voice signals according to the object position information.

[0012] In an exemplary embodiment, before sending the energy value of the target speech signal to the server, the method further includes: determining the average value of the amplitude values ​​of multiple sampling points in the target speech signal as the energy value of the target speech signal; or, determining the sum of the squares of the amplitude values ​​of multiple sampling points in the target speech signal as the energy value of the target speech signal.

[0013] In an exemplary embodiment, after sending the energy value of the target voice signal to the server, the method further includes: receiving the energy value of the voice signal sent by each device of a plurality of devices, wherein the plurality of devices include the smart device, and the voice signal to which the energy value of the voice signal sent by each device belongs is a voice signal corresponding to the voice control instruction issued by the target object; determining a target device from the plurality of devices based on the energy value of the voice signal sent by each device, wherein the target device is a device among the plurality of devices used to execute the voice control instruction; and controlling the target device to perform a device operation matching the voice control instruction.

[0014] According to another aspect of an embodiment of the present application, a voice command processing device is also provided, including: an acquisition unit, used to acquire multiple voice signals collected by multiple collection components on an intelligent device, wherein each of the multiple voice signals is a voice signal collected by one of the multiple collection components and corresponding to a voice control command issued by a target object; a selection unit, used to select a target voice signal from the multiple voice signals based on signal characteristics of the multiple voice signals; and a sending unit, used to send an energy value of the target voice signal to a server, so that the server determines whether the intelligent device responds to the voice control command based on the energy value of the target voice signal.

[0015] In an exemplary embodiment, the selection unit includes: a selection module, used to select a target acquisition component that is closest to the target object from the multiple acquisition components based on signal characteristics of the multiple voice signals; a first determination module, used to determine the voice signal collected by the target acquisition component among the multiple voice signals as the target voice signal; or, a second determination module, used to determine the voice signal with the largest energy value among the multiple voice signals as the target voice signal.

[0016] In an exemplary embodiment, the selection module includes: a determination submodule, used to determine the object angle information of the target object based on the signal characteristics of the multiple voice signals, wherein the object angle information is used to describe the relative angle between the target object and the smart device; a selection submodule, used to select the target acquisition component from the multiple acquisition components based on the object angle information, wherein the target acquisition component is the acquisition component that is closest to the target object after the target object is projected onto the plane where the multiple acquisition components are located according to the relative angle.

[0017] In an exemplary embodiment, the device also includes: an execution unit, which is used to perform an acoustic echo elimination operation on the multiple voice signals before selecting a target voice signal from the multiple voice signals based on the signal characteristics of the multiple voice signals, so as to obtain the processed multiple voice signals; and an extraction unit, which is used to extract signal characteristics of each voice signal in the processed multiple voice signals, so as to obtain the signal characteristics of the multiple voice signals.

[0018] In an exemplary embodiment, the device also includes: a collection unit, which is used to perform image collection on the target object through an image collection component on the smart device to obtain a target collection image before acquiring multiple voice signals collected by multiple collection components on the smart device; a recognition unit, which is used to perform object recognition on the target collection image to obtain object position information of the target object, wherein the object position information is used to indicate the relative position of the target object and the smart device; and an adjustment unit, which is used to adjust the collection angles of the multiple collection components for voice signal collection according to the object position information.

[0019] In an exemplary embodiment, the device also includes: a first determination unit, used to determine the average value of the amplitude values ​​of multiple sampling points in the target speech signal as the energy value of the target speech signal before sending the energy value of the target speech signal to the server; or, a second determination unit, used to determine the sum of the squares of the amplitude values ​​of multiple sampling points in the target speech signal as the energy value of the target speech signal.

[0020] In an exemplary embodiment, the device also includes: a receiving unit, which is used to receive the energy value of the voice signal sent by each device among multiple devices after sending the energy value of the target voice signal to the server, wherein the multiple devices include the smart device, and the voice signal to which the energy value of the voice signal sent by each device belongs is a voice signal corresponding to the voice control instruction issued by the target object; a third determination unit, which is used to determine the target device from the multiple devices according to the energy value of the voice signal sent by each device, wherein the target device is a device among the multiple devices used to execute the voice control instruction; and a control unit, which is used to control the target device to perform a device operation matching the voice control instruction.

[0021] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned voice instruction processing method when running.

[0022] According to another aspect of an embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the voice instruction processing method through the computer program.

[0023] In an embodiment of the present application, a method is adopted in which a voice signal for characterizing the distance between a voice device and a user is selected from a plurality of voice signals based on the signal characteristics of the voice signals collected by each voice collection component, by acquiring a plurality of voice signals collected by a plurality of collection components on an intelligent device, wherein each of the plurality of voice signals is a voice signal corresponding to a voice control instruction issued by a target object and collected by one of the plurality of collection components; a target voice signal is selected from the plurality of voice signals according to the signal characteristics of the plurality of voice signals; an energy value of the target voice signal is sent to a server, so that the server determines whether the intelligent device responds to the voice control instruction according to the energy value of the target voice signal, Since for a voice device, a voice signal for characterizing the distance between the voice device and the user is selected from multiple voice signals according to the signal characteristics of multiple voice signals collected by multiple voice collection components thereon, compared with the method of selecting voice signals collected by fixed voice components, the voice signal that best characterizes the distance between the voice device and the user can be dynamically selected based on the signal characteristics of the currently collected voice signal, thereby achieving the purpose of improving the accuracy of the energy value of the voice signal determined by the device, achieving the technical effect of improving the accuracy of the execution of voice commands, and further solving the problem of poor accuracy of the execution of voice commands due to inaccurate energy values ​​of voice signals determined by the device in the voice command processing method in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] 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.

[0025] 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.

[0026] Figure 1 is a schematic diagram of a hardware environment of an optional method for processing voice instructions according to an embodiment of the present application;

[0027] Figure 2 is a flowchart of an optional method for processing voice instructions according to an embodiment of the present application;

[0028] Figure 3 is a schematic diagram of an optional method for processing voice instructions according to an embodiment of the present application;

[0029] Figure 4is a schematic diagram of another optional method for processing voice instructions according to an embodiment of the present application;

[0030] Figure 5 is a structural block diagram of an optional voice instruction processing device according to an embodiment of the present application;

[0031] Figure 6 It is a structural block diagram of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the solution of the present application, 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 only 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 creative work should fall within the scope of protection of the present application.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] According to one aspect of an embodiment of the present application, a method for processing voice commands is provided. Optionally, the above-mentioned method for processing voice commands is widely used in smart home (Smart Home), smart home, smart home device ecology, smart residential (Intelligence House) ecology and other whole-house intelligent digital control application scenarios. Optionally, in this embodiment, the above-mentioned method for processing voice commands can be applied to Figure 1 In the hardware environment composed of the terminal 102 and the server 104 shown in FIG. Figure 1 As shown, the server 104 is connected to the terminal 102 via a network, and can be used to provide services (such as application services, etc.) for the terminal or a client installed on the terminal. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data computing services for the server 104.

[0035] The network may include but is not limited to at least one of the following: wired network, wireless network. The wired network may include but is not limited to at least one of the following: wide area network, metropolitan area network, local area network, and the wireless network may include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The terminal 102 may be but is not limited to a PC, a mobile phone, a tablet computer, a smart air conditioner, a smart range hood, a smart refrigerator, a smart oven, a smart stove, a smart washing machine, a smart water heater, a smart washing device, a smart dishwasher, a smart projection device, a smart TV, a smart clothes drying rack, a smart curtain, a smart audio and video, a smart socket, a smart speaker, a smart speaker, a smart fresh air device, a smart kitchen and bathroom device, a smart bathroom device, a smart sweeping robot, a smart window cleaning robot, a smart mopping robot, a smart air purification device, a smart steamer, a smart microwave oven, a smart kitchen treasure, a smart purifier, a smart water dispenser, a smart door lock, etc.

[0036] The method for processing voice commands in the embodiment of the present application may be executed by the server 104, or by the terminal 102, or by both the server 104 and the terminal 102. The method for processing voice commands in the embodiment of the present application may be executed by the terminal 102 or by a client installed thereon.

[0037] Taking the processing method of the voice command in this embodiment executed by the terminal 102 as an example, Figure 2 is a flow chart of an optional method for processing voice commands according to an embodiment of the present application, such as Figure 2 As shown, the process of the method may include the following steps:

[0038] Step S202, obtaining multiple voice signals collected by multiple collection components on the smart device, wherein each of the multiple voice signals is a voice signal collected by one of the multiple collection components and corresponding to a voice control instruction issued by the target object.

[0039] The method for processing voice commands in this embodiment can be applied to the scenario where a voice control command sent by a target object is processed by a smart device (i.e., the terminal 102). The smart device can be a smart home device or a terminal device. The smart home device can be a smart home device located in a user's home, and can be an electronic device equipped with a smart chip such as a smart TV, a smart refrigerator, or a smart water heater. Compared with traditional home devices, the smart home device has an additional computing module, a network interface, an input and output device, etc., so that the smart home device in this embodiment has the functions of intelligent analysis and intelligent service.

[0040] Optionally, the target object may be an object that has established a connection relationship with the smart home device, or an object that is located in the same location area as the smart home device. It may be used to represent a specific user, or it may be used to represent a user that is located in the same location area as the smart home device, which is not limited in this embodiment. For example, the target object may be a user that is located in the same room as the smart refrigerator.

[0041] In this embodiment, for the target smart device, the target smart device can obtain the voice control instructions issued by the target object. Optionally, the target smart device can obtain the voice signal collected by each of the multiple collection components (multiple voice collection components, for example, a microphone array) on the target smart device to obtain multiple voice signals. Each of the above multiple voice signals is a voice signal collected by one of the multiple collection components and corresponds to the voice control instructions issued by the target object.

[0042] The above-mentioned collection component may be a voice collection component provided in the smart device. Optionally, the above-mentioned collection component may be a microphone component provided in the smart device, for example, the voice control instructions sent by the user may be acquired through multiple microphones provided in the smart device.

[0043] Optionally, in order to better collect the voice control instructions issued by the target object through multiple collection components, the collection angles of the multiple collection components for collecting voice signals can be adjusted before obtaining the multiple voice signals collected by the multiple collection components on the smart device. This is not limited in this embodiment.

[0044] It should be noted that the above-mentioned multiple collection components can be arranged in a circle in the smart device, or can be arranged in other arrangements, which is not limited in this embodiment. In addition, the number of the multiple collection components in the above-mentioned smart device can be 4, 6, or other numbers, which is not limited in this embodiment.

[0045] For example, a microphone array may be provided on a smart home device, and multi-channel microphone signals may be collected through the microphone array.

[0046] Step S204: selecting a target speech signal from the multiple speech signals according to the signal characteristics of the multiple speech signals.

[0047] In this embodiment, after acquiring multiple voice signals, a target voice signal can be selected from the multiple voice signals, and the target voice signal is a voice signal used to represent the target smart device, or a voice signal used to represent the distance between the target smart device and the target object. Optionally, a feature extraction operation can be performed on each of the multiple voice signals to obtain the signal feature of each voice signal, and then the target voice signal can be selected from the multiple voice signals according to the signal feature of each voice signal, which is not limited in this embodiment.

[0048] Optionally, the above process of selecting a target voice signal from multiple voice signals based on the signal characteristics of the multiple voice signals may be: selecting the target voice signal from the multiple voice signals based on multiple energy values ​​corresponding to the multiple voice signals, or first selecting a target acquisition component closest to the target object from multiple acquisition components based on the signal characteristics of the multiple voice signals, and then determining the voice signal collected by the target acquisition component as the target voice signal. It may also be other ways of selecting the target voice signal, which are not limited to this in the present embodiment.

[0049] It should be noted that before performing a feature extraction operation on multiple voice signals to obtain the signal features of the multiple voice signals, a preprocessing operation can be performed on the multiple voice signals to improve the accuracy of the signal feature extraction of the multiple voice signals. The above preprocessing operation can be an AEC (Acoustic Echo Cancellation) operation performed on the multiple voice signals, or a filtering operation performed on the multiple voice signals to filter out interference signals in the multiple voice signals. This is not limited in the present embodiment.

[0050] Step S206: Send the energy value of the target voice signal to the server, so that the server determines whether the smart device responds to the voice control instruction according to the energy value of the target voice signal.

[0051] In this embodiment, after selecting a target voice signal from multiple voice signals, the energy value of the target voice signal can be sent to the server, so that the server can determine whether the smart device responds to the voice control instruction based on the energy value of the target voice signal.

[0052] Optionally, the above-mentioned server can be a server that establishes a connection relationship with the target smart device, that is, data can be exchanged between the target smart device and the server. After receiving the energy value of the target voice signal sent by the target smart device, the server can compare the energy value of the target voice signal with the energy value of the voice signal sent by other devices, and determine whether the target smart device responds to the voice control instruction (that is, which smart device responds to the voice control instruction) based on the comparison result. This is not limited in this embodiment.

[0053] It should be noted that, since the target smart device has the risk of being stolen when sending the energy value of the target voice signal to the server, the energy value of the target voice signal may be encrypted before being sent to the server. This is not limited in this embodiment.

[0054] Through the above steps S202 to S206, multiple voice signals collected by multiple collection components on the smart device are obtained, wherein each of the multiple voice signals is a voice signal collected by one of the multiple collection components and corresponds to the voice control instruction issued by the target object; according to the signal characteristics of the multiple voice signals, a target voice signal is selected from the multiple voice signals; the energy value of the target voice signal is sent to the server, so that the server determines whether the smart device responds to the voice control instruction according to the energy value of the target voice signal, thereby solving the problem of poor accuracy of voice instruction execution caused by inaccurate energy value of the voice signal determined by the device in the voice instruction processing method in the related art, and improving the accuracy of voice instruction execution.

[0055] In an exemplary embodiment, there may be multiple ways to select a target voice signal from multiple voice signals, including but not limited to at least one of the following: directly selecting a target voice signal from multiple voice signals based on voice signal features, first selecting a target acquisition component from multiple acquisition components based on voice signal features, and then determining the voice signal collected by the target acquisition component as the target voice signal.

[0056] As an optional implementation, a target collection component is selected from multiple collection components according to signal characteristics of multiple speech signals, including:

[0057] S11, selecting a target acquisition component closest to a target object from multiple acquisition components according to signal characteristics of multiple voice signals;

[0058] S12, determining the speech signal collected by the target collection component among the multiple speech signals as the target speech signal.

[0059] According to the signal characteristics of multiple voice signals, the collection component closest to the target object can be selected from multiple collection components to obtain the target collection component. For example, according to the voice information collected by multiple microphones, a DOA (Direction Of Arrival) algorithm can be used to select the microphone closest to the user object from multiple microphones to obtain the target microphone (an embodiment of the above-mentioned target collection component).

[0060] As another optional implementation, selecting a target collection component from multiple collection components according to signal features of multiple speech signals includes:

[0061] S13, determining the speech signal with the largest energy value among the multiple speech signals as the target speech signal.

[0062] The speech signal with the largest energy value among multiple speech signals can be determined as the target speech signal. For example, if among multiple microphones A, B, C, and D, the energy value of the speech signal collected by microphone A is 40, the energy value collected by microphone B is 30, the energy value of the speech signal collected by microphone C is 45, and the energy value collected by microphone D is 35, then the speech signal collected by microphone C will be determined as the target speech signal.

[0063] Through this embodiment, the voice signal collected by the collection component closest to the target object among multiple collection components or the voice signal with the largest energy value is determined as the target voice signal, which can improve the flexibility and accuracy of voice signal selection.

[0064] In an exemplary embodiment, according to the signal characteristics of the plurality of speech signals, a target acquisition component closest to the target object is selected from the plurality of acquisition components, including:

[0065] S21, determining object angle information of a target object according to signal characteristics of the plurality of voice signals, wherein the object angle information is used to describe a relative angle between the target object and the smart device;

[0066] S22, selecting a target acquisition component from multiple acquisition components according to the object angle information, wherein the target acquisition component is the acquisition component that is closest to the target object after the target object is projected onto the plane where the multiple acquisition components are located according to the relative angle.

[0067] In this embodiment, the target acquisition component closest to the target object can be selected from the multiple acquisition components according to the signal characteristics of the multiple voice signals. Optionally, the process of selecting the target acquisition component closest to the target object from the multiple acquisition components according to the signal characteristics of the multiple voice signals can be: first determine the object angle information of the target object according to the signal characteristics of the multiple voice signals, and then select the target acquisition component from the multiple acquisition components according to the object angle information. For example, the angle information of the user sound source can be calculated by the DOA algorithm based on the microphone signals of the multiple channels collected, and then the channel of the microphone signal closest to the user sound source can be found according to the calculated angle information.

[0068] Optionally, the object angle information is used to describe the relative angle between the target object and the smart device, and the target acquisition component is the acquisition component closest to the target object after the target object is projected onto the plane where the multiple acquisition components are located according to the relative angle. For example, the relative angle between the user object and the smart device may be determined first, and then the user object may be projected onto the plane where the multiple microphones are located according to the relative angle.

[0069] Optionally, the process of determining the object angle information of the target object may be: firstly establish a coordinate system with the location of the target smart device as the origin, and then determine the relative angle between the target object and the smart device according to the location of the target object in the coordinate system. This is not limited in this embodiment.

[0070] Through this embodiment, the object angle information of the target object is first determined based on the signal characteristics of multiple voice signals, and then the target acquisition component is selected from multiple acquisition components based on the object angle information, which can improve the accuracy of voice signal selection.

[0071] In an exemplary embodiment, before selecting the target speech signal from the multiple speech signals according to the signal features of the multiple speech signals, the method further includes:

[0072] S31, performing an acoustic echo cancellation operation on the multiple voice signals to obtain multiple processed voice signals;

[0073] S32, extracting signal features from each of the processed multiple speech signals to obtain signal features of the multiple speech signals.

[0074] In this embodiment, since there may be interference signals in the voice signals collected by the collection component, the accuracy of the signal features of the extracted voice signals may be affected. Optionally, before selecting the target voice signal from the multiple voice signals based on the signal features of the multiple voice signals, the multiple voice signals may be denoised first, and then the signal features of the processed voice signals may be extracted.

[0075] Optionally, the above-mentioned process of denoising the multiple voice signals may be: performing an acoustic echo cancellation operation on the multiple voice signals to obtain the processed multiple voice signals. After obtaining the processed multiple voice signals, signal feature extraction may be performed on each of the processed multiple voice signals to obtain signal features of the multiple voice signals.

[0076] Optionally, the signal features of the above-mentioned multiple signals may be energy values ​​of the multiple signals. When the signal feature is an energy value, the process of extracting the signal features of each of the processed multiple voice signals to obtain the signal features of the multiple voice signals may be: determining the energy value (i.e., signal feature) of the voice signal by taking the average value or the sum of squares of the preset elements of the multiple sampling points in each of the processed multiple voice signals as the energy value of the voice signal. The above-mentioned preset elements may be the amplitude value of the sampling point, the energy value of the sampling point, or other elements of the sampling point, which are not limited in this embodiment.

[0077] Through this embodiment, after performing the acoustic echo cancellation operation on multiple voice signals, the signal features of the multiple voice signals are extracted, which can improve the accuracy of the signal feature extraction of the voice signals.

[0078] In an exemplary embodiment, before acquiring multiple voice signals collected by multiple collection components on the smart device, the method further includes:

[0079] S41, performing image acquisition on a target object through an image acquisition component on a smart device to obtain a target acquisition image;

[0080] S42, performing object recognition on the target captured image to obtain object position information of the target object, wherein the object position information is used to indicate the relative position of the target object and the smart device;

[0081] S43, adjusting the collection angles of the multiple collection components for collecting voice signals according to the object position information.

[0082] In this embodiment, in order to better collect the voice control command sent by the target object through the collection component, the collection angles of the multiple collection components can be adjusted before obtaining the multiple voice signals collected by the multiple collection components on the smart device, for example, adjusting in the direction where the target object is located. Since it is impossible to accurately determine when the target object will issue a voice control command, the collection angles of the multiple collection components can be adjusted in real time or periodically according to the location of the target object.

[0083] When adjusting the acquisition angle once, the image acquisition component (for example, a camera) on the smart device can first acquire an image of the target object to obtain a target acquisition image, and then perform object recognition on the target acquisition image to obtain the object position information of the target object. The above object position information is used to indicate the relative position of the target object and the smart device; finally, according to the object position information, the acquisition angles of multiple acquisition components for voice signal acquisition are adjusted.

[0084] Optionally, after adjusting the collection angles of the multiple collection components for voice signal collection, the angles of the collection components for voice signal collection may be toward the target object. In addition, the relative position of the target object and the target smart device may be detected by other perception sensors (e.g., human body sensors), and the collection angles of the multiple collection components for voice signal collection may be adjusted based on the detected relative positions.

[0085] Since the target object may be in a moving state (for example, the user may move around the smart device), the relative position of the target object and the target smart device may be constantly changing. Therefore, the acquisition angles of the multiple acquisition components for voice signal acquisition may be continuously adjusted. Optionally, the target object may be imaged periodically to obtain a target acquisition image, and the acquisition angles of the multiple acquisition components for voice signal acquisition may be adjusted according to the target acquisition image acquired periodically.

[0086] Optionally, in order to reduce resource consumption, the collection angles of multiple collection components for voice signal collection may be adjusted only when the difference between the object position information of the target object determined in the next cycle and the object position information of the target object determined in the previous cycle is greater than a preset threshold. This is not limited in this embodiment.

[0087] It should be noted that the above-mentioned image acquisition component can be a camera on the smart device, an infrared surface array projector on the smart device, or other image acquisition components, which is not limited in this embodiment.

[0088] Through this embodiment, by detecting the relative position of the user and the smart device and adjusting the angle at which the collection component on the smart device collects the voice signal according to the relative position, the signal quality of the acquired voice signal can be improved.

[0089] In an exemplary embodiment, before sending the energy value of the target speech signal to the server, the method further includes:

[0090] S51, determining the average value of the amplitude values ​​of multiple sampling points in the target speech signal as the energy value of the target speech signal; or

[0091] S52, determining the sum of squares of amplitude values ​​of multiple sampling points in the target speech signal as the energy value of the target speech signal.

[0092] In this embodiment, before sending the energy value of the target speech signal to the server, the energy value of the target speech signal may be determined. Alternatively, the energy value of the target speech signal may be determined based on the amplitude values ​​of multiple sampling points in the target speech signal.

[0093] As an optional implementation, the average value of the amplitude values ​​of multiple sampling points in the target speech signal can be determined as the energy value of the target speech signal. For example, the amplitude values ​​of multiple sampling points E1, F1, and G1 are 2, 3, and 4 respectively, and the energy value of the target speech signal is 3 (i.e., (2+3+4) / 3).

[0094] As another optional implementation, the square sum of the amplitude values ​​of multiple sampling points in the target speech signal can be determined as the energy value of the target speech signal, and the number of sampling points can be preset. For example, the amplitude values ​​of the multiple sampling points E2, F2, and G2 are 2, 3, and 4 respectively, and the energy value of the target speech signal is 29 (i.e., 2^2+3^2+4^2=29).

[0095] Through this embodiment, the average value or the sum of squares of the amplitude values ​​of multiple sampling points in the speech signal is determined as the energy value of the speech signal, which can improve the convenience of determining the energy value of the speech signal.

[0096] In an exemplary embodiment, after sending the energy value of the target speech signal to the server, the method further includes:

[0097] S61, receiving an energy value of a voice signal sent by each device of a plurality of devices, wherein the plurality of devices include a smart device, and the voice signal to which the energy value of the voice signal sent by each device belongs is a voice signal corresponding to a voice control instruction issued by a target object;

[0098] S62, determining a target device from the multiple devices according to the energy value of the voice signal sent by each device, wherein the target device is a device for executing the voice control instruction among the multiple devices;

[0099] S63, controlling the target device to execute a device operation matching the voice control instruction.

[0100] In this embodiment, after the energy value of the target voice signal is sent to the server, the server can receive the energy value of the voice signal sent by other smart devices based on the received energy value of the target voice signal, that is, the energy values ​​of the voice signals sent by multiple devices are received, and the voice signals to which the energy value of the voice signal sent by each device belongs are all voice signals corresponding to the voice control instruction issued by the target object.

[0101] Determines whether the smart device responds to voice control commands.

[0102] Optionally, the server may receive energy values ​​of voice signals sent by each of a plurality of devices, wherein the plurality of devices include intelligent devices, and the voice signal to which the energy value of the voice signal sent by each device belongs is a voice signal corresponding to a voice control instruction issued by a target object.

[0103] After receiving the energy value of the voice signal sent by each device, the server can determine the target device from multiple devices according to the energy value of the voice signal sent by each device. The target device is a device used to execute the voice control instruction among the multiple devices.

[0104] Optionally, the process of determining the target device from multiple devices based on the energy value of the voice signal sent by each device may be: the device corresponding to the largest energy value among the energy values ​​of the voice signals sent by the multiple devices is determined as the target device. For example, if the energy value of the voice signal sent by device H received by the server is 40, the energy value of the voice signal sent by device I is 38, and the energy value of the voice signal sent by device J is 45, then device J will be determined as the target device.

[0105] Optionally, after determining the target device, the target device may be controlled to perform a device operation that matches the voice control instruction. For example, when the voice control instruction is a device wake-up instruction, the target device may be woken up; when the voice control instruction is used to control the target device to perform a specific device operation, a device operation instruction may be sent to the target device, and the device operation instruction may carry operation parameters for the specific device operation. After receiving the device operation instruction, the target device may perform the specific device operation according to the operation parameters in the device operation instruction.

[0106] Through this embodiment, the device that responds to the voice operation instruction is selected based on the energy values ​​sent by multiple devices, which can improve the accuracy of the execution of the voice control instruction and thus enhance the user experience.

[0107] The following is an explanation of the method for processing voice commands in the embodiment of the present application in conjunction with an optional example. In this optional example, the target smart device is a smart home device, the collection component is a microphone, and the server is a cloud (ie, a cloud server).

[0108] The method for processing voice commands in the related art generally proceeds as follows: Figure 3 As shown, a fixed signal in the multi-channel microphone array will be selected to calculate the energy value of the device. After the signal collected by this channel is processed by AEC, the energy value is calculated, and then the calculated energy value is transmitted to the cloud. After receiving the energy values ​​uploaded by each device, the cloud can compare the energy values ​​of different devices, make a judgment, and then send the judgment result to the device.

[0109] However, if a fixed signal from a multi-channel microphone array is selected to calculate the energy value of the device, the calculated energy value will have a relatively large energy difference depending on the placement of the user's device. For example, if the user is placed against a wall, if the microphone signal close to the wall is selected to calculate the energy value of the device, it will be affected by the reflection of the wall, resulting in inaccurate energy values ​​of the calculated device, and then inaccurate wake-up occurs, and the device B is woken up when it is closest to device A.

[0110] In response to the problem of inaccurate energy value calculation of the above-mentioned devices, this optional example provides a method for improving the accuracy of voice device wake-up. When calculating the energy value of the device, the microphone number closest to the user is first calculated, and the energy value is calculated using the microphone signal of this channel. By using the energy value calculated by the channel of the microphone number closest to the user, interference from the device placement can be effectively avoided.

[0111] Combination Figure 4 As shown, the process of the method for processing voice instructions in this optional example may include the following steps:

[0112] Step S402: acquiring multi-channel microphone signals.

[0113] Step S404: performing acoustic echo cancellation processing on the acquired multi-channel microphone signals.

[0114] Step S406: Calculate the angle information of the user's sound source according to the processed multi-channel microphone signal.

[0115] Step S408: Find the channel of the microphone signal closest to the user's sound source according to the calculated angle information of the user's sound source.

[0116] Step S410: energy calculation is performed using the microphone signal closest to the user's sound source.

[0117] The audio energy may be calculated by using the sum of squares of sampling points or a similar method.

[0118] Step S412, uploading the energy value calculated by the device to the cloud.

[0119] In step S414, the cloud makes a decision based on the energy values ​​reported by multiple devices.

[0120] Step S416, waking up the device with the largest energy value.

[0121] Through this embodiment, the influence of echo or wall reflection caused by the placement of the device (for example, when the device microphone is placed against a wall or the device microphone is blocked) can be avoided to a limited extent, the corresponding accuracy of the device can be improved, the problem of inaccurate wake-up can be avoided, the user experience and control accuracy can be improved, and the problem of inaccurate wake-up of multiple devices under the same family user can be effectively solved.

[0122] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0123] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM (Read-Only Memory) / RAM (Random Access Memory), a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0124] According to another aspect of the embodiments of the present application, a voice instruction processing device for implementing the above-mentioned voice instruction processing method is also provided. Figure 5 is a structural block diagram of an optional voice instruction processing device according to an embodiment of the present application, such as Figure 5 As shown, the device may include:

[0125] An acquisition unit 502 is used to acquire multiple voice signals collected by multiple collection components on the smart device, wherein each of the multiple voice signals is a voice signal collected by one of the multiple collection components and corresponding to a voice control instruction issued by a target object;

[0126] A selection unit 504, connected to the acquisition unit 502, is used to select a target speech signal from the multiple speech signals according to signal features of the multiple speech signals;

[0127] The sending unit 506 is connected to the selecting unit 504 and is used to send the energy value of the target voice signal to the server, so that the server determines whether the smart device responds to the voice control instruction according to the energy value of the target voice signal.

[0128] It should be noted that the acquisition unit 502 in this embodiment can be used to execute the above step S202, the selection unit 504 in this embodiment can be used to execute the above step S204, and the sending unit 506 in this embodiment can be used to execute the above step S206.

[0129] Through the above module, multiple voice signals collected by multiple collection components on the smart device are obtained, wherein each of the multiple voice signals is a voice signal collected by one of the multiple collection components and corresponds to the voice control instruction issued by the target object; according to the signal characteristics of the multiple voice signals, a target voice signal is selected from the multiple voice signals; the energy value of the target voice signal is sent to the server, so that the server determines whether the smart device responds to the voice control instruction according to the energy value of the target voice signal, thereby solving the problem of poor accuracy of voice instruction execution caused by inaccurate energy value of the voice signal determined by the device in the voice instruction processing method in the related art, and improving the accuracy of voice instruction execution.

[0130] In an exemplary embodiment, the selection unit includes:

[0131] According to the signal characteristics of the plurality of speech signals, a target acquisition component closest to the target object is selected from the plurality of acquisition components;

[0132] The first determination module is used to determine the voice signal collected by the target collection component among the multiple voice signals as the target voice signal.

[0133] In an exemplary embodiment, the selection unit includes:

[0134] The second determination module is used to determine the speech signal with the largest energy value among the multiple speech signals as the target speech signal.

[0135] In an exemplary embodiment, the selection module includes:

[0136] A determination submodule, used to determine object angle information of a target object according to signal characteristics of a plurality of voice signals, wherein the object angle information is used to describe a relative angle between the target object and the smart device;

[0137] The selection submodule is used to select a target acquisition component from multiple acquisition components according to the object angle information, wherein the target acquisition component is the acquisition component that is closest to the target object after the target object is projected onto the plane where the multiple acquisition components are located according to the relative angle.

[0138] In an exemplary embodiment, the above device further comprises:

[0139] An execution unit, configured to perform an acoustic echo cancellation operation on the multiple voice signals before selecting a target voice signal from the multiple voice signals according to signal characteristics of the multiple voice signals to obtain multiple processed voice signals;

[0140] The extraction unit is used to extract signal features from each of the processed multiple speech signals to obtain signal features of the multiple speech signals.

[0141] In an exemplary embodiment, the above device further comprises:

[0142] The acquisition unit is used to acquire an image of a target object through an image acquisition component on the smart device before acquiring the multiple voice signals acquired by the multiple acquisition components on the smart device to obtain a target acquisition image;

[0143] An identification unit, used to perform object identification on the target captured image to obtain object position information of the target object, wherein the object position information is used to indicate the relative position of the target object and the smart device;

[0144] The adjustment unit is used to adjust the collection angles of the multiple collection components for collecting voice signals according to the object position information.

[0145] In an exemplary embodiment, the above device further comprises:

[0146] The first determining unit is used to determine the average value of the amplitude values ​​of multiple sampling points in the target voice signal as the energy value of the target voice signal before sending the energy value of the target voice signal to the server; or

[0147] The second determining unit is used to determine the square sum of the amplitude values ​​of multiple sampling points in the target speech signal as the energy value of the target speech signal.

[0148] In an exemplary embodiment, the above device further comprises:

[0149] A receiving unit, configured to receive the energy value of a voice signal sent by each device in a plurality of devices after sending the energy value of the target voice signal to the server, wherein the plurality of devices include smart devices, and the voice signal to which the energy value of the voice signal sent by each device belongs is a voice signal corresponding to the voice control instruction issued by the target object;

[0150] A third determining unit, configured to determine a target device from a plurality of devices according to an energy value of a voice signal sent by each device, wherein the target device is a device for executing a voice control instruction among the plurality of devices;

[0151] The control unit is used to control the target device to perform device operations matching the voice control instructions.

[0152] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules as part of the device can be run in Figure 1 In the hardware environment shown, it can be implemented by software or by hardware, wherein the hardware environment includes a network environment.

[0153] According to another aspect of the embodiment of the present application, a storage medium is also provided. Optionally, in this embodiment, the storage medium can be used to execute the program code of any of the above-mentioned voice instruction processing methods in the embodiment of the present application.

[0154] Optionally, in this embodiment, the storage medium may be located on at least one network device among a plurality of network devices in the network shown in the above embodiment.

[0155] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps:

[0156] S1, acquiring multiple voice signals collected by multiple collection components on the smart device, wherein each of the multiple voice signals is a voice signal collected by one of the multiple collection components and corresponding to a voice control instruction issued by a target object;

[0157] S2, selecting a target speech signal from the multiple speech signals according to signal characteristics of the multiple speech signals;

[0158] S3, sending the energy value of the target voice signal to the server, so that the server determines whether the smart device responds to the voice control instruction according to the energy value of the target voice signal.

[0159] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, which will not be described in detail in this embodiment.

[0160] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a ROM, a RAM, a mobile hard disk, a magnetic disk, or an optical disk.

[0161] According to another aspect of an embodiment of the present application, an electronic device for implementing the above-mentioned voice instruction processing method is also provided. The electronic device may be a server, a terminal, or a combination thereof.

[0162] Figure 6 is a structural block diagram of an optional electronic device according to an embodiment of the present application, such as Figure 6 As shown, it includes a processor 602, a communication interface 604, a memory 606 and a communication bus 608, wherein the processor 602, the communication interface 604 and the memory 606 communicate with each other through the communication bus 608, wherein,

[0163] Memory 606, used to store computer programs;

[0164] The processor 602 is used to implement the following steps when executing the computer program stored in the memory 606:

[0165] S1, acquiring multiple voice signals collected by multiple collection components on the smart device, wherein each of the multiple voice signals is a voice signal collected by one of the multiple collection components and corresponding to a voice control instruction issued by a target object;

[0166] S2, selecting a target speech signal from the multiple speech signals according to signal characteristics of the multiple speech signals;

[0167] S3, sending the energy value of the target voice signal to the server, so that the server determines whether the smart device responds to the voice control instruction according to the energy value of the target voice signal.

[0168] Optionally, in this embodiment, the communication bus may be a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 The communication interface is used for communication between the electronic device and other devices.

[0169] The above-mentioned memory may include RAM, or may include non-volatile memory (non-volatile memory), for example, at least one disk memory. Optionally, the memory may also be at least one storage device located far away from the above-mentioned processor.

[0170] As an example, the memory 606 may include but is not limited to the acquisition unit 502, the selection unit 504 and the sending unit 506 in the control device of the device. In addition, it may also include but is not limited to other module units in the control device of the device, which will not be repeated in this example.

[0171] The above-mentioned processor can be a general-purpose processor, which can include but not be limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; it can also be DSP (Digital Signal Processing), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0172] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0173] It can be understood by those skilled in the art that Figure 6 The structure shown is for illustration only. The device for implementing the above-mentioned voice command processing method may be a terminal device, which may be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, and other terminal devices. Figure 6 The structure of the electronic device is not limited. Figure 6 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 6 Different configurations shown.

[0174] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, which can include: a flash drive, ROM, RAM, a magnetic disk or an optical disk, etc.

[0175] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0176] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0177] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0178] In the several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0179] 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 units may be selected according to actual needs to achieve the purpose of the solution provided in this embodiment.

[0180] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0181] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for processing voice commands, characterized in that: include: Acquire multiple voice signals collected by multiple collection components on the smart device, wherein each of the multiple voice signals is a voice signal collected by one of the multiple collection components and corresponding to a voice control instruction issued by a target object; Selecting a target speech signal from the plurality of speech signals according to signal characteristics of the plurality of speech signals; Sending the energy value of the target voice signal to a server, so that the server determines whether the smart device responds to the voice control instruction according to the energy value of the target voice signal; The step of selecting a target voice signal from the multiple voice signals according to the signal characteristics of the multiple voice signals comprises: selecting a target acquisition component closest to the target object from the multiple acquisition components according to the signal characteristics of the multiple voice signals; determining the voice signal collected by the target acquisition component among the multiple voice signals as the target voice signal; or determining the voice signal with the largest energy value among the multiple voice signals as the target voice signal; Wherein, before acquiring multiple voice signals collected by multiple collection components on the smart device, the method also includes: performing image collection on the target object through the image collection component on the smart device to obtain a target collection image; performing object recognition on the target collection image to obtain object position information of the target object, wherein the object position information is used to indicate the relative position of the target object and the smart device; and adjusting the collection angles of the multiple collection components for collecting voice signals according to the object position information.

2. The method according to claim 1, characterized in that: The step of selecting a target acquisition component closest to the target object from the multiple acquisition components according to the signal features of the multiple voice signals comprises: Determining object angle information of the target object according to signal characteristics of the multiple voice signals, wherein the object angle information is used to describe a relative angle between the target object and the smart device; The target acquisition component is selected from the multiple acquisition components according to the object angle information, wherein the target acquisition component is the acquisition component that is closest to the target object after the target object is projected onto the plane where the multiple acquisition components are located according to the relative angle.

3. The method according to claim 1, characterized in that Before selecting the target speech signal from the multiple speech signals according to the signal features of the multiple speech signals, the method further includes: Performing an acoustic echo cancellation operation on the multiple voice signals to obtain the multiple voice signals after processing; Signal features are extracted from each of the processed speech signals to obtain signal features of the speech signals.

4. The method according to claim 1, characterized in that: Before sending the energy value of the target speech signal to the server, the method further includes: Determine the average value of the amplitude values ​​of multiple sampling points in the target speech signal as the energy value of the target speech signal; or The square sum of the amplitude values ​​of multiple sampling points in the target speech signal is determined as the energy value of the target speech signal.

5. The method according to any one of claims 1 to 4, characterized in that After sending the energy value of the target speech signal to the server, the method further includes: Receiving an energy value of a voice signal sent by each device of a plurality of devices, wherein the plurality of devices include the smart device, and the voice signal to which the energy value of the voice signal sent by each device belongs is a voice signal corresponding to the voice control instruction issued by the target object; Determining a target device from the multiple devices according to the energy value of the voice signal sent by each device, wherein the target device is a device among the multiple devices for executing the voice control instruction; The target device is controlled to perform a device operation matching the voice control instruction.

6. A voice command processing device, characterized in that: include: An acquisition unit, configured to acquire a plurality of voice signals collected by a plurality of collection components on the smart device, wherein each of the plurality of voice signals is a voice signal collected by one of the plurality of collection components and corresponding to a voice control instruction issued by a target object; A selection unit, configured to select a target speech signal from the plurality of speech signals according to signal features of the plurality of speech signals; a sending unit, configured to send the energy value of the target voice signal to a server, so that the server determines whether the smart device responds to the voice control instruction according to the energy value of the target voice signal; The selection unit includes: a selection module, which is used to select a target acquisition component closest to a target object from the multiple acquisition components according to the signal characteristics of the multiple voice signals; a first determination module, which is used to determine the voice signal collected by the target acquisition component among the multiple voice signals as the target voice signal; and a second determination module, which is used to determine the voice signal with the largest energy value among the multiple voice signals as the target voice signal. The device further includes: a collection unit, which is used to collect images of the target object through the image collection component on the smart device before acquiring the multiple voice signals collected by the multiple collection components on the smart device to obtain a target collection image; a recognition unit, which is used to perform object recognition on the target collection image to obtain object position information of the target object, wherein the object position information is used to indicate the relative position of the target object and the smart device; and an adjustment unit, which is used to adjust the collection angles of the multiple collection components for collecting voice signals according to the object position information.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 5 when executed.

8. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 5 through the computer program.

Images