Cross-space speech processing method, device, equipment and storage medium

By using functional database and environmental information to determine executable devices and send voice commands across space in multi-device interaction, the problem that devices cannot accurately receive user commands is solved, and the accurate identification and processing of voice commands is realized, and the user is improved. Experience and device interaction accuracy.

CN118471224BActive Publication Date: 2024-11-12QINGDAO HAIGAO DESIGN & MANUFACTURING CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410933333.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-12
Publication Date
2024-11-12
Estimated Expiration
2044-07-12

AI Technical Summary

Technical Problem

In multi-device interaction across space, due to communication complexity and uncertainty when outputting and executing voice commands, the device may not be able to accurately receive user instructions, resulting in failure in command processing.

Method used

By obtaining the target voice command of the user in the first space, after the identification process, if the first device cannot execute, the second device that can perform the operation function and its space and is located using the function database and environment information, and the instructions are passed through the communication network Sent to the second device to ensure that the instructions can be accurately identified and processed.

Benefits of technology

Ensure that the voice commands sent by users can be accurately identified and processed, break the physical location limitations of the device, enhance the accuracy of multi-device interaction, and improve user experience and satisfaction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118471224B_ABST
    Figure CN118471224B_ABST
Patent Text Reader

Abstract

The present application belongs to the field of smart home appliances, and specifically relates to a cross-space voice processing method, device, equipment and storage medium. By obtaining the target voice command sent by the user in the first space, and according to the target voice command, determining that the first device cannot execute the operation function corresponding to the command, first, according to the function database and environmental information, determine the second device that can execute the operation function, and determine the target space where it is located. Subsequently, when it is determined that the second device is located in a second space different from the first space, the target voice command is sent to the second device through a communication network. This method not only ensures that the voice commands sent by the user can be accurately recognized and processed, but also ensures that the user is no longer restricted by the physical location of the device, and can control and manage their devices through voice commands anytime and anywhere, thereby enhancing the accuracy of interaction between multiple devices, thereby improving the user experience and satisfaction.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the field of smart home appliances, and specifically relates to a cross-space voice processing method, device, equipment and storage medium. Background Art

[0002] With the rapid development of information technology, multi-device interaction has become an important part of smart life. Traditional multi-device interaction mainly relies on short-range wireless communication technologies such as Bluetooth and Wi-Fi to achieve information transmission and control between devices.

[0003] Although cross-space multi-device interaction solutions have made some progress, they still face many challenges. For example, when the output and execution of voice commands occur in different spaces, due to the complexity and uncertainty of cross-space communication, cross-space devices may not be able to accurately perceive the user's voice commands, which may lead to command processing failure.

[0004] Therefore, how to ensure that the voice commands sent by users can be accurately recognized and processed is an urgent problem to be solved. Summary of the invention

[0005] The present application provides a cross-space voice processing method, apparatus, device and storage medium, which are used to solve the problem that it is impossible to ensure that the voice commands sent by the user can be accurately recognized and processed.

[0006] In a first aspect, the present application provides a cross-space speech processing method, comprising:

[0007] Obtaining a target voice command sent by a user in the first space;

[0008] Recognize and process the target voice command to obtain an operation function to be executed;

[0009] If it is determined that the first device cannot execute the operation function to be executed, obtaining a function database and environment information, wherein the function database is used to store the correspondence between the operation function and the device, and the environment information is used to indicate the space where each device pre-stored by the user is located;

[0010] Determine, according to the function database and the environment information, a second device capable of executing the operation function and a target space in which the second device is located;

[0011] If it is determined according to the target space that the second device is located in a second space, the target voice instruction is sent to the second device through a communication network, wherein the first space and the second space are physically different spaces.

[0012] In a second aspect, the present application provides a cross-space speech processing device, comprising:

[0013] An acquisition module, used to acquire a target voice command sent by a user in the first space;

[0014] A processing module, used to recognize and process the target voice command to obtain an operation function to be executed;

[0015] The acquisition module is further used to acquire a function database and environment information when it is determined that the first device cannot execute the operation function to be executed, wherein the function database is used to store the correspondence between the operation function and the device, and the environment information is used to indicate the space where each device pre-stored by the user is located;

[0016] a determination module, configured to determine, according to the function database and the environment information, a second device capable of executing the operation function and a target space in which the second device is located;

[0017] A sending module is used to send the target voice instruction to the second device through a communication network when it is determined that the second device is located in a second space according to the target space, wherein the first space and the second space are physically different spaces.

[0018] In a third aspect, the present application provides a cross-space speech processing device, including:

[0019] Memory;

[0020] processor;

[0021] Wherein, the memory stores computer-executable instructions;

[0022] The processor executes the computer-executable instructions stored in the memory to implement the cross-space speech processing method as described in the first aspect and various possible implementations of the first aspect.

[0023] In a fourth aspect, the present application provides a computer storage medium having computer execution instructions stored thereon, wherein the computer execution instructions are executed by a processor to implement the cross-space speech processing method as described in the first aspect and various possible implementations of the first aspect.

[0024] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the cross-space speech processing method as described above.

[0025] The cross-space voice processing method provided by the present application obtains the target voice command sent by the user in the first space, and after determining that the first device cannot execute the operation function corresponding to the command based on the target voice command, first, according to the function database and environmental information, a second device that can execute the operation function is determined, and the target space where it is located is determined. Subsequently, when it is determined that the second device is located in a second space different from the first space, the target voice command is sent to the second device through the communication network. This method not only ensures that the voice commands sent by the user can be accurately recognized and processed, but also ensures that the user is no longer restricted by the physical location of the device, and can control and manage their devices through voice commands anytime and anywhere, thereby enhancing the accuracy of interaction between multiple devices, thereby improving the user experience and satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] 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.

[0027] Figure 1 The process of the cross-space speech processing method provided by this application Figure 1 ;

[0028] Figure 2 Scenario diagram of cross-space speech processing provided by this application Figure 1 ;

[0029] Figure 3 The process of the cross-space speech processing method provided by this application Figure 2 ;

[0030] Figure 4 The process of the cross-space speech processing method provided by this application Figure 3 ;

[0031] Figure 5 Scenario diagram of cross-space speech processing provided by this application Figure 2 ;

[0032] Figure 6 The process of the cross-space speech processing method provided by this application Figure 4 ;

[0033] Figure 7 Scenario diagram of cross-space speech processing provided by this application Figure 3 ;

[0034] Figure 8 The process of the cross-space speech processing method provided by this application Figure 5 ;

[0035] Fig. 9Scenario diagram of cross-space speech processing provided by this application Figure 4 ;

[0036] Fig.10 It is a schematic diagram of the structure of the cross-space speech processing device provided by the present application;

[0037] Fig.11 It is a schematic diagram of the structure of the cross-space speech processing device provided by this application.

[0038] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0040] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present invention and the above 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 numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in sequences other than those illustrated or described herein, for example.

[0041] In the embodiments of the present application, the words "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0042] With the continuous advancement of technology, multi-device interaction has been deeply integrated into users' smart lives. However, although traditional short-range wireless communication technologies such as Bluetooth and Wi-Fi provide users with many conveniences, they still face many limitations in terms of information transmission and control between devices.

[0043] In particular, when it comes to cross-space multi-device interaction, the challenges are more prominent. For example, when the output and execution of voice commands occur in different spaces, due to the complexity and uncertainty of cross-space communication, cross-space devices may not be able to accurately receive the user's voice commands, which may lead to command processing failure.

[0044] In this embodiment, the cross-space device can be any device with voice function, such as a smart speaker, or a smart home appliance, etc. For example, the smart home appliance can be 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 equipment, a smart dishwasher, a smart projection equipment, a smart TV, a smart clothes drying rack, a smart curtain, a smart audio and video, a smart socket, a smart speaker, a smart fresh air equipment, a smart kitchen and bathroom equipment, a smart bathroom equipment, a smart sweeping robot, a smart window cleaning robot, a smart mopping robot, a smart air purification equipment, a smart steamer, a smart microwave oven, a smart kitchen treasure, a smart purifier, a smart water dispenser, a smart door lock, etc.

[0045] For example, when a user issues a voice command to the smart water heater in the kitchen to turn on the smart washing machine, if the smart water heater does not know the current working status of the smart washing machine in advance, or does not consider the specific location of the smart washing machine in the room, and directly sends a "turn on" command, then this may cause the voice command processing to fail.

[0046] Therefore, how to ensure that the voice commands sent by users can be accurately recognized and processed is an urgent problem to be solved.

[0047] The present application provides a cross-space voice processing method, which obtains a target voice command sent by a user in a first space, and after determining that the first device cannot execute the operation function corresponding to the target voice command based on the target voice command, first, according to the function database and environmental information, determines a second device that can execute the operation function, and determines the target space where it is located. Subsequently, when it is determined that the second device is located in a second space different from the first space, the target voice command is sent to the second device through a communication network. This method not only ensures that the voice commands sent by the user can be accurately recognized and processed, but also ensures that the user is no longer restricted by the physical location of the device, and can control and manage their devices through voice commands anytime and anywhere, thereby enhancing the accuracy of interaction between multiple devices, thereby improving the user experience and satisfaction.

[0048] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0049] Figure 1 The process of the cross-space speech processing method provided in this embodiment Figure 1 . Applied to the first device. Figure 1 As shown, the cross-space speech processing method provided by this embodiment includes:

[0050] S101: Acquire a target voice command sent by a user in a first space.

[0051] The first space includes but is not limited to the living room of the user's home, and may also be a bedroom, bathroom, kitchen, etc. The first device includes but is not limited to a smart speaker. Those skilled in the art will appreciate that if multiple first devices are set in the first space, the multiple first devices compete in advance to determine which first device is the master control device.

[0052] If there is only one device in the space, the device can be directly determined as the master device.

[0053] By obtaining the target voice command sent by the user, it means that the user's intention can be obtained.

[0054] The target voice command sent by the user may be obtained by, for example, the user speaking directly to a device with a voice function in the first space.

[0055] For example, if a user says "turn on the bedroom light" to the smart speaker in the living room, then the user's target voice command is "turn on the bedroom light".

[0056] Optionally, the present application provides an implementation method for determining which device is a master control device from multiple first devices, which is specifically as follows.

[0057] The first step: receiving a job competition instruction sent by the control terminal, wherein the job competition instruction is used to instruct devices in the same space to compete for the role of the master device.

[0058] The control end may be, for example, a user end or a server, and this application does not impose any special restrictions on this.

[0059] The job competition instruction is used to trigger multiple first devices in the first space to compete for roles. Therefore, when multiple first devices in the first space receive the job competition instruction sent by the control end, they will participate in a competition process so that the control end can determine which device is most suitable for the role of the master device.

[0060] For example, if the server is used as the control end, when the user is in the living room, there are many smart devices in the living room, including smart speakers, smart light bulbs, smart air conditioners, smart sockets, smart sweeping robots, and smart mopping robots. These devices can receive the job competition instructions issued by the server and start competing to become the master control device.

[0061] Step 2: Send the performance information of the first device to the control end, so that the control end selects a master control end based on the performance information.

[0062] Among them, when multiple first devices in the first space receive job competition instructions sent by the control end, these devices will respectively send their performance information to the control end, such as device name, device processing capability, and network connection status, so that the control end can determine the device that is most suitable to serve as the main control device from these devices.

[0063] For example, if the user end is the control end, and it is known that there are multiple smart devices in the living room, including smart speakers, smart light bulbs, smart air conditioners, smart sockets, smart sweeping robots, and smart mopping robots, then these devices will send their corresponding performance information to the user end after receiving the job competition instruction sent by the user end.

[0064] Step 3: Receive the election result sent by the control terminal, where the election result is used to indicate that the first device is the master control terminal.

[0065] Among them, multiple first devices in the first space can know which device among them is selected as the main control device by receiving the election result sent by the control terminal, so that devices that are not selected as the main control terminal can clearly cooperate or communicate with the main control device.

[0066] For example, if the server is used as the control end, when the server determines that the smart speaker is the main control device based on the device information sent by all devices in the first space, the server will send the election result of the smart speaker to all devices in the living room, including smart speakers, smart light bulbs, smart air conditioners, smart sockets, smart sweeping robots, and smart mopping robots, so that all devices in the living room know that the current main control device is the smart speaker.

[0067] S102: Recognize and process the target voice instruction to obtain an operation function to be executed.

[0068] The purpose of this step of recognizing and processing the target voice command is to obtain the operation function to be executed that the user expects.

[0069] It can be understood that the target voice command is usually in the form of natural language. The target voice command is converted into text through recognition processing, and then the user's desired operation function to be executed is obtained through text recognition or semantic recognition.

[0070] For example, if the target voice command sent by the user is "turn on the smart TV in the living room", then the operation function to be executed is "turn on the smart TV".

[0071] S103: If it is determined that the first device cannot execute the operation function to be executed, obtain a function database and environmental information, wherein the function database is used to store the correspondence between the operation function and the device, and the environmental information is used to indicate the space where each device pre-stored by the user is located.

[0072] It is understandable that in a smart home scenario, each device plays a specific role and has corresponding operating functions. For example, a smart speaker can play music and check the weather, while a smart air conditioner can adjust the indoor temperature and humidity. At the same time, these operating functions often vary depending on the type and configuration of the device. For example, a high-end smart air conditioner may have more sophisticated temperature adjustment and air purification functions. Therefore, after obtaining the operating function to be executed, it is necessary to determine whether the first device has the ability to execute the operating function to be executed.

[0073] If the first device cannot perform the operation function to be performed, the function database and the environment information are obtained. If the first device can perform the operation function to be performed, the first device performs the operation function to be performed locally.

[0074] S104: Determine, according to the function database and the environmental information, a second device that can execute the operation function and a target space where the second device is located.

[0075] The purpose of this step is to obtain a device that can perform the operation function required by the user and the corresponding spatial position of the device.

[0076] In this step, for example, the second device that can execute the operation function can be determined first according to the function database, and then the target space where the second device is located can be determined from the environmental information according to the second device.

[0077] It is understandable that, since the function database stores the correspondence between each device and the operational function that it can perform, by querying the function database, the second device that can perform the operational function required by the user can be found.

[0078] In addition, since the environmental information includes the spatial location of each device pre-stored by the user, after obtaining a second device that can perform the operation function required by the user, you can continue to query the environmental information to find the target space where the second device is located, so that the target voice command can be executed smoothly.

[0079] S105: If it is determined according to the target space that the second device is located in a second space, the target voice instruction is sent to the second device through a communication network, wherein the first space and the second space are physically different spaces.

[0080] The purpose of determining whether the second device is located in the second space according to the target space is to determine whether the target voice instruction needs to be executed across spaces.

[0081] If it is determined according to the target space that the second device is not located in the second space, but is located in the same space as the first device, it indicates that the target voice instruction does not need to be executed across spaces. At this time, the first device enters a voice silent state.

[0082] Those skilled in the art can understand that, after receiving the target voice command, each device in the first space will determine whether to execute it by the local machine based on the operation function to be executed. If it is executed by the local machine, the target voice command will be directly executed to ensure that the target voice command sent by the user in the first space can be executed smoothly and efficiently. At this time, when the first device determines that the second device is in the same space as the local machine, it confirms that the second device can execute the target voice command by itself. At this time, the first device enters a voice silent state and stops subsequent processing flow.

[0083] If it is determined according to the target space that the second device is located in the second space, it indicates that the target voice command needs to be executed across spaces. At this time, the target voice command can be sent to the second device through the communication network.

[0084] For example, Figure 2 Provide a scenario diagram of cross-space speech processing Figure 1 .like Figure 2 As shown. The smart TV 21 in the living room 20 is connected to the smart light 71 in the corridor 70. For example, when a user stands in the living room 20 and says "turn on the light in the corridor" to the smart TV 21, the smart TV 21 will send the voice command to the smart light 71 through the communication network, so that the smart light 71 illuminates the user according to the voice command.

[0085] The cross-space voice processing method provided in this embodiment first obtains the target voice command issued by the user in the first space. Then, after determining that the first device cannot execute the operation function corresponding to the command, the second device that can execute the operation function is determined according to the function database and environmental information, and the target space where the second device is located is determined. Then, when it is determined that the second device is located in a second space different from the first space, the target voice command is sent to the second device through the communication network.

[0086] This method not only ensures that the voice commands issued by users can be accurately recognized and efficiently processed, but also breaks the spatial limitations of traditional device interaction. Users are no longer bound by the location of the device. No matter where they are, they can easily control and manage their devices with simple voice commands, thereby enhancing the accuracy of interaction between multiple devices and improving user experience and satisfaction.

[0087] Figure 3 The process of the cross-space speech processing method provided in this embodiment Figure 2 .like Figure 3 As shown, this embodiment is based on the above embodiment and describes in detail the cross-space speech processing method. The cross-space speech processing method provided by this embodiment includes:

[0088] S201: Obtain a target voice command sent by a user in a first space.

[0089] The explanation of step S201 is similar to that of the above step S101 and will not be repeated here.

[0090] S202: Convert the target voice instruction into text information.

[0091] It can be understood that voice commands exist in the form of natural language. By converting voice commands into text information, the command content can exist in a more structured and parseable form, thereby facilitating the analysis and processing of the target voice commands.

[0092] S203: Determine whether the text information includes device information; if so, execute step S205; if not, execute step S204.

[0093] S204: Perform semantic recognition on the text information to obtain an operation function to be executed.

[0094] S205: Determine, according to the device information, a second device that can execute the target voice command, and send the target voice command to the second device via a communication network.

[0095] Among them, the device information can uniquely identify the second device.

[0096] The purpose of judging whether the text information includes the device information is to determine whether the user has sent a voice command carrying the device information.

[0097] It is understandable that device information generally refers to an identifier or name that can uniquely identify a specific device, such as "bedroom lamp" or "living room air conditioner". If the text message contains such device information, the device that needs to execute the instruction can be identified based on this information.

[0098] Therefore, by determining whether device information is included in the text message, it can not only ensure that the user's voice command is accurately sent to the correct device, but also help avoid the target voice command being sent to the wrong device or causing unnecessary operations, thereby ensuring the smooth execution of the target voice command.

[0099] If the text information includes device information, it means that the user has sent a voice command carrying the device information. At this time, the second device that can execute the target voice command can be determined based on the device information, and the target voice command can be sent to the second device through the communication network.

[0100] If the text information does not include device information, or the device information cannot uniquely identify the second device, for example, if the user says "clothing processing", it may correspond to a washing machine or a dryer. Or if the user directly says "turn on the washing machine", and there are two washing machines in the space, then the text information is semantically recognized to obtain the operation function to be executed.

[0101] S206: Determine whether the first device is unable to execute the operation function to be executed; if so, execute step S207; if not, execute step S208.

[0102] S207: Acquire a function database and environment information, wherein the function database is used to store the correspondence between the operation function and the device, and the environment information is used to indicate the space where each device pre-stored by the user is located.

[0103] S208: The first device executes the operation function to be executed.

[0104] The purpose of this step is to meet the user's operational requirements for the first device.

[0105] It is understandable that when the user conveys his / her operation requirements to the first device through voice commands, the first device will quickly identify and analyze these commands. Once it is determined that it has the ability to execute these commands, the first device will immediately start the corresponding operation program and automatically execute the function requested by the user.

[0106] S209: Determine, based on the function database and the environmental information, a second device that can execute the operation function and a target space where the second device is located.

[0107] The explanation of step S209 is similar to that of the above step S104 and will not be repeated here.

[0108] S210: If it is determined according to the target space that the second device is located in a second space, the target voice command is sent to the second device through a communication network, wherein the first space and the second space are physically different spaces.

[0109] When it is determined that the second device is located in the second space and the second space is different from the first space, it is necessary to first determine whether the first device can directly control the second device. If so, directly control it. If not, send the target voice command to the second device through the communication network.

[0110] This embodiment provides a possible implementation method, which is as follows:

[0111] Step 1: Obtain a device control list, where the device control list is used to indicate second devices that can be controlled by the first device.

[0112] The purpose of obtaining the device control list is to determine which devices can be directly controlled by the first device.

[0113] It is understandable that the device control list records in detail the detailed information of other devices that the first device can control and manage, including but not limited to the unique identification, type classification and supported functions of the device. Therefore, when a second device that can perform an operation function is obtained, it is necessary to use the device control list to determine whether the first device can directly control the second device to perform the operation function to be performed.

[0114] Step 2: If the second device is in the device control list, control the second device to execute the operation function.

[0115] If the second device is in the device control list, it means that the second device can be directly controlled by the first device. At this time, the first device can control the second device to perform operating functions without transmitting the target voice command.

[0116] Step 3: If the second device is not in the device control list, determine whether the second device is located in the first space based on the target space. If so, the first device enters a voice silent state. If not, the target voice command is sent to the second device via the communication network.

[0117] If the second device is not in the device control list, it indicates that the second device cannot be directly controlled by the first device. At this time, it is first determined whether the second device is located in the first space according to the target space.

[0118] If it is determined according to the target space that the second device is located in the first space, it means that the target voice instruction does not need to be executed across spaces, other devices in the first space will execute the target voice instruction, and the first device enters a voice silent state.

[0119] If it is determined based on the target space that the second device is not located in the first space, it indicates that the target voice command needs to be executed across spaces. At this time, the target voice command can be sent to the second device through the communication network.

[0120] The cross-space voice processing method provided in this embodiment not only ensures that the voice commands sent by users can be accurately recognized and processed, but also ensures that users are no longer restricted by the physical location of the device and can control and manage their devices through voice commands anytime and anywhere, thereby improving the stickiness between users and smart home appliances, thereby improving the user experience and satisfaction.

[0121] Optionally, in a smart home scenario, since the user is in the first space, he or she usually cannot directly see or observe the specific execution status of the second device in the second space. Therefore, in order to ensure that the user can timely understand the execution status of the target voice command, it is also necessary to confirm and notify the user whether the second device has successfully executed the corresponding operation function based on the above embodiment. The specific implementation process is as follows:

[0122] The first step: receiving feedback information sent by the second device, where the feedback information is used to indicate that the second device has executed the operation function or the interaction statement between the second device and the user.

[0123] It is understandable that in a smart home system, the first device acts as a central control unit or communication hub, responsible for coordinating the interaction between the user and the second device. Since the user and the second device are not in the same space and cannot directly observe the execution of the second device, the first device needs to receive feedback information from the second device.

[0124] The feedback information may be an executed operation function. When the second device cannot clearly execute the function, it can interact with the user through the first device, and the second device feeds back an interaction statement.

[0125] Step 2: Convert the feedback information into feedback voice, and broadcast the feedback voice to the user.

[0126] If the feedback information is used to indicate an interaction statement between the second device and the user, the first device acts as a voice relay device to enable the second device to interact with the user.

[0127] The method provides an intuitive and easy-to-understand information feedback method for users by converting feedback information into feedback voice and broadcasting it to users, thereby avoiding the trouble of users having to personally check the status or execution results of the second device, thereby improving the interactive experience between users and the smart home system.

[0128] Figure 4 The process of the cross-space speech processing method provided in this embodiment Figure 3 .like Figure 4 As shown, this embodiment is based on the above embodiment, and describes in detail the implementation process of determining the second device that can execute the operation function and the target space where the second device is located. The cross-space voice processing method provided by this embodiment includes:

[0129] S301: Acquire candidate devices that can execute the operation function according to the operation function to be executed and the function database.

[0130] The purpose of this step is to find out from the function database a device that can perform the operation indicated by the target voice command.

[0131] It is understandable that the function database contains a directory of multiple devices and their corresponding functions. Therefore, when it is determined that the first device cannot directly perform the corresponding operation according to the user's target voice instruction, the operation function to be performed can be used as a query standard to search from the function database to obtain a device that can perform the operation function and use it as a candidate device.

[0132] For example, suppose the capability database contains the following devices and their corresponding capabilities:

[0133] Device name 1: Smart TV, whose functions include "turn on / off", "adjust volume" and "change channel".

[0134] Device name 2: Smart refrigerator, whose functions include "cooling" and "heating".

[0135] Device name 3: Smart light, whose functions include "turning the light on / off" and "adjusting the brightness".

[0136] If the operation function to be executed is "turn on the light", then by querying the function database, it can be found that the candidate device corresponding to the "turn on the light" operation is "Device Name 3: Smart Light".

[0137] S302: Acquire a space where each candidate device is located according to the environment information and the candidate devices.

[0138] It can be understood that since the environmental information contains the spatial location of each device pre-stored by the user, after obtaining the candidate device that can perform the operation function required by the user, the candidate device can be used as a query standard to search from the environmental information to obtain the spatial location of the candidate device.

[0139] For example, assume that the environment information includes the following devices and their corresponding spatial locations:

[0140] Device Name 1: Smart TV, located in the living room.

[0141] Device name 2: Smart refrigerator, located in the kitchen.

[0142] Device name 3: Smart light, located in the kitchen.

[0143] If the candidate device is determined to be "smart light", then by querying the environmental information, it can be found that the spatial location corresponding to the "smart light" is "kitchen".

[0144] For example, Figure 5 Provide a scenario diagram of cross-space speech processing Figure 2 .like Figure 5 As shown. The smart TV 21 in the living room 20 is connected to the smart light 41 in the dining room 40 and the smart light 71 in the corridor 70 respectively. At the same time, the smart light 41 in the dining room 40 is also connected to the smart light 71 in the corridor 70. For example, when a user stands in the living room 20 and says "turn on the light" to the smart TV 21, the smart TV 21 will take the smart light 41 and the smart light 71 as candidate devices at the same time, and determine that the space where the smart light 41 is located is the dining room 40, and the space where the smart light 71 is located is the corridor 70.

[0145] S303: Determine the number of candidate devices.

[0146] The purpose of determining the number of candidate devices in this step is to determine the total number of devices that can execute the operation function to be executed.

[0147] It is understandable that in a smart home scenario, a specific operation function may be supported by multiple devices. For example, multiple smart lights may have the function of "turning on the light". Therefore, by determining the number of all candidate devices that can perform the operation function, not only can the target voice command be successfully processed, but also the processing efficiency of processing the target voice command can be improved.

[0148] S304: If the candidate device is one device, use the candidate device as a second device, and obtain the target space where the candidate device is located.

[0149] The purpose of this step is to ensure that the user's target voice command can be accurately executed on the correct device to avoid confusion or errors.

[0150] It is understandable that in a smart home scenario, if it is determined that there is only one candidate device, then it can be considered that there is only one device that can complete the operation function to be performed. Therefore, it is necessary to directly determine the device as the second device and determine its corresponding target space.

[0151] S305: If the candidate devices are at least two devices, then when the at least two devices are not located in the first space, determine the second device and the target space where the second device is located among the at least two candidate devices based on the space where each candidate device is located and the number of times the first device sends historical voice commands to other devices.

[0152] Among them, in the smart home scenario, if it is determined that at least two devices can execute the operation function specified by the user, then it is necessary to select a device among these devices that is most suitable for executing the target voice command and determine it as the second device.

[0153] If at least two devices are not located in the first space, it indicates that the two devices do not execute the target voice command themselves. At this time, the second device and the target space where the second device is located can be determined from the at least two candidate devices according to the space where each candidate device is located and the number of times the first device sends historical voice commands to other devices.

[0154] The cross-space voice processing method provided in this embodiment first screens out candidate devices that can execute the operation function from the function database according to the operation function to be executed. Then, the spatial position of each candidate device is determined based on the environmental information and the candidate devices. Next, the number of candidate devices is determined. If there is only one candidate device, then the device will be directly determined as the second device, and the target space where it is located will be determined. On the contrary, if the number of candidate devices is at least two, then the most suitable second device will be selected based on the space where each candidate device is located and the number of times the first device sends historical voice commands to other devices, and the target space where it is located will be determined.

[0155] This method not only improves the efficiency and accuracy of device use, but also provides users with a more convenient device control experience. At the same time, by breaking the limitations of space, the method allows users to remotely control the device through voice commands at any location, thereby improving user satisfaction and usage experience.

[0156] Figure 6 The process of the cross-space speech processing method provided in this embodiment Figure 4 .like Figure 6 As shown, based on the above embodiment, this embodiment describes in detail the implementation process of determining the second device and the target space where the second device is located among the at least two candidate devices according to the space where each candidate device is located and the number of times the first device sends historical voice commands to other devices. The cross-space voice processing method provided by this embodiment includes:

[0157] S401: According to the space where each candidate device is located, obtain a spatial relationship between the space and the first space, where the spatial relationship includes an adjacent space or an interval space.

[0158] It can be understood that the spatial relationship is used to characterize the distance and accessibility between the candidate device and the space where the user is located. When the spatial relationship is an adjacent space, it can be considered that the device in the adjacent space is more relevant to the area where the user is currently active. For example, if the user requires to turn off the lights in the living room, the lights in the dining room or corridor adjacent to the living room will be preferentially controlled, rather than the lights in the bedroom or kitchen far away.

[0159] When the spatial relationship is an interval space, it can be considered that there is a distance between the interval space and the area where the user is currently active. For example, if the user requires the washing machine to be turned on in the bedroom, the washing machine in the balcony will be given priority for control.

[0160] Therefore, by comprehensively considering the spatial relationship between the space where each candidate device is located and the first space, a spatial processing priority can be set for each device, thereby ensuring that when multiple devices can respond to the same instruction, the most appropriate device will be intelligently selected according to these priorities to execute the instruction.

[0161] For example, Figure 7 Provide a scenario diagram of cross-space speech processing Figure 3 .like Figure 7As shown. The smart TV 21 in the living room 20 is connected to the smart light 41 in the dining room 40 and the smart light 62 in the master bedroom 60 respectively. At the same time, the smart light 41 in the dining room 40 can also be connected to the smart light 62 in the master bedroom 60. For example, when a user issues a voice command of "turn on the light" to the smart TV 21 in the living room 20, the smart TV 21 will regard the two smart lights 41 and 62 connected to it as optional operating devices. Then, the smart TV 21 will judge based on the spatial location (i.e., the living room 20) where the voice command is issued. Since the bathroom 30 separates the living room 20 from the dining room 40, the smart TV 21 recognizes that the dining room 40 is a separation space, and the master bedroom 60 is adjacent to the living room 20, and is therefore recognized as an adjacent space.

[0162] S402: Determine whether the at least two candidate devices are both located in adjacent spaces or spaced spaces; if so, execute step S403; if not, execute step S404.

[0163] S403: Determine the priority of each candidate device according to the number of times the first device sends historical voice commands to at least two candidate devices; wherein the priority is proportional to the number of times.

[0164] S404: Determine the priority of each candidate device according to the number of times the first device sends historical voice commands to at least two candidate devices, wherein the priority is proportional to the number of times. When the number of times corresponding to the candidate devices of the adjacent space and the interval space is the same, the priority of the adjacent space is higher than that of the interval space.

[0165] If at least two candidate devices are located in adjacent spaces or spaced spaces, it indicates that the spatial processing priorities of the candidate devices are consistent. At this time, the priority of each candidate device can be determined based on the number of times the first device sends historical voice commands to the at least two candidate devices.

[0166] If at least two candidate devices are partially located in adjacent spaces and partially located in separated spaces, it indicates that the spatial processing priorities of the candidate devices are inconsistent. At this time, the priority of each candidate device can be determined based on the spatial relationship and the number of times the first device sends historical voice commands to at least two candidate devices.

[0167] It can be understood that by analyzing the number of times the first device sends historical voice commands to each candidate device, the user's preferences and usage habits for each candidate device can be obtained, and thus the processing priority of each candidate device can be obtained based on the user's preferences and usage habits for each candidate device.

[0168] For example, if the first device frequently sends instructions to a certain device, it indicates that the user prefers to control this device. Therefore, if multiple devices can respond to the same voice command and are in the same space, this device will be selected as a high-priority candidate to execute the user's instructions.

[0169] When the spatial processing priorities of the candidate devices are consistent, the processing priorities of these devices are determined according to the number of times the first device sends historical voice commands to each candidate device. In this process, the more frequently a device is controlled, the higher its priority.

[0170] When the spatial processing priorities of the candidate devices are inconsistent, the number of times the first device sends historical voice commands to at least two candidate devices is considered first, and the higher the number, the higher the priority. When the number of times the devices in the adjacent space and the separated space are controlled is the same, the priority of the device in the adjacent space is higher than that of the device in the separated space, because it is usually more in line with the needs and habits of users and is easier to operate.

[0171] S405: Take the candidate device with the highest priority as the second device and obtain the target space where the second device is located.

[0172] It is understandable that the candidate device with the highest priority not only reflects the device that the user uses most frequently, but also represents the user's daily usage habits and preferences. Therefore, by selecting the device with the highest priority as the second device to execute the user's voice command, it can not only ensure that the user's command is responded to by the most appropriate device, but also conform to the user's regular operation mode, thereby improving the personalization and convenience of the user experience.

[0173] Optionally, after determining the second device, in order to ensure that the second device can be correctly controlled or a target voice command is sent to the second device, whether the second device is correct can be determined through a process of interaction with the user. This application provides a possible implementation method, which is as follows.

[0174] Step 1: Acquire the position of the second device in the target space according to the environmental information.

[0175] The environmental information is used to indicate the location of each device in the space.

[0176] The second step is to send feedback information to the user, where the feedback information is used to indicate the target space where the second device is located and the position in the target space.

[0177] It is understandable that when there are multiple devices with the same function in the target space, in order to ensure that the target voice command can accurately and correctly trigger the expected device action, it is necessary to send feedback information to the user in a timely manner so that the user can verify and confirm whether the second device executes the command. This can not only prevent the command from being executed by the wrong device, but also improve the user's trust and satisfaction with the operation of the smart home system.

[0178] The third step is to receive a voice response instruction input by the user, where the voice response instruction is used to instruct the second device to execute the target voice instruction.

[0179] By receiving voice response instructions input by the user, not only can the user confirm his or her intentions and expectations by himself or herself, but also the successful execution of the target voice instructions can be ensured, thereby improving the user's experience of the smart home system.

[0180] In the fourth step, if the voice response instruction is used to indicate that the second device cannot execute the target voice instruction, a new second device is re-determined based on the priority of the candidate devices, and feedback information is resent to the user until the received voice response instruction indicates that the new second device can execute the target voice instruction.

[0181] Among them, when the user's voice response instruction indicates that the currently selected second device cannot execute the target voice instruction, it means that the user does not want the second device to execute the target voice instruction. Therefore, in order to ensure that the target voice instruction sent can be executed smoothly, it is necessary to re-determine a new second device according to the priority order of the candidate devices from high to low, and re-send feedback information to the user until the received voice response instruction indicates that the new second device can execute the target voice instruction.

[0182] The cross-space voice processing method provided in this embodiment not only improves the accuracy of determining the device most suitable for executing the target voice command by comprehensively considering the positional relationship and historical usage records of the devices, but also improves the efficiency and accuracy of device interaction, thereby ensuring that user commands can be executed in a timely and correct manner.

[0183] Figure 8 The process of the cross-space speech processing method provided in this embodiment Figure 5 .like Figure 8 As shown, based on the above embodiment, in order for the first device and the second device to communicate normally, the first device of the present application will also interact with the second device to obtain the communication status. The method specifically includes:

[0184] S501: Send detection information to the second device through the communication network, where the detection information is used to detect whether the first device and the second device can communicate; if so, execute step S503; if not, execute step S502.

[0185] S502: Determine a new second device according to the priority.

[0186] S503: Send status request information to the second device through the communication network.

[0187] Understandably, in a smart home scenario, the communication connection between devices is not always stable due to improper device settings, permission restrictions, network failures or other technical problems. Therefore, sending detection information to the second device through the communication network can not only ensure smooth interaction between devices, but also reduce the risk of voice command processing failure due to network problems.

[0188] If it is determined that the first device and the second device cannot communicate, it means that the second device does not allow the first device to connect. At this time, a new second device can be determined according to the priority.

[0189] If it is determined that the first device and the second device can communicate, it means that the second device allows the first device to connect. At this time, status request information can be sent to the second device through the communication network.

[0190] Understandably, in a smart home scenario, after confirming that the communication link with the second device is unimpeded, the first device still needs to further understand the current working status of the second device. Because the normality of the communication link alone cannot guarantee the effective execution of instructions, the working status of the device is also crucial.

[0191] Therefore, in order to avoid the instruction becoming invalid due to the second device being in a non-working or abnormal state, the first device needs to actively send a status request message to the second device to obtain its current working status information.

[0192] S504: Receive status response information fed back by the second device, where the status response information is used to indicate the current status of the second device and whether the current status can be interrupted to execute a new operation function.

[0193] Among them, by receiving the status response information fed back by the second device, the first device can not only obtain detailed information about the current working status of the second device, but also understand whether the status is allowed to be interrupted to execute a new operating function.

[0194] It is understandable that in a smart home scenario, the state of a device may change due to a variety of factors, such as user instructions, scheduled tasks, or automatic responses to environmental changes. Therefore, by receiving the state response information fed back by the second device, the first device can not only obtain the current state of the second device in real time, such as whether it is in standby, working, sleeping or other specific modes, but also understand whether the state allows interruption to execute new operating functions, thereby facilitating the successful execution of the target voice command.

[0195] S505: Determine whether the current state can be interrupted to execute a new operation function; if so, execute step S506; if not, execute step S502.

[0196] S506: Determine to execute an operation of sending a target voice instruction to the second device.

[0197] If the current state of the second device can be interrupted to execute a new operation function, it means that the first device can send the target voice instruction to the second device. At this time, it can be determined to execute the operation of sending the target voice instruction to the second device.

[0198] For example, Fig. 9 Provide a scenario diagram of cross-space speech processing Figure 4 .like Fig. 9 As shown. The smart TV 21 in the living room 20 is connected to the smart refrigerator 42 in the dining room 40. For example, when a user stands in the dining room 40 and sends a voice command "turn on the TV in the living room" to the smart refrigerator 42, the smart refrigerator 42 will first send detection information to the smart TV 21; then, when it is determined that the smart TV 21 and the smart refrigerator 42 can communicate normally, the smart refrigerator 42 will further send status request information to the smart TV 21. After receiving the status response information fed back by the smart TV 21, if the smart refrigerator 42 knows that the smart TV 21 is not currently in standby mode, it will send a voice command "turn on the TV" to the smart TV 21.

[0199] If the current state of the second device cannot be interrupted to perform a new operation function, it means that the first device cannot send the target voice command to the second device, and a new second device can be determined according to the priority. For example, if the washing machine is washing clothes and the program cannot be interrupted, the second device needs to be re-determined.

[0200] The cross-space voice processing method provided in this embodiment, after determining the second device and the target space where it is located, will first send detection information to the second device through the communication network to verify whether the communication between the first device and the second device is smooth. If the communication is normal, a status request message will be sent to the second device to obtain its current operating status. Subsequently, the status response information fed back by the second device is received, and it is determined whether its current status allows interruption to execute a new operating function. If the status of the second device allows interruption, then it is determined that the first device can send the target voice command operation to the second device. On the contrary, if the communication is not smooth or the status of the second device does not allow interruption, then a new second device is reselected according to the previously determined device priority. This method not only improves the efficiency and accuracy of device interaction, but also avoids the failure of command execution due to inappropriate device status or poor communication, thereby improving the user experience and satisfaction.

[0201] Fig.10 This is a schematic diagram of the structure of the cross-space speech processing device provided by this application. Fig.10 As shown, the present application provides a cross-space speech processing device, and the cross-space speech processing device 600 includes:

[0202] An acquisition module 601 is used to acquire a target voice command sent by a user in the first space;

[0203] The processing module 602 is used to recognize and process the target voice command to obtain an operation function to be executed;

[0204] The acquisition module 601 is further used to acquire a function database and environment information when it is determined that the first device cannot execute the operation function to be executed, wherein the function database is used to store the correspondence between the operation function and the device, and the environment information is used to indicate the space where each device pre-stored by the user is located;

[0205] A determination module 603 is used to determine, according to the function database and the environment information, a second device that can execute the operation function and a target space where the second device is located;

[0206] The sending module 604 is used to send the target voice instruction to the second device through a communication network when it is determined that the second device is located in a second space according to the target space, wherein the first space and the second space are physically different spaces.

[0207] Fig.11 This is a schematic diagram of the structure of the cross-space speech processing device provided by this application. Fig.11As shown, the present application provides a cross-space speech processing device, and the cross-space speech processing device 700 includes: a receiver 701, a transmitter 702, a processor 703 and a memory 704.

[0208] Receiver 701, for receiving instructions and data;

[0209] A transmitter 702, used to send instructions and data;

[0210] Memory 704, for storing computer-executable instructions;

[0211] The processor 703 is used to execute the computer-executable instructions stored in the memory 704 to implement the various steps performed by the cross-space speech processing method in the above embodiment. For details, please refer to the relevant description in the above cross-space speech processing method embodiment.

[0212] Optionally, the memory 704 may be independent or integrated with the processor 703 .

[0213] When the memory 704 is independently provided, the electronic device further includes a bus for connecting the memory 704 and the processor 703 .

[0214] The present application also provides a computer-readable storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, a cross-space speech processing method as performed by the above-mentioned cross-space speech processing device is implemented.

[0215] The present application also provides a computer program product, including a computer program, which implements the cross-space speech processing method as described above when executed by a processor.

[0216] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In hardware implementations, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or transient medium). As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0217] So far, the technical solution of the present application has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments, and the above embodiments are only used to illustrate the technical solution of the present application rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A cross-space speech processing method, characterized in that: Applied to a first device, the method includes: Obtaining a target voice command sent by a user in the first space; Recognize and process the target voice command to obtain an operation function to be executed; If it is determined that the first device cannot execute the operation function to be executed, obtaining a function database and environment information, wherein the function database is used to store the correspondence between the operation function and the device, and the environment information is used to indicate the space where each device pre-stored by the user is located; Determine, according to the function database and the environment information, a second device capable of executing the operation function and a target space in which the second device is located; If it is determined according to the target space that the second device is located in a second space, the target voice instruction is sent to the second device through a communication network, wherein the first space and the second space are physically different spaces.

2. The method according to claim 1, characterized in that The determining, according to the function database and the environment information, a second device capable of executing the operation function and a target space in which the second device is located includes: Acquire a candidate device that can execute the operation function according to the operation function to be executed and the function database; Acquire a space where each candidate device is located according to the environment information and the candidate device; According to the space where each candidate device is located, a second device that can execute the operation function and a target space where the second device is located are determined.

3. The method according to claim 2, characterized in that The determining, according to the space where each candidate device is located, a second device that can execute the operation function and a target space where the second device is located, includes: If the candidate device is a device, the candidate device is used as a second device, and a target space where the candidate device is located is obtained; If the candidate devices are at least two devices, when the at least two devices are not located in the first space, the second device and the target space where the second device is located are determined from the at least two candidate devices based on the space where each candidate device is located and the number of times the first device sends historical voice commands to other devices.

4. The method according to claim 3, characterized in that The determining, according to the space where each candidate device is located and the number of times the first device sends historical voice commands to other devices, the second device and the target space where the second device is located from among the at least two candidate devices comprises: According to the space where each candidate device is located, obtaining a spatial relationship between the space and the first space, where the spatial relationship includes an adjacent space or an interval space; If the at least two candidate devices are located in adjacent spaces or spaced spaces, determining the priority of each candidate device according to the number of times the first device sends historical voice commands to the at least two candidate devices; wherein the priority is proportional to the number of times; The candidate device with the highest priority is used as the second device and the target space where the second device is located is obtained.

5. The method according to claim 4, characterized in that The method further comprises: If the at least two candidate devices are partially located in the adjacent space and partially located in the interval space, the priority of each candidate device is determined according to the number of times the first device sends historical voice commands to the at least two candidate devices, wherein the priority is proportional to the number of times, and when the number of times corresponding to the candidate devices in the adjacent space and the interval space is the same, the priority of the adjacent space is higher than that of the interval space; The candidate device with the highest priority is used as the second device and the target space where the second device is located is obtained.

6. The method according to claim 4 or 5, characterized in that: The environmental information is also used to indicate the location of each device in the space. Before sending the target voice command to the second device through the communication network, the method further includes: Acquire the position of the second device in the target space according to the environmental information; Sending feedback information to the user, where the feedback information is used to indicate the target space where the second device is located and the position of the second device in the target space; A voice response instruction input by a user is received, where the voice response instruction is used to instruct the second device to execute the target voice instruction.

7. The method according to claim 6, characterized in that The method further comprises: If the voice response instruction is used to indicate that the second device cannot execute the target voice instruction, a new second device is re-determined based on the priority of the candidate devices, and feedback information is resent to the user until the received voice response instruction indicates that the new second device can execute the target voice instruction.

8. The method according to claim 1, characterized in that The step of recognizing and processing the target voice command to obtain an operation function to be executed includes: Converting the target voice command into text information; Determining whether the text information includes device information, wherein the device information can uniquely identify the second device; If the device information is not included, semantic recognition is performed on the text information to obtain the operation function to be executed; If the device information is included, a second device that can execute the target voice command is determined based on the device information, and the target voice command is sent to the second device through a communication network.

9. The method according to claim 4 or 5, characterized in that: Before sending the target voice instruction to the second device via the communication network, the method further includes: Sending detection information to the second device through the communication network, where the detection information is used to detect whether the first device and the second device can communicate; If it is determined that the first device and the second device cannot communicate, a new second device is determined according to the priority.

10. The method according to claim 9, characterized in that If the first device and the second device can communicate, the method further includes: sending status request information to the second device via the communication network; receiving status response information fed back by the second device, where the status response information is used to indicate a current status of the second device and whether the current status can be interrupted to execute a new operation function; Determining whether the current state can be interrupted to execute a new operation function; If yes, determine to execute the operation of sending the target voice command to the second device; If not, a new second device is determined according to the priority.

11. The method according to claim 10, characterized in that After sending the target voice instruction to the second device via the communication network, the method further includes: receiving feedback information sent by the second device, where the feedback information is used to indicate that the second device has executed the operation function or an interaction statement between the second device and the user; Converting the feedback information into feedback voice, and broadcasting the feedback voice to the user; If the feedback information is used to indicate an interaction statement between the second device and the user, the first device acts as a voice relay device to enable the second device to interact with the user.

12. The method according to claim 1, characterized in that After determining the second device that can perform the operation function, the method further includes: Acquire a device control list, where the device control list is used to indicate a second device that can be controlled by the first device; If the second device is in the device control list, controlling the second device to perform the operation function; If the second device is not in the device control list, determine whether the second device is located in the first space based on the target space. If so, the first device enters a voice silent state. If not, the target voice command is sent to the second device through the communication network.

13. The method according to claim 1, characterized in that Before acquiring the target voice command sent by the user in the first space, the method further includes: Receiving a job competition instruction sent by a control terminal, wherein the job competition instruction is used to instruct devices in the same space to compete for the role of a master control device; Sending the performance information of the first device to the control end, so that the control end selects a master control end based on the performance information; An election result sent by the control end is received, where the election result is used to indicate that the first device is a master control end.

14. A cross-space speech processing device, characterized in that: include: An acquisition module, used to acquire a target voice command sent by a user in the first space; A processing module, used to recognize and process the target voice command to obtain an operation function to be executed; The acquisition module is further configured to acquire a function database and environment information when it is determined that the first device cannot execute the operation function to be executed, wherein the function database is used to store the correspondence between the operation function and the device, and the environment information is used to indicate the space where each device pre-stored by the user is located; a determination module, configured to determine, according to the function database and the environment information, a second device capable of executing the operation function and a target space in which the second device is located; A sending module is used to send the target voice instruction to the second device through a communication network when it is determined that the second device is located in a second space according to the target space, wherein the first space and the second space are physically different spaces.

15. A cross-space speech processing device, characterized in that: include: Memory; processor; Wherein, the memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the cross-space speech processing method according to any one of claims 1-13.

16. A computer storage medium, characterized in that: The computer storage medium stores computer execution instructions, which, when executed by a processor, are used to implement the cross-space speech processing method according to any one of claims 1 to 13.