A user-configurable distributed wake-up method, device and electronic device

Abstract

The present invention provides a user-configurable distributed wake-up method, device and electronic device, which are applied to the field of Internet of Things technology. After obtaining the wake-up instruction of the user, the wake-up scores and the first semantic analysis result feedback by each terminal device within a preset distance range, the candidate terminal devices are determined among the terminal devices according to the expected wake-up device list, and the wake-up instruction is semantically analyzed to obtain the second semantic analysis result. Then, the matching degrees of the first semantic analysis result and the second semantic analysis result of each candidate terminal device are calculated respectively. Finally, the candidate terminal device with the highest matching degree is used as the target terminal device, and the target terminal device is woken up. Compared with the prior art, the selection of the terminal device in the present invention is more strict and has more reference bases, so the accuracy of waking up the device can be effectively improved to meet the actual application requirements.

Description

Technical Field

[0001] The present invention belongs to the technical field of the Internet of Things, and particularly relates to a user-configurable distributed wake-up method, device, and electronic device. Background Art

[0002] Distributed wake-up mainly aims at the situation where multiple AI voice terminal devices are deployed in a local space at the same time. When the user controls one or some of the terminal devices to act through a voice command, it can avoid all the terminal devices responding simultaneously when the user issues a voice command, resulting in the phenomenon of "responding to every call".

[0003] In the existing distributed wake-up method, after the user issues a voice command, each terminal device in the listening state calculates the energy of the voice signal and feeds the corresponding voice signal energy back to the AI voice platform. The AI voice platform further determines the distance between the terminal device and the user according to the voice signal energy of each terminal device. The greater the energy, the closer the terminal device is considered to be to the user, so as to preferentially wake up the terminal device with the largest voice signal energy.

[0004] However, in application scenarios such as smart home experience stores or device sales venues, due to a large number of terminal devices with voice control functions being densely placed, the voice signal energies fed back by each terminal device are very close or even the same. Based on the magnitude of the voice signal energy in the prior art, it is no longer possible to accurately wake up the device expected to be woken up by the user, and it is difficult to meet the application requirements. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a user-configurable distributed wake-up method and device, which can improve the accuracy of device wake-up and meet the actual application requirements. The specific solutions are as follows:

[0006] In the first aspect, the present invention provides a user-configurable distributed wake-up method, including:

[0007] Obtain a wake-up command of the user, wake-up scores and a first semantic analysis result fed back by each terminal device within a preset distance range;

[0008] Wherein, the wake-up score is determined by the terminal device based on the wake-up command; the first semantic analysis result is the semantic analysis result of the wake-up command by the terminal device;

[0009] Determine candidate terminal devices among each of the terminal devices according to the expected wake-up device list;

[0010] Wherein, the expected wake-up device list is configured by the user and records the terminal devices expected to be woken up;

[0011] Perform semantic analysis on the wake-up command to obtain a second semantic analysis result;

[0012] Calculate the matching degrees between the first semantic analysis results and the second semantic analysis results of each of the candidate terminal devices respectively;

[0013] Take the candidate terminal device with the highest matching degree as the target terminal device;

[0014] Wake up the target terminal device.

[0015] Optionally, the calculating the matching degrees between the first semantic analysis results and the second semantic analysis results of each of the candidate terminal devices respectively includes:

[0016] Obtain the preset weights of each of the candidate terminal devices;

[0017] For each of the candidate terminal devices, determine the total wake-up score of the candidate terminal device according to the preset weight and the wake-up score of the candidate terminal device;

[0018] Arrange the candidate terminal devices in descending order of the total wake-up scores;

[0019] For each of the first N candidate terminal devices, calculate the matching degree between the first semantic analysis result and the second semantic analysis result of the candidate terminal device;

[0020] where N≥1.

[0021] Optionally, the determining the total wake-up score of the candidate terminal device according to the preset weight and the wake-up score of the candidate terminal device includes:

[0022] Take the sum of the preset weight and the wake-up score of the candidate terminal device as the total wake-up score of the candidate terminal device;

[0023] Or,

[0024] Take the product of the preset weight and the wake-up score of the candidate terminal device as the total wake-up score of the candidate terminal device.

[0025] Optionally, if there are multiple candidate terminal devices with the highest matching degree, the taking the candidate terminal device with the highest matching degree as the target terminal device includes:

[0026] Take each of the candidate terminal devices with the highest matching degree as a primary selection terminal device respectively;

[0027] Take the primary selection terminal device with the highest sum of the matching degree and the wake-up score among the primary selection terminal devices as the target terminal device.

[0028] Optionally, the waking up the target terminal device includes:

[0029] Generate a control instruction based on the control actions included in the second semantic analysis result;

[0030] Send the control instruction to the target terminal device.

[0031] Optionally, the expected wake-up device list records the device identifiers of the terminal devices expected to be woken up;

[0032] The determining the candidate terminal devices among the terminal devices according to the expected wake-up device list includes:

[0033] Obtain the device identifiers of the terminal devices;

[0034] Use the terminal devices whose device identifiers are recorded in the expected wake-up device list as candidate terminal devices.

[0035] Optionally, the user-configurable distributed wake-up method provided in the first aspect of the present invention further includes:

[0036] Obtain a list maintenance instruction;

[0037] Edit the expected wake-up device list according to the list maintenance instruction.

[0038] In a second aspect, the present invention provides a user-configurable distributed wake-up device, including:

[0039] A first acquisition unit, configured to acquire a wake-up instruction of a user, wake-up scores fed back by each terminal device within a preset distance range, and a first semantic analysis result;

[0040] Wherein, the wake-up score is determined by the terminal device based on the wake-up instruction; the first semantic analysis result is the semantic analysis result of the wake-up instruction by the terminal device;

[0041] A first determination unit, configured to determine candidate terminal devices among the terminal devices according to the expected wake-up device list;

[0042] Wherein, the expected wake-up device list is configured by the user and records the terminal devices expected to be woken up;

[0043] An analysis unit, configured to perform semantic analysis on the wake-up instruction to obtain a second semantic analysis result;

[0044] A calculation unit, configured to calculate the matching degrees between the first semantic analysis results of the candidate terminal devices and the second semantic analysis result respectively;

[0045] A second determination unit, configured to use the candidate terminal device with the highest matching degree as the target terminal device;

[0046] A wake-up unit for waking up the target terminal device.

[0047] Optionally, the calculation unit is configured to calculate the matching degrees between the first semantic analysis results and the second semantic analysis results of the candidate terminal devices respectively, including:

[0048] Obtain the preset weights of the candidate terminal devices;

[0049] For each candidate terminal device, determine the total wake-up score of the candidate terminal device according to the preset weight and the wake-up score of the candidate terminal device;

[0050] Arrange the candidate terminal devices in descending order of the total wake-up scores;

[0051] For each of the top N candidate terminal devices, calculate the matching degree between the first semantic analysis result and the second semantic analysis result of the candidate terminal device;

[0052] where N≥1.

[0053] In a third aspect, the present invention provides an electronic device, including: a memory and a processor; the memory stores a program suitable for the processor to execute to implement the user-configurable distributed wake-up method according to any one of the first aspects of the present invention.

[0054] After obtaining the wake-up instruction of the user, the wake-up scores and the first semantic analysis results fed back by the terminal devices within the preset distance range, the user-configurable distributed wake-up method provided by the present invention determines candidate terminal devices among the terminal devices according to the expected wake-up device list, performs semantic analysis on the wake-up instruction to obtain a second semantic analysis result, then calculates the matching degrees between the first semantic analysis results and the second semantic analysis results of the candidate terminal devices respectively, and finally uses the candidate terminal device with the highest matching degree as the target terminal device and wakes up the target terminal device.

[0055] The distributed wake-up method provided by the present invention only receives the information of the terminal devices within the preset distance range, performs a first screening on the terminal devices through the preset distance range. Further, the expected wake-up device list is configured by the user and records the terminal devices expected to be woken up. Only the terminal devices recorded in the expected wake-up device list are likely to be woken up, that is, a second screening is performed on the terminal devices according to the expected wake-up device list. Finally, a third screening is performed based on the matching degree of the semantic analysis results, and the terminal device with the highest matching degree is woken up. Compared with the prior art, the present invention is more strict in selecting terminal devices and has more reference bases, so it can effectively improve the accuracy of waking up devices and meet the actual application requirements. Description of the Drawings

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0057] Figure 1 is a flowchart of a user-configurable distributed wake-up method provided by an embodiment of the present invention;

[0058] Figure 2 is a structural block diagram of a user-configurable distributed wake-up device provided by an embodiment of the present invention;

[0059] Figure 3 is a structural block diagram of another user-configurable distributed wake-up device provided by an embodiment of the present invention;

[0060] Figure 4 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0061] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0062] The user-configurable distributed wake-up method provided by the present invention is applied to an AI voice device that can control multiple terminal devices with voice control functions. It can be understood that the AI voice device and the terminal devices to be controlled are in the same environmental space and can receive the voice issued by the user; referring to Figure 1 , the process of the user-configurable distributed wake-up method provided by the embodiment of the present invention may include:

[0063] S100. Obtain the wake-up instruction of the user, the wake-up scores and the first semantic analysis results fed back by each terminal device within a preset distance range.

[0064] As described above, the AI voice device applying the distributed wake-up method provided by the embodiment of the present invention and the terminal devices to be voice-controlled are in the same environmental space. When the user issues a wake-up instruction, both the AI voice device and the terminal devices can receive the corresponding wake-up instruction.

[0065] After power-on, the terminal devices at different positions in the aforementioned environmental space are always in a listening state and can obtain the user's wake-up instruction at any time. Further, after the user issues a voice instruction, the terminal device calculates a wake-up score based on the received voice instruction. The voice score can represent the voice signal energy of the voice instruction received by the terminal device and can also represent the distance between the terminal device and the user. The higher the wake-up score, the closer the distance between the terminal device and the user.

[0066] Further, after receiving the user's voice instruction, each terminal device also performs semantic analysis on the obtained voice instruction to determine the semantics included in the voice instruction and obtains the corresponding semantic analysis result. In this embodiment, the semantic analysis results of each terminal device are defined as the first semantic analysis results.

[0067] Since the distance that sound travels in the air is limited, the voice instruction issued by the user will become very weak and disappear after traveling a certain distance. Therefore, only the terminal devices within a certain range of the user can reliably receive the user's voice instruction. Based on this, when applying this method, the terminal devices expected to be awakened can be placed within a preset distance range, and correspondingly, the terminal devices not expected to be awakened can be placed outside the preset distance range, so as to achieve the first screening of the terminal devices through the preset distance range.

[0068] S110. Determine candidate terminal devices among all terminal devices according to the expected wake-up device list.

[0069] To perform the second screening of the terminal devices, the distributed wake-up method provided by the embodiment of the present invention pre-sets an expected wake-up device list, and this expected wake-up device list is configured by the user and is used to record the terminal devices expected to be awakened.

[0070] Taking a device store as an example, if the staff only hopes that the terminal devices related to cooking can be voice-awakened by consumers, a list maintenance instruction can be sent to the AI voice device. After the AI voice device obtains the list maintenance instruction, it can create and edit the expected wake-up device list according to the list maintenance instruction.

[0071] Optionally, the expected wake-up device list can specifically adopt the form of an array. In actual applications, each terminal device corresponds to a unique device identifier. Therefore, the device identifiers expected to be awakened can be added to the array to complete the addition of the devices expected to be awakened.

[0072] Of course, the editing of the expected wake-up list also includes operations such as deleting and replacing the terminal devices expected to be awakened in the list. Without exceeding the scope of the core idea of the present invention, it also belongs to the scope protected by the present invention.

[0073] Based on the above, obtain the device identifiers of each terminal device, query the expected wake-up device list, and record the terminal devices with their device identifiers in the expected wake-up device list as candidate terminal devices. For the terminal devices not recorded in the expected wake-up device list, they can be ignored, so as to implement the second screening of terminal devices based on the expected wake-up device list.

[0074] S120. Perform semantic analysis on the wake-up instruction to obtain the second semantic analysis result.

[0075] For an AI voice device applying the distributed wake-up method provided in an embodiment of the present invention, after obtaining a voice instruction, further perform semantic analysis on the wake-up instruction, and use the obtained semantic analysis result as the second semantic analysis result.

[0076] It should be noted that there is no strict restriction on the execution order of S120 and S110. In practical applications, S120 can be executed prior to S110, and they can also be executed simultaneously. In this embodiment, S120 is set after S110 only for the convenience of explaining the solution, and it is not a limitation on their execution order. Further, as for the specific implementation method of performing voice analysis on the wake-up instruction, it can be implemented based on the prior art, and the present invention does not make any limitation thereto.

[0077] S130. Calculate the matching degrees between the first semantic analysis result and the second semantic analysis result of each candidate terminal device respectively.

[0078] For each candidate terminal device, calculate the matching degree between the first semantic analysis result and the second semantic analysis result of this candidate terminal device to obtain the matching degrees corresponding to each candidate terminal device.

[0079] It can be understood that if the number of candidate terminal devices is large, calculating the matching degrees for each candidate terminal device one by one will inevitably consume a large amount of hardware resources, prolong the time-consuming of the entire device wake-up, and affect the user experience. Therefore, an embodiment of the present invention provides a method for further screening candidate terminal devices.

[0080] Specifically, set corresponding preset weights for each candidate terminal device, that is, the terminal devices in the expected wake-up device list. In practical applications, specific weight values can be set based on the specific placement positions of the candidate terminal devices. The present invention does not make any limitation on the specific values of the preset weights. Further, there are also various choices for the specific form of the preset weights. It can be embodied in the form of a proportional coefficient, or in the form of specific numerical values the same as the aforementioned wake-up scores.

[0081] Based on the foregoing settings, obtain the preset weights of each candidate terminal device, and then for each candidate terminal device, determine the total wake-up score of the candidate terminal device according to the preset weight and wake-up score of the candidate terminal device, and arrange the candidate terminal devices in descending order of the total wake-up score. Further, for each candidate terminal device among the top N candidate terminal devices, calculate the matching degree between the first semantic analysis result and the second semantic analysis result of the corresponding candidate terminal device. Of course, N≥1, and the specific value of N is determined according to the actual control accuracy requirements and device computing power.

[0082] Through the total wake-up score, most of the candidate terminal devices can be excluded, effectively reducing the number of terminal devices that need to calculate the semantic matching degree, and effectively improving the wake-up efficiency.

[0083] Optionally, when determining the total wake-up score of the candidate terminal device according to the preset weight and wake-up score of the candidate terminal device, it can be implemented in two forms. If the preset weight uses the same representation as the wake-up score, the sum of the preset weight and wake-up score of the candidate terminal device can be used as the total wake-up score of the candidate terminal device; if the preset weight is in the form of a proportional coefficient, the product of the preset weight and wake-up score of the candidate terminal device can be used as the total wake-up score of the candidate terminal device.

[0084] S140. Use the candidate terminal device with the highest matching degree as the target terminal device.

[0085] After obtaining the matching degrees corresponding to each candidate terminal device, the candidate terminal device with the highest matching degree among the candidate terminal devices can be used as the target terminal device.

[0086] Optionally, if there are multiple candidate terminal devices with the highest matching degree, that is, there are multiple candidate terminal devices with the same and highest matching degree, each candidate terminal device with the highest matching degree is used as a primary selection terminal device, and the primary selection terminal device with the highest sum of the matching degree and wake-up score among the primary selection terminal devices is used as the target terminal device. Of course, the terminal device with the highest wake-up score among the primary selection terminal devices can also be used as the target terminal device.

[0087] S150. Wake up the target terminal device.

[0088] The target terminal device is the finally determined terminal device that needs to be woken up. Based on the control actions included in the second semantic analysis result obtained in the foregoing steps, generate corresponding control instructions and send the control instructions to the target terminal device so that the target terminal device executes the corresponding control actions.

[0089] In summary, the user-configurable distributed wake-up method provided by the embodiments of the present invention only receives information from terminal devices within a preset distance range, and performs a first screening of the terminal devices through the preset distance range. Further, the expected wake-up device list is configured by the user and records the terminal devices expected to be woken up. Only the terminal devices recorded in the expected wake-up device list are likely to be woken up, that is, a second screening of the terminal devices is performed according to the expected wake-up device list. Finally, a third screening is performed based on the matching degree of the semantic analysis result, and the terminal device with the highest matching degree is woken up. Compared with the prior art, the selection of terminal devices in the present invention is more stringent and has more reference bases, so it can effectively improve the accuracy of waking up devices and meet the actual application requirements.

[0090] Further, the user can flexibly edit the expected wake-up device list according to their own control requirements, and then flexibly select the terminal devices to be woken up according to their own control requirements.

[0091] Furthermore, the distributed wake-up method provided in this embodiment can continuously reduce the number of terminal devices to be processed during the control process, and thus continuously reduce the amount of data that the AI voice device needs to process. It has a low computational load and can effectively reduce the hardware performance requirements for the AI voice device.

[0092] Next, the user-configurable distributed wake-up device provided by the embodiments of the present invention will be introduced. The user-configurable distributed wake-up device described below can be considered as the functional module architecture that needs to be set in the central device to implement the user-configurable distributed wake-up method provided by the embodiments of the present invention. The content described below can be referred to each other with the above content.

[0093] Optionally, refer to Figure 2 , Figure 2 which is a structural block diagram of a user-configurable distributed wake-up device provided by the embodiments of the present invention. The structure of the user-configurable distributed wake-up device provided in this embodiment may include:

[0094] A first acquisition unit 10, configured to acquire a wake-up instruction of the user, wake-up scores fed back by each terminal device within a preset distance range, and a first semantic analysis result;

[0095] Wherein, the wake-up score is determined by the terminal device based on the wake-up instruction; the first semantic analysis result is the semantic analysis result of the terminal device for the wake-up instruction;

[0096] A first determination unit 20, configured to determine candidate terminal devices among each terminal device according to the expected wake-up device list;

[0097] Wherein, the expected wake-up device list is configured by the user and records the terminal devices expected to be woken up;

[0098] An analysis unit 30, configured to perform semantic analysis on the wake-up instruction to obtain a second semantic analysis result;

[0099] A calculation unit 40, configured to calculate the matching degrees between the first semantic analysis results and the second semantic analysis result of each candidate terminal device respectively;

[0100] A second determination unit 50, configured to use the candidate terminal device with the highest matching degree as the target terminal device;

[0101] A wake-up unit 60, configured to wake up the target terminal device.

[0102] Optionally, the calculation unit 40, configured to calculate the matching degrees between the first semantic analysis results and the second semantic analysis result of each candidate terminal device, includes:

[0103] Obtain the preset weights of each candidate terminal device;

[0104] For each candidate terminal device, determine the total wake-up score of the candidate terminal device according to the preset weight and the wake-up score of the candidate terminal device;

[0105] Arrange the candidate terminal devices in descending order of the total wake-up score;

[0106] For each candidate terminal device among the top N candidate terminal devices, calculate the matching degree between the first semantic analysis result and the second semantic analysis result of the candidate terminal device;

[0107] Wherein, N≥1.

[0108] Optionally, the calculation unit 40, configured to determine the total wake-up score of the candidate terminal device according to the preset weight and the wake-up score of the candidate terminal device, includes:

[0109] Use the sum of the preset weight and the wake-up score of the candidate terminal device as the total wake-up score of the candidate terminal device;

[0110] Or,

[0111] Use the product of the preset weight and the wake-up score of the candidate terminal device as the total wake-up score of the candidate terminal device.

[0112] Optionally, if there are multiple candidate terminal devices with the highest matching degree, the second determination unit 50, configured to use the candidate terminal device with the highest matching degree as the target terminal device, includes:

[0113] Respectively use each candidate terminal device with the highest matching degree as a primary selection terminal device;

[0114] Use the primary selection terminal device with the highest sum of the matching degree and the wake-up score among the primary selection terminal devices as the target terminal device.

[0115] Optionally, the wake-up unit 60 is used to wake up the target terminal device, including:

[0116] Generating a control instruction based on the control actions included in the second semantic analysis result;

[0117] Sending the control instruction to the target terminal device.

[0118] Optionally, the expected wake-up device list records the device identifiers of the terminal devices expected to be woken up;

[0119] The first determination unit 20 is used to determine candidate terminal devices among the terminal devices according to the expected wake-up device list, including:

[0120] Obtaining the device identifiers of each terminal device;

[0121] Regarding the terminal devices whose device identifiers are recorded in the expected wake-up device list as candidate terminal devices.

[0122] Optionally, see Figure 3 , Figure 3 is the structural block diagram of another user-configurable distributed wake-up device provided by an embodiment of the present invention. On the basis of the embodiment shown in Figure 2 , it further includes:

[0123] The second acquisition unit 70 is used to acquire a list maintenance instruction;

[0124] The editing unit 80 is used to edit the expected wake-up device list according to the list maintenance instruction.

[0125] Figure 4 For the structural block diagram of the electronic device provided by an embodiment of the present invention, see Figure 4 shown, which may include: at least one processor 100, at least one communication interface 200, at least one memory 300, and at least one communication bus 400;

[0126] In the embodiments of the present invention, the number of the processor 100, the communication interface 200, the memory 300, and the communication bus 400 is at least one, and the processor 100, the communication interface 200, and the memory 300 complete mutual communication through the communication bus 400; obviously, Figure 4 the communication connection schematic diagram of the processor 100, the communication interface 200, the memory 300, and the communication bus 400 shown in

[0127] Optionally, the communication interface 200 may be the interface of a communication module, such as the interface of a GSM module;

[0128] The processor 100 may be a central processing unit (CPU), or a specific integrated circuit (ASIC) (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0129] The memory 300 stores application programs, which may include high-speed RAM memory and may also include non-volatile memory, such as at least one disk memory.

[0130] Specifically, the processor 100 is configured to execute the application programs in the memory to implement any of the embodiments of the user-configurable distributed wake-up method described above.

[0131] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the various embodiments, reference can be made to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple. For the relevant parts, reference can be made to the description in the method section.

[0132] Those skilled in the art can further realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed in this document can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0133] The steps of the methods or algorithms described in combination with the embodiments disclosed in this document can be directly implemented by hardware, software modules executed by a processor, or a combination of the two. The software modules can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field.

[0134] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the core idea or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather should be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A user-configurable distributed wake-up method, characterized in that Including: Obtaining a wake-up instruction of a user, wake-up scores and a first semantic analysis result fed back by each terminal device within a preset distance range; Wherein, the wake-up score is determined by the terminal device based on the wake-up instruction; the first semantic analysis result is the semantic analysis result of the wake-up instruction by the terminal device; the terminal devices are first screened through the preset distance range; Performing a second screening on each terminal device according to the expected wake-up device list, and determining candidate terminal devices among each of the terminal devices; Wherein, the expected wake-up device list is configured by the user and records the terminal devices expected to be woken up; Performing semantic analysis on the wake-up instruction to obtain a second semantic analysis result; Calculating the matching degree between the first semantic analysis result and the second semantic analysis result of each of the candidate terminal devices respectively, and performing a third screening on each terminal device based on the matching degree of the semantic analysis results; Taking the candidate terminal device with the highest matching degree as the target terminal device; Waking up the target terminal device.

2. The user-configurable distributed wake-up method according to claim 1, wherein The calculating the matching degree between the first semantic analysis result and the second semantic analysis result of each of the candidate terminal devices respectively includes: Obtaining the preset weight of each of the candidate terminal devices; For each of the candidate terminal devices, determining the total wake-up score of the candidate terminal device according to the preset weight and the wake-up score of the candidate terminal device; Arranging each of the candidate terminal devices in descending order of the total wake-up score; For each of the first N candidate terminal devices, calculating the matching degree between the first semantic analysis result and the second semantic analysis result of the candidate terminal device; Wherein, N≥1.

3. The user-configurable distributed wake-up method according to claim 2, wherein The determining the total wake-up score of the candidate terminal device according to the preset weight and the wake-up score of the candidate terminal device includes: Taking the sum of the preset weight and the wake-up score of the candidate terminal device as the total wake-up score of the candidate terminal device; Or, Taking the product of the preset weight and the wake-up score of the candidate terminal device as the total wake-up score of the candidate terminal device.

4. The user-configurable distributed wake-up method according to claim 2, wherein If there are multiple candidate terminal devices with the highest matching degree, the taking the candidate terminal device with the highest matching degree as the target terminal device includes: Taking each of the candidate terminal devices with the highest matching degree as a primary selection terminal device respectively; Taking the primary selection terminal device with the highest sum of the matching degree and the wake-up score among each of the primary selection terminal devices as the target terminal device.

5. The user-configurable distributed wake-up method according to claim 1, characterized in that The waking up the target terminal device includes: Generating a control instruction based on the control action included in the second semantic analysis result; Sending the control instruction to the target terminal device.

6. The user-configurable distributed wake-up method according to claim 5, characterized in that The device identifier of the terminal device expected to be woken up is recorded in the expected wake-up device list; The determining candidate terminal devices among each of the terminal devices according to the expected wake-up device list includes: Obtaining the device identifier of each of the terminal devices; Taking the terminal device whose device identifier is recorded in the expected wake-up device list as the candidate terminal device.

7. The user-configurable distributed wake-up method according to any one of claims 1-6, characterized in that, It further includes: Obtaining a list maintenance instruction; Editing the expected wake-up device list according to the list maintenance instruction.

8. A user-configurable distributed wake-up device, characterized in that, Including: A first acquisition unit, configured to acquire a wake-up instruction of a user, wake-up scores and a first semantic analysis result fed back by each terminal device within a preset distance range; Wherein, the wake-up score is determined by the terminal device based on the wake-up instruction; the first semantic analysis result is a semantic analysis result of the wake-up instruction by the terminal device; the terminal devices are first screened by the preset distance range; A first determination unit, configured to perform a second screening on each terminal device according to an expected wake-up device list, and determine candidate terminal devices among each of the terminal devices; Wherein, the expected wake-up device list is configured by the user and records the terminal devices expected to be woken up; An analysis unit, configured to perform semantic analysis on the wake-up instruction to obtain a second semantic analysis result; A calculation unit, configured to calculate the matching degrees between the first semantic analysis results of each of the candidate terminal devices and the second semantic analysis result respectively, and perform a third screening on each terminal device based on the matching degrees of the semantic analysis results; A second determination unit, configured to use the candidate terminal device with the highest matching degree as the target terminal device; A wake-up unit, configured to wake up the target terminal device.

9. The user-configurable distributed wake-up device according to claim 8, characterized in that, The calculation unit, configured to calculate the matching degrees between the first semantic analysis results of each of the candidate terminal devices and the second semantic analysis result respectively, includes: Obtaining preset weights of each of the candidate terminal devices; For each of the candidate terminal devices, determining a total wake-up score of the candidate terminal device according to the preset weight and the wake-up score of the candidate terminal device; Arranging each of the candidate terminal devices in descending order of the total wake-up score; For each of the first N candidate terminal devices, calculating the matching degree between the first semantic analysis result of the candidate terminal device and the second semantic analysis result; Wherein, N≥1.

10. An electronic device, characterized in that, Including: A memory and a processor; The memory stores a program suitable for execution by the processor to implement the user-configurable distributed wake-up method according to any one of claims 1 to 7.

Images