Smart home wake-up method and smart home platform

Abstract

The embodiment of the present application discloses a smart home wake-up method and a smart home platform, which belongs to the field of smart home technology. The method includes: the smart home platform receives wake-up words sent by N smart devices among M smart devices. If the similarity between the wake-up words collected by any two smart devices among the N smart devices exceeds the similarity threshold, the smart home platform sends a positioning request message to the user terminal, so that the user terminal sends a positioning response message to the smart home platform, and the positioning response message carries the location information indicating the user terminal collected by the user terminal based on UWB positioning technology. The smart home platform wakes up the first smart device from the N smart devices based on the positioning response message. The embodiment of the present application can accurately wake up the smart device based on UWB technology.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of smart home technology, and in particular to a smart home wake-up method and a smart home platform. Background Art

[0002] Nowadays, with the continuous development of science and technology, more and more smart devices appear in people's home life, providing convenience for people's home life. Usually, these smart devices have intelligent voice control function, that is, the smart devices are equipped with voice control portal and wake-up words. The smart devices collect user voice through the voice control portal, and then match the user voice with the wake-up words of the smart devices. If there is a smart device whose wake-up word matches the user voice, the smart device is used as the smart device to be awakened, and then the user voice is collected through the smart device and the operation indicated in the user voice is executed.

[0003] However, when the user's home has a brand set of products, that is, the user has multiple smart devices with voice control entrances and the same wake-up word, if the user issues a wake-up word to wake up and control a smart device A, all smart devices in the user's home will collect the user's voice and match the user's voice with the wake-up word. Since the wake-up words of smart devices of the same brand are the same, at this time, it may be another smart device B of the same brand that is awakened, or multiple smart devices of the same brand may be awakened at the same time. In this case, the awakening of smart device A may fail or conflict, affecting the user experience. Summary of the invention

[0004] The embodiment of the present application provides a smart home wake-up method and a smart home platform, which can solve the problem of the related art that the smart device cannot be accurately woken up. The technical solution is as follows:

[0005] On the one hand, a smart home wake-up method is provided, the method is executed by a smart home platform in an intelligent voice control system, the intelligent voice control system also includes a user terminal and M smart devices, the user terminal is a terminal currently held by the user, and M is a positive integer;

[0006] The method comprises:

[0007] The smart home platform receives wake-up words sent by N smart devices among the M smart devices, where N is a positive integer less than or equal to M, and N is greater than 1;

[0008] If the similarity between the wake-up words collected by any two of the N smart devices exceeds a similarity threshold, the smart home platform sends a positioning request message to the user terminal, so that the user terminal sends a positioning response message to the smart home platform, and the positioning response message carries the positioning data collected by the user terminal based on the ultra-wideband UWB positioning technology, and the positioning data indicates the location information of the user terminal;

[0009] The smart home platform wakes up a first smart device from among the N smart devices based on the positioning response message.

[0010] Optionally, after the smart home platform wakes up the first smart device from the N smart devices based on the positioning response message, the method further includes:

[0011] The smart home platform receives the voice data collected by the first smart device;

[0012] The smart home platform determines semantic information of the voice data;

[0013] The smart home platform determines description information of the smart device to be controlled based on the semantic information;

[0014] If the number of smart devices that conform to the description information among the M smart devices is one, the smart home platform controls the corresponding smart device based on the voice data.

[0015] Optionally, the method further comprises:

[0016] If there is more than one smart device among the M smart devices that matches the description information, the smart home platform determines a smart device closest to the user terminal from the multiple smart devices based on the positioning response message;

[0017] The smart home platform controls the smart device closest to the user terminal based on the voice data.

[0018] Optionally, the positioning response message carries multiple timestamp sets corresponding to multiple base stations one by one, the multiple base stations are smart devices whose positions remain unchanged among the N smart devices within a reference time period, the timestamp set corresponding to each base station in the multiple base stations includes a sub-timestamp set corresponding to each detection data packet in the multiple detection data packets, and the sub-timestamp set corresponding to each detection data packet includes a first sending timestamp, a first receiving timestamp, a second sending timestamp, and a second receiving timestamp, the first sending timestamp is the timestamp when the user terminal sends the corresponding detection data packet, the first receiving timestamp is the timestamp when the base station receives the corresponding detection data packet, the second sending timestamp is the timestamp when the base station sends a response data packet to the corresponding detection data packet, and the second receiving timestamp is the timestamp when the user terminal receives the response data packet;

[0019] The smart home platform wakes up the first smart device from the N smart devices based on the positioning response message, including:

[0020] For any base station among the multiple base stations, the smart home platform determines the distance between the any base station and the user terminal based on a sub-timestamp set included in a timestamp set corresponding to the any base station and corresponding to each detection data packet in a plurality of detection data packets;

[0021] The smart home platform determines the location information of the user terminal based on the distance between each of the multiple base stations and the user terminal and the location information of the multiple base stations;

[0022] The smart home platform determines and wakes up the first smart device from the N smart devices based on the location information of the user terminal and the location information of each of the N smart devices.

[0023] Optionally, the smart home platform determines the distance between any base station and the user terminal based on a sub-timestamp set included in a timestamp set corresponding to any base station and corresponding to each detection data packet in a plurality of detection data packets, including:

[0024] Selecting, from the multiple detection data packets, sub-timestamp sets corresponding to a first detection data packet and a second detection data packet, respectively, where the first detection data packet and the second detection data packet are two adjacent detection data packets sent by the user terminal;

[0025] Based on the sub-timestamp sets corresponding to the first detection data packet and the second detection data packet, respectively, a first duration, a second duration, a third duration and a fourth duration are determined, wherein the first duration is the duration from when the user terminal sends the first detection data packet to when a first response data packet corresponding to the first detection data packet is received, the second duration is the duration from when the user terminal receives the first response data packet to when the second detection data packet is sent, the third duration is the duration from when any base station receives the first detection data packet to when the first response data packet is sent, and the fourth duration is the duration from when any base station sends the first response data packet to when the second detection data packet is received;

[0026] Based on the first duration, the second duration, the third duration and the fourth duration, the flight time is determined by the following formula:

[0027]

[0028] Wherein, the T indicates the flight time, the Tround1 indicates the first duration, the Tround2 indicates the fourth duration, the Treply1 indicates the third duration, and the Treply2 indicates the second duration;

[0029] The product of the flight time and the speed of light is taken as the distance between any base station and the user terminal.

[0030] Optionally, the location information of the user terminal is the image coordinates of the user terminal in the living space image of the user, the location information of each smart device is the image coordinates of the corresponding smart device in the living space image of the user, the living space image of the user includes multiple image areas, and each image area indicates a location area corresponding to a room;

[0031] The smart home platform determines a first smart device from the N smart devices based on the location information of the user terminal and the location information of each smart device in the N smart devices, including:

[0032] Based on the location information of the user terminal and the location information of each of the N smart devices, selecting a smart device located in the same image area as the user terminal from the multiple image areas;

[0033] A smart device that is closest to the user terminal is selected from smart devices located in the same image area to obtain the first smart device.

[0034] Optionally, the method further comprises:

[0035] The smart home platform receives the living space image sent by the user terminal, where the living space image is marked with image coordinates of each of the multiple base stations and boundary image coordinates of each of the multiple image areas.

[0036] Optionally, the method further comprises:

[0037] If the similarity between the wake-up words collected by two smart devices among the N smart devices is lower than the similarity threshold, determine the wake-up word with the largest clarity index based on the wake-up words collected by each smart device among the N smart devices;

[0038] The smart device corresponding to the wake-up word with the largest clarity index is determined as the first smart device to be awakened.

[0039] On the other hand, a smart home platform is provided, wherein the smart home platform is a platform in an intelligent voice control system, wherein the intelligent voice control system further comprises a user terminal and M smart devices, wherein the user terminal is a terminal currently held by a user, and M is a positive integer;

[0040] The smart home platform includes a processor, and the processor is used to:

[0041] Receive a wake-up word sent by N smart devices among the M smart devices, where N is a positive integer less than or equal to M, and N is greater than 1;

[0042] If the similarity between the wake-up words collected by any two of the N smart devices exceeds the similarity threshold, a positioning request message is sent to the user terminal, so that the user terminal sends a positioning response message to the smart home platform, and the positioning response message carries the positioning data collected by the user terminal based on the ultra-wideband UWB positioning technology, and the positioning data indicates the location information of the user terminal;

[0043] A first smart device is awakened from the N smart devices based on the positioning response message.

[0044] Optionally, the processor is further configured to:

[0045] Receiving voice data collected by the first smart device;

[0046] Determining semantic information of the speech data;

[0047] Determining description information of the smart device to be controlled based on the semantic information;

[0048] If the number of smart devices that matches the description information among the M smart devices is one, the corresponding smart device is controlled based on the voice data.

[0049] Optionally, the processor is further configured to:

[0050] If there is more than one smart device among the M smart devices that meets the description information, determine the smart device closest to the user terminal from the multiple smart devices based on the positioning response message;

[0051] The smart device closest to the user terminal is controlled based on the voice data.

[0052] Optionally, the positioning response message carries multiple timestamp sets corresponding to multiple base stations one by one, the multiple base stations are smart devices whose positions remain unchanged among the N smart devices within a reference time period, the timestamp set corresponding to each base station in the multiple base stations includes a sub-timestamp set corresponding to each detection data packet in the multiple detection data packets, and the sub-timestamp set corresponding to each detection data packet includes a first sending timestamp, a first receiving timestamp, a second sending timestamp, and a second receiving timestamp, the first sending timestamp is the timestamp when the user terminal sends the corresponding detection data packet, the first receiving timestamp is the timestamp when the base station receives the corresponding detection data packet, the second sending timestamp is the timestamp when the base station sends a response data packet to the corresponding detection data packet, and the second receiving timestamp is the timestamp when the user terminal receives the response data packet;

[0053] The processor is further configured to:

[0054] For any base station among the multiple base stations, determine the distance between the any base station and the user terminal based on a sub-timestamp set included in a timestamp set corresponding to the any base station and corresponding to each detection data packet in a plurality of detection data packets;

[0055] Determine the location information of the user terminal based on the distance between each of the multiple base stations and the user terminal and the location information of the multiple base stations;

[0056] Based on the location information of the user terminal and the location information of each of the N smart devices, the first smart device is determined and awakened from the N smart devices.

[0057] Optionally, the processor is further configured to:

[0058] Selecting, from the multiple detection data packets, sub-timestamp sets corresponding to a first detection data packet and a second detection data packet, respectively, where the first detection data packet and the second detection data packet are two adjacent detection data packets sent by the user terminal;

[0059] Based on the sub-timestamp sets corresponding to the first detection data packet and the second detection data packet, respectively, a first duration, a second duration, a third duration and a fourth duration are determined, wherein the first duration is the duration from when the user terminal sends the first detection data packet to when a first response data packet corresponding to the first detection data packet is received, the second duration is the duration from when the user terminal receives the first response data packet to when the second detection data packet is sent, the third duration is the duration from when any base station receives the first detection data packet to when the first response data packet is sent, and the fourth duration is the duration from when any base station sends the first response data packet to when the second detection data packet is received;

[0060] Based on the first duration, the second duration, the third duration and the fourth duration, the flight time is determined by the following formula:

[0061]

[0062] Wherein, the T indicates the flight time, the Tround1 indicates the first duration, the Tround2 indicates the fourth duration, the Treply1 indicates the third duration, and the Treply2 indicates the second duration;

[0063] The product of the flight time and the speed of light is taken as the distance between any base station and the user terminal.

[0064] Optionally, the location information of the user terminal is the image coordinates of the user terminal in the living space image of the user, the location information of each smart device is the image coordinates of the corresponding smart device in the living space image of the user, the living space image of the user includes multiple image areas, and each image area indicates a location area corresponding to a room;

[0065] The processor is further configured to:

[0066] Based on the location information of the user terminal and the location information of each of the N smart devices, selecting a smart device located in the same image area as the user terminal from the multiple image areas;

[0067] A smart device that is closest to the user terminal is selected from smart devices located in the same image area to obtain the first smart device.

[0068] Optionally, the processor is further configured to:

[0069] The living space image sent by the user terminal is received, where the living space image is marked with image coordinates of each of the multiple base stations and boundary image coordinates of each of the multiple image areas.

[0070] Optionally, the processor is further configured to:

[0071] If the similarity between the wake-up words collected by two smart devices among the N smart devices is lower than the similarity threshold, determine the wake-up word with the largest clarity index based on the wake-up words collected by each smart device among the N smart devices;

[0072] The smart device corresponding to the wake-up word with the largest clarity index is determined as the first smart device to be awakened.

[0073] On the other hand, a computer-readable storage medium is provided, wherein a computer program is stored in the storage medium, and when the computer program is executed by a processor, the steps of the smart home wake-up method described above are implemented.

[0074] On the other hand, a computer program product comprising instructions is provided. When the instructions are executed on a computer, the computer executes the steps of the smart home wake-up method described above.

[0075] The technical solution provided by the embodiments of the present application can at least bring the following beneficial effects:

[0076] In an embodiment of the present application, the smart home platform receives the wake-up words sent by each smart device. If the similarity between the wake-up words sent by any two smart devices exceeds the similarity threshold, it indicates that the wake-up words collected by multiple smart devices are similar. At this time, the smart home platform cannot determine the device to be awakened. In this scenario, in order to clarify the device to be awakened, the smart home platform sends a positioning request message to the user terminal. After receiving the positioning request message, the user terminal collects positioning data based on the UWB positioning technology. The positioning data indicates the location information of the user terminal. In this way, the location information of the user terminal can be accurately determined based on the UWB technology. After obtaining the location information of the user terminal, a positioning response message carrying the location information of the user terminal is sent to the smart home platform. In this way, the smart home platform can accurately determine the first smart device from multiple smart devices based on the location information of the user terminal carried in the positioning response message. The first smart device is also the smart device to be awakened, thereby achieving the effect of accurately waking up the smart device. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0078] Figure 1 It is a schematic diagram of a system architecture provided by an embodiment of the present application;

[0079] Figure 2 is a schematic diagram of a living space image provided by an embodiment of the present application;

[0080] Figure 3 is an operation flow chart of a user terminal provided in an embodiment of the present application;

[0081] Figure 4 is a flow chart of a smart home wake-up method provided by an embodiment of the present application;

[0082] Figure 5 It is a sub-timestamp set diagram provided in an embodiment of the present application;

[0083] Figure 6 is a schematic diagram of user terminal location information provided in an embodiment of the present application;

[0084] Figure 7 is a flow chart of a smart home wake-up method provided by an embodiment of the present application;

[0085] Figure 8 is a schematic diagram of the structure of a user terminal provided in an embodiment of the present application;

[0086] Fig. 9 It is a structural diagram of a server provided in an embodiment of the present application. DETAILED DESCRIPTION

[0087] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the implementation methods of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0088] Before explaining in detail the smart home wake-up method provided in the embodiment of the present application, the application scenario and system architecture provided in the embodiment of the present application are first introduced.

[0089] Nowadays, with the continuous development of science and technology, more and more home appliances appear in people's lives, providing convenience for people's daily lives. Under the influence of the Internet, home appliances begin to develop in the direction of intelligence, forming a smart home that uses the house as a platform and integrates home life facilities using network communication technology, automatic control technology, audio and video technology, etc.

[0090] Smart home allows users to manage smart devices in smart home in a more convenient way. For example, users can control smart devices through touch screens, wireless remote controls, or voice. Among them, the way users control smart devices through voice is suitable for scenarios where smart devices have intelligent voice control functions. In this scenario, the smart device is configured with a voice control portal and a wake-up word. The voice control portal is a software module on the smart device that is used to collect user voice to obtain voice data. The smart device collects the user's voice through the voice control portal to obtain voice data, and matches the voice data with the wake-up word. The smart device with the wake-up word that matches the user's voice is used as the smart device to be awakened, and the smart device to be awakened is determined based on the wake-up word of the smart device. After determining the smart device to be awakened, the smart device to be awakened recognizes the semantic information in the voice data through voice recognition technology, and then executes the instructions issued by the user according to the semantic information.

[0091] However, when the user's home has a brand set of products, that is, the user's home has multiple home appliances with voice control entrances and the same wake-up words, if the user makes a voice to wake up and control a smart device, the smart device is recorded as the wake-up device. Since the wake-up words of smart devices of the same brand are the same, at this time, there may be problems with failure or conflict in controlling the wake-up device.

[0092] Based on the above problems, an embodiment of the present application proposes a smart home wake-up method, which uses UWB (Ultra Wideband) technology to perform precise positioning and determine the location of the user terminal. The smart home platform realizes accurate voice collection according to the location of the user terminal, accurately wakes up the smart device, and then intelligently controls the smart device, providing users with high-quality and efficient voice control experience.

[0093] Please refer to Figure 1 , Figure 1 1 is a schematic diagram of a system architecture according to an exemplary embodiment. The system architecture includes a user terminal 101, multiple smart devices 102, and a smart home platform 103. The user terminal 101 is respectively connected to the smart device 102 and the smart home platform 103 for communication, and the smart home platform 103 is also connected to the smart device 102 for communication. The communication connection can be a wired or wireless connection, which is not limited in the embodiment of the present application.

[0094] The user terminal 101 is used to obtain the user's living space image on the one hand, and to collect the user terminal's location information based on the UWB technology on the other hand, and send both the living space image and the user terminal's location information to the smart home platform 103. In addition, the smart device 102 is used to collect the wake-up word issued by the user and the voice used to control the operation of the smart device, obtain voice data based on the voice, and send the wake-up word and voice data to the smart home platform 103.

[0095] The smart home platform 103 is used to receive the living space image and the location information of the user terminal sent by the user terminal 101, and the wake-up word sent by the smart device 102, and determine the smart device to be woken up in the smart device 102 based on the received wake-up word.

[0096] in addition, Figure 1 The multiple smart devices in are multiple smart devices in the user's home. That is, Figure 1 The smart devices in the system shown are based on user families. In some embodiments, the smart home platform can configure user family tags on each smart device. The user family tag is used to uniquely identify a user family, that is, to bind the smart device to the user family, so that the subsequent smart home platform can manage the smart devices in a user family.

[0097] Among them, the user terminal sends a family registration request to the smart home platform, and the family registration request carries the information of the registered user's family. After receiving the family registration request, the smart home platform configures a user family tag for the user's family, and the user family tag is used to uniquely identify the user's family.

[0098] When a user purchases a smart device, the user terminal can send a tag configuration request to the smart home platform. The tag configuration request carries the device identification of the smart device. After receiving the tag configuration request, the smart home platform establishes a correspondence between the device identification of the smart device and the user home tag that uniquely identifies the user's home, so as to bind the smart device to the user's home.

[0099] In addition, when the user terminal sends a home registration request to the smart home platform, the home registration request can also carry the user's living space image, so that the smart home platform can subsequently determine the wake-up device from multiple smart devices based on the living space image, that is, the first smart device.

[0100] The living space image includes multiple image areas and multiple smart device images, each of the multiple image areas indicates an area corresponding to a room in the user's home, and each of the multiple smart device images indicates a smart device. Figure 2As shown, the living space image includes image areas corresponding to various rooms in the user's home and multiple smart devices, such as image areas corresponding to rooms such as the master bedroom and study, and smart devices such as televisions and air conditioners.

[0101] In addition, when the user terminal sends a home registration request to the smart home platform, the home registration request also carries the location coordinates of each smart device in the multiple smart devices and the boundary image coordinates of each image area in the multiple image areas. The location coordinates of each smart device are used to represent the location information of the corresponding smart device in the living space image, and the boundary image coordinates of each image area are used to represent the corresponding location information in the living space image of each room in the user's home. For example, the boundary image coordinates include two coordinate ranges of the two-dimensional image x and y, such as the x coordinate from 0-100 and the y coordinate from 0-100. The two coordinate ranges of x and y represent a boundary image coordinate.

[0102] In addition, when the smart home platform binds the user's home and smart devices, the smart home platform also needs to record the user information of each user in the user's home, including the user terminal information of the user, the user's wake-up word, etc. The user terminal information includes the identification of the user terminal and the functions supported by the user terminal (such as whether the user terminal supports UWB technology).

[0103] When recording the user information of each user in the user's home, the smart home platform will record the user's user ID, the user's wake-up word, and the user terminal information of the user one by one. This will facilitate the subsequent smart home platform to determine which user in the user's home sent the wake-up word sent by the smart device based on the user information, and determine whether the user terminal of the user supports UWB technology.

[0104] like Figure 3 As shown, the user first logs in to the smart home APP (Application) on the user terminal, creates a new user home on the APP, sends a home registration request to the smart home platform, and uploads the living space image of the user home. The living space image of the user home is then sent to the smart home platform, so that the smart home platform can subsequently manage the smart devices in the user home based on the living space image of the user home.

[0105] Optionally, after the user has created a family on the APP, the user can upload the living space image of the user's family later.

[0106] Among them, the user terminal 101 can be any electronic product that is held by a user and can interact with the user through one or more methods such as a keyboard, touch pad, touch screen, remote control, voice interaction or handwriting device, such as a PC (Personal Computer), a mobile phone, a smart phone, a PDA (Personal Digital Assistant), a handheld computer PPC (Pocket PC), a tablet computer, etc.

[0107] The smart device 102 can be any electrical device, such as a smart TV, a smart speaker, a washing machine, a refrigerator, an air conditioner, or other electrical devices.

[0108] The smart home platform 103 may be a single server, a server cluster consisting of multiple servers, or a cloud computing service center.

[0109] In addition, those skilled in the art should understand that the above-mentioned user terminal 101, smart device 102 and smart home platform 103 are only examples, and other existing or future terminals or smart devices or smart home platforms, if applicable to the embodiments of the present application, should also be included in the protection scope of the embodiments of the present application and are included here by reference.

[0110] It should be noted that Figure 1 The system architecture shown is described by taking the user terminal 101 and the smart home platform 103 as independent devices. Optionally, the method provided in the embodiment of the present application can also be applied to a centralized terminal device, which has the functions of the user terminal 101 and the smart home platform 103, and the embodiment of the present application does not limit this.

[0111] Next, the smart home wake-up method provided in the embodiment of the present application is explained in detail.

[0112] Figure 4 This is a flow chart of a smart home wake-up method provided in an embodiment of the present application, which is applied to a smart home platform. Figure 4 , the method comprises the following steps.

[0113] Step 401: The smart home platform receives wake-up words sent by N smart devices among M smart devices, where N is a positive integer less than or equal to M, and N is greater than 1.

[0114] Among them, the smart device collects the wake-up word issued by the user through the voice control entrance on the smart device. When the user issues the wake-up word, each smart device collects the wake-up word. Since there is a certain distance between the smart device and the user, in this scenario, there may be some smart devices that fail to collect the wake-up word issued by the user due to distance reasons. Therefore, the N smart devices in the embodiment of the present application are the smart devices that collect the wake-up word issued by the user among the M smart devices.

[0115] The smart home platform receives the wake-up word sent by each of the N smart devices. The wake-up word can be the voice information sent by the user or the voice feature value extracted by the smart device. The voice feature value includes information such as the volume of the user's voice. That is, the smart home platform can receive the wake-up word sent by each of the N smart devices in the following two ways.

[0116] When the voice data is a voice message sent by a user, the implementation process of the smart home platform receiving the wake-up word sent by each of the N smart devices can be: when the user sends a wake-up word, each of the N smart devices collects the wake-up word sent by the user, that is, the voice message, through its own configured voice control entrance, and sends its collected voice information directly to the smart home platform.

[0117] When the voice data is a voice feature value extracted by a smart device, the implementation process of the smart home platform receiving the wake-up word sent by each of the N smart devices can be: when the user sends a wake-up word, each of the N smart devices collects the wake-up word sent by the user through its own configured voice control portal, that is, voice information, and extracts the user's voice information to obtain a voice feature value. Each smart device then sends its own extracted voice feature value to the smart home platform.

[0118] After the smart home platform receives the wake-up words sent by N smart devices, the smart home platform will determine the similarity between the wake-up words sent by each smart device and each other smart device in the N smart devices. For example, for smart device 1, the smart home platform will determine the similarity between the wake-up words collected by smart device 1 and each other smart device in the N smart devices.

[0119] If the wake-up word is a voice message sent by the user, the smart home platform will determine the voice feature value corresponding to each voice message based on each voice message, and then determine the similarity between each two voice feature values ​​based on each voice feature value. If the wake-up word is a voice feature value extracted by the smart device, the smart home platform will determine the similarity between each two voice feature values.

[0120] In order to enable the smart home platform to accurately determine a smart device from N smart devices, after obtaining the similarity between the wake-up words sent by each two smart devices among the N smart devices, the smart home platform will compare the similarity between the wake-up words sent by the two smart devices with the similarity threshold. The similarity threshold can be set in advance, such as 80%.

[0121] For the wake-up words sent by each of the N smart devices, when the similarity between the wake-up words sent by any two smart devices exceeds the similarity threshold, it indicates that the difference between the wake-up words sent by any two smart devices is small, and the smart home platform cannot determine the first smart device based on the wake-up words. At this time, the smart home platform first determines the user corresponding to the wake-up word, and then determines whether the user terminal of the user supports UWB technology. If the user terminal of the user corresponding to the wake-up word supports UWB technology, the first smart device is determined through the following steps 402-403, and steps 402-403 are described in detail later.

[0122] The method for determining the user corresponding to the wake-up word may be as follows: when each user in the user's home issues the wake-up word for the first time, the smart home platform records the wake-up word of each user. When the smart device subsequently sends the wake-up word to the smart home platform, the smart home platform may calculate the similarity between the wake-up word and the previously recorded wake-up words of each user in the user's home, and use the user corresponding to the wake-up word in the user's home with the highest similarity as the user corresponding to the wake-up word sent by the smart device.

[0123] If the user terminal of the user corresponding to the wake-up word does not support UWB technology, the smart home platform determines the wake-up word with the largest clarity index as described in the following scenario "When the similarity between the wake-up words sent by two smart devices is lower than the similarity threshold", and then determines the first smart device.

[0124] When the similarity between the wake-up words sent by two smart devices is lower than the similarity threshold, it indicates that there is a large difference in the wake-up words sent by the two smart devices. The smart home platform can determine the wake-up word with the largest clarity index based on the wake-up words, and then perform intelligent control based on the smart device corresponding to the wake-up word with the largest clarity index.

[0125] When determining the wake-up word with the largest clarity index, if the wake-up word is a voice message sent by the user, the implementation process of determining the clarity index can be: calculating the signal-to-noise ratio on each frequency band in the voice information, linearly converting the signal-to-noise ratio of each frequency band to [0,1] to obtain the clarity of each frequency band, and then determining the final clarity index based on the weighted sum of the clarity values ​​corresponding to each frequency band.

[0126] If the wake-up word is a voice feature value extracted by a smart device, the implementation process of determining the clarity index can be: based on information such as volume included in the voice feature value, weights are set for each piece of information, and the weight is used to indicate the proportion of each piece of information. Based on the weight of each piece of information, the value of each piece of information is multiplied by the corresponding weight, and the resulting value is then divided by the number of information items included in the voice feature value to obtain the final clarity index.

[0127] Step 402: If the similarity between the wake-up words collected by any two smart devices among the N smart devices exceeds the similarity threshold, the smart home platform sends a positioning request message to the user terminal, so that the user terminal sends a positioning response message to the smart home platform. The positioning response message carries the positioning data collected by the user terminal based on the UWB positioning technology, and the positioning data indicates the location information of the user terminal.

[0128] When the similarity between the wake-up words collected by any two smart devices exceeds the similarity threshold, it is necessary to accurately determine the location information of the user terminal to accurately determine the first smart device from the N smart devices according to the location information of the user terminal.

[0129] In the prior art, Bluetooth, WI-FI (Wireless-Fidelity), RFID (Radio Frequency Identification) and other technologies are usually used to determine the location information of the user terminal. However, the method based on the use of Bluetooth, WI-FI, RFID and other technologies to determine the location information of the user terminal has low positioning accuracy. In this case, there is still a high probability that the first smart device will fail or conflict.

[0130] Therefore, in the embodiment of the present application, the user terminal accurately determines the location information of the user terminal based on the UWB positioning technology. The basic principle of UWB technology is: each base station in multiple base stations and the tag interact to determine the distance between each base station and the tag, and then determine the location information of the tag based on the distance between each base station and the tag and the location information of each base station.

[0131] Among them, the base station is a smart device whose position remains unchanged in the living space image sent by the user terminal to the smart home platform, and the location information of the base station is the location information of these smart devices.

[0132] If the user terminal of the user who issued the wake-up word supports UWB technology, the smart home platform sends a positioning request message to the user terminal. After the user terminal collects positioning data based on UWB technology, the user terminal generates a positioning response message based on the positioning data and sends the positioning response message to the smart home platform. The positioning data can carry multiple timestamp sets corresponding to multiple base stations.

[0133] A timestamp set corresponding to each base station in a plurality of base stations includes a sub-timestamp set corresponding to each detection data packet in a plurality of detection data packets, and a sub-timestamp set corresponding to each detection data packet includes a first sending timestamp, a first receiving timestamp, a second sending timestamp, and a second receiving timestamp. The first sending timestamp is the timestamp when the user terminal sends the corresponding detection data packet, the first receiving timestamp is the timestamp when the base station receives the corresponding detection data packet, the second sending timestamp is the timestamp when the base station sends a response data packet to the corresponding detection data packet, and the second receiving timestamp is the timestamp when the user terminal receives the response data packet.

[0134] Among them, when the user terminal receives the positioning request message, the following operations are performed on each base station to obtain the timestamp set corresponding to each base station. Specifically, each base station interacts with the user terminal, that is, sends a detection data packet, and the sub-timestamp set corresponding to each detection data packet can be obtained. The number of the detection data packets is not limited in the embodiment of the present application.

[0135] Among them, the sub-timestamp set is as follows Figure 5 As shown, the first detection data packet exchanged between the base station and the user terminal is used as an example for explanation. The user terminal sends a first detection data packet to the base station at a first time, and the first time is recorded as the first sending timestamp. The base station receives the first detection data packet at a second time, and the second time is recorded as the first receiving timestamp, and the base station sends a first response data packet to the base station for the first detection data packet at a third time, and the third time is recorded as the second sending timestamp. The user terminal receives a first response data packet to the first detection data packet at a fourth time, and the fourth time is recorded as the second receiving timestamp. In this way, four timestamps are obtained based on the first detection data packet, that is, a set of sub-timestamps corresponding to the first detection data packet is obtained.

[0136] When the base station sends the first response data packet to the user terminal, it also sends the first receiving timestamp and the second sending timestamp to the user terminal at the same time, so that the user terminal can subsequently obtain the sub-timestamp set corresponding to the first detection data packet.

[0137] Step 403: The smart home platform wakes up the first smart device from the N smart devices based on the positioning response message.

[0138] When the positioning response message carries multiple timestamp sets corresponding to multiple base stations, the implementation process of step 403 can be divided into the following steps:

[0139] Step 1: For any base station among multiple base stations, the smart home platform determines the distance between any base station and the user terminal based on the sub-timestamp set included in the timestamp set corresponding to any base station and corresponding to each detection data packet in multiple detection data packets.

[0140] Step 2: The smart home platform determines the location information of the user terminal based on the distance between each of the multiple base stations and the user terminal and the location information of the multiple base stations.

[0141] Step 3: The smart home platform determines the first smart device from the N smart devices based on the location information of the user terminal and the location information of each of the N smart devices.

[0142] That is to say, after obtaining the timestamp set corresponding to each base station, the smart home platform determines the distance between any base station and the user terminal, and then determines the location information of the user terminal, and finally determines the first smart device from N smart devices based on the location information of the user terminal and the location information of each smart device.

[0143] Among them, the implementation process of determining the distance between any base station and the user terminal in step one can be: for any base station, select the sub-timestamp sets corresponding to the first detection data packet and the second detection data packet respectively from multiple detection data packets interacted between the base station and the user terminal, and the first detection data packet and the second detection data packet are two adjacent detection data packets sent by the user terminal. Based on the sub-timestamp sets corresponding to the first detection data packet and the second detection data packet, the first duration, the second duration, the third duration and the fourth duration are determined. The first duration is the duration from the user terminal sending the first detection data packet to receiving the first response data packet corresponding to the first detection data packet, the second duration is the duration from the user terminal receiving the first response data packet to sending the second detection data packet, the third duration is the duration from the base station receiving the first detection data packet to sending the first response data packet, and the fourth duration is the duration from the base station sending the first response data packet to receiving the second detection data packet. Based on the first duration, the second duration, the third duration and the fourth duration, the flight time is determined by the following formula:

[0144]

[0145] Wherein, T indicates flight time, Tround1 indicates a first duration, Tround2 indicates a fourth duration, Treply1 indicates a third duration, and Treply2 indicates a second duration. The product of the flight time and the speed of light is taken as the distance between the base station and the user terminal.

[0146] The first probe data packet and the second probe data packet may be two adjacent probe data packets sent by the user terminal selected from multiple probe data packets, that is, a set of Tround1, Tround2, Treply1 and Treply2 are obtained based on the first probe data packet and the second probe data packet to determine the flight time T according to the above formula.

[0147] For example, Figure 5 As shown, the base station and the user terminal interact three times. The user terminal initiates the first ranging message, that is, sends the first detection data packet to the base station, and the base station responds. In this process, four timestamps are obtained: the first sending timestamp, the first receiving timestamp, the second sending timestamp, and the second receiving timestamp. After a period of time, the user terminal initiates the ranging message again, that is, sends the second detection data packet to the base station, and the base station receives the second detection data packet, thereby obtaining two timestamps: the first sending timestamp and the first receiving timestamp (the first sending timestamp and the first receiving timestamp are for the time of sending and receiving the second detection data packet). After this process, four time differences Tround1, Tround2, Treply1, and Treply2 are finally obtained.

[0148] Of course, multiple flight times T can also be obtained based on each two adjacent detection data packets in the multiple detection data packets, and then the average of the multiple Ts is calculated to determine the final flight time T. After the final flight time T is obtained, the distance between the base station and the user terminal is determined according to the formula d=T·c. Among them, d represents the distance between the base station and the user terminal, and c represents the speed of light.

[0149] By performing the above operation on each of the multiple base stations, the distance between each base station and the user terminal can be obtained.

[0150] After the distance between each base station and the user terminal is determined in step one, the location information of the user terminal can be determined according to step two.

[0151] The location information of the multiple base stations is obtained based on the living space image on the smart home platform, and the location information of each base station is the image coordinates of the corresponding base station in the living space image of the user.

[0152] like Figure 6 As shown, circles can be drawn with the location coordinates of each base station as the center (such as smart devices such as air conditioners, refrigerators, washing machines, etc.) and the distance between the corresponding base station and the user terminal as the radius to obtain the intersection point O, and the coordinates of the intersection point O are the location information of the user terminal.

[0153] In other embodiments, the positioning data may also carry the location information of the mobile terminal, which is the location coordinates of the user terminal. In this scenario, the smart home platform determines the distance from each smart device to the user terminal based on the location information of the user terminal and the location information of each smart device, so that the smart home platform can subsequently determine the first smart device closest to the user terminal from multiple smart devices. The way in which the user terminal determines the location information of the user terminal is the same as the way in which the smart home platform determines the location information of the user terminal, which will not be repeated here.

[0154] After the smart home platform obtains the location information of the user terminal through the above two methods, the first smart device can be determined from the N smart devices based on step 3. The implementation process of step 3 may be: based on the location information of the user terminal and the location information of each smart device in the N smart devices, a smart device located in the same image area as the user terminal is selected from multiple image areas. The smart device closest to the user terminal is selected from the smart devices located in the same image area to obtain the first smart device.

[0155] Specifically, after obtaining the location information of the user terminal, the image coordinates of the user terminal can be marked in the user's living space image. Since the living space image includes the boundary image coordinates of each image area, the smart home platform can determine the image area where the user terminal is located based on the location information (location coordinates) of the user terminal, that is, determine the room where the user terminal is located. Then, based on the image boundary coordinates of the image area, the smart home platform determines all smart devices whose location coordinates are included in the area indicated by the image boundary coordinates, that is, determines the smart devices located in the image area.

[0156] At this time, possible results are: there is no smart device in the image area, there is only one smart device in the image area, and there are two or more smart devices in the image area.

[0157] When there is no smart device in the image area, the smart home platform may use the smart device closest to the user terminal as the first smart device based on the distance between each of the N smart devices and the user terminal.

[0158] When there is only one smart device in the image area, the smart home platform directly uses the smart device as the first smart device.

[0159] When there are two or more smart devices in the image area, the smart home platform can use the smart device closest to the user terminal in the image area as the first smart device based on the distances between these smart devices and the user terminal.

[0160] In addition, when the similarity between the wake-up words sent by two smart devices among the N smart devices is lower than the similarity threshold, the smart device corresponding to the wake-up word with the largest clarity index is determined as the first smart device.

[0161] In addition, after the smart home platform determines and wakes up the first smart device, the smart home platform also receives voice data collected by the first smart device and determines the semantic information of the voice data, and determines the description information of the smart device to be controlled based on the semantic information, and the description information includes information such as the name and / or location of the smart device to be controlled.

[0162] After the smart home platform determines the first smart device, the first smart device is also called a wake-up device. After the smart home platform wakes up the first smart device, the first smart device is used to collect the user's voice to obtain voice data, and send the voice data to the smart home platform, so that the smart home platform determines the semantic information of the voice data, and determines the description information of the smart device to be controlled based on the semantic information. The smart device is used to execute the operation indicated in the user voice data.

[0163] Among them, the implementation process of the smart home platform determining the semantic information of the voice data can be: the smart home platform extracts the feature information expressing the meaning of the voice in the voice data through voice recognition technology, recognizes words with the smallest unit according to the feature information, and performs semantic analysis on the recognized words according to the respective grammars of different voices, and connects the recognized words to form sentences that can be used for understanding.

[0164] After the smart home platform obtains the semantic information of the voice data, it determines the description information of the smart device to be controlled based on the semantic information. For example, the semantic information processed by the smart home platform may be "turn on the air conditioner". In this way, the smart home platform will obtain the description information of the smart device to be controlled, "air conditioner", and then the smart device (air conditioner) in the user's home that meets the description information will be used as the smart device to be controlled.

[0165] At this time, if the number of smart devices that meets the description information among the M smart devices is only one, the smart home platform controls the corresponding smart device based on the voice data.

[0166] For example, if the first smart device is a TV, and the user utters a voice command "turn on the living room air conditioner", the TV converts the user's voice into voice data and sends it to the smart home platform. The smart home platform reads the voice data and obtains semantic information "turn on the living room air conditioner" based on the voice data. At this time, the smart home platform obtains the description information "living room air conditioner" of the smart device to be controlled based on the semantic information, and uses the living room air conditioner as the smart device to be controlled, so that the living room air conditioner can be turned on.

[0167] In addition, if there are multiple smart devices among the M smart devices that meet the description information, the smart home platform determines the smart device closest to the user terminal from the multiple smart devices based on the positioning response message, and controls the smart device closest to the user terminal based on the voice data.

[0168] Specifically, if there are multiple smart devices that can perform the operation indicated in the user's voice data, that is, there are multiple smart devices with the same function in the user's home, then the smart home platform determines the smart device closest to the user terminal among the multiple smart devices based on the positioning response message in the above steps.

[0169] The way in which the smart home platform determines the smart device closest to the user terminal is the same as the way in which the first smart device is determined after obtaining the location information of the user terminal, and will not be repeated here.

[0170] For example, if the first smart device is a TV, and the user utters a voice command "turn on the air conditioner", the TV converts the user's voice into voice data and sends it to the smart home platform. The smart home platform reads the voice data and obtains the semantic information "turn on the air conditioner" based on the voice data. Based on the semantic information, it obtains the description information "air conditioner" of the smart device to be controlled. At this time, the smart home platform determines the air conditioner in the user's home based on the description information. If there are multiple air conditioners in the user's home, the smart home platform determines and controls the air conditioner closest to the user terminal based on the location information of the user terminal indicated in the positioning response message, so that the air conditioner performs the turn-on operation.

[0171] Below Figure 7 Taking the example, the above steps 401-403 are further explained.

[0172] Figure 7 1 is a flow chart of a smart home voice control method provided by an embodiment of the present application. Figure 7 As shown, after the user sends a wake-up word and the smart device collects and sends the wake-up word to the smart home platform, the smart home platform will first determine which user in the user's home it is based on the wake-up word, and obtain the user terminal information of the user, and the smart home platform will compare the similarities between the wake-up words sent by the smart devices.

[0173] If the similarity between the wake-up words sent by two smart devices is lower than the similarity threshold, that is, the difference between the wake-up words is large, then the smart device corresponding to the wake-up word with the largest collected clarity index is selected from N smart devices as the smart device to be awakened, that is, the first smart device.

[0174] If the similarity between the wake-up words sent by any two of the N smart devices exceeds the similarity threshold, that is, the difference between the wake-up words is small, the smart home platform first determines whether the bound user terminal supports UWB technology. If the user terminal does not support UWB technology, the smart home platform still selects the smart device corresponding to the wake-up word with the largest clarity index as the first smart device.

[0175] If the user terminal supports UWB technology, the smart home platform determines the location information of the user terminal based on the UWB technology of the user terminal and determines whether there is a smart device located in the same image area as the user terminal.

[0176] If there is no smart device located in the same image area as the user terminal, the smart home platform uses the smart device closest to the user terminal among the N smart devices as the first smart device.

[0177] If there is a smart device located in the same image area as the user terminal, the smart home platform uses the smart device located in the same image area that is closest to the user terminal as the first smart device.

[0178] After determining the first smart device, the smart home platform collects the user's voice based on the first smart device, and controls the corresponding smart device based on the user's voice, so that the smart device performs the operation indicated in the user's voice.

[0179] In the embodiment of the present application, the smart home platform uses the wake-up words collected by each smart device to compare the similarity between the wake-up words sent by each two smart devices. When the similarity between the wake-up words sent by two smart devices exceeds the similarity threshold, the smart home platform determines the location information of the user terminal based on the user terminal supporting UWB positioning technology, and determines and wakes up the first smart device from multiple smart devices based on the location information of the user terminal and each smart device. And based on the user voice collected by the first smart device, the corresponding smart device is accurately controlled so that the smart device performs the operation indicated by the user voice.

[0180] The embodiment of the present application provides a smart home platform, which is a platform in an intelligent voice control system, and the intelligent voice control system also includes a user terminal and M smart devices, the user terminal is a terminal currently held by the user, and M is a positive integer. The smart home platform includes: a first receiving module, a sending module and a first determining module.

[0181] A first receiving module, configured to receive a wake-up word sent by N smart devices among the M smart devices, where N is a positive integer less than or equal to M, and N is greater than 1;

[0182] A sending module is used to send a positioning request message to the user terminal if the similarity between the wake-up words collected by any two smart devices among the N smart devices exceeds a similarity threshold, so that the user terminal sends a positioning response message to the smart home platform, and the positioning response message carries the positioning data collected by the user terminal based on the ultra-wideband UWB positioning technology, and the positioning data indicates the location information of the user terminal;

[0183] The first determining module is used to wake up a first smart device from N smart devices based on a positioning response message.

[0184] Optionally, the smart home platform further includes:

[0185] A second receiving module, used to receive voice data collected by the first smart device;

[0186] A second determination module, used to determine semantic information of the speech data;

[0187] A third determination module is used to determine the description information of the smart device to be controlled based on the semantic information;

[0188] The first control module is used to control the corresponding smart device based on the voice data if the number of smart devices that meet the description information among the M smart devices is one.

[0189] Optionally, the smart home platform further includes:

[0190] a fourth determination module, configured to determine, if there are multiple smart devices in the M smart devices that meet the description information, a smart device closest to the user terminal from the multiple smart devices based on the positioning response message;

[0191] The second control module is used to control the smart device closest to the user terminal based on the voice data.

[0192] Optionally, the positioning response message carries multiple timestamp sets corresponding to multiple base stations one by one, the multiple base stations are smart devices whose positions remain unchanged among the N smart devices within a reference time period, the timestamp set corresponding to each of the multiple base stations includes a sub-timestamp set corresponding to each detection data packet in the multiple detection data packets, the sub-timestamp set corresponding to each detection data packet includes a first sending timestamp, a first receiving timestamp, a second sending timestamp, and a second receiving timestamp, the first sending timestamp is the timestamp when the user terminal sends the corresponding detection data packet, the first receiving timestamp is the timestamp when the base station receives the corresponding detection data packet, the second sending timestamp is the timestamp when the base station sends a response data packet to the corresponding detection data packet, and the second receiving timestamp is the timestamp when the user terminal receives the response data packet;

[0193] The first determination module includes:

[0194] A first determination submodule, configured to determine, for any base station among the multiple base stations, a distance between any base station and a user terminal based on a sub-timestamp set included in a timestamp set corresponding to any base station and corresponding to each detection data packet in a plurality of detection data packets;

[0195] A second determination submodule, configured to determine the location information of the user terminal based on the distance between each of the multiple base stations and the user terminal and the location information of the multiple base stations;

[0196] The third determination submodule is used to determine and wake up the first smart device from the N smart devices based on the location information of the user terminal and the location information of each of the N smart devices.

[0197] Optionally, the first determining submodule is used for:

[0198] Selecting sub-timestamp sets corresponding to a first detection data packet and a second detection data packet respectively from a plurality of detection data packets, where the first detection data packet and the second detection data packet are two adjacent detection data packets sent by the user terminal;

[0199] Based on the sub-timestamp sets corresponding to the first probe data packet and the second probe data packet, respectively, determine a first duration, a second duration, a third duration and a fourth duration, the first duration being the duration from when the user terminal sends the first probe data packet to when the user terminal receives the first response data packet corresponding to the first probe data packet, the second duration being the duration from when the user terminal receives the first response data packet to when the user terminal sends the second probe data packet, the third duration being the duration from when any base station receives the first probe data packet to when it sends the first response data packet, and the fourth duration being the duration from when any base station sends the first response data packet to when it receives the second probe data packet;

[0200] Based on the first duration, the second duration, the third duration, and the fourth duration, the flight time is determined by the following formula:

[0201]

[0202] Wherein, T indicates the flight time, Tround1 indicates the first duration, Tround2 indicates the fourth duration, Treply1 indicates the third duration, and Treply2 indicates the second duration;

[0203] The product of the flight time and the speed of light is taken as the distance between any base station and the user terminal.

[0204] Optionally, the location information of the user terminal is the image coordinates of the user terminal in the user's living space image, the location information of each smart device is the image coordinates of the corresponding smart device in the user's living space image, the user's living space image includes multiple image areas, and each image area indicates a location area corresponding to a room;

[0205] The third determination submodule is used for:

[0206] Based on the location information of the user terminal and the location information of each of the N smart devices, select a smart device located in the same image area as the user terminal from multiple image areas;

[0207] A smart device that is closest to the user terminal is selected from the smart devices located in the same image area to obtain a first smart device.

[0208] Optionally, the smart home platform further includes:

[0209] The third receiving module is used to receive a living space image sent by a user terminal, where the living space image is marked with image coordinates of each of the multiple base stations and boundary image coordinates of each of the multiple image areas.

[0210] Optionally, the smart home platform further includes:

[0211] a fifth determination module, configured to determine a wake-up word with a maximum clarity index based on the wake-up words collected by each of the N smart devices if the similarity between the wake-up words collected by two smart devices among the N smart devices is lower than a similarity threshold;

[0212] The sixth determination module is used to determine the smart device corresponding to the wake-up word with the largest clarity index as the first smart device to be awakened.

[0213] In the embodiment of the present application, the smart home platform uses the wake-up words collected by each smart device to compare the similarity between the wake-up words sent by each two smart devices. When the similarity between the wake-up words sent by two smart devices exceeds the similarity threshold, the smart home platform determines the location information of the user terminal based on the user terminal supporting UWB positioning technology, and determines and wakes up the first smart device from multiple smart devices based on the location information of the user terminal and each smart device. And based on the user voice collected by the first smart device, the corresponding smart device is accurately controlled so that the smart device performs the operation indicated by the user voice.

[0214] It should be noted that: the smart home platform provided in the above embodiment only uses the division of the above functional modules as an example to illustrate when waking up the smart device. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the smart home platform provided in the above embodiment and the smart home wake-up method embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0215] Figure 8 800 is a structural block diagram of a user terminal 800 provided in an embodiment of the present application. Generally, the user terminal 800 includes: a processor 801 and a memory 802 .

[0216] The processor 801 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 801 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 801 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 801 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 801 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0217] The memory 802 may include one or more computer-readable storage media, which may be non-transitory. The memory 802 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 802 is used to store at least one instruction, which is used to be executed by the processor 801 to implement the smart home voice control method provided in the method embodiment of the present application.

[0218] In some embodiments, the user terminal 800 may further optionally include: a peripheral device interface 803 and at least one peripheral device. The processor 801, the memory 802 and the peripheral device interface 803 may be connected via a bus or a signal line. Each peripheral device may be connected to the peripheral device interface 803 via a bus, a signal line or a circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 804, a touch display screen 805, a camera 806, an audio circuit 807, a positioning component 808 and a power supply 809.

[0219] Those skilled in the art will understand that Figure 8 The structure shown in the figure does not constitute a limitation on the user terminal 800, and may include more or less components than those shown in the figure, or combine certain components, or adopt a different component arrangement.

[0220] Fig. 9 9 is a schematic diagram of the structure of a server provided in an embodiment of the present application. The server 900 includes a central processing unit (CPU) 901, a system memory 904 including a random access memory (RAM) 902 and a read-only memory (ROM) 903, and a system bus 905 connecting the system memory 904 and the central processing unit 901. The server 900 also includes a basic input / output system (I / O system) 906 that helps transmit information between various devices in the computer, and a large-capacity storage device 907 for storing an operating system 913, an application program 914, and other program modules 915.

[0221] The basic input / output system 906 includes a display 908 for displaying information and an input device 909 such as a mouse and a keyboard for user inputting information. The display 908 and the input device 909 are connected to the central processing unit 901 through an input / output controller 910 connected to the system bus 905. The basic input / output system 906 may also include an input / output controller 910 for receiving and processing inputs from a plurality of other devices such as a keyboard, a mouse, or an electronic stylus. Similarly, the input / output controller 910 also provides output to a display screen, a printer, or other types of output devices.

[0222] The mass storage device 907 is connected to the central processing unit 901 through a mass storage controller (not shown) connected to the system bus 905. The mass storage device 907 and its associated computer-readable media provide non-volatile storage for the server 900. That is, the mass storage device 907 may include a computer-readable medium (not shown) such as a hard disk or a CD-ROM drive.

[0223] Without loss of generality, computer readable media may include computer storage media and communication media. Computer storage media include 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 RAM, ROM, EPROM, EEPROM, flash memory or other solid-state storage technologies, CD-ROM, DVD or other optical storage, cassettes, magnetic tapes, disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that computer storage media are not limited to the above. The above-mentioned system memory 904 and mass storage device 907 can be collectively referred to as memory.

[0224] According to various embodiments of the present application, the server 900 can also be connected to a remote computer on the network through a network such as the Internet. That is, the server 900 can be connected to the network 912 through the network interface unit 911 connected to the system bus 905, or the network interface unit 911 can be used to connect to other types of networks or remote computer systems (not shown).

[0225] The above-mentioned memory also includes one or more programs, and the one or more programs are stored in the memory and configured to be executed by the CPU.

[0226] In some embodiments, a computer-readable storage medium is further provided, in which a computer program is stored, and when the computer program is executed by a processor, the steps of the smart home voice control method in the above embodiment are implemented. For example, the computer-readable storage medium may be a ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

[0227] It is worth noting that the computer-readable storage medium mentioned in the embodiments of the present application may be a non-volatile storage medium, in other words, a non-transitory storage medium.

[0228] It should be understood that all or part of the steps to implement the above embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The computer instructions can be stored in the above-mentioned computer readable storage medium.

[0229] That is, in some embodiments, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute the steps of the smart home voice control method described above.

[0230] It should be understood that the "at least one" mentioned herein refers to one or more, and "multiple" refers to two or more. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in order to facilitate the clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, the words "first", "second" and the like are used to distinguish the same items or similar items with basically the same functions and effects. Those skilled in the art can understand that the words "first", "second" and the like do not limit the quantity and execution order, and the words "first", "second" and the like do not limit them to be necessarily different.

[0231] It can be understood that in the specific implementation method of the present application, related data such as user living space images are involved. When the above embodiments of the present application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0232] The above-mentioned embodiments are provided for the present application and are not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A smart home wake-up method, characterized in that: The method is executed by a smart home platform in an intelligent voice control system, wherein the intelligent voice control system further comprises a user terminal and M smart devices, wherein the user terminal is a terminal currently held by the user, and M is a positive integer; The method comprises: The smart home platform receives wake-up words sent by N smart devices among the M smart devices, where N is a positive integer less than or equal to M, and N is greater than 1; If the similarity between the wake-up words collected by any two of the N smart devices exceeds the similarity threshold, the smart home platform sends a positioning request message to the user terminal, so that the user terminal sends a positioning response message to the smart home platform, the positioning response message carries the positioning data collected by the user terminal based on the ultra-wideband UWB positioning technology, the positioning data indicates the location information of the user terminal, the positioning data includes multiple timestamp sets corresponding to multiple base stations one by one, the multiple base stations are smart devices whose positions remain unchanged in the reference time period among the N smart devices, the timestamp set corresponding to each base station in the multiple base stations includes a sub-timestamp set corresponding to each detection data packet in the multiple detection data packets, the sub-timestamp set corresponding to each detection data packet includes a first sending timestamp, a first receiving timestamp, a second sending timestamp and a second receiving timestamp, the first sending timestamp is the timestamp when the user terminal sends the corresponding detection data packet, the first receiving timestamp is the timestamp when the base station receives the corresponding detection data packet, the second sending timestamp is the timestamp when the base station sends a response data packet to the corresponding detection data packet, and the second receiving timestamp is the timestamp when the user terminal receives the response data packet; Based on the positioning response message, the smart home platform selects, for any base station among the multiple base stations, from the multiple detection data packets, a sub-timestamp set corresponding to a first detection data packet and a second detection data packet, respectively, where the first detection data packet and the second detection data packet are two adjacent detection data packets sent by the user terminal; Based on the sub-timestamp sets corresponding to the first detection data packet and the second detection data packet, respectively, a first duration, a second duration, a third duration and a fourth duration are determined, wherein the first duration is the duration from when the user terminal sends the first detection data packet to when a first response data packet corresponding to the first detection data packet is received, the second duration is the duration from when the user terminal receives the first response data packet to when the second detection data packet is sent, the third duration is the duration from when any base station receives the first detection data packet to when the first response data packet is sent, and the fourth duration is the duration from when any base station sends the first response data packet to when the second detection data packet is received; Based on the first duration, the second duration, the third duration and the fourth duration, the flight time is determined by the following formula: Wherein, the T indicates the flight time, the Tround1 indicates the first duration, the Tround2 indicates the fourth duration, the Treply1 indicates the third duration, and the Treply2 indicates the second duration; Taking the product of the flight time and the speed of light as the distance between any base station and the user terminal; The smart home platform determines the location information of the user terminal based on the distance between each of the multiple base stations and the user terminal and the location information of the multiple base stations; The smart home platform wakes up a first smart device from the N smart devices based on the location information of the user terminal and the location information of each of the N smart devices.

2. The method according to claim 1, characterized in that After the smart home platform wakes up the first smart device from the N smart devices, the method further includes: The smart home platform receives the voice data collected by the first smart device; The smart home platform determines semantic information of the voice data; The smart home platform determines description information of the smart device to be controlled based on the semantic information; If the number of smart devices that conform to the description information among the M smart devices is one, the smart home platform controls the corresponding smart device based on the voice data.

3. The method according to claim 2, characterized in that The method further comprises: If there are multiple smart devices among the M smart devices that match the description information, the smart home platform determines a smart device closest to the user terminal from the multiple smart devices based on the positioning response message; The smart home platform controls the smart device closest to the user terminal based on the voice data.

4. The method according to claim 1, characterized in that The location information of the user terminal is the image coordinates of the user terminal in the user's living space image, and the location information of each smart device is the image coordinates of the corresponding smart device in the user's living space image. The user's living space image includes multiple image areas, and each image area indicates a location area corresponding to a room; The smart home platform determines a first smart device from the N smart devices based on the location information of the user terminal and the location information of each smart device in the N smart devices, including: Based on the location information of the user terminal and the location information of each of the N smart devices, selecting a smart device located in the same image area as the user terminal from the multiple image areas; A smart device that is closest to the user terminal is selected from smart devices located in the same image area to obtain the first smart device.

5. The method according to claim 1, characterized in that The method further comprises: The smart home platform receives a living space image sent by the user terminal, wherein the living space image is marked with image coordinates of each of the multiple base stations and boundary image coordinates of each of the multiple image areas.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: If the similarity between the wake-up words collected by two smart devices among the N smart devices is lower than the similarity threshold, determine the wake-up word with the largest clarity index based on the wake-up words collected by each smart device among the N smart devices; The smart device corresponding to the wake-up word with the largest clarity index is determined as the first smart device to be awakened.

7. A smart home platform, characterized in that: The smart home platform is a platform in an intelligent voice control system, and the intelligent voice control system also includes a user terminal and M smart devices, the user terminal is a terminal currently held by the user, and M is a positive integer; The smart home platform includes a processor, and the processor is used to: Receive a wake-up word sent by N smart devices among the M smart devices, where N is a positive integer less than or equal to M, and N is greater than 1; If the similarity between the wake-up words collected by any two of the N smart devices exceeds the similarity threshold, a positioning request message is sent to the user terminal, so that the user terminal sends a positioning response message to the smart home platform, the positioning response message carries the positioning data collected by the user terminal based on the ultra-wideband UWB positioning technology, the positioning data indicates the location information of the user terminal, the positioning data includes multiple timestamp sets corresponding to multiple base stations one by one, the multiple base stations are smart devices whose positions remain unchanged in the reference time period among the N smart devices, the timestamp set corresponding to each base station in the multiple base stations includes a sub-timestamp set corresponding to each detection data packet in the multiple detection data packets, the sub-timestamp set corresponding to each detection data packet includes a first sending timestamp, a first receiving timestamp, a second sending timestamp, and a second receiving timestamp, the first sending timestamp is the timestamp of the user terminal sending the corresponding detection data packet, the first receiving timestamp is the timestamp of the base station receiving the corresponding detection data packet, the second sending timestamp is the timestamp of the base station sending a response data packet to the corresponding detection data packet, and the second receiving timestamp is the timestamp of the user terminal receiving the response data packet; Based on the positioning response message, for any base station among the multiple base stations, select, from the multiple probe data packets, sub-timestamp sets corresponding to a first probe data packet and a second probe data packet, respectively, where the first probe data packet and the second probe data packet are two adjacent probe data packets sent by the user terminal; Based on the sub-timestamp sets corresponding to the first detection data packet and the second detection data packet, respectively, a first duration, a second duration, a third duration and a fourth duration are determined, wherein the first duration is the duration from when the user terminal sends the first detection data packet to when a first response data packet corresponding to the first detection data packet is received, the second duration is the duration from when the user terminal receives the first response data packet to when the second detection data packet is sent, the third duration is the duration from when any base station receives the first detection data packet to when the first response data packet is sent, and the fourth duration is the duration from when any base station sends the first response data packet to when the second detection data packet is received; Based on the first duration, the second duration, the third duration and the fourth duration, the flight time is determined by the following formula: Wherein, the T indicates the flight time, the Tround1 indicates the first duration, the Tround2 indicates the fourth duration, the Treply1 indicates the third duration, and the Treply2 indicates the second duration; Taking the product of the flight time and the speed of light as the distance between any base station and the user terminal; Determine the location information of the user terminal based on the distance between each of the multiple base stations and the user terminal and the location information of the multiple base stations; Based on the location information of the user terminal and the location information of each of the N smart devices, a first smart device is awakened from the N smart devices.

8. The smart home platform as claimed in claim 7, characterized in that: The processor is further configured to: Receiving voice data collected by the first smart device; Determining semantic information of the speech data; Determining description information of the smart device to be controlled based on the semantic information; If the number of smart devices that matches the description information among the M smart devices is one, the corresponding smart device is controlled based on the voice data.

Images