WO2022222847A1

WO2022222847A1 - Device wake-up method and system, electronic device, and storage medium

Info

Publication number: WO2022222847A1
Application number: PCT/CN2022/086914
Authority: WO
Inventors: 伍云云; 谢家晖; 奉飞飞
Original assignee: 美的集团(上海)有限公司; 美的集团股份有限公司
Priority date: 2021-04-23
Filing date: 2022-04-14
Publication date: 2022-10-27
Also published as: CN114678016A

Abstract

A device wake-up method, comprising: a decision device determining, on the basis of personnel conditions in a target area, a state of a device to be woken up in the target area, wherein the state of the device to be woken up represents whether the device to be woken up is allowed to be woken up (S21); and in response to a wake-up acknowledgement request sent by the device to be woken up, instructing, on the basis of the state of the device to be woken up, the device to be woken up to wake up or not wake up a voice interaction mode (S22). The method can reduce a false wake-up rate. Also provided are a device wake-up apparatus and system, an electronic device, a storage medium, and a computer program product.

Description

Device wake-up method and system, electronic device and storage medium

This application claims the priority of the Chinese patent application with the application number 2021104412640 filed on April 23, 2021 and the invention title is "Device Wake-up Method and System, Electronic Device and Storage Medium", which is fully incorporated into this application by reference .

【Technical field】

The present application relates to the field of information technology, and in particular, to a device wake-up method and system, an electronic device and a storage medium.

【Background technique】

With the development of Internet of Things (IoT) technology and the popularization of WiFi6, Bluetooth mesh and other technologies, more and more terminal devices such as sockets, lamps, rice cookers, etc. are interconnected through the network. With the increasing number of terminal devices, traditional control methods such as mobile phone APPs (that is, application programs), panels, etc., are gradually unable to cope with increasingly complex device interactions. In this situation, voice interaction is more and more sought after by people. However, in the actual application process, voice interaction may cause false wake-up. For example, the oven is falsely woken up without human supervision, which may cause major safety hazards. In view of this, how to reduce the false wake-up rate has become an urgent problem to be solved.

[Content of the invention]

The present application provides a device wake-up method and system, an electronic device and a storage medium to reduce the false wake-up rate.

In order to solve the above technical problem, a technical solution adopted in the present application is: a device wake-up method, comprising: a decision-making device determines the state of the device to be awakened in the target area based on the personnel situation in the target area, wherein the state of the device to be awakened Indicates whether the device to be awakened is allowed to wake up; in response to the wakeup confirmation request sent by the device to be awakened, based on the state of the device to be awakened, it indicates whether the device to be awakened wakes up in voice interaction mode.

According to an embodiment of the present application, the personnel situation in the target area is determined based on the personnel detection information in the target area sent by the cloud device.

According to an embodiment of the present application, before determining the state of the device to be awakened in the target area based on the personnel situation in the target area, the method further includes: receiving personnel detection information of the target area obtained by the cloud device based on the collected data, wherein the collected data It is collected from the target area by the collection device; based on the personnel detection information, the personnel situation in the target area is obtained.

According to an embodiment of the present application, the collection device includes at least one of a door switch sensing device, an image collection device, and a target sensing device, and the collected data includes entry and exit data collected by the door switch sensing device, and image data collected by the image collection device. and at least one of sensing data of the target sensing device.

According to an embodiment of the present application, the person detection information in the target area includes at least one of the following: the person detection information corresponding to the door switch sensing device obtained based on the entry and exit data; the image obtained based on the portrait detection result of the image data The personnel detection information corresponding to the device is collected; based on the sensing data, the personnel detection information corresponding to the target sensing device is obtained.

According to an embodiment of the present application, the person detection information corresponding to the door switch sensing device includes: someone coming back state and someone leaving state. The status is generated by the cloud device receiving the exit data collected by the door switch sensor device. Based on the personnel detection information, the personnel situation in the target area can be obtained, including: when the collection device includes the door switch sensor device, compare the status of someone coming back and The number of times the person left state is generated, based on the comparison result to determine whether there is a person in the target area.

According to an embodiment of the present application, determining the state of the device to be woken up in the target area based on the personnel situation in the target area includes: when there are people in the target area, determining the state of the device to be woken up as a wake-up allowed state; in the target area In the case of no one, the state of the device to be woken up is determined as the state of prohibiting wake-up.

According to an embodiment of the present application, instructing the device to be woken up whether to wake up the voice interaction mode based on the state of the device to be woken up includes: in the case that the state of the device to be woken up is the wake-up allowed state, instructing the device to be woken up to execute the wake-up voice interaction mode; In the case that the state of the device to be woken up is the wake-up prohibited state, the device to be woken up is instructed not to perform the wake-up voice interaction mode.

According to an embodiment of the present application, the wake-up confirmation request is generated when the device to be woken up collects audio data and detects that the audio data contains preset words; when the state of the device to be woken up is the wake-up allowed state, the device to be woken up indicates that the device is to be woken up. The device executes the wake-up voice interaction mode, including: in the case that the state of the device to be woken up is the wake-up allowed state, detecting the audio data contained in the wake-up confirmation request; in the case of detecting that the audio data contains preset words, indicating the to-be-awakened state The device implements the wake-up voice interaction mode.

According to an embodiment of the present application, the decision-making device includes at least one of the following features: the decision-making device is located in the target area, and the processing capability of the decision-making device is stronger than that of the device to be awakened; and/or, the decision-making device and the device to be awakened use short-range wireless communication for communication. The communication is either connected on the same local area network; and/or the target area is a home area.

In order to solve the above technical problem, another technical solution adopted in this application is: an electronic device, comprising a processor, a memory and a communication circuit, the memory and the communication circuit are coupled to the processor; the memory stores program instructions, and the processor is used for executing Program instructions to implement the device wake-up method in the above solution.

To solve the above technical problem, another technical solution adopted in the present application is: a computer-readable storage medium storing program instructions that can be run by a processor, and the program instructions are used to implement the device wake-up method in the above solution.

In order to solve the above technical problem, another technical solution adopted in the present application is: a device wake-up system, including a decision-making device and a device to be woken up connected to each other, wherein the decision-making device is the electronic device in the above scheme, and the device to be woken up is located at the target. In the area, and can be executed in the case of waking up the voice interaction mode, the voice command is received in the target area.

According to an embodiment of the present application, the device wake-up system further includes a cloud device connected to the decision-making device, and the cloud device is used to send the personnel detection information of the target area to the decision-making device, and the personnel detection information is used to confirm the personnel situation.

According to an embodiment of the present application, the device wake-up system further includes a collection device located in the target area, and the collection device is connected to the cloud device to obtain the collection data of the target area and send the collected data to the cloud device, and the cloud device is used for collecting data based on the collection The data determines the person detection information in the target area.

In order to solve the above-mentioned technical problems, another technical solution adopted in the present application is: a device wake-up device, comprising a state determination module and a mode indication module, and the state determination module is configured for decision-making equipment to determine the target based on the personnel situation in the target area. The state of the device to be woken up in the area, where the state of the device to be woken up indicates whether the device to be woken up is allowed to wake up; the mode indication module is configured to respond to a wake-up confirmation request sent by the device to be woken up, based on the state of the device to be woken up, indicating Whether to wake up the device to wake up the voice interaction mode.

In order to solve the above technical problem, another technical solution adopted in this application is: a computer program product, when the computer program product runs on a terminal device, the terminal device can execute the device wake-up method in the above solution.

【Description of drawings】

In order to illustrate the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the drawings that are used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative effort. in:

1 is a schematic diagram of a framework of an embodiment of a device wake-up system of the present application;

2 is a schematic flowchart of an embodiment of a device wake-up method of the present application;

3 is a schematic diagram of a framework of an embodiment of an electronic device of the present application;

FIG. 4 is a schematic diagram of a framework of an embodiment of a computer-readable storage medium of the present application.

【Detailed ways】

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application. In addition, it should be noted that, for the convenience of description, the drawings only show some but not all the structures related to the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work, all belong to the protection scope of the present application.

In the disclosed embodiments of the device wake-up method of the present application, the decision-making device determines the state of the device to be woken up in the target area according to the situation of the people in the target area, and the state indicates whether the device to be woken up is allowed to wake up or not allowed to wake up, and responds to The wake-up confirmation request from the device to be awakened indicates whether the device to be awakened wakes up in the voice interaction mode based on the state of the device to be awakened. Since the state of the device to be awakened is determined by the decision-making device based on the situation of the people in the target area, it can be beneficial to Improving the accuracy of the state of the device to be woken up can help to improve the accuracy of determining whether the device to be woken up is allowed to wake up. Compared with the direct wake-up voice interaction mode in response to the wake-up confirmation request, by combining the wake-up from the device to be woken up The confirmation request and the status of the device to be awakened together indicate whether the device to be awakened wakes up in the voice interaction mode, which can help reduce the false wake-up rate.

Please refer to FIG. 1 . FIG. 1 is a schematic diagram of a framework of an embodiment of a device wake-up system of the present application. As shown in FIG. 1 , the device wake-up system includes a decision-making device and a device to be woken up, and the decision-making device and the device to be woken up are connected to each other to ensure interactive communication between the two. Specifically, the decision-making device may be an electronic device that can implement any of the device wake-up method embodiments in this application, and its specific circuit framework can refer to the relevant descriptions of the electronic device embodiments in this application, which will not be repeated here. Please continue to refer to FIG. 1 , the device to be awakened may be located in the target area, and if the voice interaction mode is awakened, the device to be awakened can execute the voice command received in the target area.

It should be noted that the devices to be woken up may include, but are not limited to, smart home devices such as smart sockets, smart lamps, and sweeping robots, and home appliances such as rice cookers, refrigerators, and ovens, which are not limited here. Without loss of generality, if the smart socket wakes up the voice interaction mode, it can execute voice commands such as "disconnect the channel" and "close the channel", so that when the voice command "close the channel" is executed, The electrical appliance (eg, water heater) on the socket is powered on, or the appliance (eg, the water heater) plugged into the smart socket can be powered off by executing the voice command "disconnect the circuit", and other devices to be woken up can be deduced by analogy , and no more examples will be given here.

In an implementation scenario, in order to improve the execution efficiency of the decision-making device and quickly and accurately determine whether to instruct the device to be woken up to wake up the voice interaction mode, the processing capability of the decision-making device may be stronger than that of the device to be woken up. For example, the number of cores, the number of threads and the frequency of the CPU (Central Processing Unit, central processing unit) of the decision-making device may be greater than that of the device to be awakened. Decision-making devices may include, but are not limited to: televisions, NAS (Network Attached Storage, network attached storage), set-top boxes, etc., which are not limited here.

In an implementation scenario, the decision-making device and the device to be woken up can communicate through short-range wireless communication, or the decision-making device and the device to be woken up can also be connected in the same local area network through short-range wireless communication. . The short-range wireless communication manner may specifically include, but is not limited to, Bluetooth, ZigBee (ie, ZigBee protocol), etc., which are not limited herein.

In an implementation scenario, as mentioned above, the device to be awakened may be located in the target area. In order to further ensure smooth communication between the device to be awakened and the decision-making device, the decision-making device may also be set in the target area.

In an implementation scenario, the target area may specifically include, but is not limited to, a home area, that is, the device wake-up system in the embodiment of the present disclosure may be specifically deployed in a home environment. For example, waiting-to-wake devices such as rice cookers, refrigerators, and ovens can be located in the kitchen of the home area, while wait-to-wake devices such as smart sockets and smart lamps can be deployed in the living room and bedroom of the home area as required, which is not limited here. .

In an implementation scenario, the device wake-up system may include only one decision-making device. For example, when the target area is small, the devices to be woken up are densely distributed. In this case, only one decision-making device can be deployed with all the devices. The device to be woken up achieves a reliable connection; alternatively, please continue to refer to Figure 1. As shown in Figure 1, the device wake-up system can also include multiple (eg, 2, 3, etc.) decision-making devices, and each decision-making device can be connected to a At least one (eg, 1, 2, 3, etc.) devices to wake up. The device to be woken up connected to the decision-making device can be specifically set according to the relative position between the decision-making device and the device to be woken up. For example, for the decision-making device "NAS" in the study room, the connected devices to be woken up may include: study room For the smart sockets in the living room and the smart lamps in the study room, for the decision-making device "TV" in the living room, the connected devices to be woken up can include: sweeping robots in the living room, smart sockets in the living room, and smart devices in the living room. Lamps and other decision-making devices can be deduced in the same way, and no examples will be given here; alternatively, the device to be woken up linked to the decision-making device can also be directly configured by the user, for example, the user can directly configure the decision-making device in the bedroom. "Connect with the smart socket in the bedroom, the air conditioner in the bedroom, and the smart lighting in the bedroom. In practical application, one of the above two methods can be selected, which is not limited here.

In an implementation scenario, as mentioned above, the decision-making device determines the state of the device to be awakened in the target area based on the personnel situation in the target area. In order to improve the accuracy of the personnel situation, as shown in Figure 1, the device wake-up system also It may further include a collection device located in the target area, and the collection device is used to obtain the collection data in the target area, and the collection data is used to determine the situation of the personnel in the target area. It should be noted that the personnel situation in the target area may specifically include, but is not limited to, whether there are people in the target area. For example, the personnel situation may include: there are people in the target area, or the personnel situation may include: no one is in the target area, which is not described here. Do limit.

In a specific implementation scenario, the acquisition device may include, but is not limited to, at least one of a door switch sensing device, an image acquisition device, and a target sensing device. It should be noted that door switch sensing devices may include but are not limited to door locks, door locks may specifically include but are not limited to: fingerprint locks, password locks, door card locks, iris locks, etc., and image capture devices may include but are not limited to cameras, Cameras can include but are not limited to: card cameras, spherical cameras, etc., target sensing devices can include but are not limited to infrared sensing devices, etc., infrared sensing devices can include but are not limited to: infrared pyroelectric sensors, etc. Do limit.

In another specific implementation scenario, as mentioned above, the collection devices may include but are not limited to door switch sensing devices, image collection devices, target sensing devices, etc. In this case, the collected data may include but not limited to door switch sensing devices The entry and exit data collected by the device, the image data captured by the image collection device, and the sensing data sensed by the target sensing device, etc. On this basis, the target area can be determined based on one of them, or a combination of two or more of them. personnel inside. For details, reference may be made to the related descriptions in the following disclosed embodiments, which are not repeated here.

It should be noted that the collection device and the device to be woken up are not opposite individuals, and the device to be woken up may also include the collection device. For example, the device to be woken up may include: rice cookers, sweeping robots, smart sockets, cameras, and the aforementioned smart sockets Similarly, if the camera wakes up the voice interaction mode, it can execute voice commands such as "delete local video", "save local video to the cloud", etc., so that when the voice command "delete local video" is executed, the local camera can be deleted. In the case of executing the voice command "Save local video to the cloud", the video stored locally by the camera is saved to the cloud. Further, the camera can also be used as a collection device to collect image data, so that according to the image Data, determine the personnel situation, and the specific determination method can refer to the relevant descriptions in the following disclosed embodiments, which will not be repeated here for the time being. Of course, the devices to be woken up may not include collection devices. For example, the devices to be woken up may include rice cookers, sweeping robots, and smart sockets, and the collection devices may include door locks and infrared sensing devices, which are not limited here.

In an implementation scenario, the decision-making device can directly determine the personnel situation in the target area based on the collection data obtained by the collection device, which can help shorten the communication link in the process of deciding whether to wake up as much as possible. Wake-up delay.

In another implementation scenario, please refer to Fig. 1, in order to reduce the processing load of the decision-making device, the device wake-up system may also include a cloud device (such as a server, etc.), and the cloud device can be connected with the decision-making device and the collection device. On this basis, the cloud device can obtain the collection data from the collection device, and determine the personnel detection information in the target area based on the collected data, and further send the personnel detection information in the target area to the decision-making device for the decision-making device to pass the target area. The personnel detection information is used to determine the personnel situation in the target area, and through the personnel situation in the target area, the state of the device to be awakened is determined. That is to say, on the one hand, the cloud device is connected to the collection device to obtain the collection data of the target area, and based on the collected data, the personnel detection information of the target area is determined; Send it to the decision-making device, so that the decision-making device can determine the situation of the personnel based on the personnel detection information, thereby determining the state of the device to be awakened. Compared with the decision-making device, the cloud device often has stronger processing capabilities, enabling it to run more complex and accurate mathematics. Model to process the collected data to improve the accuracy of the personnel situation, so that through the cooperation of cloud equipment, decision equipment, and collection equipment, it can help to improve the accuracy of the determined state of the device to be woken up, and reduce the decision-making equipment. processing load.

The above embodiments have shown the connection relationship, data interaction, and their respective functions among the decision-making device, the device to be woken up, the collection device, and the cloud device. Please refer to FIG. 2 below. FIG. 2 is a schematic flowchart of an embodiment of a device wake-up method of the present application. Specifically, the following steps can be included:

Step S21: The decision-making device determines the state of the device to be awakened in the target area based on the personnel situation in the target area.

In the embodiment of the present disclosure, the state of the device to be woken up is used to indicate whether the device to be woken up is allowed to wake up or not allowed to wake up. For details, reference may be made to the relevant descriptions in the aforementioned disclosed embodiments, which will not be repeated here.

In an implementation scenario, as described in the foregoing disclosed embodiments, the personnel situation in the target area may be specifically determined based on the data collected by the collection device for the target area. For example, if the collection device includes a door switch sensing device, the collected data may include entry and exit data collected by the door switch sensing device; and if the collection device includes an image capture device, the collected data may include image data captured by the image capture device; However, if the collection device includes a target sensing device, the collected data may include sensing data sensed by the target sensing device, which is not limited herein.

In an implementation scenario, as described in the aforementioned disclosed embodiments, the decision-making device may obtain the personnel detection information in the target area directly based on the collected data, and on this basis, determine the personnel in the target area based on the obtained personnel detection information. Happening.

In another implementation scenario, as described in the aforementioned disclosed embodiments, in order to reduce the processing load of the decision-making device and improve the accuracy of the personnel situation, the cloud device can also obtain the personnel detection in the target area based on the collection data obtained by the collection device. information, so that the decision-making device can receive the personnel detection information obtained by the cloud device from the collected data, and based on the personnel detection information, determine the personnel situation in the target area, so as to cooperate with the cloud device, the decision-making device and the collection device. Determines whether the device to be woken wakes up in voice interaction mode.

It should be noted that the personnel detection information may include but is not limited to: entry and exit information, etc., which are not limited here. Further, whether the person detection information is obtained by the cloud device or the person detection information is directly obtained by the decision device, the personnel detection information can be determined according to different collection data of the target area by different collection devices.

Taking the collection device including the door switch sensing device as an example, in this case, the person detection information corresponding to the door switch sensing device can be obtained based on the entry and exit data collected by the door switch sensing device, in order to facilitate the detection of people corresponding to other collection devices. The information is distinguished, and the person detection information corresponding to the door switch sensing device can be called the first person detection information.

In an implementation scenario, taking the aforementioned three-terminal cooperation as an example, when the cloud device receives the door entry data collected by the door switch sensing device, it can generate a status of someone coming back, and the cloud device receives the data collected by the door switch sensing device. When going out data, a person leaving state can be generated. In this case, the aforementioned first person detection information may specifically include: someone returning state and someone leaving state, and specifically may include the generation number H of someone returning state and the generation number I of someone leaving state . Taking the door switch sensing device as a fingerprint door lock as an example, when the door switch sensing device collects the fingerprint and unlocks the door, it can be considered that a door entry data is received, and when the door switch sensing device does not collect the fingerprint and the lock is unlocked, it can be considered that the door is received. One-time exit data; or, taking the door switch sensing device as a password lock as an example, when the door switch sensing device collects the correct input password and unlocks the lock, it can be considered that one-time entry data is received, but the door switch sensing device does not collect the password. When the lock is directly unlocked, it can be considered that one time out data is received, and other door locks can be deduced by analogy, and no examples will be given here.

In another implementation scenario, as mentioned above, the first person detection information may specifically include: the generation times H of the person returning state and the generation number I of the person leaving state. In this case, the generation times of the person returning state can be compared. H and the generation number I of the person leaving the state, and based on the comparison result, determine the person situation, that is, whether there is a person in the target area. Specifically, in the case where the generation times H of the person returning state is greater than the generation number I of the person leaving state, it can be determined that the target area is occupied, otherwise it can be determined that the target area is unoccupied. For example, the number of times that someone has come back is 4 times, that is, the door lock is recorded 4 times using fingerprints, passwords, etc. to unlock, and the number of times that someone has left is 3 times, that is, the door lock is recorded 3 times without using any fingerprints, passwords, etc. If the lock is opened directly after waiting, it can be determined that there are people in the target area; or, the number of times that someone has returned to the state is 4, and the number of times that someone has left the state is also 4 times, it can be considered that the door has experienced a total of 4 complete "in-door-out". ” action, so it can be determined that there is no one in the target area. Other situations can be deduced by analogy, and no examples are given here.

Taking the acquisition device including the image acquisition device as an example, in this case, the person detection information corresponding to the image acquisition device can be obtained based on the portrait detection results of the image data collected by the image acquisition device, in order to facilitate the personnel corresponding to other acquisition devices. The detection information is distinguished, and the person detection information corresponding to the image acquisition device may be referred to as the second person detection information.

In an implementation scenario, the shooting range of the image acquisition device may cover the entire target area, and the image data collected by the image acquisition device may be subjected to portrait detection to obtain a portrait detection result. The portrait detection result may specifically include whether there is a portrait in the image data, In this case, the aforementioned second person detection information may specifically include a portrait detection result. Further, the situation of the person may be determined directly based on the second person detection information. For example, by performing portrait detection on the image data, a portrait detection result can be obtained. The portrait detection result may include the presence of a portrait in the image data. At this time, it can be considered that the second person detection information includes the presence of a portrait in the image data, so that the situation of the person can be directly determined as the target area. Or, by performing portrait detection on the image data, a portrait detection result can be obtained, and the portrait detection result may include that there is no portrait in the image data. At this time, it can be considered that the second person detection information includes the image data and there is no portrait, so that the person can be directly determined. The situation is that there is no one in the target area.

In another implementation scenario, the shooting range of the image acquisition device may only cover the doorway of the target area, and then the image data collected by the image acquisition device may be subjected to portrait detection to obtain a portrait detection result. The portrait detection result may specifically include image data Whether there is a portrait in the , and if there is a portrait, whether it is entering the door or going out, in this case, the aforementioned second person detection information may specifically include the portrait detection result. Further, it is possible to compare the number of times that the presence of a portrait enters the door and the number of times that there is a presence of a portrait to go out, and based on the comparison result, determine the personnel situation, that is, determine whether there is a person in the target area. For example, performing portrait detection on the image data to obtain a portrait detection result, the portrait detection result may include the presence of a portrait, and the presence of a portrait entering the door, and after statistics, the number of times that there is a portrait entering the door is H, and the number of times that there is a portrait going out is 1, then If H is greater than I, it can be considered that the personnel situation includes that the target area is occupied, otherwise it can be considered that the personnel situation includes that the target area is unoccupied.

Taking the collection device including the target sensing device as an example, in this case, the personnel detection information corresponding to the target sensing device can be obtained based on the sensing data sensed by the target sensing device, in order to facilitate the distinction from the personnel detection information corresponding to other collection devices. , the person detection information corresponding to the target sensing device may be referred to as the third person detection information.

In an implementation scenario, target sensing devices can be deployed inside the door and outside the door, and each time the sensing data sensed by the target sensing device outside the door is received first, and then the sensing data sensed by the target sensing device inside the door, can be The state of someone returning is generated, and each time the sensing data sensed by the target sensing device inside the door is received first, and then the sensing data sensed by the target sensing device outside the door, the state that someone has left can be generated. In this case, the above-mentioned third The person detection information may specifically include: the generation times H of the state where someone came back and the generation number I of the state where someone left.

In another implementation scenario, as mentioned above, the third person detection information may specifically include: the generation times H of the state where someone came back and the number I generated when the person left the state. In this case, the generation times of the state where someone came back can be compared. H and the generation number I of the person leaving the state, and based on the comparison result, determine the person situation, that is, whether there is a person in the target area. Specifically, in the case where the generation times H of the person returning state is greater than the generation number I of the person leaving state, it can be determined that the target area is occupied, otherwise it can be determined that the target area is unoccupied. For details, reference may be made to the foregoing related descriptions, which will not be repeated here.

It should be noted that, in order to further improve the accuracy of the personnel situation, the personnel situation can be jointly determined by combining the collected data corresponding to a variety of acquisition devices, so that by combining the multimodal acquisition data, it can be beneficial to reduce the single-modal acquisition data determination. Errors that may be caused by personnel conditions and improve the accuracy of personnel conditions.

Taking the acquisition device including door switch sensing device and image acquisition device as an example, the shooting range of the image acquisition device can only cover the doorway of the target area, or can cover the entire target area. According to the entry and exit data, the aforementioned first person detection information can be obtained, and based on the portrait detection result of the image data collected by the image acquisition device, the aforementioned second person detection information can be obtained, so that the first person detection information and the second person detection information can be combined. Two people detect the information to determine the situation of the people (that is, whether there are people in the target area).

In an implementation scenario, as described above, in the case that the shooting range of the image acquisition device covers the entire target area, the second person detection information may include whether there is a person in the target area, and the first person detection information may include: someone comes back The generation times H of the state and the generation times I of people leaving the state, by comparing the generation times H and the generation times I, an initial personnel situation A (that is, whether there is a person in the target area) can be determined to be obtained. Further, the above-mentioned personnel situation A can be verified by using the second personnel detection information to obtain the final personnel situation B. For example, the user uses the fingerprint to open the door to enter the target area, so the number of generation H is 1. At this time, the door has not been closed, and because the user realizes that something falls outside the target area and directly goes out, the door lock does not detect that the door lock does not use the fingerprint. The action of opening the door directly (that is, the action of unlocking the house is not detected), so the generation number I is still 0. Since the generation number H is greater than the generation number I, it is determined that there is a person in the target area, which is inconsistent with the actual situation. That is to say, in actual application, there may be errors in the personnel situation determined by the collected data of the door lock, so the second detection information can be used to correct the personnel situation in the above-mentioned target area to obtain the final personnel situation (that is, the target area). area unoccupied).

In another implementation scenario, as mentioned above, in the case that the shooting range of the image acquisition device only covers the doorway of the target area, the second person detection information may include the current number of times that a person enters the door and the number of times that a person exits the door. is 1, and the first personnel detection information may include: the generation times H of the state that someone came back and the generation times I of the state that someone left, and by comparing the generation times H and the generation times I, it can be determined to obtain an initial personnel situation C (that is, the target whether the area is occupied). Further, the above-mentioned personnel situation C can be verified by using the second personnel detection information, and the final personnel situation D can be obtained. For example, the user uses the fingerprint to open the door to enter the target area, so the number of generation H is 1 time, and the door is closed at this time. When the user is going to go out for a party, he does not use the fingerprint to directly open the door (that is, the action of unlocking the house is detected), so the number of generation I is 1. When the door is about to close, the user receives a notification of the cancellation of the party, and the user returns to the target area and closes the door. Since the number of generation H is equal to the number of generation I, it is determined that there is no one in the target area, which is inconsistent with the actual situation. That is to say, in actual application, there may be errors in the personnel situation determined by the collected data of the door lock, so the second detection information can be used to correct the unmanned personnel situation in the above target area to obtain the final personnel situation (ie target area is occupied).

Taking the acquisition device including door switch sensing device, target sensing device and image acquisition device as an example, the target sensing device may include in-door target sensing device and out-door target sensing device respectively deployed in the door and outside the door, and the image acquisition device The shooting range can cover the entire target area, or only the doorway of the target area. In this case, based on the entry and exit data collected by the door switch sensing device, the aforementioned first person detection information can be obtained. The portrait detection result of the obtained image data can obtain the aforementioned second person detection result, and based on the sensing data sensed by the target sensing device, the aforementioned third person detection information can be obtained. As mentioned above, the first person detection information It can include: the generation times H of someone returning state and the generation number I of someone leaving state, and the third person detection information can also include: the generation number H of someone returning state and the generation number I of someone leaving state. On this basis, the first personnel detection information, the second personnel detection information and the third personnel detection information can be combined to determine the personnel situation (that is, whether there is a person in the target area).

In an implementation scenario, the generation times H of the person returning state and the generation number I of the person leaving state in the first person detection information can be compared to obtain the comparison result A, and at the same time, the person returning state in the third person detection information can be compared. The generation times H and the generation times I of someone leaving the state are obtained, and the comparison result B is obtained. If the comparison result A and the comparison result B are consistent (that is, the generation times H in the first person detection information and the third person detection information are greater than the generation times I, Alternatively, if the generation times H in the first person detection information and the third person detection information are not greater than the generation times I), it is possible to directly determine whether there is a person in the target area based on the comparison result A or the comparison result B. For the specific method of determining whether there is a person in the target area, you can refer to the above-mentioned related descriptions, which will not be repeated here; on the contrary, if the comparison result A and the comparison result B are inconsistent, the portrait detection results based on the image data collected by the camera can continue to be obtained. The second person detection information, and based on the second person detection information, determine whether there is a person in the target area, and the specific method of determining whether there is a person in the target area can refer to the foregoing related descriptions, which will not be repeated here.

In another implementation scenario, the first person detection information and the third person detection information can be compared to see if the number of times H of people coming back is the same, a comparison result C can be obtained, and the first person detection information and the third person detection information can be compared. Whether the generation times I of the person leaving the state are the same, the comparison result D is obtained. If both the comparison result C and the comparison result D indicate that the comparison is the same, it is possible to directly determine whether there is a person in the target area based on the above comparison result A or comparison result B, and specifically determine the target. For the method of whether there is a person in the area, you can refer to the above-mentioned related description, which will not be repeated here; on the contrary, if any one of the comparison result C and the comparison result D indicates that the comparison is different, you can continue to use the image data collected by the image collection device. The second person detection information is obtained, and based on the second person detection information, it is determined whether there is a person in the target area, and the specific method of determining whether there is a person in the target area can be referred to the foregoing related descriptions, which will not be repeated here.

It should be noted that, as mentioned above, the collection data obtained by the collection device can obtain personnel detection information from the cloud device (or decision-making device), and the decision-making device further determines the personnel situation in the target area based on the personnel detection information ( That is, whether there is a person in the target area), the decision-making device can further determine the state of the device to be awakened in the target area according to the personnel situation. Specifically, if there is a person in the target area, the state of the device to be woken up may be determined as the wake-up allowed state; otherwise, if there is no one in the target area, the state of the device to be woken up may be determined as the wake-up prohibited state.

As mentioned above, the personnel situation may include two situations: the target area is occupied and the target area is unmanned. In order to further reduce the false wake-up rate, the personnel situation may further include: the target area is occupied and in an active state, and the target area is occupied and in sleep. There are three situations: status and target area unmanned. Still taking the acquisition device including the image acquisition device as an example, the shooting range of the image acquisition device can cover the entire target area, in this case, based on the portrait detection result of the image data collected by the image acquisition device, the aforementioned second can be obtained. The person detection result, and the second person detection information may include whether there is a person and whether the person is in an active state or a sleep state. On this basis, the second person detection information can be used to determine the situation of the person.

In one implementation scenario, a portrait detection may be performed on the image data collected by the image acquisition device to obtain a portrait detection result. The portrait detection result may specifically include whether there is a person in the image data and whether the person is in an active state or a sleeping state. Here In this case, the aforementioned second person detection information may specifically include a portrait detection result. Further, the situation of the person may be determined directly based on the second person detection information. For example, by performing portrait detection on the image data, a portrait detection result can be obtained. The portrait detection result can include that the target area is occupied and the person is in a sleeping state. At this time, it can be directly determined that the person is in the target area and is in a sleeping state; The data is subjected to portrait detection, and the portrait detection result can be obtained. The portrait detection result can include no one in the target area. At this time, it can be directly determined that the personnel situation is no one in the target area; or, by performing portrait detection on the image data, the portrait detection result can be obtained. The portrait detection result may include that the target area is occupied and active.

It should be noted that, as mentioned above, the collection data obtained by the collection device can obtain personnel detection information from the cloud device (or the decision-making device), and the decision-making device further determines the personnel situation in the target area based on the personnel detection information. The decision-making device may further determine the state of the device to be awakened in the target area according to the personnel situation. Specifically, if the target area is occupied and in an active state, the state of the device to be woken up may be determined as a wake-up allowed state, and if the target area is in a sleep state, the state of the device to be woken up may be determined as a wake-up prohibited state. If there is no one in the target area, the state of the device to be woken up can be determined as the state of prohibiting wake-up accordingly.

Step S22: In response to the wake-up confirmation request sent by the device to be woken up, based on the state of the device to be woken up, indicate whether the device to be woken up wakes up in the voice interaction mode.

In an implementation scenario, once the device to be woken up collects audio data, it can generate a wake-up confirmation request. For example, a wake-up confirmation request can be generated when the device to be woken collects audio data "disconnected", or collects audio data "starts sweeping", or collects audio data "starts cooking".

In another implementation scenario, in order to improve the accuracy of generating the wake-up confirmation request and prevent the decision-making device from frequently responding to the wake-up confirmation request, after collecting the audio data, the device to be woken up can also detect whether the audio data contains preset words. If the word is preset, the wake-up confirmation request may be generated, otherwise, the wake-up confirmation request may not be generated. The preset words can be specifically set to phrases that are unlikely to be used in daily life, for example, can be set to "XX voice assistant", "XX life assistant", etc., which are not limited here. For example, if the device to wake up collects the audio data "XX voice assistant, please disconnect the smart socket in the bedroom", since the audio data contains the preset word "XX voice assistant", the device to wake up can generate a wake-up confirmation request, or , the device to be woken up collects the audio data "This movie is good today", since the audio data does not contain the preset word "XX voice assistant", the device to be woken up may not generate a wake-up confirmation request. Other situations can be deduced by analogy, and no examples are given here.

In an implementation scenario, if the decision-making device receives a wake-up confirmation request from the device to be woken up, it can jointly indicate whether the device to be woken up wakes up the voice interaction mode at this time, that is, instructs to execute the wake-up voice interaction mode, in combination with the state of the device to be woken up. Or indicate that the wake-up voice interaction mode is not performed. It should be noted that if the wake-up voice interaction mode is instructed, it means that the device to be woken up will be switched to "awakened device", which can respond to the user's voice command, and if it is instructed not to perform the wake-up voice interaction mode, it means that the wake-up voice interaction mode is not executed. The device to be woken up will not be switched to "awakened device", that is, the device to be woken up still cannot respond to the user's voice command. Specifically, in the case where the state of the device to be woken up is determined to be the above-mentioned wake-up allowed state, the device to be woken up may be instructed to execute the wake-up voice interaction mode; on the contrary, in the case that the state of the device to be woken up is determined to be the above-mentioned wake-up prohibited state, The device to be woken up can be instructed not to execute the above-mentioned wake-up voice interaction mode.

In another implementation scenario, as described above, if audio data is collected and contains preset words, the device to be woken up may generate a wake-up confirmation request. Further, the device to be woken up can package the audio data into the wake-up confirmation request. If the device to be woken up is in a state of prohibiting wake-up, the decision-making device can instruct the device to be woken up not to perform the above-mentioned wake-up voice interaction mode, and if the device to be woken up is allowed to wake up. In the wake-up state, the decision-making device can further detect the above-mentioned wake-up audio data, and if the preset words are also detected, the decision-making device can instruct the device to be woken up to execute the above-mentioned wake-up voice interaction mode. In the above manner, when the device to be woken up collects audio data and also detects that the audio data contains preset words, it generates a wake-up confirmation request and the wake-up confirmation request contains audio data, and the decision-making device further verifies the audio data in the wake-up confirmation request. Perform secondary detection, and instruct the device to be awakened to execute the wake-up voice interaction mode when the secondary detection also determines that the audio data contains preset words, which can help reduce the false detection rate of preset words in the audio data , which can further reduce the false wake-up rate.

In the above solution, the decision-making device determines the state of the device to be awakened in the target area based on the situation of the people in the target area, and the state indicates whether the device to be awakened is allowed to wake up or not allowed to wake up, and responds to the wake-up confirmation from the device to be awakened Request, based on the state of the device to be awakened, to indicate whether the device to be awakened wakes up in the voice interaction mode. Since the state of the device to be awakened is determined by the decision-making device based on the situation of the people in the target area, it can help to improve the state of the device to be awakened. Accuracy, that is, it can help to improve the accuracy of determining whether the device to be woken up is allowed to wake up. Compared with the voice interaction mode of directly waking up in response to the wake-up confirmation request, by combining the wake-up confirmation request from the device to be woken up and the wake-up confirmation request of the device to be awakened. state, and together indicate whether the device to be woken wakes up in the voice interaction mode, which can help reduce the false wake-up rate.

Please refer to FIG. 3 , which is a schematic diagram of a framework of an embodiment of an electronic device 30 of the present application. As shown in FIG. 3 , the electronic device 30 may include a processor 31, a memory 32, and a communication circuit 33. The memory 32 and the communication circuit 33 are coupled to the processor 31; the memory 32 stores program instructions, and the processor 31 is used for executing the program instructions. In order to implement the steps in any of the foregoing device wake-up method embodiments. Specifically, the electronic device 30 may include, but is not limited to, a television, a NAS, a set-top box, etc., which is not limited herein.

The processor 31 may also be referred to as a CPU (Central Processing Unit, central processing unit), and the processor 31 may be an integrated circuit chip with signal processing capability. The processor 31 may also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. A general purpose processor may be a microprocessor or the processor 31 may be any conventional processor or the like.

In the embodiment of the present disclosure, the processor 31 is configured to determine the state of the device to be awakened in the target area based on the personnel situation in the target area, wherein the state of the device to be awakened indicates whether the device to be awakened is allowed to wake up; the processor 31 is configured to control The communication circuit 33 and itself, in response to the wake-up confirmation request sent by the device to be woken up, indicate whether the device to be woken up wakes up in the voice interaction mode based on the state of the device to be woken up.

In some disclosed embodiments, the personnel situation in the target area is determined based on the personnel detection information in the target area sent by the cloud device. Different from the previous embodiments, the cloud device determines the personnel detection information of the target area, and the cloud device can perform the work of large computational workload such as confirming the personnel detection information, which can effectively reduce the computational load of the decision-making device and also The ability to deploy more sophisticated mathematical operation models on cloud devices is conducive to improving the accuracy of personnel conditions.

In some disclosed embodiments, the processor 31 is configured to control the communication circuit 33 to receive the person detection information of the target area obtained by the cloud device based on the collected data, wherein the collected data is obtained by the collection device from the target area; the processor 31 is configured to Based on the personnel detection information, the personnel situation in the target area is obtained. Different from the foregoing embodiments, the collection data is acquired by the cloud device, and based on the collected data, the situation of people in the target area is determined, and the situation of people in the target area is further sent to the decision-making device for the decision-making device to pass through the target area. To determine the state of the device to be woken up, because the cloud device often has stronger processing power than the decision-making device, it can run a more complex and accurate mathematical model to process the collected data, so as to improve the accuracy of the personnel situation, so as to be able to It is beneficial to improve the accuracy of determining the obtained state of the device to be woken up, and reduce the processing load of the decision-making device.

In some disclosed embodiments, the collecting device includes at least one of a door switch sensing device, an image collecting device, and a target sensing device, and the collected data includes access and door data collected by the door switch sensing device, and image data collected by the image collecting device and at least one of sensing data of the target sensing device. Different from the foregoing embodiments, the collection device includes at least one of a door switch sensing device, an image collection device, and a target sensing device, and the collected data includes entry and exit data collected by the door switch sensing device, and image data collected by the image collection device. , at least one of the sensing data of the target sensing device, so it can be beneficial to integrate multi-modal acquisition data to determine the personnel situation, thereby further improving the accuracy of the personnel situation.

In some disclosed embodiments, the person detection information of the target area includes at least one of the following: the person detection information corresponding to the door switch sensing device obtained based on the entry and exit data; the image acquisition result obtained based on the portrait detection result of the image data Person detection information corresponding to the device; based on the sensing data, the personnel detection information corresponding to the target sensing device is obtained. Different from the foregoing embodiments, the personnel detection information of the target area includes at least one of personnel detection information corresponding to the door switch sensing device, personnel detection information corresponding to the image acquisition device, and personnel detection information corresponding to the target sensing device, that is, It is possible to collect data based on different modalities, which is beneficial to obtain personnel detection information based on the multimodal acquisition data, and is beneficial to improve the accuracy of personnel conditions.

In some disclosed embodiments, the person detection information corresponding to the door switch sensing device includes: someone coming back state and someone leaving state, the someone coming back state is generated by the cloud device receiving the door entry data collected by the door switch sensing device, and the someone leaving state It is generated by the cloud device receiving the exit data collected by the door switch sensing device. The processor 31 is used to compare the generation times of the person returning state and the person leaving state when the collection device includes the door switch sensing device, based on the comparison result. Determine if the target area is occupied. Different from the previous embodiment, the cloud device generates the status of someone coming back when it receives the entry data, and generates the status that someone leaves when it receives the data going out. Determining whether there is a person in the target area based on the comparison result can help to improve the accuracy of determining whether there is a person in the target area.

In some disclosed embodiments, the processor 31 is configured to determine the state of the device to be woken up as a state allowing wake-up when there are people in the target area; the processor 31 is configured to set the device to be woken up when there is no one in the target area The state is determined to be the wake-up disabled state. Different from the foregoing embodiments, if there is a person in the target area, the state of the device to be awakened is determined to be in the wake-up allowed state accordingly, and if there is no one in the target area, the state of the device to be awakened is determined to be in the state of prohibition of wake-up accordingly, which can help reduce the false wake rate.

In some disclosed embodiments, the processor 31 is configured to instruct the device to be woken up to execute the wake-up voice interaction mode when the state of the device to be woken up is the wake-up enabled state; the processor 31 is configured to instruct the device to be woken up to prohibit wake-up in the state of the device to be woken up. In the case of the state, it indicates that the device to be woken up does not execute the wake-up voice interaction mode. Different from the foregoing embodiments, if the device to be awakened is determined to be in the wake-up allowed state, the device to be awakened is instructed to execute the above-mentioned wake-up voice interaction mode, and if the device to be awakened is determined to be in the wake-up-prohibited state, the device to be awakened is instructed not to perform the above-mentioned wake-up. Voice interaction mode, so it can help to reduce the false wake-up rate.

In some disclosed embodiments, the wake-up confirmation request is generated when the to-be-awakened device collects audio data and detects that the audio data contains preset words, and the processor 31 is configured to use the processor 31 when the state of the to-be-awakened device is the wake-up allowed state Next, the audio data included in the wake-up confirmation request is detected; the processor 31 is configured to instruct the device to be woken up to execute the wake-up voice interaction mode when it is detected that the audio data includes a preset word. Different from the foregoing embodiments, when audio data is collected and it is also detected that the audio data contains preset words, the device to be woken up generates a wake-up confirmation request, and the wake-up confirmation request contains audio data, and the decision-making device further determines the audio data. Perform secondary detection, and in the case where the secondary detection also determines that the preset words are contained, the decision-making device instructs the device to be awakened to execute the wake-up voice interaction mode, which can help reduce the false detection rate of preset words in the audio data, This can further reduce the false wake-up rate.

Please refer to FIG. 4 , which is a schematic diagram of a framework of an embodiment of a computer-readable storage medium 40 of the present application. The computer-readable storage medium 40 stores program instructions 41 that can be executed by the processor, and the program instructions 41 are used to implement the steps in any of the foregoing embodiments of the device wake-up method.

The above solution can reduce the false wake-up rate.

Specifically, the storage device may be a medium that can store program instructions, such as a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, or also It can be a server that stores the program instructions, and the server can send the stored program instructions to other devices for running, or can also run the stored program instructions by itself.

In addition, the present application also provides a device wake-up device, comprising a state determination module and a mode indication module, the state determination module is configured for the decision-making device to determine the state of the device to be awakened in the target area based on the personnel situation in the target area, wherein , the state of the device to be awakened indicates whether the device to be awakened is allowed to wake up; the mode indicating module is configured to indicate whether the device to be awakened wakes up in the voice interaction mode based on the state of the device to be awakened in response to a wakeup confirmation request sent by the device to be awakened.

In some disclosed embodiments, the personnel situation in the target area is determined based on the personnel detection information in the target area sent by the cloud device.

In some disclosed embodiments, the device wake-up device further includes an information receiving module configured to receive personnel detection information of the target area obtained by the cloud device based on the collected data, wherein the collected data is obtained by the collection device from the target area; the device The wake-up device further includes a personnel analysis module, which is configured to obtain the personnel situation in the target area based on the personnel detection information.

In some disclosed embodiments, the collecting device includes at least one of a door switch sensing device, an image collecting device, and a target sensing device, and the collected data includes access and door data collected by the door switch sensing device, and image data collected by the image collecting device and at least one of sensing data of the target sensing device.

In some disclosed embodiments, the person detection information of the target area includes at least one of the following: the person detection information corresponding to the door switch sensing device obtained based on the entry and exit data; the image acquisition result obtained based on the portrait detection result of the image data Person detection information corresponding to the device; based on the sensing data, the personnel detection information corresponding to the target sensing device is obtained.

In some disclosed embodiments, the person detection information corresponding to the door switch sensing device includes: someone coming back state and someone leaving state, the someone coming back state is generated by the cloud device receiving the door entry data collected by the door switch sensing device, and the someone leaving state It is generated by the cloud device receiving the exit data collected by the door switch sensing device; the personnel analysis module is specifically configured to use the generation times of the state of someone returning and the state of leaving when the collection device includes the door switch sensing device. Determines whether the target area is occupied based on the comparison result.

In some disclosed embodiments, the state determination module includes a first determination sub-module configured to determine the state of the device to be woken up as a wake-up allowed state when there are people in the target area; the state determination module includes a second determination sub-module , which is configured to determine the state of the device to be woken up as a wakeup-inhibiting state when there is no one in the target area.

In some disclosed embodiments, the mode indicating module includes a first indicating sub-module configured to instruct the device to be woken up to execute a wake-up voice interaction mode when the state of the device to be woken up is a state allowing wake-up; the mode indicating module includes a first The second instructing submodule is configured to instruct the device to be woken up not to perform the wake-up voice interaction mode when the state of the device to be woken up is the wake-up prohibited state.

In some disclosed embodiments, the wake-up confirmation request is generated when the device to be woken up collects audio data and detects that the audio data contains preset words; the first indication sub-module includes an audio detection unit configured to be woken up when the device is to wake up. When the state of the device is the wake-up allowed state, the audio data contained in the wake-up confirmation request is detected; the first indication sub-module includes a wake-up indication unit, which is configured to indicate that the audio data contains a preset word when it is detected. The device to be woken up executes the wake-up voice interaction mode.

In some disclosed embodiments, the decision-making device includes at least one of the following features: the decision-making device is located in the target area, and the processing capability of the decision-making device is stronger than that of the device to be awakened; and/or, the decision-making device and the device to be awakened use short-range wireless communication for communication The communication is either connected on the same local area network; and/or the target area is a home area.

In addition, the present application also provides a computer program product, which, when running on a terminal device, enables the terminal device to execute the steps in any of the foregoing device wake-up method embodiments. In the embodiments of the present application, the specific implementation form of the computer program product is not limited. Exemplarily, the computer program product can be implemented as a smart refrigerator application program, and can be installed in the smart refrigerator through factory pre-installation or user customization, so that the smart refrigerator can be used as a decision-making device and a home area such as smart door locks, cameras, etc. The smart devices are linked to perform the steps in any of the above-mentioned device wake-up method embodiments. Other situations can be deduced by analogy, and no examples are given here.

In the several embodiments provided in this application, it should be understood that the disclosed method and apparatus may be implemented in other manners. For example, the device implementations described above are only illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other divisions. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

Units described as separate components may or may not be physically separated, and components shown as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this implementation manner.

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

The integrated unit, if implemented as a software functional unit and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application can be embodied in the form of software products in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, and the computer software products are stored in a storage medium , including several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the methods of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes .

The above description is only an embodiment of the present application, and is not intended to limit the scope of the patent of the present application. Any equivalent structure or equivalent process transformation made by using the contents of the description and drawings of the present application, or directly or indirectly applied to other related technologies Fields are similarly included within the scope of patent protection of this application.

Claims

A device wake-up method, comprising:

The decision-making device determines the state of the device to be awakened in the target area based on the personnel situation in the target area, wherein the state of the device to be awakened indicates whether the device to be awakened is allowed to wake up;

In response to the wake-up confirmation request sent by the device to be woken up, based on the state of the device to be woken up, it is indicated whether the device to be woken up wakes up in the voice interaction mode.
The method according to claim 1, wherein the personnel situation in the target area is determined based on personnel detection information in the target area sent by a cloud device.
The method according to claim 2, wherein before determining the state of the device to be awakened in the target area based on the personnel situation in the target area, the method further comprises:

Receiving the personnel detection information of the target area obtained by the cloud device based on the collected data, wherein the collected data is obtained by the collection device from the target area;

Based on the personnel detection information, the personnel situation in the target area is obtained.
The method according to claim 3, wherein the collecting device comprises at least one of a door switch sensing device, an image collecting device and a target sensing device, and the collected data includes data collected by the door switch sensing device. At least one of entry and exit data, image data collected by the image collection device, and sensing data of the target sensing device.
The method according to claim 4, wherein the person detection information of the target area includes at least one of the following:

Person detection information corresponding to the door switch sensing device obtained based on the entry and exit data;

Person detection information corresponding to the image acquisition device obtained based on the portrait detection result of the image data;

Person detection information corresponding to the target sensing device is obtained based on the sensing data.
The method according to claim 5, wherein the person detection information corresponding to the door switch sensing device comprises: a person returning state and a person leaving state, and the person returning state is that the cloud device receives the door switch generated by the door entry data collected by the sensing device, and the person leaving state is generated by the cloud device receiving the exit data collected by the door switch sensing device;

The obtaining of the personnel situation in the target area based on the personnel detection information includes:

In the case where the collection device includes a door switch sensing device, whether there is a person in the target area is determined based on the comparison result by using the generation times of the person returning state and the person leaving state.
The method according to any one of claims 1 to 6, wherein the determining the state of the device to be awakened in the target area based on the personnel situation in the target area comprises:

In the case that there is a person in the target area, determining the state of the device to be woken up as a wake-up allowed state;

In the case that there is no one in the target area, the state of the device to be woken up is determined to be a wake-up prohibited state.
The method according to any one of claims 1 to 7, wherein the indicating whether the device to be awakened wakes up the voice interaction mode based on the state of the device to be awakened comprises:

In the case that the state of the device to be woken up is a wake-up allowed state, instructing the device to be woken up to execute the wake-up voice interaction mode;

In the case that the state of the device to be woken up is a wakeup-prohibited state, the device to be woken up is instructed not to wake up the voice interaction mode.
The method according to claim 8, wherein the wake-up confirmation request is generated when the device to be woken up collects audio data and detects that the audio data contains preset words;

The instructing the device to be woken up to execute the wake-up voice interaction mode when the state of the device to be woken up is a wake-up allowed state, including:

In the case that the state of the device to be woken up is a state of allowing wake-up, detecting the audio data included in the wake-up confirmation request;

In the case that it is detected that the audio data contains the preset word, the device to be woken up is instructed to perform waking up the voice interaction mode.
The method according to any one of claims 1 to 9, wherein the decision-making device includes at least one of the following features: the decision-making device is located in the target area, and the decision-making device has a stronger processing capability than the decision-making device. Describe the device to be woken up;

And/or, the decision-making device and the device to be woken up communicate by means of short-range wireless communication or are connected in the same local area network;

And/or, the target area is a home area.
A device wake-up device, characterized in that it includes:

a state determination module, configured for the decision-making device to determine the state of the device to be awakened in the target area based on the personnel situation in the target area, wherein the state of the device to be awakened indicates whether the device to be awakened is allowed to wake up;

The mode indicating module is configured to, in response to the wake-up confirmation request sent by the device to be woken up, indicate whether the device to be woken up wakes up in the voice interaction mode based on the state of the device to be woken up.
An electronic device, characterized in that it comprises a processor, a memory and a communication circuit, wherein the memory and the communication circuit are coupled to the processor; the memory stores program instructions, and the processor is used to execute the program instructions to realize any one of claims 1 to 10 The device wake-up method.
A computer-readable storage medium, characterized in that it stores program instructions that can be executed by a processor, and the program instructions are used to implement the device wake-up method according to any one of claims 1 to 10.
A device wake-up system, characterized in that it includes a decision-making device and a device to be woken up that are connected to each other, wherein the decision-making device is the electronic device according to claim 12, and the device to be woken up is located in a target area and can be In the case of waking up the voice interaction mode, execute the voice command received in the target area.
The system according to claim 14, further comprising a cloud device connected to the decision-making device, wherein the cloud device is configured to send the personnel detection information of the target area to the decision-making device, the personnel detection information Used to determine personnel status.
The system according to claim 15, further comprising a collection device located in the target area, the collection device is connected to the cloud device, and is used to obtain the collection data of the target area, and the The collection device is sent to the cloud device; the cloud device is configured to determine the personnel detection information of the target area based on the collected data.
A computer program product, characterized in that, when the computer program product runs on a terminal device, the terminal device is made to execute the device wake-up method according to any one of claims 1 to 10.