A method, device, and system for home scene recognition based on Internet of Things (IoT) devices

Abstract

This application relates to a method, apparatus, and system for home scene recognition based on Internet of Things (IoT) devices. The method includes: acquiring a map of a home scene collected by a first IoT device; the map including multiple first regions; dividing the first regions in the map into second regions according to a preset number of single scene recognition attempts; classifying and merging the second regions according to scene data collected by the first and second IoT devices from the scenes in the second regions to obtain a third region; and recognizing the home scene based on the scene data in the third region. This application solves the problem of inaccurate home scene recognition in existing technologies.

Description

Technical Field

[0001] This application relates to the field of Internet of Things (IoT) technology, and in particular to a method, apparatus, and system for identifying home scenes based on IoT devices. Background Technology

[0002] Nowadays, homes often contain multiple network-connected smart home devices such as smart cameras and robot vacuums. Robot vacuums possess mapping technology, allowing them to create a two-dimensional grid map—let's call it the first map—while cleaning the home. Figure 1 As shown, entrance information, represented by dashed lines, is extracted from the first map based on line segment information, and room information in the map is derived from this information. However, the extracted entrance information may not be accurate in real-world scenarios, and the proposed room information has a high probability of error. This is because the proposed line segment information does not necessarily represent a door to a room, and due to the lack of other feature information, this method cannot distinguish room categories such as Room 110, Room 120, and Room 130, for example, identifying room categories as bedrooms, living rooms, etc. Furthermore, open-plan family layouts are becoming increasingly common; for example, a kitchen may be located within a living room. In such scenarios, determining room locations solely based on door information is inaccurate.

[0003] There is currently no effective solution to the problem of inaccurate recognition of home scenes in existing technologies. Summary of the Invention

[0004] This embodiment provides a method, apparatus, and system for home scene recognition based on Internet of Things (IoT) devices to solve the problem of inaccurate home scene recognition in the prior art.

[0005] Firstly, this embodiment provides a method for identifying home scenes based on Internet of Things (IoT) devices, the method comprising:

[0006] Obtain a map of the home scene collected by the first IoT device; the map includes multiple first regions;

[0007] The first region in the map is divided into a second region based on a preset number of single scene recognition attempts.

[0008] Based on the scene data collected by the first IoT device and the second IoT device in the second area, the second area is classified and merged to obtain the third area;

[0009] The home scene is identified based on the scene data of the third region.

[0010] In some embodiments, the step of dividing the first region in the map according to a preset number of single scene recognitions to obtain the second region includes:

[0011] Calculate the center and boundary positions of the second region, and send the center and boundary positions of the second region to the first IoT device.

[0012] In some embodiments, the step of classifying and merging the second region based on scene data collected by the first and second IoT devices to obtain a third region includes:

[0013] Obtain the location information of the second IoT device;

[0014] Based on the location information, select the data in the scene data collected by the first IoT device that is associated with the scene data collected by the second IoT device;

[0015] Based on the associated data, the second region is classified and merged to obtain the third region.

[0016] In some embodiments, dividing the first region in the map according to a preset number of single scene recognitions to obtain the second region includes:

[0017] Each of the first regions in the map is divided into N equal parts according to the preset number of single scene recognitions N, to obtain a second region within each of the first regions.

[0018] In some embodiments, the step of classifying and merging the second region based on scene data collected by the first and second IoT devices to obtain a third region includes:

[0019] Based on the scene data collected by the first IoT device and the second IoT device on the scene of the second area, scene type identification is performed on the second area within each of the first areas;

[0020] The second regions with the same scene type in each of the first regions are merged to obtain the third region.

[0021] In some embodiments, identifying the home scene based on scene data from the third region includes:

[0022] The home scene is identified based on the scene type of the third region.

[0023] In some embodiments, dividing the first region in the map into a second region based on a preset number of single-scene recognitions includes:

[0024] Obtain the area of ​​the first region;

[0025] Based on the area of ​​the first region and the preset number of single scene recognitions, the first region in the map is divided to obtain the second region.

[0026] Secondly, this embodiment provides a method for identifying home scenes based on Internet of Things (IoT) devices, the method comprising:

[0027] A map of the home scene is collected and sent to a cloud server; the map includes multiple first areas.

[0028] The cloud server receives the center and boundary locations of the second region; the second region is obtained by the cloud server dividing the first region in the map according to a preset number of single scene recognitions.

[0029] Data is collected from the scene of the second region based on the center and boundary positions of the second region.

[0030] The collected scene data is sent to the cloud server.

[0031] Thirdly, this embodiment provides a home scene recognition device based on an Internet of Things (IoT) device, the device comprising:

[0032] The acquisition module is used to acquire a map of the home scene collected by the first IoT device; the map includes multiple first areas;

[0033] The first processing module is used to divide the first region in the map into a second region based on a preset number of single scene recognitions.

[0034] The second processing module is used to classify and merge the second region based on the scene data collected by the first IoT device and the second IoT device in the second region to obtain a third region.

[0035] The recognition module is used to recognize the home scene based on the scene data of the third area.

[0036] Fourthly, this embodiment provides a home scene recognition device based on an Internet of Things (IoT) device, the device comprising:

[0037] The first acquisition module is used to acquire a map of the home scene and send the map to a cloud server; the map includes multiple first areas;

[0038] The receiving module is used to receive the center position and boundary position of the second region sent by the cloud server; the second region is obtained by the cloud server dividing the first region in the map according to a preset number of single scene recognitions;

[0039] The second acquisition module is used to acquire scene data of the second region based on the center position and boundary position of the second region;

[0040] The sending module is used to send the collected scene data to the cloud server.

[0041] Fifthly, this embodiment provides a home scene recognition system based on Internet of Things (IoT) devices, the system including a cloud server, a first IoT device, and a second IoT device;

[0042] The cloud server is used to execute the home scene recognition method based on IoT devices as described in the first aspect;

[0043] The first IoT device is used to perform the home scene recognition method based on IoT devices as described in the second aspect;

[0044] The second IoT device is used to collect scene data.

[0045] Compared with the prior art, the home scene recognition method, device and system based on Internet of Things (IoT) devices provided in this embodiment recognizes each first area multiple times by pre-setting a single scene recognition number, and uses data collected by a second IoT device for auxiliary recognition, thereby improving the accuracy of home scene recognition and solving the problem of inaccurate home scene recognition in the prior art.

[0046] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0047] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0048] Figure 1 This is a schematic diagram of the first map in this embodiment;

[0049] Figure 2This is a hardware structure block diagram of a terminal that executes a home scene recognition method based on an Internet of Things device according to this embodiment;

[0050] Figure 3 This is a flowchart of a home scene recognition method based on IoT devices in this embodiment;

[0051] Figure 4 This is a flowchart of another home scene recognition method based on IoT devices in this embodiment;

[0052] Figure 5 This is a structural block diagram of a home scene recognition system based on Internet of Things (IoT) devices according to this embodiment;

[0053] Figure 6 This is a preferred flowchart of a home scene recognition method based on Internet of Things (IoT) devices in this embodiment;

[0054] Figure 7 This is a schematic diagram of the second map in this embodiment;

[0055] Figure 8 This is a schematic diagram of the third map in this embodiment;

[0056] Figure 9 This is a schematic diagram of the fourth map in this embodiment;

[0057] Figure 10 This is a structural block diagram of a home scene recognition device based on an Internet of Things (IoT) device according to this embodiment;

[0058] Figure 11 This is a structural block diagram of another home scene recognition device based on IoT devices in this embodiment. Detailed Implementation

[0059] To better understand the purpose, technical solution, and advantages of this application, the application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0060] Unless otherwise defined, the technical or scientific terms used in this application shall have the general meaning as understood by one of ordinary skill in the art to which this application pertains. Words such as “a,” “an,” “an,” “the,” “the,” and “these,” used in this application, do not indicate quantitative limitation and may be singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or modules (units) is not limited to the listed steps or modules (units) but may include steps or modules (units) not listed, or may include other steps or modules (units) inherent to such processes, methods, products, or devices. The terms “connected,” “linked,” and “coupled,” used in this application, are not limited to physical or mechanical connections but may include electrical connections, whether direct or indirect. The term “multiple” used in this application refers to two or more. The "and / or" operator describes the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: A alone, A and B simultaneously, and B alone. Typically, the character " / " indicates that the objects before and after it are in an "or" relationship. The terms "first," "second," and "third," etc., used in this application are merely for distinguishing similar objects and do not represent a specific ordering of the objects.

[0061] The method embodiments provided in this example can be executed on a terminal, computer, or similar computing device. For example, it can run on a terminal. Figure 2 This is a hardware structure block diagram of a terminal that executes a home scene recognition method based on an IoT device according to this embodiment. For example... Figure 2 As shown, a terminal may include one or more ( Figure 2 Only one is shown in the diagram. A processor 102 and a memory 104 for storing data are also included. The processor 102 may be, but is not limited to, a microprocessor (MCU) or a programmable logic device (FPGA). The terminal may also include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that… Figure 2 The structure shown is for illustrative purposes only and does not limit the structure of the terminal described above. For example, the terminal may also include components that are larger than... Figure 2 The more or fewer components shown, or having the same Figure 2 The different configurations shown are illustrated.

[0062] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to a home scene recognition method based on an IoT device in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the aforementioned method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0063] The transmission device 106 is used to receive or send data via a network. This network includes a wireless network provided by the terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 can be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0064] This embodiment provides a home scene recognition method based on IoT devices, applied to a cloud server. Figure 3 This is a flowchart of a home scene recognition method based on IoT devices in this embodiment, as shown below. Figure 3 As shown, the process includes the following steps:

[0065] Step S310: Obtain a map of the home scene collected by the first IoT device; the map includes multiple first areas.

[0066] Specifically, the cloud server acquires a map of the home scene collected by the first IoT device. This map includes multiple first regions. These first regions can be room areas identified by the first IoT device. For example, the first IoT device can be a robotic vacuum cleaner. The robotic vacuum cleaner possesses mapping technology and can create a two-dimensional grid map of the home scene while cleaning it. It then extracts entrance information based on line segment information on the two-dimensional grid map and derives room information from the two-dimensional grid map based on this entrance information and the line segment information, thus obtaining the first regions in the map.

[0067] Step S320: Divide the first region in the map according to the preset number of single scene recognitions to obtain the second region.

[0068] Specifically, the cloud server divides each first region in the map according to a preset number of single-scene recognition attempts, resulting in a second region within each first region. Each first region includes multiple second regions.

[0069] For example, let the preset number of single scene recognitions be N, that is, recognize each first region N times, and divide each first region in the map into N equal parts according to the preset number of single scene recognitions N, to obtain the second region within each first region.

[0070] Step S330: Based on the scene data collected by the first IoT device and the second IoT device on the scene of the second area, the second area is classified and merged to obtain the third area.

[0071] Specifically, the cloud server categorizes and merges the second region based on the scene data collected by the first and second IoT devices, resulting in a third region. The second IoT device can supplement the scene data collected by the first IoT device. The cloud server then jointly determines the category of each second region based on the scene data collected by the first and second IoT devices, and merges the second regions in the first region according to their categories, resulting in the third region. For example, the second IoT device here can be a smart camera installed in a home.

[0072] Step S340: Identify the home scene based on the scene data of the third region.

[0073] Specifically, after the cloud server determines the third region, it acquires the scene data of the third region and identifies the home scene. The scene data here includes the category of the third region.

[0074] Through the above steps, in this embodiment, each first area is identified multiple times by a preset number of single scene recognitions, and the data collected by the second IoT device is used for auxiliary recognition, thereby improving the accuracy of home scene recognition and solving the problem of inaccurate home scene recognition in the prior art.

[0075] In some embodiments, classifying and merging the second region to obtain a third region based on scene data collected by the first IoT device and the second IoT device in the second region includes: obtaining the location information of the second IoT device; selecting data from the scene data collected by the first IoT device that is associated with the scene data collected by the second IoT device based on the location information; and classifying and merging the second region based on the associated data to obtain the third region.

[0076] Specifically, the cloud server selects data from the scene data collected by the first IoT device that is related to the scene data collected by the second IoT device, based on the location information of the second IoT device. Then, based on this related data, it classifies and merges the second region to obtain the third region. This related data can be scene data collected by the second IoT device at its location that shares the same viewpoint as the scene data collected by the first IoT device, or scene data collected by the second IoT device at its location that is an extension of the scene data collected by the first IoT device. This joint judgment based on the data collected by the two IoT devices improves the accuracy of home scene recognition.

[0077] More specifically, the cloud server identifies the scene type of each second region within the first region based on the scene data collected by the first IoT device and the second IoT device for the scene in the second region; and merges the second regions with the same scene type in each first region to obtain the third region.

[0078] In some embodiments, dividing a first region in a map into a second region based on a preset number of single-scene recognitions includes: obtaining the area of ​​the first region; and dividing the first region in a map into a second region based on the area of ​​the first region and the preset number of single-scene recognitions.

[0079] Specifically, the cloud server obtains the area of ​​each first region, and divides the first region on the map into second regions based on the area of ​​the first region and the preset number of single-scene recognitions. For example, if the area of ​​one of the first regions is S and the preset number of single-scene recognitions is N, the area of ​​the first region is divided into N equal parts to obtain N second regions, and the area of ​​each second region is S / N.

[0080] This embodiment also provides another method for home scene recognition based on IoT devices, applied to the first IoT device. Figure 4 This is a flowchart of another home scene recognition method based on IoT devices in this embodiment, such as... Figure 4 As shown, the process includes the following steps:

[0081] Step S410: Collect a map of the home scene and send the map to the cloud server; the map includes multiple first areas.

[0082] Specifically, the first IoT device collects a map of the home scene and sends the collected map to the cloud server.

[0083] Step S420: Receive the center and boundary positions of the second region sent by the cloud server; the second region is obtained by the cloud server dividing the first region in the map according to a preset number of single scene recognitions.

[0084] Specifically, the first IoT device receives the center and boundary locations of a second region from the cloud server. This second region is obtained by the cloud server dividing the first region on the map based on a preset number of single-scene recognition attempts.

[0085] Step S430: Collect scene data for the second region based on the center and boundary positions of the second region.

[0086] Specifically, the first IoT device collects data about the scene in the second area based on the center and boundary positions of the second area. When the first IoT device is working, it triggers a rotation when it passes the center position of the second area, collecting image information from one full rotation.

[0087] Step S440: Send the collected scene data to the cloud server.

[0088] Specifically, the first IoT device sends the collected scene data to the cloud server. This collected scene data includes scene data from a second region collected by the first IoT device. Based on this scene data, the cloud server can determine the category of the second region and perform classification and merging of the second region.

[0089] Through the above steps, in this embodiment, each first region is identified multiple times by a preset number of single scene recognitions, thereby improving the accuracy of home scene recognition and solving the problem of inaccurate home scene recognition in the prior art.

[0090] This embodiment also provides a home scene recognition system based on Internet of Things (IoT) devices. Figure 5 This is a structural block diagram of a home scene recognition system based on Internet of Things (IoT) devices according to this embodiment, as shown below. Figure 5 As shown, the system includes: a cloud server 510, a first IoT device 520, and a second IoT device 530, wherein the cloud server 510 is connected to the first IoT device 520 and the second IoT device 530, and the first IoT device 520 and the second IoT device 530 are connected.

[0091] Specifically, the cloud server 510 is used to execute a home scene recognition method based on an Internet of Things (IoT) device provided in the aforementioned embodiments, the first IoT device 520 is used to execute another home scene recognition method based on an IoT device provided in the aforementioned embodiments, and the second IoT device 530 is used to collect scene data.

[0092] The home scene recognition system based on IoT devices provided in this embodiment uses a cloud server 510 to perform multiple recognitions on each first area by a preset number of single scene recognitions, and uses data collected by a second IoT device 530 for auxiliary recognition, thereby improving the accuracy of home scene recognition and solving the problem of inaccurate home scene recognition in the prior art.

[0093] The present embodiment will be described and explained below through specific examples.

[0094] Figure 6 This is a flowchart illustrating a specific implementation of a home scene recognition method based on IoT devices, as shown in this embodiment. Figure 6 As shown, the method includes the following steps:

[0095] Step S601: Set the number of times n can be recognized in a single scene.

[0096] Step S602: Calculate the area S of the room where the robot vacuum is located based on the second map.

[0097] Step S603: Calculate the primitive size a based on the number of times n is recognized in a single scene and the area S.

[0098] Step S604: Establish a virtual boundary based on primitive a and the outer contour of the room.

[0099] Step S605: Determine the center position of the virtual boundary based on the established virtual boundary.

[0100] Step S606: When the robot vacuum is in the center position, it rotates one full circle to collect image information.

[0101] Step S607: Determine whether there are other camera devices within the virtual boundary; if yes, proceed to step S608; if no, proceed to step S610.

[0102] Step S608: Control other camera devices to synchronously acquire image information.

[0103] Step S609: Synchronize the image information to the cloud for scene recognition.

[0104] In step S610, the cloud returns the recognition result of the current virtual boundary to the robot vacuum cleaner.

[0105] Step S611: Set the current virtual boundary to be recognized.

[0106] Step S612: Determine whether all virtual boundaries have been identified; if not, proceed to step S613; if yes, proceed to step S614.

[0107] Step S613: Control the robot vacuum cleaner to move to the center of another virtual boundary.

[0108] Step S614: Merge virtual boundaries with the same recognition results to form a new room outline.

[0109] This application proposes a dynamic primitive scene recognition method based on multi-device linkage in a home setting. This method not only utilizes the robot vacuum's own image acquisition device but also reuses image information acquired by other cameras in the home setting, solving the problem of limited viewing angle of the robot vacuum's own image acquisition device. Furthermore, based on the basic room outline information and room size of the first map, the computational primitive for scene recognition is dynamically calculated, and the same room is recognized multiple times based on this primitive, reducing the recognition error rate and enabling it to handle open home scenarios. The first map is a two-dimensional grid map constructed using SLAM technology, a function already possessed by existing robot vacuums. The computational primitive refers to the minimum spatial size for scene recognition.

[0110] Specifically, by using information collected by the robot vacuum itself and other devices in the home environment while it is cleaning, the robot vacuum calculates its own position information Pr based on the first map in real time. While cleaning, the robot vacuum can interact with a camera to confirm the camera's position information Pc in the same scene, and this position information can be marked on the first map to obtain a second map. For example... Figure 7 As shown, the location of the robot vacuum cleaner 140 in the room is obtained based on its location information Pr. Then, the positional relationship between the robot vacuum cleaner 140 and the camera 150 is obtained based on the location information Pc of multiple cameras 150. The data is then used for joint judgment based on the positional relationship between the two.

[0111] Considering the diversity of family apartment layouts and to improve the accuracy of scene recognition, multiple scene recognitions are needed for the same room, with the number of recognitions being n. This number of recognitions can be set by the user through the client or internally by the program. Since the sizes of rooms in a family setting vary, a dynamic primitive construction method is used to perform multiple scene recognitions for the same room. Based on the second map, the areas of the first room (110), the second room (120), and the third room (130) can be calculated based on the room outline information. Let the room area be S. Based on the area S and the number of recognitions for a single room (n), the room can be divided into multiple areas based on virtual boundaries. Assuming n is 4, virtual boundaries can be established as follows: Figure 8 As shown, each individual room is divided into four areas, denoted as the third map. Figure 8 The dashed lines in the diagram represent virtual boundary information.

[0112] Based on the third map, the single room in the second map is further divided into multiple areas. These multiple areas constitute the second area in this implementation, and the center of each area can be determined. When the robot vacuum 140 performs a full-coverage cleaning of the room, it triggers a rotation action when passing through the center of this area, collecting image information from one rotation. Simultaneously, if other IoT devices capable of collecting images are present in this area, they can also collect image information from the current area. These other IoT devices capable of collecting images can be cameras 150. This solves the problem of limited viewing angle of the image acquisition device carried by the robot vacuum 140 itself. The collected image information is uploaded to the cloud. The cloud uses a scene recognition model and the input image data to identify the room attributes of the area where the robot vacuum 140 is currently located and returns this information to the robot vacuum 140. After the current area is identified, it can be marked as identified to prevent duplicate identification of the same area. When it travels to the center of the next area constructed by virtual boundaries, the above operation is repeated to perform scene recognition until all areas in the room are marked as identified. Figure 9 As shown, after the entire room is identified, areas identified as belonging to the same category are connected to generate a fourth map. Different categories of areas can be marked with different colors, such as... Figure 9 As shown, the first room 110 is identified as two different scenes. For example, the dotted area of ​​the first room 110 is identified as the kitchen, and the other areas of the first room 110 excluding the dotted area are identified as the living room.

[0113] After identifying a single room, the algorithm proceeds to identify other rooms gradually, eventually identifying the entire house and recording all information on a fourth map. This embodiment can dynamically adjust the computational primitives based on the different room sizes within different houses, and can effectively handle open-plan family scenarios, overcoming the shortcomings of conventional methods that cannot identify multiple functional areas within a room.

[0114] It should be noted that the steps shown in the above process or in the flowchart of the accompanying figures can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0115] This embodiment also provides a home scene recognition device based on an Internet of Things (IoT) device. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. The terms "module," "unit," "subunit," etc., used below refer to combinations of software and / or hardware that implement a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0116] Figure 10 This is a structural block diagram of a home scene recognition device based on an Internet of Things (IoT) device according to this embodiment, such as... Figure 10 As shown, the device includes:

[0117] The acquisition module 710 is used to acquire a map of the home scene collected by the first IoT device; the map includes multiple first areas;

[0118] The first processing module 720 is used to divide the first region in the map according to the preset number of single scene recognitions to obtain the second region;

[0119] The second processing module 730 is used to classify and merge the second region based on the scene data collected by the first IoT device and the second IoT device from the scene of the second region, to obtain the third region.

[0120] The recognition module 740 is used to recognize the home scene based on the scene data of the third area.

[0121] Figure 11 This is a structural block diagram of another home scene recognition device based on IoT devices in this embodiment, such as... Figure 11 As shown, the device includes:

[0122] The first acquisition module 810 is used to acquire a map of the home scene and send the map to the cloud server; the map includes multiple first areas;

[0123] The receiving module 820 is used to receive the center position and boundary position of the second region sent by the cloud server; the second region is obtained by the cloud server dividing the first region in the map according to the preset number of single scene recognitions.

[0124] The second acquisition module 830 is used to acquire scene data of the second region based on the center position and boundary position of the second region;

[0125] The sending module 840 is used to send the collected scene data to the cloud server.

[0126] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0127] This embodiment also provides an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0128] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0129] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0130] S1, Obtain a map of the home scene collected by the first IoT device; the map includes multiple first areas;

[0131] S2, the first region in the map is divided according to the preset number of single scene recognitions to obtain the second region;

[0132] S3, Based on the scene data collected by the first IoT device and the second IoT device on the scene of the second area, the second area is classified and merged to obtain the third area;

[0133] S4 identifies the home scene based on the scene data from the third region.

[0134] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0135] Q1. Collect a map of the home scene and send the map to the cloud server; the map includes multiple first areas;

[0136] Q2, receive the center and boundary positions of the second region sent by the cloud server; the second region is obtained by the cloud server dividing the first region in the map according to the preset number of single scene recognitions;

[0137] Q3. Collect scene data for the second region based on the center and boundary positions of the second region;

[0138] Q4. Send the collected scene data to the cloud server.

[0139] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated in this embodiment.

[0140] Furthermore, in conjunction with the home scene recognition method based on IoT devices provided in the above embodiments, this embodiment can also provide a storage medium for implementation. The storage medium stores a computer program; when executed by a processor, the computer program implements the steps of any of the home scene recognition methods based on IoT devices in the above embodiments.

[0141] It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. All other embodiments derived by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0142] Obviously, the accompanying drawings are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar situations based on these drawings without any creative effort. Furthermore, it is understood that although the work done in this development process may be complex and lengthy, for those skilled in the art, certain design, manufacturing, or production modifications made based on the technical content disclosed in this application are merely conventional technical means and should not be considered as insufficient disclosure of this application.

[0143] The term "embodiment" in this application refers to a specific feature, structure, or characteristic described in connection with an embodiment that may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily imply the same embodiment, nor does it imply that it is mutually exclusive with or independent of other embodiments. It will be clearly or implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0144] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of patent protection. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the appended claims.

Claims

1.A method for recognizing a home scenario based on an Internet of Things device, the method comprising: The method comprises: acquiring a map of the home scene collected by a first Internet of Things device; the map comprises a plurality of first areas; dividing the first areas in the map according to a preset single scene recognition number, to obtain second areas; according to scene data collected by the first and second Internet of Things devices on the scenes of the second areas, selecting data associated with the scene data collected by the second Internet of Things device from the scene data collected by the first Internet of Things device, or according to the scene data collected by the first and second Internet of Things devices on the scenes of the second areas, performing scene type recognition on the second areas in each first area, to classify and merge the second areas, to obtain third areas; according to the scene data of the third areas, recognizing the home scene. 2.The IoT device-based home scenario recognition method of claim 1, wherein, After the first areas in the map are divided according to the preset single scene recognition number to obtain the second areas, the method comprises: calculating the center position and boundary position of the second areas, and sending the center position and boundary position of the second areas to the first Internet of Things device. 3.The IoT device-based home scenario recognition method of claim 1, wherein, According to the scene data collected by the first and second Internet of Things devices on the scenes of the second areas, the method comprises: acquiring position information of the second Internet of Things device; according to the position information, selecting data associated with the scene data collected by the second Internet of Things device from the scene data collected by the first Internet of Things device; according to the associated data, classifying and merging the second areas to obtain third areas. 4.The IoT device-based home scenario recognition method according to claim 1, characterized in that, According to the preset single scene recognition number, the method comprises: according to the preset single scene recognition number N, N-dividing each first area in the map, to obtain second areas in each first area. 5.The IoT device-based home scenario recognition method according to claim 1 or 4, characterized in that, According to the scene data collected by the first and second Internet of Things devices on the scenes of the second areas, the method comprises: according to the scene data collected by the first and second Internet of Things devices on the scenes of the second areas, performing scene type recognition on the second areas in each first area; merging the second areas with the same scene type in each first area to obtain the third areas. 6.The IoT device based home scenario recognition method according to any one of claims 1 to 4, characterized in that, According to the scene data of the third areas, the method comprises: according to the scene type of the third areas, recognizing the home scene. 7.The IoT device based home scenario recognition method according to any one of claims 1 to 4, characterized in that, According to the preset single scene recognition number, the method comprises: acquiring the area of the first area; according to the area of the first area and the preset single scene recognition number, dividing the first areas in the map to obtain the second areas. 8.A method for identifying a home scene based on an Internet of Things device, the method comprising: The method comprises: acquiring a map of the home scene, and sending the map to a cloud server; the map comprises a plurality of first areas; receive the center position and the boundary position of the second region sent by the cloud server; the second region is obtained by dividing the first region in the map according to a preset single scene recognition number by the cloud server; collect scene data of the second region according to the center position and the boundary position of the second region; send the collected scene data to the cloud server, so that the cloud server classifies and merges the second region to obtain a third region, and identifies the home scene according to scene data of the third region. 9.A home scene recognition apparatus based on an Internet of Things device, the apparatus comprising: The device comprises: an acquisition module configured to acquire a map of the home scene collected by a first Internet of Things device; the map comprises a plurality of first regions; a first processing module configured to divide the first regions in the map according to a preset single scene recognition number to obtain second regions; a second processing module configured to select, according to scene data collected by the first Internet of Things device and a second Internet of Things device on scenes of the second regions, data associated with scene data collected by the second Internet of Things device from scene data collected by the first Internet of Things device, or to perform scene type identification on each second region in the first regions according to scene data collected by the first Internet of Things device and the second Internet of Things device on scenes of the second regions, to classify and merge the second regions to obtain third regions; an identification module configured to identify the home scene according to scene data of the third regions. 10.A home scene recognition apparatus based on an Internet of Things device, the apparatus comprising: The device comprises: a first acquisition module configured to acquire a map of the home scene and send the map to a cloud server; the map comprises a plurality of first regions; a receiving module configured to receive the center position and the boundary position of the second region sent by the cloud server; the second region is obtained by dividing the first region in the map according to a preset single scene recognition number by the cloud server; a second acquisition module configured to collect scene data of the second region according to the center position and the boundary position of the second region; a sending module configured to send the collected scene data to the cloud server, so that the cloud server classifies and merges the second region to obtain third regions, and identifies the home scene according to scene data of the third regions. 11.A home scene recognition system based on an Internet of Things device, characterized by, The system comprises a cloud server, a first Internet of Things device, and a second Internet of Things device; the cloud server is configured to perform the home scene identification method based on the Internet of Things device in any one of claims 1 to 7; the first Internet of Things device is configured to perform the home scene identification method based on the Internet of Things device in claim 8; the second Internet of Things device is configured to collect scene data.

Images