Equipment control method and device, electronic equipment and storage medium

Abstract

The invention provides an equipment control method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a place position of a target place, and a use date corresponding to the target place; acquiring a human body posture combination corresponding to at least one human body in the target place; based on the place position, the use date and the human body posture combination, determining a target scene mode corresponding to the target place; determining a plurality of to-be-controlled devices corresponding to the target place based on the place position; and sending the target scene mode to a central control device corresponding to the target place, so that the central control device controls the plurality of to-be-controlled devices according to a control instruction corresponding to the target scene mode. Therefore, the actual use condition of the target place can be comprehensively analyzed, so that the appropriate scene mode is determined, the equipment control scheme meeting the user requirement is obtained, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of smart home technology, and in particular to a device control method, apparatus, electronic device and storage medium. Background Art

[0002] In the field of IoT (Internet of Things) intelligent control, scene automation control is an indispensable function. Through this function, after the scene is triggered, multiple smart devices associated with the scene can be controlled to switch to the corresponding working state. For example, the trigger condition associated with the smart home scene is the door magnetic opening. When the door magnetic opening is detected, the smart home scene is entered and the following linkage control is performed: turn on the living room lights, turn on the air conditioner, and close the curtains, etc.

[0003] However, the scene trigger conditions set by the current scene automation control are relatively simple and single. When faced with complex scenes, it is impossible to make appropriate scene recommendations based on complex actual usage situations, and thus it is impossible to obtain device control solutions that meet user needs. Summary of the invention

[0004] The present application provides a device control method, apparatus, electronic device and storage medium to solve the problem in the prior art that scene automation control cannot recommend appropriate scenes according to complex actual usage conditions, and thus cannot obtain a device control solution that meets user needs.

[0005] In a first aspect, the present application provides a device control method, comprising:

[0006] Obtaining the location of the target place and the usage date corresponding to the target place;

[0007] Acquire a human body posture combination corresponding to at least one human body in the target location;

[0008] Determining a target scene mode corresponding to the target place based on the place location, the use date and the human body posture combination;

[0009] Determine a plurality of to-be-controlled devices corresponding to the target location based on the location of the location;

[0010] The target scene mode is sent to a central control device corresponding to the target location, so that the central control device controls the plurality of devices to be controlled according to control instructions corresponding to the target scene mode.

[0011] In a possible implementation, the acquiring a human body posture combination corresponding to at least one human body in the target location includes:

[0012] Acquire an image frame sequence collected for the target location, wherein the image frame sequence includes a plurality of continuous image frames;

[0013] For each image frame, identifying the image frame to obtain at least one human body and a human body posture of each human body;

[0014] Determine the motion state of each of the human bodies based on at least one human body corresponding to each of the image frames and the human body posture of each of the human bodies;

[0015] A combination of motion states corresponding to at least one of the human bodies is determined as the human body posture combination.

[0016] In a possible implementation, the identifying the image frame to obtain at least one human body and a human posture of each human body includes:

[0017] Dividing the image frame into a plurality of part regions, wherein each of the part regions includes a human body part;

[0018] For each part region, determining a region distance between the part region and an adjacent part region, and dividing the plurality of part regions into at least one human body based on the region distance;

[0019] For each human body, a slope formula for each part area corresponding to the human body is determined, and the human body posture of the human body is determined based on all the slope formulas corresponding to the human body.

[0020] In a possible implementation manner, dividing the image frame into a plurality of part regions includes:

[0021] Dividing the image frame into a plurality of color blocks;

[0022] The color value of each color block is extracted one by one, and the color blocks with the same corresponding color value are marked as a region, thereby obtaining multiple regions;

[0023] A human body region is determined among the plurality of regions, and a part region is determined among the human body regions.

[0024] In a possible implementation, the acquiring a human body posture combination corresponding to at least one human body in the target location includes:

[0025] Acquire pictures collected for the target location;

[0026] Recognize the image to obtain at least one human body and a human posture corresponding to each human body;

[0027] A combination of human body postures corresponding to at least one of the human bodies is determined as the human body posture combination.

[0028] In a possible implementation, determining the target scene mode corresponding to the target place based on the place location, the use date and the human body posture combination includes:

[0029] Determining a venue type corresponding to the target venue based on the venue location;

[0030] Determining date marking information corresponding to the use date;

[0031] Determine a target posture combination consistent with the human body posture combination in a preset posture combination set;

[0032] Based on the location type, the date mark information and the target posture combination, a target scene mode is determined in a preset scene mode set.

[0033] In a possible implementation manner, determining a plurality of to-be-controlled devices corresponding to the target place based on the place location includes:

[0034] Obtaining a device set corresponding to the target location;

[0035] determining a device location of each device in the set of devices;

[0036] The device whose corresponding device location is the same as the location of the place is determined as the device to be controlled.

[0037] In a second aspect, the present application provides a device control apparatus, comprising:

[0038] A first acquisition module is used to acquire the location of a target place and the usage date corresponding to the target place;

[0039] A second acquisition module is used to acquire a human body posture combination corresponding to at least one human body in the target location;

[0040] A mode determination module, used to determine a target scene mode corresponding to the target place based on the place location, the use date and the human posture combination;

[0041] A device determination module, used for determining a plurality of to-be-controlled devices corresponding to the target location based on the location of the location;

[0042] The device control module is used to send the target scene mode to the central control device corresponding to the target place, so that the central control device controls the multiple devices to be controlled according to the control instructions corresponding to the target scene mode.

[0043] In a possible implementation manner, the second acquisition module is specifically configured to:

[0044] Acquire an image frame sequence collected for the target location, wherein the image frame sequence includes a plurality of continuous image frames;

[0045] For each image frame, identifying the image frame to obtain at least one human body and a human body posture of each human body;

[0046] Determine the motion state of each of the human bodies based on at least one human body corresponding to each of the image frames and the human body posture of each of the human bodies;

[0047] A combination of motion states corresponding to at least one of the human bodies is determined as the human body posture combination.

[0048] In a possible implementation manner, the second acquisition module is further configured to:

[0049] Dividing the image frame into a plurality of part regions, wherein each of the part regions includes a human body part;

[0050] For each part region, determining a region distance between the part region and an adjacent part region, and dividing the plurality of part regions into at least one human body based on the region distance;

[0051] For each human body, a slope formula for each part area corresponding to the human body is determined, and the human body posture of the human body is determined based on all the slope formulas corresponding to the human body.

[0052] In a possible implementation manner, the second acquisition module is further configured to:

[0053] Dividing the image frame into a plurality of color blocks;

[0054] The color value of each color block is extracted one by one, and the color blocks with the same corresponding color value are marked as a region, thereby obtaining multiple regions;

[0055] A human body region is determined among the plurality of regions, and a part region is determined among the human body regions.

[0056] In a possible implementation manner, the second acquisition module is further configured to:

[0057] Acquire pictures collected for the target location;

[0058] Recognize the image to obtain at least one human body and a human posture corresponding to each human body;

[0059] A combination of human body postures corresponding to at least one of the human bodies is determined as the human body posture combination.

[0060] In a possible implementation manner, the mode determination module is specifically configured to:

[0061] Determining a venue type corresponding to the target venue based on the venue location;

[0062] Determining date marking information corresponding to the use date;

[0063] Determine a target posture combination consistent with the human body posture combination in a preset posture combination set;

[0064] Based on the location type, the date mark information and the target posture combination, a target scene mode is determined in a preset scene mode set.

[0065] In a possible implementation manner, the device determination module is specifically configured to:

[0066] Obtaining a device set corresponding to the target location;

[0067] determining a device location of each device in the set of devices;

[0068] The device whose corresponding device location is the same as the location of the place is determined as the device to be controlled.

[0069] In a third aspect, the present application provides a device, comprising: a processor and a memory, wherein the processor is used to execute a device control program stored in the memory to implement the device control method described in any one of the first aspects.

[0070] In a fourth aspect, the present application provides a storage medium storing one or more programs, wherein the one or more programs can be executed by one or more processors to implement the device control method described in any one of the first aspects.

[0071] The above technical solution provided by the embodiment of the present application has the following advantages over the prior art: the method provided by the embodiment of the present application, first, obtains the location of the target place, and the use date corresponding to the target place, then obtains the human posture combination corresponding to at least one human body in the target place, and then, based on the location of the place, the use date and the human posture combination, determines the target scene mode corresponding to the target place, and determines the multiple devices to be controlled corresponding to the target place based on the location of the place; finally, sends the target scene mode to the central control device corresponding to the target place, so that the central control device controls the multiple devices to be controlled according to the control instructions corresponding to the target scene mode. Through this solution, the actual use of the target place can be comprehensively analyzed according to the geographical location of the target place, the human posture in the target place, and the date of use of the target place, so as to determine the appropriate scene mode, so as to obtain a device control solution that meets user needs and improve user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0073] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0074] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0075] Figure 1 A flow chart of an embodiment of a device control method provided in an embodiment of the present application;

[0076] Figure 2 A flowchart of an embodiment of the present application for obtaining a combination of human body postures corresponding to at least one human body in the target location;

[0077] Figure 3 A flowchart of another embodiment of obtaining a human body posture combination corresponding to at least one human body in the target location provided in an embodiment of the present application;

[0078] Figure 4 A block diagram of an embodiment of a device control device provided in an embodiment of the present application;

[0079] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0080] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0081] The disclosure below provides many different embodiments or examples to realize the different structures of the present application. In order to simplify the disclosure of the present application, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present application. In addition, the present application can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0082] In order to solve the technical problem that the scene trigger conditions set for the scene automation control in the prior art are relatively simple and single, and when faced with complex scenes, it is impossible to recommend suitable scenes based on complex actual usage situations, thereby failing to obtain a device control solution that meets user needs, the present application provides a device control method that can comprehensively analyze the actual usage of the target place according to the geographical location of the target place, the posture of the human body in the target place, and the date of use of the target place, so as to determine a suitable scene mode, thereby obtaining a device control solution that meets user needs and improving user experience.

[0083] Figure 1 This is a flow chart of an embodiment of a device control method provided in an embodiment of the present application. The method is applied to a smart home management platform, such as Figure 1 As shown, the method comprises the following steps:

[0084] Step 101: Obtain the location of a target place and the usage date corresponding to the target place.

[0085] In the application, the target location can be an office building, dance studio, gym, apartment, or any other place that requires intelligent control equipment.

[0086] The location of a place refers to the location of a target place, which can be obtained through positioning information uploaded by a mobile terminal (such as a user's mobile phone) in the target place.

[0087] The date of use refers to the date on which the target location is used. It is generally the date on which the user uploads the location information by default, or it can be a future date input by the user.

[0088] Step 102: Acquire a human body posture combination corresponding to at least one human body in the target location.

[0089] A human body posture combination refers to a combination of postures of at least one human body located in a target location.

[0090] In one embodiment, the posture may be a static posture of a human body. For example, a combination of human body postures in an office building is generally: multiple people sitting on chairs with their hands on the table.

[0091] In another embodiment, the posture may be a dynamic movement of the human body. For example, the combination of human body postures in a dance studio is generally: dancing, waving arms, and occasional jazz movements, etc. For another example, the combination of human body postures in a gym is generally: lifting dumbbells, running, etc.

[0092] As for how to obtain the human body posture combination corresponding to at least one human body in the target location, it will be described in detail through different embodiments later, and will not be described in detail here.

[0093] Step 103: Determine a target scene mode corresponding to the target place based on the place location, the use date and the human body posture combination.

[0094] In actual applications, scene mode related information can be set in advance on the smart home management platform, as shown in Table 1.

[0095] Table 1

[0096]

[0097] Based on this, in the embodiment of the present application, based on the location of the place, the date of use and the combination of human body postures, determining the target scene mode corresponding to the target place may specifically include the following steps:

[0098] Step A1, determining a venue type corresponding to the target venue based on the venue location;

[0099] Step A2, determining the date marking information corresponding to the usage date;

[0100] Step A3, determining a target posture combination consistent with the human body posture combination in a preset posture combination set;

[0101] Step A4: determining a target scene mode in a preset scene mode set based on the place type, the date mark information and the target posture combination.

[0102] For ease of understanding, steps A1 to A4 are described in a unified manner as follows:

[0103] The venue type is used to characterize the type of the target venue in actual applications, such as office buildings, dance studios, gyms, apartments, etc.

[0104] In the application, the smart home management platform pre-stores the locations of various types of usage places. Based on this, after the user uploads the location of the target place through the mobile terminal, the location of the place can be compared with the location pre-stored in the platform, and the type of usage places at the same location can be determined as the type of the target place.

[0105] Date marking information is used to mark the events corresponding to the date in practical applications, such as meetings, reports, training courses, performances, holidays, etc.

[0106] In the application, the date marking information of each use place can be pre-marked on the smart home management platform, based on which, when the user uploads the use date through the mobile terminal, the date marking information of the corresponding date can be found. The user can also directly upload the date marking information corresponding to the use date through the mobile terminal.

[0107] The preset posture combination set includes multiple preset posture combinations, wherein each posture combination is based on a human posture condition collected in advance in a corresponding usage scenario, for example, posture combination 1, posture combination 2, posture combination 3, and posture combination 4.

[0108] The scene mode collection includes multiple pre-set scene modes, such as daily office mode, large-scale reporting mode, holiday activity mode, dance teaching mode, daily fitness mode, etc. Each mode is pre-set with a corresponding scene execution plan.

[0109] From the description of steps A1 to A4 above, it can be seen that this solution can comprehensively analyze the actual usage of the target place according to the place type of the target place, the corresponding date marking information and the corresponding target posture combination, so as to determine the appropriate target scene mode.

[0110] Step 104: Determine a plurality of to-be-controlled devices corresponding to the target location based on the location of the location.

[0111] The devices to be controlled are generally smart devices in the target location, such as central air conditioners, smart lights, smart door locks, smart speakers, etc.

[0112] In the application, the smart building equipment is bound in the smart home management platform in advance, which includes the following steps:

[0113] 1. Home central control equipment networking:

[0114] 1. Use a mobile terminal, such as an App (Application), to scan the QR code on the screen of the home control device (a device used to centrally control smart devices in the home) (the account is not bound, the QR code data content is fixed, and it contains the ID information of the home control device), thereby obtaining the ID information of the home control device.

[0115] 2. At the same time, turn on the Bluetooth function of the mobile terminal, search for the home control device ID, then select the home control device ID to connect the mobile terminal and the home control device. Finally, enter the WiFi name and password through the mobile terminal and send the WiFi name and password to the home control device.

[0116] 3. The home control device connects to the WiFi according to the acquired WiFi name and password information, and sends the home control device ID to the server to register the home control device ID to the server.

[0117] 2. Add sub-devices to the central control device:

[0118] 1. Use the mobile terminal to connect to the discovered WiFi+BLE (GMesh) device through the Gmesh Bluetooth protocol, treat the discovered device as a sub-device, and send WiFi information to the sub-device, waiting for the first sub-device to reply. When receiving the "Device Registration Successful" message from the sub-device, it is determined that the connection to the router is successful, and then wait for the subsequent sub-devices to reply that the WiFi information is successfully received. Here, you can set the upper limit of the device connection time (such as 90s). If the connection exceeds the upper limit, it is recorded as a connection failure. If the sub-device cannot search for the SSID or other reasons when connecting to the router, it is also counted as a connection failure. If the user wants to reconnect, the SIID and password required for the sub-device to connect can be reset on the mobile terminal.

[0119] 2. For successfully connected sub-devices, the home central control device uploads the home central control device ID and the device ID information of the added sub-devices to the server, that is, the home central control device ID - sub-device A, sub-device B, sub-device C, and sets the room location corresponding to each sub-device (usually set manually).

[0120] Based on the above steps, the binding of home central control devices and sub-devices is realized in the smart home management platform.

[0121] In the embodiment of the present application, step 104 may include the following steps:

[0122] Step B1, obtaining a device set corresponding to the target location;

[0123] Step B2: determining the device location of each device in the device set;

[0124] Step B3: Determine the device whose corresponding device location is the same as the location of the venue as the device to be controlled.

[0125] For ease of understanding, steps B1 to B3 are described in a unified manner as follows:

[0126] The above device collection contains all sub-devices bound during the device binding process. The device location is the room location of the sub-device set during the device binding process.

[0127] Based on this, in this embodiment, the sub-device whose corresponding device location is the same as the location of the venue can be determined as the device to be controlled in the target venue, thereby achieving device confirmation.

[0128] Step 105: Send the target scene mode to a central control device corresponding to the target location, so that the central control device controls the plurality of devices to be controlled according to control instructions corresponding to the target scene mode.

[0129] In an embodiment of the present application, after determining the target scene mode and the device to be controlled corresponding to the target place, the target scene mode can be sent to the central control device corresponding to the target place, and the central control device controls multiple devices to be controlled according to the control instructions corresponding to the target scene mode to implement the corresponding scene execution plan.

[0130] For example, if the target scenario mode is daily office, the corresponding scenario execution plan can be:

[0131] At 8:30, the office smart lights are turned on, and at 12:00, the office smart lights are turned off. For another example, if the target scene mode is a large-scale report, the corresponding scene execution plan can be: turn on the conference room smart lights.

[0132] In another embodiment of the present application, the target scene mode can also be recommended to other places with the same posture combination, the same geographical location and the same date mark information, wherein the geographical location can be determined by using a mobile terminal to obtain the current geographical location. If the geographical location is in the same area as the location of the central control device of the target place (such as within 500m), the target scene mode can be recommended to the place for use. When applied, the central control device sends the scene execution instruction to the corresponding sub-device to realize the execution of the scene.

[0133] The technical solution provided by the embodiment of the present application first obtains the location of the target place and the date of use corresponding to the target place, then obtains the human posture combination corresponding to at least one human body in the target place, and then, based on the location of the place, the date of use and the human posture combination, determines the target scene mode corresponding to the target place, and determines the multiple devices to be controlled corresponding to the target place based on the location of the place; finally, sends the target scene mode to the central control device corresponding to the target place, so that the central control device controls the multiple devices to be controlled according to the control instructions corresponding to the target scene mode. Through this solution, the actual use of the target place can be comprehensively analyzed according to the geographical location of the target place, the human posture in the target place, and the date of use of the target place, so as to determine the appropriate scene mode, so as to obtain a device control solution that meets user needs and improve user experience.

[0134] Figure 2A flowchart of an embodiment of the present application for obtaining a human body posture combination corresponding to at least one human body in the target location. Figure 2 The process shown in Figure 1 Based on the process shown, the following steps are included:

[0135] Step 201: Acquire a sequence of image frames collected for the target location, wherein the sequence of image frames includes a plurality of continuous image frames.

[0136] The image frame sequence is acquired by using an image acquisition device (such as a camera, millimeter wave radar, etc.) set in the target location.

[0137] Step 202: for each image frame, identify the image frame to obtain at least one human body and a human body posture of each human body.

[0138] In the embodiment of the present application, step 202 may include the following steps:

[0139] Step C1, dividing the image frame into a plurality of part regions, wherein each of the part regions includes a human body part;

[0140] Step C2: for each part region, determining a region distance between the part region and an adjacent part region, and dividing the plurality of part regions into at least one human body based on the region distance;

[0141] Step C3: for each human body, determine the slope formula of each part area corresponding to the human body, and determine the human body posture based on all the slope formulas corresponding to the human body.

[0142] In this scheme, the image frame is first divided into multiple part areas.

[0143] Specifically, multiple part regions can be obtained by the following steps:

[0144] The image frame is divided into a plurality of color blocks; the color value of each color block is extracted one by one, and the color blocks with the same corresponding color value are marked as a region to obtain a plurality of regions; a human body region is determined in the plurality of regions, and a part region is determined in the human body region.

[0145] The color block may be a pixel or a rectangular area composed of several pixels.

[0146] In this scheme, the image frame is divided into multiple regions by color value, each region represents the same type of object, and then each region can be identified to determine the human body region containing the human body, and the part region containing the human body parts can be divided in the human body region.

[0147] Next, for each part area, determine the regional distance between the part area and the adjacent part area. In the application, when calculating the distance between two part areas, the two closest coordinate points of the two part areas can be selected, and the distance between the two coordinate points can be determined as the regional distance. The closer the distance, the greater the weight. When the weight value is greater than the preset threshold, it means that the two part areas are parts of the same person. In this way, multiple part areas are divided into at least one human body, that is, each human body corresponds to multiple part areas.

[0148] Finally, for each human body, the slope formula of each part area corresponding to the human body is determined. In the application, the two farthest points in each part area can be selected for calculation to obtain the corresponding slope formula. The roadmap composed of the slope formulas corresponding to each part area represents the current human posture of the human body.

[0149] For ease of understanding, step 201 and step 202 are described in detail through the following specific implementation:

[0150] 1. Signal transmission and reception: The millimeter-wave radar is used to identify the number of people and their postures in the target location. Specifically, a linear frequency modulated continuous wave (FMCW) signal is transmitted through a microwave radar system. The signal is reflected back after encountering the human body, and the radar receives these reflected signals.

[0151] 2. Data acquisition: Collect the reflected radar echo data, which contains the target's location information (X, Y, Z) and motion status.

[0152] 3. Signal processing: Process the collected radar signals, including denoising and feature extraction, to extract feature information related to human body posture.

[0153] Signal processing specifically includes the following steps:

[0154] (1) Use a model such as CNN (Convolutional Neural Network) to analyze the processed radar signal and identify the posture and movement of the human body. Specifically, cut each frame of the two-dimensional image into N color blocks (such as 1,1, 2,2, ...); extract the color values ​​of the color blocks one by one, and if the color values ​​are consistent, mark A1; if the color values ​​are inconsistent, create a new mark A2; and so on, finally combine similar color blocks together to obtain color blocks A1 (1,1, 1,2, 2,2, 2,3..5,6) and color blocks A2.

[0155] (2) Select key parts of the human body (such as shoulders, hands, elbows, legs, knees, etc.) one by one on the image. In the application, multiple parts can be obtained by manually drawing rectangular boxes diagonally on the image. For example, color block A1 is the human body area, and key parts Y1, Y2, and Y3 are circled in color block A1. For key part Y1, the two farthest points in the Y1 area (i.e., diagonal coordinates) such as 1,1, 5,6 are selected, and the function of the color block is extracted to obtain the representation function of key part Y1: Y1=a1X+b1. Correspondingly, key part Y2=a2X+b2 and key part Y3=a3X+b3 are obtained.

[0156] (3) Calculate the distance between Y1 and the adjacent key part Y2, and use the distance as the weight. The closer the distance, the greater the weight. Define whether Y1 and Y2 are parts of the same person based on the weight. Assuming that Y1, Y2, and Y5 are parts of the same person, the posture a of a person in the scene can be obtained as follows: Y1 = a1X + b1; Y2 = a2X + b2; Y5 = a5X + b5. And so on, the posture of each person in the scene is obtained.

[0157] Step 203: Determine the motion state of each human body based on at least one human body corresponding to each image frame and the human body posture of each human body.

[0158] In the embodiment of the present application, since the image frame sequence is collected continuously for a period of time, after obtaining the human body posture of each human body in each image frame, the human body posture of all image frames in the image frame sequence is analyzed to obtain the movement state of each human body, such as waving arms, lifting dumbbells, running, etc.

[0159] Step 204: Determine a combination of motion states corresponding to at least one of the human bodies as the human body posture combination.

[0160] In the embodiment of the present application, after obtaining the motion state of each human body, the combination of the motion states corresponding to all human bodies is determined as a human body posture combination. For example, the human body posture combination in the gym may include: human body A lifting dumbbells, human body B running, and human body C doing gymnastics.

[0161] pass Figure 2 The process shown can be based on the analysis of the image frame sequence collected for the target place, to obtain the motion state of each human body in the target place, and determine the combination of the motion states of all human bodies as a human posture combination. In this way, for some places that need to be analyzed based on dynamic movements, such as gyms and dance studios, the motion state of each human body in the target place can be analyzed later to determine the appropriate scene mode, so as to obtain a device control solution that meets user needs.

[0162] Figure 3 A flowchart of another embodiment of the present application for obtaining a human body posture combination corresponding to at least one human body in the target location. Figure 3 The process shown in Figure 1 Based on the process shown, the following steps are included:

[0163] Step 301: Obtain pictures collected for the target location;

[0164] Step 302: Identify the image to obtain at least one human body and a human posture corresponding to each human body;

[0165] Step 303: Determine a combination of human body postures corresponding to at least one of the human bodies as the human body posture combination.

[0166] Figure 3 The process shown is similar to Figure 2 The process shown is similar, except Figure 3 In the process shown, the human bodies and human body postures in the target place are directly analyzed through static pictures, and the combination of human body postures of all human bodies is determined as a human body posture combination. Among them, the process of obtaining pictures and identifying pictures to obtain at least one human body and the human body posture corresponding to each human body is similar to Figure 2 The description of the relevant steps is the same as in , and will not be repeated here.

[0167] pass Figure 3 The process shown can be based on the analysis of the pictures collected at the target place to obtain the human posture of each human body in the target place, and determine the combination of all human body postures as a human posture combination. In this way, for some places that only need to be analyzed based on static movements, such as offices, conference rooms, etc., the human posture of each human body in the target place can be analyzed later to determine the appropriate scene mode, so as to obtain a device control solution that meets user needs. In addition, compared with the need to analyze multiple image frames to analyze the motion state, in this solution, only one picture needs to be analyzed, which has a smaller amount of calculation and higher efficiency.

[0168] Figure 4 This is a block diagram of an embodiment of a device control device provided in an embodiment of the present application. Figure 4 As shown, the device comprises:

[0169] A first acquisition module 41 is used to acquire the location of a target place and the usage date corresponding to the target place;

[0170] A second acquisition module 42 is used to acquire a human body posture combination corresponding to at least one human body in the target location;

[0171] A mode determination module 43, for determining a target scene mode corresponding to the target place based on the place location, the use date and the human body posture combination;

[0172] A device determination module 44, configured to determine a plurality of to-be-controlled devices corresponding to the target location based on the location of the location;

[0173] The device control module 45 is used to send the target scene mode to the central control device corresponding to the target place, so that the central control device controls the multiple devices to be controlled according to the control instructions corresponding to the target scene mode.

[0174] In a possible implementation manner, the second acquisition module is specifically configured to:

[0175] Acquire an image frame sequence collected for the target location, wherein the image frame sequence includes a plurality of continuous image frames;

[0176] For each image frame, identifying the image frame to obtain at least one human body and a human body posture of each human body;

[0177] Determine the motion state of each of the human bodies based on at least one human body corresponding to each of the image frames and the human body posture of each of the human bodies;

[0178] A combination of motion states corresponding to at least one of the human bodies is determined as the human body posture combination.

[0179] In a possible implementation manner, the second acquisition module is further configured to:

[0180] Dividing the image frame into a plurality of part regions, wherein each of the part regions includes a human body part;

[0181] For each part region, determining a region distance between the part region and an adjacent part region, and dividing the plurality of part regions into at least one human body based on the region distance;

[0182] For each human body, a slope formula for each part area corresponding to the human body is determined, and the human body posture of the human body is determined based on all the slope formulas corresponding to the human body.

[0183] In a possible implementation manner, the second acquisition module is further configured to:

[0184] Dividing the image frame into a plurality of color blocks;

[0185] The color value of each color block is extracted one by one, and the color blocks with the same corresponding color value are marked as a region, thereby obtaining multiple regions;

[0186] A human body region is determined among the plurality of regions, and a part region is determined among the human body regions.

[0187] In a possible implementation manner, the second acquisition module is further configured to:

[0188] Acquire pictures collected for the target location;

[0189] Recognize the image to obtain at least one human body and a human posture corresponding to each human body;

[0190] A combination of human body postures corresponding to at least one of the human bodies is determined as the human body posture combination.

[0191] In a possible implementation manner, the mode determination module is specifically configured to:

[0192] Determining a venue type corresponding to the target venue based on the venue location;

[0193] Determining date marking information corresponding to the use date;

[0194] Determine a target posture combination consistent with the human body posture combination in a preset posture combination set;

[0195] Based on the location type, the date mark information and the target posture combination, a target scene mode is determined in a preset scene mode set.

[0196] In a possible implementation manner, the device determination module is specifically configured to:

[0197] Obtaining a device set corresponding to the target location;

[0198] determining a device location of each device in the set of devices;

[0199] The device whose corresponding device location is the same as the location of the place is determined as the device to be controlled.

[0200] like Figure 5 As shown, an embodiment of the present application provides a device, including a processor 111, a communication interface 112, a memory 113 and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114.

[0201] Memory 113, used for storing computer programs;

[0202] In one embodiment of the present application, the processor 111 is used to execute the program stored in the memory 113 to implement the device control method provided by any of the above method embodiments, including:

[0203] Obtaining the location of the target place and the usage date corresponding to the target place;

[0204] Acquire a human body posture combination corresponding to at least one human body in the target location;

[0205] Determining a target scene mode corresponding to the target place based on the place location, the use date and the human body posture combination;

[0206] Determine a plurality of to-be-controlled devices corresponding to the target location based on the location of the location;

[0207] The target scene mode is sent to a central control device corresponding to the target location, so that the central control device controls the plurality of devices to be controlled according to control instructions corresponding to the target scene mode.

[0208] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the device control method provided in any of the aforementioned method embodiments are implemented.

[0209] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0210] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0211] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0212] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.

Claims

1. A device control method, characterized in that: The method comprises: Obtaining the location of the target place and the usage date corresponding to the target place; Acquire a human body posture combination corresponding to at least one human body in the target location; Determining a target scene mode corresponding to the target place based on the place location, the use date and the human body posture combination; Determine a plurality of to-be-controlled devices corresponding to the target place based on the location of the place; The target scene mode is sent to a central control device corresponding to the target location, so that the central control device controls the plurality of devices to be controlled according to control instructions corresponding to the target scene mode.

2. The method according to claim 1, characterized in that The step of obtaining a human body posture combination corresponding to at least one human body in the target location includes: Acquire an image frame sequence collected for the target location, wherein the image frame sequence includes a plurality of continuous image frames; For each image frame, identifying the image frame to obtain at least one human body and a human body posture of each human body; Determine the motion state of each of the human bodies based on at least one human body corresponding to each of the image frames and the human body posture of each of the human bodies; A combination of motion states corresponding to at least one of the human bodies is determined as the human body posture combination.

3. The method according to claim 2, characterized in that The step of recognizing the image frame to obtain at least one human body and a human body posture of each human body includes: Dividing the image frame into a plurality of part regions, wherein each of the part regions includes a human body part; For each part region, determining a region distance between the part region and an adjacent part region, and dividing the plurality of part regions into at least one human body based on the region distance; For each human body, a slope formula for each part area corresponding to the human body is determined, and the human body posture of the human body is determined based on all the slope formulas corresponding to the human body.

4. The method according to claim 3, characterized in that The dividing the image frame into a plurality of part regions comprises: Dividing the image frame into a plurality of color blocks; The color value of each color block is extracted one by one, and the color blocks with the same corresponding color value are marked as a region, thereby obtaining multiple regions; A human body region is determined among the plurality of regions, and a part region is determined among the human body regions.

5. The method according to claim 1, characterized in that The step of obtaining a human body posture combination corresponding to at least one human body in the target location includes: Acquire pictures collected for the target location; Recognize the image to obtain at least one human body and a human posture corresponding to each human body; A combination of human body postures corresponding to at least one of the human bodies is determined as the human body posture combination.

6. The method according to claim 1, characterized in that The determining of the target scene mode corresponding to the target place based on the place location, the use date and the human body posture combination includes: Determining a venue type corresponding to the target venue based on the venue location; Determining date marking information corresponding to the use date; Determine a target posture combination consistent with the human body posture combination in a preset posture combination set; Based on the location type, the date mark information and the target posture combination, a target scene mode is determined in a preset scene mode set.

7. The method according to claim 1, characterized in that The determining, based on the location of the location, a plurality of devices to be controlled corresponding to the target location includes: Obtaining a device set corresponding to the target location; determining a device location of each device in the set of devices; The device whose corresponding device location is the same as the location of the place is determined as the device to be controlled.

8. A device control device, characterized in that: The device comprises: A first acquisition module is used to acquire the location of a target place and the usage date corresponding to the target place; A second acquisition module is used to acquire a human body posture combination corresponding to at least one human body in the target location; A mode determination module, used to determine a target scene mode corresponding to the target place based on the place location, the use date and the human posture combination; A device determination module, used for determining a plurality of to-be-controlled devices corresponding to the target location based on the location of the location; The device control module is used to send the target scene mode to the central control device corresponding to the target place, so that the central control device controls the multiple devices to be controlled according to the control instructions corresponding to the target scene mode.

9. A device, characterized in that: include: A processor and a memory, wherein the processor is used to execute a device control program stored in the memory to implement the device control method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the device control method according to any one of claims 1 to 7.

Images