Air conditioner control method and device, air conditioner and storage medium

Abstract

The invention provides an air conditioner control method and device, an air conditioner and a storage medium, and the air conditioner control method comprises the steps that in response to an air conditioner control request for a target air conditioner, scene image data corresponding to the target air conditioner are obtained; based on the scene image data, determining an object quantity type and an object dressing type in an air conditioner operation area corresponding to the target air conditioner; performing object posture recognition on the scene image data, and determining an object activity state of each target object in the scene image data; and operation control is conducted on the target air conditioner according to the object number type, the object dressing type and the object activity state, and an air conditioner control result is obtained. According to the technical scheme, the operation parameters of the air conditioner can be intelligently and individually adjusted in time according to the user state in the designated area, so that the comfort level of the user and the energy-saving efficiency of the air conditioner are effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of air conditioners, and particularly to an air conditioner control method, device, air conditioner and storage medium. Background Art

[0002] Currently, with the rapid development of the air conditioner technology field, various air conditioners are increasingly used for air conditioning in more and more indoor scenarios. However, existing air conditioning equipment relies on manual adjustment by users during operation. As a result, in crowded places such as classrooms, meeting rooms, and shopping malls, the air conditioner cannot automatically adjust in real time for temperature fluctuations caused by changes in population density, with a low degree of intelligence, thus affecting the indoor environmental comfort and easily causing energy waste. Summary of the Invention

[0003] Embodiments of the present application provide an air conditioner control method, device, air conditioner and storage medium, aiming to solve the technical problem in the prior art that the air conditioner can only manually adjust operating parameters with a low degree of intelligence.

[0004] On the one hand, embodiments of the present application provide an air conditioner control method, and the air conditioner control method includes the following steps:

[0005] Respond to an air conditioner control request for a target air conditioner, and obtain scene image data corresponding to the target air conditioner;

[0006] Based on the scene image data, determine the object quantity category and object clothing type in the air conditioner operation area corresponding to the target air conditioner;

[0007] Perform object pose recognition on the scene image data to determine the object activity status of each target object in the scene image data;

[0008] Perform operation control on the target air conditioner according to the object quantity category, the object clothing type, and the object activity status to obtain an air conditioner control result.

[0009] In a possible implementation manner of the present application, the determining the object quantity category and the object clothing type in the air conditioner operation area corresponding to the target air conditioner based on the scene image data includes:

[0010] Perform first target detection on the scene image data to determine the target objects in the scene image data;

[0011] Determine the object quantity category of the target objects according to the object statistical information of the target objects and a preset object quantity threshold;

[0012] Perform second target detection on the target object images in the scene image data to determine the object clothing type of the target objects.

[0013] In a possible implementation manner of the present application, the object pose recognition of the scene image data to determine the object activity states of each target object in the scene image data includes:

[0014] Performing image detection on the scene image data by using a state recognition model to obtain an object detection frame corresponding to each target object and object key points corresponding to the target object;

[0015] Performing state recognition on the target object according to the object detection frame and / or object key points to determine the object activity states of each target object in the scene image data.

[0016] In a possible implementation manner of the present application, the performing state recognition on the target object according to the object detection frame and / or object key points to determine the object activity states of each target object in the scene image data includes:

[0017] Obtaining a first object key point and a second object key point in the object key points;

[0018] Calculating key point displacement data of the target object according to the first object key point and the second object key point;

[0019] Performing state recognition on the target object based on the key point displacement data to determine the object activity state of the target object, where the object activity state includes any one of a dynamic activity state and a static activity state.

[0020] In a possible implementation manner of the present application, the object detection frame includes a first object detection frame and a second object detection frame;

[0021] The performing state recognition on the target object according to the object detection frame and / or object key points to determine the object activity states of each target object in the scene image data includes:

[0022] Obtaining a first detection gray level of the first object detection frame and a second detection gray level of the second object detection frame;

[0023] Determining target optical flow data of the target object according to the first detection gray level and the second detection gray level;

[0024] Performing state recognition on the target object according to the target optical flow data to determine the object activity state of the target object.

[0025] In a possible implementation manner of the present application, the performing operation control on the target air conditioner according to the object quantity category, the object clothing type, and the object activity state to obtain an air conditioner control result includes:

[0026] Obtain the target temperature difference between the target set temperature of the target air conditioner and the current regional room temperature in the air conditioner operation area;

[0027] If the target temperature difference is less than or equal to the preset temperature difference threshold, adjust the initial operation parameters of the target air conditioner according to the object quantity category, the object clothing type, and / or the object activity state to obtain an air conditioner control result, where the initial operation parameters include an initial temperature parameter and / or an initial wind speed parameter.

[0028] In a possible implementation manner of the present application, the operation control of the target air conditioner according to the object quantity category, the object clothing type, and the object activity state to obtain an air conditioner control result includes:

[0029] If the object activity state is a static activity state, determine the first operation parameters of the target air conditioner according to the static control strategy corresponding to the static activity state, the object quantity category, and the object clothing type;

[0030] If the object activity state is a dynamic activity state, correct the first operation parameters according to the dynamic control strategy corresponding to the dynamic activity state to obtain second operation parameters;

[0031] Adjust the initial operation parameters of the target air conditioner according to the first operation parameters or the second operation parameters to obtain an air conditioner control result.

[0032] On the other hand, the present application provides an air conditioner control device, and the air conditioner control device includes:

[0033] An image acquisition module, configured to obtain the scene image data corresponding to the target air conditioner in response to an air conditioner control request for the target air conditioner;

[0034] A first recognition module, configured to determine the object quantity category and the object clothing type in the air conditioner operation area corresponding to the target air conditioner based on the scene image data;

[0035] A second recognition module, configured to perform object pose recognition on the scene image data to determine the object activity state of each target object in the scene image data;

[0036] An air conditioner control module, configured to perform operation control on the target air conditioner according to the object quantity category, the object clothing type, and the object activity state to obtain an air conditioner control result.

[0037] On the other hand, the present application further provides an air conditioner, and the air conditioner includes:

[0038] One or more processors;

[0039] A memory; and

[0040] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the steps of the air conditioner control method.

[0041] On the other hand, the present application also provides a computer-readable storage medium, on which a computer program is stored, and the computer program is loaded by a processor to execute the steps in the air conditioner control method.

[0042] In the present application, by responding to an air conditioner control request for a target air conditioner, scene image data corresponding to the target air conditioner is acquired; based on the scene image data, the object quantity category and object clothing type in the air conditioner operation area corresponding to the target air conditioner are determined; object pose recognition is performed on the scene image data to determine the object activity status of each target object in the scene image data; and the target air conditioner is controlled to operate according to the object quantity category, the object clothing type, and the object activity status, so as to obtain an air conditioner control result. During the operation of the target air conditioner, scene image data associated with the air conditioner operation area corresponding to the target air conditioner is acquired, the object quantity category and object clothing type in the air conditioner operation area are determined by analyzing the scene image data, object pose recognition is performed on each target object in the scene image data to determine the object activity status of each target object, and then the target air conditioner is intelligently controlled to operate through multi-modal parameters such as the object quantity category, the object clothing type, and the object activity status, so as to realize intelligent and personalized timely adjustment of the air conditioner operation parameters according to the user status in the specified area, thereby effectively improving the user comfort and air conditioner energy-saving efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention, and those skilled in the art can obtain other drawings without creative efforts based on these drawings.

[0044] Figure 1 It is a schematic diagram of the scenario of the air conditioner control method according to the embodiment of the present application;

[0045] Figure 2 It is a flowchart of an embodiment of the air conditioner control method according to the embodiment of the present application;

[0046] Figure 3 It is a flowchart of an embodiment for determining the object activity status in the air conditioner control method provided by the embodiment of the present application;

[0047] Figure 4 It is a schematic flowchart of another embodiment for determining the activity state of an object in the air conditioner control method provided by the embodiment of the present application;

[0048] Figure 5 It is a schematic structural diagram of an embodiment of the air conditioner control device provided by the embodiment of the present application;

[0049] Figure 6 It is a schematic structural diagram of an embodiment of the air conditioner provided by the embodiment of the present application. Detailed implementation manners

[0050] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present invention.

[0051] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be understood as a limitation to the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more, unless otherwise specifically defined.

[0052] In this application, the term "exemplary" is used to mean "serving as an example, illustration, or instance". Any embodiment described as "exemplary" in this application is not necessarily to be construed as more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. In the following description, details are set forth for purposes of explanation. It should be understood that those of ordinary skill in the art can recognize that the invention can be practiced without these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the invention with unnecessary details. Therefore, the invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed in this application.

[0053] Currently, with the rapid development of the air-conditioning technology field, more and more indoor scenarios are adopting various air conditioners for air conditioning. However, existing air-conditioning devices rely on users for manual adjustment during operation, resulting in that in crowded places such as classrooms, meeting rooms, and shopping malls, the air conditioners cannot automatically adjust in real time for temperature fluctuations caused by changes in crowd density, with a low degree of intelligence, thus affecting the indoor environment comfort and easily causing energy waste.

[0054] Based on this, this application proposes an air-conditioning control method, device, equipment, and computer-readable storage medium to solve the technical problem in the prior art that air conditioners can only manually adjust operation parameters with a low degree of intelligence.

[0055] The air-conditioning control method in the embodiments of the present invention is applied to an air-conditioning control device. The air-conditioning control device is provided in an air conditioner. One or more processors, a memory, and one or more application programs are provided in the air conditioner. One or more of the application programs are stored in the memory and are configured to be executed by the processor to implement the air-conditioning control method. Among them, the air conditioner can be an intelligent air-conditioning terminal, such as a mobile air conditioner, a window air conditioner, a wall-mounted air conditioner, a floor-standing air conditioner, and a central air conditioner, etc. Optionally, the air conditioner can also be other types of intelligent air-conditioning terminals, which are not specifically limited in this embodiment.

[0056] As Figure 1 shown, Figure 1 is a schematic diagram of the scenario of the air-conditioning control method in the embodiments of this application. In the embodiments of the present invention, the air-conditioning control scenario includes an air conditioner 100 (the air-conditioning control device is integrated in the air conditioner 100). Optionally, a computer-readable storage medium corresponding to the air-conditioning control method runs in the air conditioner 100 to execute the steps of the air-conditioning control method.

[0057] It can be understood that Figure 1The air conditioner in the air conditioner control method scenario shown, or the devices included in the air conditioner, do not constitute a limitation to the embodiments of the present invention. That is, the number and types of air conditioner devices included in the air conditioner control method scenario, or the number and types of devices included in each device, do not affect the overall implementation of the technical solutions in the embodiments of the present invention, and can all be regarded as equivalent replacements or derivatives of the technical solutions required to be protected in the embodiments of the present invention.

[0058] In the embodiments of the present invention, the air conditioner 100 is mainly used for: responding to an air conditioner control request for a target air conditioner, and obtaining the scene image data corresponding to the target air conditioner;

[0059] Based on the scene image data, determining the number category of objects and the clothing type of objects in the air conditioner operation area corresponding to the target air conditioner;

[0060] Performing object pose recognition on the scene image data to determine the object activity status of each target object in the scene image data;

[0061] Performing operation control on the target air conditioner according to the object number category, the object clothing type, and the object activity status to obtain an air conditioner control result.

[0062] The air conditioner 100 in the embodiments of the present invention can be an independent air conditioner, such as an independent air conditioner terminal like an air conditioner wall-mounted unit, an air conditioner window unit, and a floor-standing air conditioner, or can also be an air conditioner control cluster composed of multiple air conditioners.

[0063] The embodiments of the present application provide an air conditioner control method, device, equipment, and computer-readable storage medium, which will be described in detail below respectively.

[0064] Those skilled in the art can understand that Figure 1 the application environment shown is only one of the application scenarios related to the solution of the present application, and does not constitute a limitation to the application scenarios of the solution of the present application. Other application environments may also include more or fewer air conditioners than Figure 1 shown, or the air conditioner control network connection relationship. For example Figure 1 only one air conditioner is shown in. It can be understood that the air conditioner control method scenario may also include one or more air conditioners, which are not specifically limited herein; the air conditioner 100 may also include a memory for storing scene image data and other data.

[0065] It should be noted that Figure 1 the scene schematic diagram of the air conditioner control method shown is only an example. The air conditioner control method scenario described in the embodiments of the present invention is for more clearly explaining the technical solutions of the embodiments of the present invention, and does not constitute a limitation to the technical solutions provided by the embodiments of the present invention.

[0066] Based on the scenarios of the above air conditioner control method, various embodiments of the air conditioner control method disclosed in the present invention are proposed.

[0067] As Figure 2 shown, Figure 2 FIG. is a schematic flowchart of an embodiment of the air conditioner control method in an embodiment of the present application. The air conditioner control method includes the following steps 201 to 204:

[0068] 201. Respond to an air conditioner control request for a target air conditioner, and obtain the scene image data corresponding to the target air conditioner;

[0069] The air conditioner control method in this embodiment is applied to an air conditioner, and the type and quantity of the air conditioner are not specifically limited. That is, the air conditioner can be one or more independent air conditioners or a multi-connected intelligent air conditioner terminal. In a specific embodiment, the air conditioner is an intelligent air conditioner.

[0070] Among them, the target air conditioner is an air conditioner configured to perform air conditioning on the corresponding air conditioner operation area. For example, the target air conditioner can adjust the temperature, humidity, etc. of a certain air conditioner operation area in the indoor environment to adjust environmental parameters such as temperature, wind speed, and humidity in the air conditioner operation area, thereby improving the user comfort in the air conditioner operation area. Optionally, the target air conditioner can be an independent air conditioner, or when the air conditioner is a multi-connected air conditioner terminal, the target air conditioner can be a cascaded sub-air conditioner of the air conditioner.

[0071] Among them, the scene image data is environmental image information collected in the air conditioner operation area where the target air conditioner performs air conditioning during operation. Optionally, the scene image information can be the environmental image information of the air conditioner operation area collected by the target air conditioner integrated with a vision sensor. Optionally, the scene image information can also be collected by other Internet of Things devices integrated with a vision sensor and transmitted to the target air conditioner. Optionally, the vision sensor can be various types of cameras or other image collection devices, and this embodiment does not make specific limitations on this. For example, in a specific embodiment, the vision sensor can be a monocular camera, a binocular camera, an RGBD camera, etc.

[0072] Specifically, during the operation of the air conditioner, in response to an air conditioner control request, where the air conditioner control request is a control event that drives the air conditioner to dynamically adjust the air conditioner operation parameters of the target air conditioner based on multi-modal object data in the air conditioner operation area to improve user comfort. Optionally, the triggering method of the air conditioner control request is not specifically limited herein, that is, the air conditioner control request can be actively triggered by the target object. For example, the target object triggers the air conditioner control request by selecting automatic control through a mobile terminal (such as a mobile phone, a tablet computer, and a wearable intelligent device, etc.) or a control button or a control interaction interface that is communicatively connected to the air conditioner. In addition, the air conditioner control request can also be automatically triggered by the air conditioner. For example, the air conditioner pre-sets an automatic control process, and when detecting that the temperature difference between the indoor temperature and the set temperature is greater than a preset temperature difference threshold, it automatically triggers the air conditioner control request.

[0073] Specifically, after the air conditioner obtains the air conditioner control request, it determines the target air conditioner to be adjusted and obtains the corresponding scene image data of the target air conditioner. That is, the air conditioner can drive the visual sensor of the target air conditioner to collect the image data of the air conditioner operation scene where the target air conditioner acts as the scene image data. In addition, the air conditioner can also communicate and interact with other Internet of Things devices integrated with visual sensors to obtain the scene image data collected by the Internet of Things devices. Among them, the scene image data includes the target object in the air conditioner operation area corresponding to the target air conditioner. Among them, the target object is a user object in the air conditioner operation area.

[0074] 202. Determine the object quantity category and object clothing type in the air conditioner operation area corresponding to the target air conditioner based on the scene image data;

[0075] Specifically, after the air conditioner obtains the scene image data corresponding to the target air conditioner, it also determines the object quantity category and object clothing type in the air conditioner operation area corresponding to the target air conditioner based on the scene image data.

[0076] Optionally, the air conditioner operation area is an indoor environment area representing the area where the target air conditioner performs air conditioning.

[0077] Optionally, the object quantity category is category label data representing the number of target objects existing in the air conditioner operation area. In a specific embodiment, the object quantity category includes a first object quantity category, a second object quantity category, a third object quantity category, and a fourth object quantity category based on the number of target objects from less to more.

[0078] Among them, the first object quantity category is the object quantity category representing that there is no target object to be served in the air conditioner operation area. That is, the first object quantity category is the object quantity category representing that the number of target objects in the air conditioner operation area is 0.

[0079] Among them, the second object quantity category is an object quantity category that characterizes a relatively small number of target objects in the air conditioner operation area.

[0080] Among them, the third object quantity category is an object quantity category that characterizes a medium number of target objects in the air conditioner operation area.

[0081] Among them, the fourth object quantity is an object quantity category that characterizes a relatively large number of target objects in the air conditioner operation area.

[0082] Optionally, the object clothing type is label data characterizing the clothing type worn by the target objects existing in the air conditioner operation area. Optionally, in a specific embodiment, the object clothing type may include a first object clothing type, a second object clothing type, a third object clothing type, and a fourth object clothing type in ascending order of warmth retention.

[0083] Among them, the first object clothing type is a clothing type that characterizes the target objects in the air conditioner operation area as having a relatively low warmth retention.

[0084] Among them, the second object clothing type is a clothing type that characterizes the target objects in the air conditioner operation area as having a medium warmth retention.

[0085] Among them, the third object clothing type is a clothing type that characterizes the target objects in the air conditioner operation area as having a relatively high warmth retention.

[0086] Specifically, after the air conditioner obtains the scene image data, it also performs target detection on the scene image data to determine the target objects existing in the scene image data, and further identifies the object quantity category and object clothing type associated with the target objects.

[0087] Specifically, the air conditioner performs a first target detection on the scene image data to determine the target objects in the scene image data, that is, the air conditioner can use a pre-set target detection model to locate the scene objects in the scene image data, obtain the scene objects to be recognized in the scene image data, recognize the scene objects, and determine whether the scene objects are human body objects in the air conditioner operation scene, and determine the human body objects in the air conditioner operation scene as target objects. Optionally, in a specific embodiment, the target detection model may be a pre-trained YOLO model. For example, the target detection model may be a YOLOv11 model.

[0088] Specifically, the air conditioner also determines the object quantity category of the target object based on the object statistical information of the target object and a preset object quantity threshold. That is, after detecting the target object in the air conditioner operation scenario, the air conditioner also uses a preset counter to count the object quantity data in the air conditioner operation scenario, obtains the object statistical information of the target object, and compares the object quantity data in the object statistical information with the preset object quantity threshold, so as to determine the object quantity category of the target object. Among them, the preset object quantity threshold is a quantity threshold for evaluating the quantity of target objects in the air conditioner operation scenario. Optionally, in a specific embodiment, the preset object quantity threshold includes a first quantity threshold and a second quantity threshold. Among them, the first quantity threshold is a quantity threshold representing a small number of target objects in the air conditioner operation scenario. The second quantity threshold is a quantity threshold representing a large number of target objects in the air conditioner operation scenario.

[0089] Optionally, if the object quantity data in the air conditioner operation scenario is 0, the air conditioner determines that there is no target object in the air conditioner operation scenario, and the air conditioner determines the object quantity category in the air conditioner operation scenario as the first object quantity category.

[0090] Optionally, if the object quantity data in the air conditioner operation scenario is less than the first quantity threshold, the air conditioner determines that the number of target objects in the air conditioner operation scenario is small, and determines the object quantity category in the air conditioner operation scenario as the second object quantity category.

[0091] Optionally, if the object quantity data in the air conditioner operation scenario is less than the second quantity threshold and greater than the first quantity threshold, the air conditioner determines that the number of target objects in the air conditioner operation scenario is in the medium quantity range, and determines the object quantity category in the air conditioner operation scenario as the third object quantity category.

[0092] Optionally, if the object quantity data in the air conditioner operation scenario is greater than the second quantity threshold, the air conditioner determines that the number of target objects in the air conditioner operation scenario is large, and determines the object quantity category in the air conditioner operation scenario as the fourth object quantity category.

[0093] Specifically, the air conditioner also performs a second target detection on the target object image in the scene image data to determine the object clothing type of the target object. That is, the air conditioner can also identify the clothing types worn by each target object in the air conditioner operation area in the target object image, and then determine the object clothing type that best matches the clothing warmth degree of each target object. Optionally, in a specific embodiment, the air conditioner can use a target detection model to perform clothing recognition on each target object detected in the first target detection process, so as to determine the clothing types worn by each target object, and then count the clothing types worn by each target object, and determine the object clothing type according to the statistical results.

[0094] Optionally, if the air conditioner performs a second target detection on the target object and determines that the most frequently appearing clothing among the target objects is lightweight clothing with low warmth retention, such as short-sleeved T-shirts, shorts, and / or sandals, then the object clothing type of the target object is determined to be the first object clothing type.

[0095] Optionally, if the air conditioner performs a second target detection on the target object and determines that the most frequently appearing clothing among the target objects is spring and autumn clothing with medium warmth retention, such as long-sleeved shirts, long pants, and thin coats, then the object clothing type of the target object is determined to be the second object clothing type.

[0096] Optionally, if the air conditioner performs a second target detection on the target object and determines that the most frequently appearing clothing among the target objects is winter clothing with high warmth retention, such as suits, formal wear, thick coats, down jackets, and sweaters, then the object clothing type of the target object is determined to be the third object clothing type.

[0097] 203. Perform object pose recognition on the scene image data to determine the object activity status of each target object in the scene image data;

[0098] Optionally, the air conditioner can also perform object pose recognition on each target object in the scene image data, so as to determine the object activity status of each target object in the scene image data. Among them, the object activity status is an object status representing whether the target object is in an active state in the air conditioner operation scene. Optionally, in a specific embodiment, the object activity status includes either a dynamic activity status or a static activity status.

[0099] Among them, the dynamic activity status is an object status representing that there is a target object in a dynamic activity state in the air conditioner operation scene.

[0100] Among them, the static activity status is an object status representing that all target objects in the air conditioner operation scene are in a static state.

[0101] Optionally, the air conditioner can use a state recognition model to perform image detection on continuous scene image data, obtain the object detection frame corresponding to each target object, and the object key points corresponding to the target object, and perform state recognition on the target object according to the object detection frame and object key points, so as to judge the object activity status of each target object in the scene image data. That is, the air conditioner can use the state recognition model to generate the object detection frame associated with each recognized target object, and collect the object key points representing the object pose of the target object, and then judge whether the target object is in a dynamic activity state according to the object key points and / or object detection frame, so as to determine the object activity status of the target object in the air conditioner operation scene. Optionally, in a specific embodiment, the state recognition model can be a YOLOPose model or other state recognition models.

[0102] Among them, the object detection box is an image detection box representing the object boundary corresponding to the target object to be recognized. Optionally, in a specific embodiment, the object detection box is a rectangular boundary detection box representing the target object in the circle. Among them, the object detection box can be represented by coordinates (x, y, w, h), where (x, y) represents the width and height of the object detection box.

[0103] Among them, the object key points are the key point coordinates representing the object pose corresponding to the target object. Optionally, the object key points can be the joint point coordinates of the target object (such as the head, shoulders, elbows, wrists, hips, knees, and ankles, etc.) or other position information that can represent the object pose corresponding to the target object.

[0104] Optionally, in a specific embodiment, after the air conditioner obtains the object detection box and / or the object key points, it can use the object key points in the continuous scene image data to determine whether the target object is in a dynamic state, and then determine the object activity state of each target object.

[0105] Optionally, in another specific embodiment, after the air conditioner obtains the object detection box and / or the object key points, it can also use the object detection boxes in the continuous scene image data to determine whether the target object is in a dynamic state, and then determine the object activity state of each target object.

[0106] 204. Perform operation control on the target air conditioner according to the object quantity category, the object clothing type, and the object activity state to obtain an air conditioner control result.

[0107] Specifically, the air conditioner performs operation control on the target air conditioner after obtaining the object quantity category, the object clothing type, and the object activity state, so as to dynamically and personalizedly adjust the initial temperature parameter and / or the initial wind speed parameter of the air conditioner to the target temperature parameter and / or the target wind speed parameter that conform to the number of target objects, the wearing situation, and the activity situation in the air conditioner operation area, and obtain an air conditioner control result that can improve user comfort and energy-saving efficiency.

[0108] Optionally, in a specific embodiment, the air conditioner can dynamically adjust the operation state of the air conditioner when the temperature difference between the set temperature and the inner loop temperature of the air conditioner is large. That is, the air conditioner obtains the target temperature difference between the target set temperature of the target air conditioner and the current area room temperature in the air conditioner operation area. The air conditioner calculates the temperature difference between the target set temperature and the current area room temperature, determines the temperature difference as the target temperature difference, and compares the target temperature difference with a preset temperature difference threshold representing the degree of the temperature difference between the set temperature and the inner loop temperature, so as to determine whether to perform dynamic temperature control on the target air conditioner.

[0109] Optionally, if the air conditioner determines that the target temperature difference is less than or equal to the preset temperature difference threshold, the air conditioner adjusts the initial operating parameters of the target air conditioner according to the object quantity category, the object clothing type, and / or the object activity state to obtain an air conditioner control result.

[0110] Specifically, after obtaining the object quantity category, the object clothing type, and the object activity state, the air conditioner selects a corresponding air conditioner control strategy according to the object activity state, and adjusts the operation of the air conditioner according to the air conditioner operating parameters corresponding to the air conditioner control strategy to obtain an air conditioner control result.

[0111] Optionally, if the air conditioner determines that the object activity state in the air conditioner operation area is a static activity state, that is, the air conditioner determines that each target object in the air conditioner operation area is in a stationary state, then it is determined that the air conditioner control strategy corresponding to the air conditioner is a static control strategy. The air conditioner determines the first operating parameters of the target air conditioner according to the static control strategy, the object quantity category, and the object clothing type, and adjusts the air conditioner operation state of the target air conditioner according to the first operating parameters to obtain a first air conditioner control result.

[0112] That is, the air conditioner obtains the first parameter table corresponding to the static control strategy, reads the first operating parameters associated with the object quantity category and the object clothing type according to the first parameter table, and adjusts the air conditioner operation state of the target air conditioner according to the first operating parameters to obtain a first air conditioner control result. Among them, the first parameter table is an air conditioner parameter mapping table representing the mapping relationship between the object quantity category and the object clothing type and the operating temperature and / or the operating wind speed in the static activity state. Among them, the first parameter table includes a static temperature parameter table and a static wind speed parameter table. The first operating parameters include a first temperature parameter and a first wind speed parameter. As shown in Table 1 and Table 2 below, Table 1 is a table representing the static temperature parameter table, and Table 2 is a static wind speed parameter table.

[0113]

[0114]

[0115] Table 1 Static Temperature Parameter Table

[0116]

[0117] Table 2 Static Wind Speed Parameter Table

[0118] Among them, T1~T 12 are the first temperature parameters corresponding to different object quantity categories and object clothing types in the static activity state. L1~L 12 are the first wind speed parameters corresponding to different object quantity categories and object clothing types in the static activity state.

[0119] Optionally, in a specific embodiment, the magnitude relationship between the first temperature parameters is T 10 > T 11 > T 12 > T7 > T8 > T9 > T4 > T5 > T6 > T1 > T2 > T3, that is, in the static activity state, for the same object dressing type, the more the number of objects in the air conditioner operation area, the lower the corresponding first temperature parameter; in the static activity state and for the same object quantity type, the higher the clothing warmth degree of the target object, the higher the corresponding first temperature parameter.

[0120] Optionally, in a specific embodiment, the magnitude relationship between the first wind speed parameters is L 10 < L 11 < L 12 < L7 < L8 < L9 < L4 < L5 < L6 < L1 < L2 < L3, that is, in the static activity state, for the same object dressing type, the more the number of objects in the air conditioner operation area, the higher the corresponding first wind speed parameter; in the static activity state and for the same object quantity type, the higher the clothing warmth degree of the target object, the lower the corresponding first wind speed parameter.

[0121] Optionally, if the air conditioner determines that the object activity state in the air conditioner operation area is a dynamic activity state, that is, there is a target object in a dynamic state in the air conditioner operation area, the air conditioner corrects the first operation parameter according to the dynamic control strategy corresponding to the dynamic activity state to obtain a second operation parameter, and adjusts the operation state of the target air conditioner according to the second operation parameter to obtain a second air conditioner control result.

[0122] That is, the air conditioner uses the dynamic control strategy to obtain the temperature correction parameter and / or wind speed correction parameter corresponding to the object quantity category and object dressing type, and uses the temperature correction parameter and / or wind speed correction parameter to correct the first operation parameter to obtain a second operation parameter. As shown in Table 3 and Table 4, Table 3 is the dynamic temperature parameter table in the dynamic activity state. Table 4 is the dynamic wind speed parameter table in the dynamic activity state.

[0123]

[0124] Table 3 Dynamic Temperature Parameter Table

[0125]

[0126]

[0127] Table 4 Dynamic Wind Speed Parameter Table

[0128] Among them, △α1~△α 12Temperature correction parameters corresponding to different object quantity categories and object clothing types in the dynamic activity state. The temperature correction parameter is negative. △β1~△β 12 Wind speed correction parameters corresponding to different object quantity categories and object clothing types in the dynamic activity state. The wind speed correction parameter is positive.

[0129] Optionally, in a specific embodiment, the magnitude relationship between the temperature correction parameters is △α 10 >△α 11 >△α 12 >△α7>△α8>△α9>△α4>△α5>△α6>△α7>△α1>△α2>△α3, that is, in the dynamic activity state, under the same object clothing type, the more the number of objects in the air-conditioning operation area, the smaller the corresponding temperature correction coefficient. In the dynamic activity state, under the same object quantity category, the higher the clothing warmth degree of the target object, the larger the corresponding temperature correction coefficient.

[0130] Optionally, in another specific embodiment, the magnitude relationship between the wind speed correction parameters is △β 10 <△β 11 <△β 12 <△β7<△β8<△β9<△β4<△β5<△β6<△β7<△β1<△β2<△β3, that is, in the dynamic activity state, under the same object clothing type, the more the number of objects in the air-conditioning operation area, the larger the corresponding wind speed correction coefficient. In the dynamic activity state, under the same object quantity category, the higher the clothing warmth degree of the target object, the smaller the corresponding wind speed correction coefficient.

[0131] That is, after the air conditioner detects that the object activity state of the target object in the air-conditioning operation area is the dynamic activity state, it obtains the temperature correction parameter and / or wind speed correction parameter corresponding to the object quantity type and object clothing type according to the dynamic control strategy, uses the temperature correction parameter and / or wind speed correction parameter to adjust the first operating parameter to obtain the second operating parameter, and uses the second operating parameter to control the operating state of the target air conditioner to obtain the second air-conditioning control result, so as to realize dynamically adjusting the air-conditioning operating state according to the different states of the target object in the air-conditioning operation area, and improve the user comfort and air-conditioning energy-saving efficiency of the air conditioner.

[0132] In this embodiment, the air conditioner obtains the scene image data corresponding to the target air conditioner by responding to an air conditioner control request for the target air conditioner; determines the object quantity category and object clothing type in the air conditioner operation area corresponding to the target air conditioner based on the scene image data; performs object pose recognition on the scene image data to determine the object activity state of each target object in the scene image data; and performs operation control on the target air conditioner according to the object quantity category, the object clothing type, and the object activity state to obtain an air conditioner control result. During the operation of the target air conditioner, the scene image data associated with the air conditioner operation area corresponding to the target air conditioner is obtained, the object quantity category and object clothing type in the air conditioner operation area are determined by analyzing the scene image data, and object pose recognition is performed on each target object in the scene image data to determine the object activity state of each target object. Furthermore, the operation of the target air conditioner is intelligently controlled through multi-modal parameters such as the object quantity category, the object clothing type, and the object activity state, so as to realize intelligent and personalized timely adjustment of the air conditioner operation parameters according to the user state in the specified area, thereby effectively improving the user comfort and air conditioner energy-saving efficiency.

[0133] As Figure 3 shown, Figure 3 FIG. is a schematic flowchart of an embodiment for determining the object activity state in the air conditioner control method provided by the embodiment of the present application. Specifically, in this embodiment, the air conditioner control method further includes steps 301 to 303:

[0134] 301. Obtain a first object key point and a second object key point among the object key points;

[0135] 302. Calculate the key point displacement data of the target object according to the first object key point and the second object key point;

[0136] 303. Perform state recognition on the target object based on the key point displacement data to determine the object activity state of the target object.

[0137] Based on the above embodiment, in this embodiment, after the air conditioner obtains the object detection frame and / or object key points, it can use the object key points of each object in the continuous scene image data to determine whether the target object is in a dynamic state, and then determine the object activity state of each target object.

[0138] Specifically, the air conditioner obtains a first object key point and a second object key point among the object key points, where the first object key point is the object key point of a specified target object in the scene image data at a certain moment. The second object key point is the object key point corresponding to the first object key point of the specified target object in the scene image data at the next moment.

[0139] Specifically, after the air conditioner obtains the first object key point and the second object key point, it calculates the key point displacement data of the target object according to the first object key point and the second object key point. The calculation method of the key point displacement data is as follows:

[0140]

[0141] where d i，j is the single-point displacement data of the i-th first object key point and the i-th second object key point; D j is the key point displacement data of the j-th target object. K is the number of key points of the target object.

[0142] Specifically, after the air conditioner obtains the key point displacement data of the target object, it performs state recognition on the target object based on the key point displacement data and a preset displacement threshold, and determines the object activity state of the target object. The preset displacement threshold is a preset average displacement parameter.

[0143] Optionally, if the key point displacement data of any target object is greater than the preset displacement threshold, the air conditioner determines that there is a target object in a dynamic activity state in the air conditioner operation area, and determines the object activity state of the air conditioner operation area as the dynamic activity state.

[0144] Optionally, if each key point displacement data is less than the preset displacement threshold, the air conditioner determines that there is no target object in a dynamic activity state in the air conditioner operation area, and determines the object activity state of the air conditioner operation area as the static activity state.

[0145] In this embodiment, the air conditioner obtains the first object key point and the second object key point in the object key points; calculates the key point displacement data of the target object according to the first object key point and the second object key point; performs state recognition on the target object based on the key point displacement data, and determines the object activity state of the target object, where the object activity state includes any one of the dynamic activity state and the static activity state. It is realized to judge the dynamicity of the target object through the displacement state of the key points of the target object in the continuous scene image data, thereby reducing the misjudgment probability of the dynamicity of the target object and improving the control accuracy of the air conditioner.

[0146] As Figure 4 shown, Figure 4 is a schematic flowchart of another embodiment for determining the object activity state in the air conditioner control method provided by the embodiment of the present application. Specifically, in this embodiment, the air conditioner control method further includes steps 401 to 403:

[0147] 401. Obtain the first detected grayscale of the first object detection frame and the second detected grayscale of the second object detection frame;

[0148] 402. Determine the target optical flow data of the target object according to the first detected grayscale and the second detected grayscale;

[0149] 403. Perform state recognition on the target object according to the target optical flow data to determine the object activity state of the target object.

[0150] Based on the first embodiment, in this embodiment, after the air conditioner obtains the object detection frame and / or object key points, it can also use the grayscale information corresponding to each object detection frame in the continuous scene image data to determine whether the target object is in a dynamic state, and then determine the object activity state of each target object.

[0151] Specifically, the air conditioner obtains the first detected grayscale of the first object detection frame and the second detected grayscale of the second object detection frame. Among them, the first object detection frame is the detection frame image data in the specific object detection frame at the first moment. The second object detection frame is the detection frame data in the specific object detection frame at the second moment. Among them, in a specific embodiment, the first moment is the t moment, and the second moment is the t + dt moment.

[0152] Among them, the first detected grayscale is the grayscale information corresponding to the scene image data corresponding to the first object detection frame. The second detected grayscale is the grayscale information corresponding to the scene image data corresponding to the second object detection frame. Optionally, in a specific embodiment, the first detected grayscale is I(x, y, t), and the second detected grayscale is I(x + dx, y + dy, t + dt).

[0153] Specifically, the air conditioner determines the target optical flow data of the target object according to the first detected grayscale and the second detected grayscale, that is, after the air conditioner obtains the first detected grayscale and the second detected grayscale, it constructs the corresponding calculation equation according to the gray-scale invariance hypothesis as follows:

[0154] I(x, y, t) = I(x + dx, y + dy, t + dt)

[0155] Perform a first-order Taylor expansion on this equation to obtain:

[0156]

[0157] Among them, is the gradient of the scene image data in the x-axis direction at this point, is the gradient of the scene image data in the y-axis direction at this point, respectively denoted as I x and I y , is the change amount of the detected grayscale with respect to time, denoted as It .

[0158] The terminal presets u and v as the dynamic optical flows of the pixel along the x-axis and y-axis respectively, and obtains:

[0159]

[0160] According to the change amount of each gradient direction and the detected gray level with respect to time, the following change matrix can be obtained:

[0161]

[0162] The terminal constructs an overdetermined equation for determining the target optical flow data of the target object according to the change matrix and the preset constraint conditions. The expression of the overdetermined equation is as follows:

[0163]

[0164] The terminal calculates the static optical flow vector corresponding to the target optical flow data according to the overdetermined equation. The calculation method is:

[0165]

[0166] where U and V are the static optical flow vectors, and u i and v i are the dynamic optical flow velocities of the feature point i.

[0167] Specifically, the terminal calculates the target optical flow data according to the static optical flow vector and the dynamic optical flow velocity. The calculation method of the target optical flow data is as follows:

[0168]

[0169] Specifically, after the terminal obtains the target optical flow data corresponding to each target object, it performs state recognition on the target object according to the target optical flow data and the preset optical flow threshold, and determines the object activity state of the target object.

[0170] Optionally, if the target optical flow data of any target object is greater than the preset optical flow threshold, the air conditioner determines that there is a target object in a dynamic activity state in the air conditioner operation area, and determines the object activity state of the air conditioner operation area as the dynamic activity state.

[0171] Optionally, if each target optical flow data is less than the preset optical flow threshold, the air conditioner determines that there is no target object in a dynamic activity state in the air conditioner operation area, and determines the object activity state of the air conditioner operation area as the static activity state.

[0172] In this embodiment, the air conditioner obtains the first detected gray level of the first object detection frame and the second detected gray level of the second object detection frame; determines the target optical flow data of the target object according to the first detected gray level and the second detected gray level; and performs state recognition on the target object according to the target optical flow data to determine the object activity state of the target object. It is realized to judge the dynamics of the target object through the optical flow change of the object detection frame in the continuous scene image data, thereby reducing the misjudgment probability of the dynamics of the target object and improving the control accuracy of the air conditioner.

[0173] To better implement the air conditioner control method in the embodiments of the present application, on the basis of the air conditioner control method, an air conditioner control device is further provided in the embodiments of the present application, as Figure 5 shown Figure 5 is a schematic structural diagram of an embodiment of the air conditioner control device provided in the embodiments of the present application. Specifically, the air conditioner control device 500 includes:

[0174] An image acquisition module 501, configured to obtain the scene image data corresponding to the target air conditioner in response to an air conditioner control request for the target air conditioner;

[0175] A first recognition module 502, configured to determine the object quantity category and object clothing type in the air conditioner operation area corresponding to the target air conditioner based on the scene image data;

[0176] A second recognition module 503, configured to perform object posture recognition on the scene image data to determine the object activity state of each target object in the scene image data;

[0177] An air conditioner control module 504, configured to perform operation control on the target air conditioner according to the object quantity category, the object clothing type, and the object activity state to obtain an air conditioner control result.

[0178] In a possible implementation manner of this embodiment, the air conditioner control device determines the object quantity category and object clothing type in the air conditioner operation area corresponding to the target air conditioner based on the scene image data, including:

[0179] Perform first target detection on the scene image data to determine the target object in the scene image data;

[0180] Determine the object quantity category of the target object according to the object statistical information of the target object and a preset object quantity threshold;

[0181] Perform second target detection on the target object image in the scene image data to determine the object clothing type of the target object.

[0182] In a possible implementation of this embodiment, the air conditioner control device performs object pose recognition on the scene image data to determine the object activity states of each target object in the scene image data, including:

[0183] Performing image detection on the scene image data by using a state recognition model to obtain an object detection frame corresponding to each target object and object key points corresponding to the target object;

[0184] Performing state recognition on the target object according to the object detection frame and / or object key points to determine the object activity states of each target object in the scene image data.

[0185] In a possible implementation of this embodiment, the air conditioner control device performs state recognition on the target object according to the object detection frame and / or object key points to determine the object activity states of each target object in the scene image data, including:

[0186] Obtaining a first object key point and a second object key point in the object key points;

[0187] Calculating key point displacement data of the target object according to the first object key point and the second object key point;

[0188] Performing state recognition on the target object based on the key point displacement data to determine the object activity state of the target object, where the object activity state includes any one of a dynamic activity state and a static activity state.

[0189] In a possible implementation of this embodiment, the object detection frame in the air conditioner control device includes a first object detection frame and a second object detection frame;

[0190] The performing state recognition on the target object according to the object detection frame and / or object key points to determine the object activity states of each target object in the scene image data includes:

[0191] Obtaining a first detection gray level of the first object detection frame and a second detection gray level of the second object detection frame;

[0192] Determining target optical flow data of the target object according to the first detection gray level and the second detection gray level;

[0193] Performing state recognition on the target object according to the target optical flow data to determine the object activity state of the target object.

[0194] In a possible implementation of this embodiment, the air conditioner control device performs operation control on the target air conditioner according to the object quantity category, the object clothing type, and the object activity state to obtain an air conditioner control result, including:

[0195] Obtain the target temperature difference between the target set temperature of the target air conditioner and the current area room temperature in the air conditioner operation area;

[0196] If the target temperature difference is less than or equal to a preset temperature difference threshold, adjust the initial operation parameters of the target air conditioner according to the object quantity category, the object clothing type, and / or the object activity state to obtain an air conditioner control result, where the initial operation parameters include an initial temperature parameter and / or an initial wind speed parameter.

[0197] In a possible implementation of this embodiment, the air conditioner control device performs operation control on the target air conditioner according to the object quantity category, the object clothing type, and the object activity state to obtain an air conditioner control result, including:

[0198] If the object activity state is a static activity state, determine the first operation parameters of the target air conditioner according to the static control strategy corresponding to the static activity state, the object quantity category, and the object clothing type;

[0199] If the object activity state is a dynamic activity state, correct the first operation parameters according to the dynamic control strategy corresponding to the dynamic activity state to obtain second operation parameters;

[0200] Adjust the initial operation parameters of the target air conditioner according to the first operation parameters or the second operation parameters to obtain an air conditioner control result.

[0201] In this embodiment, the air conditioner control device obtains the scene image data corresponding to the target air conditioner by responding to the air conditioner control request for the target air conditioner; determines the object quantity category and object clothing type in the air conditioner operation area corresponding to the target air conditioner based on the scene image data; performs object posture recognition on the scene image data to determine the object activity status of each target object in the scene image data; and performs operation control on the target air conditioner according to the object quantity category, the object clothing type, and the object activity status to obtain the air conditioner control result. During the operation of the target air conditioner, the scene image data associated with the air conditioner operation area corresponding to the target air conditioner is obtained. By analyzing the scene image data, the object quantity category and object clothing type in the air conditioner operation area are determined, and object posture recognition is performed on each target object in the scene image data to determine the object activity status of each target object. Furthermore, the target air conditioner is intelligently operated and controlled through multimodal parameters such as the object quantity category, the object clothing type, and the object activity status, so as to realize intelligent and personalized timely adjustment of the air conditioner operation parameters according to the user status in the specified area, effectively improving the user comfort and air conditioner energy-saving efficiency.

[0202] An embodiment of the present invention further provides an air conditioner, as Figure 6 shown Figure 6 which is a schematic structural diagram of an embodiment of the air conditioner provided in the embodiment of the present application.

[0203] The air conditioner integrates any one of the air conditioner control devices provided in the embodiments of the present invention. The air conditioner includes:

[0204] one or more processors;

[0205] a memory; and

[0206] one or more application programs, where the one or more application programs are stored in the memory and are configured to be executed by the processor to perform the steps in the air conditioner control method in any one of the embodiments of the above air conditioner control method.

[0207] Specifically: The air conditioner may include a processor 601 with one or more processing cores, a memory 602 with one or more computer-readable storage media, a power supply 603, an input unit 604, and other components. Those skilled in the art can understand that Figure 6 the air conditioner structure shown in

[0208] The processor 601 is the control center of the air conditioner, connecting various parts of the entire air conditioner through various interfaces and lines. By running or executing software programs and / or modules stored in the memory 602, and by invoking the data stored in the memory 602, it executes various functions of the air conditioner and processes data, thereby monitoring the air conditioner as a whole. Optionally, the processor 601 may include one or more processing cores; preferably, the processor 601 may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, user interface, application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor may not be integrated into the processor 601 either.

[0209] The memory 602 can be used to store software programs and modules. The processor 601 executes various functional applications and data processing by running the software programs and modules stored in the memory 602. The memory 602 mainly includes a program storage area and a data storage area. Among them, the program storage area can store the operating system, application programs required for at least one function (such as the sound playback function, image playback function, etc.); the data storage area can store data created according to the use of the air conditioner. In addition, the memory 602 can include high-speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices. Correspondingly, the memory 602 can also include a memory controller to provide the processor 601 with access to the memory 602.

[0210] The air conditioner also includes a power supply 603 that powers each component. Preferably, the power supply 603 can be logically connected to the processor 601 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system. The power supply 603 can also include any components such as one or more DC or AC power supplies, a recharge system, a power failure detection circuit, a power converter or inverter, and a power status indicator.

[0211] The air conditioner may also include an input unit 604, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0212] Although not shown, the air conditioner may also include a display unit, etc., which will not be elaborated here. Specifically, in this embodiment, the processor 601 in the air conditioner will load the executable files corresponding to the processes of one or more application programs into the memory 602 according to the following instructions, and the processor 601 will run the application programs stored in the memory 602 to realize various functions as follows:

[0213] In response to an air conditioner control request for a target air conditioner, obtain the scene image data corresponding to the target air conditioner;

[0214] Based on the scene image data, determine the object quantity category and object clothing type in the air conditioner operation area corresponding to the target air conditioner;

[0215] Perform object pose recognition on the scene image data to determine the object activity status of each target object in the scene image data;

[0216] Perform operation control on the target air conditioner according to the object quantity category, the object clothing type, and the object activity status to obtain an air conditioner control result.

[0217] To this end, an embodiment of the present invention provides a computer-readable storage medium, which may include: a read-only memory (ROM, Read Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, an optical disc, etc. A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in any of the air conditioner control methods provided by the embodiments of the present invention. For example, when the computer program is loaded by the processor, the following steps may be executed:

[0218] In response to an air conditioner control request for a target air conditioner, obtain the scene image data corresponding to the target air conditioner;

[0219] Based on the scene image data, determine the object quantity category and object clothing type in the air conditioner operation area corresponding to the target air conditioner;

[0220] Perform object pose recognition on the scene image data to determine the object activity status of each target object in the scene image data;

[0221] Perform operation control on the target air conditioner according to the object quantity category, the object clothing type, and the object activity status to obtain an air conditioner control result.

[0222] In the above embodiments, the descriptions of each embodiment have their own focuses. For the parts not detailed in a certain embodiment, reference may be made to the detailed descriptions of other embodiments above, and details will not be repeated here.

[0223] When specifically implemented, the above-mentioned units or structures may be implemented as independent entities, or may be combined arbitrarily to be implemented as the same or several entities. For the specific implementation of the above-mentioned units or structures, reference may be made to the method embodiments above, and details will not be repeated here.

[0224] For the specific implementation of each of the above operations, reference may be made to the above embodiments, and details will not be repeated here.

[0225] The above has introduced in detail a method for controlling an air conditioner provided by an embodiment of the present application. In this article, specific embodiments are used to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. An air conditioner control method, characterized in that, The air conditioner control method includes: Responding to an air conditioner control request for a target air conditioner, and obtaining scene image data corresponding to the target air conditioner; Based on the scene image data, determining the object quantity category and object clothing type in the air conditioner operation area corresponding to the target air conditioner; Performing object pose recognition on the scene image data to determine the object activity status of each target object in the scene image data; Performing operation control on the target air conditioner according to the object quantity category, the object clothing type, and the object activity status, to obtain an air conditioner control result.

2. The air conditioner control method according to claim 1, wherein The determining the object quantity category and object clothing type in the air conditioner operation area corresponding to the target air conditioner based on the scene image data includes: Performing first target detection on the scene image data to determine the target objects in the scene image data; Determining the object quantity category of the target objects according to the object statistical information of the target objects and a preset object quantity threshold; Performing second target detection on the target object images in the scene image data to determine the object clothing type of the target objects.

3. The air conditioner control method according to claim 1, characterized in that, The performing object pose recognition on the scene image data to determine the object activity status of each target object in the scene image data includes: Using a status recognition model to perform image detection on the scene image data, to obtain an object detection frame corresponding to each target object, and object key points corresponding to the target object; Performing status recognition on the target object according to the object detection frame and / or the object key points, to determine the object activity status of each target object in the scene image data.

4. The air conditioner control method according to claim 3, wherein, The performing status recognition on the target object according to the object detection frame and / or the object key points, to determine the object activity status of each target object in the scene image data includes: Obtaining a first object key point and a second object key point in the object key points; Calculating key point displacement data of the target object according to the first object key point and the second object key point; Performing status recognition on the target object based on the key point displacement data, to determine the object activity status of the target object, where the object activity status includes any one of a dynamic activity status and a static activity status.

5. The air conditioner control method according to claim 3, wherein The object detection frame includes a first object detection frame and a second object detection frame; The performing status recognition on the target object according to the object detection frame and / or the object key points, to determine the object activity status of each target object in the scene image data includes: Obtaining a first detection gray level of the first object detection frame, and a second detection gray level of the second object detection frame; Determining target optical flow data of the target object according to the first detection gray level and the second detection gray level; Performing status recognition on the target object according to the target optical flow data, to determine the object activity status of the target object.

6. The air conditioner control method according to any one of claims 1-5, characterized in that The performing operation control on the target air conditioner according to the object quantity category, the object clothing type, and the object activity status, to obtain an air conditioner control result includes: Obtaining a target temperature difference between a target set temperature of the target air conditioner and a current area room temperature in the air conditioner operation area; If the target temperature difference is less than or equal to the preset temperature difference threshold, the initial operating parameters of the target air conditioner are adjusted according to the number category of the objects, the clothing types of the objects, and / or the activity states of the objects to obtain an air conditioner control result, where the initial operating parameters include initial temperature parameters and / or initial wind speed parameters.

7. The air conditioner control method according to claim 6, characterized in that, The operation control of the target air conditioner according to the number category of the objects, the clothing types of the objects, and the activity states of the objects to obtain an air conditioner control result includes: If the activity state of the object is a static activity state, determine the first operating parameters of the target air conditioner according to the static control strategy corresponding to the static activity state, the number category of the objects, and the clothing types of the objects; If the activity state of the object is a dynamic activity state, correct the first operating parameters according to the dynamic control strategy corresponding to the dynamic activity state to obtain second operating parameters; Adjust the initial operating parameters of the target air conditioner according to the first operating parameters or the second operating parameters to obtain an air conditioner control result.

8. An air conditioner control device, characterized in that, The air conditioner control device includes: An image acquisition module configured to obtain the scene image data corresponding to the target air conditioner in response to an air conditioner control request for the target air conditioner; A first recognition module configured to determine the number category of the objects and the clothing types of the objects in the air conditioner operation area corresponding to the target air conditioner based on the scene image data; A second recognition module configured to perform object pose recognition on the scene image data to determine the activity states of the target objects in the scene image data; An air conditioner control module configured to perform operation control on the target air conditioner according to the number category of the objects, the clothing types of the objects, and the activity states of the objects to obtain an air conditioner control result.

9. An air conditioner, characterized in that, The air conditioner includes: One or more processors; A memory; and One or more applications, where the one or more applications are stored in the memory and configured to be executed by the processor to implement the steps of the air conditioner control method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A computer program is stored thereon, and the computer program is loaded by the processor to execute the steps of the air conditioner control method according to any one of claims 1 to 7.

Images