Intelligent air conditioner control method, device and equipment based on human body postures and medium

Abstract

The invention discloses an intelligent air conditioner control method, device and equipment based on human body postures and a medium. The method comprises the following steps: receiving a real-time human body thermal imaging picture sent by an infrared visual detection module; performing posture recognition on the human body thermal imaging picture through a preset posture recognition model to obtain a current human body posture; determining a human body metabolism rate according to the current human body posture, and performing temperature calculation according to the human body metabolism rate and a predicted average somatosensory index to obtain a target indoor temperature; and air conditioning equipment is controlled to operate according to the target indoor temperature. By means of the method, the problem that in the prior art, an intelligent air conditioner cannot give play to the high comfort characteristic of an intelligent air conditioning system can be solved.

Description

Technical Field

[0001] The present invention relates to the technical field of smart homes, and in particular to a method, device, equipment and medium for controlling smart air conditioners based on human body posture. Background Art

[0002] In modern home life, air conditioners have become standard appliances for maintaining a pleasant indoor environment, serving every family all year round. Thanks to the rapid development of artificial intelligence and sensor technology, smart air conditioners are gradually replacing traditional air conditioners and becoming the new favorite of the market. A core focus of smart air conditioner research and development is the user's physiological experience, especially the human body surface temperature, a key parameter that directly reflects thermal comfort, which is widely adopted in the data monitoring and control logic of smart air conditioners. However, the current smart air conditioner control methods are generally relatively simple and broad, making it difficult to accurately capture and respond to users' diversified pursuit of thermal comfort. In addition, although people's perception of comfortable temperature varies greatly, most smart air conditioner solutions on the market still follow the same set of standards to set the preset value of thermal comfort, ignoring the significant differences between individuals. In the subsequent control process, other relevant indicators are rarely integrated for comprehensive control, which results in the inability of smart air conditioners in the existing technology to give full play to the high comfort characteristics of smart air conditioning systems. Summary of the invention

[0003] The embodiments of the present invention provide a human body posture-based intelligent air conditioning control method, device, equipment and medium, aiming to solve the problem that the intelligent air conditioning in the prior art cannot bring into play the high comfort characteristics of the intelligent air conditioning system.

[0004] In a first aspect, an embodiment of the present invention provides an intelligent air-conditioning control method based on human body posture, which includes: receiving a real-time human body thermal imaging picture sent by an infrared visual detection module; performing posture recognition on the human body thermal imaging picture through a preset posture recognition model to obtain the current human body posture; determining the human body metabolic rate according to the current human body posture, performing temperature calculation according to the human body metabolic rate and the predicted average body sensation index to obtain the target indoor temperature; and controlling the operation of the air-conditioning equipment according to the target indoor temperature.

[0005] In the second aspect, an embodiment of the present invention also provides an intelligent air-conditioning control device based on human body posture, which includes: a receiving unit, used to receive real-time human body thermal imaging pictures sent by an infrared visual detection module; an identification unit, used to perform posture recognition on the human body thermal imaging pictures through a preset posture recognition model to obtain the current human body posture; a calculation unit, used to determine the human body metabolic rate according to the current human body posture, and perform temperature calculation according to the human body metabolic rate and the predicted average body sensation index to obtain the target indoor temperature; a control unit, used to control the operation of the air-conditioning equipment according to the target indoor temperature.

[0006] In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above method when executing the computer program.

[0007] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a computer program, wherein the computer program includes program instructions, and the program instructions can implement the above method when executed by a processor.

[0008] The embodiment of the present invention provides a method, device, equipment and medium for intelligent air conditioning control based on human posture. The method includes: receiving a real-time human thermal imaging picture sent by an infrared visual detection module; performing posture recognition on the human thermal imaging picture through a preset posture recognition model to obtain the current human posture; determining the human metabolic rate according to the current human posture, performing temperature calculation according to the human metabolic rate and the predicted average body sensation index to obtain the target indoor temperature; and controlling the operation of the air conditioning equipment according to the target indoor temperature. The embodiment of the present invention provides the latest data for subsequent posture recognition and target indoor temperature calculation by receiving the human thermal imaging picture sent by the infrared visual detection module, and provides a data basis for the real-time response of the system. The human thermal imaging picture is recognized by a preset posture recognition model to obtain the human posture, so as to identify the posture of the human body in the thermal imaging picture, such as standing, sitting, walking, etc., and provide timely human posture information for subsequent metabolic rate calculation and temperature control. And posture recognition is performed through a preset posture recognition model to determine the human metabolic rate that can reflect the individual's activity level and energy consumption, providing a personalized basis for temperature calculation. Combined with the predicted average body sensation index, the target indoor temperature required by the human body can be calculated more accurately, avoiding temperature discomfort caused by environmental differences or individual differences. The air conditioning equipment is controlled according to the target indoor temperature so that the air conditioning equipment operates according to the temperature required by the human body, ensuring the comfort of the indoor environment, improving the quality of life of users, and allowing the smart air conditioner to effectively exert the high comfort characteristics of the smart air conditioning system, thereby providing personalized needs for different users. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0010] Figure 1 A schematic diagram of a flow chart of an intelligent air conditioning control method based on human body posture provided by an embodiment of the present invention;

[0011] Figure 2 A schematic diagram of a sub-process of an intelligent air-conditioning control method based on human body posture provided by an embodiment of the present invention;

[0012] Figure 3 A schematic diagram of a sub-process of an intelligent air-conditioning control method based on human body posture provided by an embodiment of the present invention;

[0013] Figure 4 A schematic diagram of a sub-process of an intelligent air-conditioning control method based on human body posture provided by an embodiment of the present invention;

[0014] Figure 5 A schematic diagram of a sub-process of an intelligent air-conditioning control method based on human body posture provided by an embodiment of the present invention;

[0015] Figure 6 A schematic diagram of a sub-process of an intelligent air-conditioning control method based on human body posture provided by an embodiment of the present invention;

[0016] Figure 7 A schematic diagram of a sub-process of an intelligent air-conditioning control method based on human body posture provided by an embodiment of the present invention;

[0017] Figure 8 A schematic block diagram of an intelligent air-conditioning control device based on human posture provided by an embodiment of the present invention;

[0018] Fig. 9 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0021] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0022] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0023] See also Figure 1 , Figure 1 A flow chart of an intelligent air conditioning control method based on human posture provided in an embodiment of the present invention. The intelligent air conditioning control method based on human posture in this embodiment can be applied to an intelligent air conditioning control system. Specifically, in the intelligent air conditioning control system, the system master controller plays a core role, which connects and regulates the information and instructions between the thermal imaging camera and the air conditioning control module. The shooting work of the thermal imaging camera is the responsibility of the infrared visual detection module, which can capture real-time human thermal imaging pictures. The system master controller integrates an AI processing module and an air conditioning control module. The AI ​​processing module is further subdivided into a human posture recognition model, a sequence learning model, and a preset somatosensory index evaluation model, which work together to process the received thermal imaging pictures. Specifically, the AI ​​processing module is responsible for parsing the human posture in the picture, and the sequence learning model predicts and evaluates the posture changes of the human body based on these posture information. The preset somatosensory index evaluation model generates corresponding parameters based on the posture of the human body, and finally calculates the target indoor temperature in combination with the environmental conditions. The air conditioning control module uses the deep learning algorithm and control algorithm to accurately adjust the air volume of the air conditioner according to the target indoor temperature output by the AI ​​processing module, through the specific function chip on the motherboard of the system master controller, to ensure that the indoor temperature reaches the preset comfort level. Information interaction and command transmission in the entire system are completed through the circuit signals of the system master controller. In particular, the wired communication protocol is used between the system master controller and the infrared visual detection module for efficient and stable data transmission. In summary, the intelligent air conditioning control system integrates advanced AI processing technology and precise air conditioning control technology to realize real-time processing of human thermal imaging images and intelligent regulation of air conditioning air volume, providing users with a more comfortable and personalized indoor environment experience.

[0024] Figure 1 1 is a flow chart of an intelligent air-conditioning control method based on human body posture provided by an embodiment of the present invention. As shown in the figure, the method includes the following steps S110-S140.

[0025] S110, receiving a real-time human body thermal imaging picture sent by an infrared vision detection module.

[0026] In this embodiment, the infrared visual detection module is a module specially designed to capture and record human thermal radiation. It uses infrared imaging technology to generate thermal imaging pictures by detecting the heat emitted from the human body surface. The infrared visual detection module includes components such as a thermal imaging camera, a signal processing circuit and a communication interface. The thermal imaging camera is responsible for collecting human thermal imaging pictures, and the signal processing circuit converts the captured infrared signal into digital image data. The human thermal imaging picture refers to a sequence of human thermal radiation images captured and generated by the infrared visual detection module in a continuous time. These pictures can reflect the temperature distribution and changes on the human body surface in real time. The real-time human thermal imaging picture sent by the infrared visual detection module can be received through a communication protocol. Specifically, the communication protocol refers to a set of rules and standards agreed upon between two or more parties in network communication to ensure the correct transmission and analysis of information. In the intelligent air-conditioning control system, the infrared visual detection module and the system master controller or other processing units need to use a certain communication protocol for data transmission. Common communication protocols include Ethernet, serial communication, wireless local area network (Wi-Fi), etc. Among them, the specific protocol selection may depend on factors such as the specific needs of the system, transmission distance, transmission rate and cost. This is not limited. In this embodiment, the communication protocol can be a wired communication protocol, such as Modbus, 485, etc. The infrared visual detection module controls the thermal imaging camera to capture real-time indoor human thermal imaging images and continuously stores them in the specified memory location. The AI ​​processing module in the system master controller obtains the human thermal imaging images in the memory in time sequence. By receiving the real-time human thermal imaging images sent by the infrared visual detection module, it is ensured that the system can obtain human thermal radiation information in real time, providing a reliable and personalized data basis for subsequent analysis and control.

[0027] S120: Performing posture recognition on the human body thermal imaging image through a preset posture recognition model to obtain a current human body posture.

[0028] In this embodiment, the posture recognition model is a machine learning model that can extract key feature information from the input thermal imaging picture and identify the current posture of the human body based on the feature information. Among them, the preset posture recognition model is a posture recognition model after training. Specifically, human thermal imaging pictures in different air-conditioning working scenes are obtained, such as bedrooms, living rooms and other scenes using infrared cameras to take human thermal imaging pictures; then the thermal imaging pictures in different working scenes are classified, that is, the pictures in the bedroom scene are aggregated together, and the pictures in the living room are aggregated together; secondly, the aggregated photos are manually distinguished and marked with training labels, and the input model is told what action this is, and the model will recognize and automatically update the internal parameters (here all the model itself processes, and no manual intervention is required), which is the process of targeted training; finally, the model will save the parameters with the best recognition accuracy (here the model will divide the input pictures into two types: training set and test set, and the best accuracy here is that the model has been trained using the training set, and the best result in the test set) as the final model parameters according to the training results to obtain the preset posture recognition model. When the human body thermal imaging picture is input into the preset posture recognition model, the model can automatically perform posture recognition to generate a human body posture (e.g., lying on the side) corresponding to the current human body thermal imaging picture. The human body posture is obtained by combining the human body thermal imaging picture and the preset posture recognition model to accurately identify the posture of the human body in the thermal imaging picture, providing timely human body posture information for subsequent metabolic rate calculation and temperature control.

[0029] In one embodiment, if Figure 2 As shown, the step S120 includes steps S121-S122.

[0030] S121, extracting feature information of the human body thermal imaging picture through the posture recognition model;

[0031] S122: Classify the feature information through the fully connected layer of the posture recognition model to obtain the human body posture of the current human body thermal imaging picture.

[0032] In this embodiment, the fully connected layer is a layer in the model that maps the extracted feature vector to a classification space. Among them, each neuron in the fully connected layer is connected to all neurons in the previous layer. The feature information of the human body thermal imaging picture is extracted by the posture recognition model. Specifically, the posture recognition model first receives the human body thermal imaging picture as input. Then, the picture data passes through a series of convolutional layers, pooling layers, etc. (these layers are often used for image processing tasks in deep learning), which are responsible for extracting discriminative features from the original picture data. These features may include edges, textures, shapes, etc., which are crucial for identifying different human body postures. After being processed by the feature extraction layer, a series of feature maps are output, which represent the features of different positions and scales in the picture in the form of a two-dimensional matrix, and feature information (one-dimensional feature vector) is obtained according to the feature map. The feature information is classified through the fully connected layer of the posture recognition model to obtain the human body posture of the current human body thermal imaging picture. Specifically, when the feature information passes through the fully connected layer, it passes through a classifier (for example, a softmax function, a decision tree, etc.) to convert the output into a probability distribution, indicating the probability that the input picture belongs to each posture category. Finally, the category with the highest probability is selected as the human posture of the current human thermal imaging picture. The posture recognition model is used to extract features from the human thermal imaging picture and classify them to accurately identify the current posture of the human body.

[0033] S130, determining a human metabolic rate according to the current human posture, and performing temperature calculation according to the human metabolic rate and a predicted average body sensation index to obtain a target indoor temperature.

[0034] In this embodiment, the human metabolic rate refers to the heat or energy consumed by the human body to maintain basic life activities. However, when the human body is in a posture that changes significantly, the metabolic rate will change. The human metabolic rate is determined according to the current human body posture. Specifically, a metabolic table can be determined according to the corresponding metabolic data. The table contains human metabolic rates corresponding to different human body postures, and then the current human body posture is matched with the metabolic table to obtain the human metabolic rate. The target indoor temperature is obtained by performing temperature calculation according to the human body metabolic rate and the predicted average body sensation index. Specifically, the predicted average body sensation index is an evaluation index (PMV index, full name Predicted Mean Vote) that characterizes the thermal response of the human body. Among them, the predicted average body sensation index can be determined by the current human body metabolic rate and environmental parameters and clothing thermal resistance, wherein the environmental parameters include: ambient temperature, relative humidity, average radiation temperature, air velocity. The human body metabolic rate and the predicted average body sensation index are subjected to temperature calculation through a thermal comfort model or function to obtain the output target indoor temperature. The target indoor temperature can be used to adjust the indoor environment settings to ensure that the human body feels comfortable under a given posture and activity level. By determining the metabolic rate based on the current human posture, and combining environmental parameters, clothing thermal resistance, and the predicted average body sensation index to perform temperature mapping calculations to obtain the target indoor temperature, it can be ensured that the temperature provided by the air conditioning equipment meets the human body's comfort needs, thereby improving user satisfaction.

[0035] In one embodiment, if Figure 3 As shown, the step S130 includes steps S131-S133.

[0036] S131, searching a preset metabolism table according to the current human body posture to determine the human body metabolic rate;

[0037] S132, inputting the human body metabolic rate into a preset body sensation index evaluation model to obtain the predicted average body sensation index;

[0038] S133. Calculate the predicted average body sensation index, the metabolic rate and other temperature parameters through a preset calculation formula to obtain the target indoor temperature, wherein the other temperature parameters are the obtained ambient temperature, relative humidity, average radiation temperature, air flow rate, and clothing thermal resistance.

[0039] In this embodiment, the preset metabolic table is determined based on the human body posture and the reference data of the corresponding metabolic rate, wherein the specific determination method and reference data are not limited. According to the current human body posture, the preset metabolic table is queried to determine the human body metabolic rate. Specifically, according to the current human body posture, the preset metabolic table is queried. For example, if the current human body posture is sleeping, the preset metabolic table is:

[0040]

[0041] According to the preset metabolic table, the human metabolic rate corresponding to the current human posture can be queried to be 0.7. The human metabolic rate is input into the preset somatosensory index evaluation model to obtain the predicted average somatosensory index, wherein the preset somatosensory index evaluation model is a model that calculates the somatosensory index based on input environmental parameters (such as temperature, humidity, wind speed, etc.) and human parameters (metabolic rate, clothing thermal resistance, etc.). Specifically, the specific calculation formula of the preset somatosensory index evaluation model is: PMV = 0.303 × e -0.036M +0.028{ambient temperature, relative humidity, average radiation temperature, air velocity, clothing thermal resistance}, where PMV is the predicted average body sensation index, M represents the human metabolic rate, e is an index, ambient temperature, relative humidity and air velocity can all be directly obtained through air conditioning sensors, the average radiation temperature takes a temperature value one degree lower or higher than the room temperature according to the cooling and heating conditions of the air conditioning, and the clothing thermal resistance is uniformly set to a corresponding value according to the ambient temperature of the four seasons of spring, summer, autumn and winter, that is, the clothing thermal resistance is obtained from the ambient temperature. This can not only avoid causing trouble to the user's privacy, but also reduce large-scale calculations and system processing time. The predicted average body sensation index, the metabolic rate and other temperature parameters are calculated by a preset calculation formula to obtain the target indoor temperature. Specifically, the preset calculation formula is: target indoor temperature = f{ambient temperature, relative humidity, average radiation temperature, air velocity, human metabolic rate, clothing thermal resistance, PMV}, where f is a calculation function, and there is no limitation on the specific calculation function. For example, it can be calculated by a mapping function. The metabolic rate determined by human posture can reflect the individual's activity level and energy consumption, providing a personalized basis for temperature calculation. Combined with the predicted average body sensation index, the temperature required by the human body can be calculated more accurately, avoiding temperature discomfort caused by environmental differences or individual differences, thereby ensuring that the temperature provided by the air-conditioning equipment meets the comfort needs of the human body and improves user satisfaction.

[0042] S140: Control the operation of the air conditioning equipment according to the target indoor temperature.

[0043] In this embodiment, the target indoor temperature is the temperature that is currently suitable for the user's body feeling. The operation of the air-conditioning equipment is controlled according to the target indoor temperature. Specifically, the wind speed and wind direction can be adjusted according to the target indoor temperature. For example, in cooling mode, if the difference between the target indoor temperature and the current indoor temperature is large, a higher wind speed is selected to quickly cool down; while in heating mode, in order to avoid direct blowing to the human body and causing discomfort, the system may select a lower wind speed and an appropriate wind direction. By automatically adjusting the operating state of the air-conditioning equipment according to the target indoor temperature, such as adjusting the temperature, wind speed, etc., intelligent temperature control is achieved, so that the air-conditioning equipment operates according to the temperature required by the human body, ensuring the comfort of the indoor environment and improving the quality of life of the user.

[0044] In one embodiment, if Figure 4 As shown, step S140 also includes steps S1401-S1402.

[0045] S1401, determining whether the current human body posture is different from the human body posture of the previous frame through a preset sequence learning model, and if different, updating the predicted average body sensation index according to the output posture change type;

[0046] S1402. Perform temperature calculation according to the updated predicted average body sensation index to obtain the latest target indoor temperature, and update the target indoor temperature for controlling the operation of the air-conditioning device to the latest target indoor temperature.

[0047] In this embodiment, the preset sequence learning model is a trained machine learning model that can analyze continuous human posture data and identify changes between postures. The preset sequence learning model is used to determine whether the current human posture is different from the human posture of the previous frame. If different, the predicted average somatosensory index is updated according to the output posture change type. Specifically, the current human posture is input into the sequence learning model, and the model analyzes the difference between the human posture of the current frame and the human posture of the previous frame (or the previous few frames). If the difference exceeds a preset threshold, or the model identifies a specific posture change type, it is determined that the posture has changed. When the model determines that the human posture has changed, the preset sequence learning model outputs a label or vector representing the posture change type. This label or vector may represent a specific change from one posture to another. The latest current human posture is determined according to the output posture change type, and the user's human body change state is determined by the latest human posture. The predicted average body sensation index is updated according to the human body change state, and the temperature is calculated according to the updated predicted average body sensation index and the human metabolic rate and other parameters to obtain the latest target indoor temperature, and the air-conditioning equipment is controlled according to the latest target indoor temperature. The human posture change is judged by a preset sequence learning model, and the predicted average body sensation index is updated according to the posture change type, and then the temperature is calculated and the target indoor temperature of the air-conditioning equipment is updated to meet the thermal comfort requirements of different users and realize the air-conditioning environment adjustment based on different human body personalization.

[0048] In one embodiment, if Figure 5 As shown, the step S1401 includes steps S14011-S14013.

[0049] S14011, analyzing and comparing the current human body posture with the human body posture of the previous frame through the preset sequence learning model, and generating a corresponding posture transformation type if the postures are different;

[0050] S14012, querying the posture transformation type in the preset posture transformation table to obtain the user reaction status;

[0051] S14013. Determine a corresponding optimization parameter value according to the reaction state, perform update calculation according to the optimization parameter value and the predicted average somatosensory index, and obtain an updated predicted average somatosensory index.

[0052] In this embodiment, the preset posture transformation table is a table derived from a large amount of experimental data or user feedback, which records the impact of different posture changes on the user's comfort, attention, emotions and other reaction states. The preset sequence learning model analyzes and compares the current human posture with the human posture of the previous frame. If the postures are different, the corresponding posture transformation type is generated. Specifically, the model compares the human posture of the current frame with the posture of the previous frame. If the comparison result shows that the current posture is different from the posture of the previous frame, the model will generate a label or vector representing the posture transformation type to determine the current posture transformation type, and query the posture transformation type in the preset posture transformation table to obtain the user reaction state. The user reaction state is the user's feedback on the current temperature, and the reaction state is divided into positive state and negative state. For example, if the current posture change type is: from sitting and standing to hugging shoulders with both hands, the preset posture transformation table is:

[0053]

[0054]

[0055] Among them, it can be understood that the data in the table are used as examples. According to the current posture change type, the table is searched, and the current user's reaction state can be obtained as negative 1. Then, according to the negative 1, the corresponding optimization parameter value is determined to be 0.05, and the optimization parameter value is updated and calculated with the predicted average somatosensory index. Specifically, the predicted average somatosensory index is multiplied by the optimization parameter value to obtain the updated predicted average somatosensory index. By updating the predicted average somatosensory index when a small change in the user's human posture is detected, a target indoor temperature that is more suitable for the user can be obtained to provide a more personalized and comfortable target indoor temperature.

[0056] In one embodiment, if Figure 6 As shown, the step S14011 includes steps S140111-S140113.

[0057] S140111, inputting the current human body posture into the preset sequence learning model for analysis and comparison to update the model internal parameter information, wherein the model internal parameter information includes the human body posture of the previous frame;

[0058] S140112, inputting the updated model internal parameter information into the fully connected layer to calculate the probability distribution results of the posture transformation types between different actions;

[0059] S140113. Determine the posture change type of the current human body posture according to the probability distribution result.

[0060] In this embodiment, the time series human posture recognition automatically detects and identifies the posture and action of the human body at different time points through human body thermal imaging pictures, obtains the human body posture, and when the human body posture is input into the preset sequence learning model, the model will update its internal parameter state according to these input information. This state not only includes the initial recognition state information (i.e., the human body posture information at the previous moment), but also includes the current recognition state information (i.e., the human body posture information at the current moment). This state update enables the model to capture the time series feature information of the human body posture. At the end of the neural network, there are usually one or more fully connected layers. These layers connect all the neurons obtained from the previous layer with each neuron of the layer, thereby extracting high-level features. When the sequence learning model recognizes that a human body posture occurs, it will input the updated parameter state into the fully connected layer. The fully connected layer will calculate the probability distribution of different action posture transformation types based on these input information. Finally, according to the output result of the fully connected layer, the transformation type of the human body posture at the current moment can be determined. For example, the posture transformation type of the current human posture is determined by selecting the action posture transformation type with the highest probability, and the human posture is input into the preset sequence learning model for analysis and comparison to update the internal parameter information of the model to obtain the transformation type of the human posture, thereby achieving accurate recognition and classification of the human posture.

[0061] In one embodiment, if Figure 7 As shown, step S140 also includes steps S1403-S1405.

[0062] S1403, after controlling the air conditioning device to adjust the indoor temperature to the latest target indoor temperature, repeatedly executing the step of determining whether the current human body posture is different from the human body posture of the previous frame through a preset sequence learning model to obtain the posture change type;

[0063] S1404, judging whether the preset basic posture type has changed according to the posture change type, and obtaining the latest human body metabolic rate if it has changed;

[0064] S1405. Update the predicted average body sensation index according to the latest human metabolic rate, and perform temperature calculation according to the latest human metabolic rate and the updated predicted average body sensation index to update the latest target indoor temperature.

[0065] In this embodiment, the air conditioning control module in the intelligent air conditioning control system sends instructions to the air conditioning equipment according to the target indoor temperature, adjusts its working mode (such as cooling, heating, air supply, etc.) and output power to achieve indoor temperature control. When the indoor temperature reaches the target indoor temperature, the system will still repeat the step of determining whether the current human body posture is different from the previous frame posture through the preset sequence learning model to obtain the posture change type. According to the posture change type, it is determined whether the preset basic posture type has changed. The preset basic posture type is some preset basic human body postures, including standing, sitting, lying, etc. If the current posture change type indicates that the human body has changed from one basic posture to another basic posture, the system will consider that the basic posture type has changed. For example, if the user's posture changes from sitting to working to standing up and pacing, it is determined that the basic posture of the human body posture has changed. At this time, the preset metabolism table is queried again according to the human body posture to determine the latest human body metabolic rate, and the latest human body metabolic rate is input into the preset body sensation index evaluation model to obtain the updated predicted average body sensation index, and the updated predicted average body sensation index, the latest metabolic rate and other temperature parameters are calculated by the preset calculation formula to obtain the latest target indoor temperature, so as to update the previous target indoor temperature. It should be noted that if the preset basic posture type has not changed, steps S14011-S14013 are still executed, so that when the preset basic posture type does not change, only the preset basic posture type is adjusted according to the optimized parameter value, and the latest target indoor temperature is obtained, and this is repeated. By continuously detecting the changes in the user's human body posture, the temperature is adjusted in real time to meet the thermal comfort requirements of different users while allowing the intelligent air conditioner to give full play to the high comfort characteristics of the intelligent air conditioning system.

[0066] Figure 8 is a schematic block diagram of an intelligent air conditioning control device 200 based on human posture provided by an embodiment of the present invention. Figure 8 As shown, corresponding to the above intelligent air conditioning control method based on human body posture, the present invention also provides an intelligent air conditioning control device based on human body posture. The intelligent air conditioning control device based on human body posture includes a unit for executing the above intelligent air conditioning control method based on human body posture, and the device is mainly configured in an embedded system such as a single chip microcomputer. Specifically, please refer to Figure 8 The intelligent air conditioning control device based on human body posture includes a receiving unit 210, a recognition unit 220, a calculation unit 230 and a control unit 240.

[0067] The receiving unit 210 is used to receive the real-time human body thermal imaging picture sent by the infrared vision detection module.

[0068] The recognition unit 220 is used to perform posture recognition on the human body thermal imaging picture through a preset posture recognition model to obtain the current human body posture.

[0069] In one embodiment, the identification unit 220 includes an extraction unit and a classification unit.

[0070] An extraction unit, used for extracting feature information of the human body thermal imaging picture through the posture recognition model;

[0071] The classification unit is used to classify the feature information through the fully connected layer of the posture recognition model to obtain the human body posture of the current human body thermal imaging picture.

[0072] The calculation unit 230 is used to determine the human body metabolic rate according to the current human body posture, and perform temperature calculation according to the human body metabolic rate and the predicted average body sensation index to obtain the target indoor temperature.

[0073] In one embodiment, the computing unit 230 includes a query unit, an acquisition unit, and a computing subunit.

[0074] A query unit, used for querying a preset metabolism table according to the current human body posture to determine the human body metabolic rate;

[0075] an acquisition unit, configured to input the human body metabolic rate into a preset body sensation index evaluation model to acquire the predicted average body sensation index;

[0076] The calculation subunit is used to calculate the predicted average body sensation index, the metabolic rate and other temperature parameters through a preset calculation formula to obtain the target indoor temperature, wherein the other temperature parameters are the obtained ambient temperature, relative humidity, average radiation temperature, air flow rate, and clothing thermal resistance.

[0077] The control unit 240 is used to control the operation of the air-conditioning equipment according to the target indoor temperature.

[0078] In one embodiment, the control unit 240 includes a determination unit and an update unit.

[0079] A judgment unit, used to judge whether the current human body posture is different from the human body posture of the previous frame through a preset sequence learning model, and if different, update the predicted average body sensation index according to the output posture change type;

[0080] The updating unit is used to perform temperature calculation according to the updated predicted average body sensation index to obtain the latest target indoor temperature, and update the target indoor temperature for controlling the operation of the air-conditioning device to the latest target indoor temperature.

[0081] In one embodiment, the control unit 240 includes a comparison unit, a status query unit, and an optimization unit.

[0082] A comparison unit, used to analyze and compare the current human body posture with the human body posture of the previous frame through the preset sequence learning model, and generate a corresponding posture transformation type if the postures are different;

[0083] A state query unit, used for querying the posture transformation type in the preset posture transformation table to obtain a user reaction state;

[0084] The optimization unit is used to determine a corresponding optimization parameter value according to the reaction state, and perform update calculation according to the optimization parameter value and the predicted average somatosensory index to obtain an updated predicted average somatosensory index.

[0085] In one embodiment, the control unit 240 includes an input unit, a distribution unit, and a determination unit.

[0086] An input unit, used for inputting the current human body posture into the preset sequence learning model for analysis and comparison to update the model internal parameter information, wherein the model internal parameter information includes the human body posture of the previous frame;

[0087] A distribution unit, used to input the updated model internal parameter information into the fully connected layer to calculate the probability distribution results of the posture transformation types between different actions;

[0088] A determination unit is used to determine the posture transformation type of the current human body posture according to the probability distribution result.

[0089] In one embodiment, the control unit 240 includes a repeating unit, a changing unit, and a temperature updating unit.

[0090] a repeating unit, configured to control the air conditioning device to adjust the indoor temperature to the latest target indoor temperature, and then repeatedly perform the step of determining whether the current human body posture is different from the human body posture of the previous frame through a preset sequence learning model to obtain the posture change type;

[0091] a change unit, used for determining whether a preset basic posture type has changed according to the posture change type, and obtaining the latest human body metabolic rate if it has changed;

[0092] A temperature updating unit is used to update the predicted average body sensation index according to the latest human metabolic rate, and to perform temperature calculation according to the latest human metabolic rate and the updated predicted average body sensation index to update the latest target indoor temperature.

[0093] It should be noted that technicians in the relevant field can clearly understand that the specific implementation process of the above-mentioned human posture-based intelligent air-conditioning control device 200 and each unit can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and conciseness of the description, it will not be repeated here.

[0094] The above-mentioned intelligent air conditioning control device based on human body posture can be implemented in the form of a computer program, and the computer program can be used in Fig. 9 Running on the microcontroller shown.

[0095] See also Fig. 9 , Fig. 9 is a schematic block diagram of a single-chip microcomputer provided in an embodiment of the present application. The computer device may be a single-chip microcomputer, but it is understandable that it may also be other devices with computing functions. Fig. 9 Take the block diagram of a single-chip microcomputer as an example.

[0096] See also Fig. 9 The single chip computer 500 includes a processor 502 and a memory connected via a system bus 501 , wherein the memory may include a non-volatile storage medium 503 and an internal memory 504 .

[0097] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions, and when the program instructions are executed, the processor 502 can execute an intelligent air conditioning control method based on human body posture.

[0098] The processor 502 is used to provide computing and control capabilities to support the operation of the entire single-chip microcomputer 500 .

[0099] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute an intelligent air conditioning control method based on human body posture.

[0100] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the microcontroller 500 to which the scheme of the present application is applied. The specific microcontroller 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0101] The processor 502 is used to run a computer program 5032 stored in the memory to implement the steps of the above method.

[0102] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0103] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0104] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the steps of the above method.

[0105] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.

[0106] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0107] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0108] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0109] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0110] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An intelligent air conditioning control method based on human body posture, characterized in that: The method comprises: Receive real-time human thermal imaging images sent by the infrared vision detection module; Performing posture recognition on the human body thermal imaging image through a preset posture recognition model to obtain the current human body posture; Determine a human metabolic rate according to the current human posture, and perform temperature calculation according to the human metabolic rate and the predicted average body sensation index to obtain a target indoor temperature; The operation of the air conditioning equipment is controlled according to the target indoor temperature.

2. The method according to claim 1, characterized in that The step of performing posture recognition on the human body thermal imaging picture through a preset posture recognition model to obtain the current human body posture includes: Extracting feature information of the human body thermal imaging picture through the posture recognition model; The feature information is classified through the fully connected layer of the posture recognition model to obtain the human body posture of the current human body thermal imaging picture.

3. The method according to claim 1, characterized in that The step of determining the human body metabolic rate according to the current human body posture, and performing temperature calculation to obtain the target indoor temperature according to the human body metabolic rate and the predicted average body sensation index includes: Searching a preset metabolism table according to the current human body posture to determine the human body metabolic rate; Inputting the human body metabolic rate into a preset somatosensory index evaluation model to obtain the predicted average somatosensory index; The predicted average body sensation index, the metabolic rate and other temperature parameters are used to calculate the target indoor temperature through a preset calculation formula, wherein the other temperature parameters are the obtained ambient temperature, relative humidity, average radiation temperature, air flow rate, and clothing thermal resistance.

4. The method according to claim 3, characterized in that After the step of controlling the operation of the air conditioning device according to the target indoor temperature, the method further comprises: Determining whether the current human body posture is different from the human body posture of the previous frame through a preset sequence learning model, and if different, updating the predicted average body sensation index according to the output posture change type; The temperature is calculated based on the updated predicted average body sensation index to obtain the latest target indoor temperature, and the target indoor temperature for controlling the operation of the air-conditioning equipment is updated to the latest target indoor temperature.

5. The method according to claim 4, characterized in that The step of determining whether the current human body posture is different from the human body posture of the previous frame by using a preset sequence learning model, and if different, updating the predicted average body sensation index according to the output posture transformation type, comprises: Analyze and compare the current human body posture with the human body posture of the previous frame through the preset sequence learning model, and generate a corresponding posture transformation type if the postures are different; Query the posture change type in the preset posture change table to obtain the user reaction status; The corresponding optimization parameter value is determined according to the reaction state, and an update calculation is performed according to the optimization parameter value and the predicted average somatosensory index to obtain an updated predicted average somatosensory index.

6. The method according to claim 5, characterized in that The step of analyzing and comparing the current human body posture with the human body posture of the previous frame through the preset sequence learning model, and generating a corresponding posture transformation type if the postures are different, includes: Inputting the current human body posture into the preset sequence learning model for analysis and comparison to update the model internal parameter information, wherein the model internal parameter information includes the human body posture of the previous frame; The updated model internal parameter information is input into the fully connected layer to calculate the probability distribution results of the posture transformation types between different actions; The posture transformation type of the current human body posture is determined according to the probability distribution result.

7. The method according to claim 4, characterized in that After the step of controlling the target indoor temperature of the air conditioning device to be updated to the latest target indoor temperature, the method further comprises: After controlling the air conditioning device to adjust the indoor temperature to the latest target indoor temperature, repeatedly executing the step of determining whether the current human body posture is different from the human body posture of the previous frame through a preset sequence learning model to obtain the posture change type; Determining whether a preset basic posture type has changed according to the posture change type, and obtaining the latest human body metabolic rate if it has changed; The predicted average body sensation index is updated according to the latest human metabolic rate, and temperature calculation is performed according to the latest human metabolic rate and the updated predicted average body sensation index to update the latest target indoor temperature.

8. An intelligent air conditioning control device based on human body posture, characterized in that: include: A receiving unit, used to receive real-time human body thermal imaging pictures sent by the infrared vision detection module; A recognition unit, used to perform posture recognition on the human body thermal imaging picture through a preset posture recognition model to obtain a current human body posture; a calculation unit, configured to determine a human metabolic rate according to the current human posture, and to perform temperature calculation according to the human metabolic rate and a predicted average body sensation index to obtain a target indoor temperature; A control unit is used to control the operation of the air-conditioning equipment according to the target indoor temperature.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the method according to any one of claims 1 to 7 can be implemented.

Images