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

Abstract

The application provides a kind of air conditioner control method, device, storage medium and air conditioner, the method comprises: obtaining the thermal comfort model of different user attributes of different environment parameters and / or different scene factors of user established in advance;Based on the thermal comfort model obtained, the thermal comfort value of the current user is determined, and the thermal comfort value of the current user is output;According to the preset control parameter determination rule of the thermal comfort value of the current user output, the current control parameter setting value of the air conditioner is determined, to control the air conditioner according to the current control parameter setting value of the air conditioner determined.The scheme provided by the application can obtain the thermal comfort of the current user by comprehensively considering user attributes, environmental parameters and / or scene factors, more accurately judge the thermal comfort of the user, so as to control the air conditioner.

Description

TECHNICAL FIELD

[0001] The present application relates to the control field, and particularly to a control method and device of an air conditioner, a storage medium and the air conditioner. BACKGROUND

[0002] With the improvement of people's living standards, the comfort requirements for indoor environment are also getting higher and higher. The traditional thermal comfort model cannot accurately describe the instantaneous state of indoor personnel, so the data-driven individual thermal comfort model research has gradually been valued by scholars.

[0003] The general comfort model is difficult to be universal for all people and environment, so it is necessary to design individual thermal comfort model suitable for different people and different climate environment to solve the above problems. SUMMARY

[0004] The main purpose of the present application is to overcome the defects of the above related technology, and provide a control method and device of an air conditioner, a storage medium and the air conditioner, to solve the problem that the comfort model in the related art is difficult to be universal for all people, environment and climate.

[0005] In one aspect, the present application provides a control method of an air conditioner, comprising: obtaining a thermal comfort model of different user attributes of users under different environmental parameters and / or different scene factors; determining a thermal comfort value of a current user based on the obtained thermal comfort model, and outputting the thermal comfort value of the current user; determining a current control parameter setting value of the air conditioner according to a preset control parameter determination rule according to the output thermal comfort value of the current user, so as to control the air conditioner according to the determined current control parameter setting value of the air conditioner.

[0006] Optionally, the thermal comfort model of different user attributes of users under different environmental parameters and / or different scene factors is established by the following steps: collecting physiological parameter thermal comfort feedback information of different user attributes of users under different environmental parameters and / or different scene factors; and establishing a thermal comfort model based on the collected physiological parameter and thermal comfort feedback information of different user attributes of users under different environmental parameters and / or different scene factors.

[0007] Optionally, collecting physiological parameter and thermal comfort feedback information of different user attributes of users under different environmental parameters comprises: collecting physiological parameter of different user attributes of users under different environmental parameters and / or different scene factors through thermal comfort experiment, and collecting thermal comfort feedback information of different user attributes of users under different environmental parameters and / or different scene factors.

[0008] Optionally, the user attributes include at least one of gender, age, body shape, and clothing thermal resistance; and / or the environmental parameters include at least one of air temperature, air humidity, mean radiant temperature, air flow rate, and pollutant concentration; and / or the physiological parameters include at least one of skin temperature, heart rate, pulse, and metabolic rate, wherein the skin temperature includes skin temperatures of different parts of the human body; and / or the scenario factors include at least one of control behavior, time information, and place information; and / or the thermal comfort feedback information includes at least one of thermal sensation feedback information, comfort level feedback information, thermal preference, and satisfaction.

[0009] Optionally, the thermal comfort model is established based on the physiological parameters and the thermal comfort feedback information of different users with different user attributes under different environmental parameters and / or different scenario factors, including: arranging and combining data of each data item of the user attributes, the physiological parameters of the users, the scenario factors, and the environmental parameters as input parameters, taking the thermal comfort feedback information as output parameters, performing model training to obtain two or more models; performing model performance measurement on the obtained two or more models, and selecting a model with the best performance from the two or more models as the thermal comfort model.

[0010] Optionally, according to the output thermal comfort value of the current user, a preset control parameter determination rule is used to determine the current control parameter setting value of the air conditioner, including: based on the output thermal comfort value of the current user, according to the settable range of the control parameter of the air conditioner and / or the current control parameter setting value of the air conditioner, a preset control parameter determination rule is used to determine the current control parameter setting value of the air conditioner.

[0011] Another aspect of the present application provides a control device of an air conditioner, including: an acquisition unit configured to acquire a pre-established thermal comfort model of different users with different user attributes under different environmental parameters and / or different scenario factors; an output unit configured to determine a thermal comfort value of a current user based on the thermal comfort model acquired by the acquisition unit, and output the thermal comfort value of the current user; a determination unit configured to determine a current control parameter setting value of the air conditioner according to the thermal comfort value of the current user output by the output unit, according to a preset control parameter determination rule; and a control unit configured to control the air conditioner according to the current control parameter setting value of the air conditioner determined by the determination unit.

[0012] Optionally, the method further comprises: establishing, by an establishing unit, the thermal comfort model of the user with different user attributes under different environmental parameters and / or different scene factors by: collecting physiological parameter thermal comfort feedback information of the user with different user attributes under different environmental parameters and / or different scene factors; and establishing the thermal comfort model based on the collected physiological parameters and thermal comfort feedback information of the user with different user attributes under different environmental parameters and / or different scene factors.

[0013] Optionally, the control device further comprises: an establishing unit configured to establish the thermal comfort model of the user with different user attributes under different environmental parameters and / or different scene factors; the establishing unit comprises: a collecting sub-unit and an establishing sub-unit; the collecting sub-unit is configured to collect physiological parameter thermal comfort feedback information of the user with different user attributes under different environmental parameters and / or different scene factors; and the establishing sub-unit is configured to establish the thermal comfort model based on the physiological parameters and thermal comfort feedback information of the user with different user attributes under different environmental parameters and / or different scene factors collected by the collecting sub-unit.

[0014] Optionally, the collecting sub-unit collects physiological parameter thermal comfort feedback information of the user with different user attributes under different environments by: collecting physiological parameters of the user with different user attributes under different environmental parameters and / or different scene factors through a thermal comfort experiment, and collecting thermal comfort feedback information of the user with different user attributes under different environmental parameters and / or different scene factors.

[0015] Optionally, the different user attributes comprise at least one of gender, age, body shape and clothing thermal resistance; and / or the environmental parameters comprise at least one of air temperature, air humidity, mean radiant temperature, air flow rate and pollutant concentration; and / or the physiological parameters comprise at least one of skin temperature, heart rate, pulse and metabolic rate, wherein the skin temperature comprises skin temperatures of different parts of the human body; and / or the scene factors comprise at least one of control behavior, time information and place information; and / or the thermal comfort feedback information comprises at least one of thermal sensation feedback information, comfort level feedback information, thermal preference and satisfaction.

[0016] Optionally, the determining unit determines the current control parameter setting value of the air conditioner according to the output thermal comfort value of the current user and according to a preset control parameter determination rule, comprising: determining the current control parameter setting value of the air conditioner according to the output thermal comfort value of the current user, according to a settable range of the control parameter of the air conditioner and / or the current control parameter setting value of the air conditioner, and according to the preset control parameter determination rule.

[0017] Optionally, the establishing subunit establishes a thermal comfort model based on the physiological parameters and thermal comfort feedback information of users with different user attributes under different environmental parameters and / or different scene factors collected by the collecting subunit, including: arranging and combining data of each data item of the user attributes, the physiological parameters of the user, the scene factors and the environmental parameters as input parameters, taking the thermal comfort feedback information as an output parameter, performing model training to obtain two or more models; performing model performance measurement on the obtained two or more models, and selecting a model with the best performance from the two or more models as the thermal comfort model.

[0018] In still another aspect, the present application provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the preceding methods.

[0019] In still another aspect, the present application provides an air conditioner comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of any of the preceding methods when executing the program.

[0020] In still another aspect, the present application provides an air conditioner comprising the control device of any of the preceding.

[0021] According to the technical solution of the present application, air conditioner control can be adaptively performed based on individual difference comfort requirements and oriented by human comfort. According to the technical solution of the present application, a thermal comfort model of users with different user attributes under different environmental parameters and / or different scene factors is established in advance, so that the thermal comfort of the current user can be obtained by comprehensively considering the user attributes, environmental parameters and / or scene factors, the thermal comfort of the user is more accurately judged, and air conditioner control is performed. According to the technical solution of the present application, the control parameter set value of the air conditioner can be adjusted according to the thermal comfort of the current user obtained by the thermal comfort model, so that the indoor temperature is adaptively adjusted to meet the thermal comfort requirements of the current user. BRIEF DESCRIPTION OF DRAWINGS

[0022] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the present application and together with the description serve to explain the present application. In the drawings:

[0023] Figure 1 FIG. 1 is a method schematic diagram of an embodiment of the control method of the air conditioner provided by the present application;

[0024] Figure 2 FIG. 3 shows a training process of the thermal comfort model of users with different user attributes under different environments;

[0025] Figure 3An example of a thermal comfort experiment questionnaire is shown;

[0026] Figure 4 An example of thermal sensation corresponding to different TSV levels is shown;

[0027] Figure 5 An example of a model parameter combination is shown;

[0028] Figure 6 is a schematic diagram of air conditioning control logic according to a specific embodiment of the present invention;

[0029] Figure 7 This is a structural block diagram of an embodiment of the air conditioner control device provided by the present invention;

[0030] Figure 8 is a structural block diagram of an acquisition unit according to a specific embodiment of the present invention;

[0031] Figure 9 It is a schematic diagram of the temperature increase rate in the area where the human body feels thermally cooler and the temperature decrease rate in the area where the human body feels thermally warmer. DETAILED DESCRIPTION

[0032] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with specific embodiments of the present invention and corresponding drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0033] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] Figure 1 1 is a schematic diagram of an embodiment of the air conditioner control method provided by the present invention.

[0035] like Figure 1As shown, according to one embodiment of the present application, the control method comprises at least steps S110, S120 and S130.

[0036] In step S110, a pre-trained thermal comfort model of users with different user attributes under different environmental parameters and / or different scene factors is obtained.

[0037] The thermal comfort model of users with different user attributes under different environmental parameters is pre-trained by the following steps. Referring to Figure 2 As shown, Figure 2 The training process of the thermal comfort model of users with different user attributes under different environments is shown. As shown in Figure 2 As shown, training the thermal comfort model of users with different user attributes under different environmental parameters comprises steps S1 and S2.

[0038] In step S1, physiological parameter thermal comfort feedback information of users with different user attributes under different environmental parameters and / or different scene factors is collected.

[0039] User attributes may include at least one of gender, age, body type, and clothing thermal resistance. Body type may be, for example, a body mass index (BMI), which can be calculated based on height and weight according to a preset formula. Clothing thermal resistance may be determined based on the user's attire (e.g., clothes, pants, shoes). Selecting different environments may include at least one of seasonal, climatic, and geographically diverse environments. Different environments may be represented by environmental parameters, which may include at least one of air temperature, air humidity, mean radiant temperature, air velocity, and pollutant concentration. Optionally, the physiological parameters of different users may include at least one of skin temperature, heart rate, pulse, and metabolic rate. Skin temperature may include the temperature of different parts of the human body, such as the forehead, cheek, nose, mouth, and chin. Scenario factors may include, for example, at least one of control behavior, time information, and / or location information (e.g., including at least one of location, room size, ventilation conditions, and residential type), i.e., information related to the air conditioner usage scenario. Control behavior refers to control behavior of the air conditioner, such as temperature setting, wind speed, and timer. Adjusting the temperature too high or too low can cause discomfort, so avoid large temperature swings. Excessively high air speeds can make people feel too cold, while too low can make people feel stuffy. A timer can save energy while maintaining comfort. Time information, namely, the varying climates across seasons and time periods, can influence people's air conditioning needs accordingly. For example, during hot summer weather, a stronger cooling effect is needed to maintain comfort, while during cooler times like evenings and early mornings, appropriately adjusting the temperature and operating time can better meet people's needs. Location information, namely, geographic and climatic conditions, can influence air conditioning usage, especially in hot and humid regions. Furthermore, factors such as the size and ventilation of the space used during air conditioning can also affect comfort, requiring adjustments based on actual conditions. Residential type: The building's material, orientation, and interior design all have a certain impact on air conditioning effectiveness. For example, north-south facing homes can better utilize natural ventilation and avoid direct sunlight, while more enclosed and crowded apartments require greater attention to spatial layout and ventilation.

[0040] In some embodiments, thermal comfort experiments are conducted to collect physiological parameters of users with different user attributes under different environmental parameters and / or different scenario factors, and to collect thermal comfort feedback information from users with different user attributes under different environmental parameters and / or different scenario factors. For example, subjects of different genders, ages, and body types are selected, and different experimental environments (such as seasonal environments, climates, and geographical environments) and / or scenarios (at least one of control behavior, time information, and location information) are used.

[0041] Specifically, through thermal comfort experiments, the physiological parameters of the subjects, the environmental parameters in the experiment, the scene factors and the thermal comfort feedback of the subjects are collected to establish an individual difference thermal comfort sample library.

[0042] Preferably, the thermal comfort feedback information of the subject is collected at set intervals (a period of time) during the thermal comfort experiment. The thermal comfort feedback information can be pre-set to two or more levels, and the subject can choose according to his or her own feelings. The thermal comfort feedback information can specifically include thermal sensation feedback information, comfort level (thermal comfort) feedback information, thermal preference and / or satisfaction. Thermal comfort mainly reflects the comfort state of the human body in the current environment, for example, it can be reflected by the TSV (thermal sensation vote) indicator. Table 1 shows the data categories collected in the thermal comfort experiment and the data items contained in each data category.

[0043]

[0044]

[0045] Table 1

[0046] In a specific embodiment, the thermal comfort feedback information of users with different user attributes under different environmental parameters and / or different scene factors can be collected through a questionnaire. For example, an online questionnaire is designed to collect data, and the main content filled in the questionnaire includes the subject's personal information (attribute information, such as gender, age, height, weight, clothing) and the current subject's thermal comfort feedback information, such as thermal sensation feedback (such as thermal sensation voting TSV) and / or comfort level feedback. For example, refer to Figure 3 , Figure 3 An example of a thermal comfort experiment questionnaire is shown.

[0047] Thermal sensation feedback is, for example, thermal sensation voting (TSV). For example, a 7-level thermal sensation index is set to evaluate the hot and cold sensation of indoor occupants, with values ​​of -3, -2, -1, 0, 1, 2, and 3, representing very hot, very hot, slightly hot, comfortable, slightly cold, very cold, and very cold, respectively. Comfort feedback is, for example, a 4-level comfort index is set to evaluate the comfort of indoor occupants, with values ​​of 3, 2, 1, and 0, representing very uncomfortable, uncomfortable, slightly uncomfortable, and very comfortable, respectively. For example, reference Figure 4 , Figure 4 An example of thermal sensations corresponding to different TSV levels is shown. The subject can select the corresponding level based on their own feelings. For example, if the subject feels slightly cold, they can select TSV level -1.

[0048] Step S2: establishing a thermal comfort model based on the collected physiological parameters and thermal comfort feedback information of users with different user attributes under different environmental parameters and / or different scene factors.

[0049] Specifically, user attributes, physiological parameters, environmental parameters, and scenario factors are used as input parameters, and thermal comfort feedback information is used as output parameters for model training to obtain a thermal comfort model. Through experimental design and questionnaires, a large amount of thermal comfort data is obtained, allowing for targeted implementation. After statistical analysis of the experimental data, machine learning algorithms are used to train and model individual thermal comfort data. Optimization and analysis are performed on algorithm selection, algorithm parameters, and model input parameters to achieve a highly accurate individual thermal comfort model.

[0050] Preferably, the data of each data item of user attributes, user physiological parameters, scene factors and environmental parameters can be arranged and combined as input parameters, and the thermal comfort feedback information can be used as output parameters to perform model training to obtain two or more models; the model performance of the two or more models obtained is measured, and the model with the best performance among the two or more models is selected as the thermal comfort model.

[0051] For example, multiple parameters such as skin temperature, air temperature, and air humidity (mainly including physiological factors, environmental factors, and other factors) are randomly arranged and combined as input parameters, and TSV is used as output parameter. They are trained separately using the machine learning algorithm library in sklearn. After training, the performance of the models obtained by different data permutations and combinations is measured, and the best thermal comfort model is selected. For details on the permutations and combinations of data of different data types, please refer to Figure 5 As shown, Figure 5 Examples of model parameter combinations are shown.

[0052] Preferably, the data is preprocessed before data training. Specifically, preprocessing the data may include: deleting data points with missing input parameters, and / or deleting abnormal temperature data points (for example, deleting abnormal temperature data points in the data due to experiments or human errors, such as abnormal temperatures caused by abnormal non-human heat sources, clothing coverings, etc., which are usually not within the normal temperature range of the human body and are identified as abnormal temperature data points), and / or normalizing the data (for example, since some algorithms require samples to have zero mean and unit variance, it is necessary to eliminate the influence of different user attributes of the samples having different magnitudes, so the data can be normalized, that is, the maximum value is set to 1, the minimum value is set to 0, and other values ​​are distributed therein, that is, between 0 and 1).

[0053] The formula is as follows:

[0054]

[0055] Among them, x new is the new data value (i.e., the data value after normalization), x old is the old data value (i.e., the original data value), x min is the minimum value in the data, x max is the maximum value in the data.

[0056] In terms of model performance measurement, accuracy (acc) and root mean square error (RMSE) are used as measures of model quality. The formulas are as follows:

[0057] acc=n i / m i

[0058] Among them, ni is the number of correctly classified data in the i-th category, and mi is the number of all data in the i-th category.

[0059]

[0060] Among them, pi is the predicted result of the case, and ai is the correct result of the case.

[0061] Step S120 : determining a thermal comfort value of the current user based on the acquired thermal comfort model, and outputting the thermal comfort value of the current user.

[0062] After the optimal individual thermal comfort model is trained in step S110, the thermal comfort value of the current user can be output based on the obtained thermal comfort model. Specifically, the user's attribute information, physiological parameters, environmental parameters of the current environment, and / or scene factors are input into the thermal comfort model to output the user's thermal comfort value.

[0063] The attribute information of the current user can be acquired in advance, for example, it can be pre-entered and stored. The current user is identified through facial recognition and the corresponding attribute information is acquired. The physiological parameters of the current user can be detected by a temperature detection device and sensor, such as detecting the user's skin temperature through a temperature detection device. For example, an infrared sensor detects the temperature of each pixel in the image pixel by pixel, and a face detection model is used to identify the face area. The face area is detected and the pixel range is framed. The average temperature or maximum temperature of the face area can be calculated based on the pixel temperature and used as the face skin temperature. For example, a millimeter-wave radar can be used to detect the user's heart rate, pulse, respiration, and metabolic rate.

[0064] The environmental parameters of the current environment can be detected by sensors, such as detecting the indoor temperature (air temperature) by a temperature sensor, detecting the indoor humidity (air humidity) by a humidity sensor, and the average radiant temperature, air flow rate and / or pollutant concentration can be obtained through a weather server.

[0065] Step S130, according to the output thermal comfort value of the current user, according to the preset control parameter determination rule, determine the current control parameter setting value of the air conditioner, and control the air conditioner according to the determined current control parameter setting value of the air conditioner.

[0066] Specifically, based on the output thermal comfort value of the current user, the current control parameter setting value of the air conditioner is determined according to the settable range of the control parameter of the air conditioner and / or the current control parameter setting value of the air conditioner, according to a preset control parameter determination rule. The control parameter may, for example, include at least one of a set temperature, humidity, and wind speed. For example, the set values ​​of corresponding environmental parameters (temperature, humidity, wind speed, etc.) are adjusted based on the TSV value output by the thermal comfort model. In the individual thermal comfort model, the TSV value output by the model changes with the thermal sensation state of the human body, and the output of the environmental parameter set point is achieved using a temperature set point algorithm.

[0067] More specifically, based on the current user's thermal comfort value, the current control parameter setting value of the air conditioner is determined according to a settable range of the control parameter of the air conditioner (e.g., an upper limit and a lower limit of the set temperature), a last adjusted control parameter setting value (the current control parameter setting value of the air conditioner), and / or a preset thermal sensation adjustment parameter (specifically, a temperature increase rate in an area where the human body thermally feels cooler and / or a temperature decrease rate in an area where the human body thermally feels warmer). The control parameter may include, for example, a set temperature.

[0068] For example, with respect to the set temperature, when the thermal comfort value of the current user is less than a first threshold value, the current set temperature of the air conditioner is determined to be the upper limit value of the settable range of the set temperature; when the thermal comfort value of the current user is greater than or equal to the first threshold value and less than a second threshold value, the current set temperature of the air conditioner is determined based on the last adjusted control parameter setting value, the temperature increase rate in the area where the human body feels relatively cold, and the thermal comfort value of the current user; when the thermal comfort value of the current user is greater than or equal to the second threshold value and less than a third threshold value, the current set temperature of the air conditioner is determined to be equal to the last adjusted control parameter setting value; when the thermal comfort value of the current user is greater than or equal to the third threshold value and less than a fourth threshold value, the current set temperature of the air conditioner is determined based on the last adjusted control parameter setting value, the temperature decrease rate in the area where the human body feels relatively hot, and the thermal comfort value of the current user; when the thermal comfort value of the current user is greater than the fourth threshold value, the current set temperature of the air conditioner is determined to be the lower limit value of the settable range.

[0069] For example, taking TSV voting as an example, the following formula can be used to determine the current control parameter setting value of the air conditioner:

[0070]

[0071] Among them, Tst is the temperature set point (set temperature) calculated after the thermal comfort value is obtained by the thermal comfort model this time, Tst0 is the temperature set point (set temperature) calculated after the thermal comfort value is obtained by the thermal comfort model last time, Tstmax is the preset upper limit of the indoor set temperature, Tstmin is the preset lower limit of the indoor set temperature, TSV is the thermal sensation state fed back by the thermal comfort model this time, that is, the thermal comfort value obtained by the thermal comfort model, Ksti represents the preset area where the human body feels colder (thermal comfort value interval, for example, TSV∈[ The temperature rise rate in the area of ​​-2.5, -0.5) is equal to the slope of the coordinate system with thermal comfort as the horizontal axis and set temperature as the vertical axis, from the point determined by the upper limit value of the set temperature (Tstmax) and the minimum value of thermal comfort in the area (for example, -2.5 in the area of ​​TSV∈[-2.5,-0.5) in the above formula) to the point determined by the previous set temperature value (Tst0) (calculated after the thermal comfort value is obtained by the thermal comfort model) and the maximum value of thermal comfort in the area (for example, -0.5 in the area of ​​TSV∈[-2.5,-0.5) in the above formula). Figure 9 shown.

[0072] Kstd represents the temperature reduction rate in the preset area where the human body feels hotter (thermal comfort value interval, for example, the area of ​​TSV∈[0.5,2.5) in the above formula is the area where the human body feels hotter), which is equal to the slope of the coordinate system with thermal comfort as the horizontal axis and set temperature as the vertical axis, from the point determined by the last set temperature value (Tst0) (calculated after the thermal comfort value is obtained through the thermal comfort model) and the minimum value of the thermal comfort of the area (for example, 0.5 for the area of ​​TSV∈[0.5,2.5) in the above formula) to the point determined by the lower limit value of the set temperature (Tstmin) and the maximum value of the thermal comfort of the area (for example, 2.5 for the area of ​​TSV∈[0.5,2.5) in the above formula). You can refer to Figure 9 shown.

[0073] In the above formula, when the TSV value is in the range of -0.5 to 0.5, it is considered that the indoor occupants feel comfortable at this time, and there is no need to adjust the temperature set point. The temperature set point adjusted last can be maintained.

[0074] By identifying the current user's facial temperature, the air conditioning system controls the airflow direction based on that temperature. For example, using an infrared image captured by an infrared camera, the 2D image is mapped into 3D space. Using a distortion correction method based on camera lens distortion, the distance and orientation of the person in 3D space are output. A facial detection model is combined with the image pixel temperature to calculate the current user's facial temperature. This, combined with other parameters, is input into a thermal comfort model to output a thermal comfort level, which is then used to adjust the temperature setpoint. The user's orientation can also be determined based on the camera's position, allowing for accurate positioning. Based on the user's thermal comfort level, rapid or slow cooling can be selected, enabling control strategies such as wind following or avoiding the person, or varying wind speed. This allows for a rapid and effective return to zero of the optimal comfort TSV that deviates too far from zero. Humidity is used as a supplementary control measure for temperature and wind speed, selecting the appropriate humidity for the corresponding temperature and wind speed.

[0075] Figure 6 FIG. 1 is a schematic diagram of the air conditioning control logic of a specific embodiment of the present invention. Figure 6 As shown, first, the air conditioning system detects indoor air parameters and accurately detects facial skin temperature through sensors (such as infrared sensors) in conjunction with a face detection model. The various detected parameters (such as the user's physiological parameters and environmental parameters) are input into the comfort model for analysis and decision-making, and the current user's thermal comfort value (such as the TSV value) is output. Based on the thermal comfort value and the temperature set point algorithm, the temperature is set and controlled by the air conditioning main control module.

[0076] The invention also provides a control device for an air conditioner.

[0077] Figure 7 FIG. 1 is a structural block diagram of an embodiment of the air conditioner control device provided by the present invention. Figure 7 As shown, the control device 100 includes: an acquisition unit 110 , an output unit 120 , a determination unit 130 and a control unit 140 .

[0078] The acquisition unit 110 is used to obtain pre-established thermal comfort models of users with different user attributes under different environmental parameters and / or different scenario factors. The output unit 120 is used to determine the thermal comfort value of the current user based on the thermal comfort model obtained by the acquisition unit 110, and output the thermal comfort value of the current user. The determination unit 130 is used to determine the current control parameter setting value of the air conditioner according to the thermal comfort value of the current user output by the output unit 120 and a preset control parameter determination rule. The control unit 140 is used to control the air conditioner according to the current control parameter setting value of the air conditioner determined by the determination unit 130.

[0079] The acquisition unit 110 is configured to acquire pre-established thermal comfort models of users with different user attributes under different environmental parameters and / or different scenario factors.

[0080] The thermal comfort models of users with different user attributes under different environmental parameters are pre-trained by the following steps. The control device 100 may further include: an establishment unit 101 for establishing thermal comfort models of users with different user attributes under different environmental parameters and / or different scene factors. The establishment unit 101 includes: a collection subunit 1011 and an establishment subunit 1012; Figure 8 As shown, Figure 8 is a structural block diagram of an acquisition unit according to a specific embodiment of the present invention.

[0081] The collecting subunit 1011 is used to collect thermal comfort feedback information of physiological parameters of users with different user attributes under different environmental parameters and / or different scene factors.

[0082] The user attributes may include at least one of gender, age, body type, and clothing thermal resistance. Body type may be, for example, a body mass index (BMI), which can be calculated based on height and weight according to a preset formula. Clothing thermal resistance may be determined based on the user's clothing (e.g., clothes, pants, shoes). The selection of different environments may include at least one of seasonal, climatic, and geographically diverse environments. Different environments may be represented by environmental parameters, which may include at least one of air temperature, air humidity, mean radiant temperature, air velocity, and pollutant concentration. Optionally, the physiological parameters of different users may include at least one of skin temperature, heart rate, pulse, and metabolic rate. Skin temperature may include the temperature of different parts of the human body, such as the forehead, cheek, nose, mouth, and chin. Scenario factors may include, for example, at least one of control behavior, time information, and / or location information (e.g., including at least one of location, room size, ventilation conditions, and residential type), i.e., information related to the air conditioner usage scenario. Control behavior refers to control behavior of the air conditioner, such as temperature setting, wind speed, and timer. Adjusting the temperature too high or too low can cause discomfort, so avoid large temperature swings. Excessively high air speeds can make people feel too cold, while too low can make people feel stuffy. A timer can save energy while maintaining comfort. Time information, namely, the varying climates across seasons and time periods, can influence people's air conditioning needs accordingly. For example, during hot summer weather, a stronger cooling effect is needed to maintain comfort, while during cooler times like evenings and early mornings, appropriately adjusting the temperature and operating time can better meet people's needs. Location information, namely, geographic and climatic conditions, can influence air conditioning usage, especially in hot and humid regions. Furthermore, factors such as the size and ventilation of the space used during air conditioning can also affect comfort, requiring adjustments based on actual conditions. Residential type: The building's material, orientation, and interior design all have a certain impact on air conditioning effectiveness. For example, north-south facing homes can better utilize natural ventilation and avoid direct sunlight, while more enclosed and crowded apartments require greater attention to spatial layout and ventilation.

[0083] In some specific embodiments, the establishment subunit 1012 is used to establish a thermal comfort model based on the physiological parameters and thermal comfort feedback information of users with different user attributes under different environmental parameters and / or different scene factors collected by the collection subunit 1011. For example, subjects of different genders, ages, and body types are selected, and different test environments (seasonal environments, climates, geographical environments, etc.) and / or scenes (at least one of control behavior, time information, and location information) are replaced. Specifically, through thermal comfort experiments, the physiological parameters of the subjects, the environmental parameters in the experiment, the scene factors, and the thermal comfort feedback of the subjects are collected to establish an individual difference thermal comfort sample library.

[0084] Preferably, the thermal comfort feedback information of the subject is collected at set intervals (a period of time) during the thermal comfort experiment. The thermal comfort feedback information can be pre-set to two or more levels, and the subject can choose according to his or her own feelings. The thermal comfort feedback information can specifically include thermal sensation feedback information, comfort level (thermal comfort) feedback information, thermal preference and / or satisfaction. Thermal comfort mainly reflects the comfort state of the human body in the current environment, for example, it can be reflected by the TSV (thermal sensation vote) indicator. Table 1 shows the data categories collected in the thermal comfort experiment and the data items contained in each data category.

[0085]

[0086] Table 1

[0087] In a specific embodiment, the thermal comfort feedback information of users with different user attributes under different environmental parameters and / or different scene factors can be collected through a questionnaire. For example, an online questionnaire is designed to collect data, and the main content filled in the questionnaire includes the subject's personal information (attribute information, such as gender, age, height, weight, clothing) and the current subject's thermal comfort feedback information, such as thermal sensation feedback (such as thermal sensation voting TSV) and / or comfort level feedback. For example, refer to Figure 3 , Figure 3 An example of a thermal comfort experiment questionnaire is shown.

[0088] Thermal sensation feedback is, for example, thermal sensation voting (TSV). For example, a 7-level thermal sensation index is set to evaluate the hot and cold sensation of indoor occupants, with values ​​of -3, -2, -1, 0, 1, 2, and 3, representing very hot, very hot, slightly hot, comfortable, slightly cold, very cold, and very cold, respectively. Comfort feedback is, for example, a 4-level comfort index is set to evaluate the comfort of indoor occupants, with values ​​of 3, 2, 1, and 0, representing very uncomfortable, uncomfortable, slightly uncomfortable, and very comfortable, respectively. For example, reference Figure 4 , Figure 4An example of thermal sensations corresponding to different TSV levels is shown. The subject can select the corresponding level based on their own feelings. For example, if the subject feels slightly cold, they can select TSV level -1.

[0089] The establishing subunit 1012 is used to establish a thermal comfort model based on the physiological parameters and thermal comfort feedback information of users with different user attributes under different environmental parameters and / or different scene factors collected by the collecting subunit 1011.

[0090] Specifically, user attributes, physiological parameters, environmental parameters, and scenario factors are used as input parameters, and thermal comfort feedback information is used as output parameters for model training to obtain a thermal comfort model. Through experimental design and questionnaires, a large amount of thermal comfort data is obtained, allowing for targeted implementation. After statistical analysis of the experimental data, machine learning algorithms are used to train and model individual thermal comfort data. Optimization and analysis are performed on algorithm selection, algorithm parameters, and model input parameters to achieve a highly accurate individual thermal comfort model.

[0091] Preferably, the data of each data item of user attributes, user physiological parameters, scene factors and environmental parameters can be arranged and combined as input parameters, and the thermal comfort feedback information can be used as output parameters to perform model training to obtain two or more models; the model performance of the two or more models obtained is measured, and the model with the best performance among the two or more models is selected as the thermal comfort model.

[0092] For example, multiple parameters such as skin temperature, air temperature, and air humidity (mainly including physiological factors, environmental factors, and other factors) are randomly arranged and combined as input parameters, and TSV is used as output parameter. They are trained separately using the machine learning algorithm library in sklearn. After training, the performance of the models obtained by different data permutations and combinations is measured, and the best thermal comfort model is selected. For details on the permutations and combinations of data of different data types, please refer to Figure 5 As shown, Figure 5 An example of model parameter combination is shown. Individual parameters are user attributes.

[0093] Preferably, the data is preprocessed before data training. Specifically, preprocessing the data may include: deleting data points with missing input parameters, and / or deleting abnormal temperature data points (for example, deleting abnormal temperature data points in the data due to experiments or human errors, such as abnormal temperatures caused by abnormal non-human heat sources, clothing coverings, etc., which are usually not within the normal temperature range of the human body and are identified as abnormal temperature data points), and / or normalizing the data (for example, since some algorithms require samples to have zero mean and unit variance, it is necessary to eliminate the influence of different user attributes of the samples having different magnitudes, so the data can be normalized, that is, the maximum value is set to 1, the minimum value is set to 0, and other values ​​are distributed therein, that is, between 0 and 1).

[0094] The formula is as follows:

[0095]

[0096] Among them, x new is the new data value (i.e., the data value after normalization), x old is the old data value (i.e., the original data value), x min is the minimum value in the data, x max is the maximum value in the data.

[0097] In terms of model performance measurement, accuracy (acc) and root mean square error (RMSE) are used as measures of model quality. The formulas are as follows:

[0098] acc=n i / m i

[0099] Among them, ni is the number of correctly classified data in the i-th category, and mi is the number of all data in the i-th category.

[0100]

[0101] Among them, pi is the predicted result of the case, and ai is the correct result of the case.

[0102] The output unit 120 is configured to determine a thermal comfort value of a current user based on the thermal comfort model acquired by the acquisition unit 110 , and output the thermal comfort value of the current user.

[0103] After the establishment unit 110 has trained and obtained the optimal individual thermal comfort model, it can output the thermal comfort value of the current user based on the obtained thermal comfort model. Specifically, the thermal comfort model inputs the current user's attribute information, physiological parameters, environmental parameters of the current environment, and / or scene factors to output the thermal comfort value of the current user.

[0104] The attribute information of the current user can be acquired in advance, for example, it can be pre-entered and stored. The current user is identified through facial recognition and the corresponding attribute information is acquired. The physiological parameters of the current user can be detected by a temperature detection device and sensor, such as detecting the user's skin temperature through a temperature detection device. For example, an infrared sensor detects the temperature of each pixel in the image pixel by pixel, and a face detection model is used to identify the face area. The face area is detected and the pixel range is framed. The average temperature or maximum temperature of the face area can be calculated based on the pixel temperature and used as the face skin temperature. For example, a millimeter-wave radar can be used to detect the user's heart rate, pulse, respiration, and metabolic rate.

[0105] The environmental parameters of the current environment can be detected by sensors, such as detecting the indoor temperature (air temperature) by a temperature sensor, detecting the indoor humidity (air humidity) by a humidity sensor, and the average radiant temperature, air flow rate and / or pollutant concentration can be obtained through a weather server.

[0106] The determination unit 130 determines the current control parameter setting value of the air conditioner according to the thermal comfort value of the current user output by the output unit 120 and a preset control parameter determination rule.

[0107] Specifically, based on the output thermal comfort value of the current user, according to the settable range of the control parameters of the air conditioner and / or the current control parameter setting value of the air conditioner, the current control parameter setting value of the air conditioner is determined according to the preset control parameter determination rules.

[0108] The control parameters may include, for example, at least one of set temperature, humidity, and wind speed. For example, the set values ​​of corresponding environmental parameters (such as temperature, humidity, and wind speed) are adjusted based on the TSV value output by the thermal comfort model. In an individual thermal comfort model, the TSV value output by the model changes with the body's thermal sensation state, and a temperature setpoint algorithm is used to output the environmental parameter setpoint.

[0109] More specifically, based on the current user's thermal comfort value, the current control parameter setting value of the air conditioner is determined according to a settable range of the control parameter of the air conditioner (e.g., an upper limit and a lower limit of the set temperature), a last adjusted control parameter setting value (the current control parameter setting value of the air conditioner), and / or a preset thermal sensation adjustment parameter (specifically, a temperature increase rate in an area where the human body thermally feels cooler and / or a temperature decrease rate in an area where the human body thermally feels warmer). The control parameter may include, for example, a set temperature.

[0110] For example, for a set temperature, when the current user's thermal comfort value is less than a first threshold value, it is determined that the current set temperature of the air conditioner is an upper limit value of a set temperature range, when the current user's thermal comfort value is greater than or equal to the first threshold value and less than a second threshold value, the current set temperature of the air conditioner is determined according to the last adjusted control parameter set value, a temperature increase rate in a region where the human body feels cold, and the current user's thermal comfort value; when the current user's thermal comfort value is greater than or equal to the second threshold value and less than a third threshold value, it is determined that the current set temperature of the air conditioner is equal to the last adjusted control parameter set value, when the current user's thermal comfort value is greater than or equal to the third threshold value and less than a fourth threshold value, the current set temperature of the air conditioner is determined according to the last adjusted control parameter set value, a temperature decrease rate in a region where the human body feels hot, and the current user's thermal comfort value, and when the current user's thermal comfort value is greater than the fourth threshold value, it is determined that the current set temperature of the air conditioner is a lower limit value of the set temperature range.

[0111] For example, for TSV voting, the current control parameter set value of the air conditioner can be determined by the following formula:

[0112]

[0113] wherein Tst is a temperature set point (set temperature) calculated after obtaining the thermal comfort value by the thermal comfort model this time, Tst0 is a temperature set point (set temperature) calculated after obtaining the thermal comfort value by the thermal comfort model last time, Tstmax is a preset upper limit value of the indoor set temperature, Tstmin is a preset lower limit value of the indoor set temperature, TSV is the thermal sensation state fed back by the thermal comfort model this time, i.e. the thermal comfort value obtained by the thermal comfort model. Ksti represents a temperature increase rate in a region where the human body feels cold (thermal comfort value interval, for example, the region of TSV∈[-2.5, -0.5) in the above formula), which is equal to the slope of the line determined by the upper limit value of the set temperature (Tstmax) and the minimum value of the thermal comfort in the region (for example, -2.5 in the region of TSV∈[-2.5, -0.5) in the above formula) and the point determined by the last set temperature value (Tst0) obtained after obtaining the thermal comfort value by the thermal comfort model and the maximum value of the thermal comfort in the region (for example, -0.5 in the region of TSV∈[-2.5, -0.5) in the above formula) in the coordinate system with thermal comfort as the horizontal axis and set temperature as the vertical axis. Please refer to the following figure for details. Figure 9 Figure 9 is a schematic diagram of the temperature increase rate in the region where the human body feels cold and the temperature decrease rate in the region where the human body feels hot.

[0114] ​Kstd represents the temperature reduction rate in the region where the human body feels hot (the region of the thermal comfort value interval, for example, the region where TSV∈[0.5, 2.5) in the above formula is the region where the human body feels hot), which is equal to the slope of the line from the point determined by the last set temperature value (Tst0) and the minimum value of the thermal comfort degree of the region (for example, 0.5 in the region where TSV∈[0.5, 2.5) in the above formula) to the point determined by the lower limit value of the set temperature (Tstmin) and the maximum value of the thermal comfort degree of the region (for example, 2.5 in the region where TSV∈[0.5, 2.5) in the above formula) in the coordinate system with the thermal comfort degree as the horizontal axis and the set temperature as the vertical axis. For reference Figure 9 Figure 9 is a schematic diagram of the temperature increase rate set in the region where the human body feels cold and the temperature reduction rate in the region where the human body feels hot.

[0115] In the above formula, when the TSV value is in the interval of-0.5 to 0.5, it is considered that the indoor personnel feel comfortable at this time, and the temperature set point does not need to be adjusted, and the last adjusted temperature set point can be maintained.

[0116] By identifying the face temperature of the current user, the air supply direction of the air conditioner is controlled according to the face temperature. For example, an infrared image is captured by an infrared camera, a two-dimensional image is mapped to a three-dimensional space, a distortion correction method depending on the lens distortion of the camera is used to output the distance and orientation of the person in the three-dimensional space, and the face temperature of the current user is calculated by a face detection model and image pixel temperature, and other parameters are input into a thermal comfort model to output a thermal comfort degree, and the temperature set point is adjusted according to the output thermal comfort degree. The orientation of the human body can also be determined according to the position of the camera photo, so as to determine the position of the human body, select fast cooling or slow cooling according to the thermal comfort degree of the human body, and thus implement the control mode of wind following the human body or wind avoiding the human body, changing the wind speed, etc., so that the TSV deviating too much from the optimal comfort value of 0 is quickly and effectively returned to 0. Humidity is used as an auxiliary control measure for temperature and wind speed, and under the corresponding temperature and wind speed, the appropriate humidity is selected.

[0117] The application also provides a storage medium corresponding to the control method of the air conditioner, which stores a computer program, and the program is executed by a processor to realize the steps of any of the above-mentioned methods.

[0118] The application also provides an air conditioner corresponding to the control method of the air conditioner, which comprises a processor, a memory, and a computer program stored on the memory and executable on the processor, and the processor executes the program to realize the steps of any of the above-mentioned methods.

[0119] ​The present invention also provides an air conditioner corresponding to the control device of the air conditioner, comprising any of the aforementioned control devices of the air conditioner.

[0120] Existing comfort models are difficult to universally apply to all populations, environments, and climates. For example, they fail to account for individual differences in comfort requirements. Users with different user attributes (age, gender, and / or health status) in the same environment, or users with the same user attributes in different environments, may experience significant differences in comfort. Furthermore, human comfort is influenced by numerous environmental factors, such as temperature, humidity, air quality, and airflow velocity. The combined effects of these environmental parameters can produce complex effects, making the models difficult to adapt to all situations.

[0121] The solution provided by the present invention pre-establishes thermal comfort models for users with different user attributes under different environmental parameters and / or different scenario factors. This allows the thermal comfort of the current user to be determined by integrating the user attributes, environmental parameters, and / or scenario factors, enabling a more accurate assessment of the user's thermal comfort and thus enabling air conditioning control. The present invention also adjusts the control parameter settings of the air conditioner based on the current user's thermal comfort level determined by the thermal comfort model, thereby adaptively adjusting the indoor temperature to meet the current user's thermal comfort requirements.

[0122] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and implementations are within the scope and spirit of the present invention and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwiring, or a combination of any of these. Furthermore, each functional unit may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit.

[0123] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0124] The units described as separate components may or may not be physically separate, and the components of the control device may or may not be physical units, i.e., may be located in one place or may be distributed to multiple units. Part or all of the units can be selected as needed to achieve the purpose of the embodiment.

[0125] The integrated units, if implemented in the form of software functional units and sold or used as independent products, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the part that contributes to the related art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0126] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the scope of the claims of the present application.

Claims

1. A method for controlling an air conditioner, characterized in that: include: Obtaining pre-established thermal comfort models of users with different user attributes under different environmental parameters and / or different scenario factors; Determining a thermal comfort value of a current user based on the acquired thermal comfort model, and outputting the thermal comfort value of the current user; Determining a current control parameter setting value of the air conditioner according to the output thermal comfort value of the current user and a preset control parameter determination rule, so as to control the air conditioner according to the determined current control parameter setting value of the air conditioner; The control parameter setting value is a set temperature, and the preset control parameter determination rule includes: When the thermal comfort value of the current user is less than a first threshold, determining the current set temperature of the air conditioner as the upper limit of the set temperature range; when the thermal comfort value of the current user is greater than or equal to the first threshold and less than a second threshold, determining the current set temperature of the air conditioner based on the last adjusted control parameter setting value, the temperature increase rate in the area where the human body feels colder thermally, and the thermal comfort value of the current user; When the thermal comfort value of the current user is greater than or equal to the second threshold and less than the third threshold, it is determined that the current set temperature of the air conditioner is equal to the control parameter setting value adjusted last time; when the thermal comfort value of the current user is greater than or equal to the third threshold and less than the fourth threshold, the current set temperature of the air conditioner is determined based on the control parameter setting value adjusted last time, the temperature reduction rate in the area where the human body feels hotter, and the thermal comfort value of the current user; when the thermal comfort value of the current user is greater than the fourth threshold, it is determined that the current set temperature of the air conditioner is the lower limit of the settable range.

2. The control method according to claim 1, characterized in that: The thermal comfort models of users with different user attributes under different environmental parameters and / or different scenario factors are established by the following steps: Collect thermal comfort feedback information of physiological parameters of users with different user attributes under different environmental parameters and / or different scene factors; A thermal comfort model is established based on the collected physiological parameters and thermal comfort feedback information of users with different user attributes under different environmental parameters and / or different scenario factors.

3. The control method according to claim 2, characterized in that: Collect physiological parameters and thermal comfort feedback information of users with different user attributes under different environmental parameters, including: Through thermal comfort experiments, physiological parameters of users with different user attributes under different environmental parameters and / or different scenario factors are collected, and thermal comfort feedback information of users with different user attributes under different environmental parameters and / or different scenario factors is collected.

4. The control method according to claim 2 or 3, characterized in that: The user attributes include: at least one of gender, age, body type and clothing thermal resistance; and / or, The environmental parameters include: at least one of air temperature, air humidity, mean radiant temperature, air velocity and pollutant concentration; and / or, The physiological parameters include: at least one of skin temperature, heart rate, pulse and metabolic rate, wherein the skin temperature includes the skin temperature of different parts of the human body; and / or, The scenario factors include: at least one of control behavior, time information and location information; and / or, The thermal comfort feedback information includes at least one of thermal sensation feedback information, comfort level feedback information, thermal preference, and satisfaction level.

5. The control method according to claim 2 or 3, characterized in that: Based on the collected physiological parameters and thermal comfort feedback information of users with different user attributes under different environmental parameters and / or different scene factors, a thermal comfort model is established, including: Arrange and combine data items of user attributes, user physiological parameters, scene factors, and environmental parameters as input parameters, and use the thermal comfort feedback information as output parameters to perform model training to obtain two or more models; The obtained two or more models are subjected to model performance measurement, and the model with the best performance among the two or more models is selected as the thermal comfort model.

6. A control device for an air conditioner, characterized in that: include: An acquisition unit, configured to acquire pre-established thermal comfort models of users with different user attributes under different environmental parameters and / or different scenario factors; an output unit, configured to determine a thermal comfort value of a current user based on the thermal comfort model acquired by the acquisition unit, and output the thermal comfort value of the current user; a determination unit, configured to determine a current control parameter setting value of the air conditioner according to the thermal comfort value of the current user output by the output unit and a preset control parameter determination rule; a control unit, configured to control the air conditioner according to a current control parameter setting value of the air conditioner determined by the determination unit; The control parameter setting value is a set temperature, and the preset control parameter determination rule includes: When the thermal comfort value of the current user is less than a first threshold, determining the current set temperature of the air conditioner as the upper limit of the set temperature range; when the thermal comfort value of the current user is greater than or equal to the first threshold and less than a second threshold, determining the current set temperature of the air conditioner based on the last adjusted control parameter setting value, the temperature increase rate in the area where the human body feels colder thermally, and the thermal comfort value of the current user; When the thermal comfort value of the current user is greater than or equal to the second threshold and less than the third threshold, it is determined that the current set temperature of the air conditioner is equal to the control parameter setting value adjusted last time; when the thermal comfort value of the current user is greater than or equal to the third threshold and less than the fourth threshold, the current set temperature of the air conditioner is determined based on the control parameter setting value adjusted last time, the temperature reduction rate in the area where the human body feels hotter, and the thermal comfort value of the current user; when the thermal comfort value of the current user is greater than the fourth threshold, it is determined that the current set temperature of the air conditioner is the lower limit of the settable range.

7. The control device according to claim 6, characterized in that The invention also includes: an establishing unit for establishing thermal comfort models of users with different user attributes under different environmental parameters and / or different scene factors; the establishing unit includes: a collecting subunit and an establishing subunit; The collecting subunit is used to collect thermal comfort feedback information of physiological parameters of users with different user attributes under different environmental parameters and / or different scene factors; The establishing subunit is used to establish a thermal comfort model based on the physiological parameters and thermal comfort feedback information of users with different user attributes under different environmental parameters and / or different scene factors collected by the collecting subunit; 8. The control device according to claim 7, characterized in that: The collecting subunit collects physiological parameters and thermal comfort feedback information of users with different user attributes under different environmental parameters, including: Through thermal comfort experiments, physiological parameters of users with different user attributes under different environmental parameters and / or different scenario factors are collected, and thermal comfort feedback information of users with different user attributes under different environmental parameters and / or different scenario factors is collected.

9. The control device according to claim 7 or 8, characterized in that: The user attributes include: at least one of gender, age, body type and clothing thermal resistance; and / or, The environmental parameters include: at least one of air temperature, air humidity, mean radiant temperature, air velocity and pollutant concentration; and / or, The physiological parameters include: at least one of skin temperature, heart rate, pulse and metabolic rate, wherein the skin temperature includes the skin temperature of different parts of the human body; and / or, The scenario factors include: at least one of control behavior, time information and location information; and / or, The thermal comfort feedback information includes at least one of thermal sensation feedback information, comfort level feedback information, thermal preference, and satisfaction level.

10. The control device according to claim 7 or 8, characterized in that: The establishing subunit establishes a thermal comfort model based on the physiological parameters and thermal comfort feedback information of users with different user attributes under different environmental parameters and / or different scenario factors collected by the collecting subunit, including: Arrange and combine data items of user attributes, user physiological parameters, scene factors, and environmental parameters as input parameters, and use the thermal comfort feedback information as output parameters to perform model training to obtain two or more models; The obtained two or more models are subjected to model performance measurement, and the model with the best performance among the two or more models is selected as the thermal comfort model.

11. A storage medium, characterized in that: A computer program is stored thereon, and when the program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

12. An air conditioner, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 5 when executing the program, or comprises a control device according to any one of claims 6 to 10.

Images