Training method, device and equipment of air conditioner control model and storage medium

Abstract

The embodiment of the invention provides an air conditioner control model training method and device, equipment and a storage medium. The method comprises the steps that multiple sets of in-vehicle environment data collected by a PMV measuring device, clothes thermal resistance and human body metabolic rates corresponding to the sets of environment data and actual air conditioner operation parameters corresponding to the sets of environment data are obtained; training data are generated based on the multiple sets of in-vehicle environment data, the clothes thermal resistance and the human body metabolic rate corresponding to each set of environment data and the actual air conditioner operation parameters corresponding to each set of environment data; training data is adopted to train the initial prediction model, the air conditioner control model is obtained, the air conditioner control model is used for adjusting operation parameters of the vehicle-mounted air conditioner, in the model training process, the current in-vehicle environment is considered, multiple input variables such as the metabolism condition and the wearing condition of the user are also considered, and the air conditioner control model is obtained; intelligent adjustment is carried out through the air conditioner control model, a more comfortable in-vehicle environment is provided, and the requirements of different users are met.

Description

Technical Field

[0001] The present application relates to the field of air conditioning technology, and in particular to a training method, device, equipment and storage medium for an air conditioning control model. Background Art

[0002] In recent years, the automotive industry has developed rapidly. Vehicle air conditioning is an indispensable device for improving riding comfort, and it plays a major role in creating a thermal environment inside the vehicle. In order to improve the comfort of riding in the vehicle, when using the vehicle air conditioning, it is usually necessary to set a suitable temperature to provide users with a comfortable riding environment.

[0003] Currently, the temperature of a vehicle's air conditioner is usually set by the user according to his or her own needs, or the vehicle control system adjusts the air conditioner temperature according to the detected temperature inside the vehicle, thereby achieving automatic control.

[0004] However, when the vehicle air conditioning temperature is set in the above manner, the user needs to manually adjust the temperature to a comfortable level for the user each time the vehicle is used. Although automatic adjustment does not require manual operation by the user, the adjusted temperature may not necessarily meet the user's needs. Summary of the invention

[0005] The embodiments of the present application provide a training method, device, equipment and storage medium for an air-conditioning control model, which are used to solve the problem that the air-conditioning adjustment method in a car cannot meet the needs of users.

[0006] In a first aspect, an embodiment of the present application provides a training method for an air conditioning control model, comprising:

[0007] Acquire multiple groups of in-vehicle environment data collected by a PMV measurement device, clothing thermal resistance corresponding to each group of environment data, human metabolic rate, and actual air-conditioning operation parameters corresponding to each group of environment data;

[0008] Generate training data based on the multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operating parameters corresponding to each set of environmental data;

[0009] The training data is used to train the initial prediction model to obtain an air-conditioning control model, and the air-conditioning control model is used to adjust the operating parameters of the vehicle air-conditioning.

[0010] In a possible implementation, the PMV measuring device includes at least one wind speed sensor, at least one radiation temperature sensor, and multiple temperature and humidity sensors, wherein the multiple temperature and humidity sensors are used to collect temperature and humidity values ​​of multiple areas in the vehicle, and the multiple temperature and humidity sensors correspond one-to-one to the multiple areas; each group of in-vehicle environmental data includes: radiation temperature values, wind speed values, and multiple temperature and humidity values ​​collected at the same time; the air-conditioning parameters include: air-conditioning outlet temperature and air-conditioning wind speed.

[0011] In a possible implementation, generating training data based on the multiple sets of in-vehicle environment data, clothing thermal resistance corresponding to each set of environment data, human metabolic rate, and actual air-conditioning operation parameters corresponding to each set of environment data includes:

[0012] A training set and a test set are generated according to a proportional relationship using multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operating parameters corresponding to each set of environmental data, wherein the training set includes a first training set, a second training set, and a third training set, and the air-conditioning outlet temperature and / or air-conditioning wind speed corresponding to the second training set are smaller than the air-conditioning outlet temperature and / or air-conditioning wind speed corresponding to the first training set, and larger than the air-conditioning outlet temperature and / or air-conditioning wind speed corresponding to the third training set.

[0013] In a possible implementation, the initial prediction model is a neural network model or a random forest regression model; and the initial prediction model is trained using the training data to obtain the air conditioning control model, including:

[0014] The initial prediction model is trained using the training set, and the trained initial prediction model is tested using the test set to obtain the air conditioning control model; the initial prediction model is a neural network model or a random forest regression model.

[0015] In a possible implementation, the initial prediction model is a neural network model or a random forest regression model; and the initial prediction model is trained using the training data to obtain the air conditioning control model, including:

[0016] The initial prediction model is trained using the training set, and the trained initial prediction model is tested using the test set to obtain the air conditioning control model.

[0017] In a possible implementation, the thermal resistance of clothing and the metabolic rate of the human body are obtained by the following method:

[0018] For each set of environmental data, the age, gender and clothing type of the test user are obtained, and the corresponding human metabolic rate is determined according to the mapping relationship between the age, gender and the preset age, gender and human metabolic rate;

[0019] According to the mapping relationship between the clothing type and the preset clothing type and clothing thermal resistance, the corresponding clothing thermal resistance is determined.

[0020] In a second aspect, an embodiment of the present application provides an air conditioning control method, including:

[0021] Obtain current in-vehicle environment data collected by the on-vehicle PMV measurement device;

[0022] Obtain the age, gender and clothing type input by the user, and determine the clothing thermal resistance and human metabolic rate based on the age, gender and clothing type;

[0023] Inputting the in-vehicle environment data, the clothing thermal resistance, and the human metabolic rate into an air conditioning control model to obtain air conditioning operation parameters output by the air conditioning control model;

[0024] The operation of the vehicle air conditioner is controlled based on the air conditioner operation parameters, and the air conditioner control model is a model trained by the method described in the first aspect.

[0025] In a third aspect, an embodiment of the present application provides an air conditioning control system, comprising: an on-board PMV measuring device and an on-board air conditioning controller; the on-board PMV measuring device is connected to the controller;

[0026] The vehicle-mounted PMV measuring device is used to collect in-vehicle environmental data, wherein the in-vehicle environmental data includes: current radiation temperature value, wind speed value, and multiple temperature and humidity values;

[0027] The controller is used to input the in-vehicle environment data, clothing thermal resistance, and human metabolic rate into the air conditioning control model to obtain the air conditioning operation parameters output by the air conditioning control model; the clothing thermal resistance and human metabolic rate are determined according to the age, gender, and clothing type input by the user;

[0028] The controller is further used to control the operation of the vehicle air conditioner based on the air conditioner operation parameters, and the air conditioner control model is a model trained by the method described in the first aspect.

[0029] In a fourth aspect, an embodiment of the present application provides a training device for an air conditioning control model, comprising:

[0030] The first acquisition module is used to obtain multiple groups of in-vehicle environmental data collected by the average thermal sensation index PMV measurement device, clothing thermal resistance corresponding to each group of environmental data, human metabolic rate, and actual air conditioning operation parameters corresponding to each group of environmental data;

[0031] A first processing module, configured to generate training data based on the multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operation parameters corresponding to each set of environmental data;

[0032] The first processing module is also used to train the initial prediction model using the training data to obtain an air-conditioning control model, and the air-conditioning control model is used to adjust the operating parameters of the vehicle air-conditioning.

[0033] In a fifth aspect, an embodiment of the present application provides an air conditioning control device, including:

[0034] The second acquisition module is used to acquire the current in-vehicle environment data collected by the vehicle-mounted PMV measurement device, wherein the in-vehicle environment data includes: the current radiation temperature value, the wind speed value, and multiple temperature and humidity values;

[0035] The second acquisition module is also used to obtain the age, gender and clothing type input by the user, and determine the clothing thermal resistance and human metabolic rate according to the age, gender and clothing type;

[0036] A second processing module is used to input the in-vehicle environment data, the clothing thermal resistance, and the human metabolic rate into an air conditioning control model to obtain air conditioning operation parameters output by the air conditioning control model;

[0037] A control module is used to control the operation of the vehicle air conditioner based on the air conditioner operation parameters, and the air conditioner control model is a model trained by the method described in the first aspect.

[0038] In a sixth aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0039] The memory stores computer-executable instructions;

[0040] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect, and the second aspect and / or various possible implementations of the second aspect.

[0041] In the seventh aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement the above first aspect and / or various possible implementation methods of the first aspect, as well as the second aspect and / or various possible implementation methods of the second aspect.

[0042] In an eighth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementations of the first aspect, as well as the second aspect and / or various possible implementations of the second aspect.

[0043] The training method, device, equipment and storage medium of the air-conditioning control model provided in the embodiments of the present application not only take into account the current in-car environment, but also take into account multiple input variables such as the user's metabolic condition and clothing condition during the model training process to obtain the air-conditioning control model. Through the air-conditioning control model, intelligent adjustment is performed to provide a more comfortable in-car environment and personalized settings to meet the needs of different users. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0045] Figure 1 A schematic diagram of a scenario for the training method of the air conditioning control model provided in this application;

[0046] Figure 2 Schematic diagram of the training method of the air conditioning control model provided in this application Figure 1 ;

[0047] Figure 3 Schematic diagram of the PMV device provided for this application;

[0048] Figure 4 Schematic diagram of the training method of the air conditioning control model provided in this application Figure 1 ;

[0049] Figure 5 Schematic diagram of the temperature and humidity sensor structure provided for this application;

[0050] Figure 6 A schematic diagram of the wind speed sensor structure provided for this application;

[0051] Figure 7 A schematic diagram of the structure of the radiation temperature sensor provided in this application;

[0052] Figure 8 A flow chart of the air conditioning control method provided in this application;

[0053] Fig. 9 A schematic diagram of the structure of the training device for the air conditioning control model provided in this application;

[0054] Fig.10 A schematic diagram of the structure of the air conditioning control device provided in this application;

[0055] Fig.11 A schematic diagram of the structure of the electronic device provided in this application.

[0056] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0057] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0058] Figure 1 A schematic diagram of a scenario of the training method of the air conditioning control model provided in this application, such as Figure 1 As shown, the specific application scenarios of the present application include: a PMV measuring device 101 and an electronic device 102, the PMV measuring device 101 reports the collected in-vehicle environmental data to the electronic device 102, the electronic device 102 obtains multiple groups of in-vehicle environmental data collected by the average thermal sensation index PMV measuring device, the clothing thermal resistance corresponding to each group of environmental data, the human metabolic rate and the actual air-conditioning operating parameters corresponding to each group of environmental data, the PMV measuring device includes at least one wind speed sensor, at least one radiation temperature sensor, and multiple temperature and humidity sensors, the multiple temperature and humidity sensors are used to collect temperature and humidity values ​​of multiple areas in the car, and the multiple temperature and humidity sensors correspond to the multiple areas one by one; each group of in-vehicle environmental data includes: the radiation temperature value, the wind speed value and multiple temperature and humidity values ​​collected at the same time; the air-conditioning parameters include: the air-conditioning outlet temperature and the air-conditioning wind speed, the electronic device 102 generates training data based on multiple groups of in-vehicle environmental data, the clothing thermal resistance corresponding to each group of environmental data, the human metabolic rate and the actual air-conditioning operating parameters corresponding to each group of environmental data; the initial prediction model is trained using the training data to obtain an air-conditioning control model, and the air-conditioning control model is used to adjust the operating parameters of the vehicle air-conditioning.

[0059] In combination with the above scenarios, it can be seen that in the prior art, the problem that the in-car air conditioning adjustment method cannot meet user needs is solved.

[0060] The training method of the air-conditioning control model provided in the present application obtains multiple groups of in-vehicle environmental data collected by a PMV testing device, the thermal resistance of clothing corresponding to each group of environmental data, the human metabolic rate, and the actual air-conditioning operating parameters corresponding to each group of environmental data, and generates training data based on the multiple groups of in-vehicle environmental data, the thermal resistance of clothing corresponding to each group of environmental data, the human metabolic rate, and the actual air-conditioning operating parameters corresponding to each group of environmental data. The training data is used to train the initial prediction model to obtain the air-conditioning control model. During the model training process, not only the current in-vehicle environment is taken into account, but also multiple input variables such as the user's metabolic condition and wearing condition are taken into account to obtain the air-conditioning control model. The air-conditioning control model is used to perform intelligent adjustment to provide a more comfortable in-vehicle environment and provide personalized settings to meet the needs of different users.

[0061] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0062] Figure 2 Schematic diagram of the training method of the air conditioning control model provided in this application Figure 1 ,like Figure 2 As shown, the method includes:

[0063] Step 201, obtaining multiple groups of in-vehicle environment data collected by a PMV measurement device, clothing thermal resistance corresponding to each group of environment data, human metabolic rate, and actual air-conditioning operation parameters corresponding to each group of environment data.

[0064] In this embodiment, under different environmental conditions, the PMV measuring device is used to collect multiple sets of in-vehicle environmental data. Multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operation parameters corresponding to each set of environmental data are obtained, wherein clothing thermal resistance and human metabolic rate are determined according to the age, gender, and clothing type of the test user; wherein the actual air-conditioning operation parameters are the actual air-conditioning operation parameters set by the test user under different environmental conditions during the test, a set of environmental data corresponding to a clothing thermal resistance, human metabolic rate, and actual air-conditioning operation parameters.

[0065] Optionally, the PMV measuring device includes at least one wind speed sensor, at least one radiation temperature sensor, and multiple temperature and humidity sensors. The multiple temperature and humidity sensors are used to collect temperature and humidity values ​​of multiple areas in the vehicle, and the multiple temperature and humidity sensors correspond one-to-one to the multiple areas; each group of in-vehicle environmental data includes: radiation temperature value, wind speed value and multiple temperature and humidity values ​​collected at the same time; the air-conditioning parameters include: air-conditioning outlet temperature and air-conditioning wind speed.

[0066] Specifically, the PMV measuring device is used for testing, and the PMV measuring device includes at least one wind speed sensor, at least one radiation temperature sensor, and multiple temperature and humidity sensors. Optionally, the multiple temperature and humidity sensors are distributedly arranged on the body of the test user, such as Figure 3As shown, a wind speed sensor 301 is arranged on one shoulder of the test user, a radiation temperature sensor 302, such as a black ball temperature and humidity sensor, is arranged on the other shoulder of the test user, and multiple temperature and humidity sensors 303 are arranged on multiple parts of the test user, such as the left leg, left arm, head, and arm. When the test user is in the car, the temperature and humidity values ​​of multiple areas in the car are collected by the above-mentioned multiple temperature and humidity sensors. The multiple temperature and humidity sensors correspond to the multiple areas one by one. It is precisely because the user is in the vehicle and is exposed to direct sunlight that the temperature of the area where the upper body is located will be higher than the temperature of the area where the lower body is located, so the temperatures of multiple areas are taken into consideration.

[0067] Optionally, since air temperature is the main factor affecting the PMV value among environmental factors, the temperature and humidity sensor is the most used sensor in the PMV measuring device, so the proportion of temperature and humidity sensors should be 30%-90% of the total number. Since humidity, radiation temperature and wind speed have less impact on the PMV value than air temperature, the number of radiation temperature sensors and wind speed sensors used is less than the number of temperature and humidity sensors used. Therefore, the proportion of wireless wind speed sensors and radiation temperature sensors should be 5%-35% of the total number.

[0068] Among them, each group of in-vehicle environmental data includes: radiation temperature value, wind speed value and multiple temperature and humidity values ​​collected at the same time; air-conditioning parameters include: air-conditioning outlet temperature and air-conditioning wind speed.

[0069] Optionally, the radiation temperature sensor and the wind speed sensor may be handheld, or worn on the test user, or placed in different areas around the test user.

[0070] Step 202 , generating training data based on multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operating parameters corresponding to each set of environmental data.

[0071] In this embodiment, training data is generated based on multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operating parameters corresponding to each set of environmental data. The in-vehicle environmental data, clothing thermal resistance, and human metabolic rate are used as feature parameters, which are the inputs of the initial prediction model, and the actual air-conditioning operating parameters are used as the target values ​​of the initial prediction model.

[0072] Step 203 , using the training data to train the initial prediction model to obtain an air conditioning control model, where the air conditioning control model is used to adjust the operating parameters of the vehicle air conditioning.

[0073] In this embodiment, training data is used to train the initial prediction model, wherein the initial prediction model includes a neural network model or a random forest regression model. The air-conditioning control model is obtained through training. Since more feature parameters are used in the training process, the air-conditioning parameters can be predicted more accurately, and the air-conditioning control model is used to adjust the operating parameters of the vehicle air-conditioning.

[0074] In this embodiment, multiple groups of in-vehicle environmental data collected by the PMV testing device, clothing thermal resistance corresponding to each group of environmental data, human metabolic rate, and actual air-conditioning operating parameters corresponding to each group of environmental data are obtained, and training data is generated based on the multiple groups of in-vehicle environmental data, clothing thermal resistance corresponding to each group of environmental data, human metabolic rate, and actual air-conditioning operating parameters corresponding to each group of environmental data. The training data is used to train the initial prediction model to obtain an air-conditioning control model. During the model training process, not only the current in-vehicle environment but also multiple input variables such as the user's metabolic condition and wearing condition are taken into consideration to obtain the air-conditioning control model. The air-conditioning control model is used for intelligent adjustment to provide a more comfortable in-vehicle environment and provide personalized temperature and wind speed settings to meet the needs of different users.

[0075] Figure 4 Schematic diagram of the training method of the air conditioning control model provided in this application Figure 2 ,like Figure 4 As shown, in this embodiment Figure 2 Based on the embodiment, a training method for the air conditioning control model is described in detail, and the method includes:

[0076] Step 401, obtain multiple groups of in-vehicle environmental data collected by a mean thermal sensation index PMV measuring device, clothing thermal resistance corresponding to each group of environmental data, human metabolic rate, and actual air-conditioning operating parameters corresponding to each group of environmental data, the PMV measuring device includes at least one wind speed sensor, at least one radiation temperature sensor, and multiple temperature and humidity sensors, the multiple temperature and humidity sensors are used to collect temperature and humidity values ​​of multiple areas in the vehicle, and the multiple temperature and humidity sensors correspond one-to-one to the multiple areas; each group of in-vehicle environmental data includes: radiation temperature value, wind speed value and multiple temperature and humidity values ​​collected at the same time; air-conditioning parameters include: air-conditioning outlet temperature and air-conditioning wind speed.

[0077] Specifically, the PMV measuring device is used for testing, and the PMV measuring device includes at least one wind speed sensor, at least one radiation temperature sensor, and multiple temperature and humidity sensors. Optionally, the multiple temperature and humidity sensors are distributedly arranged on the body of the test user, such as Figure 3As shown, a wind speed sensor 301 is set at one shoulder position of the test user, a radiation temperature sensor 302, such as a black ball temperature and humidity sensor, is set at the other shoulder position of the test user, and multiple temperature and humidity sensors 303 are set at multiple parts of the test user, such as the left leg, left arm, head, and arm. When the test user is in the car, the temperature and humidity values ​​of multiple areas in the car are collected through the above-mentioned multiple temperature and humidity sensors, and the multiple temperature and humidity sensors correspond to the multiple areas one by one.

[0078] See also Figure 5 , Figure 5 : is a schematic diagram of the structure of a temperature and humidity sensor, which is a wireless temperature and humidity sensor, including a front side 501 and a back side 503, wherein the front side 501 includes a temperature and humidity circuit module 502 with a temperature and humidity sensor, and the back side 503 of the temperature and humidity sensor module includes a button battery 504, a wireless transmission circuit module 505, and a switch 506, wherein the button battery 504 is used to supply power to the temperature and humidity circuit module 502 and the wireless transmission circuit module 505; the switch 506 is used to turn on and off the power supply of the button battery 504; when the button battery 504 is not exhausted and the switch 506 is turned on, the temperature and humidity circuit module 502 collects temperature and humidity data and sends the temperature and humidity data to the electronic device through the wireless transmission circuit module 505.

[0079] See also Figure 6 , Figure 6 Schematic diagram of the wind speed sensor structure. The wind speed sensor is a wireless wind speed sensor. The wind speed sensor includes a data acquisition circuit module 601, a wireless transmission circuit module 602, and a battery 603. The wind speed sensor collects wind speed information and transmits it to the data acquisition circuit module 601, and then sends the wind speed information to the electronic device through the wireless transmission circuit module 602; the battery 603 is responsible for power supply.

[0080] See also Figure 7 , Figure 7 Schematic diagram of the structure of the radiation temperature sensor. The radiation temperature sensor is a wireless temperature sensor structure. The black ball temperature sensor is used for illustration. The black ball temperature sensor includes a data acquisition circuit module 701, a wireless transmission circuit module 702, and a battery 703. The black ball temperature sensor collects radiation temperature information and transmits it to the data acquisition circuit module 701, and then sends the radiation temperature information to the electronic device through the wireless transmission circuit module 702; the battery 703 is responsible for power supply.

[0081] When using the PMV measurement device, you first need to connect the radiation temperature sensor and wind speed sensor to their respective wireless acquisition and transmission modules to form a wireless wind speed sensor module and a wireless radiation temperature sensor module. Then install the batteries in each module. If each sensor module has not been initialized, you should first initialize each module, and then proceed to the next step after initialization. The initialization process is mainly to initialize the wireless transmission circuit, including the initialization of the data transmission address and the initialization of the active sending time interval.

[0082] In this embodiment, under different environmental conditions, the PMV measuring device is used to collect multiple groups of in-vehicle environmental data, each group of in-vehicle environmental data includes: radiation temperature value, wind speed value and multiple temperature and humidity values ​​collected at the same time, and obtain multiple groups of in-vehicle environmental data, clothing thermal resistance corresponding to each group of environmental data, human metabolic rate and actual air-conditioning operation parameters corresponding to each group of environmental data, wherein clothing thermal resistance and human metabolic rate are determined according to the age, gender and clothing type of the test user; wherein the actual air-conditioning operation parameters are the actual air-conditioning operation parameters set by the test user under different environmental conditions during the test, a group of environmental data corresponds to a clothing thermal resistance, human metabolic rate, and actual air-conditioning operation parameters, and the air-conditioning parameters include: air-conditioning outlet temperature and air-conditioning wind speed.

[0083] Optionally, clothing thermal resistance and human metabolic rate can be obtained by:

[0084] For each set of environmental data, the age, gender and clothing type of the test user are obtained, and the corresponding human metabolic rate is determined based on the mapping relationship between age, gender and preset age, gender and human metabolic rate; the corresponding clothing thermal resistance is determined based on the mapping relationship between clothing type and preset clothing type and clothing thermal resistance.

[0085] In this embodiment, for each group of environmental data, the age, gender and clothing type of the test user are obtained, the age and gender of the test user are matched with the mapping relationship between the preset age, gender and human metabolic rate, the human metabolic rate corresponding to the preset age and gender that match the age and gender of the test user is obtained, and the human metabolic rate is determined as the human metabolic rate corresponding to the group of environmental data; the clothing type of the test user is matched with the mapping relationship between the preset clothing type and clothing thermal resistance, the clothing thermal resistance corresponding to the preset clothing type that matches the clothing type of the test user is obtained, and the clothing thermal resistance is determined as the clothing thermal resistance corresponding to the group of environmental data.

[0086] Step 402, generating a training set and a test set according to a proportional relationship based on multiple groups of in-vehicle environmental data, clothing thermal resistance corresponding to each group of environmental data, human metabolic rate, and actual air-conditioning operating parameters corresponding to each group of environmental data, wherein the training set includes a first training set, a second training set, and a third training set, and the air-conditioning outlet temperature and / or air-conditioning wind speed corresponding to the second training set is less than the air-conditioning outlet temperature and / or air-conditioning wind speed corresponding to the first training set, and is greater than the air-conditioning outlet temperature and / or air-conditioning wind speed corresponding to the third training set.

[0087] In this embodiment, training data is generated based on multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operating parameters corresponding to each set of environmental data. The in-vehicle environmental data, clothing thermal resistance, and human metabolic rate are used as feature parameters, which are the inputs of the initial prediction model, and the actual air-conditioning operating parameters are used as the target values ​​of the initial prediction model.

[0088] Specifically, multiple groups of in-vehicle environmental data, clothing thermal resistance corresponding to each group of environmental data, human metabolic rate, and actual air-conditioning operating parameters corresponding to each group of environmental data are used to generate training sets and test sets in a proportional relationship. For example, the ratio of the training set to the test set is 7:3, wherein the training set includes a first training set, a second training set, and a third training set. The first training set is aggressive data, the second training set is conventional data, and the third training set is moderate data. The air-conditioning outlet temperature and / or air-conditioning wind speed corresponding to the second training set are less than the air-conditioning outlet temperature and / or air-conditioning wind speed corresponding to the first training set, and the air-conditioning outlet temperature and / or air-conditioning wind speed corresponding to the second training set are less than the air-conditioning outlet temperature and / or air-conditioning wind speed corresponding to the first training set. Or the air conditioning wind speed is greater than the air conditioning outlet temperature and / or air conditioning wind speed corresponding to the third training set. For example, if the test user sets the air conditioning outlet temperature and wind speed higher, the air conditioning outlet temperature, wind speed, and the in-vehicle environmental data, clothing thermal resistance, and human metabolic rate corresponding to the air conditioning outlet temperature and air conditioning wind speed are taken as a set of training data, and the training data belongs to the third training set. For example, if the test user sets the air conditioning outlet temperature and wind speed lower, the air conditioning outlet temperature, wind speed, and the in-vehicle environmental data, clothing thermal resistance, and human metabolic rate corresponding to the air conditioning outlet temperature and air conditioning wind speed are taken as a set of training data, and the training data belongs to the first training set. Based on the air conditioning outlet temperature and air conditioning wind speed, the in-vehicle environmental data, clothing thermal resistance corresponding to each group of environmental data, human metabolic rate, and actual air conditioning operating parameters corresponding to each group of environmental data are divided to obtain different types of training sets, providing relatively rich training samples.

[0089] Optionally, multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operation parameters corresponding to each set of environmental data are used to generate training sets and test sets in a proportional relationship, including:

[0090] Multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operating parameters corresponding to each set of environmental data are normalized, and training sets and test sets are generated according to a proportional relationship for the processed multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operating parameters corresponding to each set of environmental data.

[0091] In this embodiment, multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operation parameters corresponding to each set of environmental data are normalized. Normalization is an important step in data preprocessing. Normalization can reduce the model's dependence on a specific numerical range in the training data, thereby improving the model's generalization ability on test data. Moreover, normalization can make the model more reasonably adjust the weights of different features, thereby improving the accuracy and stability of the model. Further, the processed multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operation parameters corresponding to each set of environmental data are used to generate training sets and test sets according to a proportional relationship.

[0092] Step 403 , using the training data to train the initial prediction model to obtain an air conditioning control model, where the air conditioning control model is used to adjust the operating parameters of the vehicle air conditioning.

[0093] In this embodiment, training data is used to train the initial prediction model, wherein the initial prediction model includes a neural network model or a random forest regression model. The air-conditioning control model is obtained through training. Since more feature parameters are used in the training process, the air-conditioning parameters can be predicted more accurately, and the air-conditioning control model is used to adjust the operating parameters of the vehicle air-conditioning.

[0094] In a possible implementation, the initial prediction model is a neural network model; the initial prediction model is trained using training data to obtain an air conditioning control model, including:

[0095] The training set is used to train the initial prediction model, and the test set is used to test the trained initial prediction model to obtain the air conditioning control model. The initial prediction model is a neural network model or a random forest regression model.

[0096] In this embodiment, an initial prediction model is constructed, and the initial prediction model is a neural network model or a random forest regression model.

[0097] Specifically, a three-layer neural network is constructed: input layer, hidden layer and output layer.

[0098] Among them, the input layer is the first layer of the initial prediction model, and it is also the place where data enters the initial prediction model. For example, the input layer has 16 nodes, and each node corresponds to the reading of a sensor. For example, PMV measurement pre-sets 13 temperature and humidity sensors, 1 radiation temperature sensor, and 1 wind speed sensor, and reads the temperature values ​​of 13 temperature and humidity sensors, the humidity value of 1 temperature and humidity sensor, the radiation temperature value of 1 radiation temperature sensor, and the wind speed value of 1 wind speed sensor. The value of each node is the reading of the corresponding sensor.

[0099] The hidden layer is located between the input layer and the output layer, which can help extract important features of the input data. The hidden layer has several nodes, and the specific number can be determined based on experience or experimental requirements. The hidden layer uses ReLU (Rectified Linear Unit) as the activation function. The advantage of the ReLU activation function is that it can effectively alleviate the gradient vanishing problem in the back propagation process without affecting the forward propagation.

[0100] The output layer is the last layer of the initial prediction model, which outputs the prediction results of the model. The output layer has two nodes, corresponding to the predicted air outlet temperature and air speed of the air conditioner. The activation function of the output layer is usually selected according to the specific task. Since this is a regression problem, a linear activation function can be selected.

[0101] Specifically, the training of the initial prediction model usually includes two processes: forward propagation and back propagation: In the forward propagation process, the input data starts from the input layer, passes through the hidden layer, and finally reaches the output layer to obtain the predicted output of the initial prediction model. Each layer performs some linear transformation (i.e., weighted summation) and nonlinear transformation (i.e., activation function) on the input data.

[0102] Among them, back propagation: During the back propagation process, the model first calculates the difference between the predicted output and the true output (i.e., the loss), and then starts from the output layer and calculates the gradient of each layer layer by layer in the direction of the input layer, and updates the weight of each layer according to these gradients. The training goal of the initial prediction model is to minimize the difference between the predicted output and the true output, which is usually achieved through some optimization algorithm (such as gradient descent or its variants, such as Adam).

[0103] In this embodiment, the initial prediction model is trained using the first training set, the second training set, and the third training set, respectively. For example, the neural network model is trained using the first training set, and the trained neural network model is tested using the test set to obtain a trained first air conditioning control model; the neural network model is trained using the second training set, and the trained neural network model is tested using the test set to obtain a trained second air conditioning control model; the neural network model is trained using the third training set, and the trained neural network model is tested using the test set to obtain a trained third air conditioning control model. Different types of training data are used during the training of the above models, and air conditioning control models suitable for different users can be obtained. Because the air conditioning temperature and wind speed output by the model are continuous values, a regression model needs to be selected for training, such as a neural network model, a random forest regression model, etc. For this regression problem, a general mean square error can be selected as a loss function. An optimization algorithm, such as stochastic gradient descent, is selected to minimize the loss function.

[0104] In this embodiment, during the model training process, not only the current in-car environment is taken into consideration, but also multiple input variables such as the user's metabolic condition and clothing condition to obtain an air-conditioning control model. Through the air-conditioning control model, intelligent adjustment is performed to provide a more comfortable in-car environment and personalized temperature and wind speed settings to meet the needs of different users.

[0105] Figure 8 A flow chart of the air conditioning control method provided in this application, such as Figure 8 As shown, the method includes:

[0106] Step 801, obtaining current in-vehicle environment data collected by a vehicle-mounted PMV measurement device.

[0107] In this embodiment, the current in-vehicle environment data collected by the vehicle-mounted PMV measuring device is obtained. The vehicle-mounted PMV measuring device is arranged in the vehicle. The vehicle-mounted PMV measuring device includes at least one wind speed sensor, at least one radiation temperature sensor, and multiple temperature and humidity sensors. The multiple temperature and humidity sensors are respectively arranged in multiple areas in the vehicle. The multiple temperature and humidity sensors are used to collect temperature and humidity values ​​of multiple areas in the vehicle, and the multiple temperature and humidity sensors correspond one-to-one to the multiple areas; the wind speed sensor and the radiation temperature sensor are arranged in the vehicle.

[0108] Step 802, obtaining the age, gender and clothing type input by the user, and determining clothing thermal resistance and human metabolic rate according to the age, gender and clothing type.

[0109] In this embodiment, the age, gender and clothing type input by the user are obtained, and the human metabolic rate is determined according to the age and gender. Specifically, the user's age and gender are matched with the mapping relationship between the preset age, gender and human metabolic rate, and the human metabolic rate corresponding to the preset age and gender that matches the user's age and gender is obtained, and the human metabolic rate is determined as the user's human metabolic rate; the clothing thermal resistance is determined according to the user's clothing type. Specifically, the user's clothing type is matched with the mapping relationship between the preset clothing type and clothing thermal resistance, and the clothing thermal resistance corresponding to the preset clothing type that matches the user's clothing type is obtained, and the clothing thermal resistance is determined as the user's clothing thermal resistance.

[0110] Step 803, inputting the in-vehicle environment data, clothing thermal resistance, and human metabolic rate into the air conditioning control model to obtain the air conditioning operation parameters output by the air conditioning control model.

[0111] In this embodiment, the in-vehicle environment data, clothing thermal resistance, and human metabolic rate are input into the air-conditioning control model, which is obtained by training through the above-mentioned embodiments, and the air-conditioning operation parameters output by the air-conditioning control model are obtained. The air-conditioning operation parameters include: air-conditioning outlet temperature and air-conditioning wind speed.

[0112] Step 804, controlling the operation of the vehicle air conditioner based on the air conditioner operation parameters.

[0113] In this embodiment, the operation of the vehicle air conditioner is controlled based on the air outlet temperature and the air conditioning wind speed. The operation of the air conditioner can be automatically adjusted according to the current vehicle environment and the user's metabolic and wearing conditions. Through automatic control, the frequency of manual adjustment of the air conditioner by the user is reduced, and the convenience and comfort of use are improved. Moreover, the model can process multiple variables at the same time, such as temperature and humidity in multiple areas of the vehicle, wind speed, radiant temperature, and the user's own conditions, thereby achieving more comprehensive and precise air conditioning control.

[0114] Optionally, there may be some situations that do not satisfy the user. At this time, the model needs to be further optimized and improved to adapt to the user's situation. Every time the user forcibly modifies the air outlet temperature and wind speed of the air conditioner, the characteristic data and target value at this time are automatically obtained. The characteristic data includes the current environmental data, clothing thermal resistance and human metabolic rate. The target value is the current clothing thermal resistance and human metabolic rate. The above collected data are added to the original data set to train the model. You can also choose to update the parameters of the model by incremental learning. If it is a neural network model, the weights and parameters of the model can be updated by the back propagation algorithm to adapt it to the new data. In the above way, a personalized air conditioning control model can be obtained to meet the needs of users. By learning the user's preferences, the model can provide personalized temperature and wind speed settings to meet the needs of different users.

[0115] The present application also provides an air-conditioning control system. The air-conditioning control system provided in this embodiment includes: a vehicle-mounted PMV measuring device and a vehicle-mounted air-conditioning controller; the vehicle-mounted PMV measuring device is connected to the controller; the vehicle-mounted PMV measuring device is used to collect in-vehicle environmental data, and the in-vehicle environmental data include: current radiation temperature value, wind speed value and multiple temperature and humidity values; the controller is used to input the in-vehicle environmental data, clothing thermal resistance, and human metabolic rate into the air-conditioning control model to obtain the air-conditioning operating parameters output by the air-conditioning control model; clothing thermal resistance and human metabolic rate are determined according to the age, gender and clothing type input by the user; the controller is also used to control the operation of the vehicle-mounted air-conditioning based on the air-conditioning operating parameters, and the air-conditioning control model is a model trained by the method of the above embodiment.

[0116] In this embodiment, the air-conditioning control system includes a vehicle-mounted PMV measuring device and a vehicle-mounted air-conditioning controller. The vehicle-mounted PMV measuring device and the vehicle-mounted air-conditioning controller are communicatively connected. The vehicle-mounted PMV measuring device is used to collect in-vehicle environmental data and send the environmental data to the controller. The in-vehicle environmental data include: current radiation temperature value, wind speed value, and multiple temperature and humidity values. The controller determines clothing thermal resistance and human metabolic rate based on the age, gender, and clothing type input by the user. The controller inputs the in-vehicle environmental data, clothing thermal resistance, and human metabolic rate into the air-conditioning control model to obtain the air-conditioning operating parameters output by the air-conditioning control model. The air-conditioning operating parameters include: air-conditioning outlet temperature and air-conditioning wind speed. It can sense the current in-vehicle environment and the user's metabolic and wearing conditions to automatically adjust the operation of the air-conditioning. Through automatic regulation, the frequency of users manually adjusting the air-conditioning is reduced, thereby improving the convenience and comfort of use.

[0117] Fig. 9 A structural diagram of the training device for the air conditioning control model provided in this application, such as Fig. 9 As shown, the training device 90 of the air conditioning control model provided in this embodiment includes:

[0118] Among them, the first acquisition module 901 is used to obtain multiple sets of in-vehicle environmental data collected by the average thermal sensation index PMV measurement device, the clothing thermal resistance corresponding to each set of environmental data, the human metabolic rate, and the actual air-conditioning operating parameters corresponding to each set of environmental data. The first processing module 902 is used to generate training data based on the multiple sets of in-vehicle environmental data, the clothing thermal resistance corresponding to each set of environmental data, the human metabolic rate, and the actual air-conditioning operating parameters corresponding to each set of environmental data. The first processing module 902 is also used to train the initial prediction model using the training data to obtain an air-conditioning control model, which is used to adjust the operating parameters of the vehicle air conditioner.

[0119] In one possible implementation, the first processing module 902 is also used to generate a training set and a test set according to a proportional relationship based on multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operating parameters corresponding to each set of environmental data, wherein the training set includes a first training set, a second training set, and a third training set, and the air-conditioning outlet temperature and / or air-conditioning wind speed corresponding to the second training set are smaller than the air-conditioning outlet temperature and / or air-conditioning wind speed corresponding to the first training set, and are larger than the air-conditioning outlet temperature and / or air-conditioning wind speed corresponding to the third training set.

[0120] In a possible implementation, the first processing module 902 is also used to train the initial prediction model using a training set, and to test the trained initial prediction model using a test set to obtain an air conditioning control model, where the initial prediction model is a neural network model or a random forest regression model.

[0121] In a possible implementation, the first processing module 902 is also used to normalize multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operating parameters corresponding to each set of environmental data, and generate training sets and test sets according to a proportional relationship for the processed multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operating parameters corresponding to each set of environmental data.

[0122] In a possible implementation, the first processing module 902 is also used to obtain the age, gender and clothing type of the test user for each group of environmental data, and determine the corresponding human metabolic rate based on the mapping relationship between age, gender and preset age, gender and human metabolic rate; determine the corresponding clothing thermal resistance based on the mapping relationship between clothing type and preset clothing type and clothing thermal resistance.

[0123] The training device for the air conditioning control model provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail in this embodiment.

[0124] Fig.10 The structural diagram of the air conditioning control device provided in this application is as follows: Figure 7 As shown, the air conditioning control device 100 provided in this embodiment includes:

[0125] Among them, the second acquisition module 1001 is used to obtain the current in-vehicle environment data collected by the vehicle-mounted PMV measurement device. The second acquisition module 1001 is also used to obtain the age, gender and clothing type input by the user, and determine the clothing thermal resistance and human metabolic rate according to the age, gender and clothing type. The second processing module 1002 is used to input the in-vehicle environment data, clothing thermal resistance, and human metabolic rate into the air conditioning control model to obtain the air conditioning operation parameters output by the air conditioning control model. The control module is used to control the operation of the vehicle-mounted air conditioning based on the air conditioning operation parameters, and the air conditioning control model is a model trained by the above method.

[0126] The air conditioning control device provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be described in detail here.

[0127] Fig.11 This is a schematic diagram of the structure of the electronic device provided in this application. Fig.11 As shown, the electronic device 110 provided in this embodiment includes: at least one processor 1101 and a memory 1102. Optionally, the device 110 further includes a communication component 1103. The processor 1101, the memory 1102 and the communication component 1103 are connected via a bus 1104.

[0128] In a specific implementation process, at least one processor 1101 executes the computer-executable instructions stored in the memory 1102, so that at least one processor 1101 executes the above method.

[0129] The specific implementation process of the processor 1101 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0130] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0131] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0132] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0133] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0134] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0135] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0136] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0137] The division of units is only a logical function division, and there may be other divisions in actual implementation, 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 an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0138] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0139] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0140] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0141] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0142] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A training method for an air conditioning control model, characterized in that: include: Obtain multiple groups of in-vehicle environmental data collected by a PMV measuring device, clothing thermal resistance corresponding to each group of environmental data, human metabolic rate, and actual air-conditioning operating parameters corresponding to each group of environmental data; Generate training data based on the multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operating parameters corresponding to each set of environmental data; The training data is used to train the initial prediction model to obtain an air-conditioning control model, and the air-conditioning control model is used to adjust the operating parameters of the vehicle air-conditioning.

2. The method according to claim 1, characterized in that: The PMV measuring device includes at least one wind speed sensor, at least one radiation temperature sensor, and multiple temperature and humidity sensors, wherein the multiple temperature and humidity sensors are used to collect temperature and humidity values ​​of multiple areas in the vehicle, and the multiple temperature and humidity sensors correspond to the multiple areas one by one; Each set of in-vehicle environmental data includes: a radiation temperature value, a wind speed value, and multiple temperature and humidity values ​​collected at the same time; the air-conditioning parameters include: air-conditioning outlet temperature and air-conditioning wind speed.

3. The method according to claim 1, characterized in that The generating of training data based on the multiple sets of in-vehicle environment data, clothing thermal resistance corresponding to each set of environment data, human metabolic rate, and actual air-conditioning operation parameters corresponding to each set of environment data includes: A training set and a test set are generated according to a proportional relationship using multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operating parameters corresponding to each set of environmental data, wherein the training set includes a first training set, a second training set, and a third training set, and the air-conditioning outlet temperature and / or air-conditioning wind speed corresponding to the second training set are smaller than the air-conditioning outlet temperature and / or air-conditioning wind speed corresponding to the first training set, and larger than the air-conditioning outlet temperature and / or air-conditioning wind speed corresponding to the third training set.

4. The method according to claim 3, characterized in that The step of training the initial prediction model using the training data to obtain the air conditioning control model includes: The initial prediction model is trained using the training set, and the trained initial prediction model is tested using the test set to obtain the air conditioning control model; The initial prediction model is a neural network model or a random forest regression model.

5. The method according to claim 3, characterized in that: The method generates a training set and a test set according to a proportional relationship of multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operation parameters corresponding to each set of environmental data, including: Multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operating parameters corresponding to each set of environmental data are normalized, and training sets and test sets are generated according to a proportional relationship for the processed multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operating parameters corresponding to each set of environmental data.

6. The method according to any one of claims 1 to 5, characterized in that: The thermal resistance of clothing and the metabolic rate of the human body are obtained by: For each set of environmental data, the age, gender and clothing type of the test user are obtained, and the corresponding human metabolic rate is determined according to the mapping relationship between the age, gender and the preset age, gender and human metabolic rate; According to the mapping relationship between the clothing type and the preset clothing type and clothing thermal resistance, the corresponding clothing thermal resistance is determined.

7. An air conditioning control method, characterized in that: include: Obtain current in-vehicle environment data collected by the on-vehicle PMV measurement device; Obtain the age, gender and clothing type input by the user, and determine the clothing thermal resistance and human metabolic rate based on the age, gender and clothing type; Inputting the in-vehicle environment data, the clothing thermal resistance, and the human metabolic rate into an air conditioning control model to obtain air conditioning operation parameters output by the air conditioning control model; The operation of the vehicle air conditioner is controlled based on the air conditioner operation parameters, and the air conditioner control model is a model trained by the method according to any one of claims 1 to 6.

8. An air conditioning control system, characterized in that: include: On-board PMV measuring device and on-board air conditioning controller; The vehicle-mounted PMV measuring device is connected to the controller; The vehicle-mounted PMV measuring device is used to collect in-vehicle environmental data, wherein the in-vehicle environmental data includes: current radiation temperature value, wind speed value, and multiple temperature and humidity values; The controller is used to input the in-vehicle environment data, clothing thermal resistance, and human metabolic rate into the air conditioning control model to obtain the air conditioning operation parameters output by the air conditioning control model; the clothing thermal resistance and human metabolic rate are determined according to the age, gender, and clothing type input by the user; The controller is further used to control the operation of the vehicle air conditioner based on the air conditioner operation parameters, and the air conditioner control model is a model trained by the method described in any one of claims 1 to 6.

9. A training device for an air conditioning control model, characterized in that: include: The first acquisition module is used to obtain multiple groups of in-vehicle environmental data collected by the average thermal sensation index PMV measurement device, clothing thermal resistance corresponding to each group of environmental data, human metabolic rate, and actual air conditioning operation parameters corresponding to each group of environmental data; A first processing module, configured to generate training data based on the multiple sets of in-vehicle environmental data, clothing thermal resistance corresponding to each set of environmental data, human metabolic rate, and actual air-conditioning operation parameters corresponding to each set of environmental data; The first processing module is also used to train the initial prediction model using the training data to obtain an air-conditioning control model, and the air-conditioning control model is used to adjust the operating parameters of the vehicle air-conditioning.

10. An air conditioning control device, characterized in that: include: The second acquisition module is used to acquire the current in-vehicle environment data collected by the vehicle-mounted PMV measurement device; The second acquisition module is also used to obtain the age, gender and clothing type input by the user, and determine the clothing thermal resistance and human metabolic rate according to the age, gender and clothing type; A second processing module is used to input the in-vehicle environment data, the clothing thermal resistance, and the human metabolic rate into an air conditioning control model to obtain air conditioning operation parameters output by the air conditioning control model; A control module is used to control the operation of the vehicle air conditioner based on the air conditioner operation parameters, and the air conditioner control model is a model trained by the method according to any one of claims 1 to 6.

11. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 7.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

Images