Vehicle-mounted air conditioner control method, vehicle and readable storage medium

Abstract

The invention discloses a vehicle-mounted air conditioner control method, a vehicle and a readable storage medium, and relates to the technical field of vehicles, and the method comprises the steps that in response to a vehicle-mounted air conditioner control instruction, the current environment, the current vehicle running state and vehicle user characteristics are obtained; target air conditioner parameters under the current environment, the current vehicle running state and the vehicle user characteristics are determined through a preset air conditioner prediction model, and the preset air conditioner prediction model is obtained by training the initial air conditioner prediction model based on the credible training sample set; and according to the target air conditioner parameters, a vehicle-mounted air conditioner in the vehicle is controlled to operate. The technical problem that the intelligent degree of the vehicle-mounted air conditioner is low is solved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a vehicle air-conditioning control method, a vehicle and a readable storage medium. Background Art

[0002] With the development of intelligent vehicle technology, users have higher and higher requirements for the comfort of the in-car environment. Traditional car air conditioners generally use manual adjustment. If the temperature is adjusted too high, it will waste energy. If the temperature is adjusted too low, it will affect the riding comfort. In actual driving scenarios, users are often in a hurry to set off and have no time to set the air conditioner, which will also affect the riding comfort. Therefore, there is currently a technical problem that the degree of intelligence of car air conditioners is low.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a vehicle air-conditioning control method, a vehicle and a readable storage medium, aiming to solve the technical problem of low intelligence level of vehicle air-conditioning.

[0005] To achieve the above object, the present application provides a vehicle air conditioning control method, the method comprising: Responding to the vehicle air conditioning control command, obtaining the current environment, the current vehicle operating state and the vehicle user characteristics; Determining target air conditioning parameters under the current environment, the current vehicle operating state and the vehicle user characteristics by using a preset air conditioning prediction model, wherein the preset air conditioning prediction model is obtained by training an initial air conditioning prediction model based on a credible training sample set; The operation of the vehicle air conditioner in the vehicle is controlled according to the target air conditioning parameter. In one embodiment, the method comprises: Acquire historical air-conditioning usage data of a target user group, wherein the target user group includes vehicle users corresponding to the vehicle air-conditioning and users of the same type as the vehicle users, and the historical air-conditioning usage data includes a plurality of sub-usage data, and the sub-usage data includes at least one of the following: historical vehicle user characteristics, historical air-conditioning feedback adjustment data, historical air-conditioning setting parameters, historical environment, and historical vehicle operating status; According to a plurality of preset large models, a credible training sample set is selected from the historical usage data of the air conditioner; A preset air conditioning prediction model is determined based on the credible training sample set and the initial air conditioning prediction model.

[0006] In one embodiment, the step of selecting a credible training sample set from the air conditioner historical usage data based on a plurality of preset large models comprises: For each preset large model, the air conditioner historical usage data is input into the preset large model, and abnormal sub-usage data in the air conditioner historical usage data is removed by the preset large model to obtain a normal usage data set filtered from the air conditioner historical usage data by the preset large model; Target normal data commonly contained in all the normally used data sets are extracted to obtain a credible training sample set.

[0007] In one embodiment, the step of determining a preset air conditioning prediction model based on the credible training sample set and the initial air conditioning prediction model includes: Performing scene feature extraction on the credible training sample set to obtain a plurality of scene parameter training features, wherein each scene parameter training feature includes a scene training feature and an air conditioning parameter setting feature associated with the scene training feature, the scene training feature includes at least one of the following: a training vehicle user feature, training air conditioning feedback adjustment data, a training environment, and a training vehicle operating state, and the air conditioning parameter setting feature includes at least one of the following: an air conditioning switch setting parameter, a seat heating setting parameter, a blowing setting parameter, an air conditioning temperature setting parameter, an air conditioning air volume setting parameter, a temperature adjustment mode setting parameter, and a circulation mode setting parameter; According to the plurality of scene parameter training features, the initial air conditioning prediction model is trained to obtain a trained teacher model; A student model having a parameter magnitude smaller than that of the teacher model is obtained, and the student model is updated by the teacher model, and the updated student model is used as a preset air conditioning prediction model.

[0008] In one embodiment, the target air conditioning parameter includes at least one of a target air conditioning switch parameter, a target seat heating parameter, a target blowing mode, a target air conditioning temperature, a target air conditioning air volume, a target circulation mode, and a target temperature adjustment mode; the step of determining the target air conditioning parameter under the current environment, the current vehicle operating state, and the vehicle user characteristics by using a preset air conditioning prediction model includes: The current environment, the current vehicle operating state and the vehicle user characteristics are input into a preset air conditioning prediction model, and a target air conditioning switch parameter, a target seat heating parameter, a target blowing mode, a target air conditioning temperature, a target air conditioning air volume, a target circulation mode and / or a target temperature adjustment mode under the current environment, the current vehicle operating state and the vehicle user characteristics are determined by the preset air conditioning prediction model; Among them, the current environment includes: current weather, current outside temperature, current inside temperature, current inside humidity, current outside rainfall, current outside environment image and at least one of the current inside environment image; the current vehicle operating status includes the current vehicle power; the vehicle user characteristics include the vehicle user's age, gender, current usage month, current vehicle latitude and at least one of the user's behavior.

[0009] In one embodiment, the method further comprises: In a preset driving scenario, if the current outside temperature is greater than a preset high temperature threshold, the output of the preset air conditioning prediction model includes: the target air conditioning switch parameter is on, the target air conditioning air volume includes increasing the air volume, and / or the target blowing mode includes blowing downward and / or blowing cold air; In a preset driving scenario, if the current outside temperature is less than a preset low temperature threshold, the output of the preset air conditioning prediction model includes: the target air conditioning switch parameter is on, the target air conditioning air volume includes increasing the air volume, and / or the target blowing mode includes blowing downward and / or blowing hot air; Among them, the preset driving scenarios include: the current weather is rainy, the current humidity inside the vehicle is greater than a preset humidity threshold, the current rainfall outside the vehicle is greater than a preset rainfall threshold, and / or the amount of water detected in the current external environment image is greater than a preset water threshold.

[0010] In one embodiment, the method comprises: When it is detected that the air quality outside the vehicle in the current outside vehicle environment image is less than a preset quality standard, the output of the preset air-conditioning prediction model includes the target circulation mode being internal circulation.

[0011] In one embodiment, the method further comprises: In the case where the target comfortable temperature corresponding to the current clothing thickness of the vehicle occupant is detected in the current vehicle interior environment image, the absolute value of the difference between the target comfortable temperature and the current vehicle interior temperature is greater than a preset temperature difference threshold, and the temperature adjustment time for adjusting the vehicle from the current vehicle interior temperature to the target comfortable temperature in a preset rapid temperature adjustment mode is less than an expected driving time of the vehicle, determining the output of the preset air conditioning prediction model includes: the target temperature adjustment mode includes a preset rapid temperature adjustment mode, and the target air conditioning temperature includes adjusting the current vehicle interior temperature to the target comfortable temperature; The target comfort temperature is obtained by adjusting the preset standard body comfort temperature based on the current clothing thickness to obtain the initial comfort temperature, and adjusting the initial comfort temperature according to the acquired temperature preference of the vehicle occupant.

[0012] In addition, to achieve the above-mentioned purpose, the present application also provides a vehicle air conditioning control device, the device comprising: An acquisition module, for acquiring the current environment, the current vehicle operation state and the vehicle user characteristics in response to the vehicle air conditioning control command; A determination module, configured to determine target air conditioning parameters under the current environment, the current vehicle operating state, and vehicle user characteristics by using a preset air conditioning prediction model, wherein the preset air conditioning prediction model is obtained by training an initial air conditioning prediction model based on a credible training sample set; The operation module is used to control the operation of the vehicle air conditioner in the vehicle according to the target air conditioning parameter. In addition, to achieve the above-mentioned purpose, the present application also provides a vehicle, which includes a vehicle body and a controller, wherein the controller is arranged in the vehicle body, and the controller is used to execute the steps of implementing the vehicle air conditioning control method as described above.

[0013] In addition, to achieve the above-mentioned purpose, the present application also provides a computer-readable storage medium, on which is stored a program for implementing the vehicle air-conditioning control method. When the program of the vehicle air-conditioning control method is executed by a processor, the steps of the vehicle air-conditioning control method as described above are implemented.

[0014] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned vehicle air conditioning control method when executed by a processor.

[0015] One or more technical solutions proposed in this application have at least the following technical effects: This application can obtain the current environment, the current vehicle operating status and the vehicle user characteristics, and determine the target air-conditioning parameters under the current environment, the current vehicle operating status and the vehicle user characteristics through the preset air-conditioning prediction model, so that the target air-conditioning parameters can adapt to the external environment, the vehicle operating status and meet the personalized needs of users at the same time. Furthermore, since the preset air-conditioning prediction model is obtained by training the initial air-conditioning prediction model based on the credible training sample set, and the credible training samples are credible, the prediction accuracy of the preset air-conditioning prediction model obtained by training the credible training samples is higher, which facilitates more accurate determination of the target air-conditioning parameters, so as to control the operation of the vehicle-mounted air-conditioning in the vehicle according to the target air-conditioning parameters, and the vehicle-mounted air-conditioning can be accurately controlled without user operation, thereby improving the intelligence of the vehicle-mounted air-conditioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings herein are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the description, are used to explain the principles of the present application.

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0018] Figure 1 This is a flow chart of the first embodiment of the vehicle air conditioning control method of the present application; Figure 2 This is a flow chart of the second embodiment of the vehicle air conditioning control method of the present application; Figure 3 A schematic diagram of a process of determining target air-conditioning parameters and controlling the operation of the vehicle air-conditioning according to the target air-conditioning parameters in an example of the vehicle air-conditioning control method of the present application; Figure 4 A schematic diagram of a process of training a preset air conditioning prediction model and predicting target air conditioning parameters through the preset air conditioning prediction model in another example of the vehicle air conditioning control method of the present application; Figure 5 This is a schematic diagram of the structure of the vehicle air conditioning control device of this application.

[0019] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0021] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0022] With the development of intelligent vehicle technology, users have higher and higher requirements for the comfort of the in-car environment. Traditional air-conditioning systems cannot be adjusted according to the personalized needs of users. Therefore, the present application provides a method for controlling vehicle air-conditioning. This embodiment can obtain the current environment, the current vehicle operating status, and the characteristics of the vehicle user. By presetting the air-conditioning prediction model, the target air-conditioning parameters under the current environment, the current vehicle operating status, and the characteristics of the vehicle user are determined, so that the target air-conditioning parameters can adapt to the external environment (current environment), adapt to the vehicle operating environment, and meet the personalized needs of users at the same time. Furthermore, the preset air-conditioning prediction model can be obtained by training the initial air-conditioning prediction model based on a credible training sample set screened out by multiple preset large models, and each preset large model has a strong semantic understanding ability, so that the training samples can be effectively screened. In this embodiment, a credible training sample set is obtained by jointly screening multiple preset large models, which can ensure the credibility of the credible training sample set, and at the same time, it can also avoid the inaccurate screening caused by the cognitive bias of a single preset large model. Then, the initial air-conditioning prediction model is trained with the credible training sample set obtained by screening, which can improve the accuracy of the preset air-conditioning prediction model, facilitate more accurate determination of the target air-conditioning parameters, and control the operation of the vehicle-mounted air-conditioning in the vehicle based on the target air-conditioning parameters. The vehicle-mounted air-conditioning can be accurately controlled without user operation, thereby improving the intelligence of the vehicle-mounted air-conditioning.

[0023] The present application provides a vehicle air conditioning control method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the vehicle air conditioning control method of the present application. In the first embodiment, the vehicle air conditioning control method includes steps S10 to S30: Step S10, in response to the vehicle air conditioning control command, obtaining the current environment, the current vehicle operating state and the vehicle user characteristics; It should be noted that the vehicle may be an electric vehicle, a hybrid vehicle, etc., and this embodiment does not specifically limit this. The current environment may reflect the environment of the location of the vehicle, for example, the current environment may reflect the temperature, humidity and / or weather of the location of the vehicle. For example, the current environment may include at least one of the current weather, the current temperature outside the vehicle, the current temperature inside the vehicle, the current humidity inside the vehicle, the current rainfall outside the vehicle, the current image of the environment outside the vehicle, and the current image of the environment inside the vehicle.

[0024] The current weather can be obtained through the weather API (Application Programming Interface) interface on the vehicle. The current weather can describe the weather conditions in the area where the vehicle is located. The current weather can be rainy, sunny, cloudy, etc.; rainy days can also be divided into heavy rain, heavy rain, and light rain, etc. based on the amount of rainfall. The current outside temperature may include the current climate temperature detected by the Meteorological Bureau and / or the outside temperature detected by the outside temperature sensor. The current climate temperature is the ambient temperature of the area where the vehicle is located. The current climate temperature can be detected by the Meteorological Bureau. In this embodiment, the current climate temperature can be obtained through the vehicle's weather API interface. Different climate environments require different parameters for the vehicle air conditioner.

[0025] The current temperature inside the vehicle can be detected by the temperature sensor inside the vehicle, and the current temperature outside the vehicle can be detected by the device outside the vehicle for detecting temperature. Although the current climate temperature can reflect the temperature of the area where the vehicle is located, the current climate temperature reflects the overall temperature of the area where the vehicle is located, and the temperature of different places in the area may be different. For example, the temperature outside the vehicle may be higher or lower than the current climate temperature due to the influence of the environment such as buildings near the vehicle. Therefore, this embodiment detects the current temperature outside the vehicle, which is also convenient for determining the corresponding setting parameters of the vehicle air conditioner more accurately in the future. The current rainfall outside the vehicle can be detected by the rainfall sensor outside the vehicle.

[0026] The current humidity inside the vehicle can be detected by a device inside the vehicle for detecting humidity, such as a humidity sensor, etc. The location of the humidity sensor can also be set based on actual conditions. For example, the humidity sensor inside the vehicle can be set in the footrest area of ​​the vehicle, so as to facilitate the detection of whether the feet of the people in the vehicle are wet, and then facilitate the subsequent adaptive adjustment of the parameters of the vehicle air conditioning settings. The current external environment image can be obtained by an image detection device set on the outside of the vehicle body. The current external environment image can reflect the driving conditions of the vehicle. The current in-vehicle environment image can be obtained by an image detection device set in the vehicle. The image detection device can be a device such as a camera. The current in-vehicle environment image can reflect the status of the passengers in the vehicle, such as the sitting conditions of the passengers in the vehicle, the thickness of the clothes of the passengers in the vehicle, etc.

[0027] The current vehicle operating status can reflect the vehicle status, and the current vehicle operating status will also affect the parameters of the vehicle air conditioning settings. The current vehicle operating status can include the current vehicle power. The current vehicle operating status is the vehicle driving status currently detected in real time. The current vehicle power represents the current remaining power of the vehicle. Since the vehicle air conditioning consumes energy when it is turned on, and the corresponding energy consumption varies with the degree of turning on, it is necessary to obtain the current vehicle power, so as to facilitate the subsequent combination of the current vehicle power to determine the corresponding vehicle air conditioning parameters, so as to adapt to the actual operating environment of the vehicle.

[0028] The vehicle user characteristics can reflect the personalized needs of the user. The vehicle user characteristics can include at least one of age, gender, current usage month, current vehicle latitude and user behavior. The vehicle user characteristics can be represented in the form of a vector. The current usage month represents the month when the vehicle user is currently driving the vehicle. Different months have different climate temperatures, so the air conditioning parameters set in different months may also be different. Therefore, the vehicle user characteristics can include the current usage month so that the air conditioning parameters of the current month can be set in a personalized way in combination with the usage month. The current vehicle latitude represents the latitude of the area where the vehicle user is driving the vehicle. The climates at different latitudes are different, so the air conditioning parameters set by vehicle users at different latitudes may not be the same. Therefore, the vehicle user characteristics can include the current vehicle latitude so that the air conditioning setting parameters can be set in a personalized way in combination with the latitude in the future.

[0029] User behavior is characterized by the user's behavior in the car. The user behavior can be the user's current behavior or the user's historical behavior. For example, when the user currently operates the air conditioner in the car, the user behavior is the current behavior. When the user does not currently operate the air conditioner in the car, the user behavior can be the user's historical behavior, which makes it easier to provide the user with personalized car air conditioning settings based on the user's age, gender, user behavior, current month of use, and current vehicle latitude. In other embodiments, the vehicle user characteristics can also include the current clothing thickness. The set air conditioning parameters may not be the same for different clothing thicknesses, so the current clothing thickness can be combined to provide the user with personalized air conditioning setting parameters.

[0030] For example, the current weather and current climate temperature can be obtained through the vehicle's weather API, the current humidity and current temperature in the vehicle can be obtained through the temperature sensor and humidity sensor in the vehicle, the current temperature outside the vehicle can be obtained through the temperature sensor outside the vehicle, the current rainfall outside the vehicle can be detected by the rain sensor, the current image of the environment in the vehicle can be obtained through the image detection device in the vehicle, the current image of the environment outside the vehicle can be obtained through the image detection device outside the vehicle, and the current vehicle power can be obtained through the vehicle's battery management system. Since the current weather reflects the overall weather in the region, the rainfall in different places in the region may be inconsistent, so the rainfall outside the vehicle can be detected by the rain sensor, so as to improve the accuracy of the setting of the vehicle air conditioning parameters in the future. The user's age and gender are obtained. If the user currently has an operation behavior on the vehicle air conditioning, the operation behavior is used as the user behavior. If the user currently does not have an operation behavior on the vehicle air conditioning, the user's historical operation behavior can be used as the user behavior. The current clothing thickness can be obtained by calling a preset visual large model to recognize the user image. The user image can be obtained through a device that can be used to obtain images, such as an in-vehicle camera or an infrared sensor. The preset visual large model can be used to detect the current clothing thickness of the user. The current clothing thickness can be the clothing thickness of the vehicle driver. The preset visual large model can be VLM (Visual Language Mode, large model). VLM is a multimodal artificial intelligence model that combines visual perception and natural language processing. Therefore, the current clothing thickness identified by the preset visual large model can be used as one of the vehicle user characteristics, so that the subsequent preset air-conditioning prediction model can collect the current clothing thickness for corresponding air-conditioning settings. In other embodiments, the current clothing thickness may not be included in the vehicle user characteristics. The current clothing thickness can also be obtained by recognizing the current in-vehicle environment image through the preset air-conditioning prediction model.

[0031] Step S20, determining target air conditioning parameters under the current environment, the current vehicle operating state and the vehicle user characteristics through a preset air conditioning prediction model, wherein the preset air conditioning prediction model is obtained by training an initial air conditioning prediction model based on a credible training sample set; It should be noted that the preset air-conditioning prediction model can be used to determine the target air-conditioning parameters under the current environment, the current vehicle operating state and the vehicle user characteristics; the target air-conditioning parameters are characterized as the parameters that need to be set for the vehicle air-conditioning.

[0032] The credible training sample set is jointly screened by multiple preset large models and can be used to train the initial air conditioning prediction model. For example, data for training can be input into each preset large model, and each preset large model can screen these data, and then the credible training sample set jointly screened by all preset large models can be determined. The preset air conditioning prediction model can be obtained by pre-training the initial air conditioning prediction model using credible training samples.

[0033] The preset large model is a large language model. Each preset large model is different. Each preset large model can come from a different supplier. The number of preset large models is at least 3. The number of preset large models can also be 4, 5, etc. This embodiment does not make specific restrictions on this. For example, multiple preset large models can be large language models of Wenxin Yiyan, Doubao, deepseek, Kimi, etc. This embodiment does not make specific restrictions on this. In addition, in this embodiment, the preset air conditioning prediction model can also identify the thickness of the clothing of the occupants in the current in-vehicle environment image.

[0034] Exemplarily, the current environment, the current vehicle operating state, and vehicle user characteristics may be input into a preset air-conditioning prediction model, and the preset air-conditioning prediction model may output target air-conditioning parameters.

[0035] Step S30, controlling the operation of the vehicle air conditioner in the vehicle according to the target air conditioning parameters. The vehicle air conditioner can be controlled to operate according to the target air conditioning parameters, so that the vehicle air conditioner can be automatically adjusted for the user while meeting the user's needs.

[0036] For example, the target air conditioning parameters can be input into the vehicle air conditioner so that the vehicle air conditioner can operate according to the target air conditioning parameters. The data format of the target air conditioning parameters output by the preset air conditioning prediction model needs to be consistent with the data format of the vehicle interface, so as to ensure that the vehicle air conditioner can be controlled to operate according to the target air conditioning parameters.

[0037] The embodiment of the present application can obtain the current environment, the current vehicle operating status and the vehicle user characteristics, and determine the target air conditioning parameters under the current environment, the current vehicle operating status and the vehicle user characteristics through the preset air conditioning prediction model, so that the target air conditioning parameters can adapt to the external environment, adapt to the vehicle operating status and meet the personalized needs of the user at the same time. Furthermore, since the preset air conditioning prediction model is obtained by training the initial air conditioning prediction model based on the credible training sample set, and the credible training sample is credible, the prediction accuracy of the preset air conditioning prediction model obtained by training with the credible training sample is higher, which facilitates more accurate determination of the target air conditioning parameters, so as to control the operation of the vehicle-mounted air conditioning in the vehicle according to the target air conditioning parameters, and the vehicle-mounted air conditioning can be accurately controlled without user operation, thereby improving the intelligence of the vehicle-mounted air conditioning.

[0038] Further, based on the above embodiments of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction, and will not be described in detail later. Figure 2 The vehicle air conditioner control method further includes steps A10 to A30: Step A10, obtaining historical air-conditioning usage data of a target user group, wherein the target user group includes vehicle users corresponding to the vehicle air-conditioning and users of the same type as the vehicle users, and the historical air-conditioning usage data includes a plurality of sub-usage data, and the sub-usage data includes at least one of the following: historical vehicle user characteristics, historical air-conditioning feedback adjustment data, historical air-conditioning setting parameters, historical climate environment, and historical vehicle operation status; It should be noted that the historical air conditioning feedback adjustment data is characterized by the adjustment operation performed by the user on the vehicle air conditioning after getting in the vehicle. For example, after getting in the vehicle, the user may turn on the air conditioning by default, but the user may adjust the vehicle air conditioning according to personal habits, and the adjustment is the user's historical air conditioning feedback adjustment data. The historical climate environment refers to the historical climate temperature and historical weather, and the historical vehicle operation status refers to the historical in-vehicle temperature, the historical outside vehicle temperature, the historical in-vehicle humidity, and the historical vehicle power; in other embodiments, the historical vehicle operation status may also include the historical outside vehicle rainfall. The historical air conditioning setting parameters are characterized by the air conditioning setting parameters under the conditions of historical vehicle user characteristics, historical air conditioning feedback adjustment data, historical climate environment, and historical vehicle operation status.

[0039] In this embodiment, the setting types of air conditioning parameters corresponding to the vehicle air conditioner may include multiple types, namely, air conditioning switch, seat heating, blowing mode, air conditioning temperature, air conditioning air volume, temperature adjustment mode and circulation mode. The air conditioning switch indicates whether the air conditioning is turned on, and the seat heating indicates whether the seat heating is turned on, and the specific heating value of the seat heating. The circulation mode may include internal circulation and external circulation, and the temperature adjustment mode may include a preset rapid temperature adjustment mode and a preset normal temperature adjustment mode. The preset rapid temperature adjustment mode may include a rapid heating mode and a rapid cooling mode. The temperature change rate of the preset normal temperature adjustment mode is less than that of the preset rapid temperature adjustment mode.

[0040] The blowing mode may include downward blowing and upward blowing, etc., which may be specifically determined based on the vehicle signal. Different vehicle models may include different blowing modes, and this embodiment does not specifically limit this.

[0041] The historical vehicle user characteristics refer to the characteristics of the user corresponding to the sub-usage data, and the historical vehicle user characteristics include at least one of the age, gender, historical month, historical vehicle latitude, and historical user behavior of the user corresponding to the sub-usage data. The historical month refers to the month corresponding to the sub-usage data, and the historical user behavior is characterized by the operation behavior of the vehicle air conditioner when the user just enters the vehicle. The historical vehicle latitude represents the latitude corresponding to the sub-usage data. The climates at different latitudes are different, and the climates of areas with similar latitudes are also similar. Therefore, when determining similar users, similar users of vehicle users can also be matched based on latitude to improve the accuracy of determining similar users of vehicle users. In other embodiments, the historical vehicle user characteristics may also include historical clothing thickness. The historical clothing thickness represents the thickness of the clothing worn by the user corresponding to the sub-usage data, and the clothing thickness can be obtained by identifying the preset visual macro model. For example, a device that can take images is provided in the car, and the image of the user can be taken, and the image of the user is input into the preset visual macro model, and the thickness of the user's clothing is output through the preset visual macro model.

[0042] The target user group includes the vehicle users corresponding to the vehicle air conditioner and the same type of users as the vehicle users. The same type of users are users similar to the vehicle users. Specifically, the corresponding same type of users can be found based on the vehicle user characteristics corresponding to the vehicle users. The corresponding same type of users can be found based on the age, gender and vehicle latitude in the vehicle user characteristics corresponding to the vehicle users. For example, users who are in the same age group and gender as the vehicle user and whose absolute value of the difference between the latitudes of the two vehicles is less than or equal to the preset latitude threshold can be regarded as the same type of users as the vehicle user. Then, the historical air conditioning usage data of the same type of users can be obtained, which is also convenient for enriching the training data and helps to improve the accuracy of subsequent model training. Different ages can be divided into different age groups based on actual conditions. For example, the age groups can be divided into 18-25, 26-30, 31-35, 36-40, 41-45, 46-50, etc. This embodiment does not make specific limitations on this. When the absolute value of the difference between the vehicle latitude of a similar user and the vehicle user is less than the preset latitude threshold, it means that the latitudes of the similar user and the vehicle user are not much different, and the climate environment of the two regions is the same, so the historical air-conditioning usage data of the similar user can also be used as training data.

[0043] In other embodiments, the corresponding similar users can also be found according to the age, gender, vehicle latitude, month and clothing thickness in the vehicle user characteristics, wherein the process of finding similar users corresponding to age, gender and vehicle latitude has been described above, and this embodiment will not be repeated, and then the vehicle users can be in the same age group, gender and absolute value of the difference between the two vehicle latitudes less than or equal to the preset latitude threshold, if the absolute value of the difference between the two clothing thicknesses is less than the preset clothing difference threshold, the user belonging to the same month and / or the same season as the month corresponding to the vehicle user is regarded as a similar user. In other embodiments, the similar users of the vehicle user can also be found in combination with the user behavior, and this embodiment does not make specific restrictions on this. Therefore, in this embodiment, the similar users can be users with the same gender, age group and similar vehicle latitude as the vehicle user. In other embodiments, the similar users can also be users with the same gender, age group, vehicle latitude, clothing thickness and month as the vehicle user, or the similar users can also be users with the same gender, age group, vehicle latitude, clothing thickness and season as the vehicle user. It can also be users with the same vehicle gender, the same age group, similar vehicle latitude, similar clothing thickness, and the same vehicle signal.

[0044] Exemplarily, historical usage data of a vehicle user is obtained, and multiple similar users are searched based on the vehicle user's vehicle user characteristics, and the historical usage data corresponding to each similar user is obtained, and the historical usage data of the vehicle user and the historical usage data of all similar users are used as the air conditioning historical usage data, wherein the historical usage data of the vehicle user includes multiple sub-usage data, and the historical usage data of the similar users also includes multiple usage data.

[0045] Step A20, screening out a credible training sample set from the historical usage data of the air conditioner based on a plurality of preset large models; It should be noted that the credible training sample set is characterized as reasonable sub-usage data, and each preset large model can filter out the credible training sample set from the air conditioner usage data based on its own powerful semantic understanding ability. In order to ensure the accuracy of the credible training sample set, at least three different preset large models can be used to filter the air conditioner historical usage data in this embodiment, and the three different preset large models are characterized by different technical architectures of the large models, and each preset large model can be the latest and optimal model version under the corresponding technical architecture. For example, different preset large models can be deepseek-R1, Doubao and kimi. This embodiment does not make specific limitations on this.

[0046] Exemplarily, the historical usage data of the air conditioner is input into each preset large model, and a credible training sample set is screened out through all the preset large models.

[0047] In a feasible embodiment, step A20 further includes steps A21 and A22: Step A21, for each preset large model, input the historical usage data of the air conditioner into the preset large model, remove the abnormal sub-usage data in the historical usage data of the air conditioner through the preset large model, and obtain a normal usage data set filtered from the historical usage data of the air conditioner by the preset large model; Step A22: extract target normal data contained in all normal use data sets to obtain a credible training sample set.

[0048] It should be noted that the air conditioner historical usage data includes multiple sub-usage data, and the abnormal usage data is the abnormal sub-usage data. The normal usage data set is a collection of multiple normal data. Each preset large model can output its corresponding normal usage data set, and the normal usage data set output by each preset large model may be different.

[0049] Each piece of sub-usage data is the actual operation behavior of the vehicle user on the vehicle air conditioner. There are many unreasonable air conditioner operation behaviors in the actual user behavior, but they cannot be cleaned according to the rules. If these unreasonable air conditioner operation behaviors are also used as samples for training the model, the model will also predict unreasonable air conditioner operation behaviors, and it will be difficult to automatically set the best parameters for the vehicle air conditioner for the user. Therefore, this embodiment cleans and filters the historical air conditioner usage data through multiple preset large models. Each preset large model can remove abnormal usage data of the historical air conditioner usage data, and then filter out the normal usage data set.

[0050] Although multiple preset big models are all big language models, different big language models may not have the same semantic understanding capabilities. In this embodiment, in order to avoid the situation where there is a deviation in the training samples caused by the screening of a single big model, multiple preset big models can be used for joint screening. For example, the optimal big language models of multiple third-party big model suppliers can be used as each preset big model, and the historical usage data of the same air conditioner can be screened. The data that each preset big model considers to be credible and reasonable can be retained as a feasible training sample set.

[0051] The target normal data is characterized as the sub-usage data that all preset large models consider to be normal. The normal usage data sets corresponding to all preset large models include the target normal data. Each target normal usage data can constitute a credible training sample set, thereby improving the credibility and rationality of the credible training sample set, and further facilitating the subsequent improvement of the accuracy of vehicle air-conditioning parameter prediction.

[0052] Exemplarily, the historical usage data of the air conditioner is input into each preset large model respectively. For each preset large model, the abnormal usage data in the historical usage data of the air conditioner is removed by the preset large model to obtain the normal usage data set screened by the preset large model, and the target normal data contained in all normal usage data sets are extracted from all normal data sets to obtain a credible training sample set. This ensures the credibility of the sample set, which facilitates improving the accuracy of subsequent model training.

[0053] Step A30, determining a preset air conditioning prediction model based on the credible training sample set and the initial air conditioning prediction model.

[0054] It should be noted that the credible training sample set can be used to train the initial air conditioning prediction model, and then determine the trained preset air conditioning prediction model. The initial air conditioning prediction model can also be a large language model, and the preset air conditioning prediction model also belongs to the large language model, which helps to improve the prediction accuracy of the vehicle air conditioning setting parameters.

[0055] Exemplarily, feature extraction may be performed on a credible training sample set, and an initial air-conditioning prediction model may be trained based on the feature-extracted data to determine a preset air-conditioning prediction model.

[0056] In a feasible embodiment, step A30 further includes steps A31 to A33: Step A31, extracting scene features from the credible training sample set to obtain a plurality of scene parameter training features, wherein each scene parameter training feature includes a scene training feature and an air conditioning parameter setting feature associated with the scene training feature, the scene training feature includes at least one of the following: a training vehicle user feature, training air conditioning feedback adjustment data, a training environment, and a training vehicle operating state, and the air conditioning parameter setting feature includes at least one of the following: an air conditioning switch setting parameter, a seat heating setting parameter, a blowing setting parameter, an air conditioning temperature setting parameter, an air conditioning air volume setting parameter, a temperature adjustment mode setting parameter, and a circulation mode setting parameter; It should be noted that the credible training sample set includes a large amount of target normal usage data. In each target normal usage data, there may be multiple target similar normal usage data with the same historical air conditioning setting parameters. Therefore, scene feature extraction can be performed on the multiple target similar normal data to extract the commonality of the multiple target similar normal data, so that the scene parameter training features corresponding to the multiple target similar normal data can be obtained. In this embodiment, multiple scene parameter training features can be screened out from the credible training samples.

[0057] Different scene parameter training features correspond to different scenes, and different scenes correspond to different air conditioning parameter setting features. The air conditioning parameter setting features in each scene parameter training feature can be characterized as the parameters corresponding to the vehicle air conditioning settings in the corresponding scene, for example, air conditioning switch setting parameters, seat heating setting parameters, blowing setting parameters, air conditioning temperature setting parameters, air conditioning air volume setting parameters, temperature adjustment mode setting parameters and / or circulation mode setting parameters, etc. The air conditioning parameter setting features can be determined based on the historical air conditioning setting parameters in similar multiple target similar normal use data. The historical air conditioning setting parameters of multiple target similar normal use data are also similar. For example, the historical air conditioning setting parameters can be the same, or the average value of each historical air conditioning setting parameter can be taken as the air conditioning setting parameter. The air conditioning switch setting parameter represents the setting of the vehicle air conditioning switch, the seat heating setting parameter represents the setting of the seat heating switch, the blowing setting parameter represents the setting of the blowing direction, the air conditioning temperature setting parameter represents the setting of the vehicle air conditioning temperature, the air conditioning air volume setting parameter represents the setting of the air volume of the vehicle air conditioning, the temperature adjustment mode setting parameter represents the setting of the temperature adjustment mode of the vehicle air conditioning, such as rapid heating and cooling, etc., and the circulation mode setting parameter represents the setting of the circulation mode of the vehicle air conditioning, such as internal circulation and external circulation, etc.

[0058] The scene training features in each scene parameter training feature can be reflected in the scene corresponding to the air conditioning parameter setting feature. The scene training features include the training vehicle user features, training air conditioning feedback adjustment data, training climate environment and training vehicle operating environment corresponding to the air conditioning parameter setting feature. Since the scene training features are extracted from multiple target similar normal data, the training vehicle user features in the scene training features are the commonality of the historical vehicle user features corresponding to the multiple target similar normal data. Generally, the historical vehicle user features of the multiple target similar normal data are the same, or the age, gender and vehicle latitude in the historical vehicle user features are the same. The training vehicle user features can also include age, gender and vehicle latitude, etc. The training air conditioning feedback adjustment data, training climate environment and training vehicle operating environment are all the same data extracted from the target similar normal data. For example, the historical air conditioning feedback adjustment data, historical climate environment and historical vehicle operating status in the multiple target similar normal data are the same, so that the corresponding training air conditioning feedback adjustment data, training climate environment and training vehicle operating environment can be extracted.

[0059] For example, in this embodiment, the environmental scene features corresponding to the rapid temperature rise can be extracted from the credible training sample set, and the air conditioning setting parameter features corresponding to the rapid temperature rise and the environmental scene features can be used as a scene parameter training feature. The environmental scene features corresponding to the rapid temperature drop can also be extracted from the credible training sample set, and the air conditioning setting parameter features corresponding to the rapid temperature drop and the environmental scene features can be used as another scene parameter training feature. The environmental scene features corresponding to each of the other different air conditioning setting parameter features can also be extracted to construct the corresponding scene parameter training features, which is not specifically limited in this embodiment.

[0060] Exemplarily, extraction data sets corresponding to different historical air-conditioning setting parameters can be extracted from credible training samples. For each different historical air-conditioning setting parameter, there is a corresponding extraction data set. Each extraction data set can include multiple target normal usage data. The historical air-conditioning setting parameters of each target normal usage data in the same extraction data set are the same. For the same extraction data set, the historical air-conditioning setting parameters of any target normal usage data in the extraction data set can be used as air-conditioning parameter setting features, and then the commonalities of historical vehicle user characteristics, historical air-conditioning feedback adjustment data, historical climate environment and historical vehicle operating status in each target normal usage data are extracted in the extraction data set, so as to obtain training vehicle user characteristics, training air-conditioning feedback adjustment data, training climate environment and training vehicle operating environment corresponding to the air-conditioning parameter setting features.

[0061] Multiple scene parameter training features can each correspond to a different scene, and different scenes correspond to different air conditioning setting parameters. This embodiment extracts multiple scene parameter training features from the credible training sample set, so that the initial air conditioning prediction model can be trained to learn the air conditioning setting parameters in different scenes. As a result, the final preset air conditioning prediction model can cope with the air conditioning setting parameters in different scenes, thereby facilitating the improvement of the intelligence of the vehicle air conditioning and ensuring the comfort of the user.

[0062] Step A32, training the initial air conditioning prediction model based on multiple scene parameter training features to obtain a trained teacher model; Step A33, obtaining a student model whose parameter magnitude is smaller than that of the teacher model, and updating the student model through the teacher model, and using the updated student model as the preset air conditioning prediction model.

[0063] It should be noted that the initial air conditioning prediction model can be a large language model. The parameter magnitude of the teacher model is greater than that of the student model. The parameter magnitude is the order of magnitude of the model training parameters (i.e., the size range of the quantity). The parameter magnitude can reflect the scale of the model. The larger the parameter magnitude, the larger the scale of the model, and the smaller the parameter magnitude, the smaller the scale of the model. The scale of the student model is smaller than that of the teacher model, and the student model also belongs to the large language model. For example, the teacher model can be a 70B (Billion) large language model, and the student model can be a 1.5B large language model. The model output is characterized by the output distribution of the teacher model.

[0064] The initial air conditioning prediction model can be trained based on a large number of scene parameter training features. For example, the scene training features in the scene parameter training features can be input into the initial air conditioning prediction model. The initial air conditioning prediction model outputs the air conditioning parameter results. The model error between the air conditioning parameter results and the air conditioning parameter setting features in the scene training features can be calculated. If the model error is less than the preset loss threshold, a trained teacher model can be obtained. If the model error is greater than or equal to the preset loss threshold, new scene parameter training features can be re-input into the model to be trained until the model error is less than the preset loss threshold. The preset loss threshold can be set based on actual conditions, and this embodiment does not specifically limit this.

[0065] This embodiment obtains a student model with a smaller parameter magnitude than the teacher model, so that the air-conditioning parameters can be predicted more accurately while further reducing the parameter magnitude. This embodiment is based on the principle of model distillation. Model distillation (ModelDistillation) is a technology that transfers the knowledge of a complex model (teacher model) to a simple model (student model). Its core principle is to significantly reduce the computational complexity of the student model while maintaining high performance by imitating the output distribution of the teacher model. Therefore, this embodiment obtains a student model with a smaller parameter magnitude than the teacher model, and learns the model output of the teacher model through the student model, so that the student model can imitate the output of the teacher model and reduce the complexity at the same time, and then the completed learning model can be used as the preset air-conditioning prediction model.

[0066] Therefore, the preset air-conditioning prediction model can be deployed in the vehicle. Since the preset air-conditioning prediction model can reduce the computational complexity while maintaining a high prediction accuracy, the preset air-conditioning prediction model can also be supported on the vehicle side, which will not bring greater operating pressure to the vehicle side, and thus facilitate improving the prediction efficiency of the vehicle air-conditioning parameters and improving the user experience.

[0067] For a better understanding of this embodiment, please refer to Figure 3 , Figure 3The flowchart is as follows: determining the target air conditioning parameters and controlling the operation of the vehicle air conditioning according to the target air conditioning parameters; briefly describing the process from model training to model prediction in this embodiment, step N1: obtaining the historical usage data of the air conditioning; step N2: multiple preset large models screen the historical usage data of the air conditioning to obtain a credible training sample set; step N3: extracting features from the credible training sample set to obtain a large number of scene parameter training features; step N4: using a large number of scene parameter training features to train the initial air conditioning prediction model and determine the preset air conditioning prediction model; step N5: deploying the preset air conditioning prediction model in the vehicle and periodically updating the preset air conditioning prediction model; periodically updating the preset air conditioning prediction model can be obtaining new usage data of the vehicle air conditioning, and then using the new usage data to update the preset air conditioning prediction model, thereby helping to improve the prediction accuracy of the preset air conditioning prediction model. This embodiment does not limit the period for updating the preset air conditioning prediction model, which can be set based on actual conditions. Step N6: obtain the current environment, the current vehicle operating state and the vehicle user characteristics; Step N6 is combined with the preset air conditioning prediction model in step N5, and the target air conditioning parameters under the current environment, the current vehicle operating state and the vehicle user characteristics are determined by the preset air conditioning prediction model; for example, step N7: determine the target air conditioning parameters; step N8: control the operation of the vehicle air conditioning according to the target air conditioning parameters. In addition, it should be noted that if the preset air conditioning prediction model is not sure what target air conditioning parameters correspond to the current environment, the current vehicle operating state and the vehicle user characteristics, the teacher model in the cloud can be called to determine the target air conditioning parameters under the current environment, the current vehicle operating state and the vehicle user characteristics. Because the preset air conditioning prediction model is deployed offline on the vehicle side, the scene of the target air conditioning parameters that can be predicted by the preset air conditioning prediction model is the scene that exists in the credible training sample set, and because the preset air conditioning prediction model belongs to the student model, the parameter magnitude of the student model is small, so the preset air conditioning prediction model may have a situation where the target air conditioning parameters in individual scenes cannot be accurately determined, so the teacher model in the cloud can be called for prediction. Although the preset air-conditioning prediction model may have some individual scenarios where it is difficult to accurately predict the target air-conditioning parameters, this does not mean that the preset air-conditioning prediction model can predict few scenarios, because in this embodiment, a large number of scene parameter training features can be extracted from the trusted training sample set, and thus the preset air-conditioning prediction model can predict the corresponding target air-conditioning parameters in a large number of scenarios.

[0068] In a feasible embodiment, the target air conditioning parameter includes at least one of a target air conditioning switch parameter, a target seat heating parameter, a target blowing mode, a target air conditioning temperature, a target air conditioning air volume, a target circulation mode, and a target temperature adjustment mode; step S30 also includes step S31: inputting the current environment, the current vehicle operating state, and the vehicle user characteristics into a preset air conditioning prediction model, and determining the target air conditioning switch parameter, the target seat heating parameter, the target blowing mode, the target air conditioning temperature, the target air conditioning air volume, the target circulation mode, and / or the target temperature adjustment mode under the current environment, the current vehicle operating state, and the vehicle user characteristics through the preset air conditioning prediction model; Among them, the current environment includes: at least one of the current weather, the current temperature outside the vehicle, the current temperature inside the vehicle, the current humidity inside the vehicle, the current rainfall outside the vehicle, the current external environment image and the current internal environment image; the current vehicle operating status includes the current vehicle power; the vehicle user characteristics include the vehicle user's age, gender, current usage month, current vehicle latitude and at least one of the user's behavior.

[0069] It should be noted that the target air conditioning switch parameter can be on or off, etc. When the target air conditioning switch parameter is on, it indicates that the vehicle air conditioning is turned on, and when the target air conditioning switch parameter is off, it indicates that the vehicle air conditioning is turned off. The target seat heating parameter can be to turn on the seat heating or turn off the seat heating, etc. The target blowing mode can be to blow upward or blow downward, etc. The air conditioning blowing control parameters at different locations in the vehicle can be different or the same.

[0070] The target air conditioning temperature may be a specific set temperature of the vehicle air conditioning; the target air conditioning air volume may be a specific set air volume of the vehicle air conditioning, and the set air volumes at different locations in the vehicle may be different or the same. The target circulation mode may be to set the vehicle air conditioning to internal circulation or external circulation, etc., and the target temperature adjustment mode may be to set the vehicle air conditioning to perform preset rapid temperature adjustment or preset normal temperature adjustment, etc.

[0071] The current environment, the current vehicle operating status, and the vehicle user characteristics will all affect the target air conditioning parameters. The vehicle user characteristics may refer to the characteristics of the driver. For example, when the current climate temperature is less than the preset low temperature threshold and the current clothing thickness is thicker, the vehicle air conditioner can be set to heating mode. The thicker the current clothing thickness, the lower the set temperature can be, and the smaller the set air volume can be. The thinner the current clothing thickness, the higher the set temperature of the vehicle air conditioner can be, and the larger the set air volume can be. When the current climate temperature is greater than the preset high temperature threshold, the vehicle air conditioner can be set to cooling mode. If the current humidity in the car is higher, the air volume can be increased. The set temperature may be different in different months. In addition, even if the age, gender, month, clothing thickness, and user behavior are the same, if the current vehicle latitude is different, the corresponding target air conditioning parameters may be different.

[0072] Exemplarily, the current environment, current vehicle operating status, and vehicle user characteristics are all input into a preset air-conditioning prediction model, and the preset air-conditioning prediction model is used to determine the target air-conditioning switch parameters, target seat heating parameters, target blowing mode, target air-conditioning temperature, and target air-conditioning air volume under the scenarios of the current environment, current vehicle operating status, and vehicle user characteristics.

[0073] In this embodiment, various air-conditioning setting parameters of the vehicle air-conditioning can be determined by presetting a large air-conditioning model, thereby eliminating the need for manual setting, thereby improving the intelligence level of the vehicle air-conditioning and also improving the comfort of the user.

[0074] For a better understanding of this embodiment, please refer to Figure 4 , Figure 4 The flowchart is as follows: a preset air conditioning prediction model is trained and a target air conditioning parameter is predicted by the preset air conditioning prediction model. The process of determining the target air conditioning parameter in this embodiment is briefly described: the air conditioning historical usage data may include historical vehicle user characteristics, historical air conditioning feedback adjustment data, historical air conditioning setting parameters, historical climate environment and historical vehicle operation status. The historical air conditioning feedback adjustment data may be the user's historical air conditioning feedback adjustment behavior. The historical vehicle user characteristics may also include user historical behavior, and the user historical behavior may refer to the user's behavior of adjusting the air conditioning for the first time after getting on the car. A credible training sample set of the air conditioning historical usage data can be determined. Feature extraction refers to extracting a large number of scene parameter training features from the credible training sample set. The scene parameter training features extracted from the credible training sample set can be used to train the initial air conditioning prediction model to obtain a trained teacher model, and the student model is used to learn the teacher model to obtain the preset air conditioning prediction model. When training the initial air conditioning prediction model, the data format of the data input into the initial air conditioning prediction model needs to be consistent with the data format input into the preset air conditioning prediction model, and the data format needs to comply with the specifications of the vehicle-side interface, so that the vehicle can receive the target air conditioning parameters output by the preset air conditioning prediction model. The real-time data may include vehicle user characteristics, current environment, and current vehicle operating status, wherein the vehicle user characteristics include user behavior, and the user behavior may be the user's current behavior or historical behavior. For example, when the user has no current behavior, the user behavior is historical behavior, and the historical behavior may include the user's historical air conditioning feedback adjustment behavior. Inputting the real-time data into the preset air conditioning prediction model may obtain the target air conditioning parameters, which may include: target air conditioning switch parameters, target seat heating parameters, target blowing mode, target air conditioning temperature, target air conditioning air volume, target temperature adjustment mode, and target circulation mode.

[0075] In a feasible embodiment, the vehicle air conditioning control method further includes step X10: in a preset driving scenario, if the current outside temperature of the vehicle is greater than a preset high temperature threshold, the output of the preset air conditioning prediction model includes: the target air conditioning switch parameter is on, the target air conditioning air volume includes increasing the air volume, and / or the target blowing mode includes blowing downward and / or blowing cold air; In a preset driving scenario, if the current outside temperature is less than a preset low temperature threshold, the output of the preset air conditioning prediction model includes: the target air conditioning switch parameter is on, the target air conditioning air volume includes increasing the air volume, and / or the target blowing mode includes blowing downward and / or blowing hot air; Among them, the preset driving scenarios include: the current weather is rainy, the current humidity inside the car is greater than the preset humidity threshold, the current rainfall outside the car is greater than the preset rainfall threshold, and / or the amount of water detected in the current external environment image is greater than the preset water threshold.

[0076] It should be noted that when the current weather is rainy, it means that it is raining in the area where the vehicle is located. Therefore, when the person who needs to take the vehicle just enters the vehicle, the shoes or trouser legs and other body parts may be wet by the rain. For example, it may be detected that the current humidity in the vehicle is greater than the preset humidity threshold. At this time, the air volume can be increased and the air can be blown downward, so as to help the user dry the shoes and / or trouser legs and other body parts, thereby improving the comfort of the people in the vehicle. When the humidity in the vehicle is greater than the preset humidity threshold, it means that the humidity in the vehicle is high and the people in the vehicle may be wet by the rain, for example, the shoes and / or trouser legs and other parts.

[0077] It is also possible to turn on the vehicle air conditioner, increase the air volume, and blow air downward when it is detected that the rainfall outside the vehicle is greater than the preset rainfall threshold, so as to facilitate timely drying of body parts such as shoes and / or trouser legs for passengers in the vehicle. For example, when it is detected that the current weather in the area where the vehicle is located is cloudy and the probability of rain is 50%, it may not be possible to determine whether it is raining at the current location of the vehicle based on the current weather alone. Therefore, it is possible to determine whether it is raining at the location of the vehicle based on the rainfall outside the vehicle, thereby facilitating the improvement of the accuracy of the preset air conditioning prediction model prediction, and also facilitating the determination of the preset target value of the air conditioning air volume and the specific setting parameters of the vehicle air conditioner based on the vehicle rainfall. This not only improves the accuracy of the vehicle air conditioning parameter settings, but also improves the riding comfort of the passengers in the vehicle.

[0078] It is also possible to turn on the vehicle air conditioner, increase the air volume, and blow air downward when it is detected that the amount of water in the current vehicle exterior environment image is greater than the preset water accumulation threshold, so as to facilitate timely drying of body parts such as shoes and / or trouser legs for passengers in the vehicle. The preset water accumulation threshold and the preset rainfall threshold can be set based on actual conditions, and this embodiment does not make specific restrictions on this. The water accumulation area in the current vehicle exterior environment image can be detected by a preset air conditioning prediction model, so as to detect the amount of water accumulation in the preset air conditioning prediction model through the water accumulation area, and then the vehicle air conditioner can be turned on in time, increase the air volume, and blow air downward when the amount of water accumulation is greater than the preset water accumulation threshold. For example, the water accumulation area in the water accumulation area in the current vehicle exterior environment image can be detected, and the water accumulation area can be used as the amount of water accumulation. In other embodiments, the water accumulation depth in the water accumulation area can also be detected, and the water accumulation amount can be calculated based on the water accumulation depth and the water accumulation area. This embodiment does not make specific restrictions on this. In other embodiments, the current vehicle exterior environment image can also be detected by calling a preset visual large model to detect the amount of water accumulation in the current vehicle exterior environment image.

[0079] Increasing the air volume can be characterized as a continuous increase in the air volume. In other embodiments, increasing the air volume can include increasing the air conditioning air volume to a preset target value, which is also the output of a preset air conditioning prediction model; blowing air downward helps dry trouser legs or shoes, etc.

[0080] Exemplarily, when the current weather is rainy, the current humidity inside the car is greater than the preset humidity threshold, the current rainfall outside the car is greater than the preset rainfall threshold, and / or the amount of water accumulated in the current image of the vehicle's environment is detected to be greater than the preset water accumulation threshold, if the current temperature outside the car is greater than the preset high temperature threshold, it means that the current temperature outside the car is high, and there may be a situation where wet shoes are getting on the car, so the output of the preset air conditioning prediction model includes: the target air conditioning switch parameter is turned on, the target air conditioning air volume includes increasing the air volume, the target blowing mode includes blowing downwards, and / or the target blowing mode includes blowing downwards and / or blowing cold air; blowing cold air is convenient for providing a more comfortable environment for users, avoiding the passengers in the car from being hot and humid, resulting in a poor riding experience for the passengers in the car. In other embodiments, the output of the preset air conditioning prediction model may also include: the target air conditioning temperature includes lowering the temperature to create a more comfortable riding environment for the passengers in the car.

[0081] In the case where the current weather is rainy, the current humidity inside the car is greater than the preset humidity threshold, the current rainfall outside the car is greater than the preset rainfall threshold, and / or the amount of water accumulated in the current image of the vehicle's external environment is detected to be greater than the preset water accumulation threshold, if the current temperature outside the car is less than the preset low temperature threshold, it means that the current climate temperature is low and there may be a situation where wet shoes are getting on the car, so the output of the preset air conditioning prediction model includes: the target air conditioning switch parameter is turned on, the target air conditioning air volume includes increasing the air volume, and / or the target blowing mode includes blowing downward and / or blowing hot air; thereby facilitating the blowing of hot air when the temperature is low, so as to help the occupants in the car quickly dry the wet body parts and improve the comfort of the human body. In other embodiments, the output of the preset air conditioning prediction model may also include: the target air conditioning temperature includes increasing the temperature to create a more comfortable riding environment for the occupants in the car.

[0082] This embodiment automatically dries the wetted passengers in the car in rainy days or when there is a lot of water outside the car, so as to improve the riding comfort of the passengers in the car. In addition, since this application can also determine the specific setting parameters of the car air conditioner in combination with the rainfall outside the car, the accuracy of the prediction of the car air conditioner parameters can be improved. Because the current weather is obtained through the weather API interface, and the data source of the weather API interface is the Meteorological Bureau, and the Meteorological Bureau generally estimates the overall weather conditions of the region, and different weather conditions may exist in the same region at the same time, for example, it may be cloudy and rainy at the same time, so in this embodiment, the rainfall outside the car is combined to improve the accuracy of the prediction of the car air conditioner parameters. This embodiment can provide a more comfortable experience for users who get on the car on rainy days.

[0083] In another feasible embodiment, the vehicle air conditioning control method further includes step Y10: when it is detected that the outdoor air quality in the current outdoor environment image is less than a preset quality standard, the output of the preset air conditioning prediction model includes the target circulation mode being internal circulation.

[0084] It should be noted that the current image of the outside environment can be obtained in real time, so it is convenient to detect the outside air quality in real time during the driving process of the vehicle. The outside air quality can reflect the outside air condition of the vehicle during the driving process. When the outside air quality is relatively poor, the circulation mode of the vehicle air conditioner can be adjusted to internal circulation to avoid the air inside the vehicle being polluted by the outside, thereby facilitating the improvement of the riding comfort of the passengers inside the vehicle.

[0085] The air quality outside the vehicle of the current vehicle exterior environment image can be detected by the preset air conditioning prediction model. For example, the facility pollution type of the building facilities in the current vehicle exterior environment image, the road dust concentration in the current vehicle exterior environment image, and / or the cloud color in the current vehicle exterior environment image can be detected. The detected facility pollution degree, road dust concentration and / or cloud color can be used to determine whether the air quality outside the vehicle is less than the preset quality standard. For example, if the facility pollution type is detected as an air pollution building, it can be determined that the air quality outside the vehicle is less than the preset quality standard. If the road dust concentration is detected to be greater than the preset concentration threshold, it can be determined that the air quality outside the vehicle is less than the preset quality standard. If the cloud color is detected to be gray or yellow, it can also be determined that the air quality outside the vehicle is less than the preset quality standard. The preset quality standard, the preset concentration threshold, etc. can be determined based on actual conditions, and this embodiment does not make specific settings for this.

[0086] The road dust concentration can reflect the environmental quality of the road and the degree of air pollution. The road dust concentration can also be reflected in the outdoor environment image, which can be specifically manifested as dust or haze visible in the image. Therefore, the preset air-conditioning prediction model can identify the road dust concentration in the current vehicle external environment image by detecting the distribution of dust in the outdoor environment image, or detecting the density of dust or the density of haze.

[0087] The facility pollution type of building facilities can reflect the pollution sources existing in the driving environment or the characteristics that affect the environment. The facility pollution types can include chemical plants, garbage stations, civil engineering, high-rise buildings and other facilities. Civil engineering indicates that the road is under construction, so there will be air pollution.

[0088] The circulation mode of the vehicle air conditioner can include internal circulation and external circulation. The internal circulation refers to circulating only the air inside the vehicle; the external circulation refers to introducing new air from outside the vehicle, filtering and adjusting it, and then sending it into the vehicle to achieve the renewal and ventilation of the air inside the vehicle. The internal circulation can be used in scenarios where the external air quality is poor or the temperature inside the vehicle needs to be adjusted quickly, while the external circulation can be used in scenarios where the air quality inside the vehicle needs to be improved or the external environment is relatively fresh. Therefore, in this embodiment, when the air quality outside the vehicle is less than the preset quality standard, the circulation mode of the vehicle air conditioner is controlled to be internal circulation, which can prevent the air inside the vehicle from being polluted by the air outside the vehicle.

[0089] Air pollution buildings are characterized as buildings that reduce air quality. The preset air conditioning prediction model can identify whether the facility pollution type of the building facilities belongs to air pollution buildings. For example, chemical plants, garbage stations, and civil engineering belong to air pollution buildings. The preset concentration threshold can be set based on actual conditions, and this embodiment does not specifically limit this.

[0090] Exemplarily, the current external environment image during vehicle driving is acquired in real time, and the facility pollution type of the building facilities in the current external environment image is detected by a preset air conditioning prediction model. If the facility pollution type is an air pollution building, it can be determined that the air quality outside the vehicle is less than the preset quality standard; and / or, the road dust concentration in the current external environment image is detected by a preset air conditioning prediction model. If the road dust concentration is greater than a preset concentration threshold, it can be determined that the air quality outside the vehicle is less than the preset quality standard; and / or, the cloud color in the current external environment image is detected by a preset air conditioning prediction model. If the cloud color is gray or yellow, it can be determined that the air quality outside the vehicle is less than the preset quality standard. In the case where the air quality outside the vehicle is less than the preset quality standard, the output of the preset air conditioning prediction model includes the target circulation mode being internal circulation.

[0091] This embodiment detects the quality of the air outside the vehicle in real time while the vehicle is driving, so that when the quality of the air outside the vehicle is poor, the circulation mode of the vehicle can be dynamically switched to internal circulation, thereby ensuring the comfort of the passengers in the vehicle. At the same time, there is no need for manual identification of whether to switch to internal circulation, and no manual operation is required, thereby improving the intelligence of the vehicle air conditioner.

[0092] In another feasible embodiment, the vehicle air conditioning control method further includes step Z10: when the absolute value of the difference between the target comfort temperature corresponding to the current clothing thickness of the vehicle occupant detected in the current vehicle interior environment image and the current vehicle interior temperature is greater than a preset temperature difference threshold, and the vehicle is in a preset rapid temperature adjustment mode, and the temperature adjustment time from the current vehicle interior temperature to the target comfort temperature is less than the estimated driving time of the vehicle, determining the output of the preset air conditioning prediction model includes: the target temperature adjustment mode includes a preset rapid temperature adjustment mode, and the target air conditioning temperature includes adjusting the current vehicle interior temperature to the target comfort temperature; Among them, the target comfort temperature is obtained by adjusting the preset standard body comfort temperature based on the current clothing thickness to obtain the initial comfort temperature, and the initial comfort temperature is adjusted according to the temperature preference of the occupants in the car.

[0093] It should be noted that the current in-car environment image is detected by an image detection device in the car, and the current in-car environment image can reflect the clothing of the in-car occupants, and the current clothing thickness can be determined by detecting the clothing of the in-car occupants in the current in-car environment image. The preset air conditioning prediction model can identify the clothing of the in-car occupants in the current in-car environment image. When there are multiple passengers in the car, the current in-car environment image including all passengers in the car can be obtained, and the current in-car environment image including all passengers can be obtained by splicing multiple seat images, and the seat image is also obtained by the image detection device in the car. Each seat in the car can be provided with an image detection device so that the seat image corresponding to each seat can be obtained. When there are occupants in the seat, the seat corresponding to the image includes the occupant. When there are multiple in-car occupants in the car, the current clothing thickness of the driver in the current in-car environment image can be identified, the current clothing thickness of any passenger in the car can also be identified, and the current clothing thickness of passengers in the car whose age is greater than a preset high-age threshold can also be identified, and / or the current clothing thickness of passengers in the car whose age is less than a preset low-age threshold can be identified. The preset high age threshold and the preset low age threshold can be set based on actual conditions, and this embodiment does not make any specific limitation on this.

[0094] When there are multiple passengers in the car, the target comfort temperature may correspond to the current clothing thickness of any of the passengers in the car, for example, the current clothing thickness of the driver, the current clothing thickness of passengers in the car whose age is greater than a preset high-age threshold, or the current clothing thickness of passengers in the car whose age is less than a preset low-age threshold. The specific thickness may be determined based on actual conditions, and this embodiment does not specifically limit this. The preset air conditioning prediction model may identify the current clothing thickness of the passengers in the car by identifying the coats worn by the passengers in the car.

[0095] The target comfort temperature represents the comfortable temperature that the human body can feel under the current clothing thickness. Based on the current clothing thickness, the preset standard body comfort temperature can be adjusted to obtain the initial comfort temperature, and based on the acquired temperature preference of the occupants in the vehicle, the initial comfort temperature can be adjusted to obtain the target comfort temperature. Specifically, based on the clothing thermal resistance value corresponding to the current clothing thickness, the difference between the preset standard body comfort temperature and the clothing thermal value corresponding to the current clothing thickness can be calculated to obtain the initial comfort temperature.

[0096] The preset standard comfortable temperature is the suitable temperature perceived by the human body when in a stationary state and without wearing clothes. For example, the preset standard comfortable temperature may be 26°C, 27°C or 28°C, etc. The specific selection may be based on actual conditions, and this embodiment does not make any specific limitation on this.

[0097] The thermal resistance value of clothing is a physical quantity that characterizes the thermal insulation performance of clothing. The thickness or material of clothing is different, and the corresponding thermal resistance value of clothing is also different. Different clothing has its own corresponding clothing thermal resistance value. The preset air conditioning prediction model can determine the corresponding clothing thermal resistance value of clothing by identifying the material and thickness of the clothing. For example, thicker down jackets or wool sweaters have higher thermal resistance values, while thin short-sleeved clothing has lower thermal resistance values. Clothing with different thermal resistance values ​​will affect the human body's perception of environmental temperature, so the thermal resistance characteristics of clothing need to be considered when setting the vehicle air conditioning parameters.

[0098] Temperature preference can include hot, cold and standard. Hot means that the driver may be afraid of cold and tend to set the car air-conditioning temperature to a higher value; cold means that the driver may be afraid of heat and tend to set the car air-conditioning temperature to a lower value; standard means that the temperature demand of the passengers in the car is normal. When the temperature preference is standard, the target comfort temperature is the initial comfort temperature.

[0099] The temperature preference may be pre-set by the vehicle occupant, and options such as cooler, warmer, and standard may be provided for the vehicle occupant to choose. Alternatively, the vehicle occupant's temperature preference may be determined based on the vehicle occupant's historical air conditioning usage data.

[0100] Exemplarily, the difference between a preset standard perceived comfort temperature and the thermal resistance value of clothing corresponding to the current clothing thickness is used as the initial comfort temperature. Different people have different temperature preferences. Therefore, the initial comfort temperature can be adjusted according to the temperature preference. When the temperature preference is on the cold side, the initial comfort temperature can be reduced to obtain the target comfort temperature. For example, the initial comfort temperature can be reduced by 1~3℃, etc. The specific setting can be based on actual conditions. For example, the degree of reduction in the initial comfort temperature can be determined based on the degree of coldness of the occupants in the car (such as the driver). The higher the degree of coldness, the greater the degree of reduction, and the lower the degree of coldness, the less the degree of reduction. The degree of coldness can also be input by the occupants in the car. In other embodiments, the preset default temperature can also be directly reduced. The preset default temperature can be customized. For example, it can be 1, 2, or 3. The difference between the initial comfort temperature and the preset default temperature is the target comfort temperature.

[0101] When the temperature preference is hot, the initial comfort temperature can be increased to obtain the target comfort temperature. The initial comfort temperature can be increased by 1~3℃, etc., which can be set specifically based on the actual situation. For example, the degree of increase in the initial comfort temperature can be determined based on the degree of heat preference of the occupant in the car (for example, the driver). The higher the degree of heat preference, the more the degree is reduced, and the lower the degree of heat preference, the less the degree is reduced. The degree of heat preference can also be input by the occupant in the car. In other embodiments, the preset default temperature can also be directly reduced. The preset default temperature can be customized, for example, it can be 1, 2, or 3. The sum of the initial comfort temperature and the preset default temperature is the target comfort temperature. When the driver's temperature preference is standard, the initial comfort temperature can be directly used as the target comfort temperature. If the thickness of the clothing is less than or equal to the preset thickness threshold, there is no need to determine the target comfort temperature, and the current state of the vehicle air conditioner can be directly maintained.

[0102] When the difference between the target comfort temperature and the current in-car temperature is greater than the preset temperature difference threshold, it means that the current in-car temperature has not reached the target comfort temperature, so the in-car temperature may need to be adjusted. The preset temperature difference threshold can be set based on actual conditions, and this embodiment does not specifically limit this. The preset rapid temperature adjustment mode is one of the temperature adjustment modes of the vehicle air conditioner. The preset rapid temperature adjustment mode represents the rapid adjustment of the in-car temperature. The preset rapid temperature adjustment mode includes a rapid heating mode and a rapid cooling mode.

[0103] The estimated driving time may be the estimated driving time of the vehicle, and the estimated driving time may be determined based on the navigation path of the vehicle. The rapid heating mode represents rapid heating to quickly increase the temperature inside the vehicle. The rapid cooling mode represents rapid cooling to quickly increase the temperature inside the vehicle. The shortest temperature adjustment time is represented by the time required to adjust the current temperature inside the vehicle to the target comfortable temperature in the preset rapid temperature adjustment mode.

[0104] If the absolute value of the difference between the target comfort temperature and the current vehicle interior temperature is greater than the preset temperature difference threshold, and the vehicle is in the preset rapid temperature adjustment mode, and the temperature adjustment time from the current vehicle interior temperature to the target comfort temperature is less than the estimated driving time of the vehicle, it means that the current vehicle interior temperature has not yet reached the comfort temperature, and if the preset rapid temperature adjustment mode is used, the current vehicle interior temperature can be adjusted to the target comfort temperature before the vehicle stops. Therefore, in this scenario, the preset rapid temperature adjustment mode can be used for temperature adjustment.

[0105] Exemplarily, when there are multiple passengers in the vehicle, the target comfort temperature corresponding to the current clothing thickness of any passenger in the vehicle can be determined. When the number of passengers in the vehicle is 1, the target comfort temperature corresponding to the current clothing thickness of the passenger in the vehicle can be directly determined. When the absolute value of the difference between the target comfort temperature and the current vehicle temperature is greater than the preset temperature difference threshold, and the temperature adjustment time from the current vehicle temperature to the target comfort temperature in the vehicle is less than the expected driving time of the vehicle in the preset rapid temperature adjustment mode, the output of the preset air conditioning prediction model is determined to include: the target temperature adjustment mode includes the preset rapid temperature adjustment mode, and the target air conditioning temperature includes adjusting the current vehicle temperature to the target comfort temperature; thus, the current vehicle temperature can be adjusted to a temperature that the passengers in the vehicle feel comfortable before the vehicle stops driving, thereby facilitating improving the user's riding experience. Specifically, when the vehicle air conditioner is currently in the heating mode, the preset rapid temperature adjustment mode can be a rapid heating mode, and when the vehicle air conditioner is currently in the cooling mode, the preset rapid temperature adjustment mode can be a rapid cooling mode.

[0106] Furthermore, this embodiment may also include steps a1 to a4: Step a1, when the vehicle is in the light clothing mode, the driver's clothing thickness is determined from the current in-vehicle environment image by using a preset air conditioning prediction model, wherein the driver's clothing thickness includes the driver's coat thickness and the inner clothing thickness corresponding to the driver's coat thickness and the current climate temperature; It should be noted that the light clothing mode is characterized by the temperature in the car supporting the user to wear thin clothes. The light clothing mode can be turned on manually by the user. After it is turned on once, there is no need to set it again when the vehicle is restarted. The light clothing mode will be turned on automatically. The preset air conditioning prediction model can identify the type of coat worn by the human body in the clothing image, and then identify the thickness of the coat in the clothing image. The driver's clothing thickness includes the thickness of the driver's coat and the thickness of the inner clothes. Since the user is wearing a coat, it may not be possible to detect the inner clothes inside the coat, and it is difficult to identify the thickness of the inner clothes. Therefore, the corresponding inner clothes thickness can be determined based on the current climate temperature. Because the current climate temperature will affect the thickness of the clothes worn by the human body, after determining the thickness of the driver's coat, the corresponding inner clothes thickness can also be determined based on the current climate temperature. The inner clothes thickness may also be different due to different current climate temperatures and different driver coat thicknesses.

[0107] Step a2, if the clothing thickness is greater than a preset thickness threshold, the difference between the preset standard body-felt comfort temperature and the clothing thermal resistance value corresponding to the thickness of the inner clothing is calculated to obtain a first comfortable temperature, and the first comfortable temperature is adjusted according to the obtained driving temperature preference of the driver to obtain a second comfortable temperature of the driver after the thickness of the driver's clothing is reduced; It should be noted that the preset thickness threshold can be set based on actual conditions, and this embodiment does not make specific limitations on this. When the clothing thickness is greater than the preset thickness threshold, it means that the driver may be wearing thicker clothes, which may affect human body movements and may not be very comfortable. Therefore, when this embodiment detects that the clothing thickness is greater than the preset thickness threshold, it determines the second comfortable temperature of the driver after the driver's clothing thickness is reduced, thereby ensuring that the driver will not feel cold after taking off his coat.

[0108] Driving temperature preferences may include hot, cold and standard. Hot indicates that the driver may be afraid of cold and tend to set the car air-conditioning temperature to a higher value; cold indicates that the driver may be afraid of heat and tend to set the car air-conditioning temperature to a lower value; standard indicates that the driver has a normal temperature demand. When the driving temperature preference is standard, the second comfortable temperature is the first comfortable temperature.

[0109] The driver's driving temperature preference may be pre-set by the driver, and options such as cooler, warmer, and standard may be provided for the driver to choose from. Alternatively, the driver's driving temperature preference may be determined based on the driver's historical air conditioning usage data.

[0110] The second comfortable temperature is characterized by a temperature at which the driver will not feel cold after taking off clothes. Reducing the thickness of the driver's clothes generally means that the driver will take off his coat, so the second comfortable temperature can be determined based on the driving temperature preference and the first comfortable temperature, and the first comfortable temperature can be determined based on the thickness of the inner clothes and the preset standard body comfort temperature.

[0111] Exemplarily, if the clothing thickness is greater than a preset thickness threshold, the difference between the preset standard perceived comfort temperature and the clothing thermal resistance value corresponding to the thickness of the inner clothing is used as the first comfort temperature. Different drivers have different corresponding driving temperature preferences. Therefore, the first comfort temperature can be adjusted according to the driving temperature preference to obtain the second comfort temperature of the driver after taking off the coat. When the driver's driving temperature preference is on the cold side, the first comfort temperature can be reduced to obtain the second comfort temperature. For example, the first comfort temperature can be reduced by 1~3℃, etc. The specific setting can be based on actual conditions. For example, the degree of reduction in the first comfort temperature can be determined based on the degree of coldness of the driver. The higher the degree of coldness, the greater the degree of reduction, and the lower the degree of coldness, the less the degree of reduction. The degree of coldness can also be input by the driver. In other embodiments, the preset default temperature can also be directly reduced. The preset default temperature can be customized. For example, it can be 1, 2, or 3. The difference between the first comfort temperature and the preset default temperature is the second comfort temperature.

[0112] When the driver's driving temperature preference is hot, the first comfortable temperature can be increased to obtain the second comfortable temperature. The first comfortable temperature can be increased by 1~3℃, etc., and can be set specifically based on actual conditions. For example, the degree of increase in the first comfortable temperature can be determined based on the driver's degree of hotness. The higher the degree of hotness, the more the degree is reduced, and the lower the degree of hotness, the less the degree is reduced. The degree of hotness can also be input by the driver. In other embodiments, the preset default temperature can also be directly reduced. The preset default temperature can be customized, for example, it can be 1, 2, or 3. The sum of the first comfortable temperature and the preset default temperature is the second comfortable temperature. When the driver's driving temperature preference is standard, the first comfortable temperature can be directly used as the second comfortable temperature. If the thickness of the clothing is less than or equal to the preset thickness threshold, there is no need to determine the second comfortable temperature, and the current state of the vehicle air conditioner can be directly maintained.

[0113] Step a3, obtaining the current vehicle interior temperature and the estimated driving time of the vehicle, and estimating the shortest heating time for the vehicle air conditioner to heat up from the current vehicle interior temperature to the second comfortable temperature in the rapid heating mode; It should be noted that the estimated driving time may be the estimated driving time of the vehicle this time, and the estimated driving time may be determined based on the navigation path of the vehicle. The shortest heating time is characterized by the time required to heat up from the current vehicle interior temperature to the second comfortable temperature in the rapid heating mode.

[0114] Step a4: If the shortest heating time is less than the expected driving time, the vehicle air conditioner is controlled to operate in a rapid heating mode, and a prompt is output to prompt the driver to reduce the thickness of clothing after the shortest heating time.

[0115] It should be noted that the output prompt can be a voice prompt. For example, when the second comfortable temperature is 28°C and the shortest heating time is 8 minutes, the voice prompt can be: It is detected that you are wearing a thick coat, and the temperature has been quickly raised to 28°C. It can be adjusted to the light and thin mode after 8 minutes. In this way, the driver can be prompted that he will not feel cold after taking off the coat in 8 minutes. In addition, in this embodiment, after the vehicle air conditioner responds to the target air conditioning parameter operation, it can respond to the control mode corresponding to the vehicle air conditioner in the light clothing mode.

[0116] For example, if the shortest heating time is less than the expected driving time, it means that the temperature can be rapidly heated to the second comfortable temperature before the vehicle ends. At this time, the vehicle air conditioner can be controlled to run in the rapid heating mode and a prompt can be output to improve the driver's comfort. When the temperature inside the vehicle is equal to the second comfortable temperature, the rapid heating mode can be turned off and the vehicle air conditioner can be controlled to continue to run at the currently set temperature. If the shortest heating time is greater than or equal to the expected driving time, it means that the temperature cannot be rapidly heated to the second comfortable temperature before the vehicle ends. At this time, rapid heating can be omitted and the current operating state of the vehicle air conditioner can be maintained. At the same time, a prompt can be output to remind the driver that it may be cold to take off the coat. This can save energy.

[0117] In other embodiments, when the driver takes off his coat, the type of inner clothing actually worn by the driver can be identified. If the thermal resistance value of the clothing corresponding to the actual inner clothing is greater than the expected thermal resistance value of the clothing of the inner clothing, the temperature inside the vehicle can be lowered, for example, the set temperature of the vehicle air conditioner can be lowered. If the thermal resistance value of the clothing corresponding to the actual inner clothing is less than the expected thermal resistance value of the clothing of the inner clothing, the temperature inside the vehicle can be appropriately increased, for example, the set temperature of the vehicle air conditioner can be increased. The expected thermal resistance value of the clothing of the inner clothing can be the thermal resistance value of the clothing thickness of the inner clothing determined by the preset visual macro model based on the thickness of the driver's coat and the current climate temperature when the driver is wearing the coat.

[0118] This embodiment determines the second comfortable temperature of the driver after taking off his coat, thereby facilitating raising the temperature inside the vehicle to the second comfortable temperature, so that the driver can drive in light clothing, thereby improving driving comfort.

[0119] The present application also provides a vehicle air conditioning control device. Figure 5 , the device comprises: The acquisition module 10 is used to obtain the current environment, the current vehicle operation state and the vehicle user characteristics in response to the vehicle air conditioning control command; A determination module 20, for determining target air conditioning parameters under the current environment, the current vehicle operating state and the vehicle user characteristics through a preset air conditioning prediction model, wherein the preset air conditioning prediction model is obtained by training an initial air conditioning prediction model based on a credible training sample set; The operation module 30 is used to control the operation of the vehicle air conditioner in the vehicle according to the target air conditioning parameter. The present application provides a vehicle including a vehicle body and a controller, wherein the controller is arranged in the vehicle body and is used to execute a vehicle air conditioner control method.

[0120] The vehicle provided by the present application adopts the vehicle air conditioning control method in the above embodiment, which can solve the technical problem of low intelligence of the vehicle air conditioning. Compared with the prior art, the beneficial effects of the vehicle provided by the present application are the same as the beneficial effects of the vehicle air conditioning control method provided by the above embodiment, and other technical features in the vehicle are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0121] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0122] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0123] The present embodiment provides a computer-readable storage medium having computer-readable program instructions stored thereon, and the computer-readable program instructions are used to execute the vehicle air conditioning control method in the above-mentioned embodiment 1. The computer-readable storage medium provided in the embodiment of the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor devices, equipment or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable EPROM (Electrical Programmable Read Only Memory, read-only memory) or flash memory, an optical fiber, a portable compact disk CD-ROM (compact disc read-only memory, read-only memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution device, device or device. The program code contained in the computer-readable storage medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above. The above-mentioned computer-readable storage medium may be contained in an electronic device; or it may exist alone without being assembled into the electronic device. The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains the current environment, the current vehicle operating state and the vehicle user characteristics; determines the target air-conditioning parameters under the current environment, the current vehicle operating state and the vehicle user characteristics through a preset air-conditioning prediction model, wherein the preset air-conditioning prediction model is obtained by training the initial air-conditioning prediction model based on a credible training sample set jointly selected by multiple preset large models; and controls the operation of the vehicle-mounted air-conditioning in the vehicle according to the target air-conditioning parameters.

[0124] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a LAN (local area network) or a WAN (Wide Area Network), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0125] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the equipment, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based device that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0126] The modules involved in the embodiments described in the present disclosure may be implemented by software or by hardware. The name of the module does not constitute a limitation on the unit itself under certain circumstances. The computer-readable storage medium provided in the present application stores computer-readable program instructions for executing the above-mentioned vehicle air-conditioning control method, aiming to solve the technical problem of the low degree of intelligence of the vehicle air-conditioning. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the embodiments of the present application are the same as the beneficial effects of the vehicle air-conditioning control method provided in the above-mentioned embodiments, which will not be repeated here.

[0127] The present application also provides a computer program product, including a computer program, which implements the steps of the vehicle air-conditioning control method as described above when the computer program is executed by a processor. The computer program product provided by the present application is intended to solve the technical problem of the low degree of intelligence of the vehicle air-conditioning. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiment of the present application are the same as the beneficial effects of the vehicle air-conditioning control method provided by the above embodiment, which will not be repeated here. The above is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. All equivalent structures or equivalent process transformations made using the contents of the specification and drawings of this application, or directly or indirectly used in other related technical fields, are similarly included in the patent processing scope of the present application.

Claims

1. A vehicle air conditioning control method, characterized in that: The method includes: Responding to the vehicle air conditioning control command, obtaining the current environment, the current vehicle operating state and the vehicle user characteristics; Determining target air conditioning parameters under the current environment, the current vehicle operating state and the vehicle user characteristics by using a preset air conditioning prediction model, wherein the preset air conditioning prediction model is obtained by training an initial air conditioning prediction model based on a credible training sample set; The operation of the vehicle air conditioner in the vehicle is controlled according to the target air conditioning parameter.

2. The vehicle air conditioning control method according to claim 1, characterized in that: The method includes: Acquire historical air-conditioning usage data of a target user group, wherein the target user group includes vehicle users corresponding to the vehicle air-conditioning and users of the same type as the vehicle users, and the historical air-conditioning usage data includes a plurality of sub-usage data, and the sub-usage data includes at least one of the following: historical vehicle user characteristics, historical air-conditioning feedback adjustment data, historical air-conditioning setting parameters, historical environment, and historical vehicle operating status; According to a plurality of preset large models, a credible training sample set is selected from the historical usage data of the air conditioner; A preset air conditioning prediction model is determined based on the credible training sample set and the initial air conditioning prediction model.

3. The vehicle air conditioning control method according to claim 2, characterized in that: The step of selecting a credible training sample set from the air conditioner historical usage data based on a plurality of preset large models comprises: For each preset large model, the air conditioner historical usage data is input into the preset large model, and abnormal sub-usage data in the air conditioner historical usage data is removed by the preset large model to obtain a normal usage data set filtered from the air conditioner historical usage data by the preset large model; Target normal data commonly contained in all the normally used data sets are extracted to obtain a credible training sample set.

4. The vehicle air conditioning control method according to claim 2, characterized in that: The step of determining a preset air conditioning prediction model based on the credible training sample set and the initial air conditioning prediction model comprises: Performing scene feature extraction on the credible training sample set to obtain a plurality of scene parameter training features, wherein each scene parameter training feature includes a scene training feature and an air conditioning parameter setting feature associated with the scene training feature, the scene training feature includes at least one of the following: a training vehicle user feature, training air conditioning feedback adjustment data, a training environment, and a training vehicle operating state, and the air conditioning parameter setting feature includes at least one of the following: an air conditioning switch setting parameter, a seat heating setting parameter, a blowing setting parameter, an air conditioning temperature setting parameter, an air conditioning air volume setting parameter, a temperature adjustment mode setting parameter, and a circulation mode setting parameter; According to the plurality of scene parameter training features, the initial air conditioning prediction model is trained to obtain a trained teacher model; A student model having a parameter magnitude smaller than that of the teacher model is obtained, and the student model is updated by the teacher model, and the updated student model is used as a preset air conditioning prediction model.

5. The vehicle air conditioning control method according to claim 2, characterized in that: The target air conditioning parameter includes at least one of a target air conditioning switch parameter, a target seat heating parameter, a target blowing mode, a target air conditioning temperature, a target air conditioning air volume, a target circulation mode, and a target temperature adjustment mode; The step of determining the target air conditioning parameters under the current environment, the current vehicle operating state and the vehicle user characteristics by using the preset air conditioning prediction model comprises: The current environment, the current vehicle operating state and the vehicle user characteristics are input into a preset air conditioning prediction model, and a target air conditioning switch parameter, a target seat heating parameter, a target blowing mode, a target air conditioning temperature, a target air conditioning air volume, a target circulation mode and / or a target temperature adjustment mode under the current environment, the current vehicle operating state and the vehicle user characteristics are determined by the preset air conditioning prediction model; Among them, the current environment includes: current weather, current outside temperature, current inside temperature, current inside humidity, current outside rainfall, current outside environment image and at least one of the current inside environment image; the current vehicle operating status includes the current vehicle power; the vehicle user characteristics include the vehicle user's age, gender, current usage month, current vehicle latitude and at least one of the user's behavior.

6. The vehicle air conditioning control method according to claim 5, characterized in that: The method further comprises: In a preset driving scenario, if the current outside temperature is greater than a preset high temperature threshold, the output of the preset air conditioning prediction model includes: the target air conditioning switch parameter is on, the target air conditioning air volume includes increasing the air volume, and / or the target blowing mode includes blowing downward and / or blowing cold air; In a preset driving scenario, if the current outside temperature is less than a preset low temperature threshold, the output of the preset air conditioning prediction model includes: the target air conditioning switch parameter is on, the target air conditioning air volume includes increasing the air volume, and / or the target blowing mode includes blowing downward and / or blowing hot air; Among them, the preset driving scenarios include: the current weather is rainy, the current humidity inside the vehicle is greater than a preset humidity threshold, the current rainfall outside the vehicle is greater than a preset rainfall threshold, and / or the amount of water detected in the current external environment image is greater than a preset water threshold.

7. The vehicle air conditioning control method according to claim 5, characterized in that: The method includes: When it is detected that the air quality outside the vehicle in the current outside vehicle environment image is less than a preset quality standard, the output of the preset air-conditioning prediction model includes the target circulation mode being internal circulation.

8. The vehicle air conditioning control method according to claim 5, characterized in that: The method further comprises: In the case where the target comfortable temperature corresponding to the current clothing thickness of the vehicle occupant is detected in the current vehicle interior environment image, the absolute value of the difference between the target comfortable temperature and the current vehicle interior temperature is greater than a preset temperature difference threshold, and the temperature adjustment time for adjusting the vehicle from the current vehicle interior temperature to the target comfortable temperature in a preset rapid temperature adjustment mode is less than an expected driving time of the vehicle, determining the output of the preset air conditioning prediction model includes: the target temperature adjustment mode includes a preset rapid temperature adjustment mode, and the target air conditioning temperature includes adjusting the current vehicle interior temperature to the target comfortable temperature; The target comfort temperature is obtained by adjusting the preset standard body comfort temperature based on the current clothing thickness to obtain the initial comfort temperature, and adjusting the initial comfort temperature according to the acquired temperature preference of the vehicle occupant.

9. A vehicle, characterized in that: The vehicle includes a vehicle body and a controller, wherein the controller is disposed in the vehicle body, and the controller is used to execute the steps of implementing the vehicle air conditioning control method according to any one of claims 1 to 8.

10. A readable storage medium, characterized in that: The readable storage medium is a computer-readable storage medium, on which is stored a program for implementing the vehicle air conditioning control method. The program for implementing the vehicle air conditioning control method is executed by a processor to implement the steps of the vehicle air conditioning control method as described in any one of claims 1 to 8.

Images