Vehicle-mounted air conditioner air outlet control method, system and device based on machine vision and medium

Abstract

The invention discloses a vehicle-mounted air conditioner air outlet control method, system and device based on machine vision and a medium, and the method comprises the steps that user identity information of a target user is obtained, and a corresponding target air outlet control model is obtained through matching in a personalized database; acquiring internal and external environment data of a target vehicle, and inputting the data into the target air-out control model to obtain a target air-out control strategy; performing air-out control on a vehicle-mounted air conditioner of the target vehicle according to the target initial air-out configuration information, acquiring physiological state change data and sitting posture change data of the target user, and inputting the physiological state change data and the sitting posture change data into a pre-trained air-out adjustment prediction model to obtain a target adjustment trend and a target adjustment proportion; and air outlet configuration adjusting information is determined according to the target adjusting trend, the target adjusting proportion and the target air outlet configuration adjustable range, and air outlet adjustment is conducted on the vehicle-mounted air conditioner. The vehicle-mounted air conditioner air outlet control method improves the efficiency and accuracy of vehicle-mounted air conditioner air outlet control, also improves the vehicle using experience of the user, and can be applied to the technical field of vehicle control.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle control, and in particular to an in-vehicle air conditioner air outlet control method, system, device and medium based on machine vision. Background Art

[0002] As a common means of transportation, automobiles have become indispensable in human life. The internal environment of automobiles affects the comfort of drivers and passengers. At present, most automobiles are equipped with in-vehicle air conditioners to adjust and control the temperature inside the vehicle to provide users with a good driving and riding environment.

[0003] In the prior art, the electronic air outlet control of in-vehicle air conditioners can be automatically turned on / off through touch or voice commands, and the air outlet target can be set according to user commands to adjust the air outlet temperature, air outlet speed and air direction, so as to maintain a comfortable cabin environment.

[0004] However, the existing electronic air outlet control solutions for in-vehicle air conditioners have the following disadvantages:

[0005] 1) It is necessary for users to issue commands to turn on / off the automatic adjustment function, which is not convenient enough;

[0006] 2) The default target values (temperature / direction / air volume / air staying time, etc.) of air outlet adjustment are relatively general, or it is necessary for users to issue commands to set them one by one, and it is impossible to automatically match the personalized habit requirements of users, resulting in poor user experience;

[0007] 3) During the use of the vehicle, when the physiological characteristics of the user change, the air outlet of the air conditioner cannot be automatically adjusted and matched. For example, when the user's sitting posture changes, the air outlet angle will not be automatically adjusted to cover the human body coverage area preferred by the user for blowing air to meet the dynamic needs of the user. Summary of the Invention

[0008] An object of the present invention is to solve at least to some extent one of the technical problems existing in the prior art.

[0009] To this end, an object of an embodiment of the present invention is to provide an in-vehicle air conditioner air outlet control method based on machine vision, which improves the efficiency and accuracy of in-vehicle air conditioner air outlet control and also improves the user's vehicle use experience.

[0010] Another object of an embodiment of the present invention is to provide an in-vehicle air conditioner air outlet control system based on machine vision.

[0011] In order to achieve the above technical object, the technical solutions adopted in the embodiments of the present invention include:

[0012] In the first aspect, an embodiment of the present invention provides an in-vehicle air conditioner air outlet control method based on machine vision, including the following steps:

[0013] Obtain the user identity information of the target user, and match the corresponding target air outlet control model in the pre-constructed personalized database according to the user identity information;

[0014] Obtain the vehicle interior and exterior environment data of the target vehicle, input the vehicle interior and exterior environment data into the target air outlet control model, and obtain a target air outlet control strategy, where the target air outlet control strategy includes target initial air outlet configuration information and a target air outlet configuration adjustable range;

[0015] Perform air outlet control on the vehicle-mounted air conditioner of the target vehicle according to the target initial air outlet configuration information, and obtain the physiological state change data and sitting posture change data of the target user;

[0016] Input the physiological state change data and the sitting posture change data into a pre-trained air outlet adjustment prediction model to obtain a target adjustment trend and a target adjustment ratio;

[0017] Determine air outlet configuration adjustment information according to the target adjustment trend, the target adjustment ratio, and the target air outlet configuration adjustable range, and perform air outlet adjustment on the vehicle-mounted air conditioner according to the air outlet configuration adjustment information.

[0018] Further, in an embodiment of the present invention, the personalized database is constructed through the following steps:

[0019] Obtain a first face image of the current user through an in-vehicle camera, and identify the first identity information of the current user according to the first face image;

[0020] Obtain vehicle interior and exterior environment sample data of the current vehicle through in-vehicle sensors, and record the initial air outlet configuration operation of the current user and subsequent air outlet adjustment operations during vehicle use;

[0021] Determine an initial air outlet configuration sample according to the initial air outlet configuration operation, determine an air outlet configuration adjustable range sample according to the subsequent air outlet adjustment operations, and further determine an air outlet control strategy label according to the initial air outlet configuration sample and the air outlet configuration adjustable range sample;

[0022] Construct a first training data set according to the vehicle interior and exterior environment sample data and the air outlet control strategy label, and train the first air outlet control model of the current user according to the first training data set;

[0023] Establish a first mapping relationship between the first identity information and the first air outlet control model, and construct the personalized database according to the first mapping relationship.

[0024] Further, in an embodiment of the present invention, training the first air outlet control model of the current user according to the first training data set specifically includes:

[0025] Inputting the vehicle interior and exterior environment sample data into a pre-constructed deep neural network to obtain a predicted air outlet control strategy;

[0026] Determining a first loss value according to the predicted air outlet control strategy and the air outlet control strategy label;

[0027] Updating the parameters of the deep neural network according to the first loss value to obtain the first air outlet control model;

[0028] Wherein, the predicted air outlet control strategy includes predicted initial air outlet configuration information and a predicted adjustable range of the air outlet configuration. The predicted initial air outlet configuration information includes predicted air outlet temperature, predicted air outlet size, predicted air outlet coverage area, and predicted air outlet residence time. The predicted adjustable range of the air outlet configuration includes a predicted air outlet temperature adjustment range, a predicted air outlet size adjustment range, a predicted air outlet coverage area adjustment range, and a predicted air outlet residence time adjustment range.

[0029] Further, in an embodiment of the present invention, obtaining the user identity information of the target user and matching the corresponding target air outlet control model in a pre-constructed personalized database specifically includes:

[0030] Obtaining the face image information of the target user through an in-vehicle camera, and identifying the user identity information according to the face image information;

[0031] Matching the corresponding target mapping relationship in the personalized database according to the user identity information, and determining the target air outlet control model according to the target mapping relationship.

[0032] Further, in an embodiment of the present invention, the air outlet adjustment prediction model is trained through the following steps:

[0033] Obtaining the physiological state change sample data and sitting posture change sample data of the tester in the test vehicle, and recording the air outlet adjustment operations of the tester;

[0034] Determining an adjustment trend label and an adjustment ratio label according to the air outlet adjustment operations;

[0035] Inputting the physiological state change sample data and the sitting posture change sample data into a pre-constructed long short-term memory network to obtain a predicted adjustment trend and a predicted adjustment ratio;

[0036] Determine a second loss value according to the predicted adjustment trend, the predicted adjustment ratio, the adjustment trend label, and the adjustment ratio label;

[0037] Update the parameters of the long short-term memory network according to the second loss value to obtain the air outlet adjustment prediction model;

[0038] Among them, the predicted adjustment trend includes the predicted air outlet temperature adjustment trend, the predicted air outlet size adjustment trend, the predicted air outlet coverage area adjustment trend, and the predicted air outlet residence time adjustment trend, and the predicted adjustment ratio includes the predicted air outlet temperature adjustment ratio, the predicted air outlet size adjustment ratio, the predicted air outlet coverage area adjustment ratio, and the predicted air outlet residence time adjustment ratio.

[0039] Further, in an embodiment of the present invention, the determining the air outlet configuration adjustment information according to the target adjustment trend, the target adjustment ratio, and the adjustable range of the target air outlet configuration specifically includes:

[0040] Obtain the current air outlet configuration information, and determine the target air outlet configuration information according to the target adjustment trend, the target adjustment ratio, and the current air outlet configuration information;

[0041] Compare the target air outlet configuration information with the adjustable range of the target air outlet configuration;

[0042] When the target air outlet configuration information meets the adjustable range of the target air outlet configuration, determine the air outlet configuration adjustment information according to the target air outlet configuration information and the current air outlet configuration information;

[0043] When the target air outlet configuration information does not meet the adjustable range of the target air outlet configuration, determine the extreme value of the adjustable range of the target air outlet configuration close to the target air outlet configuration information as the target air outlet configuration extreme value, and determine the air outlet configuration adjustment information according to the target air outlet configuration extreme value and the current air outlet configuration information.

[0044] Further, in an embodiment of the present invention, the vehicle-mounted air conditioner air outlet control method further includes the following steps:

[0045] Obtain the air outlet adjustment feedback information of the target user, and perform feedback adjustment on the vehicle-mounted air conditioner according to the air outlet adjustment feedback information;

[0046] Optimize the personalized database and the air outlet adjustment prediction model according to the air outlet adjustment feedback information.

[0047] In a second aspect, an embodiment of the present invention provides a vehicle-mounted air conditioner air outlet control system based on machine vision, including:

[0048] A model matching module, configured to obtain the user identity information of a target user, and match a corresponding target air outlet control model in a pre-constructed personalized database according to the user identity information;

[0049] A control strategy determination module, configured to obtain the vehicle interior and exterior environment data of a target vehicle, input the vehicle interior and exterior environment data into the target air outlet control model, and obtain a target air outlet control strategy, where the target air outlet control strategy includes target initial air outlet configuration information and a target air outlet configuration adjustable range;

[0050] An air outlet control module, configured to perform air outlet control on the in-vehicle air conditioner of the target vehicle according to the target initial air outlet configuration information, and obtain the physiological state change data and sitting posture change data of the target user;

[0051] An adjustment prediction module, configured to input the physiological state change data and the sitting posture change data into a pre-trained air outlet adjustment prediction model to obtain a target adjustment trend and a target adjustment ratio;

[0052] An air outlet adjustment module, configured to determine air outlet configuration adjustment information according to the target adjustment trend, the target adjustment ratio, and the target air outlet configuration adjustable range, and perform air outlet adjustment on the in-vehicle air conditioner according to the air outlet configuration adjustment information.

[0053] In a third aspect, an embodiment of the present invention provides an in-vehicle air conditioner air outlet control device based on machine vision, including:

[0054] At least one processor;

[0055] At least one memory, configured to store at least one program;

[0056] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned in-vehicle air conditioner air outlet control method based on machine vision.

[0057] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, in which a processor-executable program is stored, and the processor-executable program is used to execute the above-mentioned in-vehicle air conditioner air outlet control method based on machine vision when executed by a processor.

[0058] The advantages and beneficial effects of the present invention will be partially given in the following description, partially will become obvious from the following description, or will be understood through the practice of the present invention:

[0059] In an embodiment of the present invention, the user identity information of the target user is obtained, the corresponding target air outlet control model is obtained by matching in a pre-constructed personalized database according to the user identity information, the vehicle interior and exterior environment data of the target vehicle is obtained, and the vehicle interior and exterior environment data is input into the target air outlet control model to obtain a target air outlet control strategy. The target air outlet control strategy includes target initial air outlet configuration information and a target air outlet configuration adjustable range. The air outlet of the in-vehicle air conditioner of the target vehicle is controlled according to the target initial air outlet configuration information, and the physiological state change data and sitting posture change data of the target user are obtained. The physiological state change data and sitting posture change data are input into a pre-trained air outlet adjustment prediction model to obtain a target adjustment trend and a target adjustment ratio. The air outlet configuration adjustment information is determined according to the target adjustment trend, the target adjustment ratio and the target air outlet configuration adjustable range, and the air outlet of the in-vehicle air conditioner is adjusted according to the air outlet configuration adjustment information. In the embodiment of the present invention, first, the corresponding target air outlet control model is obtained by matching in the personalized database according to the user identity information, and the corresponding target air outlet control strategy is determined in combination with the current vehicle interior and exterior environment data. The target air outlet control strategy gives the target initial air outlet configuration information and the target air outlet configuration adjustable range that are suitable for the current vehicle interior and exterior environment and conform to the user's habits, and can provide a customized air outlet control solution for the user; in the subsequent process, the physiological state change data and sitting posture change data of the user are continuously obtained, and the target adjustment trend and the target adjustment ratio are obtained in combination with the pre-trained air outlet adjustment prediction model, so that the air outlet configuration adjustment information that is suitable for the current vehicle interior and exterior environment and conforms to the user's habits can be determined according to the target adjustment trend, the target adjustment ratio and the target air outlet configuration adjustable range, realizing the automatic adjustment of the air outlet control of the in-vehicle air conditioner, meeting the real-time and dynamic air outlet requirements of the user, improving the efficiency and accuracy of the air outlet control of the in-vehicle air conditioner, and also improving the user's driving experience. Description of the Drawings

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following introduces the drawings required to be used in the embodiments of the present invention. It should be understood that the drawings introduced below are only for conveniently and clearly expressing some embodiments of the technical solutions in the present invention. For those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.

[0061] Figure 1 It is a flowchart of the steps of a method for controlling the air outlet of an in-vehicle air conditioner based on machine vision provided by an embodiment of the present invention;

[0062] Figure 2 It is a block diagram of the structure of a system for controlling the air outlet of an in-vehicle air conditioner based on machine vision provided by an embodiment of the present invention;

[0063] Figure 3It is a structural block diagram of an in-vehicle air conditioner air outlet control device based on machine vision provided by an embodiment of the present invention. Specific embodiments

[0064] The embodiments of the present invention will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present invention and should not be construed as a limitation to the present invention. For the step numbers in the following embodiments, they are only set for the convenience of elaboration and explanation, and no limitation is imposed on the order between the steps. The execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0065] In the description of the present invention, the meaning of "a plurality of" is two or more. If the first and second are described, it is only for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features or implicitly indicating the sequence of the indicated technical features. In addition, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field of the present invention.

[0066] Refer to Figure 1 , an embodiment of the present invention provides an in-vehicle air conditioner air outlet control method based on machine vision, specifically including the following steps:

[0067] S101. Obtain the user identity information of the target user, and match the corresponding target air outlet control model in the pre-constructed personalized database according to the user identity information;

[0068] S102. Obtain the in-vehicle and out-of-vehicle environment data of the target vehicle, input the in-vehicle and out-of-vehicle environment data into the target air outlet control model, and obtain a target air outlet control strategy, where the target air outlet control strategy includes target initial air outlet configuration information and a target air outlet configuration adjustable range;

[0069] S103. Control the air outlet of the in-vehicle air conditioner of the target vehicle according to the target initial air outlet configuration information, and obtain the physiological state change data and sitting posture change data of the target user;

[0070] S104. Input the physiological state change data and sitting posture change data into the pre-trained air outlet adjustment prediction model to obtain a target adjustment trend and a target adjustment ratio;

[0071] S105. Determine the air outlet configuration adjustment information according to the target adjustment trend, the target adjustment ratio, and the target air outlet configuration adjustable range, and adjust the air outlet of the in-vehicle air conditioner according to the air outlet configuration adjustment information.

[0072] Specifically, during the initial driving and riding periods of different users (including drivers and passengers), in-vehicle cameras are used to identify different users, and the air outlet habit data of users in different in-vehicle and out-of-vehicle environments are collected (including air outlet temperature, air outlet size, air outlet coverage area, and the air outlet residence time in the corresponding area, etc.), so as to form air outlet control strategies preferred by users in different in-vehicle and out-of-vehicle environments, and then different air outlet control models for different users are trained to form a personalized database; during the subsequent vehicle use process, the in-vehicle camera identifies different users, automatically matches the target air outlet control model of the target user, obtains the corresponding target initial air outlet configuration information and the adjustable range of the target air outlet configuration, controls the air outlet of the in-vehicle air conditioner according to the target initial air outlet configuration information, and at the same time, during the vehicle use process, the in-vehicle vision system is used to continuously monitor the physiological state change data and sitting posture change data of the user during the vehicle use process, inputs them into the pre-trained air outlet adjustment prediction model to obtain the target adjustment trend and the target adjustment ratio, and then combines the adjustable range of the target air outlet configuration to determine the air outlet configuration adjustment information, so that the air outlet of the in-vehicle air conditioner can be adjusted according to the air outlet configuration adjustment information to meet the dynamic air outlet needs of users in real time.

[0073] It can be recognized that in the embodiment of the present invention, first, the corresponding target air outlet control model is matched in the personalized database according to the user identity information, and the corresponding target air outlet control strategy is determined in combination with the current in-vehicle and out-of-vehicle environment data. The target air outlet control strategy gives the target initial air outlet configuration information and the adjustable range of the target air outlet configuration that are suitable for the current in-vehicle and out-of-vehicle environment and meet the user's habits, and can provide a customized air outlet control solution for users; in the subsequent process, the physiological state change data and sitting posture change data of the user are continuously obtained, and the target adjustment trend and the target adjustment ratio are obtained in combination with the pre-trained air outlet adjustment prediction model, so that the air outlet configuration adjustment information that is suitable for the current in-vehicle and out-of-vehicle environment and meets the user's habits can be determined according to the target adjustment trend, the target adjustment ratio, and the adjustable range of the target air outlet configuration, realizing the automatic adjustment of the in-vehicle air conditioner air outlet control, meeting the real-time and dynamic air outlet needs of users, improving the efficiency and accuracy of the in-vehicle air conditioner air outlet control, and also improving the user's vehicle use experience.

[0074] It should be noted that considering the personalized air outlet requirements of users, the embodiments of the present invention construct an air outlet control model applicable to different users and form a personalized database. However, the historical data samples of the same user are limited, and it is impossible to train an accurate and reliable refined air outlet control model for different vehicle interior and exterior environments, different physiological state changes, and different sitting posture changes. Therefore, the air outlet control models trained for different users by the embodiments of the present invention only fit the initial air outlet configuration information and the adjustable range information of the air outlet configuration preferred by the user, and generally give the air outlet control strategy preferred by the user in different vehicle interior and exterior environments to complete the initial air outlet configuration. For the air outlet adjustment for physiological state changes and sitting posture changes, the air outlet adjustment prediction model with more sample data and stronger generalization ability (applicable to all users) is used to predict the corresponding adjustment trend and adjustment ratio, and then combined with the adjustable range information of the air outlet configuration in the air outlet control strategy, the air outlet configuration adjustment information that conforms to the user's habits is obtained. Through the cooperation of these two links, the air outlet control of the vehicle-mounted air conditioner is more in line with the user's habits and real-time needs.

[0075] Further as an optional implementation manner, the personalized database is constructed through the following steps:

[0076] S201. Obtain the first face image of the current user through the vehicle-mounted camera, and identify the first identity information of the current user according to the first face image;

[0077] S202. Obtain the vehicle interior and exterior environment sample data of the current vehicle through the vehicle-mounted sensors, and record the initial air outlet configuration operation of the current user and the subsequent air outlet adjustment operations during the vehicle use process;

[0078] S203. Determine the initial air outlet configuration sample according to the initial air outlet configuration operation, and determine the adjustable range sample of the air outlet configuration according to the subsequent air outlet adjustment operations. Furthermore, determine the air outlet control strategy label according to the initial air outlet configuration sample and the adjustable range sample of the air outlet configuration;

[0079] S204. Construct the first training data set according to the vehicle interior and exterior environment sample data and the air outlet control strategy label, and train the first air outlet control model of the current user according to the first training data set;

[0080] S205. Establish the first mapping relationship between the first identity information and the first air outlet control model, and construct the personalized database according to the first mapping relationship.

[0081] The specific process of constructing the personalized database is as follows:

[0082] 1) In the initial stage of the user using the vehicle, the first identity information of the user is recognized based on the face images collected by the in-vehicle camera. The in-vehicle and external environment sample data is obtained through in-vehicle sensors (such as temperature sensors, humidity sensors, light sensors, etc.). At the same time, the vehicle head unit records the initial air outlet configuration operation of the user manually adjusting the in-vehicle air conditioner and the subsequent air outlet adjustment operations during the vehicle use process;

[0083] 2) Determine the initial air outlet configuration sample according to the initial air outlet configuration operation. For example, an array {air outlet temperature 0, air outlet size 0, air outlet coverage area 0, air outlet residence time 0} can be used to represent the initial air outlet configuration of a certain air outlet. Arrange the initial air outlet configurations of all air outlets in a predetermined order to obtain the initial air outlet configuration sample;

[0084] 3) Determine the adjustable range sample of the air outlet configuration according to the subsequent air outlet adjustment operations. For example, an array {[air outlet temperature 1, air outlet temperature 2], [air outlet size 1, air outlet size 2], [air outlet coverage area 1, air outlet coverage area 2], [air outlet residence time 1, air outlet residence time 2]} can be used to represent the adjustable range of the air outlet configuration of a certain air outlet. Arrange the adjustable ranges of the air outlet configurations of all air outlets in a predetermined order to obtain the adjustable range sample of the air outlet configuration;

[0085] 4) Determine the air outlet control strategy label according to the initial air outlet configuration sample and the adjustable range sample of the air outlet configuration. For example, splice the initial air outlet configuration sample and the adjustable range sample of the air outlet configuration obtained in the previous steps. An array {air outlet temperature 0, [air outlet temperature 1, air outlet temperature 2], air outlet size 0, [air outlet size 1, air outlet size 2], air outlet coverage area 0, [air outlet coverage area 1, air outlet coverage area 2], air outlet residence time 0, [air outlet residence time 1, air outlet residence time 2]} is used to represent the air outlet control strategy of a certain air outlet. Arrange the air outlet control strategies of all air outlets in a predetermined order to obtain the air outlet control strategy label;

[0086] 5) Form training samples by corresponding the air outlet control strategy labels one by one with the in-vehicle and external environment sample data, construct the first training data set, and train the first air outlet control model using a neural network model;

[0087] 6) Establish the mapping relationship between the first identity information and the first air outlet control model. After collecting the mapping relationships for different users, a personalized database can be constructed.

[0088] Further as an optional implementation manner, train the first air outlet control model of the current user according to the first training data set, which specifically includes:

[0089] S2041. Input the in-vehicle and external environment sample data into a pre-constructed deep neural network to obtain the predicted air outlet control strategy;

[0090] S2042. Determine the first loss value according to the predicted air outlet control strategy and the air outlet control strategy label;

[0091] S2043. Update the parameters of the deep neural network according to the first loss value to obtain the first air outlet control model;

[0092] Among them, the predicted air outlet control strategy includes the predicted initial air outlet configuration information and the predicted adjustable range of the air outlet configuration. The predicted initial air outlet configuration information includes the predicted air outlet temperature, the predicted air outlet size, the predicted air outlet coverage area, and the predicted air outlet residence time. The predicted adjustable range of the air outlet configuration includes the predicted air outlet temperature adjustment range, the predicted air outlet size adjustment range, the predicted air outlet coverage area adjustment range, and the predicted air outlet residence time adjustment range.

[0093] Specifically, in the embodiment of the present invention, a deep neural network is used to train the first air outlet control model. The vehicle interior and exterior environment sample data is input into the pre-constructed deep neural network to obtain the predicted air outlet temperature, the predicted air outlet size, the predicted air outlet coverage area, the predicted air outlet residence time, the predicted air outlet temperature adjustment range, the predicted air outlet size adjustment range, the predicted air outlet coverage area adjustment range, and the predicted air outlet residence time adjustment range of each air outlet. Then, combined with the air outlet control strategy label, the first loss value is calculated. According to the first loss value, the parameters of the deep neural network are continuously updated through the backpropagation algorithm. When the preset convergence condition is reached, the first air outlet control model can be obtained.

[0094] Further as an optional implementation manner, obtain the user identity information of the target user, and match the corresponding target air outlet control model in the pre-constructed personalized database, which specifically includes:

[0095] S1011. Obtain the face image information of the target user through the vehicle-mounted camera, and identify the user identity information according to the face image information;

[0096] S1012. Match the corresponding target mapping relationship in the personalized database according to the user identity information, and determine the target air outlet control model according to the target mapping relationship.

[0097] Specifically, after the vehicle-mounted air conditioner air outlet control method in the embodiment of the present invention is deployed on the target vehicle, when the user uses the vehicle, the user identity information is also recognized through face image recognition, and then the corresponding target mapping relationship is matched in the personalized database, so as to obtain the target air outlet control model.

[0098] Obtain the in-vehicle and out-of-vehicle environment data of the target vehicle, and input it into the target air outlet control model to obtain the target initial air outlet configuration information and the adjustable range of the target air outlet configuration that are suitable for the current in-vehicle and out-of-vehicle environment and meet the user's habits. According to the target initial air outlet configuration information, the initial air outlet control of the vehicle-mounted air conditioner can be completed, and during the subsequent driving process, continuously collect the physiological state change data and sitting posture change data of the target user, and input them into the pre-trained air outlet adjustment prediction model to obtain the target adjustment trend and the target adjustment ratio.

[0099] Further, as an optional implementation manner, the air outlet adjustment prediction model is trained through the following steps:

[0100] S301. Obtain the physiological state change sample data and sitting posture change sample data of the tester in the test vehicle, and record the air outlet adjustment operation of the tester;

[0101] S302. Determine the adjustment trend label and the adjustment ratio label according to the air outlet adjustment operation;

[0102] S303. Input the physiological state change sample data and sitting posture change sample data into the pre-constructed long short-term memory network to obtain the predicted adjustment trend and the predicted adjustment ratio;

[0103] S304. Determine the second loss value according to the predicted adjustment trend, the predicted adjustment ratio, the adjustment trend label, and the adjustment ratio label;

[0104] S305. Update the parameters of the long short-term memory network according to the second loss value to obtain the air outlet adjustment prediction model;

[0105] Among them, the predicted adjustment trend includes the predicted air outlet temperature adjustment trend, the predicted air outlet size adjustment trend, the predicted air outlet coverage area adjustment trend, and the predicted air outlet dwell time adjustment trend, and the predicted adjustment ratio includes the predicted air outlet temperature adjustment ratio, the predicted air outlet size adjustment ratio, the predicted air outlet coverage area adjustment ratio, and the predicted air outlet dwell time adjustment ratio.

[0106] The specific process of training the air outlet adjustment prediction model is as follows:

[0107] 1) Continuously obtain the physiological state change sample data of the tester in the test vehicle through the physiological monitoring sensor, continuously obtain the sitting posture change sample data of the tester in the test vehicle through the vehicle-mounted camera, and at the same time record the corresponding air outlet adjustment operation of the tester through the vehicle computer;

[0108] 2) Determine the adjustment trend label and adjustment ratio label according to the air outlet adjustment operation. For example, use an array {the air outlet temperature increases / decreases, the air outlet size increases / decreases, the air outlet coverage area increases / decreases, the air outlet dwell time increases / decreases} to represent the adjustment trend of a certain air outlet. Arrange the adjustment trends of all air outlets in a predetermined order to obtain the adjustment trend label; use an array {the adjustment percentage of the air outlet temperature, the adjustment percentage of the air outlet size, the adjustment percentage of the air outlet coverage area, the adjustment percentage of the air outlet dwell time} to represent the adjustment ratio of a certain air outlet. Arrange the adjustment ratios of all air outlets in a predetermined order to obtain the adjustment ratio label. It should be noted that the calculation of the adjustment percentage can be the adjustment amount divided by the current value or the adjustment amount divided by the total adjustment range. The embodiments of the present invention do not limit this here;

[0109] 3) Input the physiological state change sample data and sitting posture change sample data into the pre-constructed long short-term memory network to obtain the predicted adjustment trend and predicted adjustment ratio; determine the second loss value according to the predicted adjustment trend, predicted adjustment ratio, adjustment trend label, and adjustment ratio label. Continuously update the parameters of the long short-term memory network through the backpropagation algorithm according to the second loss value. When the preset convergence condition is reached, the air outlet adjustment prediction model can be obtained.

[0110] Further, as an optional implementation manner, determine the air outlet configuration adjustment information according to the target adjustment trend, target adjustment ratio, and target air outlet configuration adjustable range, which specifically includes:

[0111] S1051. Obtain the current air outlet configuration information, and determine the target air outlet configuration information according to the target adjustment trend, target adjustment ratio, and current air outlet configuration information;

[0112] S1052. Compare the target air outlet configuration information with the target air outlet configuration adjustable range;

[0113] S1053. When the target air outlet configuration information meets the target air outlet configuration adjustable range, determine the air outlet configuration adjustment information according to the target air outlet configuration information and the current air outlet configuration information;

[0114] S1054. When the target air outlet configuration information does not meet the target air outlet configuration adjustable range, determine the extreme value of the target air outlet configuration adjustable range close to the target air outlet configuration information as the target air outlet configuration extreme value, and determine the air outlet configuration adjustment information according to the target air outlet configuration extreme value and the current air outlet configuration information.

[0115] Specifically, obtain the current air outlet configuration information, including the current values and total adjustment ranges of the air outlet temperatures, air outlet sizes, air outlet coverage areas, and air outlet residence times of each current air outlet; determine the adjustment amount based on the product of the target adjustment ratio and the current value / total adjustment range (corresponding to the above two calculation methods of the adjustment percentage respectively), and obtain the predicted configuration of each adjustment category of each air outlet, that is, the target air outlet configuration information, according to the current value, the target adjustment trend, and the adjustment amount; compare the target air outlet configuration information with the adjustable range of the target air outlet configuration item by item for each adjustment category of each air outlet. If the target air outlet configuration information of a certain adjustment category of a certain air outlet meets the adjustable range of the target air outlet configuration, it means that the predicted configuration of this adjustment category of this air outlet conforms to the current user's air outlet control strategy, and then the air outlet configuration adjustment information can be determined according to the target air outlet configuration information and the current air outlet configuration information. For example, the target air outlet configuration information corresponding to the air outlet temperature of air outlet A is 25 degrees, the current value is 24 degrees, and the corresponding adjustable range of the target air outlet configuration is [23 degrees, 26 degrees]. Since 25 degrees is within the range of [23 degrees, 26 degrees], the adjustment information for the air outlet temperature of air outlet A can be determined to be adjusted upward by 1 degree according to the difference between 25 degrees and 24 degrees; if the target air outlet configuration information of a certain adjustment category of a certain air outlet does not meet the adjustable range of the target air outlet configuration, it means that the predicted configuration of this adjustment category of this air outlet does not conform to the current user's air outlet control strategy. At this time, it is necessary to correct the predicted configuration of this adjustment category of this air outlet according to the adjustable range of the target air outlet configuration, that is, use the extreme value of the adjustable range of the target air outlet configuration close to the target air outlet configuration information as the target air outlet configuration extreme value, and then determine the air outlet configuration adjustment information according to the target air outlet configuration extreme value and the current air outlet configuration information. For example, the target air outlet configuration information corresponding to the air outlet temperature of air outlet A is 27 degrees, the current value is 24 degrees, and the corresponding adjustable range of the target air outlet configuration is [23 degrees, 26 degrees]. Since 27 degrees exceeds the range of [23 degrees, 26 degrees], take the extreme value 26 degrees close to 27 degrees as the target air outlet configuration extreme value, and then the adjustment information for the air outlet temperature of air outlet A can be determined to be adjusted upward by 2 degrees according to the difference between 26 degrees and 24 degrees.

[0116] Further as an optional implementation manner, the vehicle air conditioner air outlet control method further includes the following steps:

[0117] S106. Obtain the air outlet adjustment feedback information of the target user, and perform feedback adjustment on the vehicle air conditioner according to the air outlet adjustment feedback information;

[0118] S107. Optimize the personalized database and the air outlet adjustment prediction model according to the air outlet adjustment feedback information.

[0119] Specifically, after performing the automatic air outlet adjustment of the vehicle air conditioner, obtain the feedback information of the target user, perform feedback adjustment on the vehicle air conditioner according to the feedback information, and at the same time re-form sample data according to the feedback information for optimizing the personalized database and the air outlet adjustment prediction model. For example, after performing the automatic air outlet adjustment of the vehicle air conditioner, if the user manually adjusts the air outlet coverage area of a certain air outlet, it can be used to update the adjustable range of the corresponding air outlet coverage area and the training samples of the air outlet coverage area under the corresponding conditions, so as to optimize the personalized database and the air outlet adjustment prediction model.

[0120] The method steps of the embodiments of the present invention are described above. It can be understood that the embodiments of the present invention first match the corresponding target air outlet control model in the personalized database according to the user identity information, and determine the corresponding target air outlet control strategy in combination with the current vehicle interior and exterior environment data. The target air outlet control strategy gives the target initial air outlet configuration information and the adjustable range of the target air outlet configuration that are suitable for the current vehicle interior and exterior environment and conform to the user's habits, and can provide a customized air outlet control solution for the user; in the subsequent process, continuously obtain the physiological state change data and sitting posture change data of the user, and combine the pre-trained air outlet adjustment prediction model to obtain the target adjustment trend and the target adjustment ratio, so that the air outlet configuration adjustment information that is suitable for the current vehicle interior and exterior environment and conforms to the user's habits can be determined according to the target adjustment trend, the target adjustment ratio, and the adjustable range of the target air outlet configuration, realizing the automatic adjustment of the vehicle air conditioner air outlet control, meeting the real-time and dynamic air outlet needs of the user, improving the efficiency and accuracy of the vehicle air conditioner air outlet control, and also improving the user's driving experience.

[0121] Refer to Figure 2 , the embodiments of the present invention provide a vehicle air conditioner air outlet control system based on machine vision, including:

[0122] A model matching module, configured to obtain the user identity information of the target user, and match the corresponding target air outlet control model in the pre-constructed personalized database according to the user identity information;

[0123] A control strategy determination module, configured to obtain the vehicle interior and exterior environment data of the target vehicle, input the vehicle interior and exterior environment data into the target air outlet control model, and obtain a target air outlet control strategy, where the target air outlet control strategy includes target initial air outlet configuration information and an adjustable range of the target air outlet configuration;

[0124] An air outlet control module, configured to perform air outlet control on the vehicle air conditioner of the target vehicle according to the target initial air outlet configuration information, and obtain the physiological state change data and sitting posture change data of the target user;

[0125] An adjustment prediction module, configured to input physiological state change data and sitting posture change data into a pre-trained air outlet adjustment prediction model to obtain a target adjustment trend and a target adjustment ratio;

[0126] An air outlet adjustment module, configured to determine air outlet configuration adjustment information according to the target adjustment trend, the target adjustment ratio, and the adjustable range of the target air outlet configuration, and perform air outlet adjustment on the vehicle-mounted air conditioner according to the air outlet configuration adjustment information.

[0127] The content in the above method embodiments is applicable to the present system embodiment. The functions specifically implemented by the present system embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above method embodiments.

[0128] Refer to Figure 3 , an embodiment of the present invention provides a vehicle-mounted air conditioner air outlet control device based on machine vision, including:

[0129] At least one processor;

[0130] At least one memory, configured to store at least one program;

[0131] When the above at least one program is executed by the above at least one processor, the above at least one processor implements the above vehicle-mounted air conditioner air outlet control method based on machine vision.

[0132] The content in the above method embodiments is applicable to the present device embodiment. The functions specifically implemented by the present device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above method embodiments.

[0133] An embodiment of the present invention further provides a computer-readable storage medium, in which a program executable by a processor is stored, and the program executable by the processor is used to execute the above vehicle-mounted air conditioner air outlet control method based on machine vision when executed by the processor.

[0134] A computer-readable storage medium according to an embodiment of the present invention can execute a vehicle-mounted air conditioner air outlet control method provided by an embodiment of the method of the present invention, can execute any combination of implementation steps of the method embodiment, and has the corresponding functions and beneficial effects of the method.

[0135] An embodiment of the present invention also discloses a computer program product or a computer program, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes Figure 1 the method shown.

[0136] In some alternative embodiments, the functions / operations recited in the block diagrams may not occur in the order presented in the operational illustrations. For example, depending on the functions / operations involved, two consecutive blocks shown may actually be executed substantially simultaneously or the blocks may sometimes be executed in the reverse order. Additionally, the embodiments presented and described in the flowcharts of the present invention are provided by way of example for the purpose of providing a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logical flows presented herein. Alternative embodiments are contemplated in which the order of various operations is altered and in which sub-operations described as part of a larger operation are performed independently.

[0137] Furthermore, although the present invention has been described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the above-described functions and / or features may be integrated in a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It should also be understood that a detailed discussion of the actual implementation of each module is not necessary for an understanding of the present invention. Rather, given the attributes, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the modules will be understood within the ordinary skill of an engineer. Thus, those skilled in the art can implement the present invention as set forth in the claims without undue experimentation. It should also be understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0138] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in the various embodiments of the present invention. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs.

[0139] The logic and / or steps represented in the flowchart or otherwise described herein can, for example, be considered as a definitional sequence of executable instructions for implementing logical functions and can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.

[0140] More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the above-described program can be printed, as the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then storing it in a computer memory.

[0141] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gates for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0142] In the above description of this specification, the descriptions referring to the terms "one embodiment / example", "another embodiment / example", or "certain embodiments / examples", etc., mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0143] Although embodiments of the present invention have been shown and described, those of ordinary skill in the art will understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the claims and their equivalents.

[0144] The above is a specific description of the preferred embodiments of the present invention, but the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent deformations or substitutions without departing from the spirit of the present invention, and these equivalent deformations or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A vehicle air conditioner air outlet control method based on machine vision, characterized in that It includes the following steps: Obtain the user identity information of the target user, and match the corresponding target air outlet control model in the pre-constructed personalized database according to the user identity information; Obtain the vehicle interior and exterior environment data of the target vehicle, input the vehicle interior and exterior environment data into the target air outlet control model, and obtain a target air outlet control strategy, where the target air outlet control strategy includes target initial air outlet configuration information and a target air outlet configuration adjustable range; Perform air outlet control on the in-vehicle air conditioner of the target vehicle according to the target initial air outlet configuration information, and obtain the physiological state change data and sitting posture change data of the target user; Input the physiological state change data and the sitting posture change data into a pre-trained air outlet adjustment prediction model to obtain a target adjustment trend and a target adjustment ratio; Determine air outlet configuration adjustment information according to the target adjustment trend, the target adjustment ratio, and the target air outlet configuration adjustable range, and perform air outlet adjustment on the in-vehicle air conditioner according to the air outlet configuration adjustment information.

2. The on-vehicle air conditioner air outlet control method based on machine vision according to claim 1, wherein, The personalized database is constructed through the following steps: Obtain a first face image of the current user through an in-vehicle camera, and identify the first identity information of the current user according to the first face image; Obtain vehicle interior and exterior environment sample data of the current vehicle through in-vehicle sensors, and record the initial air outlet configuration operation of the current user and subsequent air outlet adjustment operations during vehicle use; Determine an initial air outlet configuration sample according to the initial air outlet configuration operation, determine an air outlet configuration adjustable range sample according to the subsequent air outlet adjustment operations, and further determine an air outlet control strategy label according to the initial air outlet configuration sample and the air outlet configuration adjustable range sample; Construct a first training data set according to the vehicle interior and exterior environment sample data and the air outlet control strategy label, and train the first air outlet control model of the current user according to the first training data set; Establish a first mapping relationship between the first identity information and the first air outlet control model, and construct the personalized database according to the first mapping relationship.

3. The on-vehicle air-conditioning air-out control method based on machine vision according to claim 2, wherein, The training of the first air outlet control model of the current user according to the first training data set specifically includes: Input the vehicle interior and exterior environment sample data into a pre-constructed deep neural network to obtain a predicted air outlet control strategy; Determine a first loss value according to the predicted air outlet control strategy and the air outlet control strategy label; Update the parameters of the deep neural network according to the first loss value to obtain the first air outlet control model; Among them, the predicted air outlet control strategy includes predicted initial air outlet configuration information and a predicted air outlet configuration adjustable range, the predicted initial air outlet configuration information includes predicted air outlet temperature, predicted air outlet size, predicted air outlet coverage area, and predicted air outlet residence time, and the predicted air outlet configuration adjustable range includes a predicted air outlet temperature adjustment range, a predicted air outlet size adjustment range, a predicted air outlet coverage area adjustment range, and a predicted air outlet residence time adjustment range.

4. A method for controlling the air outlet of an in-vehicle air conditioner based on machine vision according to claim 2, characterized in that, Obtaining the user identity information of the target user, and matching the corresponding target air outlet control model in the pre-constructed personalized database, which specifically includes: Obtaining the face image information of the target user through an in-vehicle camera, and identifying the user identity information according to the face image information; Matching the corresponding target mapping relationship in the personalized database according to the user identity information, and determining the target air outlet control model according to the target mapping relationship.

5. A vehicle-mounted air conditioner air outlet control method based on machine vision according to claim 1, characterized in that The air outlet adjustment prediction model is trained through the following steps: Obtaining the sample data of the physiological state change and the sample data of the sitting posture change of the tester in the test vehicle, and recording the air outlet adjustment operation of the tester; Determining the adjustment trend label and the adjustment ratio label according to the air outlet adjustment operation; Inputting the sample data of the physiological state change and the sample data of the sitting posture change into the pre-constructed long short-term memory network to obtain the predicted adjustment trend and the predicted adjustment ratio; Determining the second loss value according to the predicted adjustment trend, the predicted adjustment ratio, the adjustment trend label and the adjustment ratio label; Updating the parameters of the long short-term memory network according to the second loss value to obtain the air outlet adjustment prediction model; Wherein, the predicted adjustment trend includes the predicted air outlet temperature adjustment trend, the predicted air outlet size adjustment trend, the predicted air outlet coverage area adjustment trend and the predicted air outlet dwell time adjustment trend, and the predicted adjustment ratio includes the predicted air outlet temperature adjustment ratio, the predicted air outlet size adjustment ratio, the predicted air outlet coverage area adjustment ratio and the predicted air outlet dwell time adjustment ratio.

6. The on-vehicle air-conditioning air-out control method based on machine vision according to claim 1, wherein Determining the air outlet configuration adjustment information according to the target adjustment trend, the target adjustment ratio and the adjustable range of the target air outlet configuration, which specifically includes: Obtaining the current air outlet configuration information, and determining the target air outlet configuration information according to the target adjustment trend, the target adjustment ratio and the current air outlet configuration information; Comparing the target air outlet configuration information with the adjustable range of the target air outlet configuration; When the target air outlet configuration information meets the adjustable range of the target air outlet configuration, determining the air outlet configuration adjustment information according to the target air outlet configuration information and the current air outlet configuration information; When the target air outlet configuration information does not meet the adjustable range of the target air outlet configuration, determining the extreme value of the adjustable range of the target air outlet configuration close to the target air outlet configuration information as the target air outlet configuration extreme value, and determining the air outlet configuration adjustment information according to the target air outlet configuration extreme value and the current air outlet configuration information.

7. A vehicle air conditioner air outlet control method based on machine vision according to any one of claims 1 to 6, characterized in that The in-vehicle air conditioner air outlet control method further includes the following steps: Obtaining the air outlet adjustment feedback information of the target user, and performing feedback adjustment on the in-vehicle air conditioner according to the air outlet adjustment feedback information; Optimizing the personalized database and the air outlet adjustment prediction model according to the air outlet adjustment feedback information.

8. An air outlet control system for a vehicle-mounted air conditioner based on machine vision, characterized in that Including: A model matching module, configured to obtain the user identity information of the target user, and match the corresponding target air outlet control model in the pre-constructed personalized database; A control strategy determination module, configured to obtain the in-vehicle and out-vehicle environment data of the target vehicle, input the in-vehicle and out-vehicle environment data into the target air outlet control model, and obtain a target air outlet control strategy, where the target air outlet control strategy includes target initial air outlet configuration information and a target air outlet configuration adjustable range; An air outlet control module, configured to perform air outlet control on the on-vehicle air conditioner of the target vehicle according to the target initial air outlet configuration information, and obtain the physiological state change data and sitting posture change data of the target user; An adjustment prediction module, configured to input the physiological state change data and the sitting posture change data into a pre-trained air outlet adjustment prediction model to obtain a target adjustment trend and a target adjustment ratio; An air outlet adjustment module, configured to determine air outlet configuration adjustment information according to the target adjustment trend, the target adjustment ratio, and the target air outlet configuration adjustable range, and perform air outlet adjustment on the on-vehicle air conditioner according to the air outlet configuration adjustment information.

9. An in-vehicle air conditioner air outlet control device based on machine vision, characterized in that, Comprising: At least one processor; At least one memory, configured to store at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements a machine vision-based on-vehicle air conditioner air outlet control method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that, The program executable by the processor, when executed by the processor, is used to execute a machine vision-based on-vehicle air conditioner air outlet control method according to any one of claims 1 to 7.

Images