Air supply control method, system, device and storage medium for vehicle air conditioner

By acquiring information from inside the vehicle and using neural networks to identify humidity levels, the system automatically adjusts the temperature and direction of the vehicle's air conditioning, solving the problem of cold air blowing directly on the human body and improving passenger comfort and experience.

CN118722140BActive Publication Date: 2026-01-16GUANGZHOU AUTOMOBILE GROUP CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202410910175.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-08
Publication Date
2026-01-16
Estimated Expiration
2044-07-08

AI Technical Summary

Technical Problem

The existing vehicle air conditioning systems primarily rely on manual operation for adjusting the temperature, fan speed, and airflow direction. This results in discomfort when cold air blows directly on the body and makes it difficult to quickly dry wet clothes, thus affecting the passenger experience.

Method used

By acquiring image information of the seats inside the vehicle, as well as information on the temperature and humidity of the people's body surface, a pre-trained neural network is used to identify the dryness and humidity attributes, and the air supply temperature and direction are automatically adjusted according to these attributes to control the vehicle's air conditioning system to deliver air.

Benefits of technology

It automatically adjusts the airflow direction and temperature of the air conditioning vents according to the dryness of the clothes of the people in the seats, reducing the direct blowing of cold air on the people while speeding up the drying of wet clothes, thus improving the riding experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118722140B_ABST
    Figure CN118722140B_ABST
Patent Text Reader

Abstract

The application provides a kind of air supply control method of vehicle-mounted air conditioner, comprising the following steps: obtaining image information of each seat in the vehicle, body surface temperature information of personnel in the seat and humidity information in the vehicle;The obtained information is input into the neural network trained in advance, to obtain the dry and wet degree attribute on the body of each personnel in the seat;According to the dry and wet degree attribute on the body of each personnel, the corresponding air supply temperature is obtained, and the vehicle-mounted air conditioner is controlled to supply air to the corresponding personnel in the seat at the air supply temperature.Processing. The application also discloses a corresponding system, device and storage medium. By implementing the application, the dry and wet degree of the clothes of the personnel in the seat can be automatically detected, and the temperature of the corresponding air conditioner outlet can be automatically adjusted, which can reduce the excessive cold air of the air conditioner blowing directly on the human body, speed up the drying of dry and wet clothes, and improve the experience.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the field of automobile technology, in particular to a method, system and device for air supply control of a vehicle air conditioner and a storage medium. BACKGROUND

[0002] As an important device for improving the comfort of car riding, the vehicle air conditioner is an indispensable part in the car. When the temperature inside and outside the car is high, the pores of the human body will spread sweat, which will wet the clothes. If the vehicle air conditioner is used to blow cold air directly to the human body when the sweat has not stopped or the clothes have not dried, it will easily cause wind-chill if the time is too long. At the same time, because the cold air is not easy to dry the clothes, the clothes will still be wet after the human body adapts to the environment temperature, which will cause discomfort. Therefore, it is necessary to create a suitable environment in the car to ensure the normal driving or riding feeling of the people in the car and avoid the influence of high temperature in the car on the fatigue, comfort and driving efficiency of the people in the car.

[0003] However, the cold and hot air adjustment, air speed adjustment and air direction adjustment of the existing vehicle air conditioner are basically manual, and manual adjustment is often performed when the person is uncomfortable due to direct blowing of cold air.

[0004] Therefore, there is an urgent need for a new control method for the vehicle air conditioner, which can automatically realize the functions of cold and hot air adjustment, air speed adjustment and air direction adjustment, so as to reduce the direct blowing of too much cold air of the air conditioner to the human body and accelerate the drying of wet clothes, thereby improving the experience. SUMMARY

[0005] The technical problem to be solved by the embodiments of the present application is to provide a method, system and device for air supply control of a vehicle air conditioner and a storage medium, which can automatically adjust the temperature of the air outlet of the air conditioner according to the dryness and wetness of the clothes of the people in the seats, can reduce the direct blowing of too much cold air of the air conditioner to the human body and accelerate the drying of wet clothes, and improve the experience.

[0006] In order to solve the above technical problems, the embodiments of the present application provide a method for air supply control of a vehicle air conditioner, which at least includes the following steps:

[0007] Obtain image information of each seat in the vehicle, body surface temperature information of the people in the seats and humidity information in the vehicle;

[0008] Input the obtained information into a pre-trained neural network to obtain the dryness and wetness attributes of the people in each seat;

[0009] Obtain the corresponding air supply temperature according to the dryness and wetness attributes of the people, and control the vehicle air conditioner to supply air to the corresponding people in the seats at the air supply temperature.

[0010] The obtained information is input into a pre-trained neural network to obtain the dry-wet degree attribute of each person in each seat, and the method further comprises:

[0011] The obtained image information, humidity information, and humidity information are input into a pre-set and trained neural network;

[0012] According to the plurality of region block information pre-divided for each seat in the vehicle, the dry-wet degree attribute of each region block in each seat is obtained through the neural network analysis;

[0013] The dry-wet degree attribute of the region block with a human body area ratio greater than a preset threshold in the recognition result is determined as a person attribute; the dry-wet degree attribute of the region block with a wet clothes area ratio greater than a preset threshold in the recognition result is determined as a wet clothes attribute; the dry-wet degree attribute of the region block with a dry clothes area ratio greater than a preset threshold in the recognition result is determined as a dry clothes attribute; and the dry-wet degree attribute of the region block with other recognition results is determined as a no person attribute.

[0014] According to the dry-wet degree attribute of each person, the corresponding air supply temperature is obtained, and the vehicle-mounted air conditioner is controlled to supply air to the corresponding person in the seat at the air supply temperature, and the method further comprises:

[0015] The air supply sequence of the air supply port of each seat region to each region block of the seat is obtained, and the corresponding air supply region block of the person is determined;

[0016] According to the dry-wet degree attribute of the corresponding air supply region block of each person, the corresponding air supply temperature is calculated and obtained;

[0017] The air supply port of the vehicle-mounted air conditioner is controlled to supply air to the corresponding air supply region block of the person at the calculated air supply temperature, and the process is continued for a predetermined time.

[0018] According to the dry-wet degree attribute of the corresponding air supply region block of each person, the corresponding air supply temperature is calculated and obtained, and the method further comprises:

[0019] For the region block with a person attribute, the corresponding air supply temperature T 人 is calculated by the following formula:

[0020] T 人 = T 体 -(a1*N 无 +a2*N 干 +a3*N 人 +a4*N 湿 ) / M;

[0021] For the region block with a dry clothes attribute, the corresponding air supply temperature T 干:

[0022] T 干 =T 体 -(b1*N 无 +b2*N 干 +b3*N 人 +b4*N 湿 ) / M;

[0023] For the region block with the wetness attribute of wet clothes attribute, the corresponding supply air temperature T 湿 is calculated by the following formula:

[0024] T 湿 =T 体 -(c1*N 无 +c2*N 干 +c3*N 人 +c4*N 湿 ) / M;

[0025] Wherein, T 体 is the body surface temperature value of the person in the corresponding seat; N 无 is the number of region blocks with no one attribute; N 干 is the number of region blocks with dry clothes attribute; N 人 is the number of region blocks with someone attribute; N 湿 is the number of region blocks with clothes attribute; M is the number of region blocks divided by the seat area; a1, a2, a3 and a4, b1, b2, b3 and b4, c1, c2, c3 and c4 are respectively preset weight values between (0, 1).

[0026] Further comprising:

[0027] A coordinate system is established for each seat in advance, and a plurality of horizontally and vertically arranged region blocks of a predetermined size divided by each seat area are determined according to the center of each region block to determine the coordinate information of each region block.

[0028] The neural network comprises the following structure:

[0029] An input layer is used to receive image information, temperature value and humidity value;

[0030] A feature extraction layer uses a VGG16 or ResNet pre-trained CNN model as a basis to extract clothes and dryness features in the image; temperature and humidity features are input into a fully connected layer to extract features related to clothes dryness;

[0031] A feature fusion layer is used to fuse image features and temperature and humidity features by splicing, combine features from different sources to form a fused feature vector;

[0032] a hidden layer with a non-linear activation function;

[0033] an output layer using a Sigmoid activation function to map the output value between 0, 1, for representing the area proportion of the clothes wet part.

[0034] Correspondingly, the application also provides a kind of air supply control system of vehicle-mounted air conditioner, it at least includes:

[0035] vehicle interior information acquisition unit, for obtaining the image information of each seat in vehicle, the body surface temperature information of personnel in seat and the humidity information in vehicle interior;

[0036] dry and wet degree attribute acquisition unit, for inputting the information obtained into neural network trained in advance, obtains the dry and wet degree attribute on the body of each personnel in seat;

[0037] air supply control unit, for obtaining corresponding air supply temperature according to the dry and wet degree attribute on the body of each personnel, and controls vehicle-mounted air conditioner to carry out air supply processing to corresponding personnel in seat with the air supply temperature.

[0038] Wherein, the dry and wet degree attribute acquisition unit further includes:

[0039] input unit, for inputting the image information, humidity information and humidity information obtained into neural network set in advance and trained;

[0040] analysis and identification unit, for obtaining the dry and wet degree attribute of each region block in each seat by neural network analysis according to multiple region block information divided in advance for each seat in vehicle interior;Wherein, the dry and wet degree attribute of region block in which human body area proportion is greater than preset threshold in identification result is determined as person attribute;The dry and wet degree attribute of region block in which wet clothes area proportion is greater than preset threshold in identification result is determined as wet clothes attribute;The dry and wet degree attribute of region block in which dry clothes area proportion is greater than preset threshold in identification result is determined as dry clothes attribute;The dry and wet degree attribute of region block in other identification result is determined as no person attribute.

[0041] Wherein, the air supply control unit further includes:

[0042] current air supply region block determination unit, for obtaining the air supply sequence of air supply port of each seat region to each region block of seat of preconfigured each seat region, determines the air supply region block of personnel corresponding;

[0043] air supply temperature calculation unit, for calculating the air supply temperature corresponding to each personnel according to the dry and wet degree attribute of air supply region block corresponding to each personnel;

[0044] The air supply processing unit controls the air outlets of the vehicle's air conditioning system to supply air to the corresponding air supply areas of personnel at the calculated air supply temperature for a predetermined time.

[0045] The supply air temperature calculation unit calculates the supply air temperature for each current supply air zone block in the following manner:

[0046] For an area block with a humidity level attribute indicating occupancy, the corresponding supply air temperature T is calculated using the following formula. 人 :

[0047] T 人 =T 体 -(a1*N 无 +a2*N 干 +a3*N 人 +a4*N 湿 ) / M;

[0048] For a zone with a moisture content attribute of "dry clothes", the corresponding supply air temperature T is calculated using the following formula. 干 :

[0049] T 干 =T 体 -(b1*N 无 +b2*N 干 +b3*N 人 +b4*N 湿 ) / M;

[0050] For a region with a wet clothing attribute, the corresponding supply air temperature T is calculated using the following formula. 湿 :

[0051] T 湿 =T 体 -(c1*N 无 +c2*N 干 +c3*N 人 +c4*N 湿 ) / M;

[0052] Among them, T 体 This corresponds to the body surface temperature of the person in the seat; N 无 N represents the number of unoccupied region blocks. 干 N represents the number of regions with the drying property. 人 N represents the number of areas with human attributes; 湿 M represents the number of regions with the wet clothing attribute; M represents the number of regions divided into the seat area; a1, a2, a3 and a4, b1, b2, b3 and b4, c1, c2, c3 and c4 are preset weight values ​​located between (0, 1).

[0053] Correspondingly, the embodiment of the present application further provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the air supply control method of the vehicle-mounted air conditioner when executing the program.

[0054] Correspondingly, the embodiment of the present application further provides a storage medium storing computer executable instructions for executing the air supply control method of the vehicle-mounted air conditioner when executed by a computer processor.

[0055] The embodiment of the present application has the following beneficial effects:

[0056] The present application provides an air supply control method, system, device and storage medium of a vehicle-mounted air conditioner. By obtaining image information of each seat, body surface temperature information of a person in the seat, and indoor humidity information, and inputting them into a pre-trained neural network, the dry and wet degree attribute of the person on each seat is obtained; the corresponding air supply temperature is obtained according to the dry and wet degree attribute, and the vehicle-mounted air conditioner is controlled to sequentially supply air to the corresponding person in the seat at the corresponding air supply temperature. Thus, the air direction and temperature of the corresponding air outlet of the air conditioner can be automatically adjusted according to the dry and wet degree of the clothes of the person in the seat, which can reduce the direct blowing of too much cold air of the air conditioner to the human body and accelerate the blowing of dry and wet clothes, thereby improving the experience. BRIEF DESCRIPTION OF DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings obtained according to these drawings without creative labor are still within the scope of the present application.

[0058] Figure 1 A main flowchart of an embodiment of the air supply control method of the vehicle-mounted air conditioner provided by the present application;

[0059] Figure 2 A detailed flowchart of a specific application scenario of the air supply control method of the vehicle-mounted air conditioner provided by the present application;

[0060] Figure 3 A structure diagram of an embodiment of the air supply control system of the vehicle-mounted air conditioner provided by the present application;

[0061] Figure 4 A structure diagram of the dry and wet degree attribute obtaining unit provided by the present application; Figure 3 A structure diagram of the dry and wet degree attribute obtaining unit provided by the present application;

[0062] Figure 5 A structure diagram of the dry and wet degree attribute obtaining unit provided by the present application; Figure 3A structure diagram of a central air supply control unit;

[0063] Figure 6 A main structure diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0064] To make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings.

[0065] As Figure 1 shown, a main flow diagram of an embodiment of a vehicle air conditioning air supply control method provided by the present application is shown. In combination with Figure 2 shown, the method at least includes the following steps:

[0066] Step S10, obtaining image information of each seat in the vehicle, body surface temperature information of the person in the seat, and vehicle humidity information;

[0067] Step S11, inputting the obtained information into a pre-trained neural network to obtain the dry and wet degree attribute on the body of each person in the seat;

[0068] Step S12, obtaining the corresponding air supply temperature according to the dry and wet degree attribute on the body of each person, and controlling the vehicle air conditioner to perform air supply processing on the corresponding person in the seat at the air supply temperature.

[0069] The steps of the method of the embodiment of the present application will be described in detail below.

[0070] Specifically, in the embodiment of the present application, a coordinate system needs to be established for each seat in advance, and each seat area is divided into a plurality of predetermined size area blocks arranged horizontally and vertically in the coordinate system, and the coordinate information of each area block is determined according to the center of each area block. In a specific example, each seat area can be divided into a nine-square grid form.

[0071] In an example, the step S10 of obtaining the image information of each seat in the vehicle, the body surface temperature information of the person in the seat, and the vehicle humidity information is specifically:

[0072] The image information P of each seat is obtained by a plurality of cameras arranged in the vehicle; 图 The body surface temperature value T of the person in the seat is obtained by an infrared sensor arranged in the vehicle; 体 The vehicle humidity value H is obtained by a humidity sensor arranged in the vehicle; 湿 It can be understood that the humidity sensor can be multiple, for example, a humidity sensor can be arranged near each seat to detect the humidity of the clothes of the person in the vehicle;

[0073] It can be understood that in specific examples, by installing multiple cameras in the vehicle, for example, the cameras can be installed on the rearview mirror, steering wheel, A-pillar and B-pillar to capture images of the seats and the people in the seats. Each seat in the vehicle corresponds to a set of monitoring equipment, and each seat can correspond to at least one camera, an infrared sensor, at least one humidity sensor and a temperature sensor installed in the vehicle. In some examples, a humidity sensor can be additionally installed on the side of the seat to further obtain the clothing humidity information of the back of the person.

[0074] In some examples, once it is detected that a user has sat in the vehicle, the temperature in the vehicle is obtained by the temperature sensor in the vehicle, and it is determined whether the temperature in the vehicle is greater than or equal to a first temperature threshold (such as 27°C). If the temperature in the vehicle is >= the first temperature threshold (such as 27°C), the vehicle-mounted air conditioner is started to automatically cool. At the same time, the body surface temperature of the user is obtained by the infrared sensor installed near each seat, the image of the seat area where the user sits (i.e., the image of the area near the person and the seat) is obtained by the camera in the vehicle, and the humidity information in the vehicle is obtained by the humidity sensor.

[0075] In an embodiment of the present application, the step S11 of inputting the obtained information into a pre-trained neural network to obtain the dryness and wetness degree attributes of the people on each seat comprises:

[0076] The obtained image information, humidity value, and humidity value are input into a pre-set and trained neural network;

[0077] According to the plurality of region block information pre-divided for each seat in the vehicle, the dryness and wetness degree attributes of each region block in each seat are obtained by the neural network analysis;

[0078] The dryness and wetness degree attribute of the region block whose body area ratio is greater than a preset threshold in the recognition result is determined as the person attribute; the dryness and wetness degree attribute of the region block whose wet clothes area ratio is greater than a preset threshold in the recognition result is determined as the wet clothes attribute; the dryness and wetness degree attribute of the region block whose dry clothes area ratio is greater than a preset threshold in the recognition result is determined as the dry clothes attribute; and the dryness and wetness degree attribute of the region block with other recognition results is determined as the no person attribute.

[0079] In an embodiment of the present application, the neural network is pre-trained and can include the following structure:

[0080] The input layer is used to receive image information, temperature value and humidity value; specifically, P 图 After preprocessing (such as scaling to uniform size), the image information is sent to the subsequent CNN to extract features; T 体 Directly as an input node; H 湿 Directly as an input node;

[0081] The feature extraction layer uses a VGG16 or ResNet pre-trained CNN model as the basis to extract the clothing and dry-wet features in the image; the temperature and humidity features are input into the fully connected layer for linear transformation and non-linear planning to extract features related to clothing dry-wet;

[0082] The feature fusion layer is used to fuse the image features and temperature and humidity features through splicing, combine features from different sources, and form a fused feature vector from the combined features from different sources;

[0083] The hidden layer has a non-linear activation function to increase the non-linear expression capability of the model;

[0084] The output layer uses a Sigmoid activation function to map the output value to between 0 and 1, which is used to represent the area portion of the wet clothing.

[0085] At this time, the training method is supervised learning. By using a labeled data set for training, by comparing the difference between the calculated result and the actual result, and by updating the model parameters through the optimizer.

[0086] In a specific example, when the image recognized by the neural network shows that the area of the human body in a region block is greater than a preset first percentage (such as 90%) in the current region block, the dry-wet degree attribute of the region block is determined as the person attribute I 人 ;

[0087] When the image recognized by the neural network shows that the area of the wet clothing in a region block is greater than a preset second percentage (such as 90%) in the current region block, the dry-wet degree attribute of the region block is determined as the wet clothing attribute I 湿 ;

[0088] When the image recognized by the neural network shows that the area of the dry clothing in a region block is greater than a preset third percentage (such as 90%) in the current region block, the dry-wet degree attribute of the region block is determined as the dry clothing attribute I 干 ;

[0089] When the image recognized by the neural network shows that the region block does not meet the above three situations, the dry-wet degree attribute of the region block is determined as the no person attribute I 无 .

[0090] In a specific example, the step S12 obtains the corresponding supply air temperature according to the dry-wet degree attribute of each person, and controls the vehicle-mounted air conditioner to supply air to the corresponding person in the seat at the supply air temperature, further comprising:

[0091] Step S120, obtaining the air supply sequence of each air supply port to the blocks of each seat area, and determining the air supply area block of each air supply port of the vehicle air conditioner corresponding to the personnel;

[0092] For example, in one example, the air supply sequence can be in the order of the size of the coordinates of each block of each seat area, such as in the order of small to large, and the air supply can be performed in sequence; it can be understood that other air supply sequences can also be used in other examples, such as a wet clothing attribute priority air supply sequence.

[0093] Step S121, calculating the corresponding air supply temperature according to the dry and wet degree attribute of the air supply area block corresponding to each personnel;

[0094] In this step, the number of blocks with people, the number of blocks with dry clothes, the number of blocks with wet clothes, and the number of blocks without people are obtained, and the air supply temperature corresponding to each type of block is calculated in combination with the body surface temperature of the user.

[0095] Specifically, in one example, the step S121 further comprises:

[0096] For the blocks with the dry and wet degree attribute of people, the corresponding air supply temperature T is calculated by the following formula 人 :

[0097] T 人 =T 体 -(a1*N 无 +a2*N 干 +a3*N 人 +a4*N 湿 ) / M;

[0098] For the blocks with the dry and wet degree attribute of dry clothes, the corresponding air supply temperature T is calculated by the following formula 干 :

[0099] T 干 =T 体 -(b1*N 无 +b2*N 干 +b3*N 人 +b4*N 湿 ) / M;

[0100] For the blocks with the dry and wet degree attribute of wet clothes, the corresponding air supply temperature T is calculated by the following formula 湿 :

[0101] T 湿 =T 体 -(c1*N 无 +c2*N 干+c3*N 人 +c4*N 湿 ) / M;

[0102] For an area block with a humidity level attribute of "unoccupied", the corresponding supply air temperature T is calculated using the following formula. 无 :

[0103] T 无 =T 体 -d;

[0104] Among them, T 体 This corresponds to the body surface temperature of the person in the seat;

[0105] N 无 The dryness / wetness attribute is unmanned attribute I. 无 The number of area blocks; it is understandable that the statistical range can be within the nine-square grid of the seating area;

[0106] N 干 The region I has the attribute of dryness / wetness as dry clothes. 干 The number;

[0107] N 人 Block I is a region with a wet / dry attribute and a human presence attribute. 人 The number;

[0108] N 湿 The dryness / wetness attribute is the wet clothing attribute I. 湿 The number of region blocks;

[0109] M represents the number of blocks that divide the seating area into;

[0110] a1, a2, a3 and a4, b1, b2, b3 and b4, c1, c2, c3 and c4 are preset weight values ​​located between (0, 1);

[0111] d is the preset temperature difference value.

[0112] In a specific example, the weight values ​​of each formula and the temperature difference value can be set as follows:

[0113] a1=0.6, a2=0.6, a3=0.5, a4=0.2;

[0114] b1=0.8, b2=0.6, b3=0.5, b4=0.3;

[0115] c1=0.6, c2=0.5, c3=0.4, c4=0.2;

[0116] d = 1.5℃.

[0117] Through the above numerical setting, the wet clothes attribute corresponding air supply temperature N 湿 is higher than the dry clothes attribute corresponding air supply humidity N 干 , the influence of air conditioning cold wind directly blowing on the human body to cause wind cold can be reduced, and the wet clothes are blown dry, and the use experience of the person in the seat is improved.

[0118] Step S122, control the air supply port of the vehicle-mounted air conditioner to perform air supply processing on the corresponding air supply area block of the person at the calculated air supply temperature, and continue for a predetermined time (such as 5 seconds).

[0119] Specifically, when the current area block of the air supply port is I 人 , the air supply temperature is adjusted to T 人 ; when the current area block of the air supply port is I 干 , the air supply temperature is adjusted to T 干 ; when the current area block of the air supply port is I 湿 , the air supply temperature is adjusted to T 湿 ; when the current area block of the air supply port is I 无 , the air supply temperature is adjusted to T 无 .

[0120] Further, in the implementation of the embodiments of the present application, some measures described below can also be considered and adopted:

[0121] It can be understood that in the step S11, the work of obtaining the dry and wet degree attribute of each area block can be periodically updated (such as once every 5 seconds); at the same time, the air supply sequence can also be polled with the same period, so that the air conditioning parameters can be dynamically adjusted to further reduce the air conditioning cold wind directly blowing on the human body, and to speed up the blowing of wet clothes, thereby improving the experience. Of course, when the temperature in the vehicle is less than the first temperature threshold (such as 27℃) in any period, the vehicle-mounted air conditioner is immediately stopped for cooling, so that the energy consumption of the vehicle can be dynamically reduced.

[0122] In the embodiments of the present application, the temperature in the vehicle can be controlled to be reduced before the user enters the vehicle in high temperature weather, therefore, the method further comprises: when the weather temperature at the location of the vehicle exceeds the second temperature threshold (such as 30℃), if there is no user in the vehicle, when it is detected that the outdoor temperature is greater than or equal to the third temperature threshold (such as 30℃) and the temperature difference between the outdoor temperature and the indoor temperature is greater than the preset second temperature value (such as 2℃), the vehicle-mounted air conditioner is started to automatically cool, and the temperature difference is kept equal to the second temperature value until the outdoor temperature is less than the third temperature threshold.

[0123] Specifically, first, based on the latitude and longitude information on the vehicle GPS, the city where the vehicle is located is determined to obtain the weather temperature in the weather information of the city where the vehicle is located. Secondly, it is judged whether the weather temperature exceeds the first temperature threshold (such as 30 DEG C). If the weather temperature exceeds the second temperature threshold 30 DEG C, it is determined that it is high temperature weather, so that the inside and outside cameras of the vehicle are started to detect whether there is a user in the vehicle.

[0124] Secondly, when it is detected that there is no user in the vehicle, it is judged whether the outside temperature is greater than or equal to the third temperature threshold (such as 30 DEG C). If the outside temperature >= the third temperature threshold (30 DEG C), it is continued to be judged whether the temperature difference between the outside temperature and the inside temperature is greater than the preset second temperature value (2 DEG C). If the outside temperature - the inside temperature = the temperature difference > the second temperature value 2 DEG C, the vehicle air conditioner is started to automatically cool to control the temperature difference to gradually decrease and keep the temperature difference = the second temperature value 2 DEG C.

[0125] Finally, when it is detected that the outside temperature < the third temperature threshold 30 DEG C, the control of the temperature difference = the second temperature value 2 DEG C by the vehicle air conditioner for automatic cooling is terminated.

[0126] Through such a setting, the use experience of the user can be improved while the energy consumption is reduced.

[0127] As shown in Figure 2 , a detailed flow chart of one specific application scenario of the air supply control method of the vehicle air conditioner provided by the application is shown; the following flow combined Figure 2 with the application scenario is described, which specifically includes the following steps:

[0128] Step 1: Obtain the current vehicle latitude and longitude position L to obtain the real-time weather temperature W of the location of the vehicle, and obtain the inside temperature T 内 , the outside temperature T 外 .

[0129] Step 2: According to the real-time weather temperature W of the location of the vehicle, the first temperature threshold is preset to determine whether the current weather belongs to high temperature weather; if it does not belong to high temperature weather, it jumps to step 8; otherwise, if it belongs to high temperature weather, it continues to execute step 3.

[0130] Step 3: If there is no one in the vehicle, when the outside temperature T 外 >= the third temperature threshold 30 DEG C and the temperature difference T 外 -T 内 between the outside temperature T 外 and the inside temperature T 内 > 2 DEG C, the vehicle air conditioner is automatically started to cool, and the temperature difference T 外 -T 内 = 2 DEG C is kept until the outside temperature T 外Cooling stops when the third temperature threshold of 30°C is reached, thus terminating the control of the aforementioned 2°C temperature difference.

[0131] Step 4: If someone is seated inside the vehicle, then set the temperature inside the vehicle to T. 内 When the second temperature threshold of 27℃ is reached, the vehicle's air conditioning will automatically start to cool the vehicle and will blow air through a swing mode until the interior temperature reaches T. 内 The vehicle's air conditioning will stop working when the second temperature threshold of 27°C is reached.

[0132] Step 5: Obtain an image of the current seat (including the human body) area using the in-vehicle camera. 图 Human body surface temperature T is obtained through infrared sensors. 体 And obtain the current humidity H in the seat area (including the human body) through a humidity sensor. 湿 The coordinates I of the area block with human attributes are updated every 5 seconds using neural network calculation. 人 (Xi, Yi), the coordinates of the region block with the wet clothing attribute. 湿 (Xo, Yo), the coordinates of the region block with the drying attribute. 干 (Xp, Yp).

[0133] The area blocks are divided into nine-square grids based on each seat area. At this time, the coordinate I(X,Y) is the center point of a square block with a variable length of a centimeters. The specific value of a can be defined according to the air conditioning air supply zone.

[0134] I 人 (Xi, Yi) represents a region whose area occupies more than 90% of the image recognition area; in this case, the region is considered I. 人 ;I 湿 (Xo, Yo) represents the image P generated by combining the current seat (including human body) region image with the corresponding neural network. 图 Human body surface temperature T 体 Current humidity H in the seating area (including the human body) 湿 Parameter input determines whether the wet portion of the clothing area occupies more than 90% of the area; if so, the area is considered an I region. 湿 ;

[0135] I 干 (Xp, Yp) represents the image P generated by combining the current seat (including human body) region image with the corresponding neural network. 图 Human body surface temperature T 体 Current humidity H in the seating area (including the human body) 湿 Parameter input determines whether the dry portion of the clothing area occupies more than 90% of the area of ​​the region; in this case, the region is considered an I. 干 ;

[0136] I 无 (Xq, Yq): Not I人 (Xi, Yi), I 湿 (Xo, Yo), I 干 (Xp, Yp) of the region block.

[0137] Step 6: The air conditioner circulates air supply in the order of the sorted region blocks (X1, Y1)→(X2, Y2)→…→(X9, Y9) with a 5s period.

[0138] Step 7: When the current region block of the air conditioner air supply outlet is I 人 , adjust its air supply temperature to T 人 ; when the current region block of the air conditioner air supply outlet is I 干 , adjust its air supply temperature to T 干 ; when the current region block of the air conditioner air supply outlet is I 湿 , adjust its air supply temperature to T 湿 ; when the current region block of the air conditioner air supply outlet is I 无 , adjust its air supply temperature to T 无 .

[0139] T 人 : the air supply temperature of the air conditioner, its value = T 体 -(0.6*N 无 +0.6N 干 +0.5N 人 +0.2N 湿 ) / 9, the weight can be diagnosed service configuration;

[0140] T 干 : the air supply temperature of the air conditioner, its value = T 体 -(0.8*N 无 +0.6N 干 +0.5N 人 +0.3N 湿 ) / 9, the weight can be diagnosed service configuration;

[0141] T 湿 : the air supply temperature of the air conditioner, its value = T 体 -(0.6*N 无 +0.5N 干 +0.4N 人 +0.2N 湿 ) / 9, the weight can be diagnosed service configuration.

[0142] T 无 : the air supply temperature of the air conditioner, its value = T 体 -1.5℃, the difference value can be diagnosed service configuration.

[0143] Step 8: Turn off the air conditioner and stop air supply.

[0144] Step 9: End.

[0145] As Figure 3 shown, a structural schematic diagram of an embodiment of an air supply control system of a vehicle air conditioner provided by the present application is shown. In combination with Figure 4 and Figure 5 shown, in the present embodiment, the air supply control system 1 of the vehicle air conditioner at least includes:

[0146] an in-vehicle information acquisition unit 10 for acquiring image information of each seat in the vehicle, body surface temperature information of a person in the seat, and in-vehicle humidity information;

[0147] a dry-wet degree attribute acquisition unit 11 for inputting the acquired information into a pre-trained neural network to obtain a dry-wet degree attribute on the person in each seat, the dry-wet degree attribute at least including a person attribute, a dry clothes attribute, and a wet clothes attribute;

[0148] an air supply control unit 12 for obtaining a corresponding air supply temperature according to the dry-wet degree attribute on each person, and controlling the vehicle air conditioner to perform air supply processing on the corresponding person in the seat at the air supply temperature.

[0149] Specifically, as Figure 4 shown, the dry-wet degree attribute acquisition unit 11 further includes:

[0150] an input unit 110 for inputting the acquired image information, humidity value, and humidity value into a pre-set and trained neural network;

[0151] an analysis and recognition unit 111 for obtaining a dry-wet degree attribute of each region block in each seat by analyzing the neural network according to a plurality of region block information pre-divided for each seat in the vehicle;

[0152] wherein the dry-wet degree attribute of a region block with a body area proportion greater than a preset threshold in the recognition result is determined as the person attribute; the dry-wet degree attribute of a region block with a wet clothes area proportion greater than a preset threshold in the recognition result is determined as the wet clothes attribute; the dry-wet degree attribute of a region block with a dry clothes area proportion greater than a preset threshold in the recognition result is determined as the dry clothes attribute; and the dry-wet degree attribute of a region block with other recognition results is determined as the no person attribute.

[0153] Specifically, as Figure 5 shown, the air supply control unit 12 further includes:

[0154] a current air supply region block determination unit 120 for acquiring an air supply sequence of each seat region of a pre-configured air supply port of the seat, and determining a corresponding air supply region block of a person associated with each air supply port of the vehicle air conditioner;

[0155] The air supply temperature calculation unit 121 is configured to calculate the air supply temperature of each air supply area block according to the dry-wet degree attribute of the air supply area block corresponding to each person;

[0156] The air supply processing unit 122 is configured to control the air supply port of the vehicle air conditioner to perform air supply processing on the air supply area block corresponding to each person at the calculated air supply temperature, and continue for a predetermined time.

[0157] The air supply temperature calculation unit 121 calculates the air supply temperature of each current air supply area block in the following manner:

[0158] For the air supply area block with the person attribute, the air supply temperature T corresponding to the air supply area block is calculated by the following formula: 人 :

[0159] T 人 = T 体 -(a1*N 无 +a2*N 干 +a3*N 人 +a4*N 湿 ) / M;

[0160] For the air supply area block with the clothes drying attribute, the air supply temperature T corresponding to the air supply area block is calculated by the following formula: 干 :

[0161] T 干 = T 体 -(b1*N 无 +b2*N 干 +b3*N 人 +b4*N 湿 ) / M;

[0162] For the air supply area block with the clothes drying attribute, the air supply temperature T corresponding to the air supply area block is calculated by the following formula: 湿 :

[0163] T 湿 = T 体 -(c1*N 无 +c2*N 干 +c3*N 人 +c4*N 湿 ) / M;

[0164] For the air supply area block with the no person attribute, the air supply temperature T corresponding to the air supply area block is calculated by the following formula: 无 :

[0165] T 无 = T 体 -d;

[0166] wherein T 体N is the number of the region blocks with the body surface temperature value corresponding to the person in the seat; N 无 N is the number of the region blocks with the dry-wet degree attribute being the no person attribute; 干 N is the number of the region blocks with the dry-wet degree attribute being the dry clothes attribute; 人 N is the number of the region blocks with the dry-wet degree attribute being the person attribute; 湿 N is the number of the region blocks with the dry-wet degree attribute being the wet clothes attribute; M is the number of the region blocks divided by the seat region; a1, a2, a3 and a4, b1, b2, b3 and b4, c1, c2, c3 and c4 are preset weight values between (0, 1) respectively; and d is a preset temperature difference value.

[0167] For more details, refer to the foregoing descriptions of the Figure 1 and Figure 2 , which will not be repeated here.

[0168] As another aspect of the present application, in one embodiment, an electronic device is also provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the aforementioned air supply control method of the vehicle-mounted air conditioner when executing the program.

[0169] As still another aspect of the present application, in one embodiment, a storage medium storing computer executable instructions is provided, which, when executed by a computer processor, is used to execute the aforementioned air supply control method of the vehicle-mounted air conditioner.

[0170] It is worth noting that in the above system embodiment, each system unit included is only divided according to functional logic, but is not limited to the above division, as long as the corresponding function can be implemented; in addition, the specific names of each functional unit are only for the convenience of mutual differentiation, and are not used to limit the protection scope of the present application.

[0171] At this time, each system unit of the above system embodiment can be integrated on a physical entity in whole or in part, or can be physically separated. These system units can all be implemented in the form of software called by a processing element, or can all be implemented in the form of hardware, or some components can be implemented in the form of software called by a processing element, and some components can be implemented in the form of hardware. For example, a certain above-mentioned module can be a separately established processing element, or can be implemented in a certain chip of an electronic device. The implementation of other components is similar. In addition, all or part of these components can be integrated together, or can be independently implemented. In the implementation process, each step of the above method or each component can be completed by the integrated logic circuit of hardware or the instruction in the form of software in the processing element.

[0172] For example, the above components can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), or one or more Digital Signal Processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), etc. For another example, the components can be integrated together in the form of a System-On-a-Chip (SOC).

[0173] In light of the above embodiments and preferred solutions, those skilled in the art can understand that, in actual operations, the technical concept involved in the present application can be applied to various embodiments. The present application takes the following carrier as an illustrative description:

[0174] (1) An electronic device. The electronic device can specifically include one or more processors, a memory, and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions that, when executed by the electronic device, cause the electronic device to perform the steps / functions of the above embodiments or equivalent implementations. The electronic device can be a computer-related electronic device, such as, but not limited to, various interactive terminals and electronic products, such as a vehicle-mounted intelligent terminal, a mobile terminal, etc.

[0175] As shown in Figure 4 An electronic device provided in an embodiment of the present application. Specifically, the electronic device includes a processor 41 and a memory 42. The processor 41 and the memory 42 can communicate with each other through an internal connection path to transfer control and / or data signals. The memory 42 is configured to store a computer program, and the processor 41 is configured to call and run the computer program from the memory 42. The processor 41 and the memory 42 can be integrated into one processing device, or more commonly, they are independent components. The processor 41 is configured to execute the program code stored in the memory 42 to implement the above functions. In specific implementations, the memory 42 can be integrated into the processor 41, or independent of the processor 41.

[0176] The processor 41 in the electronic device can be a system on chip (SOC), which can include a central processing unit (CPU) and can further include other types of processors, such as a graphics processing unit (GPU), and the like. In general, the various processors or processing units within the processor 41 can collectively implement the method steps / functions of the aforementioned embodiments or equivalent implementations. For more details, reference can be made to the foregoing description of Figures 1 to 2 .

[0177] (2) A computer data storage medium, which stores a computer program or the above-described apparatus, and when the computer program or the above-described apparatus is executed, causes a computer to perform the method steps / functions of the aforementioned embodiments or equivalent implementations. For more details, reference can be made to the foregoing description of Figures 1 to 2 .

[0178] (3) A computer program product, which includes a computer program / instruction, and the computer program / instruction can be stored on a storage medium, and when the computer program / instruction is executed by a processor, causes a computer to perform the method steps / functions of the aforementioned embodiments or equivalent implementations. For more details, reference can be made to the foregoing description of Figures 1 to 2 .

[0179] In several embodiments provided by the present application, any function, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer data storage medium. Based on such understanding, some technical solutions of the present application or parts of the technical solutions that make essential contributions or parts of the technical solutions can be embodied in the form of software products as described below.

[0180] In particular, it is pointed out that the storage medium can be a server or a similar computer device, and specifically, the storage medium can be a storage device in the server or the similar computer device that stores the aforementioned computer program or the above-described apparatus.

[0181] The implementation of the embodiments of the present application has the following beneficial effects:

[0182] The application provides a kind of air supply control method, system, equipment and storage medium of vehicle-mounted air conditioner. By obtaining the image information of each seat, the body surface temperature information of the personnel in the seat and the humidity information in the vehicle, and inputting into the neural network trained in advance, the dry and wet degree attribute on the personnel in each seat is obtained;According to the dry and wet degree attribute, the corresponding air supply temperature is obtained, and the vehicle-mounted air conditioner is controlled to sequentially air supply the corresponding personnel in the seat with the corresponding air supply temperature.Processing. Thus, the air direction and temperature of the corresponding air outlet of air conditioner can be automatically adjusted according to the dry and wet degree of the clothes of the personnel in the seat, which can reduce the direct blowing of excessive cold air of air conditioner to human body and speed up the blowing of dry and wet clothes, and improve the experience.

[0183] Those skilled in the art can appreciate that the modules, units and method steps described in the embodiments disclosed in the specification can be realized by electronic hardware, computer software and combination of electronic hardware and computer software. Whether the functions are realized by hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different ways to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0184] The above disclosure is only the preferred embodiment of the present application, and of course cannot limit the scope of the present application, so the equivalent changes made according to the claims of the present application still fall within the scope of the present application.

Claims

1. A method of air supply control of a vehicle air conditioner, characterized by, At least comprising the steps of: Obtaining image information of each seat in the vehicle, body surface temperature information of the person in the seat, and humidity information in the vehicle; Inputting the obtained information into a pre-trained neural network to obtain the dry and wet degree attribute of the person in each seat; According to the dry and wet degree attribute of each person, obtain the corresponding air supply temperature, and control the vehicle-mounted air conditioner to supply air to the corresponding person in the seat at the air supply temperature; Wherein, inputting the obtained information into a pre-trained neural network to obtain the dry and wet degree attribute of the person in each seat further comprises: Input the obtained image information, temperature information and humidity information into the pre-set and trained neural network; According to the region block information divided in advance for each seat in the vehicle, the dry and wet degree attribute of each region block in each seat is obtained by analyzing the neural network; Wherein, the dry and wet degree attribute of the region block with a human body area ratio greater than a preset threshold is determined as the person attribute; the dry and wet degree attribute of the region block with a wet clothes area ratio greater than a preset threshold is determined as the wet clothes attribute; the dry and wet degree attribute of the region block with a dry clothes area ratio greater than a preset threshold is determined as the dry clothes attribute; the dry and wet degree attribute of the region block with other identification results is determined as the no person attribute.

2. The method of claim 1, wherein, According to the dry and wet degree attribute of each person, obtain the corresponding air supply temperature, and control the vehicle-mounted air conditioner to supply air to the corresponding person in the seat at the air supply temperature, further comprising: Obtain the air supply sequence of each seat region of the air supply port to the seat region block, and determine the corresponding air supply region block of the person; According to the dry and wet degree attribute of the corresponding air supply region block of each person, calculate the corresponding air supply temperature; Control the air supply port of the vehicle-mounted air conditioner to supply air to the corresponding air supply region block of the person at the calculated air supply temperature, and continue for a predetermined time.

3. The method of claim 2, wherein, According to the dry and wet degree attribute of the corresponding air supply region block of each person, calculate the corresponding air supply temperature, further comprising: For the region block with the human attribute for the dryness and wetness degree attribute, the corresponding supply air temperature T is calculated by the following formula 人 : T 人 = T 体 - (a1*N 无 + a2*N 干 + a3*N 人 + a4*N 湿 ) / M; For the region block with the dryness attribute as the dry clothes attribute, the corresponding supply air temperature T is calculated by the following formula 干 : T 干 = T 体 - (b1*N 无 + b2*N 干 + b3*N 人 + b4*N 湿 ) / M; For the region block with the wetness attribute of wet clothes attribute, the corresponding supply air temperature T is calculated by the following formula 湿 : T 湿 = T 体 -(c1*N 无 + c2*N 干 + c3*N 人 + c4*N 湿 ) / M; wherein T 体 is a body surface temperature value of a person in the corresponding seat; N 无 is the number of region blocks with no one attribute; N 干 is the number of region blocks with dry clothes attribute; N 人 is the number of region blocks with someone attribute; N 湿 is the number of region blocks with wet clothes attribute; M is the number of region blocks divided by the seat region; a1, a2, a3, and a4, b1, b2, b3, and b4, c1, c2, c3, and c4 are preset weight values respectively located between (0, 1).

4. The method of claim 3, wherein, Further comprising: A coordinate system is established for each seat in advance, and each seat region is divided into a plurality of predetermined size region blocks arranged horizontally and vertically in the coordinate system, and the coordinate information of each region block is determined according to the center of each region block.

5. The method according to any one of claims 1 to 4, characterized in that, The neural network comprises the following structure: An input layer for receiving image information, temperature value and humidity value; A feature extraction layer using a VGG16 or ResNet pre-trained CNN model as a basis for extracting clothes and dry and wet features in the image; temperature and humidity features are input into a fully connected layer to extract features related to clothes dry and wet; A feature fusion layer for fusing image features and temperature and humidity features by splicing, combining features from different sources to form a fused feature vector; A hidden layer with a nonlinear activation function; An output layer using a Sigmoid activation function to map the output value to 0, 1, which is used to represent the area ratio of wet clothes.

6. An air supply control system for a vehicle air conditioner, characterized by comprising: At least comprising: An in-vehicle information acquisition unit for obtaining image information of each seat in the vehicle, body surface temperature information of the person in the seat, and humidity information in the vehicle; The dry-wet degree attribute obtaining unit is configured to input the obtained information into a pre-trained neural network to obtain the dry-wet degree attribute of each person on each seat; The air supply control unit is configured to obtain the air supply temperature corresponding to the dry-wet degree attribute of each person and control the vehicle-mounted air conditioner to supply air to the corresponding person on the seat at the air supply temperature; The dry-wet degree attribute obtaining unit further includes: The input unit is configured to input the obtained image information, temperature information, and humidity information into a pre-set and trained neural network; The analysis and recognition unit is configured to obtain the dry-wet degree attribute of each region block in each seat through the neural network analysis according to the region block information pre-divided for each seat in the vehicle. In the analysis and recognition unit, the dry-wet degree attribute of a region block in which the human body area ratio is greater than a preset threshold is determined as the person attribute; the dry-wet degree attribute of a region block in which the wet clothes area ratio is greater than a preset threshold is determined as the wet clothes attribute; the dry-wet degree attribute of a region block in which the dry clothes area ratio is greater than a preset threshold is determined as the dry clothes attribute; and the dry-wet degree attribute of a region block with other recognition results is determined as the no person attribute.

7. The system of claim 6, wherein, The air supply control unit further includes: The current air supply region block determining unit is configured to obtain the air supply sequence of the air supply port of each seat region to each region block of the seat and determine the air supply region block of the person; The air supply temperature calculation unit is configured to calculate the air supply temperature corresponding to the dry-wet degree attribute of the air supply region block of each person; The air supply processing unit is configured to control the air supply port of the vehicle-mounted air conditioner to supply air to the air supply region block of the person at the calculated air supply temperature and for a predetermined time.

8. The system of claim 7, wherein, The air supply temperature calculation unit calculates the air supply temperature of each current air supply region block in the following manner: For the region block with the human attribute for the dryness and wetness degree attribute, the corresponding supply air temperature T is calculated by the following formula 人 : T 人 = T 体 -(a1*N 无 + a2*N 干 + a3*N 人 + a4*N 湿 ) / M; For the region block with the dryness attribute as the dry clothes attribute, the corresponding supply air temperature T is calculated by the following formula 干 : T 干 = T 体 -(b1*N 无 + b2*N 干 + b3*N 人 + b4*N 湿 ) / M; For the region block with the wetness attribute of wet clothes attribute, the corresponding supply air temperature T is calculated by the following formula 湿 : T 湿 = T 体 - (cl * N 无 + c2 * N 干 + c3 * N 人 + c4 * N 湿 ) / M; wherein T 体 is a body surface temperature value of a person in the corresponding seat; N 无 is the number of region blocks with no one attribute; N 干 is the number of region blocks with dry clothes attribute; N 人 is the number of region blocks with someone attribute; N 湿 is the number of region blocks with wet clothes attribute; M is the number of region blocks divided by the seat region; a1, a2, a3, and a4, b1, b2, b3, and b4, c1, c2, c3, and c4 are preset weight values respectively located between (0, 1).

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the air supply control method of the vehicle-mounted air conditioner according to any one of claims 1 to 5 when executing the program.

10. A storage medium storing computer-executable instructions, wherein: The computer executable instructions are used to execute the air supply control method of the vehicle-mounted air conditioner according to any one of claims 1 to 5 when executed by the computer processor.

Citation Information

Patent Citations

  • Vehicle control system

    CN115723507A

  • Child seat with intelligent temperature and humidity adjusting function and vehicle

    CN117284175A

  • System and method for dynamic climate control

    CN117621751A