Temperature control method of vehicle, vehicle, electronic equipment and storage medium

Abstract

The invention relates to the technical field of vehicle control, and provides a vehicle temperature control method, a vehicle, electronic equipment and a storage medium. The method comprises the following steps: acquiring an article identification result in a vehicle, and if the identification result represents that the vehicle contains at least one preset target article, acquiring the temperature in the vehicle; determining a risk level corresponding to each target article according to the temperature in the vehicle, and determining a target risk level of the vehicle according to the risk level corresponding to each target article; a cooling strategy is determined according to the target risk level, and the cooling strategy is used for indicating cooling control over the vehicle so as to reduce the target risk level corresponding to the vehicle; according to the method and the device, the risk level of each target article can be monitored and adjusted, then the target risk level in the vehicle is integrally determined, cooling control is performed on the vehicle according to the target risk level, the temperature in the vehicle is reduced, then the risk level of each target article is reduced, and the safety of the vehicle is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a vehicle temperature control method, a vehicle, an electronic device, and a storage medium. Background Art

[0002] With the development of technology, vehicles have become an important means of transportation for people. However, when the temperature inside a car rises, many everyday items are prone to fire accidents under high temperatures. For example, lighters, perfume, power banks, cooling sprays, alcohol-based disinfectants, and other items can become safety hazards when the temperature inside the car rises.

[0003] Due to the negligence of car owners, the above dangerous goods are often left in the car, which increases the risk of accidents. Therefore, how to control the temperature of the vehicle to avoid safety accidents caused by the increase in temperature inside the car has become an urgent problem to be solved. Summary of the Invention

[0004] In view of this, the embodiments of the present application provide a vehicle temperature control method, a vehicle, an electronic device and a storage medium to solve the problem in the prior art that daily necessities are prone to cause safety accidents when the temperature in the vehicle rises.

[0005] In a first aspect of an embodiment of the present application, a vehicle temperature control method is provided, the method comprising: identifying items in the vehicle, and if the identification result indicates that the vehicle contains at least one pre-set target item, performing temperature detection on the vehicle to obtain the temperature inside the vehicle; determining the risk level corresponding to each target item based on the temperature inside the vehicle, and determining the target risk level of the vehicle based on the risk level corresponding to each target item; and performing cooling control on the vehicle based on the target risk level to reduce the target risk level corresponding to the vehicle.

[0006] In a second aspect of an embodiment of the present application, a vehicle is provided, comprising: an electronic control unit, the electronic control unit being used to obtain an identification result of items in the vehicle, and obtaining an interior temperature of the vehicle if the identification result indicates that the vehicle contains at least one pre-set target item; determining a risk level corresponding to each target item based on the interior temperature of the vehicle, and determining a target risk level of the vehicle based on the risk level corresponding to each target item; determining a cooling strategy based on the target risk level, the cooling strategy being used to instruct cooling control of the vehicle to reduce the target risk level corresponding to the vehicle.

[0007] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0008] According to a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the above method are implemented.

[0009] The beneficial effects of the embodiments of the present application compared with the prior art are as follows: the method in the embodiments of the present application identifies the items in the vehicle, and if the identification result indicates that the vehicle contains at least one pre-set target item, the vehicle is temperature-detected to obtain the temperature inside the vehicle; the risk level corresponding to each target item is determined according to the temperature inside the vehicle, and the target risk level of the vehicle is determined according to the risk level corresponding to each target item; the vehicle is cooled according to the target risk level to reduce the target risk level corresponding to the vehicle; wherein, the present application can monitor and adjust the risk level of each target item, and then determine the target risk level inside the vehicle as a whole, and cool the vehicle according to the target risk level, reduce the temperature inside the vehicle, and then reduce the risk level of each target item, thereby improving the safety of the vehicle and avoiding the problem in the related art that daily necessities are prone to cause safety accidents when the temperature inside the vehicle rises. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0011] Figure 1 This is a flow chart of a vehicle temperature control method provided by an embodiment of the present application; Figure 2 is a flow chart of another vehicle temperature control method provided by an embodiment of the present application; Figure 3 This is a schematic diagram of the network structure of an object recognition model provided in an embodiment of the present application; Figure 4 This is a basic schematic diagram of an implementation of an attention module provided in an embodiment of the present application; Figure 5 This is a schematic diagram of the working principle of an activation function provided in an embodiment of the present application; Figure 6 1 is a flow chart of another vehicle temperature control method provided in an embodiment of the present application; Figure 7 1 is a flow chart of another vehicle temperature control method provided in an embodiment of the present application; Figure 8is a flow chart of another optional vehicle temperature control method provided in an embodiment of the present application; Figure 9 1 is a flow chart of another optional vehicle temperature control method provided in an embodiment of the present application; Figure 10 This is a flow chart of another optional vehicle temperature control method provided in an embodiment of the present application; Figure 11 1 is a flow chart of another optional vehicle temperature control method provided in an embodiment of the present application; Figure 12 This is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0012] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0013] A vehicle temperature control method and a vehicle according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0014] Figure 1 This is a vehicle temperature control method provided by an embodiment of the present application, such as Figure 1 As shown, the method includes: S101, obtaining an identification result of an object in a vehicle, and if the identification result indicates that the vehicle contains at least one preset target object, obtaining the temperature in the vehicle; S102: Determine the risk level corresponding to each target item based on the temperature inside the vehicle, and determine the target risk level of the vehicle based on the risk level corresponding to each target item; S103. Determine a cooling strategy according to the target risk level. The cooling strategy is used to instruct to perform cooling control on the vehicle to reduce the target risk level corresponding to the vehicle.

[0015] It can be understood that the temperature control method of the vehicle provided in this example is applied to vehicles, including vehicles with automatic driving or intelligent driving (including vehicles with passenger functions (such as cars, buses, large buses, minibuses, etc.), cargo vehicles (such as ordinary trucks, vans, trailers, closed trucks, tank trucks, flatbed trucks, container trucks, dump trucks, special structure trucks), special vehicles (such as logistics distribution vehicles, automatic guided transport vehicles AGV, patrol cars, cranes, cranes, excavators, bulldozers, forklifts, rollers, loaders, off-road engineering vehicles, armored engineering vehicles, sewage treatment vehicles, sanitation vehicles, vacuum trucks, floor washing vehicles, sprinkler trucks, sweeping robots, food delivery robots, shopping guide robots, lawn mowers, golf carts, etc.), vehicles with entertainment functions (such as entertainment vehicles, amusement park automatic driving devices, balance cars, etc.), rescue vehicles (such as fire trucks, ambulances, power repair vehicles, engineering rescue vehicles, etc.)), etc.

[0016] It is understood that the vehicle is also equipped with one or more cameras capable of capturing images of the vehicle interior and subsequently identifying objects within the vehicle based on the captured images. Preferably, the one or more cameras provided in the vehicle have night vision capabilities and a wide-angle field of view to ensure that objects in every corner of the vehicle can be clearly captured under varying lighting conditions.

[0017] After obtaining a photo of the interior environment of the vehicle, this application will identify the items in the vehicle based on the photo of the environment; it can be understood that the types of items in this application include two types: target items and non-target items. Among them, target items are items that may cause fire accidents in a high temperature environment, such as lighters, perfume bottles, power banks, sprays, carbonated beverage cans and other items; non-target items are items that will not cause fire accidents in a high temperature environment.

[0018] It is understood that if a target object is present in a vehicle and the vehicle interior temperature is too high, the target object may cause a fire accident. Therefore, when the recognition result indicates that the vehicle contains at least one pre-set target object, the present application will obtain the vehicle interior temperature and perform subsequent control based on the vehicle interior temperature. If the recognition result indicates that the vehicle does not contain the pre-set target object, subsequent control based on the vehicle interior temperature will not be performed.

[0019] Among them, the present application realizes temperature detection of the vehicle through a temperature sensor installed on the vehicle, and the above-mentioned temperature sensor includes but is not limited to one of a resistance temperature sensor, an infrared temperature sensor, a semiconductor temperature sensor, and an optical fiber temperature sensor.

[0020] It is understandable that since different target items have different chemical properties and temperature sensitivities, different types of target items may exhibit different hazardous characteristics under temperature changes, thus corresponding to different risk levels. The risk level is used to characterize the level of safety accidents caused by the target items. The higher the risk level, the higher the possibility that the target item will cause a safety accident (for example, spontaneous combustion). The lower the risk level, the lower the possibility that the target item will cause a safety accident.

[0021] Continuing with the above example, based on the aforementioned reasons, this application will determine the risk level corresponding to each target item based on the temperature inside the vehicle. It is understood that the specific risk level corresponding to the target item can be flexibly set by relevant personnel based on the chemical properties, temperature sensitivity, and other characteristics of the target item.

[0022] In some examples, after determining the risk level corresponding to each target item, the present application will determine the target risk level of the vehicle based on the risk level corresponding to each target item; specifically, if there are at least two target items in the vehicle, the present application will compare the risk levels corresponding to the at least two target items, determine the highest risk level, and use the highest risk level as the target risk level; if there is only one target item in the vehicle, the present application will directly use the risk level corresponding to the target item as the target risk level.

[0023] In some examples, the present application will also determine a cooling strategy based on the target risk level. The cooling strategy is used to instruct cooling control of the vehicle, thereby lowering the temperature inside the vehicle, reducing the risk level of each target item, and thus achieving the effect of lowering the target risk level corresponding to the vehicle, thereby avoiding natural problems caused by overheating of the target item.

[0024] According to the technical solution provided in the embodiment of the present application, by obtaining the recognition results of the items in the vehicle, if the recognition results indicate that the vehicle contains at least one pre-set target item, the temperature in the vehicle is obtained; the risk level corresponding to each target item is determined according to the temperature in the vehicle, and the target risk level of the vehicle is determined according to the risk level corresponding to each target item; a cooling strategy is determined according to the target risk level, and the cooling strategy is used to instruct cooling control of the vehicle to reduce the target risk level corresponding to the vehicle; wherein, the present application can monitor and adjust the risk level of each target item, and then determine the target risk level in the vehicle as a whole, and cool the vehicle according to the target risk level, reduce the temperature in the vehicle, and then reduce the risk level of each target item, thereby improving the safety of the vehicle and avoiding the problem in the related art that daily necessities are prone to cause safety accidents after the temperature in the vehicle rises.

[0025] In some embodiments, Figure 2 As shown, before obtaining the recognition result of the object in the vehicle, the method further includes: S201: Obtain a model training sample, where the model training sample includes multiple items, and some items are pre-set with a label for indicating that the item is a target item; S202: Determine an object recognition model through model training samples, and use the object recognition model to perform object recognition.

[0026] Specifically, the present application uses an object recognition model to identify objects in the vehicle. Specifically, the environment picture inside the vehicle taken by the camera is input into the object recognition model to determine whether the vehicle contains the target object.

[0027] The object recognition model described in this application is a deep learning model. After training, this deep learning model can accurately identify target objects (such as perfume bottles, lighters, and power banks). This application obtains model training samples, which include multiple objects, some of which are pre-labeled to indicate that they are target objects. Specifically, by consulting relevant literature, regulations, and standards, target objects that may cause combustion at high temperatures (such as lighters, perfume bottles, power banks, sprays, and carbonated beverage cans) are identified. A camera is then used to capture photos of the target objects in different vehicle models and lighting conditions. The target objects are photographed from a variety of angles, including front, side, and overhead views, to simulate viewing conditions in real-world scenarios. It should be understood that this example does not limit the number of model training samples; illustratively, the number of model training samples is 5,000.

[0028] It is understandable that in order to enable the trained object recognition model to accurately identify the target object from different perspectives, this application will also perform image transformation, color adjustment, noise addition and other operations on the images in the model training samples. Specifically, image transformation is to rotate, scale, crop and other operations on the original images in the model training samples to simulate different observation angles and distances. Color adjustment is to change the brightness, contrast, saturation, etc. of the images in the model training samples to simulate different lighting conditions. This helps the trained object recognition model adapt to different lighting environments. Adding noise is to add Gaussian noise, salt and pepper noise, etc. to the images in the model training samples to simulate the noise interference of the camera sensor. This helps the trained object recognition model learn to maintain robustness in a noisy environment. The 5,000 original images collected are expanded to 10,000 valid images through data enhancement.

[0029] It is understandable that the model training samples contain multiple items, and some items are pre-set with labels for characterizing the items as target items. This application does not limit the method of setting labels for target items. For example, LabelImg is used to develop a labeling tool to label the target items with bounding boxes and label the target items with label information. The bounding box labeling is to draw a bounding box for each target item and record its position in the image (usually represented by the coordinates of the upper left and lower right corners). The bounding box will surround the item as closely as possible to reduce background noise. The label information of the target item is to assign a category label to each target item, such as "lighter", "perfume bottle", etc. This enables the model to learn to distinguish different types of items.

[0030] This application will divide the model training samples into a test set and a training set. For example, 9,000 images in the model training samples are the training set and 1,000 images are the test set.

[0031] Then, the initial object recognition model is trained using model training samples to obtain an object recognition model.

[0032] In order to better understand the above steps, this application uses a more specific example to illustrate. In this application, the YOLOv5s model is used as the initial object recognition model. The YOLOv5s model in this application introduces the ECA (Efficient Channel Attention) attention mechanism. The network structure diagram of the YOLOv5s model is as follows: Figure 3As shown, this application improves the representation ability of the network by using the ECA attention mechanism on the three feature maps output by the YOLOv5s backbone. In neural networks, the idea of ​​the attention mechanism is to assign different weights to different input parts. The specific implementation is to use an additional neural network to learn the importance of different input parts, so as to focus on important channels and suppress unimportant channels, thereby improving the learning ability of the network. The SE channel attention mechanism improves the representation ability of the network by explicitly modeling the interdependence between convolutional feature channels. It first converts the H×W×C feature map into a 1×1×C feature vector through global average pooling, and maps each channel to a number with a global receptive field. Then, the weight of each channel is obtained through an excitation network with two fully connected layers. Finally, the weight is multiplied by the input feature channel by channel to obtain the output feature. Through the analysis of SE, it is found that the two fully connected layers in SE reduce the computational complexity by first reducing and then expanding the channels, which will bring side effects. In addition, capturing the correlation of all feature channels is inefficient and unnecessary. Based on this, the ECA attention module is proposed. This module uses adaptive one-dimensional convolution to capture the correlation between each channel and its k neighboring channels, thereby obtaining the weight of each channel. Compared with the full connection, it has less computational complexity. Here, k is the size of the one-dimensional convolution kernel, which is calculated as follows: in, is the scaling factor, is the translation term, is the number of channels of the feature map.

[0033] The implementation process of the ECA attention mechanism is as follows Figure 4 As shown in the figure, first, the H×W×C feature matrix is ​​transformed into a 1×1×C feature vector through global average pooling. The adaptive one-dimensional convolution kernel kernel_size is calculated according to the number of channels of the input feature map. Then kernel_size is used in the one-dimensional convolution to obtain the weight of each channel of the entire feature map. Finally, the normalized weight is multiplied by the original input feature map channel by channel to obtain the weighted feature map.

[0034] This application also introduces the FReLU visual function as the activation function of the YOLOv5s model, specifically modeling the pixel-level spatial information in the activation layer to enhance its sensitivity to spatial information, such as Figure 5 As shown, Figure 5 The figure shows the working principle of the FreLU activation function. The FReLU activation function enhances the ability to capture spatial information. Its mathematical expression can be expressed as: ; ; in, Represents spatial information, Represents the cth channel and two-dimensional spatial position in the original input feature map The pixel value of Represents a two-dimensional spatial position The parameterized pooling window centered on the input pixel of the nonlinear activation function on the cth channel. Indicates the weight of the convolution kernel in the same channel in the depth-wise separable convolution.

[0035] This application sets the YOLOv5s model training epoch to 200 and the batch size to 32. It uses the pre-trained weights commonly used by the YOLOv5s model. After training, the trained model is evaluated using metrics such as average recall (AR), average precision (AP), mean average precision (mAP) for each category, number of parameters, and inference speed to ensure that the model has good object recognition capabilities.

[0036] According to the technical solution provided in the embodiment of the present application, a model training sample is obtained, which contains multiple items, and some items are pre-set with labels for characterizing the items as target items; the initial item recognition model is trained using the model training samples to obtain an item recognition model. The present application uses the trained item recognition model to realize the recognition of items in the vehicle, thereby improving the accuracy of target item recognition.

[0037] In some embodiments, Figure 6 As shown, the risk level corresponding to each target item is determined based on the temperature inside the vehicle, including: S601. Obtain a risk factor corresponding to each target item based on the type of the target item; S602: Obtain the retention time of each target object in the vehicle; S603: Calculate the risk level corresponding to each target item based on the temperature in the vehicle, the risk factor corresponding to each target item, and the retention time.

[0038] It is understandable that since different target items have different chemical properties and temperature sensitivities, different types of target items correspond to different risk factors. The higher the risk factor, the higher the possibility that the target item will cause a safety accident (for example, spontaneous combustion). The lower the risk factor, the lower the possibility that the target item will cause a safety accident. Therefore, when determining the risk level corresponding to the target item, it is necessary to take into account the type of target item and determine the corresponding risk factor based on the type of item.

[0039] It is understandable that high temperature environment is the inducement or accelerator of many risk events. For example, lighters, spray cans (such as insecticides, body sprays), etc. are high-pressure packaged items. High temperature will cause the internal gas pressure to rise sharply, which may exceed the pressure limit of the can and may spontaneously combust or explode. For example, lithium battery devices (mobile power banks, Bluetooth headsets) are prone to thermal runaway due to high temperature, which may cause electrolyte decomposition, expansion and deformation, fire or explosion. Therefore, when determining the risk level corresponding to the target item, this application needs to take into account the temperature inside the vehicle.

[0040] In addition, the danger level of many risky items in the vehicle will increase as the time they stay in the vehicle increases. For example, spray cans, lighters, mobile power supplies, etc., as time goes by, the internal pressure in a closed, high-temperature environment continues to increase, and the probability of combustion increases significantly. Therefore, this application introduces the dynamic factor of "residence time" to make the risk level more in line with the actual evolution logic, avoid "static assessment" based solely on the type of item and temperature, realize dynamic risk management, and enhance the interpretability and intelligence of the system.

[0041] Based on the above reasons, this application needs to calculate the risk level corresponding to each target item based on the in-vehicle temperature, the risk factor corresponding to each target item, and the detention time. Specifically, this application will determine the temperature risk based on the in-vehicle temperature, determine the detention time enhancement factor based on the detention time, and then perform weighted processing on the risk factor corresponding to the target item based on the temperature risk and the detention time enhancement factor to obtain the risk level corresponding to the target item, that is, RiskScore=R_obj×f(T)×g(Δt), where RiskScore is the risk level corresponding to the target item, R_obj is the risk factor corresponding to the target item, f(T) is the temperature risk corresponding to the in-vehicle temperature T, and g(Δt) is the detention time enhancement factor corresponding to the target item's detention time t.

[0042] The temperature risk corresponding to the temperature inside the vehicle can be determined by the temperature risk function, which is as follows: , T is the temperature inside the vehicle; the residence time enhancement factor corresponding to the residence time can be determined by the residence time enhancement factor function, which is as follows: g(Δt) = 1 +log(Δt + 1), where Δt is the residence time of the target object in the vehicle.

[0043] According to the technical solution provided in the embodiment of the present application, the risk factor corresponding to each target item is obtained according to the type of the target item; the detention time of each target item in the vehicle is obtained; the risk level corresponding to each target item is calculated according to the temperature in the vehicle, the risk factor corresponding to each target item and the detention time; among them, the present application makes the risk level assessment result more comprehensive and accurate by comprehensively considering the static risk factor of the item type and the dynamic factors such as temperature and detention time.

[0044] In some examples, the risk level can also be determined directly based on the temperature inside the vehicle. Specifically, the risk level corresponding to each target item is determined based on the temperature inside the vehicle, including: obtaining the correspondence between the pre-set temperature and the risk level corresponding to each target item, matching the temperature inside the vehicle with the correspondence between the temperature and the risk level corresponding to each target item, and obtaining the risk level corresponding to each target item.

[0045] Since different target items have different chemical properties and temperature sensitivities, they may exhibit different hazardous characteristics under temperature changes, corresponding to different risk levels. The risk level is used to characterize the level of safety accidents caused by the target items. The higher the risk level, the higher the possibility that the target item will cause a safety accident (for example, spontaneous combustion). The lower the risk level, the lower the possibility that the target item will cause a safety accident.

[0046] Continuing with the previous example, assuming the risk levels include low, medium, and high, within the low temperature range, the risk level of the target item is defined as "low." This means that within this temperature range, the likelihood of the target item spontaneously combusting is extremely low.

[0047] Medium Risk Level: Within the medium temperature range, the risk level of the target item is raised to "Medium." This indicates that as the temperature rises, the instability of the target item begins to increase, and there is a medium possibility of danger.

[0048] High Risk Level: In the high temperature range, the risk level of the target item is marked as "High". This means that within this temperature range, the target item is very likely to spontaneously combust and other dangerous events.

[0049] For example, taking the target items as lighters, perfume bottles, power banks, sprays, and carbonated beverage cans, the corresponding relationships between the preset temperatures and risk levels of the target items are as follows: Lighters: Because the liquefied petroleum gas (LPG) or natural gas in lighters has a low boiling point and flash point, it is highly susceptible to spontaneous combustion at high temperatures. Therefore, this application sets the risk level for lighters below 20°C as low; between 21°C and 45°C as medium; and above 45°C as high.

[0050] Perfume bottles: The alcohol content in perfume bottles has low flash and boiling points, and alcohol vapor easily forms a pyrophoric mixture when mixed with air. Therefore, this application assigns a low risk level to perfume bottles with a temperature below 20°C; a medium risk level to perfume bottles with a temperature between 21°C and 50°C; and a high risk level to perfume bottles with a temperature above 50°C.

[0051] Power banks: Although power banks themselves are not flammable or explosive, their internal lithium batteries can experience thermal runaway reactions at high temperatures and cause fires. Therefore, this application sets the risk level for power banks with a temperature below 35°C as low; the risk level for power banks with a temperature between 36°C and 55°C as medium; and the risk level for power banks with a temperature above 55°C as high.

[0052] Sprays: Spray products typically contain flammable propellants and solvents, which may evaporate more rapidly at high temperatures and form pyrophoric mixtures. Therefore, this application sets the risk level for sprays below 24°C as low; the risk level for sprays between 25 and 55°C as medium; and the risk level for sprays above 55°C as high.

[0053] Carbonated beverage cans: The carbon dioxide gas inside carbonated beverage cans can expand at high temperatures, potentially causing the can to rupture or even explode. Therefore, this application assigns a low risk level to carbonated beverage cans with a temperature below 44°C; a medium risk level to cans between 45°C and 65°C; and a high risk level to cans with a temperature above 65°C.

[0054] It can be understood that the correspondence between the pre-set temperature and risk level corresponding to each target item mentioned above is only for illustration. This example does not limit the correspondence between the temperature and risk level corresponding to each target item to only the above example. Relevant personnel can flexibly set the correspondence between the temperature and risk level corresponding to each target item; and this example is not used to limit the target items to only lighters, perfume bottles, power banks, sprays, and carbonated beverage cans. Relevant personnel can flexibly set target items with spontaneous combustion risks.

[0055] In some examples, this application will match the vehicle interior temperature with the corresponding relationship between the temperature and risk level of each target item to obtain the corresponding risk level of each target item. For example, if the target item is a lighter and the vehicle interior temperature is 35°C, then the risk level corresponding to the lighter at the current vehicle interior temperature is determined to be medium risk level.

[0056] According to the technical solution provided in the embodiment of the present application, by obtaining the correspondence between the pre-set temperature and the risk level corresponding to each target item; matching the temperature in the vehicle with the correspondence between the temperature and the risk level corresponding to each target item, the risk level corresponding to each target item is obtained, thereby accurately obtaining the risk level corresponding to each target item at the current temperature in the vehicle.

[0057] In some embodiments, Figure 7 As shown, the temperature inside the vehicle is obtained, including: S701: Generate a temperature detection instruction, where the temperature detection instruction is used to control at least one temperature sensor to detect the temperature of the vehicle; S702: Acquire a detected temperature returned by at least one temperature sensor, and obtain the vehicle interior temperature based on the detected temperature returned by the at least one temperature sensor.

[0058] It can be understood that the temperature sensor includes but is not limited to a resistance temperature sensor, an infrared temperature sensor, a semiconductor temperature sensor, and an optical fiber temperature sensor. In order to avoid the waste of resources caused by the temperature sensor performing real-time temperature detection, the present application will generate a temperature detection instruction and send the temperature detection instruction to the temperature sensor, so that the temperature sensor performs temperature detection on the vehicle when it receives the temperature detection instruction.

[0059] It is understandable that the temperature detection instruction may be sent to any temperature sensor or to every temperature sensor, and this embodiment does not limit this.

[0060] In some examples, the present application will also determine the temperature inside the vehicle based on the detection temperature returned by the temperature sensor. For example, when only one temperature sensor returns the detection temperature, the detection temperature returned by the temperature sensor is directly used as the temperature inside the vehicle; when two temperature sensors return the detection temperature, the average of the detection temperatures of the two temperature sensors is used as the temperature inside the vehicle; when at least three temperature sensors return the detection temperature, the average of the detection temperatures of at least three temperature sensors is used as the temperature inside the vehicle or the median of the detection temperatures of at least three temperature sensors is used as the temperature inside the vehicle.

[0061] In some examples, when at least two temperature sensors return detected temperatures, the highest value of the detected temperatures returned by the at least two temperature sensors may be used as the temperature inside the vehicle.

[0062] According to the technical solution provided in the embodiment of the present application, a temperature detection instruction is generated, and the temperature detection instruction is used to control at least one temperature sensor to perform temperature detection on the vehicle; the detection temperature returned by at least one temperature sensor is obtained, and the temperature inside the vehicle is obtained based on the detection temperature returned by at least one temperature sensor, thereby realizing the acquisition of the temperature inside the vehicle according to the temperature detection instruction, avoiding the problem of invalid acquisition of the temperature inside the vehicle.

[0063] In some embodiments, Figure 8 As shown, generate temperature detection instructions, including: S801, determining a placement area corresponding to each target object, and generating the temperature detection instruction corresponding to each placement area; Acquiring a detected temperature returned by at least one of the temperature sensors, and obtaining the vehicle interior temperature based on the detected temperature returned by at least one of the temperature sensors, including: S802: Receive the detected temperature returned for each of the placement areas, and determine the temperature inside the vehicle according to the detected temperature returned for each of the placement areas.

[0064] It can be understood that when there are multiple target objects in a vehicle, the placement areas of the target objects are different, and the ambient temperature of the target objects in the vehicle may also be different; for example, the vehicle is parked under the shade of a tree, the vehicle is partially blocked by the shade of the tree, and the vehicle is partially not blocked by the shade of the tree, then when the sun shines, the temperature of the blocked area of ​​the vehicle is significantly lower than the temperature of the unblocked area of ​​the vehicle.

[0065] Continuing with the above example, in order to accurately determine the risk level corresponding to each target item, this application will determine the placement area corresponding to each target item, and then generate the temperature detection instruction corresponding to each placement area, so that the temperature sensor performs temperature detection on the placement area corresponding to each target item according to the temperature detection instruction corresponding to each placement area, and then receives the detection temperature returned for each placement area, and determines the temperature inside the vehicle based on the detection temperature returned for each placement area (for example, the highest value of the detection temperature obtained is used as the temperature inside the vehicle).

[0066] In some examples, the present application may also perform temperature detection on the area where the temperature sensor is set, and directly use the temperature detection result as the temperature inside the vehicle.

[0067] According to the technical solution provided in the embodiment of the present application, the placement area corresponding to each target item is determined, and the temperature detection instruction corresponding to each placement area is generated; the detection temperature returned for each placement area is received, and the in-vehicle temperature is determined based on the detection temperature returned for each placement area, thereby achieving the determination of the risk level of each target item based on the in-vehicle temperature of the placement area corresponding to the target item, thereby improving the accuracy of the risk level.

[0068] It can be understood that this application will obtain the cooling strategy corresponding to the target risk level and send the cooling strategy to the terminal associated with the vehicle; when the terminal responds to the start-up instruction of the cooling strategy, the cooling strategy will be sent to the corresponding cooling device (such as air conditioning, blower), so that the corresponding cooling device controls the vehicle to cool down according to the cooling strategy.

[0069] Among them, this application pre-sets the correspondence between the target risk level and the cooling strategy. By matching the target risk level with the pre-set correspondence between the target risk level and the cooling strategy, the cooling strategy corresponding to the target risk level can be obtained.

[0070] For example, taking the target risk levels as low, medium, and high, the corresponding relationship between target risk levels and cooling strategies is as follows: the cooling strategy for the low risk level is opening the windows; the cooling strategy for the medium risk level is turning on the air conditioner and setting the temperature to 25°C; and the cooling strategy for the high risk level is turning on the air conditioner and setting the temperature to 20°C. The corresponding relationship between target risk levels and cooling strategies can be flexibly set by relevant personnel based on actual needs.

[0071] After obtaining the cooling strategy corresponding to the target risk level, this application will send the cooling strategy to the terminal associated with the vehicle, so that the user can understand the current condition of the vehicle through the terminal. When the user agrees to the cooling strategy, a start-up instruction for the cooling strategy will be issued through the terminal. When the vehicle receives the start-up instruction of the cooling strategy in response to the terminal, it will control the vehicle to cool down according to the cooling strategy.

[0072] It is understandable that the user can also manually modify the cooling strategy and send the modified cooling strategy to the vehicle so that the vehicle controls the vehicle to cool down according to the modified cooling strategy.

[0073] In some examples, after the vehicle obtains the cooling strategy corresponding to the target risk level, it can also directly execute the cooling strategy to cool the vehicle without waiting for the terminal to issue a start instruction in response to the cooling strategy.

[0074] In some embodiments, Figure 9As shown, after determining a cooling strategy based on the target risk level, the cooling strategy is used to instruct to control the vehicle's temperature to reduce the target risk level corresponding to the vehicle, the method further includes: S901. Re-determine the target risk level of the vehicle, and compare the re-determined target risk level with the target risk level determined in the previous cycle; S902: If the re-determined target risk level is not lower than the target risk level determined in the previous cycle, perform cooling control on the vehicle according to the re-determined target risk level.

[0075] Specifically, after the vehicle is cooled according to the target risk level, if the cooling is effective, the temperature inside the vehicle drops, the risk level of the target items in the vehicle also drops, and the target risk level corresponding to the vehicle also drops.

[0076] Based on the above principles, this application will redetermine the target risk level of the vehicle and compare the redetermined target risk level with the target risk level determined in the previous cycle, wherein the target risk level determined in the previous cycle is the target risk level before the redetermined target risk level.

[0077] Continuing with the above example, if the re-determined target risk level is lower than the target risk level determined in the previous cycle, it proves that the vehicle's cooling is effective and no subsequent steps are required. If the re-determined target risk level is not lower than the target risk level determined in the previous cycle, it proves that the vehicle's current cooling range is low or has failed to cool down successfully. At this time, the vehicle needs to control its cooling according to the re-determined target risk level to lower the vehicle's corresponding target risk level.

[0078] According to the technical solution provided in the embodiment of the present application, the target risk level of the vehicle is re-determined and compared with the target risk level determined in the previous cycle; if the re-determined target risk level is not lower than the target risk level determined in the previous cycle, the vehicle is cooled according to the re-determined target risk level to achieve effective cooling of the vehicle.

[0079] In some embodiments, Figure 10 As shown, after determining the cooling strategy according to the re-determined target risk level, the method further includes: S1001. Obtain a cooling strategy corresponding to the re-determined target risk level, and compare the re-determined cooling strategy with the cooling strategy determined in the previous cycle; S1002: When the re-determined cooling strategy is the same as the cooling strategy determined in the previous cycle, a high temperature warning is issued to a terminal associated with the vehicle.

[0080] Specifically, this application will obtain the cooling strategy corresponding to the re-determined target risk level, and compare the re-determined cooling strategy with the cooling strategy determined in the previous cycle. If the re-determined cooling strategy is the same as the cooling strategy determined in the previous cycle, the cooling strategy has not changed, and the vehicle cannot be further cooled. Therefore, a high temperature warning needs to be issued to the terminal associated with the vehicle, so that the user can take external means to manually cool down the vehicle; if the re-determined cooling strategy is different from the cooling strategy determined in the previous cycle, the cooling strategy has changed, and the vehicle can be cooled directly according to the re-determined cooling strategy.

[0081] In order to better understand the above steps, this application provides a more specific example for illustration. When the vehicle CAN bus obtains the information that the vehicle enters the parking gear, the four doors are closed, and the vehicle triggers the power-off action, that is, the owner is about to leave the vehicle, the vehicle temperature control method provided by this application starts working immediately. Figure 11 As shown, a camera on the vehicle captures images of the interior environment. These images are then preprocessed, including image resizing. A trained object recognition model is then used to identify the presence of target objects (dangerous items) within the vehicle. The vehicle also monitors the interior temperature in real time. If a target object is present, the risk level of the target object is assessed based on the interior temperature. The target risk level of the vehicle is then determined based on the risk level of each target object. A cooling strategy is then determined based on this target risk level and transmitted via CAN messages to the vehicle's internet communication ECU, the T-BOX. Upon receiving the cooling strategy execution request, the T-BOX transmits the strategy to the user terminal via Ethernet. The terminal then displays the strategy to the user, serving as a risk reminder. The cooling strategy recommends opening the windows for low-risk conditions, turning on the air conditioner to an initial temperature of 25°C for medium-risk conditions, and 20°C for high-risk conditions. When the user selects a cooling strategy, the remote vehicle control mode can be called to remotely open the windows, turn on the air conditioner, and set the air conditioner to the corresponding temperature, and the remote control command can be sent to the vehicle through T-BOX.

[0082] According to the technical solution provided in the embodiment of the present application, a cooling strategy corresponding to the re-determined target risk level is obtained, and the re-determined cooling strategy is compared with the cooling strategy determined in the previous cycle; when the re-determined cooling strategy is the same as the cooling strategy determined in the previous cycle, a high temperature warning is issued to the terminal associated with the vehicle. Specifically, when the cooling strategy of the present application has not changed, resulting in the vehicle itself being unable to further cool down, a high temperature warning is issued to the terminal associated with the vehicle, allowing the user to take external means to manually cool down, thereby improving the safety of the vehicle and avoiding the problem of excessive temperature inside the vehicle causing spontaneous combustion of the target item.

[0083] All of the above optional technical solutions can be combined in any way to form optional embodiments of the present application, and will not be described in detail here.

[0084] The following are vehicle embodiments of the present application, which can be used to implement the method embodiments of the present application. For details not disclosed in the vehicle embodiments of the present application, please refer to the method embodiments of the present application.

[0085] This embodiment also provides a vehicle, which includes: an electronic control unit, which is used to obtain an identification result of an item in the vehicle, and if the identification result indicates that the vehicle contains at least one pre-set target item, obtain the temperature inside the vehicle; determine the risk level corresponding to each target item based on the temperature inside the vehicle, and determine the target risk level of the vehicle based on the risk level corresponding to each target item; determine a cooling strategy based on the target risk level, and the cooling strategy is used to instruct cooling control of the vehicle to reduce the target risk level corresponding to the vehicle.

[0086] In some examples, the electronic control unit is further configured to obtain model training samples, which include multiple items, and some items are pre-set with labels for characterizing the items as target items; the initial item recognition model is trained using the model training samples to obtain an item recognition model, which is used to perform item recognition.

[0087] In some examples, the electronic control unit is further configured to obtain a correspondence between a preset temperature and a risk level corresponding to each target item; match the temperature inside the vehicle with the correspondence between the temperature and the risk level corresponding to each target item to obtain the risk level corresponding to each target item.

[0088] In some examples, the electronic control unit is further configured to generate a temperature detection instruction, which is used to control at least one temperature sensor to perform temperature detection on the vehicle; obtain the detection temperature returned by at least one temperature sensor, and obtain the temperature inside the vehicle based on the detection temperature returned by at least one temperature sensor.

[0089] In some examples, the electronic control unit is further configured to determine a placement area corresponding to each target item and generate a temperature detection instruction corresponding to each placement area; obtain the detection temperature returned by at least one temperature sensor, and obtain the temperature inside the vehicle based on the detection temperature returned by at least one temperature sensor, including: receiving the detection temperature returned for each placement area, and determining the temperature inside the vehicle based on the detection temperature returned by each placement area.

[0090] In some examples, the electronic control unit is further configured to redetermine the target risk level of the vehicle and compare the redetermined target risk level with the target risk level determined in the previous cycle; if the redetermined target risk level is not lower than the target risk level determined in the previous cycle, a cooling strategy is determined based on the redetermined target risk level.

[0091] In some examples, the electronic control unit is also configured to obtain a cooling strategy corresponding to the re-determined target risk level, and compare the re-determined cooling strategy with the cooling strategy determined in the previous cycle; if the re-determined cooling strategy is the same as the cooling strategy determined in the previous cycle, a high temperature warning is issued to a terminal associated with the vehicle.

[0092] According to the technical solution provided in the embodiment of the present application, the vehicle provided in the present embodiment obtains the recognition result of the items in the vehicle, and if the recognition result indicates that the vehicle contains at least one pre-set target item, the temperature in the vehicle is obtained; the risk level corresponding to each target item is determined according to the temperature in the vehicle, and the target risk level of the vehicle is determined according to the risk level corresponding to each target item; a cooling strategy is determined according to the target risk level, and the cooling strategy is used to instruct cooling control of the vehicle to reduce the target risk level corresponding to the vehicle; wherein, the present application can monitor and adjust the risk level of each target item, and then determine the target risk level in the vehicle as a whole, and cool the vehicle according to the target risk level, reduce the temperature in the vehicle, and then reduce the risk level of each target item, thereby improving the safety of the vehicle and avoiding the problem in the related art that daily necessities are prone to cause safety accidents after the temperature in the vehicle rises.

[0093] Figure 12 Schematic diagram of the electronic device 12 provided in the embodiment of the present application. Figure 12 As shown, the electronic device 12 of this embodiment includes: a processor 1201, a memory 1202, and a computer program 1203 stored in the memory 1202 and executable by the processor 1201. When the processor 1201 executes the computer program 1203, the steps of each of the above-described method embodiments are implemented. Alternatively, when the processor 1201 executes the computer program 1203, the functions of the above-described vehicle embodiments are implemented.

[0094] The electronic device 12 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 12 may include but is not limited to a processor 1201 and a memory 1202. Those skilled in the art will appreciate that Figure 12 The electronic device 12 is merely an example and does not limit the electronic device 12 . The electronic device 12 may include more or fewer components than shown in the figure, or different components.

[0095] The processor 1201 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0096] The memory 1202 may be an internal storage unit of the electronic device 12, such as a hard disk or memory of the electronic device 12. The memory 1202 may also be an external storage device of the electronic device 12, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. The memory 1202 may also include both the internal storage unit of the electronic device 12 and an external storage device. The memory 1202 is used to store computer programs and other programs and data required by the electronic device.

[0097] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of each functional unit and module is used as an example. In actual applications, the above functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0098] If the integrated module / unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program can include computer program code, which can be in source code form, object code form, executable file, or some intermediate form. Computer-readable media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, removable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier distance, telecommunication distance, and software distribution media. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased based on regional requirements and patent practice. For example, in some regions, based on regional requirements and patent practice, the computer-readable medium does not include electric carrier distance and telecommunication distance.

[0099] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in each of the aforementioned embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of each embodiment of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A vehicle temperature control method, characterized in that: The method comprises: Obtaining an identification result of an object in the vehicle, and if the identification result indicates that the vehicle contains at least one preset target object, obtaining the temperature in the vehicle; Determining a risk level corresponding to each target item according to the temperature inside the vehicle, and determining a target risk level of the vehicle according to the risk level corresponding to each target item; A cooling strategy is determined according to the target risk level, and the cooling strategy is used to instruct to perform cooling control on the vehicle to reduce the target risk level corresponding to the vehicle.

2. The method according to claim 1, characterized in that Before obtaining the identification result of the vehicle interior object, the method further includes: Obtaining a model training sample, wherein the model training sample includes a plurality of items, and some of the items are pre-set with a label for characterizing the item as a target item; An object recognition model is determined through the model training samples, and the object recognition model is used to perform object recognition.

3. The method according to claim 1, characterized in that Determining the risk level corresponding to each target object according to the temperature inside the vehicle includes: Obtaining a risk factor corresponding to each target item according to the type of the target item; Obtaining the retention time of each target object in the vehicle; The risk level corresponding to each target item is calculated according to the temperature in the vehicle, the risk factor corresponding to each target item, and the residence time.

4. The method according to claim 1, wherein Get the vehicle interior temperature, including: generating a temperature detection instruction, wherein the temperature detection instruction is used to control at least one temperature sensor to perform temperature detection on the vehicle; A detection temperature returned by at least one of the temperature sensors is obtained, and the vehicle interior temperature is obtained according to the detection temperature returned by at least one of the temperature sensors.

5. The method according to claim 4, characterized in that Generating a temperature detection instruction includes: determining a placement area corresponding to each target object, and generating the temperature detection instruction corresponding to each placement area; Obtaining the detected temperature returned by at least one of the temperature sensors and obtaining the temperature inside the vehicle based on the detected temperature returned by at least one of the temperature sensors, including: receiving the detected temperature returned for each of the placement areas, and determining the temperature inside the vehicle based on the detected temperature returned by each of the placement areas.

6. The method according to claim 1, characterized in that After determining a cooling strategy according to the target risk level, the cooling strategy being used to instruct to perform cooling control on the vehicle to reduce the target risk level corresponding to the vehicle, the method further includes: re-determining a target risk level for the vehicle; If the re-determined target risk level is not lower than the target risk level determined in the previous cycle, a cooling strategy is determined based on the re-determined target risk level.

7. The method according to claim 6, characterized in that After determining a cooling strategy based on the re-determined target risk level, the method further includes: Obtain the cooling strategy corresponding to the re-determined target risk level; When the re-determined cooling strategy is the same as the cooling strategy determined in the previous cycle, a high temperature warning is issued to a terminal associated with the vehicle.

8. A vehicle, comprising: An electronic control unit, characterized in that the electronic control unit is used to obtain an identification result of an item in a vehicle, and if the identification result indicates that the vehicle contains at least one pre-set target item, obtain the temperature inside the vehicle; determine the risk level corresponding to each of the target items based on the temperature inside the vehicle, and determine the target risk level of the vehicle based on the risk level corresponding to each of the target items; determine a cooling strategy based on the target risk level, and the cooling strategy is used to instruct cooling control of the vehicle to reduce the target risk level corresponding to the vehicle.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images