Parking method and device, vehicle, electronic equipment and storage medium

Abstract

The invention relates to the technical field of vehicles, and discloses a parking method and device, a vehicle, electronic equipment and a storage medium, and the method comprises the steps: obtaining the positions of a plurality of to-be-parked parking areas of a target vehicle in response to a parking instruction; a first parking area is determined according to the positions of the multiple parking areas, and the exposure index of the first parking area is calculated; if the exposure index of the first parking area is smaller than a preset exposure index, the target vehicle is controlled to be parked in the first parking area; and if the exposure index of the first parking area is greater than or equal to a preset exposure index, searching a second parking area meeting a preset driving distance for parking by taking the first parking area as a starting point. According to the method, the parking position, the driving distance and the exposure risk are comprehensively considered, a convenient and safe parking scheme is provided, the parking efficiency is improved, and the satisfaction degree and experience of a user are improved.

Description

Technical Field

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

[0002] With the development of unmanned autonomous driving technology, unmanned valet parking functions have been officially commercialized on some new energy vehicles. Unmanned valet parking refers to the automatic parking of the vehicle, that is, the autonomous driving system can automatically help users park the vehicle into the parking space.

[0003] In the related art, when a vehicle autonomously searches for an empty parking area (parking space), it often only considers whether the current parking space is empty and whether the size of the parking space can accommodate the vehicle, but does not consider whether the currently selected parking space is appropriate. Especially in the summer when the light intensity is high, the vehicle is exposed to high-intensity sunlight for a long time, which not only affects the service life of the electronic components in the vehicle, but also causes high temperature, stuffiness, harmful gases and other phenomena in the vehicle, greatly reducing the user experience. Summary of the invention

[0004] The embodiments of the present application provide a parking method, device, vehicle, electronic device and storage medium to solve the technical problem in the related art that vehicles automatically park easily into parking areas with high exposure indexes.

[0005] An embodiment of the present application provides a parking method, which includes: in response to a parking instruction, obtaining the positions of multiple parking areas where a target vehicle is to be parked; determining a first parking area according to the positions of the multiple parking areas, and calculating an exposure index of the first parking area; if the exposure index of the first parking area is less than a preset exposure index, controlling the target vehicle to park in the first parking area; if the exposure index of the first parking area is greater than or equal to the preset exposure index, taking the first parking area as a starting point, finding a second parking area within or outside a preset driving distance for parking.

[0006] In one embodiment of the present application, the first parking area is used as a starting point, and a second parking area within or outside a preset driving distance is searched for parking, including: taking the first parking area as a starting point, recording the driving mileage; if the driving mileage does not exceed the preset driving mileage, calculating the exposure index of the parking area in an idle state found, taking the parking area with the exposure index less than the preset exposure index as the second parking area, and controlling the target vehicle to park in the second parking area; or, if the driving mileage exceeds the preset driving mileage, and the exposure indexes of multiple parking areas found are all greater than or equal to the preset exposure index, selecting the parking area corresponding to the minimum value of the multiple exposure indexes as the second parking area, and controlling the target vehicle to park in the second parking area; or, if the driving mileage exceeds the preset driving mileage and no idle parking area is found, taking any idle parking area found by the target vehicle next as the second parking area, and controlling the target vehicle to park in the second parking area.

[0007] In one embodiment of the present application, the method for determining the exposure index includes: obtaining the temperature characteristics, solar radiation intensity characteristics and humidity characteristics of the parking area currently in an idle state, and the color characteristics and orientation characteristics of the target vehicle; performing weighted calculation on the temperature characteristics, the solar radiation intensity characteristics, the humidity characteristics, the color characteristics and the orientation characteristics according to a preset weight coefficient to determine the exposure index; or, obtaining a data set, the data set including the temperature characteristics, solar radiation intensity characteristics and humidity characteristics of each parking area after preprocessing, and the color characteristics and orientation characteristics of the vehicle; dividing the data set into a training set and a test set; constructing a residual network model based on a fusion attention mechanism, using the temperature characteristics, solar radiation intensity characteristics, humidity characteristics of each parking area in the training set, and the color characteristics and orientation characteristics of the vehicle, and performing weighted fusion training through a preset weight coefficient to determine a first exposure index model; using the test set to test the first exposure index model, adjusting the loss value until a preset convergence condition is reached, and determining a second exposure index model; inputting each feature of the parking area currently in an idle state into the second exposure index model to determine the exposure index.

[0008] In one embodiment of the present application, before determining the temperature characteristics, solar radiation intensity characteristics, and humidity characteristics of the parking area, the method further includes: obtaining a three-dimensional map of the parking place currently entered by the target vehicle and the parking time, wherein the three-dimensional map includes a plurality of the parking areas; determining a first position of the parking area currently in an idle state in the three-dimensional map, and an initial temperature characteristic, an initial solar radiation intensity characteristic, and an initial humidity characteristic of the parking area at a current moment; determining, according to the solar azimuth at a current time and the first position of the current parking area, a respective range of variation of the initial temperature characteristic, the initial solar radiation intensity characteristic, and the initial humidity characteristic relative to the current moment after the parking time; determining a temperature compensation factor, a radiation compensation factor, and a humidity compensation factor according to the respective range of variation of the initial temperature characteristic, the initial solar radiation intensity characteristic, and the initial humidity characteristic of the parking area; and performing compensation calculations on the initial temperature characteristic, the initial solar radiation intensity characteristic, and the initial humidity characteristic of the parking area according to the temperature compensation factor, the radiation compensation factor, and the humidity compensation factor, to determine the temperature characteristic, the solar radiation intensity characteristic, and the humidity characteristic of the parking area within the parking time.

[0009] In one embodiment of the present application, determining a first parking area according to the positions of a plurality of parking areas includes: obtaining an input operation instruction, the operation instruction carrying the target parking area in which the target vehicle is to be parked; parsing the operation instruction, matching the obtained target parking area with the plurality of parking areas, and determining the first parking area, wherein the operation instruction is voice information or image information; or obtaining map information of the plurality of parking areas in the parking place currently entered by the target vehicle; matching the map information distributed in the plurality of parking areas according to the driver's personalized configuration, and determining the first parking area, wherein the personalized configuration is generated based on the driver's parking driving habits, or is close to a parking lot entrance or exit.

[0010] In one embodiment of the present application, before calculating the exposure index of the first parking area, it also includes: if the target vehicle is close to the first parking area and it is detected that the first parking area is in a non-idle state, matching is performed in multiple parking areas according to the driver's personalized configuration to determine the first parking area that is in an idle state.

[0011] An embodiment of the present application also provides a parking device, which includes: a position acquisition module, used to respond to a parking instruction and obtain the positions of multiple parking areas where a target vehicle is to be parked; an exposure index calculation module, used to determine a first parking area according to the positions of the multiple parking areas, and calculate the exposure index of the first parking area; a first parking control module, used to control the target vehicle to park in the first parking area if the exposure index of the first parking area is less than a preset exposure index; a second parking control module, used to use the first parking area as a starting point to find a second parking area that meets a preset driving distance for parking if the exposure index of the first parking area is greater than or equal to the preset exposure index.

[0012] An embodiment of the present application further provides a vehicle, which includes a parking device as described in any of the above embodiments.

[0013] An embodiment of the present application further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any one of the above embodiments when executing the computer program.

[0014] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method described in any one of the above embodiments is implemented.

[0015] In the scheme implemented by the parking method, device, vehicle, electronic device and storage medium provided above, the parking method obtains the positions of multiple parking areas to be parked by the target vehicle in response to the parking instruction; determines the first parking area according to the positions of the multiple parking areas, thereby reducing the trouble of manually finding a parking space; calculates the exposure index of the first parking area, and if the exposure index of the first parking area is less than the preset exposure index, controls the target vehicle to park in the first parking area; before parking in the parking area, reduces the risk of the vehicle being exposed to the sun by evaluating the exposure index, thereby avoiding reducing the service life of the electronic components of the vehicle; if the exposure index of the first parking area is greater than or equal to the preset exposure index, takes the first parking area as the starting point, and searches for a second parking area within or outside the preset driving distance for parking. The present application comprehensively considers the parking position, driving distance and exposure risk, and provides a convenient and safe parking solution, which not only improves the parking efficiency, but also improves the user satisfaction and experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. 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 creative labor.

[0017] Figure 1 An exemplary system architecture diagram to which the parking method provided in the embodiment of the present application can be applied;

[0018] Figure 2 A schematic diagram of a parking method provided in an embodiment of the present application;

[0019] Figure 3 A specific schematic diagram of a parking method provided in an embodiment of the present application;

[0020] Figure 4 A schematic diagram of the structure of a parking device provided in an embodiment of the present application;

[0021] Figure 5 A structural schematic diagram of an electronic device in an embodiment of the present application;

[0022] Figure 6 Another structural schematic diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0024] In order to enable those skilled in the art to better understand the improvements of the technical solution provided by the present disclosure, the present disclosure briefly introduces the implementation scenarios and related information of the parking method in the related technology.

[0025] Figure 11 is a functional block diagram of a vehicle 100 provided in an embodiment of the present application. The vehicle 100 may include a perception system, a display device, and a computing platform, wherein the perception system may include several sensors for sensing information about the environment around the vehicle 100. For example, the perception system may include a positioning system, and the positioning system may be a global positioning system (GPS), or a Beidou system or other positioning systems, an inertial measurement unit (IMU), a laser radar, a millimeter wave radar, an ultrasonic radar, and a camera device. One or more.

[0026] Some or all functions of the vehicle 100 may be controlled by a computing platform. The computing platform may include multiple processors. A processor is a circuit with signal processing capabilities. In one implementation, the processor may be a circuit with instruction reading and execution capabilities, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor) or a digital signal processor (DSP); in another implementation, the processor may implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit is fixed or reconfigurable, such as a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc. In addition, the computing platform can also include a memory, the memory is used to store instructions, and some or all of the multiple processors can call the instructions in the memory to implement corresponding functions.

[0027] Vehicle 100 may include an advanced driving assistant system (ADAS), which utilizes a variety of sensors on the vehicle (including but not limited to: lidar, millimeter wave radar, camera, ultrasonic sensor, global positioning system, inertial measurement unit) to obtain information from the surroundings of the vehicle, and analyzes and processes the obtained information to achieve functions such as obstacle perception, target recognition, vehicle positioning, path planning, driver monitoring / reminder, etc., thereby improving the safety, automation and comfort of vehicle driving.

[0028] Sensors can include laser radar, millimeter wave radar, camera, ultrasonic sensor, among which millimeter wave radar can be divided into long-range radar and medium / short-range radar. At present, the sensing range of laser radar is about 80-150 meters, the sensing range of long-range millimeter wave radar is about 1-250 meters, the sensing range of medium / short-range millimeter wave radar is about 30-120 meters, the sensing range of camera is about 50-200 meters, and the sensing range of ultrasonic radar is about 0-5 meters.

[0029] In terms of logical functions, ADAS systems generally include three main functional modules: perception module, decision module and execution module. The perception module perceives the environment around the vehicle body through sensors and inputs corresponding real-time data to the decision-making layer processing center. The perception module mainly includes on-board cameras / ultrasonic radars / millimeter-wave radars / lidar, etc.; the decision module uses computing devices and algorithms to make corresponding decisions based on the information obtained by the perception module; the execution module takes corresponding actions after receiving the decision signal from the decision module, such as driving, changing lanes, steering, braking, warnings, etc.

[0030] At different levels of autonomous driving (L0-L5), ADAS can achieve different levels of autonomous driving assistance based on artificial intelligence algorithms and information obtained by multiple sensors. The above autonomous driving levels (L0-L5) are based on the grading standards of the Society of Automotive Engineers (SAE). Among them, L0 is no automation; L1 is driving assistance; L2 is partial automation; L3 is conditional automation; L4 is highly automated; L5 is fully automated. The tasks of monitoring road conditions and responding to L1 to L3 are completed by the driver and the system together, and the driver needs to take over the dynamic driving tasks. L4 and L5 levels allow the driver to completely transform into the role of a passenger. At present, the functions that ADAS can achieve mainly include but are not limited to: adaptive cruise, automatic emergency braking, automatic parking, blind spot monitoring, front intersection traffic warning / braking, rear intersection traffic warning / braking, front vehicle collision warning, lane departure warning, lane keeping assist, rear vehicle collision avoidance warning, traffic sign recognition, traffic congestion assistance, highway assistance, etc. It should be understood that the above-mentioned various functions may have specific modes under different autonomous driving levels (L0-L5), and the higher the level of autonomous driving, the smarter the corresponding mode. For example, automatic parking may include APA, RPA, and AVP. For APA, the driver does not need to operate the steering wheel, but still needs to operate the accelerator and brake on the vehicle; for RPA, the driver can use a terminal (such as a mobile phone) to remotely park the vehicle from the outside of the vehicle; for AVP, the vehicle can complete parking without a driver. In terms of the corresponding autonomous driving level, APA is approximately at the L1 level, RPA is approximately at the L2-L3 level, and AVP is approximately at the L4 level.

[0031] As mentioned earlier, currently, when the user has not specified a fixed dedicated parking space, although valet parking can autonomously find an empty parking space to park, it does not consider whether this empty parking space is the best location. For example, especially in the summer when the light intensity is extremely high, the vehicle is exposed to the sun for a long time, which will have an adverse effect on the service life of the vehicle, reduce the experience of automatic parking, and cause some irreversible effects on the vehicle, such as the volatilization of harmful substances, accelerated vehicle aging, high-temperature deformation and fading of some interior decorations, or high-temperature damage to electronic components.

[0032] In view of this, the embodiments of the present application provide a parking method, device, vehicle, electronic device and storage medium. The vehicle can calculate the exposure index for the parking area based on the current location of the vehicle, which helps to ensure that the unmanned vehicle can find a shaded or non-sun-exposed parking space for parking.

[0033] See also Figure 2 , Figure 2A flowchart of a parking method provided in an embodiment of the present application is provided, and the method comprises the following steps:

[0034] Step S201, in response to a parking instruction, obtaining positions of a plurality of parking areas where a target vehicle is to be parked;

[0035] Among them, the vehicle (sometimes referred to as a vehicle) in this application is a vehicle in a broad sense, which can be a means of transportation (such as: cars, trucks, motorcycles, trains, airplanes, ships, etc.), industrial vehicles (such as: forklifts, trailers, tractors, etc.), engineering vehicles (such as: excavators, bulldozers, cranes, etc.), agricultural equipment (such as mowers, harvesters, etc.), amusement equipment, toy vehicles, etc. The vehicles in this application include fuel vehicles and new energy vehicles, and there is no limitation on the type of vehicle.

[0036] Exemplarily, the parking area includes a parking exit area (eg, an area after a vehicle is parked) or a parking entry area (eg, a parking space), and the present application mainly considers the parking entry area.

[0037] Exemplarily, the parking command is triggered by the user, which can be triggered by IVI, smart phone or smart key. Among them, the in-vehicle infotainment system (In-Vehicle Infotainment, referred to as IVI) is an in-vehicle comprehensive information processing system formed by using a dedicated in-vehicle central processor, based on the body bus system and Internet services. The human-computer interaction form of IVI can be sound, image, text. The human-computer interaction media of IVI include the central control screen (display, touch), instrument display, voice, steering wheel, etc.

[0038] Step S202, determining a first parking area according to the positions of the plurality of parking areas, and calculating an exposure index of the first parking area;

[0039] Among them, the first parking area can be set according to user presets. For example, if there are fixed parking spaces at work or in the residential area, the fixed parking space number can be automatically set; the first parking area can also be determined by circling a parking area from the multiple parking areas displayed on the in-vehicle infotainment system; and the first parking area can also be determined by matching conditions at the locations of multiple parking areas through personalized configurations set in advance.

[0040] The exposure index is usually associated with the UV index. It is a quantitative indicator used to describe the potential harm of ultraviolet radiation to the human body. However, for vehicles, according to the "European Exposure Conditions" and "American Exposure Conditions" in the GB / T8427 standard, combined with common sense, the environmental data that can be collected by the on-board sensors can be used to extract the characteristic quantities that have a strong correlation with whether the vehicle is in an exposed state: such as temperature, solar radiation, humidity, vehicle color and vehicle orientation. The above quantitative features can be used to determine the exposure index through a linear model.

[0041] Step S203, if the exposure index of the first parking area is less than the preset exposure index, control the target vehicle to park in the first parking area;

[0042] The parking position of the target vehicle is determined by comparing the exposure index of the first parking area with the preset exposure index. For example, if the exposure index of the first parking area is less than the preset exposure index, the target vehicle is controlled to park in the first parking area. The preset exposure index can be set by the vehicle factory, or the threshold can be set according to the user's own preferences and health conditions, so as to ensure comfort during parking.

[0043] Step S204: If the exposure index of the first parking area is greater than or equal to the preset exposure index, the first parking area is used as a starting point to find a second parking area within or outside the preset driving distance for parking.

[0044] Among them, take the first parking area as the starting point, start the mileage and record it.

[0045] Exemplarily, if the exposure index of the first parking area is greater than or equal to the preset exposure threshold, the search algorithm will be activated, starting from the first parking area, to find a second parking area within or outside the preset driving distance. Here, the second parking area may be a parking space that meets the preset exposure threshold, or it may be a parking space that does not meet the preset exposure threshold.

[0046] For example, when selecting a parking area, in addition to considering the exposure index, other factors may also be considered, such as the distance, cost, and safety of the parking area, and decisions may be made based on these factors to provide a more comprehensive and intelligent parking service.

[0047] Through the above method, the present application reduces the trouble of manually searching for parking spaces, and by calculating the exposure index of the first parking area, before parking in the parking area, the exposure index is evaluated to reduce the risk of the vehicle being exposed to the sun, thereby avoiding reducing the service life of the vehicle's electronic components; it also comprehensively considers the parking position, driving distance and exposure risk, and provides a convenient and safe parking solution, which not only improves parking efficiency, but also improves user satisfaction and experience.

[0048] Optionally, after the vehicle is parked according to a preset route or a preset parking space, once it is found that the preset parking space does not meet the parking requirements (for example, the exposure index is too high or the current parking space is full), how should a parking position desired by the user be selected?

[0049] In some embodiments, starting from the first parking area, searching for a second parking area within or outside a preset driving distance for parking includes:

[0050] Taking the first parking area as the starting point, record the mileage;

[0051] If the mileage does not exceed the preset mileage, the exposure index of the found idle parking area is calculated, and the parking area with an exposure index less than the preset exposure index is used as the second parking area, and the target vehicle is controlled to park in the second parking area; or

[0052] If the driving mileage exceeds the preset driving mileage, and the exposure indexes of the multiple parking areas found are all greater than or equal to the preset exposure index, a parking area corresponding to the minimum value of the multiple exposure indexes is selected as the second parking area, and the target vehicle is controlled to park in the second parking area; or

[0053] If the mileage exceeds the preset mileage and no idle parking area is found, the target vehicle will find any idle parking area next as the second parking area, and the target vehicle will be controlled to park in the second parking area.

[0054] Among them, by recording the mileage, it can be ensured that the vehicle prioritizes searching for parking areas within a preset mileage range to avoid unnecessary driving and energy waste; at the same time, by calculating and comparing the exposure index of the new parking area searched, a parking area that is more friendly to the human body and the vehicle can be selected; if the ideal parking area cannot be found, a relatively good parking area will be selected to balance the effects of driving distance and exposure index; in extreme cases (i.e., no idle parking area is found), the exposure index condition requirement will be abandoned to ensure that the vehicle can be parked in an available parking area as soon as possible.

[0055] For example, when the vehicle starts from the first parking area to look for other parking areas, the vehicle system will start to record the mileage of the vehicle, and the mileage record can be realized through the vehicle's odometer or GPS system. All idle parking areas are searched and identified within a preset range, and for each parking area found, its exposure index is calculated and compared with the preset exposure index, and a parking area with an exposure index less than the preset exposure index is selected as the second parking area.

[0056] When the vehicle mileage exceeds the preset range and no parking area with an exposure index less than the preset value can be found, the parking area with the smallest exposure index among all the parking areas found will be screened out; then, the vehicle will be controlled to park in this parking area with the smallest exposure index. When the vehicle mileage exceeds the preset range and no free parking area can be found, the search will continue until the first free parking area is found. Once a free parking area is found, the vehicle will be controlled to park immediately.

[0057] Through the above method, on the one hand, the search efficiency is improved to ensure that the vehicle can find a suitable parking area within a reasonable range; on the other hand, the comfort of the parking environment is improved to reduce the potential damage to the vehicle caused by exposure to the sun; on the other hand, when the optimal solution cannot be found, a suboptimal solution is provided to ensure the smooth progress of the parking process; finally, in extreme cases, the smooth progress of the parking process is ensured to avoid parking difficulties caused by the inability to find a parking area.

[0058] Optionally, in the related art, since the exposure index cannot be accurately calculated and there is a lack of effective quantitative means for the exposure of vehicles parked in open-air dams, users lack awareness of this situation.

[0059] In one embodiment, the method for determining the exposure index includes:

[0060] Obtain the temperature characteristics, solar radiation intensity characteristics and humidity characteristics of the parking area that is currently idle, as well as the color characteristics and orientation characteristics of the target vehicle;

[0061] Determine the exposure index by weighting the temperature characteristics, solar radiation intensity characteristics, humidity characteristics, color characteristics and orientation characteristics according to the preset weight coefficients; or

[0062] Acquire a data set, the data set including pre-processed temperature characteristics, solar radiation intensity characteristics and humidity characteristics of each parking area, and color characteristics and orientation characteristics of the vehicle;

[0063] Divide the dataset into training set and test set;

[0064] A residual network model based on the fusion attention mechanism is constructed. The temperature characteristics, solar radiation intensity characteristics, humidity characteristics, and vehicle color characteristics and orientation characteristics of each parking area in the training set are used to perform weighted fusion training through preset weight coefficients to determine the first exposure index model.

[0065] The first exposure index model is tested using the test set, the loss value is adjusted until a preset convergence condition is reached, and the second exposure index model is determined;

[0066] The characteristics of the parking area currently in an idle state are input into the second exposure index model to determine the exposure index.

[0067] Among them, the temperature characteristics, solar radiation intensity characteristics and humidity characteristics of the parking area, as well as the color characteristics and orientation characteristics of the target vehicle can be collected based on the vehicle-mounted temperature sensor, based on the vehicle-mounted sunlight and rainfall sensor, and based on the vehicle-mounted humidity sensor respectively; the vehicle color, the quantization value is 1 for a dark-colored vehicle, and 0 for a light-colored vehicle, which can be read based on the vehicle configuration word; the vehicle orientation, the quantization value is 1 for facing the sun, and 0 for facing away from the sun, which can be collected based on the vehicle-mounted camera, that is, after the camera or image sensor captures the vehicle image, the color and orientation information of the vehicle are extracted through image processing algorithms (such as color space conversion, edge detection, etc.).

[0068] In one embodiment, the collected temperature features, solar radiation intensity features, humidity features, color features, and orientation features are input into a preset weighted calculation model, and each feature is weighted according to a preset weight coefficient to obtain an exposure index. In addition, meteorological data, geographic location information, etc. can also be combined to improve the prediction accuracy of the exposure index.

[0069] Through the above method, by calculating and providing an accurate exposure index, a scientific basis is provided for vehicle protection and management; at the same time, through the preset weight coefficient, the influence of various characteristics on the exposure degree is fully considered to improve the calculation accuracy and reliability of the exposure index.

[0070] In another embodiment, data preprocessing aims to improve data quality and model training effect, and improve input data accuracy by removing outliers, filling missing values, standardizing or normalizing data. Dividing the data set into a training set and a test set can effectively avoid model overfitting and ensure that the model can also perform well on unseen data. The attention mechanism can focus on the important parts of the input features and improve the model's ability to capture key information; and the residual connection can retain the information of the previous layer, so that the network can still learn useful feature representations at a deep level. Weighted fusion training can make full use of the information of each feature and improve the prediction accuracy of the model, wherein the preset weight coefficient can be set according to experience or experimental results to balance the impact of different features on the prediction results. The test set is used to evaluate the performance and generalization ability of the model. By comparing the predicted results and the actual results of the model, targeted adjustments and optimizations are made to obtain the final second exposure index model. By inputting the feature data of the current parking area, the real-time exposure index can be obtained.

[0071] For example, by constructing a residual network model based on a fusion attention mechanism, multiple input features (temperature features, solar radiation intensity features, humidity features, color features, and orientation features) are received, and these features are weighted and fused through the attention mechanism; at the same time, residual connections are used to avoid the gradient vanishing or gradient exploding problems caused by the network being too deep. In addition, other types of neural network models can also be used, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), or graph neural networks (GNNs).

[0072] The temperature characteristics, solar radiation intensity characteristics, humidity characteristics, and color characteristics and orientation characteristics of each parking area in the training set are input into the model, and weighted fusion training is performed through preset weight coefficients. During the training process, appropriate loss functions and optimization algorithms are used to minimize the prediction error of the model; the data in the test set are input into the first exposure index model, and the prediction error and performance indicators of the model (such as accuracy, recall rate, F1 score, etc.) are calculated. According to the test results, the model is adjusted and optimized as necessary until the preset convergence conditions are met (such as the prediction error is less than a certain threshold or the performance indicator reaches a certain level). Finally, the second exposure index model is determined.

[0073] In the above manner, the quality of the data set is improved through preprocessing, and the data set is divided into a training set and a test set, so that the model can learn the inherent laws of the data during the training process and show good generalization ability during the test process. By integrating the residual network model with the attention mechanism, the model's ability to capture and fuse input features is improved, thereby more accurately predicting the exposure index. The application has obtained the final second exposure index model after sufficient testing and optimization, which has high prediction accuracy and generalization ability. At the same time, the output predicted exposure index provides a scientific basis for vehicle protection and management in parking areas, and also improves the safety and service life of vehicles.

[0074] 1. Model construction

[0075] According to the "European Exposure Conditions" and "American Exposure Conditions" in the GB / T8427 standard, combined with common sense, the environmental data collected from existing vehicle sensors and the following features that are highly correlated with judging whether the vehicle is in an exposed state are extracted: temperature, solar radiation, humidity, vehicle color and vehicle orientation. A linear model can be constructed to calculate the exposure index.

[0076] SEI=wTemperature×T+wSolarRadiation×R+wHumidity×H+wCarColor×C+wCarOrientation×O(1)

[0077] In formula (1), SEI is characterized by the exposure index; w is the weight of the corresponding feature; T represents temperature, the dimension is Celsius (℃), which can be collected based on the vehicle temperature sensor; R represents the solar radiation intensity, the dimension is watt per square meter (W / m 2 ), which can be collected based on the on-board sunlight and rain sensor; H represents humidity, the dimension is percentage (%), which can be collected based on the on-board humidity sensor; C represents the color of the vehicle, the quantitative value is 1 for a dark-colored vehicle, and 0 for a light-colored vehicle, which can be read based on the vehicle configuration word. O represents the direction of the vehicle, the quantitative value is 1 for facing the sun, and 0 for facing away from the sun, which can be collected based on the on-board camera.

[0078] Based on this model, the weights of each feature value and the SEI threshold for judging whether the object is in an exposed state are determined.

[0079] 2. Determination of feature weights

[0080] Collect and organize user data on parking temperature, solar radiation intensity, humidity, vehicle color, vehicle orientation and other feature quantities, and label each set of data to see if it is in the sun, divide it into training and test sets (generally 70% of the data is used for training and 30% for testing), and train it by building a random forest model. The random forest algorithm will normalize the feature importance so that the sum of all feature importances is 1. In this way, the importance of each feature can be interpreted as a weight, indicating its contribution to the model prediction.

[0081] Here, we use 10,000 data sets to construct the random forest model to obtain the weight value results. You can also find relevant data sets for model training. Temperature weight: 0.4; solar radiation weight: 0.3; humidity weight: 0.2; vehicle color weight: 0.08; vehicle orientation weight: 0.02.

[0082] Temperature threshold: European exposure conditions require a maximum black mark temperature of 50°C, and American exposure conditions require a blackboard temperature of 63±1°C. The average of these two values ​​is taken as the temperature threshold, that is, Tthreshold=50+62=56.5°C, Tthreshold=50+63=56.5°C.

[0083] Solar radiation intensity threshold: Both European and American exposure conditions require an irradiance of 42W / m 2 (wavelength 300-400nm) or 1.10W / m 2 (wavelength is 420nm), the higher value of these two values ​​is taken as the radiation intensity threshold, that is, Rthreshold = 42W / m 2 , Rthreshold=42W / m 2 .

[0084] Humidity threshold: The exposure conditions in the United States require a relative humidity of 30%. This value is used as the humidity threshold, that is, Hthreshold = 30% Hthreshold = 30%.

[0085] The SEI exposure index threshold for this vehicle can be calculated

[0086] SEIthreshold=wTemperature×Tthreshold+wSolarRadiation×Rthreshold

[0087] +wHumidity×Hthreshold+wCarColor×Cthreshold+wCarOrientation×Othreshold SEIthreshold=0.4×56.5+0.3×42+0.2×30+0.08×Cthreshold+0.02×Othreshold

[0088] That is, SEIthreshold = 41.2 + 0.08 × Cthreshold + 0.02 × Othreshold

[0089] Among them, the SEI exposure index is calculated through the quantified vehicle color and vehicle orientation.

[0090] Alternatively, compared to calculating the exposure index at a certain moment, it is often impossible to subsequently estimate whether the exposure index will increase or decrease during the parking period, which is not conducive to reducing the negative impact of exposure on the vehicle.

[0091] In one embodiment, before determining the temperature characteristic, solar radiation intensity characteristic, and humidity characteristic of the parking area, the method further includes:

[0092] Obtaining a three-dimensional map of the parking space currently entered by the target vehicle and the parking duration, wherein the three-dimensional map includes multiple parking areas;

[0093] Determine a first position of a parking area currently in an idle state in the three-dimensional map, as well as initial temperature characteristics, initial solar radiation intensity characteristics, and initial humidity characteristics of the parking area at the current moment;

[0094] According to the solar azimuth at the current time and the first azimuth of the current parking area, determining the respective change ranges of the initial temperature characteristic, the initial solar radiation intensity characteristic, and the initial humidity characteristic relative to the current time after the parking time;

[0095] Determine the temperature compensation factor, the radiation compensation factor and the humidity compensation factor according to the respective variation ranges of the initial temperature characteristics, the initial solar radiation intensity characteristics and the initial humidity characteristics of the parking area;

[0096] According to the temperature compensation factor, radiation compensation factor and humidity compensation factor, compensation calculation is performed on the initial temperature characteristics, initial solar radiation intensity characteristics and initial humidity characteristics of the parking area to determine the temperature characteristics, solar radiation intensity characteristics and humidity characteristics of the parking area during the parking time.

[0097] Exemplarily, the current parking lot location of the target vehicle is obtained through the vehicle's GPS positioning information or the parking lot entrance identification (or, the vehicle location and parking lot information is quickly and accurately obtained using positioning technology and database query technology); the three-dimensional map data of the parking lot is retrieved from the parking lot database, including the location, size, shape and other information of each parking area, the time when the vehicle enters the parking lot is recorded, and the parking time is determined according to the user's intention or travel plan, the free parking area is queried, and the first position is determined according to the three-dimensional map. The initial environmental feature data at the current moment is collected using the vehicle's own sensors (such as temperature sensors, solar radiation intensity sensors, and humidity sensors), and the solar azimuth at the current time is calculated using astronomical algorithms by collecting environmental images.

[0098] In combination with the first orientation and solar azimuth of the parking area, changes in solar radiation at different time periods are estimated through environmental modeling. In this way, the irradiation area and irradiation duration of sunlight in the current parking area during the parking time are calculated, and the time the vehicle is at high temperature is estimated, so as to determine the respective change amplitudes of temperature characteristics, solar radiation intensity characteristics and humidity characteristics in this period. Finally, the change range of environmental characteristics after estimating the parking time is determined, and the compensation factor is determined according to the predicted change range of environmental characteristics. For example, the compensation factor can be a fixed value or a function based on the change range of environmental characteristics. The compensation factor is used to compensate the initial environmental characteristics to obtain the predicted values ​​of environmental characteristics (i.e., temperature characteristics, solar radiation intensity characteristics, humidity characteristics) during the parking time, and the predicted values ​​are used as the environmental characteristics of the parking area during the parking time.

[0099] It should be noted that by dynamically updating the temperature characteristics, solar radiation intensity characteristics, and humidity characteristics during the parking time, calling the second exposure index model can determine the exposure index of the parking time period.

[0100] By acquiring vehicle and parking lot information in the above manner, it is beneficial to obtain the environmental characteristics of the parking area in real time, provide basic data for subsequent compensation calculations, accurately predict the range of environmental characteristics, reasonably determine compensation factors, and improve the accuracy and reliability of environmental characteristic data. At the same time, by improving the accuracy and practicality of compensation calculations, accurate parking area environmental characteristic prediction values ​​can be obtained.

[0101] Optionally, in the related art, if multiple parking areas appear at the same time, it is often difficult for users with selection difficulties to select a suitable parking area as a parking space.

[0102] In one embodiment, determining the first parking area according to the positions of the plurality of parking areas includes:

[0103] Obtaining an input operation instruction, the operation instruction carrying a target parking area in which the target vehicle is to be parked;

[0104] parsing the operation instruction, performing position matching between the obtained target parking area and the plurality of parking areas, and determining the first parking area, wherein the operation instruction is voice information or image information; or

[0105] Obtaining map information of multiple parking areas in the parking lot currently entered by the target vehicle;

[0106] A first parking area is determined by matching the map information distributed in multiple parking areas according to the driver's personalized configuration, where the personalized configuration is generated based on the driver's parking driving habits or near the parking lot entrance and exit.

[0107] In one embodiment, the microphone of the vehicle system recognizes the location or name of the target parking area spoken by the user, and the voice information is converted into text information through voice recognition. Alternatively, an image of the target parking area is captured by a vehicle camera or a mobile phone, or an image of the target parking area is determined through IVI interaction, and the information of the target parking area is extracted by processing the image. The target parking area information extracted from the voice or image input is parsed to extract key information (e.g., the name and location of the parking area), and the parsed target parking area information is positionally matched with multiple parking area information, and the first parking area closest to the target parking area is determined according to the matching result.

[0108] Through the above method, not only a variety of input methods are provided to meet the usage habits and needs of different users and reduce the possibility of misoperation; by automatically matching and determining the parking area, the efficiency and accuracy of parking are improved, and at the same time, the user experience and satisfaction are enhanced.

[0109] In another embodiment, a parking lot management system or an in-vehicle navigation system is used to obtain map information of multiple parking areas in the parking lot, including the location, size, shape, etc. of the parking areas. The driver's personalized configuration information is obtained from the driver's personal account or in-vehicle system, including parking driving habits, preferred parking locations, etc. The driver's personalized configuration is matched with the map information of multiple parking areas in the parking lot to find a parking area that meets the driver's needs. Based on the matching results, one or more qualified parking areas are determined as candidate parking areas, and the first one is selected as the first parking area according to priority.

[0110] Through the above method, the map information of multiple parking areas in the parking lot where the vehicle is currently located is obtained and processed, and the parking area matching based on the driver's personalized configuration is improved, which improves the parking efficiency and satisfaction and reduces the driver's time and energy in finding a suitable parking area in the parking lot.

[0111] Optionally, in the related art, when the selected first parking area is a condition where a vehicle is parked, how should the vehicle make a decision?

[0112] In one embodiment, before calculating the exposure index of the first parking area, it also includes: if the target vehicle approaches the first parking area and it is detected that the first parking area is in a non-idle state, matching is performed in multiple parking areas according to the driver's personalized configuration to determine the first parking area that is in an idle state.

[0113] Exemplarily, the state of the first parking area (i.e., free or occupied) is detected in real time using a parking lot management system or through on-board sensors (e.g., radar, camera, etc.) or a vehicle positioning system. If the first parking area is detected to be in a non-free state, it has been occupied by other vehicles. The driver's personalized configuration information is obtained from the driver's personal account or on-board system, including parking preferences (e.g., near entrances and exits, spacious areas, shaded places, etc.), parking habits (e.g., backing into a garage, parallel parking, etc.), etc. According to the driver's personalized configuration, a match is performed among multiple parking areas in the parking lot to find a free parking area that meets the driver's needs. Based on the matching results and the parking area status, a new first parking area in a free state is determined for the target vehicle to park.

[0114] Through the above method, by real-time detection of parking area status and personalized configuration matching, a suitable vacant parking area can be quickly found for the driver, reducing the driver's time and energy in finding a parking space in the parking lot; at the same time, the parking area is selected according to the driver's personalized needs to meet the driver's parking preferences and habits, thereby improving parking comfort and satisfaction.

[0115] The parking method provided in the above embodiment obtains the positions of multiple parking areas where the target vehicle is to be parked in response to a parking instruction; determines a first parking area according to the positions of the multiple parking areas, thereby reducing the trouble of manually searching for parking spaces; calculates the exposure index of the first parking area, and if the exposure index of the first parking area is less than a preset exposure index, controls the target vehicle to park in the first parking area; before parking in the parking area, reduces the risk of the vehicle being exposed to the sun by evaluating the exposure index, thereby avoiding reducing the service life of the vehicle's electronic components; if the exposure index of the first parking area is greater than or equal to the preset exposure index, takes the first parking area as the starting point, and searches for a second parking area within or outside a preset driving distance for parking. The present application comprehensively considers the parking position, driving distance, and exposure risk, and provides a convenient and safe parking solution, which not only improves parking efficiency, but also improves user satisfaction and experience.

[0116] In some embodiments, the CPU computing power of the IVI is strong, the memory is sufficient, the storage space is sufficient, and the IVI runs on the Android operating system. Figure 3 , is a specific schematic diagram of the parking method provided in the embodiment of the present application, and the detailed process of the parking method is as follows:

[0117] 1) Start, as the starting point of the process;

[0118] If the user activates the autonomous parking function;

[0119] 2) Vehicles search for vacant parking spaces: Vehicles find vacant parking spaces in the parking lot;

[0120] 3) Information collected by on-board sensors: The vehicle's sensors collect temperature, solar radiation, humidity, vehicle orientation, and vehicle color, and determine quantized feature values;

[0121] 4) Calculate SEI value: Calculate the SEI value according to the characteristic value converted from the collected data according to formula (1);

[0122] 5) Determine whether the SEI value is greater than or equal to a preset SEI threshold;

[0123] If it is greater than or equal to the preset SEI threshold, the vehicle's mileage is recorded; and it is determined whether the vehicle's mileage is greater than 1KM;

[0124] If it is greater than 1KM, continue to step 2) to find the next free parking space;

[0125] If it is not greater than 1KM, proceed to step 6);

[0126] If it is less than the preset SEI threshold, proceed to step 6)

[0127] 6) Parking in an empty parking space: The automatic parking function ends after parking in this empty parking space.

[0128] In the present application, the trouble of manually searching for parking spaces is reduced. By calculating the exposure index, the risk of vehicle exposure is reduced by evaluating the exposure index before parking in the parking area, thereby avoiding reducing the service life of the vehicle's electronic components; avoiding adverse effects on the vehicle due to parking in a parking space that may cause exposure; and comprehensively considering the parking position, driving distance and exposure risk, a convenient and safe parking solution is provided, which not only improves parking efficiency, but also improves user satisfaction and experience.

[0129] In one embodiment, a parking device is provided, and the parking device is used to execute the parking method provided in any of the above embodiments. Figure 4 , Figure 4 A schematic diagram of the structure of the parking device provided in the embodiment of the present application is shown in FIG. Figure 4 As shown, the parking device includes a position acquisition module 401, an exposure index calculation module 402, a first parking control module 403 and a second parking control module 404, wherein:

[0130] A position acquisition module 401 is used to obtain the positions of multiple parking areas where the target vehicle is to be parked in response to a parking instruction;

[0131] An exposure index calculation module 402, configured to determine a first parking area according to the positions of the plurality of parking areas, and calculate an exposure index of the first parking area;

[0132] The first parking control module 403 is used to control the target vehicle to park in the first parking area if the exposure index of the first parking area is less than a preset exposure index;

[0133] The second parking control module 404 is configured to, if the exposure index of the first parking area is greater than or equal to a preset exposure index, use the first parking area as a starting point to find a second parking area that meets a preset driving distance for parking.

[0134] For the specific definition of the parking device, please refer to the definition of the parking method above, which will not be repeated here. Each module in the above parking device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0135] In this embodiment, the parking device is substantially provided with a plurality of modules for executing the parking method in any of the above embodiments. The specific functions and technical effects can be referred to the above embodiments and will not be described in detail here.

[0136] In one embodiment, a vehicle is provided, the vehicle comprising the parking device provided by any one of the above embodiments.

[0137] For the specific definition of the vehicle, please refer to the definition of the parking method above, which will not be repeated here. Each module in the above-mentioned vehicle can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0138] In one embodiment, an electronic device is provided. The electronic device may be a server, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The electronic device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, the functions or steps on the server side of the above method are implemented.

[0139] In one embodiment, an electronic device is provided. The electronic device may be a client, and its internal structure diagram may be as follows: Figure 6 As shown. The electronic device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external server via a network connection. When the computer program is executed by the processor, the functions or steps of the client side of the above method are implemented.

[0140] In one embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0141] In response to a parking instruction, positions of multiple parking areas where a target vehicle is to be parked are obtained; a first parking area is determined according to the positions of the multiple parking areas, and an exposure index of the first parking area is calculated; if the exposure index of the first parking area is less than a preset exposure index, the target vehicle is controlled to park in the first parking area; if the exposure index of the first parking area is greater than or equal to the preset exposure index, the first parking area is used as a starting point to find a second parking area that meets a preset driving distance for parking.

[0142] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0143] In response to a parking instruction, positions of multiple parking areas where a target vehicle is to be parked are obtained; a first parking area is determined according to the positions of the multiple parking areas, and an exposure index of the first parking area is calculated; if the exposure index of the first parking area is less than a preset exposure index, the target vehicle is controlled to park in the first parking area; if the exposure index of the first parking area is greater than or equal to the preset exposure index, the first parking area is used as a starting point to find a second parking area that meets a preset driving distance for parking.

[0144] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or electronic device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0145] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program, and the above-mentioned computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0146] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the above-mentioned device or system can be divided into different functional units or modules to complete all or part of the functions described above.

[0147] The embodiments provided above 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 the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A parking method, characterized in that: The method comprises: In response to a parking instruction, obtaining positions of a plurality of parking areas where the target vehicle is to be parked; Determining a first parking area according to the positions of the plurality of parking areas, and calculating an exposure index of the first parking area; If the exposure index of the first parking area is less than a preset exposure index, controlling the target vehicle to park in the first parking area; If the exposure index of the first parking area is greater than or equal to a preset exposure index, the first parking area is used as a starting point to find a second parking area within or outside a preset driving distance for parking.

2. The parking method according to claim 1, characterized in that: Taking the first parking area as a starting point, searching for a second parking area within or outside a preset driving distance for parking includes: Taking the first parking area as the starting point, recording the mileage; If the mileage does not exceed the preset mileage, then calculating the exposure index of the found idle parking area, taking the parking area with the exposure index less than the preset exposure index as the second parking area, and controlling the target vehicle to park in the second parking area; or If the driving mileage exceeds the preset driving mileage, and the exposure indexes of the multiple parking areas are all greater than or equal to the preset exposure index, the parking area corresponding to the minimum value of the multiple exposure indexes is selected as the second parking area, and the target vehicle is controlled to park in the second parking area; If the mileage exceeds the preset mileage and no idle parking area is found, any idle parking area that the target vehicle finds next is used as the second parking area, and the target vehicle is controlled to park in the second parking area.

3. The parking method according to claim 1 or 2, characterized in that: The method for determining the exposure index includes: Acquire temperature characteristics, solar radiation intensity characteristics and humidity characteristics of the parking area currently in an idle state, and color characteristics and orientation characteristics of the target vehicle; Performing weighted calculation on the temperature feature, the solar radiation intensity feature, the humidity feature, the color feature and the orientation feature according to a preset weight coefficient to determine the exposure index; or Acquire a data set, wherein the data set includes pre-processed temperature characteristics, solar radiation intensity characteristics and humidity characteristics of each parking area, and color characteristics and orientation characteristics of the vehicle; Dividing the data set into a training set and a test set; Constructing a residual network model based on a fusion attention mechanism, using the temperature characteristics, solar radiation intensity characteristics, humidity characteristics of each parking area in the training set, and the color characteristics and orientation characteristics of the vehicle, performing weighted fusion training through preset weight coefficients, and determining a first exposure index model; Using the test set to test the first exposure index model, adjusting the loss value until a preset convergence condition is reached, and determining a second exposure index model; Inputting various characteristics of the parking area currently in an idle state into the second exposure index model to determine the exposure index.

4. The parking method according to claim 3, characterized in that: Before determining the temperature characteristics, solar radiation intensity characteristics, and humidity characteristics of the parking area, the method further includes: Obtaining a three-dimensional map of the parking space currently entered by the target vehicle and the parking duration, wherein the three-dimensional map includes a plurality of parking areas; Determine a first position of the parking area currently in an idle state in the three-dimensional map, as well as initial temperature characteristics, initial solar radiation intensity characteristics, and initial humidity characteristics of the parking area at a current moment; Determine, according to the solar azimuth at the current time and the first azimuth of the current parking area, respective change ranges of the initial temperature characteristic, the initial solar radiation intensity characteristic, and the initial humidity characteristic relative to the current time after the parking time; Determine a temperature compensation factor, a radiation compensation factor, and a humidity compensation factor according to respective variation ranges of the initial temperature characteristic, the initial solar radiation intensity characteristic, and the initial humidity characteristic of the parking area; According to the temperature compensation factor, the radiation compensation factor and the humidity compensation factor, compensation calculation is performed on the initial temperature characteristics, initial solar radiation intensity characteristics and initial humidity characteristics of the parking area to determine the temperature characteristics, solar radiation intensity characteristics and humidity characteristics of the parking area during the parking time.

5. The parking method according to claim 1 or 2, characterized in that: Determining a first parking area according to the positions of the plurality of parking areas comprises: Acquire an input operation instruction, wherein the operation instruction carries the target parking area in which the target vehicle is to be parked; parsing the operation instruction, performing position matching between the obtained target parking area and the plurality of parking areas, and determining a first parking area, wherein the operation instruction is voice information or image information; or Acquire map information of a plurality of parking areas in the parking space currently entered by the target vehicle; A first parking area is determined by matching the map information distributed in the plurality of parking areas according to the driver's personalized configuration, wherein the personalized configuration is generated based on the driver's parking habit or close to a parking lot entrance or exit.

6. The parking method according to claim 5, characterized in that: Before calculating the exposure index of the first parking area, the method further includes: if the target vehicle approaches the first parking area and it is detected that the first parking area is in a non-idle state, matching is performed in multiple parking areas according to the driver's personalized configuration to determine the first parking area that is in an idle state.

7. A parking device, characterized in that: The parking device comprises: A position acquisition module, for acquiring positions of a plurality of parking areas where the target vehicle is to be parked in response to a parking instruction; an exposure index calculation module, configured to determine a first parking area according to the positions of the plurality of parking areas, and calculate an exposure index of the first parking area; a first parking control module, configured to control the target vehicle to park in the first parking area if the exposure index of the first parking area is less than a preset exposure index; The second parking control module is used to find a second parking area that meets a preset driving distance for parking with the first parking area as a starting point if the exposure index of the first parking area is greater than or equal to a preset exposure index.

8. A vehicle, characterized in that: The vehicle comprises the parking device according to claim 7.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images