Vehicle control method and device, computer equipment and storage medium

Abstract

The invention relates to a vehicle control method and device, computer equipment and a storage medium. The method comprises the steps of obtaining sensor data of a vehicle sensor based on the opening state of a vehicle tail door; identifying object information and environment information inside and outside the vehicle according to the sensor data; transmitting the object information and the environment information to a cloud server, so that the cloud server determines a user intention according to the object information and the environment information; and receiving the user intention, and controlling the vehicle according to the user intention. The current environment scene information is intelligently identified, and the vehicle is automatically controlled, so that the vehicle control time of a user based on a certain scene is shortened, and the vehicle control is more convenient.

Description

Technical Field

[0001] This application relates to the technical field of vehicle intelligent control, and particularly to a vehicle control method, device, computer device, and storage medium. Background Art

[0002] With the development of new energy vehicles, the intelligence level of household vehicles is getting higher and higher. By setting a variety of different types of sensors inside and outside the vehicle, the vehicle obtains the data collected by the sensors and analyzes the data to achieve intelligent driving and intelligent control of the vehicle.

[0003] In the current related technologies, when a user needs to control a vehicle in some scenarios, different devices need to be manipulated separately, with low intelligence level and cumbersome operations. For example, in the trunk market scenario, the user needs to adjust devices such as the in-vehicle lights, in-vehicle air conditioner, rear seat angle, and audio, and manipulating these devices one by one takes a long time and is cumbersome. Summary of the Invention

[0004] Based on this, it is necessary to provide a vehicle control method, device, computer device, and storage medium for the above technical problems.

[0005] In a first aspect, this application provides a vehicle control method, the method includes: obtaining sensor data of vehicle sensors based on the opening state of the vehicle tailgate; the sensor data includes: image sensor data, radar sensor data, and position sensor data; identifying object information and environmental information inside and outside the vehicle according to the sensor data; transmitting the object information and environmental information to a cloud server so that the cloud server determines the user intention according to the object information and environmental information; receiving the user intention and controlling the vehicle according to the user intention; the controlling the vehicle includes: controlling at least one of the in-vehicle lights, air conditioner, seats, audio, refrigerator, display screen, suspension, and vehicle tailgate of the vehicle.

[0006] In one embodiment, the obtaining sensor data of vehicle sensors based on the opening state of the vehicle tailgate includes: obtaining an opening signal of the vehicle tailgate and starting timing; obtaining timing information, and if the timing information meets a preset condition, obtaining sensor data of vehicle sensors.

[0007] In one embodiment, the identifying object information and environmental information inside and outside the vehicle according to the sensor data includes: determining all objects inside and outside the vehicle according to the sensor data; identifying object information inside and outside the vehicle based on all the objects and the sensor data; the object information includes position information and shape information; determining environmental information outside the vehicle based on the object information and the sensor data.

[0008] In one embodiment, determining the environmental information outside the vehicle based on the object information and the sensor data includes: determining first object information of a moving object and second object information of a stationary object based on the object information and the sensor data; determining a first object category corresponding to the first object information and a second object category corresponding to the second object information according to the first object information and the second object information; and determining the environmental information according to the first object category and the second object category.

[0009] In one embodiment, determining the environmental information according to the first object category and the second object category includes: determining geographical location information according to the position sensor data and preset map data; and determining the environmental information according to the first object category, the second object category, and the geographical location information.

[0010] In one embodiment, transmitting the object information and the environmental information to a cloud server so that the cloud server determines a user intention according to the object information and the environmental information includes: the cloud server pre-stores a first mapping relationship among the object information, the environmental information, and the user intention; and transmitting the object information and the environmental information to the cloud server so that the cloud server compares the object information and the environmental information with the first mapping relationship to determine the user intention.

[0011] In one embodiment, receiving the user intention and controlling the vehicle according to the user intention includes: receiving the user intention; matching the user intention in a second mapping relationship to determine a target control strategy corresponding to the user intention; the second mapping relationship being a mapping relationship between the user intention and the vehicle control strategy; and controlling the vehicle according to the target control strategy.

[0012] In a second aspect, the present application further provides a vehicle control device, and the device includes: an acquisition module configured to acquire sensor data of vehicle sensors based on the opening state of a vehicle tailgate; the sensor data including: image sensor data, radar sensor data, and position sensor data; an identification module configured to identify object information and environmental information inside and outside the vehicle according to the sensor data; an intention determination module configured to transmit the object information and the environmental information to a cloud server so that the cloud server determines a user intention according to the object information and the environmental information; and a control module configured to receive the user intention and control the vehicle according to the user intention; the controlling the vehicle including: controlling at least one of in-vehicle lights, an air conditioner, seats, a stereo, a refrigerator, a display screen, a suspension, and the vehicle tailgate of the vehicle.

[0013] In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, any of the vehicle control methods in the first aspect described above is implemented.

[0014] In a fourth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, any of the vehicle control methods in the first aspect described above is implemented.

[0015] For the above vehicle control method, device, computer device, and storage medium, based on the opening state of the vehicle tailgate, sensor data of vehicle sensors is acquired. According to the sensor data, object information and environmental information inside and outside the vehicle are identified. The object information and environmental information are transmitted to a cloud server so that the cloud server determines a user intention based on the object information and environmental information. Then, the user intention sent by the cloud server is received, and the vehicle is controlled according to the user intention. Through the vehicle's own vehicle sensors, the object information and environmental information inside and outside the vehicle are automatically identified, and based on the object information and environmental information, the user intention when the user opens the vehicle tailgate at this time is determined. Finally, the vehicle is controlled according to the user intention. Thus, the current environmental scenario is intelligently identified, and the vehicle is automatically controlled, reducing the user's vehicle operation time based on a certain scenario and further making vehicle operation more convenient. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flowchart of a vehicle control method in an embodiment;

[0017] Figure 2 It is a flowchart of an information recognition method in an embodiment;

[0018] Figure 3 It is a flowchart of a vehicle control method based on user intention in an embodiment;

[0019] Figure 4 It is a structural block diagram of a vehicle control device in an embodiment;

[0020] Figure 5 It is an internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] In order to make the objectives, technical solutions, and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0022] With the popularization of automobiles, the frequency of vehicle use in daily life is increasing. For example, during leisure time, goods can be sold by placing items in the trunk, that is, a trunk fair; or fishing enthusiasts can drive the vehicle to the edge of a fishpond, open the trunk, and fish based on the space at the rear of the vehicle, that is, the fishing mode; or prepare a surprise gift for a friend in the trunk and create a surprise atmosphere through in-vehicle devices, that is, the surprise mode. When using the above different modes, users need to adjust vehicle devices one by one. For example, devices such as in-vehicle lights, in-vehicle air conditioners, the angle of the rear seats, and the audio system. Adjusting vehicle devices one by one takes a long time to operate and is cumbersome.

[0023] In one embodiment, as Figure 1 shown, a vehicle control method is provided, including the following steps:

[0024] Step 101, based on the opening state of the vehicle tailgate, obtain the sensor data of the vehicle sensors.

[0025] In this embodiment, the vehicle control method is a vehicle control method that needs to be linked with the vehicle tailgate. It can be understood that it is not necessary to be linked with the vehicle tailgate, that is, the sensor data of the vehicle sensors can be obtained in any state. Taking the vehicle control method linked with the vehicle tailgate as an example, when the user stops the vehicle and opens the vehicle tailgate. Among them, the vehicle tailgate can be the trunk door of a household car, used to open the trunk space. The vehicle tailgate includes two states, a closed state and an open state. The state of the vehicle tailgate can be sensed and obtained through a tailgate sensor, and it is determined whether the vehicle tailgate is in the open state or the closed state through the tailgate sensor. When the vehicle tailgate is in the open state, obtain the sensor data of the vehicle sensors. Specifically, the vehicle sensors include an image sensor installed inside the vehicle, an image sensor installed outside the vehicle, a millimeter-wave radar installed outside the vehicle, and a lidar installed outside the vehicle. The sensor data includes vehicle internal image data, vehicle external image data, vehicle external millimeter-wave radar data, and vehicle external lidar data. Specifically, the sensor data includes: image sensor data, radar sensor data, and position sensor data.

[0026] Step 102, according to the sensor data, identify the object information and environmental information inside and outside the vehicle.

[0027] After obtaining the sensor data, identify the object information and environmental information inside and outside the vehicle based on the sensor data. Among them, the objects include objects inside the vehicle and objects outside the vehicle. Examples of objects inside the vehicle are: any objects such as a table in the trunk, goods placed on the table, people in the vehicle, and fishing rods placed in the vehicle. Examples of objects outside the vehicle are: any objects such as trees outside the vehicle, utility poles outside the vehicle, a small cart outside the vehicle, goods on the small cart outside the vehicle, people outside the vehicle, and a pond outside the vehicle. For static objects, their object information may include information such as object position, object shape, object color, and object contour; for dynamic objects, on the basis of the above static object information, it may also include: object movement speed, object movement acceleration, and object movement direction, etc. Among them, the object position can be the position of the object relative to the vehicle itself, for example, it can be represented by the direction and distance from the vehicle itself. The environmental information is the environmental information of the current vehicle determined after overall analysis of all object information. For example, if the current objects include: a school, a stationery store, and a snack stand, the current environmental information is the school entrance; if the current objects include: a snack stand and a trash can by the roadside arranged in sequence, the current environmental information is a night market; if the current objects include: multiple vehicles, the trunk of the vehicle is opened, and there are goods or a subtitle board placed in the trunk of the vehicle, the current environmental information is a trunk fair; if the current objects include: trees and a pond, the current environmental information is a fish pond.

[0028] Step 103, transmit the object information and environmental information to the cloud server so that the cloud server can determine the user's intention according to the object information and environmental information.

[0029] A cloud server refers to a server that is connected to the vehicle itself through a network and provides services such as data storage, computing, and processing. After determining the object information and environmental information, the object information and environmental information are transmitted to the cloud server. The cloud server determines the user's intention based on the object information and environmental information. Specifically, the cloud server can be configured with a trained deep learning model. After obtaining the object information and environmental information, it inputs them into the trained deep learning model to determine the user's intention. It can also be that the mapping relationships between all the object information, environmental information, and user intentions pre-provided by users are stored in the database of the cloud server. By comparing the obtained object information and environmental information in the database, the user's intention is determined. Among them, the user's intention refers to the action that the user wants to perform subsequently based on the current object information and environmental information. For example, according to the object information and environmental information, it is determined that the vehicle is at the school gate. Combining with the time, for example, 6 pm, then the user's intention is to pick up the child after school; according to the object information and environmental information, it is determined that the vehicle is at the trunk market, and there is a table in the trunk with goods placed on the table, then the user's intention is to set up a stall at the trunk market; according to the object information and environmental information, it is determined that the vehicle is at the fish pond and there is a fishing rod in the vehicle, then the user's intention is to fish.

[0030] Step 104, receive the user's intention and control the vehicle according to the user's intention.

[0031] After the cloud server determines the user's intention, it sends the user's intention to the vehicle itself. The vehicle itself receives the user's intention and controls the vehicle according to the user's intention. Controlling the vehicle includes: controlling at least one of the in-vehicle lights, air conditioner, seats, audio, refrigerator, display screen, suspension, and vehicle tailgate of the vehicle. For example, when the user's intention is to pick up the child after school, control operations such as adjusting the co-pilot seat to the child's position and turning on the air conditioner; when the user's intention is to set up a stall at the trunk market, control operations such as in-vehicle lights, air conditioner, rear seat angle, and audio; when the user's intention is to fish, control operations such as suspension height, rear seat angle, vehicle tailgate opening angle, and air conditioner.

[0032] In the above embodiments, based on the opening state of the vehicle tailgate, the sensor data of the vehicle sensors is obtained. According to the sensor data, the object information and environmental information inside and outside the vehicle are identified. The object information and environmental information are transmitted to the cloud server so that the cloud server can determine the user's intention based on the object information and environmental information. Then, the user's intention sent by the cloud server is received, and the vehicle is controlled according to the user's intention. Through the vehicle's own vehicle sensors, the object information and environmental information inside and outside the vehicle are automatically identified, and according to the object information and environmental information, the user's intention to open the vehicle tailgate at this time is determined, and finally the vehicle is controlled according to the user's intention. Thus, the current environmental scene is intelligently identified, and the vehicle is automatically controlled, reducing the user's vehicle operation time based on a certain scene, and further making the vehicle operation more convenient.

[0033] In one of the embodiments, when obtaining the sensor data of the vehicle sensors based on the opening state of the vehicle tailgate, the following steps are specifically included:

[0034] Step 1, obtain the opening signal of the vehicle tailgate and start timing.

[0035] The opening signal of the vehicle tailgate can be a signal generated by the tailgate sensor when the vehicle tailgate is opened. This signal is used to notify the vehicle system of the state change of the tailgate. The tailgate sensor can be an infrared sensor, an ultrasonic sensor, an angle sensor, an electromagnetic induction sensor, etc. This embodiment does not make specific limitations, and only needs to be able to detect the opening state of the vehicle tailgate. After receiving the opening signal of the vehicle tailgate, the timer starts timing. This timer is used to record the time from the opening of the vehicle tailgate to the current moment.

[0036] Step 2, obtain the timing information. If the timing information meets the preset conditions, obtain the sensor data of the vehicle sensors.

[0037] After the vehicle tailgate is opened, the timing information is obtained in real time. When the timing information meets the preset conditions, the sensor data of the vehicle sensors is obtained. Among them, the preset conditions can be that the timing information reaches the preset threshold. The preset threshold can be set according to the user's usage requirements, and this embodiment does not make specific limitations. For example, the preset threshold can be 5 minutes. When the timing information is greater than 5 minutes, the sensor data of the vehicle sensors is obtained.

[0038] By setting the preset conditions and obtaining the sensor data when the preset conditions are met, it is possible to avoid the situation where the user routinely opens the vehicle tailgate to pick up items, thereby further improving the accuracy of vehicle control.

[0039] In one embodiment, as Figure 2 shown, an information recognition method is provided, including the following steps:

[0040] Step 201: Determine all objects inside and outside the vehicle based on sensor data.

[0041] The sensor data includes: image sensor data, radar sensor data, and position sensor data. Specifically, the vehicle sensors include: an image sensor installed inside the vehicle, an image sensor installed outside the vehicle, a millimeter-wave radar installed outside the vehicle, a lidar installed outside the vehicle, and a real-time positioning sensor. The image sensor can be a sensor used to capture visual information around the vehicle, and can be obtained through visual devices such as vehicle cameras. Exemplarily, the image sensor data can include visual elements such as roads, people, objects, traffic signs, etc. outside and inside the vehicle. The radar sensor can detect the environment around the vehicle using radar waves and output the data, and the radar sensor data can be obtained through radar devices on the vehicle. Exemplarily, the radar sensor data can include information such as obstacles around the vehicle and vehicle speed. The position sensor can be a sensor used to determine the position and motion state of the vehicle itself, and the position sensor data can be obtained through devices such as GPS and inertial measurement unit (IMU). Exemplarily, the position sensor data can include the longitude and latitude coordinates, speed, acceleration, etc. of the vehicle. Based on the above, the image sensor data includes: image data collected by the image sensor installed inside the vehicle and the image sensor installed outside the vehicle. The radar sensor data includes: radar data collected by the millimeter-wave radar installed outside the vehicle and the lidar installed outside the vehicle. The position sensor data includes: real-time positioning data collected by the real-time positioning sensor. After obtaining the sensor data, first identify all objects inside and outside the vehicle based on the image sensor data and the radar sensor data.

[0042] Step 202: Identify object information inside and outside the vehicle based on all objects and sensor data.

[0043] For each object among all objects, determine the object information corresponding to each object inside and outside the vehicle according to the image sensor data and the radar sensor data. The object information can include position information, shape information, color information, contour information, speed information, acceleration information, running direction information, etc. The position information of each object relative to the vehicle itself can be determined through the radar sensor data; the color information of each object can be determined through the image sensor data; by combining the image sensor data and the radar sensor data, the shape information, contour information, speed information, acceleration information, and running direction information of each object can be determined. More specifically, by outlining the contours of all objects in the image sensor data, the shape information and contour information are determined. According to the image sensor data and the radar sensor data of adjacent multiple frames, the speed information, acceleration information, and running direction information are determined.

[0044] Step 203: Determine the environmental information outside the vehicle based on the object information and sensor data.

[0045] After identifying all the object information inside and outside the vehicle, based on the object information and combined with the sensor data, determine the environmental information outside the vehicle. By way of example, first, according to the object information of each object, determine the object category corresponding to the object information. Specifically, according to the contour information of each object, determine the object category of the object. The object category can be a person, a tree, a pond, a food stall, a non-motor vehicle, a road sign, a sign, etc. The corresponding object category can be identified based on the contour information of the object. A database of the mapping relationship between the contour and the object category can be set in advance. When it is necessary to determine the object category, compare the contour information to be recognized with the mapping relationship stored in the database, so as to determine the object category corresponding to the contour information to be recognized; a deep learning model for identifying the object type can also be trained in advance. When it is necessary to determine the object category, input the contour information to be recognized into the deep learning model for identifying the object type, so as to output the object category corresponding to the contour information to be recognized. After determining the object category corresponding to each object information, based on the object category and combined with the sensor data, determine the environmental information. A database of the mapping relationship between the object category and the environmental information can be set in advance. When it is necessary to determine the environmental information, compare the object category with the mapping relationship stored in the database, so as to determine the environmental information; a deep learning model for determining the environmental information can also be trained in advance. When it is necessary to determine the environmental information, input the object category into the deep learning model for determining the environmental information, so as to determine the environmental information.

[0046] In one embodiment, determining the environmental information outside the vehicle based on the object information and sensor data may include the following steps:

[0047] Step 1: Based on the object information and sensor data, determine the first object information of the moving object and the second object information of the stationary object.

[0048] Based on the speed information, acceleration information, and running direction information in the object information, divide the object information into: the first object information corresponding to the moving object and the second object information corresponding to the stationary object. For example, regard the object information with a speed information less than the speed threshold as the stationary object information, and regard the object information with a speed information greater than or equal to the speed threshold as the moving object information. Among them, the speed threshold can be set according to actual usage requirements, and this embodiment does not make specific limitations. Preferably, the speed threshold can be 0.

[0049] Step 2: According to the first object information and the second object information, determine the first object category corresponding to the first object information and the second object category corresponding to the second object information.

[0050] A database that pre-sets the mapping relationship between the contour and the object category. The first object information includes contour information, and the first object information is compared in this database to determine the first object category corresponding to the first object information; the second object information includes contour information, and the second object information is compared in this database to determine the second object category corresponding to the second object information.

[0051] A deep learning model pre-trained for identifying object types. The first object information is input into the deep learning model for identifying object types to output the first object category corresponding to the first object information; the second object information is input into the deep learning model for identifying object types to output the second object category corresponding to the second object information. The deep learning model for identifying object types classifies the features in the object information using a trained classification model (such as support vector machine, random forest, neural network, etc.) to determine the category of the object. This process may include the following sub-steps: feature selection, model training, prediction, etc.

[0052] Step 3, determine the environmental information according to the first object category and the second object category.

[0053] A database that pre-sets the mapping relationship between the object category and the environmental information. The first object category is compared in this database to determine the environmental information; or the second object category is compared in this database to determine the environmental information; or the first object category and the second object category are compared in this database to determine the environmental information.

[0054] A deep learning model pre-trained for determining environmental information. The first object category is input into the deep learning model for determining environmental information to determine the environmental information; or the second object category is input into the deep learning model for determining environmental information to determine the environmental information; or both the first object information and the second object information are input into the deep learning model for determining environmental information to determine the environmental information.

[0055] In one embodiment, when determining the environmental information according to the first object category and the second object category, it may further include: determining the geographical location information according to the position sensor data and the preset map data; determining the environmental information according to the first object category, the second object category, and the geographical location information. Among them, the position sensor data is the real-time positioning information of the vehicle itself, such as longitude and latitude information. By combining the position sensor data with the preset map data, the geographical location information of the vehicle itself on the current map can be determined. For example, the geographical location information includes: there is a school near the current longitude and latitude, currently at an intersection, there is a certain night market nearby, currently on a certain road, etc. After obtaining the current geographical location information, the environmental information is determined in combination with the first object category and the second object category. The method for determining the environmental information is the same as above, and it can adopt the method of a mapping relationship database or the method of training a deep learning model, which will not be elaborated here.

[0056] Determine the object category through the contour information of the object, and then determine the environmental information according to the object category. It can more accurately identify the environment where the vehicle itself is located, providing a data basis for the precise control of the subsequent vehicle.

[0057] In one embodiment, the cloud server prestores a first mapping relationship among object information, environmental information, and user intent. Transmit the object information and the environmental information to the cloud server, so that the cloud server compares the object information and the environmental information with the first mapping relationship to determine the user intent. All the data of object information, environmental information, and user intent uploaded by all users accumulated in the long term are stored in the cloud server. A database of the first mapping relationship among object information, environmental information, and user intent is constructed based on the above data. After the cloud server obtains the object information and the environmental information, it compares the object information and the environmental information in the first mapping relationship to determine the user intent. More specifically, all the data in the first mapping relationship can be vectorized. When determining the user intent, the obtained object information and environmental information are also vectorized, and vectorized matching is performed to determine the matching degree. The user intent corresponding to the mapping relationship with the highest matching degree is used as the output user intent. Or perform multiple user intent matches. When the same result appears multiple times among the multiple user intent results, the corresponding user intent is used as the output user intent. It can be understood that a deep learning model can also be trained based on all the data of object information, environmental information, and user intent uploaded by all users accumulated in the long term stored in the cloud server. Then, when determining the user intent, the object information and environmental information are input into the trained deep learning model to output the user intent.

[0058] By building a database in the cloud server and identifying the user intent in the cloud, the computing power of the vehicle side is saved. And using the computing power of the server can identify the user intent faster and more accurately.

[0059] In one embodiment, as Figure 3 shown, a vehicle control method based on user intent is provided, including the following steps:

[0060] Step 301, receive the user intent.

[0061] Receive the user intent sent by the cloud server.

[0062] Step 302, match the user intent in the second mapping relationship to determine the target control strategy corresponding to the user intent.

[0063] The second mapping relationship is the mapping relationship between the user intent and the vehicle control strategy. For example, the second mapping relationship includes: picking up children after school and the corresponding first control strategy; setting up a trunk market and the corresponding second control strategy; fishing and the corresponding third control strategy; camping and the corresponding fourth control strategy. When the received user intent is to set up a trunk market, the second control strategy corresponding to setting up a trunk market is taken as the target control strategy. Among them, the first control strategy can be operations such as adjusting to the location of the child and turning on the air conditioner; the first control strategy can be operations such as controlling the interior lights, air conditioner, rear seat angle, and stereo in the vehicle; the third control strategy can be operations such as controlling the suspension height, rear seat angle, vehicle tailgate opening angle, and air conditioner.

[0064] More specifically, when the user intent is to set up a trunk market, play music based on the music playing rules preset by the user. The preset music playing rules can be: playing preset music, not playing music and waiting for the user's instruction to play music, and playing the N most-played online music for the trunk market scene and looping. Because in the trunk market scene, regardless of what goods are sold, the user and customers are concentrated in the direction directly facing the trunk, so the direction of the air conditioner can be adjusted to face the trunk directly. For the lights, the lights need to face the goods and the interior, and cannot face the vehicle tailgate to avoid direct light shining into the customer's eyes. For the seats, they can be rotated and adjusted according to the user's usage needs to meet the trunk market scene.

[0065] Step 303, control the vehicle according to the target control strategy.

[0066] After obtaining the target control strategy, the vehicle can be overall controlled based on the target control strategy. Thus, the state of the controlled vehicle conforms to the user's current vehicle usage needs.

[0067] The above embodiment intelligently identifies the current environmental scene and automatically controls the vehicle, reducing the vehicle operation time of the user based on a certain scene, and further making the vehicle operation more convenient.

[0068] In one specific embodiment, for the trunk market scenario, when a user wants to set up a stall in the trunk market, it takes a long time to prepare the relevant functions of the trunk market, and when adjusting the overall effect, the user cannot observe and adjust the lights, air conditioner, and seat angles at the trunk position at the same time. In this embodiment, when the vehicle stops and the user opens the rear tailgate, the vehicle body processor receives the signal that the user has opened the rear tailgate. At this time, the vehicle does not yet know the specific purpose of the user opening the rear tailgate, and can only determine that the rear tailgate has been opened. The opening duration of the rear tailgate is obtained in real time. After the rear tailgate has been opened for more than 5 minutes, the user's people and objects inside and outside the vehicle are obtained through the recognition unit covering inside and outside the vehicle. Among them, the recognition unit includes: an in-vehicle camera, an out-of-vehicle camera, a millimeter-wave radar, and a lidar. For the sensor data obtained by the recognition unit, first, conventional recognition is performed to recognize obstacles, that is, to recognize all objects, and the positions of all objects inside and outside the vehicle, that is, the distances from the vehicle itself. Then, object recognition is performed. Through the imaging ability of the camera and the mapping ability of the radar, the distance between the object and the vehicle itself and the shape of the object are recognized. Taking radar mapping as an example, the radar performs mapping based on the time when the radar wave is emitted and then reflected back to the radar after hitting an object. According to the wavelengths of different radar waves, the shape, distance, and orientation of the object can be determined. Then, speculation recognition is performed to recognize whether all objects are moving objects or non-moving objects, so as to infer the approximate current environmental information. Among them, moving objects include vehicles, pedestrians, non-motor vehicles, animals, leaves moved by external forces such as wind, snow, and rain, etc., and non-moving objects include trees, trash cans, stopped pedestrians, vehicles, non-motor vehicles, etc.; environmental information includes parking in a parking lot, parking in a night market, temporary roadside parking, camping parking, etc., all of which can be determined after mapping through the data obtained by the radar and the camera. Environmental recognition is used to recognize environmental information and perform data comparison based on cloud data to determine environmental information. The recognized object information and environmental information are transmitted to the vehicle body processor. The vehicle body processor uploads the received data to the cloud network service through the vehicle body network service. The cloud network service receives the object information and environmental information, performs comparative analysis, and determines the usage intention of the user opening the trunk. The vehicle body network service receives the intention result from the cloud and transmits it to the vehicle body processor, and the vehicle body processor issues unified instructions. Specifically, when the vehicle body processor receives the intention result that it is in the night market area, the trunk market for setting up a stall is opened. Then, for the audio, music is played based on the music playback rules preset by the user. Among them, the preset music playback rules can be: playing preset music, not playing music and waiting for the user's instruction to play music, and playing the top N music for the stall setting scenario on the Internet and playing it in a loop. And the audio at the trunk is used as the main sound unit, which can be understood as moving the sound area in the new energy vehicle to the trunk. For the air conditioner, because in the trunk market scenario, regardless of what goods are sold, the user and customers are concentrated in the direction directly facing the trunk. Therefore, the direction of the air conditioner can be adjusted to face the trunk direction.Regarding the lighting, the lighting needs to face the goods and the interior directly, and should not face the vehicle's tailgate directly to avoid direct light shining into the customer's eyes. Regarding the seats, they can be rotated and adjusted according to the user's usage needs to meet the trunk market scenario.

[0069] When determining the object information and the user's intention, after obtaining the contour information of the object, the vehicle body processor transmits the contour information to the cloud through the vehicle's network service system. The cloud stores the mapping relationship between the contour and the object category. The cloud conducts a comparison of the graphic contours to determine the category of the object. Regarding whether the object is a moving object, since the images obtained by the radar and the camera are 3D graphics, it avoids the misjudgment caused by 2D graphics. By comparing the position of the object relative to the vehicle at n seconds with the position of the object relative to the vehicle at n + 0.01 seconds, it is determined whether the object moves. After determining the category of the object, all the object categories existing around the vehicle can be known, and according to the data stored in the cloud, the environmental information in which this type of item appears is determined. For example: The environments where small food trucks appear are mostly night market roadside stalls in areas with dense population flow such as communities, shopping malls, and schools.

[0070] In the above embodiment, when the user parks and opens the trunk, the seat, lighting, audio, and air conditioner start all automatic adjustments, saving adjustment time and simplifying the adjustment process. And the user does not need to check the effect at the rear tailgate and then go to the vehicle's central control for adjustment, but it is fully automatic control.

[0071] Regarding the trunk market, in the existing trunk markets, users need to purchase many items separately, and most of these items are available on new energy vehicles, such as: ambient lights. There are even items that are not available elsewhere in the vehicle, such as: air conditioners, the space brought by seat movement, etc. This embodiment can integrate these functions in the vehicle to provide a more direct trunk market for users. When the user has needs such as preparing a surprise, trunk market, fishing, resting, ventilation, etc., by obtaining the data of the vehicle sensors and conducting big data comparison and analysis on the obtained data, the user's intention can be accurately determined. Through various types of sensors, all the information of the object and the environment is determined, such as: people, objects, temperature, humidity, etc. are cross-compared, a preliminary comparison is made at the vehicle end, and a big data comparison is made in the cloud, thus realizing the automatic control of the vehicle and further improving the accuracy and speed of intention recognition.

[0072] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0073] Based on the same inventive concept, an embodiment of the present application further provides a vehicle control device for implementing the vehicle control method described above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the vehicle control device provided below can refer to the limitations on the vehicle control method in the above text, and will not be repeated here.

[0074] In one embodiment, as Figure 4 shown, a vehicle control device is provided, including: an acquisition module 100, an identification module 200, an intention determination module 300, and a control module 400, where:

[0075] The acquisition module 100 is configured to acquire sensor data of vehicle sensors based on the opening state of the vehicle tailgate.

[0076] The identification module 200 is configured to identify object information and environmental information inside and outside the vehicle according to the sensor data.

[0077] The intention determination module 300 is configured to transmit the object information and environmental information to a cloud server, so that the cloud server determines the user intention according to the object information and environmental information.

[0078] The control module 400 is configured to receive the user intention and control the vehicle according to the user intention.

[0079] The acquisition module 100 is further configured to acquire an opening signal of the vehicle tailgate and start timing; acquire timing information, and if the timing information meets a preset condition, acquire sensor data of vehicle sensors.

[0080] The recognition module 200 is further configured to determine all the objects inside and outside the vehicle according to the sensor data; identify the object information inside and outside the vehicle based on all the objects and the sensor data; the object information includes position information and shape information; determine the environmental information outside the vehicle based on the object information and the sensor data.

[0081] The recognition module 200 is further configured to determine the first object information of the moving object and the second object information of the stationary object based on the object information and the sensor data; determine the first object category corresponding to the first object information and the second object category corresponding to the second object information according to the first object information and the second object information; determine the environmental information according to the first object category and the second object category.

[0082] The recognition module 200 is further configured to determine the geographical location information according to the position sensor data and the preset map data; determine the environmental information according to the first object category, the second object category, and the geographical location information.

[0083] The intention determination module 300 is further configured to transmit the object information and the environmental information to the cloud server, so that the cloud server compares the object information and the environmental information with the first mapping relationship to determine the user intention.

[0084] The control module 400 is further configured to receive the user intention; match the user intention in the second mapping relationship to determine the target control strategy corresponding to the user intention; the second mapping relationship is the mapping relationship between the user intention and the vehicle control strategy; control the vehicle according to the target control strategy.

[0085] Each module in the above vehicle control device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above respective modules.

[0086] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as Figure 5As shown. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a vehicle control method.

[0087] Those skilled in the art can understand that Figure 5 the structure shown in [the figure] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0088] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, it implements any one of the vehicle control methods in the above embodiments.

[0089] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, it implements any one of the vehicle control methods in the above embodiments.

[0090] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties.

[0091] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The 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 methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRAM), magnetoresistive random access memories (MRAM), ferroelectric random access memories (FRAM), phase change memories (PCM), graphene memories, etc. Volatile memories can include random access memory (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0092] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0093] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A vehicle control method, characterized in that, The method includes: Obtaining sensor data of vehicle sensors based on the opening state of the vehicle tailgate; the sensor data includes: image sensor data, radar sensor data, and position sensor data; Identifying object information and environmental information inside and outside the vehicle according to the sensor data; Transmitting the object information and the environmental information to a cloud server, so that the cloud server determines a user intention according to the object information and the environmental information; Receiving the user intention and controlling the vehicle according to the user intention; the controlling the vehicle includes: controlling at least one of in-vehicle lights, air conditioners, seats, stereos, refrigerators, display screens, suspensions, and vehicle tailgates of the vehicle.

2. The method according to claim 1, characterized in that The obtaining sensor data of vehicle sensors based on the opening state of the vehicle tailgate includes: Obtaining an opening signal of the vehicle tailgate and starting timing; Obtaining timing information, and if the timing information meets a preset condition, obtaining sensor data of vehicle sensors.

3. The method according to claim 1, wherein The identifying object information and environmental information inside and outside the vehicle according to the sensor data includes: Determining all objects inside and outside the vehicle according to the sensor data; Identifying object information inside and outside the vehicle based on all the objects and the sensor data; the object information includes position information and shape information; Determining environmental information outside the vehicle based on the object information and the sensor data.

4. The method according to claim 3, wherein The determining environmental information outside the vehicle based on the object information and the sensor data includes: Determining first object information of moving objects and second object information of stationary objects based on the object information and the sensor data; Determining a first object category corresponding to the first object information and a second object category corresponding to the second object information according to the first object information and the second object information; Determining environmental information according to the first object category and the second object category.

5. The method according to claim 4, wherein The determining environmental information according to the first object category and the second object category includes: Determining geographical location information according to the position sensor data and preset map data; Determining environmental information according to the first object category, the second object category, and the geographical location information.

6. The method according to claim 1, wherein The transmitting the object information and the environmental information to a cloud server, so that the cloud server determines a user intention according to the object information and the environmental information includes: the cloud server prestores a first mapping relationship among object information, environmental information, and user intention; Transmitting the object information and the environmental information to the cloud server, so that the cloud server compares the object information and the environmental information with the first mapping relationship to determine the user intention.

7. The method according to claim 1, wherein The receiving the user intention and controlling the vehicle according to the user intention includes: Receiving the user intention; Matching the user intention in a second mapping relationship to determine a target control strategy corresponding to the user intention; the second mapping relationship is a mapping relationship between user intention and vehicle control strategy; Controlling the vehicle according to the target control strategy.

8. A vehicle control device, characterized in that, The device includes: An acquisition module, configured to acquire sensor data of vehicle sensors based on the opening state of the vehicle tailgate; the sensor data includes: image sensor data, radar sensor data, and position sensor data; An identification module, configured to identify object information and environmental information inside and outside the vehicle according to the sensor data; An intention determination module, configured to transmit the object information and environmental information to a cloud server, so that the cloud server determines a user intention according to the object information and environmental information; A control module, configured to receive the user intention and control the vehicle according to the user intention; the control of the vehicle includes: controlling at least one of in-vehicle lights, air conditioners, seats, stereos, refrigerators, displays, suspensions, and vehicle tailgates of the vehicle.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

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

Images