Vehicle control method and device, vehicle-mounted terminal and vehicle

Abstract

The invention is suitable for the technical field of automobiles, and provides a vehicle control method and device, a vehicle-mounted terminal and a vehicle, and the method comprises the steps: determining a dangerous case type and a dangerous case level when a dangerous case is sensed in an area where the vehicle is located through an intelligent agent of the vehicle; obtaining processing demand information corresponding to the dangerous case type; the processing demand information is used for describing information required for dealing with the dangerous case; generating a vehicle control mode based on the dangerous case level and the processing demand information; and controlling the vehicle based on the vehicle control mode through the automatic calling tool function of the intelligent agent. Compared with the prior art, the method and the device have the advantages that the control mode of the vehicle at the moment can be flexibly and specifically determined according to the dangerous case type and the dangerous case level, so that the vehicle is subsequently controlled according to the control mode, and the control accuracy of the vehicle is improved.

Description

Technical Field

[0001] The present application belongs to the field of automobile technology, and in particular, relates to a vehicle control method, device, vehicle-mounted terminal and vehicle. Background Art

[0002] With the rapid development of automobile technology, the complexity and intelligence level of automobile electronic systems are constantly improving, vehicle functions are becoming increasingly rich, and user experience has also been significantly improved. In practical applications, since the road environment is complex and changeable, and emergencies are prone to occur, in order to further improve the user's riding experience and riding safety, it is necessary to promptly control the vehicle to leave the corresponding location of the emergency when an emergency occurs.

[0003] However, existing vehicle control methods usually directly control the vehicle to drive away from the location of the emergency when an emergency is detected around the vehicle. This method is not comprehensive enough and is difficult to meet actual needs, thus reducing the accuracy of vehicle control. Summary of the invention

[0004] The embodiments of the present application provide a vehicle control method, device, vehicle-mounted terminal and vehicle to solve the problems in the prior art that the considerations are not comprehensive enough, it is difficult to meet actual needs, and the control accuracy of the vehicle is reduced.

[0005] In a first aspect, an embodiment of the present application provides a vehicle control method, including:

[0006] When the intelligent body of the vehicle senses that a dangerous situation occurs in the area where the vehicle is located, determine the type and level of the dangerous situation;

[0007] Acquire processing requirement information corresponding to the risk type; the processing requirement information is used to describe the information required when dealing with the risk;

[0008] generating the vehicle control mode based on the danger level and the processing requirement information;

[0009] The vehicle is controlled by invoking the vehicle control method through the intelligent agent.

[0010] Optionally, the determining of the risk type and risk level includes:

[0011] Acquire an environmental image of the location of the dangerous situation;

[0012] Analyzing the environmental image to obtain the dangerous situation type;

[0013] Acquire target dangerous situation data corresponding to the dangerous situation type;

[0014] The target hazard data is analyzed to obtain the hazard level.

[0015] Optionally, generating the vehicle control mode based on the danger level and the processing requirement information includes:

[0016] Determining a user's participation result according to the risk level; the participation result is used to describe whether the user participates in controlling the vehicle;

[0017] The vehicle control method is generated according to the participation result and the processing requirement information.

[0018] Optionally, generating the vehicle control method according to the participation result and the processing requirement information includes:

[0019] When the participation result is that no participation is required, the method of calling the automatic driving function of the vehicle to control the driving of the vehicle based on the processing requirement information is determined as the vehicle control method.

[0020] Optionally, the controlling the vehicle by invoking the vehicle control method through the intelligent agent includes:

[0021] When the vehicle control mode is to control the vehicle according to a user instruction, a prompt message is generated to prompt the user that a first level of danger occurs in the area;

[0022] Acquire a dangerous situation image corresponding to the dangerous situation;

[0023] The agent calls a notification module in the vehicle to send the prompt information, the danger image and the processing requirement information to the user's terminal device;

[0024] receiving a user instruction sent by the terminal device; the user instruction is generated by the user based on the prompt information, the dangerous situation image and the vehicle control information generated by the processing requirement information;

[0025] The vehicle is controlled according to the user command.

[0026] Optionally, the controlling the vehicle by invoking the vehicle control method by the intelligent agent includes:

[0027] When the vehicle control mode is to call the automatic driving function of the vehicle based on the processing requirement information to control the driving of the vehicle, obtaining processing requirement information corresponding to the dangerous situation type; the processing requirement information includes multiple points of interest, road condition information and environmental information in the area;

[0028] Determining a driving destination from a plurality of points of interest according to the road condition information and the environment information;

[0029] Performing path planning according to the driving destination and the current position of the vehicle to obtain the driving path of the vehicle;

[0030] The automatic driving function of the vehicle is called by the intelligent agent to control the vehicle to travel along the driving path so as to drive the vehicle away from the dangerous situation.

[0031] Optionally, analyzing the target hazard data to obtain the hazard level includes:

[0032] Inputting the target hazard data into a trained level determination model for processing to obtain the hazard level;

[0033] or,

[0034] Determine the danger range of the target danger data;

[0035] The danger range is compared with each preset range one by one to obtain the danger level; each preset range corresponds to a different danger level.

[0036] In a second aspect, an embodiment of the present application provides a vehicle control device, including:

[0037] A first determination unit is used to determine the type and level of danger when a danger occurs in the area where the vehicle is located through the intelligent body of the vehicle;

[0038] A first acquisition unit is used to acquire processing requirement information corresponding to the risk type; the processing requirement information is used to describe the information required when dealing with the risk;

[0039] A first generating unit, configured to generate the vehicle control mode based on the danger level and the processing requirement information;

[0040] The first control unit is used to control the vehicle by calling the vehicle control method through the intelligent agent.

[0041] In a third aspect, an embodiment of the present application provides a vehicle-mounted terminal, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, a vehicle control method as described in any one of the first aspects above is implemented.

[0042] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the vehicle control method as described in any one of the above-mentioned first aspects is implemented.

[0043] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed on a vehicle-mounted terminal, enables the vehicle-mounted terminal to execute the vehicle control method described in any one of the above-mentioned first aspects.

[0044] In a sixth aspect, an embodiment of the present application provides a vehicle, comprising an on-board terminal, wherein the on-board terminal is used to execute the vehicle control method as described in any one of the first aspects.

[0045] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0046] A vehicle control method provided by an embodiment of the present application, when the intelligent body of the vehicle perceives that a dangerous situation occurs in the area where the vehicle is located, determines the type of dangerous situation and the level of dangerous situation; obtains processing requirement information corresponding to the type of dangerous situation; the processing requirement information is used to describe the information required when dealing with dangerous situations; based on the dangerous situation level and processing requirement information, generates a vehicle control method; and controls the vehicle according to the vehicle control method. In this application, the intelligent body has an environmental perception function, which can monitor various conditions in the area where the vehicle is located in real time and detect the occurrence of dangerous situations in a timely manner. And it is not only limited to finding abnormalities, but also can further determine the type of dangerous situation (such as collision risk, road water accumulation, fire hazard, etc.) and the level of dangerous situation (for example, divided into low, medium and high levels according to the degree of danger), which reflects the in-depth analysis and accurate judgment ability of environmental information, and provides an accurate basis for subsequent targeted response measures. Afterwards, according to the determined dangerous situation type, the corresponding processing requirement information is obtained, which emphasizes the pertinence and relevance of information acquisition, so that the subsequent vehicle control is more in line with the actual dangerous situation needs. Afterwards, when generating the vehicle control method, it is not based on a single factor, but takes into account two important factors: the level of danger and the processing demand information. The level of danger reflects the urgency of the danger, and the processing demand information clarifies the specific response goals and required conditions to be achieved. By combining the two, a more scientific, reasonable and practical vehicle control strategy can be formulated, avoiding the risks brought by one-sided decisions. Finally, the intelligent agent effectively integrates the execution link of vehicle control. Once the vehicle control method is generated, the intelligent agent can call the vehicle control method to actually control the vehicle without manual intervention, realizing the automated process from decision-making to execution, improving the timeliness and accuracy of responding to dangers, reducing the delays and errors that may be caused by human operations, and improving the accuracy of vehicle control. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art 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 paying any creative work.

[0048] Figure 1 is a flow chart of an implementation of a vehicle control method provided by an embodiment of the present application;

[0049] Figure 2 is a flow chart of an implementation of a vehicle control method provided by another embodiment of the present application;

[0050] Figure 3 is a flow chart of an implementation of a vehicle control method provided in yet another embodiment of the present application;

[0051] Figure 4 is a structural schematic diagram of a vehicle control device provided by an embodiment of the present application;

[0052] Figure 5 It is a structural diagram of a vehicle-mounted terminal provided in one embodiment of the present application. DETAILED DESCRIPTION

[0053] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0054] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0055] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0056] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0057] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0058] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0059] In practical applications, with the rapid development of automobile technology, the complexity and intelligence level of automobile electronic systems are constantly improving, vehicle functions are becoming increasingly rich, and user experience has also been significantly improved. In practical applications, since the road environment is complex and changeable, and emergencies are prone to occur, in order to further improve the user's riding experience and riding safety, it is necessary to promptly control the vehicle to leave the corresponding location of the emergency when an emergency occurs.

[0060] However, the existing vehicle control method, on the one hand, waits for the user's control command when an emergency is detected around the vehicle, and only after receiving the user's command will the vehicle be controlled accordingly based on the user's command. This may easily lead to damage to the vehicle or even endanger the user's personal safety when the emergency is very critical and the user is unable to make accurate instructions in time.

[0061] On the other hand, when an emergency is detected around the vehicle, the vehicle is directly controlled to move away from the location of the emergency. This may easily lead to a sudden change in the original driving route of the vehicle when the danger level of the emergency is low, thereby reducing the user's riding experience and increasing the energy consumption of the vehicle when the route is suddenly changed.

[0062] In summary, the existing technologies are not comprehensive enough and cannot meet actual needs, which reduces the vehicle control accuracy and user experience.

[0063] Based on this, an embodiment of the present application proposes a vehicle control method that can improve the control accuracy of the vehicle.

[0064] See also Figure 1 , Figure 1 This is a flow chart of a vehicle control method provided in an embodiment of the present application. In the embodiment of the present application, the execution subject of the vehicle control method is a vehicle-mounted terminal. The vehicle-mounted terminal may be a vehicle-mounted intelligent terminal (Telematics BOX, T-BOX).

[0065] It should be noted that in order to improve the analysis efficiency and accuracy of the vehicle-mounted terminal on various data, the vehicle-mounted terminal includes an intelligent agent.

[0066] It should be noted that the agent is an intelligent system integrated into the car. It can sense the vehicle's own status, surrounding environment and user needs, and make decisions to control certain functions of the vehicle or provide services to users by analyzing and processing this information. It is like the "brain" of the car, allowing the car to run more intelligently.

[0067] Among them, the intelligent agent in the vehicle usually runs on a specific automotive operating system, such as Linux, QNX, etc. At the same time, the core processor of the intelligent agent is generally located in the electronic control unit (ECU) of the vehicle.

[0068] In the embodiments of the present application, the intelligent agent in the vehicle generally has environmental perception function, active service function and automatic tool calling function.

[0069] The environmental perception functions include:

[0070] The agent collects image data through the cameras equipped on the vehicle (such as front view, rear view, surround view cameras, etc.). These cameras can capture information such as road conditions, traffic signs, other vehicles, pedestrians, and possible obstacles around the vehicle. For example, the front view camera can monitor in real time whether there are animals appearing suddenly on the road ahead, vehicles braking suddenly, or road collapses.

[0071] At the same time, the intelligent agent pre-sets a series of rules based on knowledge and experience to identify dangerous situations. For example, if the deceleration of the vehicle in front exceeds a certain threshold and the distance from the vehicle is less than the safe distance, it is judged as a rear-end collision; if the vehicle is driving on a flooded road section and the water level sensor detects that the water level exceeds the safe level, it is judged as a flooding danger. These rules can be formulated based on traffic regulations, vehicle dynamics principles and actual driving experience.

[0072] Among them, the active service functions specifically include:

[0073] Environmental perception and automatic adjustment: The agent can monitor temperature, humidity, air quality, and the number of passengers through in-car sensors and actively adjust the air conditioning system. For example, when the temperature in the car is detected to be too high or too low, the agent will automatically adjust the temperature, air volume, and air outlet mode of the air conditioner to keep the in-car environment comfortable. If the air quality in the car is poor (such as detecting harmful gases or odors), the agent can automatically switch to air circulation mode and start the air purification function to improve the air quality in the car.

[0074] Itinerary planning and reminders: Intelligent navigation and route optimization: Combining real-time traffic information, weather conditions, and the driver's preferences (such as avoiding toll roads, choosing scenic routes, etc.), the intelligent agent can proactively plan the best route for the driver. During driving, if there is traffic congestion or other emergencies, the intelligent agent will re-plan the route in real time and inform the driver through voice or screen prompts. For example, when the driver enters the destination, the intelligent agent will not only provide the fastest route, but also take into account the location and use of facilities such as gas stations and parking lots along the way, and provide the driver with comprehensive itinerary planning suggestions.

[0075] Trip reminders and service recommendations: Based on the driver's schedule and instructions, the agent can proactively provide relevant reminders and service recommendations. For example, if the driver often goes to the gym at a certain time, the agent can remind the driver when it is close to that time and recommend nearby gyms or fitness classes; when the vehicle's fuel level is low, the agent will proactively remind the driver of the location of nearby gas stations and provide discount information and business hours of the gas stations.

[0076] Among them, the automatic call tool function:

[0077] It is the ability to select and use various appropriate control tools or systems inside the vehicle to achieve specific vehicle operations based on pre-set strategies or real-time generated decisions. It is equivalent to the "executive hand" of the intelligent body, converting decisions into actual vehicle actions, such as braking, steering, acceleration, etc., so as to effectively control the vehicle.

[0078] Based on the agent's perception of the danger (including the type and level of danger) and the generated vehicle control method, the agent can formulate a specific control strategy. The control strategy specifies in detail which tools should be called in different situations, in what order, and how the control parameters of the tools should be set. For example, for a high-level forward collision danger, the control strategy may be emergency braking first (calling the ABS system and setting the maximum brake pressure) and slight steering avoidance (calling the electric power steering system and setting the steering torque according to the target avoidance angle).

[0079] like Figure 1 As shown, the vehicle control method provided in one embodiment of the present application may include S101 to S103, which are described in detail as follows:

[0080] In S101, when the intelligent body of the vehicle senses that a dangerous situation occurs in the area where the vehicle is located, the type and level of the dangerous situation are determined.

[0081] In the embodiment of the present application, the vehicle-mounted terminal can detect in real time with the intelligent entity to which it is wirelessly connected whether there is any dangerous situation in the area where the vehicle is located.

[0082] In some possible embodiments, the vehicle-mounted terminal can detect in real time whether there is any danger in the area where the vehicle is located through the environment perception capability of the intelligent body.

[0083] In some other possible embodiments, the vehicle-mounted terminal can detect in real time whether a dangerous situation occurs in the area where the vehicle is located through a dangerous situation perception system connected to the vehicle by wireless communication.

[0084] In this embodiment, the danger perception system can collect the environmental information of the area where the vehicle is located in real time through various vehicle-mounted sensors connected to the vehicle wirelessly. Among them, the vehicle-mounted sensors include but are not limited to: temperature sensors, smoke sensors, image sensors, humidity sensors, and road condition sensors. Correspondingly, the environmental information of the area where the vehicle is located includes but is not limited to: temperature, smoke level, humidity, and road condition information.

[0085] In this embodiment, after acquiring the above environmental information, the danger perception system can input the environmental information into the danger detection model for processing to obtain a danger result, wherein the danger result is used to describe whether a danger occurs in the area where the vehicle is located.

[0086] The danger detection model is trained by a pre-built neural network model.

[0087] It should be noted that the hazard detection model can be obtained by training a pre-built neural network model based on a preset sample set. Among them, each sample data in the preset sample set includes sample environmental information and a sample hazard result corresponding to the sample environmental information. When training the pre-built neural network model, the sample environmental information in each sample data is used as the input of the neural network model, and the sample hazard result corresponding to the sample environmental information in each sample data is used as the output of the neural network model. Through training, the neural network model can learn the correspondence between all possible sample environmental information and sample hazard results, and use the trained neural network model as a hazard detection model.

[0088] Afterwards, the danger perception system can send the above danger results to the vehicle terminal.

[0089] In this embodiment, when the vehicle-mounted terminal detects that a dangerous situation exists, it can determine that a dangerous situation occurs in the area where the vehicle is located.

[0090] In the embodiment of the present application, when the vehicle-mounted terminal detects a dangerous situation in the area where the vehicle is located, in order to achieve precise control of the vehicle, the vehicle-mounted terminal can determine the type and level of the dangerous situation.

[0091] Among them, the types of dangerous situations include but are not limited to: vehicle collisions (such as rear-end collisions, side collisions, etc.), road conditions (such as water accumulation, ice, and large potholes, etc.), fires and floods, etc.

[0092] The danger level is used to describe the danger level of the danger. The danger level includes but is not limited to the first and second levels. Among them, the first level is used to describe the danger level of the danger as general, that is, the general danger. The second level is used to describe the danger level of the danger as critical, that is, the critical danger.

[0093] In one embodiment of the present application, the vehicle-mounted terminal can obtain real-time environmental images of the location of the dangerous situation through a camera connected to it through wireless communication.

[0094] In this embodiment, the vehicle-mounted terminal pre-stores a set of danger images of various different types of dangers, wherein each set of danger images of a type of danger includes standard danger images of the type of danger at different danger levels.

[0095] Based on this, the vehicle-mounted terminal can compare the environment image with each standard dangerous situation image in the dangerous situation image set of different types of dangerous situations one by one, so as to obtain the target dangerous situation image that is most similar to the environment image.

[0096] Afterwards, the vehicle-mounted terminal can directly determine the type corresponding to the target danger image as the danger type of the danger in the area where the vehicle is currently located, and determine the danger level corresponding to the target danger image as the danger level of the danger in the area where the vehicle is currently located.

[0097] In another embodiment of the present application, in order to improve the accuracy of determining the type and level of danger of the danger in the area where the vehicle is located, the vehicle terminal can also Figure 2 Steps S201 to S204 shown determine the risk type and risk level, as detailed below:

[0098] In S201, an environmental image of the dangerous situation location is obtained.

[0099] In S202, the environmental image is analyzed to obtain the dangerous situation type.

[0100] In some possible embodiments, the vehicle-mounted terminal can obtain real-time environmental images of the dangerous situation location through a camera connected to the vehicle-mounted terminal through wireless communication.

[0101] In this embodiment, after obtaining the environment image, the vehicle-mounted terminal can input the environment image into the danger type determination model for analysis, thereby obtaining the danger type corresponding to the danger. The danger type determination model is trained based on the pre-built first deep learning model.

[0102] It should be noted that the hazard type determination model can be obtained by training a pre-constructed first deep learning model based on a preset sample set. Among them, each sample data in the preset sample set includes a sample environment image and a sample hazard type corresponding to the sample environment image. When training the pre-constructed first deep learning model, the sample environment image in each sample is used as the input of the first deep learning model, and the sample hazard type corresponding to the sample environment image in each sample is used as the output of the first deep learning model. Through training, the first deep learning model can learn the correspondence between all possible sample environment images and sample hazard types, and use the trained first deep learning model as the hazard type determination model.

[0103] In S203, target dangerous situation data corresponding to the dangerous situation type is obtained.

[0104] In this embodiment, after the vehicle terminal determines the type of danger, since the corresponding danger data of different types of dangers are not exactly the same, the vehicle terminal can obtain target danger data collected by various vehicle sensors related to the danger type.

[0105] In some possible embodiments, the vehicle terminal may obtain a historical danger data set corresponding to the danger type in a historical time period, wherein the historical danger data set includes historical data of different data types related to the danger type in the historical time period.

[0106] The historical time period can be determined according to actual needs and is not limited here.

[0107] Based on this, the vehicle-mounted terminal may determine the type of target dangerous situation data to be acquired based on the data type of each historical data in the above historical dangerous situation data set, so as to acquire the target dangerous situation data.

[0108] It should be noted that when the hazard type is fire, the corresponding target hazard data includes but is not limited to: temperature data, fire data, and smoke data; when the hazard type is road condition, the corresponding target hazard data includes but is not limited to: road surface data and liquid level data; when the hazard type is vehicle collision, the corresponding target hazard data includes but is not limited to: the number of colliding vehicles and the number of injured people.

[0109] In S204, the target hazard data is analyzed to obtain the hazard level.

[0110] In this embodiment, after obtaining the target danger data, the vehicle terminal can directly input the target danger data into the trained level determination model for analysis, thereby obtaining the danger level of the danger. The level determination model is trained based on the pre-built second deep learning model.

[0111] It should be noted that the level determination model can be obtained by training a pre-constructed second deep learning model based on a preset sample set. Among them, each sample data in the preset sample set includes sample hazard data and the sample hazard level corresponding to the sample hazard data. When training the pre-constructed second deep learning model, the sample hazard data in each sample is used as the input of the second deep learning model, and the sample hazard level corresponding to the sample hazard data in each sample is used as the output of the second deep learning model. Through training, the second deep learning model can learn the correspondence between all possible sample hazard data and sample hazard levels, and use the trained second deep learning model as the level determination model.

[0112] In another embodiment of the present application, since the training of deep learning models usually requires a large number of samples, huge amount of calculations, and a long training time, in order to improve the rate of determining the hazard level, when the target hazard data is a specific value, the vehicle-mounted terminal can detect the hazard range of the target hazard data after obtaining the target hazard data.

[0113] It should be noted that the number of hazard ranges corresponds to the number of hazard levels, that is, the hazard ranges may include the same number of ranges as the hazard levels include.

[0114] In this embodiment, since the danger level includes a first level and a second level, the preset range may include: a first preset range and a second preset range. The first preset range may be [0, first threshold), and the second preset range may be [first threshold, +∞). The first threshold may be determined according to actual needs and is not limited here.

[0115] Since the danger level of the first level of danger is lower than that of the second level of danger, and the larger the specific value of the target danger data, the higher the danger level, the on-board terminal can determine that the danger range corresponding to the first level is the first preset range, and the on-board terminal can determine that the danger range corresponding to the second level is the second preset range.

[0116] In this embodiment, after determining the danger range where the target danger data is located, the vehicle terminal can compare the danger range with each of the above preset ranges one by one to determine which preset range the danger range is in. Afterwards, the vehicle terminal can determine the danger level corresponding to the preset range where the danger range is located as the danger level of the danger in the area where the vehicle is located at this time.

[0117] As can be seen from the above, the vehicle control method provided by this embodiment can present the on-site situation in an intuitive visual form by acquiring the environmental image of the location of the dangerous situation. The image contains rich detailed information, such as road conditions, distribution of surrounding objects, status of traffic participants, etc. Compared with other single data sources, it is easier to quickly understand the overall scene, and provides a comprehensive and visual basis for the subsequent accurate judgment of the type of dangerous situation. After determining the type of dangerous situation, the corresponding target dangerous situation data can be obtained, and the association mechanism between the dangerous situation type and the relevant data is established. Different types of dangerous situations often have different data requirements. For example, for the dangerous situation of road collapse, the relevant terrain data, the stability data of the surrounding building structure, etc. may be the key; while for the dangerous situation of vehicle fire, the temperature data of the vehicle, the status data of the fuel system, etc. are more important. Through this association, the data closely related to the current dangerous situation can be accurately extracted to avoid the interference of irrelevant data. By conducting in-depth analysis of the target dangerous situation data to obtain the dangerous situation level, a systematic logic from data characteristics to quantitative evaluation of the degree of danger is followed. This embodiment can accurately grasp the specific situation of the dangerous situation, and clearly know what type of danger it is and the severity of the danger.

[0118] In S102, processing requirement information corresponding to the risk type is obtained; the processing requirement information is used to describe the information required when dealing with the risk.

[0119] In the embodiment of the present application, in order to obtain comprehensive and rich information, the vehicle terminal can obtain the processing requirement information corresponding to the type of danger in real time through various devices connected to it by wireless communication. The processing requirement information is used to describe the information required when dealing with the danger.

[0120] In some possible embodiments, the vehicle-mounted terminal can obtain in real time the common sense of handling danger corresponding to the danger type and the surrounding POI information of the area where the vehicle is located through an external knowledge base connected to the vehicle by wireless communication.

[0121] In practical applications, an external knowledge base refers to a resource collection that is independent of a specific system or application and stores various types of knowledge and information. It is intended to provide knowledge reference and support for different demand entities and assist them in making decisions, solving problems, studying and researching. Among them, external knowledge bases include but are not limited to: encyclopedia knowledge bases, professional knowledge bases, and industry knowledge bases.

[0122] The surrounding POI information is used to describe points of interest around the area where the vehicle is located, including but not limited to hospitals, fire stations, emergency exits, and open spaces.

[0123] Taking fire as an example, the vehicle terminal can collect common sense on fire causes, fire types (such as Class A solid fire, Class B liquid fire, Class C gas fire, etc.), fire fighting methods (such as what kind of fire extinguisher to use, fire extinguishing procedures), fire escape skills (including how to choose escape routes, how to correctly use protective equipment such as wet towels, escape strategies in different building environments, etc.), identification of common flammable materials and dangerous areas, etc. through channels such as fire manuals, emergency rescue guides, safety knowledge documents issued by the fire department, and academic research literature contained in external knowledge bases.

[0124] At the same time, the vehicle terminal can obtain various points of interest information around the area where the vehicle is located from the external knowledge base, including but not limited to fire stations, hospitals, police stations, gas stations, open spaces (such as parks and squares that can be used as temporary shelters), large shopping malls (with complete fire-fighting facilities and evacuation passages, which can provide certain safety guarantees in emergency situations), location coordinates, names, contact information (if any) and basic attribute information (such as the size of hospitals, equipment of fire stations, etc.), residential areas, etc.

[0125] In some other possible embodiments, the vehicle-mounted terminal may also obtain various historical driving trajectory data of the vehicle around the dangerous situation and the surrounding environment information corresponding to each historical driving trajectory data from the memory of the intelligent agent contained in the vehicle.

[0126] In this embodiment, since the vehicle is equipped with a high-precision positioning system (such as GPS, Beidou, etc.), the vehicle's driving trajectory data, including timestamps, longitude and latitude information, etc., can be continuously recorded during the user's daily driving process. These data can accurately depict the route the vehicle has passed. At the same time, the vehicle's surrounding environment information, such as road signs, building outlines, intersection shapes, nearby landmark buildings, etc., is collected through on-board sensors (such as cameras, lidars, millimeter-wave radars, etc.). Afterwards, the intelligent agent in the vehicle can store the above-collected data in its own memory. Therefore, the on-board terminal can obtain the various historical driving trajectories of the vehicle around the place where the dangerous situation occurred and the surrounding environment information corresponding to each historical driving trajectory from the memory of the intelligent agent contained in it.

[0127] In some other possible embodiments, the vehicle-mounted terminal can also obtain the external weather information and relevant latest news information of the area where the vehicle is located in real time through the server connected to it by wireless communication. Among them, the server includes but is not limited to desktop computers and computers and other devices.

[0128] In S103, the vehicle control method is generated based on the danger level and the processing requirement information.

[0129] In this embodiment, the vehicle terminal can directly input the danger level and processing requirement information into the mode determination model for processing, thereby obtaining the vehicle control mode. The mode determination model is trained based on the pre-built third deep learning model.

[0130] It should be noted that the method determination model can be obtained by training a pre-constructed third deep learning model based on a preset sample set. Among them, each sample data in the preset sample set includes sample information (including sample hazard level and sample demand information) and the sample control method corresponding to the sample information. When training the pre-constructed third deep learning model, the sample information in each sample is used as the input of the third deep learning model, and the sample control method corresponding to the sample information in each sample is used as the output of the third deep learning model. Through training, the third deep learning model can learn the correspondence between all possible sample information and sample control methods, and use the trained third deep learning model as the method determination model.

[0131] In the embodiments of the present application, the vehicle control method includes but is not limited to: controlling the vehicle according to user instructions and controlling the vehicle's driving by calling the vehicle's automatic driving function based on processing demand information.

[0132] In one embodiment of the present application, since the training of the deep learning model usually requires a large number of samples, the amount of calculation is huge, and the training takes a long time, in order to improve the efficiency of determining the vehicle control mode, the vehicle terminal can also Figure 3 The steps S301 to S302 shown implement step S103, which is described in detail as follows:

[0133] In S301, the user's participation result is determined according to the risk level; the participation result is used to describe whether the user participates in controlling the vehicle.

[0134] In this embodiment, when the vehicle-mounted terminal detects that the danger level is the first level, it means that the danger level of the danger in the area where the vehicle is located is not high, and it is a general danger. Therefore, in order to improve the user experience, the vehicle-mounted terminal can determine that the user's participation result is participation.

[0135] When the vehicle-mounted terminal detects that the danger level is the second level, it means that the danger level of the danger in the area where the vehicle is located is high and it is an emergency situation. Therefore, in order to improve the safety of the vehicle and the user and avoid vehicle damage and user injury due to the user's inability to take timely response measures due to sudden dangers, the vehicle-mounted terminal can determine that the user's participation result is no need to participate.

[0136] It should be noted that the second level of danger is higher than the first level of danger.

[0137] In S302, the vehicle control method is generated according to the participation result and the processing requirement information.

[0138] In this embodiment, when the vehicle-mounted terminal detects that the user's participation result is that no participation is required, it indicates that the danger level of the dangerous situation in the area where the vehicle is located is high, and it is an emergency situation. Therefore, in order to improve the safety of the vehicle and the user, and avoid vehicle damage and user injury due to the user's inability to take timely response measures due to sudden emergencies, the vehicle-mounted terminal can determine the vehicle control method based on the processing demand information to call the vehicle's automatic driving function to control the vehicle's driving.

[0139] When the vehicle terminal detects that the user's participation result is participation, it means that the danger level of the danger in the area where the vehicle is located is not high at this time, and it is a general danger. Therefore, in order to improve the user experience, the vehicle terminal can determine the vehicle control mode according to the user's instructions. Among them, the user instruction is generated by the user based on the processing demand information and sent to the vehicle through the user's terminal device.

[0140] In some possible embodiments, after obtaining the danger type and danger level, the vehicle-mounted terminal can directly input the danger type and danger level into a trained control mode determination model for processing, thereby obtaining a vehicle control mode. The control mode determination model is trained based on a pre-built fourth deep learning model.

[0141] It should be noted that the control mode determination model can be obtained by training a pre-constructed fourth deep learning model based on a preset sample set. Among them, each sample data in the preset sample set includes sample information (including sample hazard type and hazard level) and the sample control mode corresponding to the sample information. When training the pre-constructed fourth deep learning model, the sample information in each sample is used as the input of the fourth deep learning model, and the sample control mode corresponding to the sample information in each sample is used as the output of the fourth deep learning model. Through training, the fourth deep learning model can learn the correspondence between all possible sample information and sample control modes, and use the trained fourth deep learning model as the control mode determination model.

[0142] From the above, it can be seen that the method provided in this embodiment determines whether the user participates in the vehicle control according to the danger level, which embodies a hierarchical decision-making logic. For low danger levels, it may be considered that the vehicle's intelligent control system is sufficient to cope with it, and no user intervention is required to avoid unnecessary risks caused by user tension or misoperation; for high danger levels, it may be considered to allow experienced users (such as professional drivers) to participate, and use human judgment and emergency response capabilities to coordinate with the intelligent system to deal with extreme dangerous situations. This hierarchical decision can flexibly allocate resources under different degrees of danger and optimize the response effect. When generating a vehicle control method, the user's participation results and processing demand information are fully considered. The processing demand information clarifies the various conditions and operation goals required to deal with dangerous situations, and the user's participation injects human experience and flexible adaptability into the control process. For example, when the user participates in the control, the on-board terminal can coordinate the vehicle's power, steering, braking and other systems based on the user's operating intentions (such as the operating trends through the steering wheel and pedals) and combined with processing demand information (such as the required avoidance direction, safe parking distance, etc.), so that the vehicle's response is consistent with the intelligent body's rational judgment based on data and algorithms, and can adapt to the user's actual operating habits and on-site judgment, thereby improving the accuracy and effectiveness of control.

[0143] In S104, the vehicle is controlled by invoking the vehicle control method through the intelligent agent.

[0144] In the embodiment of the present application, after obtaining the vehicle control method, the vehicle-mounted terminal can call the vehicle control method through the intelligent agent to control the vehicle.

[0145] In some possible embodiments, since the agent has the function of automatically calling tools, and the automatic calling tool function is the ability to select and use various appropriate control tools or systems inside the vehicle to achieve specific vehicle operations according to pre-set strategies or real-time generated decisions, it is equivalent to the "executive hand" of the agent, converting decisions into actual vehicle actions, such as braking, steering, acceleration, etc., so as to effectively control the vehicle.

[0146] Therefore, in this embodiment, the agent can formulate a specific control strategy based on the perception of the danger (including the type and level of the danger) and the generated vehicle control method. The control strategy specifies in detail which tools should be called in different situations, in what order, and how to set the control parameters of the tools. After that, the agent can control the vehicle according to the control strategy.

[0147] For example, for a high-level front collision hazard, the control strategy may be to perform emergency braking first (calling the ABS system and setting the maximum braking pressure) and at the same time perform slight steering avoidance (calling the electric power steering system and setting the steering torque according to the target avoidance angle).

[0148] In one embodiment of the present application, when the vehicle control mode is to control the vehicle according to user instructions, it means that the danger level of the danger situation in the area where the vehicle is located is not high, and it is a general danger situation. Therefore, in order to achieve precise control of the vehicle and improve user experience, the vehicle terminal can specifically control the vehicle according to the following steps, which are detailed as follows:

[0149] When the vehicle control mode is to control the vehicle according to a user instruction, a prompt message is generated to prompt the user that a first level of danger occurs in the area;

[0150] Acquire a dangerous situation image corresponding to the dangerous situation;

[0151] The agent calls a notification module in the vehicle to send the prompt information, the danger image and the processing requirement information to the user's terminal device;

[0152] receiving a user instruction sent by the terminal device; the user instruction is generated by the user based on the prompt information, the dangerous situation image and the vehicle control information generated by the processing requirement information;

[0153] The vehicle is controlled according to the user command.

[0154] In this embodiment, when the vehicle terminal detects that the vehicle control mode is to control the vehicle according to user instructions, it means that the vehicle needs to be controlled by the user at this time. Therefore, in order to facilitate the user to clearly understand the danger level of the area where the vehicle is located at this time, the vehicle terminal can generate a prompt information for prompting the user that a first level of danger has occurred in the area.

[0155] At the same time, in order to facilitate users to understand the handling methods and situations related to dangerous situations, the vehicle-mounted terminal can obtain dangerous situation images corresponding to the dangerous situation, as well as processing requirement information corresponding to the dangerous situation type.

[0156] In some possible embodiments, the vehicle-mounted terminal may acquire the danger image corresponding to the danger in real time through a camera wirelessly connected thereto.

[0157] In this embodiment, since the user may not be around the vehicle, that is, the vehicle is in an unmanned scene, in order to let the user know the relevant information of the dangerous situation in time, the vehicle-mounted terminal can call the notification module in the vehicle through the automatic calling tool function of the intelligent body, so as to send the above-mentioned prompt information, dangerous situation image and processing requirement information to the user's terminal device through the notification module.

[0158] Afterwards, the user can determine the control instructions for the vehicle, that is, user instructions, through the prompt information, danger images and processing requirement information displayed on his own terminal device.

[0159] Based on this, the above terminal device can send the user instruction to the vehicle-mounted terminal.

[0160] In this embodiment, after receiving the user instruction sent by the terminal device, the vehicle-mounted terminal can directly control the vehicle according to the user instruction.

[0161] In some possible embodiments, after receiving the user instruction sent by the terminal device, the vehicle-mounted terminal can also control the vehicle according to the user instruction through the active service function of the intelligent body.

[0162] It can be seen from the above that the vehicle control method provided in this embodiment, when detecting the first level of danger, not only generates a prompt message to inform the user that a danger has occurred in the area, but also obtains the corresponding danger image and processing demand information and sends it to the user. This approach ensures that the user can receive multi-dimensional information, from text descriptions of danger prompts, images that intuitively present the on-site conditions, to the specific requirements required to deal with the danger, to fully understand the current dangerous situation, and provide sufficient and comprehensive basis for users to make reasonable vehicle control decisions. At the same time, the use of an intelligent agent to call the notification module in the vehicle to send information demonstrates the automatic calling and coordination capabilities of the intelligent agent for the internal functional modules of the vehicle. Without manual operation by the user, the intelligent agent can autonomously start the notification process to ensure that the information is conveyed to the user in a timely and accurate manner, which improves the efficiency of information transmission and also reflects the automation and intelligence of the intelligent driving system in dealing with dangers.

[0163] In another embodiment of the present application, when the vehicle control mode is to call the vehicle's automatic driving function to control the vehicle's driving, it means that the danger level of the dangerous situation in the area where the vehicle is located is high, which is an emergency situation. Therefore, in order to improve the safety of the vehicle and the safety of the user, avoid vehicle damage and user injury caused by the user's inability to take timely response measures due to the sudden danger, and realize accurate control of the vehicle, the vehicle terminal can specifically realize the control of the vehicle according to the following steps, which are detailed as follows:

[0164] When the vehicle control mode is to call the automatic driving function of the vehicle based on the processing requirement information to control the driving of the vehicle, obtaining processing requirement information corresponding to the dangerous situation type; the processing requirement information includes multiple points of interest, road condition information and environmental information in the area;

[0165] Determining a driving destination from a plurality of points of interest according to the road condition information and the environment information;

[0166] Performing path planning according to the driving destination and the current position of the vehicle to obtain the driving path of the vehicle;

[0167] The automatic driving function of the vehicle is called by the intelligent agent to control the vehicle to travel along the driving path so as to drive the vehicle away from the dangerous situation.

[0168] In this embodiment, when the vehicle terminal detects that the vehicle control mode is to call the automatic driving function to control the vehicle based on the processing demand information, it indicates that the danger level of the danger in the area where the vehicle is located is high and it is an emergency. Therefore, in order to improve the safety of the vehicle and the user, and avoid the damage to the vehicle and the user caused by the user's inability to take timely response measures due to the sudden danger, and at the same time, in order to realize the automatic departure from the danger location when the vehicle is in an unmanned scene, the vehicle terminal can obtain the processing demand information corresponding to the danger type. Among them, the processing demand information includes multiple points of interest, road condition information and environmental information in the area.

[0169] It should be noted that the above-mentioned points of interest include but are not limited to hospitals, fire stations, emergency exits and open spaces.

[0170] The road condition information is used to describe the road conditions in the area where the vehicle is located, including but not limited to: traffic flow, road congestion level, and road surface conditions.

[0171] Environmental information is used to describe the weather conditions in the area where the vehicle is located.

[0172] In this embodiment, the vehicle terminal can input road condition information, environmental information and multiple points of interest into the destination determination model for processing, thereby determining the final driving destination. The destination determination model is trained based on the pre-built fifth deep learning model.

[0173] It should be noted that the destination determination model can be obtained by training a pre-constructed fifth deep learning model based on a preset sample set. Each sample data in the preset sample set includes sample information (including road condition information, environmental information, and multiple points of interest) and a sample destination corresponding to the sample information. When training the pre-constructed fifth deep learning model, the sample information in each sample is used as the input of the fifth deep learning model, and the sample destination corresponding to the sample information in each sample is used as the output of the fifth deep learning model. Through training, the fifth deep learning model can learn the correspondence between all possible sample information and sample destinations, and the trained fifth deep learning model is used as the destination determination model.

[0174] In this embodiment, after determining the driving destination, the vehicle-mounted terminal can plan a path for the vehicle in combination with the current position of the vehicle and the driving destination, thereby obtaining the driving path of the vehicle.

[0175] In some possible embodiments, the vehicle-mounted terminal may input the current location and the driving destination into a path planning model for processing, thereby determining the driving path. The path planning model is trained based on the pre-built sixth deep learning model.

[0176] It should be noted that the path planning model can be obtained by training a pre-constructed sixth deep learning model based on a preset sample set. Among them, each sample data in the preset sample set includes sample information (including the driving destination and vehicle location) and a sample path corresponding to the sample information. When training the pre-constructed sixth deep learning model, the sample information in each sample is used as the input of the sixth deep learning model, and the sample path corresponding to the sample information in each sample is used as the output of the sixth deep learning model. Through training, the sixth deep learning model can learn the correspondence between all possible sample information and sample paths, and use the trained sixth deep learning model as the path planning model.

[0177] In this embodiment, after the vehicle-mounted terminal obtains the driving path, the intelligent agent in the vehicle can automatically call the vehicle's automatic driving function through its own automatic calling tool function, and control the vehicle to travel along the driving path to drive the vehicle away from the dangerous situation.

[0178] Based on this, when facing the situation where the automatic driving function needs to be called to deal with the danger, this embodiment fully considers the processing demand information corresponding to the danger type, covering multiple points of interest in the area, road condition information, environmental information and other aspects. This comprehensive integration means not looking at a certain factor in isolation, but comprehensively considering various factors that may affect vehicle driving and risk avoidance, and formulating response strategies from multiple dimensions, so that subsequent decisions are more in line with the actual danger scene. Determining the driving destination from multiple points of interest based on road condition information and environmental information reflects the full consideration of the actual situation. Instead of randomly selecting points of interest, the system analyzes factors such as whether the current road is unobstructed and whether the surrounding environment is safe, and selects a place that can meet the needs of leaving the dangerous situation and is relatively safe and easy to reach as the driving destination, ensuring that the vehicle's subsequent driving direction is towards a more favorable environment, avoiding driving into dangerous areas or getting into trouble.

[0179] As can be seen from the above, a vehicle control method provided by the embodiment of the present application, when the environment perception function of the intelligent body of the vehicle detects that a dangerous situation occurs in the area where the vehicle is located, determines the type of dangerous situation and the level of dangerous situation; obtains the processing requirement information corresponding to the dangerous situation type; the processing requirement information is used to describe the information required when dealing with the dangerous situation; based on the dangerous situation level and the processing requirement information, generates a vehicle control method; and controls the vehicle according to the vehicle control method. In this application, the intelligent body has an environmental perception function, which can monitor various conditions in the area where the vehicle is located in real time and detect the occurrence of dangerous situations in a timely manner. And it is not only limited to finding abnormalities, but also can further determine the type of dangerous situation (such as collision risk, road water accumulation, fire hazard, etc.) and the level of dangerous situation (for example, divided into low, medium and high levels according to the degree of danger), which reflects the deep analysis and accurate judgment ability of environmental information, and provides an accurate basis for subsequent targeted response measures. Afterwards, according to the determined dangerous situation type, the corresponding processing requirement information is obtained, which emphasizes the pertinence and relevance of information acquisition, so that the subsequent vehicle control is more in line with the actual dangerous situation needs. Afterwards, when generating the vehicle control method, it is not based on a single factor, but takes into account two important factors: the level of danger and the processing demand information. The level of danger reflects the urgency of the danger, and the processing demand information clarifies the specific response goals and required conditions to be achieved. By combining the two, a more scientific, reasonable and practical vehicle control strategy can be formulated, avoiding the risks brought by one-sided decisions. Finally, the intelligent agent effectively integrates the execution links of vehicle control. Once the vehicle control method is generated, the intelligent agent can call the vehicle control method to actually control the vehicle without manual intervention, realizing an automated process from decision-making to execution, improving the timeliness and accuracy of responding to dangers, reducing the delays and errors that may be caused by human operations, and improving the accuracy of vehicle control.

[0180] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0181] Corresponding to a vehicle control method described in the above embodiment, Figure 4 The structure diagram of a vehicle control device provided by an embodiment of the present application is shown. For the convenience of explanation, only the part related to the embodiment of the present application is shown. Figure 4 The vehicle control device 400 includes: a first determination unit 41, a first acquisition unit 42, a first generation unit 43 and a first control unit 44. Among them:

[0182] The first determining unit 41 is used to determine the type and level of danger when the intelligent body of the vehicle senses that a danger occurs in the area where the vehicle is located.

[0183] The first acquisition unit 42 is used to acquire processing requirement information corresponding to the dangerous situation type; the processing requirement information is used to describe the information required when dealing with the dangerous situation.

[0184] The first generating unit 43 is used to generate the vehicle control mode based on the risk level and the processing requirement information.

[0185] The first control unit 44 is used to control the vehicle by invoking the vehicle control method through the intelligent agent.

[0186] In one embodiment of the present application, the first determining unit 41 specifically includes: a second acquiring unit, a first analyzing unit, a third acquiring unit and a second analyzing unit. Among them:

[0187] The second acquisition unit is used to acquire an environmental image of the dangerous situation location.

[0188] The first analysis unit is used to analyze the environmental image to obtain the dangerous situation type.

[0189] The third acquisition unit is used to acquire target dangerous situation data corresponding to the dangerous situation type.

[0190] The second analysis unit is used to analyze the target hazard data to obtain the hazard level.

[0191] In one embodiment of the present application, the first generating unit 43 specifically includes: a second determining unit and a second generating unit. Among them:

[0192] The second determination unit is used to determine the user's participation result according to the risk level; the participation result is used to describe whether the user participates in controlling the vehicle.

[0193] The second generating unit is used to generate the vehicle control method according to the participation result and the processing requirement information.

[0194] In one embodiment of the present application, the second generating unit specifically includes: a third determining unit.

[0195] in:

[0196] The third determination unit is used to determine, when the participation result is that no participation is required, a method of controlling the driving of the vehicle by calling the automatic driving function of the vehicle based on the processing requirement information as the vehicle control method.

[0197] In one embodiment of the present application, the first control unit 43 specifically includes: a third generating unit, a fourth acquiring unit, a sending unit, a receiving unit and a second control unit. Among them:

[0198] The third generating unit is used for generating prompt information for prompting the user that a first level of danger occurs in the area when the vehicle control mode is to control the vehicle according to a user instruction.

[0199] The fourth acquisition unit is used to acquire a dangerous situation image corresponding to the dangerous situation.

[0200] The sending unit is used to call the notification module in the vehicle through the intelligent agent to send the prompt information, the dangerous situation image and the processing requirement information to the user's terminal device.

[0201] The receiving unit is used to receive a user instruction sent by the terminal device; the user instruction is generated by the user based on the prompt information, the dangerous situation image and the vehicle control information generated by the processing requirement information.

[0202] The second control unit is used to control the vehicle according to the user instruction.

[0203] In one embodiment of the present application, the first control unit 43 specifically includes: a fifth acquisition unit, a fourth determination unit, a planning unit and a third control unit. Among them:

[0204] The fifth acquisition unit is used to obtain processing requirement information corresponding to the dangerous situation type when the vehicle control method is to call the automatic driving function of the vehicle based on the processing requirement information to control the driving of the vehicle; the processing requirement information includes multiple points of interest, road conditions and environmental information in the area.

[0205] The fourth determining unit is used to determine a driving destination from the plurality of points of interest according to the road condition information and the environment information.

[0206] The planning unit is used to perform path planning according to the driving destination and the current position of the vehicle to obtain the driving path of the vehicle.

[0207] The third control unit is used to call the automatic driving function of the vehicle through the intelligent agent, and control the vehicle to travel along the driving path so that the vehicle drives away from the dangerous situation.

[0208] In one embodiment of the present application, the second analysis unit specifically includes: a processing unit.

[0209] The processing unit is used to input the target hazard data into the trained level determination model for processing to obtain the hazard level.

[0210] In one embodiment of the present application, the second analysis unit specifically includes: a fifth determination unit and a comparison unit.

[0211] The fifth determining unit is used to determine the danger range in which the target danger data is located.

[0212] The comparison unit is used to compare the danger range with each preset range one by one to obtain the danger level; each preset range corresponds to a different danger level.

[0213] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0214] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0215] Figure 5 This is a schematic diagram of the structure of a vehicle-mounted terminal provided in one embodiment of the present application. Figure 5 As shown, the vehicle terminal 5 of this embodiment includes: at least one processor 50 ( Figure 5 Only one is shown in the figure) a processor, a memory 51, and a computer program 52 stored in the memory 51 and executable on the at least one processor 50, and when the processor 50 executes the computer program 52, the steps in any of the above-mentioned vehicle control method embodiments are implemented.

[0216] The vehicle-mounted terminal may include, but is not limited to, a processor 50 and a memory 51. Those skilled in the art will appreciate that Figure 5 It is only an example of the vehicle-mounted terminal 5 and does not constitute a limitation on the vehicle-mounted terminal 5. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0217] The processor 50 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0218] In some embodiments, the memory 51 may be an internal storage unit of the vehicle-mounted terminal 5, such as the memory of the vehicle-mounted terminal 5. In other embodiments, the memory 51 may also be an external storage device of the vehicle-mounted terminal 5, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the vehicle-mounted terminal 5. Further, the memory 51 may also include both the internal storage unit of the vehicle-mounted terminal 5 and an external storage device. The memory 51 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 51 may also be used to temporarily store data that has been output or is to be output.

[0219] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0220] An embodiment of the present application provides a computer program product. When the computer program product runs on a vehicle-mounted terminal, the vehicle-mounted terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0221] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying the computer program code to the vehicle-mounted terminal, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0222] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0223] The embodiments described 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 vehicle control method, characterized in that: include: When the intelligent body of the vehicle senses that a dangerous situation occurs in the area where the vehicle is located, determine the type and level of the dangerous situation; Obtaining processing requirement information corresponding to the risk type; The processing requirement information is used to describe the information required when dealing with the dangerous situation; generating the vehicle control mode based on the danger level and the processing requirement information; The vehicle is controlled by invoking the vehicle control method through the intelligent agent.

2. The vehicle control method according to claim 1, characterized in that: Determining the risk type and risk level includes: Acquire an environmental image of the location of the dangerous situation; Analyze the environmental image to obtain the dangerous situation type; Acquire target dangerous situation data corresponding to the dangerous situation type; The target hazard data is analyzed to obtain the hazard level.

3. The vehicle control method according to claim 1, characterized in that: The generating the vehicle control mode based on the danger level and the processing requirement information includes: Determining a user's participation result according to the risk level; the participation result is used to describe whether the user participates in controlling the vehicle; The vehicle control method is generated according to the participation result and the processing requirement information.

4. The vehicle control method according to claim 3, characterized in that: Generating the vehicle control method according to the participation result and the processing requirement information includes: When the participation result is that no participation is required, the method of calling the automatic driving function of the vehicle to control the driving of the vehicle based on the processing requirement information is determined as the vehicle control method.

5. The vehicle control method according to any one of claims 1 to 4, characterized in that: The controlling the vehicle by invoking the vehicle control method through the intelligent agent includes: When the vehicle control mode is to control the vehicle according to a user instruction, a prompt message is generated to prompt the user that a first level of danger occurs in the area; Acquire a dangerous situation image corresponding to the dangerous situation; The agent calls a notification module in the vehicle to send the prompt information, the danger image and the processing requirement information to the user's terminal device; receiving a user instruction sent by the terminal device; the user instruction is generated by the user based on the prompt information, the dangerous situation image and the vehicle control information generated by the processing requirement information; The vehicle is controlled according to the user command.

6. The vehicle control method according to any one of claims 1 to 4, characterized in that: The controlling the vehicle by invoking the vehicle control method through the intelligent agent includes: When the vehicle control mode is to call the automatic driving function of the vehicle based on the processing requirement information to control the driving of the vehicle, obtaining processing requirement information corresponding to the dangerous situation type; the processing requirement information includes multiple points of interest, road condition information and environmental information in the area; Determining a driving destination from the plurality of points of interest according to the road condition information and the environment information; Performing path planning according to the driving destination and the current position of the vehicle to obtain the driving path of the vehicle; The automatic driving function of the vehicle is called by the intelligent agent to control the vehicle to travel along the driving path so as to drive the vehicle away from the dangerous situation.

7. The vehicle control method according to claim 2, characterized in that: The step of analyzing the target hazard data to obtain the hazard level includes: Inputting the target hazard data into a trained level determination model for processing to obtain the hazard level; or, Determine the danger range of the target danger data; The danger range is compared with each preset range one by one to obtain the danger level; each preset range corresponds to a different danger level.

8. A vehicle control device, characterized in that: include: A first determination unit is used to determine the type and level of danger when a danger occurs in the area where the vehicle is located through the intelligent body of the vehicle; A first acquisition unit, used to acquire processing requirement information corresponding to the risk type; The processing requirement information is used to describe the information required when dealing with the dangerous situation; A first generating unit, configured to generate the vehicle control mode based on the danger level and the processing requirement information; The first control unit is used to control the vehicle by calling the vehicle control method through the intelligent agent.

9. A vehicle-mounted terminal, 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 vehicle control method according to any one of claims 1 to 7 is implemented.

10. A vehicle, characterized in that: Comprising the vehicle-mounted terminal as claimed in claim 9.

Images