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: obtaining historical interaction information between a user in the vehicle and an intelligent agent of the vehicle, current behavior information of the user, and obtaining environment information of the vehicle; analyzing the historical interaction information and the current behavior information, and determining target demand information of the user; and controlling the vehicle based on the target demand information and the environment information through an active service function of the intelligent agent. Compared with the prior art, the behavior habit of the user in the vehicle can be determined by analyzing the historical interaction information, then the target demand of the user at the moment is accurately determined in combination with the current behavior of the user, and finally accurate control over the vehicle is achieved in combination with the target demand and the environment, so that needed services are actively provided for the user, and the user experience is improved. And the practicability 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] In practical applications, in order to improve the user's driving experience in the vehicle, the vehicle has become increasingly intelligent so as to provide relevant services to the user in a timely manner. However, although the existing vehicle control method can provide relevant services to the user by controlling the voice assistant and the navigation system, the existing technology is usually passive when providing relevant services, that is, the user needs to actively issue instructions to provide relevant services. It can be seen that the existing technology has the problem of low practicality of the vehicle. Summary of the invention

[0003] The embodiments of the present application provide a vehicle control method, device, vehicle-mounted terminal and vehicle to solve the problem of low practicality of vehicles in the prior art.

[0004] In a first aspect, an embodiment of the present application provides a vehicle control method, including:

[0005] Acquire historical interaction information between a user in a vehicle and an intelligent agent of the vehicle, current behavior information of the user, and environmental information of the vehicle;

[0006] Analyze the historical interaction information and the current behavior information to determine the target demand information of the user;

[0007] Through the active service function of the intelligent body, the vehicle is controlled based on the target demand information and the environmental information.

[0008] Optionally, analyzing the historical interaction information and the current behavior information to determine the target demand information of the user includes:

[0009] Inputting the historical interaction information into a behavior analysis model for processing to obtain historical behavior information of the user;

[0010] The current behavior information is subjected to demand analysis based on the historical behavior information to obtain the target demand information.

[0011] Optionally, the current behavior information includes voice information and a plurality of different action information; and performing demand analysis on the current behavior information based on the historical behavior information to obtain the target demand information includes:

[0012] Determining a device to be controlled of the vehicle according to the voice information;

[0013] If the control modes corresponding to the plurality of action information are all different, obtaining the control preference information of the user for the device to be controlled from the historical behavior information;

[0014] determining the control priority of each of the plurality of action information according to the control preference information;

[0015] The target demand information is determined according to the control priorities of the plurality of action information.

[0016] Optionally, the method further includes:

[0017] If the control preference information is blank, outputting voice prompt information; the voice prompt information is used to prompt the user to select gesture control and eye movement control;

[0018] The target demand information is generated according to the feedback information input by the user.

[0019] Optionally, the environmental information includes external environmental information and internal environmental information; the controlling the vehicle based on the target demand information and the environmental information through the active service function of the intelligent body includes:

[0020] Detecting, by means of the active service function of the intelligent agent, a first conflict result between the target demand information and the vehicle exterior environment information, and a second conflict result between the target demand information and the vehicle interior environment information;

[0021] generating a vehicle control instruction based on the first conflict result and the second conflict result;

[0022] The vehicle is controlled based on the vehicle control command.

[0023] Optionally, generating a vehicle control instruction based on the first conflict result and the second conflict result includes:

[0024] If the first conflict result is no conflict and the second conflict result is no conflict, a first control instruction is generated according to the target demand information, a second control instruction is generated according to the external vehicle environment information, and a third control instruction is generated according to the internal vehicle environment information.

[0025] Optionally, generating a vehicle control instruction based on the first conflict result and the second conflict result includes:

[0026] If the first conflict result is a conflict, and the second conflict result is a non-conflict, generating a fourth control instruction according to the in-vehicle environment information;

[0027] Performing a conflict analysis on the target demand information and the vehicle external environment information to determine at least one backup control mode;

[0028] Determining a target control mode from the at least one backup control mode according to the selection information input by the user;

[0029] A fifth control instruction is generated based on the target control mode.

[0030] In a second aspect, an embodiment of the present application provides a vehicle control device, including:

[0031] A first acquisition unit, configured to acquire historical interaction information between a user in a vehicle and an intelligent agent of the vehicle, current behavior information of the user, and environmental information of the vehicle;

[0032] A first analyzing unit, configured to analyze the historical interaction information and the current behavior information to determine target demand information of the user;

[0033] A first control unit is used to control the vehicle based on the target demand information and the environmental information through the active service function of the intelligent body.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0039] A vehicle control method provided by an embodiment of the present application obtains historical interaction information between a user in a vehicle and an intelligent agent of the vehicle, the user's current behavior information, and the vehicle's environmental information; analyzes the historical interaction information and current behavior information to determine the user's target demand information; and controls the vehicle based on the target demand information and environmental information through the active service function of the intelligent agent. The present application obtains a variety of information sources, including historical interaction information, current behavior information, and environmental information, so that the vehicle-mounted terminal can have a more comprehensive and in-depth understanding of user needs and vehicle status. At the same time, by analyzing the historical interaction information and current behavior information to determine the user's target demand information, a highly personalized service can be achieved, that is, the corresponding service and control can be accurately provided according to the user's unique habits and preferences. In addition, based on the target demand information and environmental information, the intelligent agent can actively control the vehicle and has active adaptability, that is, the intelligent agent does not passively wait for user instructions, but makes decisions and actions in advance based on real-time information changes. In summary, the present application avoids the user's frequent manual operation of various functions of the vehicle. The intelligent agent can automatically set and adjust according to the user's habits and current situation, achieve accurate control of the vehicle, improve the user experience and the practicality of the vehicle; at the same time, it can also accurately grasp the user's personalized needs, and the services provided by the intelligent agent are more in line with the user's expectations. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] 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.

[0041] Figure 1 is a flow chart of an implementation of a vehicle control method provided by an embodiment of the present application;

[0042] Figure 2 is a flow chart of an implementation of a vehicle control method provided by another embodiment of the present application;

[0043] Figure 3 is a flow chart of an implementation of a vehicle control method provided in yet another embodiment of the present application;

[0044] Figure 4 is a flow chart of an implementation of a vehicle control method provided by another embodiment of the present application;

[0045] Figure 5 is a flow chart of an implementation of a vehicle control method provided by another embodiment of the present application;

[0046] Figure 6is a flow chart of an implementation of a vehicle control method provided by another embodiment of the present application;

[0047] Figure 7 is a structural schematic diagram of a vehicle control device provided by an embodiment of the present application;

[0048] Figure 8 It is a structural diagram of a vehicle-mounted terminal provided in one embodiment of the present application. DETAILED DESCRIPTION

[0049] 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.

[0050] 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.

[0051] 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.

[0052] 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.

[0053] 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.

[0054] 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.

[0055] In practical applications, in order to improve the user's driving experience in the vehicle, the vehicle has become more and more intelligent so as to provide relevant services to the user in a timely manner. However, smart cars still have some shortcomings in providing users with a convenient driving experience. Although current smart cars can provide users with certain assistance through functions such as voice assistants and navigation systems, most of these functions are passive and require users to actively issue commands to achieve them. It can be seen that the existing technology not only has low practicality of the vehicle, but also increases the user's operating burden. At the same time, in some cases, users may not be able to issue commands in time, resulting in a poor experience.

[0056] Based on this, the present application proposes a vehicle control method that can control the vehicle accordingly based on the user's behavior and the environment inside and outside the vehicle, so as to actively provide targeted services to the user, thereby improving the practicality of the vehicle, reducing the user's operating burden, and improving the user's riding experience.

[0057] 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 vehicle control method is executed by a vehicle terminal. The vehicle terminal may be a telematics box (T-BOX).

[0058] In the embodiment of the present application, an intelligent agent is provided in the vehicle.

[0059] It should be noted that the agent is an intelligent system integrated into the car, which can perceive 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.

[0060] 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.

[0061] In the embodiments of the present application, the intelligent agent in the vehicle generally has driving assistance functions, environmental perception and safety functions, human-computer interaction functions, active service functions, and analysis functions.

[0062] Among them, the driving assistance functions specifically include:

[0063] Adaptive Cruise Control (ACC): monitors the distance and speed of the vehicle in front through radar or camera, automatically adjusts the vehicle's speed, and maintains a safe following distance. For example, when driving long distances, the driver sets the cruising speed and following distance, and the intelligent agent in the vehicle can automatically accelerate and decelerate according to the driving status of the vehicle in front, reducing the driver's driving burden.

[0064] Lane Keeping Assist (LKA): Utilizes a camera to identify lane lines and automatically fine-tune the steering wheel to keep the vehicle in the lane when the vehicle tends to deviate from the lane. This is particularly useful on highways to prevent lane departure accidents caused by driver fatigue or distraction.

[0065] Automatic Parking Assist (APA): The ultrasonic sensor and camera sense the location and size of the parking space and automatically control the vehicle to complete the parking action. Whether it is parallel parking or perpendicular parking, the intelligent body in the vehicle can help the driver park easily, which is very convenient for users who are not proficient in parking skills.

[0066] Among them, environmental perception and safety functions specifically include:

[0067] Obstacle detection and warning: Use sensors such as radar, lidar and cameras to detect obstacles around the vehicle in real time, such as other vehicles, pedestrians, roadblocks, etc. When a potential collision risk is detected, an alert is issued to the driver in a timely manner, and in some cases the brakes can be automatically applied to avoid or reduce the severity of the collision.

[0068] Traffic sign recognition and road condition reminder: Identify traffic signs on the road, such as speed limit signs, no overtaking signs, etc., and convey the information to the driver. At the same time, it can also analyze road conditions, such as road surface flatness, water accumulation, etc., to remind the driver to drive safely.

[0069] Among them, the human-computer interaction functions specifically include:

[0070] Voice interaction: Drivers and passengers can control some vehicle functions through voice commands, such as adjusting the air conditioning temperature, playing music, and querying navigation information. The intelligent agent in the vehicle understands the user's instructions through voice recognition technology and performs corresponding operations. This method is convenient and fast, and allows the driver to focus more on the road.

[0071] Touch screen and button interaction: In addition to voice interaction, the car is also equipped with a touch screen or physical buttons, through which users can intuitively operate various functions of the vehicle, such as setting vehicle parameters, selecting multimedia content, etc.

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

[0073] Environmental perception and automatic adjustment: Automatic air conditioning adjustment: The intelligent 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 intelligent 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 intelligent agent can automatically switch to air circulation mode and start the air purification function to improve the air quality in the car.

[0074] Automatic adjustment of seats and rearview mirrors: Some cars are equipped with memory seats and rearview mirrors. The agent can actively adjust the seat position, rearview mirror angle, etc. according to the identity of different drivers or driving scenarios. For example, when the driver gets in the car and is recognized by the agent, the seat and rearview mirror will automatically adjust to the comfortable position used by the driver last time; when reversing, the agent can automatically adjust the rearview mirror to the reversing perspective, making it easier for the driver to observe the situation behind, and then automatically return to the normal driving perspective after reversing is completed.

[0075] 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.

[0076] Trip reminders and service recommendations: Based on the driver's schedule and habits, 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.

[0077] The analysis functions include:

[0078] Analysis of user behavior: Driving habit analysis: The agent can analyze the driver's driving habits through data collected by the vehicle's sensors (such as accelerator pedal sensor, brake pedal sensor, steering wheel angle sensor, etc.). For example, it can count the frequency of the driver's sudden acceleration and sudden braking, and determine whether the driver has an aggressive or stable driving style. It can also analyze the driver's driving habits under different road conditions (such as urban roads, highways, and mountain roads). For example, on the highway, the agent can observe whether the driver often maintains a stable speed range or frequently changes lanes to overtake. These analysis results can be used to optimize the vehicle's power system control and safety reminder strategies.

[0079] Preference analysis: The agent can analyze the user’s preferences from the user’s interaction history with the vehicle. For example, by recording the radio stations, music genres, or playlists that the user frequently listens to, the agent can understand the user’s music preferences.

[0080] Analysis of the environment: Road condition analysis: The agent uses data from onboard sensors (such as cameras, radars, lidars, etc.) to analyze road conditions. It can identify road types (such as highways, urban main roads, rural roads), road conditions (such as whether it is flat, whether there is water or snow), and traffic signs (such as speed limit signs, lane signs). It can also analyze traffic flow and traffic congestion. For example, through vehicle-to-vehicle communication (V2V) or communication with traffic infrastructure (V2I), the agent can obtain the speed and location information of surrounding vehicles, thereby determining whether the current road section is congested and planning a suitable driving route in advance.

[0081] Weather condition analysis: Although the vehicle itself may not have dedicated weather sensors, the agent can receive external weather data (such as connecting to weather services through the Internet of Vehicles) and combine it with feedback from vehicle sensors to analyze the impact of weather on the vehicle and driving. For example, in rainy weather, the agent can analyze the size of the rain based on the raindrops detected by the raindrop sensor or camera, and automatically adjust the speed and frequency of the wipers. In cold weather, the agent can consider the possibility of icy road conditions, remind the driver to pay attention to driving safety, and can provide corresponding driving suggestions based on the vehicle's configuration (such as whether there is an anti-skid system).

[0082] 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:

[0083] In S101, historical interaction information between a user in a vehicle and an intelligent agent of the vehicle, current behavior information of the user, and environmental information of the vehicle are obtained.

[0084] In the embodiment of the present application, the vehicle terminal can obtain the historical interaction information between the user in the vehicle and the intelligent agent through the intelligent agent in the vehicle. The historical interaction information includes but is not limited to the conversation record between the user and the intelligent agent. The conversation record includes but is not limited to the chat information between the user and the intelligent agent and the historical operation record of the user on the vehicle through the intelligent agent.

[0085] In one implementation of the present application, the vehicle-mounted terminal can obtain the vehicle's interior environment information in real time through various vehicle-mounted sensors connected to it by wireless communication.

[0086] The in-car environment information includes, but is not limited to, in-car temperature, humidity, user's sitting state, etc. The user's sitting state is used to describe the state of the user in the seat, including but not limited to sleeping, awake, and tired, etc.

[0087] Based on this, the above-mentioned various vehicle-mounted sensors include but are not limited to: vehicle-mounted temperature sensors, vehicle-mounted humidity sensors, and vehicle-mounted image sensors, etc. Among them, the vehicle-mounted image sensors include but are not limited to cameras and video cameras, etc.

[0088] In another implementation of the present application, the vehicle-mounted terminal can obtain the vehicle's external environment information in real time through various external sensors connected to the vehicle through wireless communication.

[0089] The external environment information includes, but is not limited to, weather conditions and road conditions outside the vehicle.

[0090] Based on this, the above-mentioned various off-vehicle sensors include but are not limited to: meteorological sensors and road condition sensors.

[0091] In the embodiment of the present application, the user's current behavior information includes but is not limited to: voice information and multiple different action information. Among them, the multiple different action information may include gesture information and eye movement information. The gesture information is used to describe the user's gesture action, and the eye movement information is used to describe the user's eye movement.

[0092] Therefore, in another implementation of the present application, the vehicle-mounted terminal can obtain the user's gesture information and eye movement information through the vehicle-mounted image sensor connected to the vehicle-mounted image sensor wirelessly, and the vehicle-mounted terminal can obtain the user's language information through the vehicle-mounted language module connected to the vehicle-mounted image sensor wirelessly. The vehicle-mounted language module can be a microphone.

[0093] In S102, the historical interaction information and the current behavior information are analyzed to determine the target demand information of the user.

[0094] In the embodiment of the present application, after obtaining the above historical interaction information and the user's current behavior information, the vehicle terminal can input the historical interaction information and the user's current behavior information into the trained demand determination model for processing to obtain the user's target demand information. The target demand information is used to describe the user's needs at this time, such as opening a window, increasing the volume, or turning on a light.

[0095] It should be noted that the demand determination model is obtained by training a pre-built first neural network model.

[0096] In an embodiment of the present application, the demand determination model can be obtained by training a pre-constructed first neural network model based on a preset sample set. Each sample data in the preset sample set includes sample information (the sample information includes the interaction information between the user and the agent and the user's behavior information) and sample demand information corresponding to the sample information. When training the pre-constructed first neural network model, the sample information in each sample data is used as the input of the first neural network model, and the sample demand information corresponding to the sample information in each sample data is used as the output of the first neural network model. Through training, the first neural network model can learn the correspondence between all possible sample information and sample demand information, and use the trained first neural network model as the demand determination model.

[0097] In some possible embodiments, since the intelligent agent in the vehicle also has an analysis function, the vehicle-mounted terminal can call the analysis function of the intelligent agent to enable the intelligent agent to analyze historical interaction information and current behavior information to determine the user's target demand information.

[0098] In one embodiment of the present application, in order to determine the user's behavior habits and preferences so that the subsequent determination of the user's needs is more compatible with the user, so as to further improve the accuracy of determining the user's target demand information, the vehicle terminal can specifically perform the following steps: Figure 2 Steps S201 to S202 shown determine the user's target demand information, as detailed below:

[0099] In S201, the historical interaction information is input into a behavior analysis model for processing to obtain the historical behavior information of the user.

[0100] In this embodiment, the vehicle terminal can input the historical interaction information into the behavior analysis module for processing to analyze the user's historical behavior, thereby obtaining the user's historical behavior information. The historical behavior information includes but is not limited to the user's historical behavior, behavior results, and behavior preferences.

[0101] The user's behavior preference includes but is not limited to the control preference information of each device in the vehicle, wherein the control preference information is used to describe the control method of each device in the vehicle, including but not limited to gesture control and eye movement control.

[0102] The user's behavior result is used to describe the historical control results of the historical devices in the vehicle corresponding to the user's historical behavior.

[0103] It should be noted that the behavior analysis model is trained by a pre-built first deep learning model.

[0104] In an embodiment of the present application, the behavior analysis model can be obtained by training a pre-constructed first deep learning model based on a preset sample set. Each sample data in the preset sample set includes sample interaction information and sample behavior information corresponding to the sample interaction information. When training the pre-constructed first deep learning model, the sample interaction information in each sample data is used as the input of the first deep learning model, and the sample behavior information corresponding to the sample interaction information in each sample data 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 interaction information and sample behavior information, and use the trained first deep learning model as the behavior analysis model.

[0105] In some possible embodiments, since the training of deep learning models usually requires a large number of samples, huge amount of calculation, and long training time, in order to improve the efficiency of determining historical behavior information, the vehicle terminal can filter the historical interaction information from the pre-stored behavior information storage list to obtain the user's historical behavior information;

[0106] In this embodiment, the above behavior information storage list may be composed of different behavior determination rules of users in real life.

[0107] In S202, a demand analysis is performed on the current behavior information based on the historical behavior information to obtain the target demand information.

[0108] In this embodiment, the vehicle terminal can compare the current behavior information with the historical behavior information to filter out the historical behavior that is the same as the current behavior information from the historical behavior information. Afterwards, the vehicle terminal can determine the historical device in the behavior result corresponding to the historical behavior as the device to be controlled in the vehicle at this time, and determine the control demand for the device to be controlled at this time based on the historical control result of the historical device in the behavior result corresponding to the historical behavior, thereby completing the demand analysis and obtaining the user's target demand information.

[0109] From the above, it can be seen that by utilizing the rich data resource of historical interaction information, the behavior analysis model of this embodiment can deeply explore the user's behavior patterns and preferences, thereby realizing highly personalized demand analysis. It does not rely solely on general rules or preset scenarios, but customizes the understanding and response to current behavior based on each user's unique historical behavior trajectory, fully considering the differences between individual users, so that the vehicle terminal can accurately predict the user's possible needs in the current situation. It can be seen that this embodiment can accurately determine the user's behavioral habits and preferences, so that the subsequent determination of user needs is more matched with the user, thereby further improving the accuracy of determining the user's target demand information.

[0110] In one embodiment of the present application, when the current behavior information includes voice information and multiple different action information, and the multiple action information are all used to represent the control method of the same to-be-controlled device of the vehicle, since there may be conflicts between the multiple action information, that is, different action information corresponds to different control methods, therefore, in order to clarify the user's control method for the to-be-controlled device of the vehicle, and then accurately determine the user's needs, the vehicle terminal can specifically perform the following steps: Figure 3 Steps S301 to S304 shown determine target demand information, as detailed below:

[0111] In S301, a device to be controlled of the vehicle is determined according to the voice information.

[0112] In this embodiment, the vehicle-mounted terminal may extract target keywords from the language information input by the user according to a pre-stored keyword table.

[0113] It should be noted that the preset keywords in the keyword table include but are not limited to the names and abbreviations of various devices in the vehicle (such as ceiling lights, voice players, and windows, etc.), and the functions of each device (such as the functions of the voice player are play, increase volume, and decrease volume), etc.

[0114] Afterwards, the vehicle-mounted terminal can directly determine the device to be controlled at this time according to the name or abbreviation of at least one device of the vehicle contained in the extracted target keyword.

[0115] Exemplarily, assuming that the voice information is "open window", the vehicle-mounted terminal can determine that the device to be controlled at this time is the vehicle window.

[0116] In this embodiment, since the plurality of different action information are used to represent the control mode of the device to be controlled, the vehicle-mounted terminal can detect whether the control modes corresponding to the plurality of different action information are the same.

[0117] In S302, if the control modes corresponding to the plurality of action information are different, the control preference information of the user for the device to be controlled is obtained from the historical behavior information.

[0118] In this embodiment, when the vehicle-mounted terminal detects that the control methods corresponding to multiple action information are different, it means that there is a conflict between the multiple action information. Therefore, in order to clarify the user's control method for the vehicle's controlled device and then accurately determine the user's needs, the vehicle-mounted terminal can obtain the user's control preference information for the controlled device from the behavior preferences in the historical behavior information.

[0119] In S303, the control priority of each of the plurality of action information is determined according to the control preference information.

[0120] In this embodiment, the control preference information includes the execution times and execution order of each of the plurality of action information in a historical time period.

[0121] Based on this, the vehicle terminal can determine the weight value of each action according to the execution times and execution order of each action information.

[0122] In some possible embodiments, the vehicle terminal may sequentially input the execution times and execution order of each action information into a trained weight determination model for processing to obtain the weight value of each action information. The weight determination model is obtained by training a pre-built second neural network model.

[0123] It should be noted that the weight determination model can be obtained by training a pre-constructed second neural network model based on a preset sample set. Each sample data in the preset sample set includes sample information (including the number of executions and the execution order of the sample action information) and a sample weight value corresponding to the sample information. When training the pre-constructed second neural network model, the sample information in each sample data is used as the input of the second neural network model, and the sample weight value corresponding to the sample information in each sample data is used as the output of the second neural network model. Through training, the second neural network model can learn the correspondence between all possible sample information and sample weight values, and the trained second neural network model is used as the weight determination model.

[0124] In this embodiment, after obtaining the weight value of each action information, the vehicle terminal can sort the action information in descending order of the weight value, and determine the position of each action information after sorting as the control priority of each action information.

[0125] It should be noted that the greater the weight value of a certain action information is, the higher its ranking position is and the higher its control priority is.

[0126] Exemplarily, assuming that the weight value of a certain action information is the largest, its ranking position is the first priority, and its control priority is the first priority.

[0127] In another embodiment of the present application, when the vehicle-mounted terminal detects that the user's control preference information is blank, it means that the user has no control preference for the device to be controlled. Therefore, in order to improve the user experience, the vehicle-mounted terminal can output prompt information to prompt the user to select between gesture control and eye control.

[0128] Afterwards, the user can determine the control method for the device to be controlled according to the prompt information, and input feedback information to the vehicle terminal, wherein the feedback information is used to describe the control method of the user for the device to be controlled.

[0129] Based on this, after receiving the feedback information input by the user, the vehicle-mounted terminal can generate target demand information according to the feedback information.

[0130] In S304, the target demand information is determined according to the control priorities of the plurality of action information.

[0131] In this embodiment, after obtaining the control priority of each action information, the vehicle-mounted terminal can directly generate the target demand information according to the action information of the first priority.

[0132] As can be seen from the above, this embodiment uses voice information as a starting point to determine the vehicle's to-be-controlled devices, making full use of the convenience and naturalness of voice interaction. Users do not need to manually operate a complex control panel, and can start the entire intelligent decision-making process through voice commands, which greatly improves the convenience and efficiency of operation. At the same time, by referring to historical behavior information to obtain the user's control preference for a specific device, the personalized factor is cleverly integrated into the current decision-making process, not only considering the user's long-term habits and preferences, but also combining the specific context triggered by the current voice command (i.e., the device to be controlled and multiple action information involved), so that the determination of the target demand information has both the uniqueness of the individual user and closely fits the actual operation needs of the moment, achieving the organic unity of personalization and contextualization. Finally, the control priority of multiple action information is determined according to the user's control preference information, rather than adopting a fixed preset priority mode, which has strong dynamic adaptability. As the user's time using the vehicle increases and the behavior pattern changes, the control preference information will also be updated accordingly, resulting in the control priority of the action information being able to be dynamically adjusted accordingly. This ensures that the decision of the vehicle terminal can always meet the actual needs of users at different stages and in different contexts to the greatest extent, and provide more flexible and considerate services.

[0133] In S103, the vehicle is controlled based on the target demand information and the environmental information through the active service function of the intelligent agent.

[0134] In the embodiment of the present application, after obtaining the target demand information, the vehicle terminal can call the active service function of the intelligent agent, so that the intelligent agent can input the target demand information and environmental information into the trained control strategy determination model for processing to obtain the target control strategy of the vehicle. Afterwards, the intelligent agent can realize active control of the vehicle according to the control strategy under the active service function.

[0135] It should be noted that the control strategy determination model is trained by a pre-built second deep learning model.

[0136] In an embodiment of the present application, the control strategy determination model can be obtained by training a pre-constructed second deep learning model based on a preset sample set. Wherein, each sample data in the preset sample set includes sample information (including demand information, external environment information and internal environment information) and a sample control strategy corresponding to the sample information. When training the pre-constructed second deep learning model, the sample information in each sample data is used as the input of the second deep learning model, and the sample control strategy corresponding to the sample information in each sample data 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 information and sample control strategies, and use the trained second deep learning model as the control strategy determination model.

[0137] In one embodiment of the present application, when the environmental information includes in-vehicle environmental information and out-vehicle environmental information, the user's target demand information may conflict with the out-vehicle environmental information, or with the in-vehicle environmental information. For example, assuming the target demand information is to open the window, and the weather condition in the out-vehicle environmental information is heavy rain, since opening the window at this time will allow rain to enter the vehicle, it can be determined that the target demand information conflicts with the out-vehicle environmental information; for another example, assuming the target demand information is to increase the volume, and the in-vehicle environmental information is that the passenger in the rear passenger seat is sleeping, since increasing the volume at this time will affect the passenger's sleep, it can be determined that the target demand information conflicts with the in-vehicle environmental information.

[0138] Based on this, in order to improve the control accuracy of the vehicle when the target demand information conflicts with the external environment information or the internal environment information, and to ensure the user's riding experience under such conflicting circumstances, the vehicle terminal can specifically Figure 4 The steps S401 to S403 shown implement the control of the vehicle, which are described in detail as follows:

[0139] In S401, through the active service function of the intelligent body, a first conflict result between the target demand information and the external vehicle environment information is detected, and a second conflict result between the target demand information and the internal vehicle environment information is detected.

[0140] In this embodiment, the vehicle terminal can call the active service function of the intelligent agent, so that the intelligent agent can input the target demand information, the external environment information and the internal environment information into the conflict detection model for processing, so as to detect whether the target demand information conflicts with the external environment information, and detect whether the target demand information conflicts with the internal environment information, thereby obtaining the first conflict result between the target demand information and the external environment information, and the second conflict result between the target demand information and the internal environment information. Among them, the first conflict result is used to describe whether the user's demand conflicts with the external environment, and the second conflict result is used to describe whether the user's demand conflicts with the internal environment.

[0141] It should be noted that the conflict detection model is trained by a pre-built third deep learning model.

[0142] In an embodiment of the present application, the conflict detection model can be obtained by training a pre-constructed third deep learning model based on a preset sample set. Each sample data in the preset sample set includes sample information (including demand information, external environment information and internal environment information) and sample conflict results corresponding to the sample information (including conflict results between demand information and external environment information, and conflict results between demand information and internal environment information). When training the pre-constructed third deep learning model, the sample information in each sample data is used as the input of the third deep learning model, and the sample conflict results corresponding to the sample information in each sample data are 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 conflict results, and the trained third deep learning model is used as the conflict detection model.

[0143] In this embodiment, the first conflict result includes but is not limited to: no conflict and conflict. Among them, no conflict in the first conflict result is used to describe that there is no conflict between the target demand information and the vehicle external environment information, and conflict in the first conflict result is used to describe that there is a conflict between the target demand information and the vehicle external environment information.

[0144] The second conflict result includes but is not limited to: no conflict and conflict. The no conflict in the second conflict result is used to describe that there is no conflict between the target demand information and the in-vehicle environment information, and the conflict in the second conflict result is used to describe that there is a conflict between the target demand information and the in-vehicle environment information.

[0145] In S402 , a vehicle control instruction is generated based on the first conflict result and the second conflict result.

[0146] In this embodiment, the vehicle terminal can continue to call the active service function of the intelligent agent so that after obtaining the first conflict result and the second conflict result, the intelligent agent can automatically determine whether a vehicle control instruction can be generated according to the target demand information based on the first conflict result and the second conflict result.

[0147] Specifically, when the vehicle-mounted terminal detects that the first conflict result is no conflict and the second conflict result is no conflict, it means that there is no conflict between the target demand information and the in-vehicle environment information and the out-vehicle environment information. Therefore, at this time, the intelligent body can use the active service function to actively generate vehicle control instructions based on the target demand information.

[0148] When the vehicle terminal detects that the first conflict result is a conflict, or the second conflict result is a conflict, it means that the target demand information conflicts with the in-vehicle environment information, or the target demand information conflicts with the out-vehicle environment information. Therefore, at this time, the intelligent agent can actively output prompt information for prompting the user whether to continue to control the vehicle according to the target demand information through the active service function. Afterwards, the user can input response information corresponding to the prompt information. The response information is used to describe whether the user needs to continue to control the vehicle according to the target demand information.

[0149] When the vehicle-mounted terminal detects that the response information is not required, it means that the user has determined that there is no need to continue controlling the vehicle according to the target demand information. Therefore, the intelligent agent can stop using the active service function and actively stop the control operation of the to-be-controlled device corresponding to the target demand information.

[0150] When the vehicle-mounted terminal detects that the response information is required, it means that the user is determined to continue to control the vehicle according to the target demand information. Therefore, at this time, the intelligent agent can actively generate vehicle control instructions according to the target demand information through the active service function.

[0151] In one embodiment of the present application, in order to further improve the practicality of the vehicle and enhance the riding experience of the user, the vehicle terminal can specifically Figure 5 The step S501 shown generates a vehicle control instruction, which is described in detail as follows:

[0152] In S501, if the first conflict result is no conflict and the second conflict result is no conflict, a first control instruction is generated according to the target demand information, a second control instruction is generated according to the external vehicle environment information, and a third control instruction is generated according to the internal vehicle environment information.

[0153] In this embodiment, when the vehicle-mounted terminal detects that the first conflict result is no conflict and the second conflict result is no conflict, it means that there is no conflict between the target demand information and the in-vehicle environment information and the outside-vehicle environment information. Therefore, the vehicle-mounted terminal can call the active service function of the intelligent body, so that the intelligent body can generate a first control instruction according to the target demand information, generate a second control instruction according to the outside-vehicle environment information, and generate a third control instruction according to the in-vehicle environment information, so as to achieve control of other equipment of the vehicle while meeting user needs, so that the in-vehicle environment after controlling other equipment of the vehicle is more adapted to the user.

[0154] In another embodiment of the present application, in order to generate accurate control instructions when the target demand information conflicts with the vehicle external environment information, so as to achieve accurate control of the vehicle and improve the user's riding experience, the vehicle terminal can specifically generate accurate control instructions when the target demand information conflicts with the vehicle external environment information, so as to achieve accurate control of the vehicle and improve the user's riding experience. Figure 6 The steps S601 to S604 shown generate vehicle control instructions, which are described in detail as follows:

[0155] In S601, if the first conflict result is a conflict, and the second conflict result is a non-conflict, a fourth control instruction is generated according to the in-vehicle environment information.

[0156] In this embodiment, when the vehicle-mounted terminal detects that the first conflict result is a conflict and the second conflict result is no conflict, it means that there is a conflict between the target demand information and the external environment information, and there is no conflict between the target demand information and the internal environment information. Therefore, the vehicle-mounted terminal can call the active service function of the intelligent body so that the intelligent body can directly generate a fourth control instruction based on the internal environment information.

[0157] In S602, a conflict analysis is performed on the target demand information and the vehicle external environment information to determine at least one backup control mode.

[0158] In this embodiment, since the first conflict result is a conflict, that is, there is a conflict between the target demand information and the external environment information, therefore, in order to generate accurate control instructions when the target demand information conflicts with the external environment information to achieve accurate control of the vehicle, the on-board terminal can call the active service function of the intelligent body so that the intelligent body can input the target demand information and the external environment information into the first conflict analysis model for conflict analysis, thereby obtaining at least one backup control method for the vehicle.

[0159] It should be noted that the first conflict analysis model is trained by a pre-built fourth deep learning model.

[0160] In an embodiment of the present application, the first conflict analysis model may be obtained by training a pre-constructed fourth deep learning model based on a preset sample set. Each sample data in the preset sample set includes sample information (including demand information and vehicle external environment information) and a first sample control method corresponding to the sample information. When training the pre-constructed fourth deep learning model, the sample information in each sample data is used as the input of the fourth deep learning model, and the first sample control method corresponding to the sample information in each sample data 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 the first sample control method, and use the trained fourth deep learning model as the first conflict analysis model.

[0161] For example, assuming that the target demand information is to open the window and the outside environment information is heavy rain, the alternative control methods may include closing the window and turning on the air conditioner.

[0162] Afterwards, the vehicle terminal can display at least one of the above-mentioned backup control methods on the vehicle central control screen.

[0163] In S603, a target control mode is determined from the at least one backup control mode according to the selection information input by the user.

[0164] In S604, a fifth control instruction is generated based on the target control mode.

[0165] In this embodiment, the user can click on at least one of the alternate control modes displayed on the vehicle-mounted central control screen to send the selection information input by the user to the vehicle-mounted terminal, wherein the selection information is used to describe the target control mode of the vehicle that the user has selected from the at least one alternate control mode.

[0166] Afterwards, after receiving the selection information input by the user, the intelligent agent in the vehicle terminal can call the active service function and determine the target control mode for the vehicle from at least one backup control mode according to the selection information.

[0167] In this embodiment, the vehicle-mounted terminal can generate a vehicle control instruction according to the determined target control method.

[0168] It can be seen from the above that the present embodiment can carefully distinguish the conflict between the external environment information and the target demand information and the conflict between the internal environment information and the target demand information, and adopt corresponding different processing methods. This differentiated processing reflects the intelligence and refinement of the system. It does not blindly generalize all conflicts, but formulates personalized solutions for specific conflict scenarios, so that the vehicle control is more accurate and in line with actual needs. At the same time, after determining the backup control mode, the selection information input by the user can be introduced to determine the final target control mode, and the user's subjective will is incorporated into the control decision-making process. This feature fully respects the user's autonomy and decision-making power, avoids the situation that the intelligent body's completely autonomous decision-making may be inconsistent with the user's expectations, and also enhances the interactivity and sense of participation between the user and the vehicle, so that the user is no longer a passive recipient in the vehicle control process, but becomes part of the decision. Finally, whether it is the fourth control instruction generated based on the internal environment information or the fifth control instruction generated according to the target control mode determined by the user's selection, it reflects the flexibility of the system in generating control instructions. It can quickly and accurately generate appropriate control instructions according to different situations and conditions to cope with various complex and changeable driving scenarios and user needs, ensuring that the vehicle is always in a state that can meet the basic needs of users and maintain safe and stable operation under the constraints of the external environment.

[0169] In another embodiment of the present application, in order to generate accurate control instructions when the target demand information conflicts with the in-vehicle environment information, so as to achieve accurate control of the vehicle and improve the user's riding experience, the vehicle terminal can specifically generate the vehicle control instructions according to the following steps, which are described in detail as follows:

[0170] If the first conflict result is no conflict, and the second conflict result is conflict, generating a sixth control instruction according to the vehicle external environment information;

[0171] Performing a conflict analysis on the target demand information and the in-vehicle environment information to determine at least one alternative control method;

[0172] Determining a vehicle control mode from the at least one candidate control mode according to the response information input by the user;

[0173] A seventh control instruction is generated based on the vehicle control method.

[0174] In this embodiment, the vehicle-mounted terminal can call the active service function of the intelligent body so that when the intelligent body detects that the first conflict result is no conflict and the second conflict result is a conflict, it indicates that there is no conflict between the target demand information and the external environment information, and there is a conflict between the target demand information and the internal environment information. Therefore, the vehicle-mounted terminal can call the active service function of the intelligent body so that the intelligent body can directly generate the sixth control instruction based on the external environment information.

[0175] Since the second conflict result is a conflict, that is, there is a conflict between the target demand information and the in-vehicle environment information, therefore, in order to generate accurate control instructions when the target demand information and the in-vehicle environment information conflict, so as to achieve accurate control of the vehicle, the on-board terminal can call the active service function of the intelligent body, so that the intelligent body can input the target demand information and the in-vehicle environment information into the second conflict analysis model for conflict analysis, thereby obtaining at least one alternative control method for the vehicle.

[0176] It should be noted that the second conflict analysis model is trained by a pre-built fifth deep learning model.

[0177] In this embodiment, the second conflict analysis model can be obtained by training a pre-constructed fourth deep learning model based on a preset sample set. Each sample data in the preset sample set includes sample information (including demand information and in-vehicle environment information) and a second sample control method corresponding to the sample information. When training the pre-constructed fifth deep learning model, the sample information in each sample data is used as the input of the fifth deep learning model, and the second sample control method corresponding to the sample information in each sample data 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 the second sample control method, and the trained fifth deep learning model is used as the second conflict analysis model.

[0178] For example, assuming that the target demand information is to turn up the volume, and the in-vehicle environment information is that the passenger in the rear passenger seat is in a sleeping state, the alternative control method may include turning up the volume of the front speaker, etc.

[0179] Afterwards, the vehicle terminal can display at least one of the above-mentioned alternative control methods on the vehicle central control screen.

[0180] In this embodiment, the user can click on at least one of the alternative control modes displayed on the vehicle-mounted central control screen to send the response information input by the user to the vehicle-mounted terminal, wherein the response information is used to describe the vehicle control mode selected by the user from the at least one alternative control mode.

[0181] Afterwards, after receiving the response information input by the user, the intelligent agent in the vehicle terminal can call the active service function and determine the vehicle control mode from at least one alternative control mode according to the response information.

[0182] In this embodiment, the vehicle-mounted terminal can call the active service function of the intelligent agent so that the intelligent agent can generate a vehicle control instruction according to the determined vehicle control method.

[0183] It should be noted that the vehicle control instruction includes but is not limited to the device to be controlled and the control operation corresponding to the device to be controlled.

[0184] It can be seen from the above that the present embodiment can carefully distinguish the conflict between the external environment information and the target demand information and the conflict between the internal environment information and the target demand information, and adopt corresponding different processing methods. This differentiated processing reflects the intelligence and refinement of the system. It does not blindly generalize all conflicts, but formulates personalized solutions for specific conflict scenarios, so that the vehicle control is more accurate and in line with actual needs. At the same time, after determining the backup control mode, the selection information input by the user can be introduced to determine the final target control mode, and the user's subjective will is incorporated into the control decision-making process. This feature fully respects the user's autonomy and decision-making power, avoids the situation that the intelligent body may not meet the user's expectations due to the completely autonomous decision-making of the intelligent body, and also enhances the interactivity and sense of participation between the user and the vehicle, so that the user is no longer a passive recipient in the vehicle control process, but becomes part of the decision. Finally, whether it is the sixth control instruction generated based on the external environment information or the seventh control instruction generated according to the target control mode determined by the user's selection, it reflects the flexibility of the system in generating control instructions. It can quickly and accurately generate appropriate control instructions according to different situations and conditions to cope with various complex and changeable driving scenarios and user needs, ensuring that the vehicle is always in a state that can meet the basic needs of users and maintain safe and stable operation under the constraints of the external environment.

[0185] In S403, the vehicle is controlled based on the vehicle control instruction.

[0186] In this embodiment, the vehicle-mounted terminal can call the active service function of the intelligent agent so that the intelligent agent can extract the device to be controlled and the corresponding control operation of the device to be controlled from the vehicle control instruction. Afterwards, the intelligent agent can control the device to be controlled based on the control operation under the active service function, thereby realizing control of the vehicle.

[0187] This embodiment fully considers the external environment information and the internal environment information of the vehicle, and performs multi-dimensional conflict detection on the target demand information. This comprehensive perception method can more accurately grasp the actual situation of the vehicle. It not only pays attention to the needs of users, but also takes into account various factors inside and outside the vehicle, so that the vehicle terminal can discover potential contradictions and mismatches, so as to make more reasonable decisions. At the same time, generating vehicle control instructions based on the conflict detection results means that the control of the vehicle is not statically preset, but can be adjusted dynamically in real time according to the actual situation. With the changes in the internal and external environment of the vehicle and the changes in the user's target needs, the vehicle terminal can quickly re-evaluate and generate new control instructions to keep the vehicle in an optimal operating state at all times and adapt to various complex and changing driving scenarios.

[0188] From the above, it can be seen that a vehicle control method provided by an embodiment of the present application obtains historical interaction information between the user in the vehicle and the intelligent agent of the vehicle, the current behavior information of the user, and the environmental information of the vehicle; analyzes the historical interaction information and the current behavior information to determine the target demand information of the user; and controls the vehicle based on the target demand information and the environmental information through the active service function of the intelligent agent. The present application obtains a variety of information sources, including historical interaction information, current behavior information, and environmental information, so that the vehicle terminal can have a more comprehensive and in-depth understanding of user needs and vehicle status. At the same time, by analyzing the historical interaction information and the current behavior information to determine the target demand information of the user, a highly personalized service can be achieved, that is, the corresponding service and control can be accurately provided according to the unique habits and preferences of the user. In addition, based on the target demand information and the environmental information, the intelligent agent can actively control the vehicle and has active adaptability, that is, the intelligent agent does not passively wait for user instructions, but makes decisions and actions in advance according to real-time information changes. In summary, the present application avoids the user's frequent manual operation of various functions of the vehicle. The intelligent agent can automatically set and adjust according to the user's habits and current situation, achieve accurate control of the vehicle, improve the user experience and the practicality of the vehicle; at the same time, it can also accurately grasp the user's personalized needs, and the services provided by the intelligent agent are more in line with the user's expectations.

[0189] 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.

[0190] Corresponding to a vehicle control method described in the above embodiment, Figure 7 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 7The vehicle control device 700 includes: a first acquisition unit 71, a first analysis unit 72 and a first control unit 73. Among them:

[0191] The first acquisition unit 71 is used to acquire historical interaction information between a user in a vehicle and an intelligent agent of the vehicle, current behavior information of the user, and environmental information of the vehicle.

[0192] The first analyzing unit 72 is used to analyze the historical interaction information and the current behavior information to determine the target demand information of the user.

[0193] The first control unit 73 is used to control the vehicle based on the target demand information and the environmental information through the active service function of the intelligent body.

[0194] In one embodiment of the present application, the first analysis unit 72 specifically includes: a processing unit and a second analysis unit. Among them:

[0195] The processing unit is used to input the historical interaction information into the behavior analysis model for processing to obtain the historical behavior information of the user.

[0196] The second analysis unit is used to perform demand analysis on the current behavior information based on the historical behavior information to obtain the target demand information.

[0197] In one embodiment of the present application, the current behavior information includes voice information and multiple different action information; the second analysis unit specifically includes: a first determination unit, a second acquisition unit, a second determination unit and a third determination unit. Among them:

[0198] The first determination unit is used to determine the to-be-controlled device of the vehicle according to the voice information.

[0199] The second acquisition unit is configured to acquire the control preference information of the user for the device to be controlled from the historical behavior information if the control modes corresponding to the plurality of action information are different.

[0200] The second determining unit is used to determine the control priority of each of the plurality of action information according to the control preference information.

[0201] The third determining unit is used to determine the target demand information according to the control priorities of the plurality of action information.

[0202] In one embodiment of the present application, the vehicle control device 700 further includes: an output unit and a third generating unit.

[0203] The output unit is used to output voice prompt information if the control preference information is blank; the voice prompt information is used to prompt the user to select gesture control and eye movement control.

[0204] The third generating unit is used to generate the target demand information according to the feedback information input by the user.

[0205] In one embodiment of the present application, the environmental information includes external environmental information and internal environmental information; the first control unit 73 specifically includes: a detection unit, a fourth generation unit and a second control unit. Among them:

[0206] Through the active service function of the intelligent body, the detection unit is used to detect a first conflict result between the target demand information and the external environment information, and to detect a second conflict result between the target demand information and the internal environment information; the first conflict result is used to describe whether the user's demand conflicts with the external environment; the second conflict result is used to describe whether the user's demand conflicts with the internal environment.

[0207] The fourth generating unit is used to generate a vehicle control instruction based on the first conflict result and the second conflict result.

[0208] The second control unit is used to control the vehicle based on the vehicle control instruction.

[0209] In one embodiment of the present application, the fourth generating unit specifically includes: a fifth generating unit.

[0210] The fifth generation unit is used to generate a first control instruction according to the target demand information, generate a second control instruction according to the external vehicle environment information, and generate a third control instruction according to the internal vehicle environment information if the first conflict result is no conflict and the second conflict result is no conflict.

[0211] In one embodiment of the present application, the fourth generating unit specifically includes: a sixth generating unit, a second determining unit, a third determining unit and a seventh generating unit. Wherein:

[0212] The sixth generating unit is configured to generate a fourth control instruction according to the in-vehicle environment information if the first conflict result is a conflict and the second conflict result is a non-conflict.

[0213] The second determination unit is used to perform conflict analysis on the target demand information and the vehicle exterior environment information to determine at least one backup control mode.

[0214] The third determining unit is used to determine a target control mode from the at least one backup control mode according to the selection information input by the user.

[0215] The seventh generating unit is used to generate a fifth control instruction based on the target control mode.

[0216] 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.

[0217] 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.

[0218] Figure 8 This is a schematic diagram of the structure of a vehicle-mounted terminal provided in one embodiment of the present application. Figure 8 As shown, the vehicle terminal 8 of this embodiment includes: at least one processor 80 ( Figure 8 Only one is shown in the figure) a processor, a memory 81, and a computer program 82 stored in the memory 81 and executable on the at least one processor 80, wherein the processor 80 implements the steps in any of the above-mentioned vehicle control method embodiments when executing the computer program 82.

[0219] The vehicle terminal may include, but is not limited to, a processor 80 and a memory 81. Those skilled in the art will appreciate that Figure 8 It is only an example of the vehicle-mounted terminal 8 and does not constitute a limitation on the vehicle-mounted terminal 8. 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.

[0220] The processor 80 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.

[0221] In some embodiments, the memory 81 may be an internal storage unit of the vehicle-mounted terminal 8, such as the memory of the vehicle-mounted terminal 8. In other embodiments, the memory 81 may also be an external storage device of the vehicle-mounted terminal 8, 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 8. Further, the memory 81 may also include both the internal storage unit of the vehicle-mounted terminal 8 and an external storage device. The memory 81 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 81 may also be used to temporarily store data that has been output or is to be output.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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: Acquire historical interaction information between a user in a vehicle and an intelligent agent of the vehicle, current behavior information of the user, and environmental information of the vehicle; Analyze the historical interaction information and the current behavior information to determine the target demand information of the user; Through the active service function of the intelligent body, the vehicle is controlled based on the target demand information and the environmental information.

2. The vehicle control method according to claim 1, characterized in that: The analyzing the historical interaction information and the current behavior information to determine the target demand information of the user includes: Inputting the historical interaction information into a behavior analysis model for processing to obtain historical behavior information of the user; The current behavior information is subjected to demand analysis based on the historical behavior information to obtain the target demand information.

3. The vehicle control method according to claim 2, characterized in that: The current behavior information includes voice information and a plurality of different action information; the demand analysis of the current behavior information based on the historical behavior information to obtain the target demand information includes: Determining a device to be controlled of the vehicle according to the voice information; If the control modes corresponding to the plurality of action information are all different, obtaining the control preference information of the user for the device to be controlled from the historical behavior information; determining the control priority of each of the plurality of action information according to the control preference information; The target demand information is determined according to the control priorities of the plurality of action information.

4. The vehicle control method according to claim 3, characterized in that: The method further comprises: If the control preference information is blank, outputting voice prompt information; the voice prompt information is used to prompt the user to select gesture control and eye movement control; The target demand information is generated according to the feedback information input by the user.

5. The vehicle control method according to any one of claims 1 to 4, characterized in that: The environmental information includes external vehicle environmental information and internal vehicle environmental information; The controlling of the vehicle based on the target demand information and the environment information through the active service function of the intelligent agent includes: Detecting a first conflict result between the target demand information and the vehicle exterior environment information, and detecting a second conflict result between the target demand information and the vehicle interior environment information, through the active service function of the intelligent agent; generating a vehicle control instruction based on the first conflict result and the second conflict result; The vehicle is controlled based on the vehicle control command.

6. The vehicle control method according to claim 5, characterized in that: The generating of the vehicle control instruction based on the first conflict result and the second conflict result includes: If the first conflict result is no conflict and the second conflict result is no conflict, a first control instruction is generated according to the target demand information, a second control instruction is generated according to the external vehicle environment information, and a third control instruction is generated according to the internal vehicle environment information.

7. The vehicle control method according to claim 5, characterized in that: The generating of the vehicle control instruction based on the first conflict result and the second conflict result includes: If the first conflict result is a conflict, and the second conflict result is a non-conflict, generating a fourth control instruction according to the in-vehicle environment information; Performing a conflict analysis on the target demand information and the vehicle external environment information to determine at least one backup control mode; Determining a target control mode from the at least one backup control mode according to the selection information input by the user; A fifth control instruction is generated based on the target control mode.

8. A vehicle control device, characterized in that: include: A first acquisition unit, configured to acquire historical interaction information between a user in a vehicle and an intelligent agent of the vehicle, current behavior information of the user, and environmental information of the vehicle; A first analyzing unit, configured to analyze the historical interaction information and the current behavior information to determine target demand information of the user; A first control unit is used to control the vehicle based on the target demand information and the environmental information through the active service function of the intelligent body.

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