Vehicle control method and device, vehicle and storage medium

Abstract

The embodiment of the invention provides a vehicle control method, which is applied to the field of vehicle control, and comprises the following steps: determining a plurality of control instructions by responding to an input operation of a user, respectively determining urgency indexes and resource demand information of the plurality of control instructions according to the control instructions for different subsystems, and determining the urgency indexes and the resource demand information of the plurality of control instructions according to the urgency indexes and the resource demand information; according to the method, the urgency indexes are determined, resource use information of the subsystems is determined, target execution priorities corresponding to the control instructions are determined in combination with the urgency indexes, the resource demand information and the resource use information, the subsystems are scheduled to perform collaborative operation according to the control instructions according to the target execution priorities, and a unified and efficient instruction processing mechanism is provided. And complex coordination and conflicts in a plurality of subsystems in the vehicle are effectively avoided.

Description

Technical Field

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

[0002] The smart cockpit is a combination of intelligent technology and vehicle control systems. The existing smart cockpit includes control systems, entertainment systems, air conditioning systems, communication systems, seat systems, interactive systems, perception systems, etc. It is not only a control center, but also an important bridge connecting drivers, passengers and vehicles. The smart cockpit integrates a variety of electronic devices and functions to provide a safe, comfortable and intelligent driving experience.

[0003] Among them, driving information display is the basic function of the smart cockpit, including the instrument panel, head-up display and navigation system. These devices provide the driver with real-time vehicle speed, fuel level, navigation information, etc., to help the driver better control the vehicle status; the entertainment system provides passengers with a rich entertainment experience through multimedia playback, voice assistant and in-vehicle applications; the communication system supports in-car phones, Wi-Fi hotspots and car networking to achieve seamless connection between the vehicle and the outside world; comfort functions such as air-conditioning system, seat adjustment and window control enhance the passengers' riding experience; and safety functions such as driving assistance systems, emergency call systems and driver monitoring systems provide multiple guarantees for driving safety.

[0004] In related technologies, smart cockpits usually adopt a multi-level system architecture, with different subsystems responsible for different tasks or modules. Although this architecture can share the processing load to a certain extent, different subsystems process instructions independently, lacking unified scheduling and planning, which easily leads to conflicts between instructions, especially when multiple tasks need to be executed at the same time, the system is difficult to coordinate effectively, increasing the delay and complexity of instruction execution. Summary of the invention

[0005] In view of the above problems, a method, device, vehicle and storage medium for vehicle control are proposed to overcome the above problems or at least partially solve the above problems, including:

[0006] A method for controlling a vehicle, wherein the vehicle is equipped with a plurality of subsystems and an agent connected to the plurality of subsystems, the method comprising:

[0007] In response to an input operation of a user, a plurality of control instructions are determined; wherein the plurality of control instructions include control instructions for different subsystems;

[0008] respectively determining the urgency indicators and resource requirement information of the plurality of control instructions, and determining the resource usage information of the plurality of subsystems;

[0009] Determine the target execution priorities corresponding to the multiple control instructions respectively in combination with the urgency index, the resource demand information, and the resource usage information;

[0010] According to the target execution priority, the multiple subsystems are scheduled to perform collaborative operations according to the multiple control instructions.

[0011] In some optional embodiments of the present application, the control instruction includes target control state information, and the respectively determining the urgency indicators and resource requirement information of the multiple control instructions includes:

[0012] Determine the target subsystem for each of the control instructions;

[0013] Acquire current status information of the target subsystem;

[0014] The resource requirement information of the plurality of control instructions is determined according to the current state information and the target control state information.

[0015] In some optional embodiments of the present application, the scheduling the multiple subsystems to perform collaborative operations according to the multiple control instructions includes:

[0016] Obtaining historical user preference information of the user for each of the subsystems;

[0017] The plurality of subsystems are scheduled to adopt the user historical preference information to execute the plurality of control instructions.

[0018] In some optional embodiments of the present application, after scheduling the multiple subsystems to perform collaborative operations according to the multiple control instructions, the method further includes:

[0019] Obtaining post-execution status information of the target subsystem;

[0020] Execution feedback information is determined according to the post-execution state information and the target control state information, and the execution feedback information is fed back to the user.

[0021] In some optional embodiments of the present application, the method further includes:

[0022] Obtain vehicle external environment information;

[0023] When it is determined that the vehicle external environment information has changed, adjusting the target execution priority according to the external environment information to obtain an adjusted target execution priority;

[0024] According to the adjusted target priorities, the multiple subsystems are scheduled to work collaboratively according to the multiple control instructions.

[0025] In some optional embodiments of the present application, the determining of multiple control instructions in response to the user's input operation includes:

[0026] Acquire user input content, where the user input content is at least one of voice input, gesture input, touch input, and eye movement input;

[0027] Performing semantic analysis on the user input content to obtain multiple control intention information;

[0028] Determine a plurality of control instructions corresponding to the plurality of control intention information.

[0029] In some optional embodiments of the present application, the urgency index includes a preset security level, and the respectively determining the urgency index and resource requirement information of the plurality of control instructions includes:

[0030] According to the multiple control instructions, a preset association table is searched to obtain the preset security levels respectively corresponding to the multiple control instructions, wherein the preset association table is used to store the association relationship between the control instructions and the preset security levels.

[0031] A vehicle control device, wherein the vehicle is equipped with a plurality of subsystems and an agent connected to the plurality of subsystems, the device comprising:

[0032] An input response module, configured to determine a plurality of control instructions in response to an input operation of a user; wherein the plurality of control instructions include control instructions for different subsystems;

[0033] a resource determination module, configured to respectively determine the urgency indicators and resource requirement information of the plurality of control instructions, and determine resource usage information of the plurality of subsystems;

[0034] a priority determination module configured to determine target execution priorities corresponding to the plurality of control instructions respectively in combination with the urgency indicator, the resource demand information, and the resource usage information;

[0035] The scheduling module is configured to schedule the multiple subsystems to perform collaborative operations according to the multiple control instructions based on the target execution priority.

[0036] A vehicle comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the vehicle control method as described above when executed by the processor.

[0037] A computer-readable storage medium is characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the vehicle control method as described above is implemented.

[0038] The embodiments of the present application have the following advantages:

[0039] By responding to the user's input operation, multiple control instructions are determined, wherein the multiple control instructions include control instructions for different subsystems, and the urgency indicators and resource requirement information of the multiple control instructions are respectively determined, and the resource usage information of the multiple subsystems is determined. In combination with the urgency indicators, resource requirement information, and resource usage information, the target execution priorities corresponding to the multiple control instructions are respectively determined. According to the target execution priorities, the multiple subsystems are scheduled to work collaboratively according to the multiple control instructions, providing a unified and efficient instruction processing mechanism, effectively avoiding complex coordination and conflicts within multiple subsystems in the vehicle, and realizing intelligent control of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the description of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0041] Figure 1 is a flowchart of a vehicle control method provided by some embodiments of the present application;

[0042] Figure 2 is a flowchart of another vehicle control method provided by some embodiments of the present application;

[0043] Figure 3 is a flowchart of the steps of instruction planning provided by some embodiments of the present application;

[0044] Figure 4 This is a structural block diagram of a vehicle control device provided in some embodiments of the present application. DETAILED DESCRIPTION

[0045] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0046] Reference Figure 1, shows a flowchart of a vehicle control method provided by some embodiments of the present application, which is applied to a smart cockpit of an automobile, and may specifically include the following steps:

[0047] Step 101: In response to a user's input operation, determine a plurality of control instructions; wherein the plurality of control instructions include control instructions for different subsystems.

[0048] Among them, the vehicle is deployed with multiple subsystems and agents connected to multiple subsystems. The multiple subsystems of the vehicle refer to the independent parts that constitute the entire vehicle system, and each subsystem is responsible for specific functions and tasks. These subsystems usually work together to ensure that the vehicle can operate safely and efficiently. For example, the audio system, navigation system, and air conditioning system. The audio system in the vehicle is an important part of providing in-vehicle entertainment and information. It not only provides music, broadcasts and other audio content for passengers, but also integrates functions such as navigation, telephone and vehicle information display; the navigation system in the vehicle is designed to help the driver determine the current location, plan the route and guide it to the destination, providing real-time navigation, map display, traffic information and voice prompts; the air conditioning system is an important part of ensuring the comfort of the in-vehicle environment. It provides passengers with a suitable riding environment by adjusting the temperature, humidity and air flow in the car. In the case where the user needs to adjust the internal environment of the vehicle, the user's input operation refers to the operation information containing the user's adjustment needs.

[0049] The agent terminal refers to the control center that can control various subsystems to work together. The agent terminal in this application can communicate with multiple subsystems in the vehicle and support a variety of different interaction methods, such as supporting different input methods, including but not limited to voice input, gesture input, touch input, eye movement control, etc.

[0050] In some implementations of this embodiment, since the proxy terminal can control multiple subsystems to work in coordination, the user can adjust and control different subsystems in different ways at the same time. For example, the user can adjust the volume of the audio system by touching the vehicle display system, and adjust the vehicle's air conditioning subsystem by voice command "turn on the air conditioning". In other words, the control instructions for different subsystems can be determined from the user's input operations.

[0051] Step 102: respectively determining urgency indicators and resource requirement information of a plurality of control instructions, and determining resource usage information of a plurality of subsystems.

[0052] Among them, the urgency index is used to evaluate the priority of different control instructions to ensure that the most urgent tasks are handled first when resources are limited. Urgency indicators can include time sensitivity indicators, safety indicators, and user demand indicators; time sensitivity refers to how long it takes for an instruction to be executed, for example, an emergency braking instruction needs to be executed within a few milliseconds, while an air conditioning temperature adjustment instruction can be executed within a few seconds. Safety indicators refer to the safety impact of instructions on vehicles and passengers. For example, an instruction to avoid a collision is more urgent than an instruction to adjust the seat position; user demand indicators refer to whether an instruction meets the immediate needs of the driver or passenger, for example, a navigation system route update instruction is more urgent than a background music playback instruction.

[0053] In some implementations of this embodiment, an urgency score may be pre-assigned to each control instruction. For example, a scoring system of 1 to 10 is used, with 1 representing the lowest urgency and 10 representing the highest urgency. For example, the time sensitivity index of the air conditioning temperature adjustment instruction is 5, the safety index is 3, and the user demand index is 6. In order to calculate the comprehensive urgency index of each instruction, weights may also be assigned to the various urgency indicators of each instruction. For example, the time sensitivity weight is 0.5, the safety weight is 0.4, and the user demand weight is 0.1. Then the urgency index of the air conditioning temperature adjustment instruction may be calculated as 0.5×5+0.4×3+0.1×6=4.3.

[0054] Resource requirement information is used to evaluate the computing resources, storage resources, communication resources, energy resources, etc. required for each control instruction. Computing resources refer to the CPU and GPU computing power required for the instruction. For example, image processing instructions require higher computing resources. Storage resources refer to the data storage space required for the instruction. For example, map data update instructions require a larger storage space. Communication resources refer to the network bandwidth and communication delay required for the instruction. For example, real-time traffic information update instructions require higher communication resources. Energy resources refer to the energy required to execute instructions. For example, how much energy is required to adjust the temperature inside the car.

[0055] The resource usage information of multiple subsystems refers to the computing resources, storage resources, communication resources and energy resources consumed by each subsystem during operation. In a specific implementation, the resource usage of each subsystem can be monitored in real time, and the consumption of computing resources, storage resources, communication resources and energy resources can be recorded.

[0056] Step 103: Determine the target execution priorities corresponding to the multiple control instructions respectively by combining the urgency index, the resource demand information, and the resource usage information;

[0057] In order to ensure that the various subsystems of the vehicle can work in coordination and operate efficiently and safely, after determining the urgency index, resource demand information and resource usage information of each subsystem, different execution priorities can be assigned to multiple control instructions based on this information.

[0058] In some implementations of this embodiment, the urgency index can be given priority, and the resource demand information and resource usage information can be used as secondary considerations to assign target execution priorities to multiple control instructions. For example, when the vehicle is moving, when the user needs to adjust the air-conditioning temperature and start navigation at the same time, since the urgency index of starting navigation is higher, resources can be allocated to start navigation first. If the urgency indexes of two control instructions are the same, the resource demand information and resource usage information are used as reference factors. For example, when the user needs to adjust the air-conditioning temperature and the refrigerator temperature at the same time, but the vehicle is low on power or fuel, if the energy required to adjust the air-conditioning temperature is less than the energy required to adjust the refrigerator temperature, the air-conditioning temperature adjustment operation can be performed on the user first. Of course, the user can adjust the execution order of control instructions with low urgency indicators.

[0059] Step 104: According to the target execution priority, multiple subsystems are scheduled to perform collaborative operations according to multiple control instructions.

[0060] The urgency index helps each subsystem prioritize the most urgent control instructions. Resource demand information and resource usage information can ensure that control instructions can obtain sufficient resources. According to the target execution priority, multiple subsystems are scheduled to work together according to multiple control instructions. Instructions with high priority obtain better resources and get faster responses.

[0061] The embodiment of the present application determines multiple control instructions in response to user input operations, wherein the multiple control instructions include control instructions for different subsystems, and respectively determines urgency indicators and resource requirement information of the multiple control instructions, and determines resource usage information of the multiple subsystems. In combination with the urgency indicators, resource requirement information, and resource usage information, the target execution priorities corresponding to the multiple control instructions are respectively determined. Based on the target execution priorities, the multiple subsystems are scheduled to work collaboratively according to the multiple control instructions, thereby providing a unified and efficient instruction processing mechanism to effectively avoid complex coordination and conflicts within multiple subsystems in the vehicle.

[0062] Reference Figure 2 , shows a flowchart of another method for controlling a vehicle provided in some embodiments of the present application, wherein the vehicle is deployed with multiple subsystems and an agent connected to the multiple subsystems, and specifically may include the following steps:

[0063] Step 201: In response to a user's input operation, determine a plurality of control instructions; wherein the plurality of control instructions include control instructions for different subsystems;

[0064] In some embodiments of the present application, step 201 may include the following sub-steps:

[0065] Sub-step 11: obtaining user input content, where the user input content is at least one of voice input, gesture input, touch input, and eye movement input;

[0066] The agent can be a Single-Agent, and the agent in this application supports multiple input methods, including voice, gesture, touch, eye movement, etc. The user can send commands through these methods, for example, the user says "turn on the air conditioner" through voice, and adjusts the volume through gestures at the same time.

[0067] Through the preset NLU model, Single-Agent can accurately identify and parse the user's voice, gesture and other commands to resolve semantic ambiguity and command ambiguity. Single-Agent not only processes simple commands, but also understands complex semantic relationships. For example, when a user speaks "I'm a little cold, turn up the temperature", Single-Agent's deep understanding of the context and command can obtain the keywords "cold", "turn up", and "temperature", which in turn provides a basis for determining the user's intention in the next step.

[0068] Sub-step 12: performing semantic analysis on the user input content to obtain multiple control intention information;

[0069] Sub-step 13: Determine multiple control instructions corresponding to the multiple control intention information.

[0070] Single-Agent can also fuse input content from different channels (voice, gesture, touch) at the same time, and extract effective information from it through deep learning technology to ensure that the user's intention can be accurately understood. After the user inputs content through voice or gesture, the input content is semantically parsed to obtain multiple control intentions. For example, the user inputs "turn on the air conditioner" through voice and adjusts the volume through gesture at the same time. Single-Agent can fuse the content input from the two channels of voice input and gesture input, and extract effective information from them, that is, extract multiple control intention information "turn on the air conditioner" and "adjust the volume". The fusion of Single-Agent further improves the robustness and accuracy of instruction acquisition. After obtaining multiple control intention information, the corresponding control instructions can be determined. The control instructions can be pre-stored instruction codes. For example, the control instruction corresponding to "turn on the air conditioner" is "003" and the control instruction corresponding to "adjust the volume" is "005".

[0071] In some embodiments of the present application, confirmation operations can also be performed on specific control instructions. Specifically, confirmation is performed when performing key operations to avoid misoperation and improve user satisfaction and safety. For example, when the user starts long-distance navigation, the user confirms the operation through voice, "The long-distance navigation route is about to be started, please confirm whether you need service area recommendations along the way?"; when the user closes all windows, the confirmation operation is "You are about to close all windows in the cabin, do you want to continue with this operation?"; when the user deletes all travel records, the confirmation operation is "Are you sure to delete all travel records? Once deleted, they cannot be restored."

[0072] In other embodiments of the present application, guiding prompt words may be provided to the user in response to the user's input operation. For example, in response to the user's ambiguous voice command "It's too noisy", guiding prompt words may be provided, such as "Do you need to lower the music volume?".

[0073] In other embodiments of the present application, the Single-Agent agent can be a trained vehicle-side model. In a specific implementation, the vehicle-side model can plan the human setting prompt words for the model in advance during the training process or before being deployed to the vehicle-side, build the role characteristics of the vehicle-side model, customize the dialogue style, and realize anthropomorphic intelligent interaction in multiple scenarios. The vehicle-side model can be given a personality through the human setting prompt words, and its speech and behavior style and emotional tone can be clarified to adapt to the target interaction scenario. For example, the vehicle-side model can be set with the human setting prompt words "You are a professional and humorous assistant who can always find appropriate solutions when facing problems and can bring a relaxed atmosphere.", "Your tone is always friendly but not overly enthusiastic, adapting to different situations, and respecting the user's emotional state.", "If the user is depressed, you will gently encourage them and recommend some suitable music or activities to relax." The vehicle-side model can also be set with a context-awareness function through context-awareness prompt words, and the vehicle-side model can be set to adjust the dialogue content according to the scene, such as driving mode, work mode or leisure mode. For example, context-aware prompts can be "When you are in driving mode, keep it simple and focused, and mainly provide navigation and driving assistance.", "When users ask about weather or road conditions, please give priority to providing relevant information and simplify other unnecessary content", "Users want to relax, you can recommend music, tell jokes or introduce activities in a more relaxed and pleasant tone". Emotion-guiding prompts can also be used to guide the vehicle-side model to identify user emotions, make appropriate responses or actively adjust the atmosphere. For example, emotion-guiding prompts can be "When it is detected that the user is in a low mood, talk to them in a comforting tone and provide soothing options, such as playing soothing music", "When the user shows anger, respond in a calm tone to help them gradually calm down", "If the user is in a good mood, you can agree moderately and recommend some activities to add fun". Personalized feedback prompts can also be used to guide the vehicle-side model to provide tailored answers or suggestions based on the user's history and preferences. For example, personalized feedback prompts may be "Please recommend travel destinations that users may be interested in based on their favorite routes.", "If you detect that the user plays a specific music list every Monday, please ask the user whether to continue playing the list.", "If the user is accustomed to a specific air-conditioning temperature, automatically adjust it and prompt: 'I have set the temperature to your favorite 22 degrees.'" The embodiments of the present application use a variety of set prompts to enable the vehicle-side model to have role-playing characteristics when interacting with the user, and dynamically adjust behavior according to the user's emotions, scenarios, and personalized needs.

[0074] Step 202: respectively determining urgency indicators and resource requirement information of a plurality of control instructions, and determining resource usage information of a plurality of subsystems;

[0075] In some embodiments of the present application, the control instruction includes target control state information, and step 202 may include the following sub-steps:

[0076] Sub-step 21: Determine the target subsystem to which each of the control instructions is directed.

[0077] The control instructions are used to control a subsystem according to user needs; therefore, it is necessary to determine the target subsystem for each control instruction. For example, when the user needs to "turn on the air conditioner" and "adjust the volume", the target subsystems for the control instructions are "air conditioning system" and "audio system" respectively.

[0078] Sub-step 22: Acquire current status information of the target subsystem.

[0079] After determining the target subsystem for the control instruction, it is necessary to determine the current status information of the target subsystem. Since the Single-Agent is connected to each subsystem in the embodiment of the present application, the current status information of each subsystem can be obtained.

[0080] Sub-step 23: Determine the resource requirement information of the multiple control instructions based on the current state information and the target control state information.

[0081] The current state information refers to the current state of the system, for example, the air conditioning system is currently in the on state or off state, if it is in the on state, what is the current temperature; the current volume of the audio system is what. The target control state refers to the state information that the user wants to adjust, for example, the user wants to adjust the temperature to "26℃" and the volume to 15.

[0082] Therefore, the resource requirement information of each control instruction can be determined based on the current status information of each subsystem and the target control status information that the user wants to achieve. For example, if the current cabin temperature is 31° and the user wants to adjust it to 26°, the resource requirement information can be determined based on the temperature difference and the outside temperature. Alternatively, if the user is driving and the navigation is turned off, and at a certain moment the user instructs to turn on the navigation through a control instruction, the CPU resource information, GPU resource information, and communication resources required to turn on the navigation need to be determined.

[0083] In some embodiments of the present application, the urgency indicator includes a preset security level, and step 202 may also include the following sub-steps:

[0084] Sub-step 31: searching a preset association table according to the plurality of control instructions to obtain preset security levels corresponding to the plurality of control instructions respectively.

[0085] The urgency index refers to the urgency level of the control instruction, including the preset safety level, wherein the preset association table is used to store the association between the control instruction and the preset safety level. For example, the safety instruction when the vehicle collides is the highest safety level, the navigation is turned on and the navigation is updated as the second safety level, the air conditioning is turned on as the third safety level, the volume is adjusted as the fourth safety level, and the air conditioning temperature is adjusted as the fifth safety level. Therefore, the preset association table can be searched according to the control instruction to obtain the corresponding preset safety level, and the preset safety level is determined as the urgency index, such as the urgency index of the air conditioning temperature adjustment control instruction is the fifth safety level, and the urgency index of the navigation turn-on control instruction is the highest safety level. When calculating the urgency index, in order to reflect that the higher the safety level, the higher the priority, and the lower the safety level, the lower the priority, the specific value corresponding to the fifth safety level can be 1, and the specific value corresponding to the first safety level can be 5.

[0086] In other embodiments of the present application, the urgency index may also include the user's demand level for control instructions. For example, if the user frequently issues the voice command "adjust the air conditioner to 23°", the urgency index corresponding to the air conditioner temperature adjustment control instruction can be dynamically adjusted to 3, that is, adjusted to the third safety level. It should be noted that this is only to meet the dynamic adjustment made by the user, and the preset association table is not adjusted.

[0087] Step 203: Determine the target execution priorities corresponding to the multiple control instructions respectively by combining the urgency index, the resource demand information, and the resource usage information;

[0088] In some implementations of this example, Single-Agent can assign priorities to commands based on the urgency of user needs, resource demand information, the current state of the cabin, and the availability of system resources. For example, safety-related commands (such as navigation and alarms) will be executed first, while entertainment commands can be executed later. Specifically, Single-Agent monitors in-car environmental parameters in real time, such as temperature, humidity, air quality, etc.; and monitors the status of the audio and navigation systems in real time, such as whether the currently playing audio and navigation are updated.

[0089] When the user issues the "turn on the air conditioner" command and operates the volume adjustment, if the navigation is updated at the same time, the navigation update control command is assigned the highest priority, the air conditioner is assigned the second highest priority, and the volume adjustment is assigned the lowest priority, ensuring that each subsystem works together according to the target execution priority. For example, if the user requests navigation and adjusts the cabin temperature at the same time, but the cabin temperature is too high at this time, the air conditioner adjustment command will be set to a higher priority and the navigation turn-on command will be set to a lower priority. In addition, when the vehicle receives a collision alert, the system immediately interrupts all non-emergency tasks and sets the safety command to the highest priority to ensure that the safety command is executed first.

[0090] Step 204: scheduling multiple subsystems to perform collaborative operations according to multiple control instructions according to the target execution priority;

[0091] In some embodiments of the present application, step 204 may include the following sub-steps:

[0092] Sub-step 41: Obtaining the user's historical preference information for each of the subsystems;

[0093] Sub-step 42: Scheduling the plurality of subsystems to adopt the user historical preference information and execute the plurality of control instructions.

[0094] Among them, user historical preference information refers to the preferences and habits that users have shown when using various subsystems in the past. For example, after the user adjusts the temperature of the air conditioner many times, the system can learn that the user's temperature preference is 23 degrees in summer, and actively optimize the temperature adjustment parameters to 23 degrees during the control instruction planning and execution process. For another example, if a user goes from A to B and often rests at the rest stop at C, when providing navigation planning for the user, the ACB route planning navigation can be provided to the user first.

[0095] In other embodiments of the present application, confirmation information can also be provided to the user when saving the user's historical preference information or executing a control command based on the historical preference information, for example, "I have observed that you have frequently adjusted the volume recently. Do you need to save the current setting as the new default value?", "I have detected that the traffic at your frequently visited destination has changed. Do you need to recommend a faster route for you?", "Based on your music preferences, I have updated the recommended playlist for this week. Do you want to play it now?". Through continuous learning and optimization, the vehicle-side model can provide accurate and considerate services, bringing a natural, intelligent and humanized interactive experience.

[0096] In some embodiments of the present application, step 204 may further include the following sub-steps:

[0097] Sub-step 51: obtaining post-execution status information of the target subsystem;

[0098] Sub-step 52: Determine execution feedback information based on the post-execution state information and the target control state information, and feed back the execution feedback information to the user.

[0099] Among them, the post-execution state information refers to the state information actually reached by the vehicle subsystem after executing the user control command. Based on the post-execution state information and the target control state information, it can be determined whether the execution is in place, and whether the execution is in place can be fed back to the user as feedback information, so that the user can get feedback information in time and improve the vehicle experience.

[0100] In some implementations of this embodiment, during the execution process, the Single-Agent will continuously monitor the operating status of each subsystem to ensure that all tasks are executed as planned, and feedback information on whether the tasks are executed as planned will be fed back to the user. For example, whether the temperature adjustment of the air conditioner has reached the expected level, whether the volume of the audio system is adjusted according to the instructions, whether the navigation accurately broadcasts the route, etc. For example, when the user expects to adjust the temperature to 23°, the temperature is adjusted to 25° due to insufficient power, and feedback is given to the user that "the power supply is insufficient, adjust the temperature to 25°".

[0101] Step 205: Obtain vehicle external environment information.

[0102] Among them, vehicle external environment information refers to various data and states of the surrounding environment perceived by the vehicle during driving. This information is crucial for vehicle navigation, safety, driving assistance and other functions. Vehicle external environment information is usually collected through various sensors and devices, including but not limited to cameras, radars, lidars, ultrasonic sensors, GPS, etc. Lidars obtain high-precision distance information by emitting laser beams and measuring the reflection time, which is used for environmental modeling in autonomous driving systems.

[0103] In some implementations of this embodiment, the vehicle external environment information is acquired by integrating data from various sensors.

[0104] Step 206: When it is determined that the vehicle external environment information has changed, the target execution priority is adjusted according to the external environment information to obtain an adjusted target execution priority;

[0105] In some implementations of this embodiment, the external environment (such as external temperature changes, vehicle speed changes) is monitored in real time through a variety of sensors to automatically adjust the air conditioning and audio settings. The vehicle position is monitored in real time through radar, camera and GPS (Global Positioning System). If the agent assigns the highest, second highest and lowest priorities to the user's "adjust volume", "adjust air conditioning" and "adjust lights" in turn, if it is detected that the vehicle enters a tunnel, the priority of the light adjustment control instruction is adjusted to the highest, and the priority of "adjust volume" is adjusted to the lowest.

[0106] In some embodiments of the present application, the control instructions can also be adjusted according to the external environmental information of the vehicle. For example, after the user issues the command "Please turn up the volume" in a noisy environment, the vehicle assigns it the command "Adjust the volume to 30" but does not execute it. The next moment, the vehicle enters a quieter area. The system will integrate the current environmental data and adjust the volume control command to "Adjust the volume to 25", providing the user with more reasonable command control based on environmental information.

[0107] Step 207: According to the adjusted target priority, multiple subsystems are scheduled to work collaboratively according to multiple control instructions.

[0108] After the target execution priority is adjusted in the above step 206, an adjusted target priority is obtained. If it is detected that a vehicle enters a tunnel, the priority of adjusting the lighting control instruction is adjusted to the highest, and the priority of "adjusting the volume" is adjusted to the lowest. The present application adopts the adjusted target priority and dispatches multiple subsystems to coordinate according to the control instruction. When the vehicle enters the tunnel, the brightness of the lights in the car is first increased to ensure safe driving, and the air conditioner is appropriately adjusted to adapt to the confined space of the tunnel. Finally, the volume is adjusted to meet user needs and make real-time adjustments according to environmental conditions to ensure driving safety.

[0109] In some embodiments of the present application, Single-Agent continuously collects feedback data while coordinating with various subsystems to execute instructions, including but not limited to user behavior, cabin environment, system performance, etc. By analyzing these data, Single-Agent can identify potential problems or optimization points in execution. Based on feedback information, Single-Agent can optimize instruction planning and execution logic. For example, after a user adjusts the temperature of the air conditioner multiple times, the system can learn the user's temperature preference and actively optimize the temperature adjustment parameters in future instructions. Through continuous adaptive optimization, Single-Agent can respond to user needs more accurately and quickly, reduce the need for users to repeatedly issue instructions, and thus greatly improve the overall experience of the smart cockpit.

[0110] Figure 3The overall flow chart of instruction planning and execution provided for some embodiments of the present application is as follows: Figure 3 As shown, command collection and analysis refers to the collection and analysis of control commands input by users in the cockpit; command planning refers to planning multiple control commands input by users or adjusting commands for the vehicle according to the external environment of the vehicle; command execution and monitoring refers to the process in which the vehicle-side model continuously monitors the internal and external states of the vehicle during command execution, and makes real-time adjustments based on this status information to ensure the orderly execution of commands to meet user needs and ensure vehicle safety; adaptive optimization and feedback refers to learning user behavior through a learning mechanism and optimizing the vehicle-side model based on the user's common behavior, and providing instant feedback to the user.

[0111] The embodiment of the present application determines multiple control instructions by responding to the user's input operation, wherein the multiple control instructions include control instructions for different subsystems, respectively determine the urgency index and resource demand information of the multiple control instructions, and determine the resource usage information of the multiple subsystems, and respectively determine the target execution priority corresponding to the multiple control instructions in combination with the urgency index, resource demand information, and resource usage information. According to the target execution priority, the multiple subsystems are scheduled to work in coordination according to the multiple control instructions, providing a unified and efficient instruction processing mechanism, and effectively avoiding the complex coordination and conflict within the multiple subsystems in the vehicle. Supporting control instructions of multiple input methods is convenient for user operation; accurately identifying the control instructions input by the user in multiple input methods through the language understanding model, setting the priority of the control instructions according to the status of each subsystem and the resource demand information, ensuring that the execution of the control instructions can meet the needs of the user and ensure a reasonable priority. Using historical preference information to execute control instructions can save the time of the user inputting the control instructions and simplify the user operation; continuously monitoring the status of each subsystem and the external environment information of the vehicle, adjusting the priority of the control instructions, ensuring the safety of the vehicle and ensuring the reasonable satisfaction of the user's needs. In addition, the agent in this application has role-based characteristics and dynamically adjusts its behavior according to the user's emotions, scenarios, and personalized needs. Through continuous learning and optimization, the agent can provide accurate and considerate services, bring a natural, intelligent, and personified interactive experience, and further enhance the user experience.

[0112] It should be noted that, for the method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present application are not limited by the described order of actions, because according to the embodiments of the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present application.

[0113] Reference Figure 4, shows a schematic diagram of the structure of a vehicle control device provided in some embodiments of the present application, which may specifically include the following modules:

[0114] The input response module 401 is configured to determine a plurality of control instructions in response to an input operation of a user; wherein the plurality of control instructions include control instructions for different subsystems;

[0115] The resource determination module 402 is configured to respectively determine the urgency indicators and resource requirement information of the plurality of control instructions, and determine the resource usage information of the plurality of subsystems;

[0116] The priority determination module 403 is configured to determine the target execution priorities corresponding to the multiple control instructions respectively in combination with the urgency index, the resource demand information, and the resource usage information;

[0117] The scheduling module 404 is configured to schedule the multiple subsystems to perform collaborative operations according to the multiple control instructions based on the target execution priority.

[0118] In an optional embodiment of the present application, the control instruction includes target control state information, and the resource determination module 402 includes:

[0119] A subsystem determination submodule is configured to determine a target subsystem for each of the control instructions;

[0120] A state acquisition submodule, configured to acquire current state information of the target subsystem;

[0121] The resource determination submodule is configured to determine the resource requirement information of the multiple control instructions according to the current state information and the target control state information.

[0122] In an optional embodiment of the present application, the scheduling module 404 includes:

[0123] A history information acquisition submodule, configured to acquire the user's history preference information for each of the subsystems;

[0124] The first scheduling submodule is configured to schedule the multiple subsystems to adopt the user historical preference information and execute the multiple control instructions.

[0125] In an optional embodiment of the present application, the device further includes:

[0126] A post-execution status acquisition module, configured to acquire post-execution status information of the target subsystem;

[0127] The information feedback module is configured to determine execution feedback information according to the post-execution state information and the target control state information, and feed back the execution feedback information to the user.

[0128] In an optional embodiment of the present application, the device further includes:

[0129] An external information acquisition module is configured to acquire vehicle external environment information;

[0130] A priority adjustment module is configured to adjust the target execution priority according to the external environment information when it is determined that the vehicle external environment information has changed, so as to obtain an adjusted target execution priority;

[0131] The second scheduling submodule is configured to schedule the multiple subsystems to perform collaborative operations according to the multiple control instructions based on the adjusted target priorities.

[0132] In an optional embodiment of the present application, the input response module 401 includes:

[0133] An input acquisition submodule is configured to acquire user input content, where the user input content is at least one of voice input, gesture input, touch input, and eye movement input;

[0134] A semantic analysis submodule is configured to perform semantic analysis on the user input content to obtain a plurality of control intention information;

[0135] The instruction determination submodule is configured to determine a plurality of control instructions corresponding to the plurality of control intention information.

[0136] In an optional embodiment of the present application, the urgency indicator includes a preset security level, and the resource determination module 402 includes:

[0137] The security level search submodule is configured to search a preset association table based on the multiple control instructions to obtain the preset security levels corresponding to the multiple control instructions respectively, wherein the preset association table is used to store the association between the control instructions and the preset security levels.

[0138] An embodiment of the present application also provides an electronic device, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor, and when the computer program is executed by the processor, the above vehicle control method is implemented.

[0139] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above vehicle control method is implemented.

[0140] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0141] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0142] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0143] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the embodiments of the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0144] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0145] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0146] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0147] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0148] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the above elements.

[0149] The above is a detailed introduction to the provided vehicle control method, device, vehicle and storage medium. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A vehicle control method, characterized in that: The vehicle is deployed with a plurality of subsystems and an agent connected to the plurality of subsystems, and the method comprises: In response to an input operation of a user, a plurality of control instructions are determined; wherein the plurality of control instructions include control instructions for different subsystems; respectively determining the urgency indicators and resource requirement information of the plurality of control instructions, and determining the resource usage information of the plurality of subsystems; Determine the target execution priorities corresponding to the multiple control instructions respectively in combination with the urgency index, the resource demand information, and the resource usage information; According to the target execution priority, the multiple subsystems are scheduled to perform collaborative operations according to the multiple control instructions.

2. The method according to claim 1, characterized in that The control instruction includes target control state information, and the urgency indicators and resource requirement information of the multiple control instructions are determined separately, including: Determine the target subsystem for each of the control instructions; Acquire current status information of the target subsystem; The resource requirement information of the plurality of control instructions is determined according to the current state information and the target control state information.

3. The method according to claim 1, characterized in that The scheduling the multiple subsystems to perform collaborative operations according to the multiple control instructions includes: Obtaining historical user preference information of the user for each of the subsystems; The plurality of subsystems are scheduled to adopt the user historical preference information to execute the plurality of control instructions.

4. The method according to claim 2, characterized in that: After scheduling the multiple subsystems to perform collaborative operations according to the multiple control instructions, the method further includes: Obtaining post-execution status information of the target subsystem; Execution feedback information is determined according to the post-execution state information and the target control state information, and the execution feedback information is fed back to the user.

5. The method according to claim 4, characterized in that The method further comprises: Obtain vehicle external environment information; When it is determined that the vehicle external environment information has changed, adjusting the target execution priority according to the external environment information to obtain an adjusted target execution priority; According to the adjusted target priorities, the multiple subsystems are scheduled to work collaboratively according to the multiple control instructions.

6. The method according to any one of claims 1 to 4, characterized in that: The step of determining a plurality of control instructions in response to an input operation of a user comprises: Acquire user input content, where the user input content is at least one of voice input, gesture input, touch input, and eye movement input; Performing semantic analysis on the user input content to obtain multiple control intention information; Determine a plurality of control instructions corresponding to the plurality of control intention information.

7. The method according to any one of claims 1 to 4, characterized in that: The urgency index includes a preset security level, and the respectively determining the urgency index and resource requirement information of the plurality of control instructions includes: According to the multiple control instructions, a preset association table is searched to obtain the preset security levels respectively corresponding to the multiple control instructions, wherein the preset association table is used to store the association relationship between the control instructions and the preset security levels.

8. A vehicle control device, characterized in that: The vehicle is deployed with a plurality of subsystems and an agent connected to the plurality of subsystems, and the device comprises: An input response module, configured to determine a plurality of control instructions in response to an input operation of a user; wherein the plurality of control instructions include control instructions for different subsystems; a resource determination module, configured to respectively determine the urgency indicators and resource requirement information of the plurality of control instructions, and determine resource usage information of the plurality of subsystems; a priority determination module configured to determine target execution priorities corresponding to the plurality of control instructions respectively in combination with the urgency indicator, the resource demand information, and the resource usage information; The scheduling module is configured to schedule the multiple subsystems to perform collaborative operations according to the multiple control instructions based on the target execution priority.

9. A vehicle, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the vehicle control method according to any one of claims 1 to 7 when executed by the processor.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the vehicle control method according to any one of claims 1 to 7 is implemented.

Images