Methods, apparatuses, devices, and media for controlling a vehicle

Abstract

The present disclosure relates to a method, apparatus, device and medium for controlling a vehicle. The method comprises obtaining scene information, the scene information being associated with a first component, and the first component being independent of the vehicle. The method further comprises in response to the vehicle not supporting the first component, obtaining a second component of the vehicle based on the scene information, the second component being functionally associated with the first component. The method further comprises controlling the vehicle by executing the second component. By the method of the embodiments of the present disclosure, other components functionally associated can be obtained when the vehicle lacks the component associated with the scene information, thereby enabling unified scene configuration across vehicle models.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle technology, and more specifically, to methods, apparatus, devices, and media for controlling vehicles. Background Technology

[0002] With the rapid development of intelligent connected vehicles, more and more intelligent vehicles are launching various intelligent vehicle scenario functions. These functions refer to the use of software-defined and intelligent control technologies to combine multiple previously independent components inside the vehicle, such as air conditioning, seats, lights, windows, and entertainment systems, with sensor data, user needs, and external environmental information. According to preset or real-time generated control logic, multiple components can work together to achieve coordinated operation. The core is to transform "single-function control" into "scenario-based service." In other words, in intelligent vehicle scenarios, users do not need to operate the air conditioning, adjust the seat, or select music separately. Instead, they can trigger multiple execution components of the vehicle with a single click through simple voice or interface commands to achieve specific scenario modes, thereby providing users with a more intelligent and personalized driving experience. Summary of the Invention

[0003] Embodiments of this disclosure provide a method, apparatus, device, and medium for controlling a vehicle.

[0004] In a first aspect of this disclosure, a method for controlling a vehicle is provided. The method includes acquiring scene information associated with the first component, and the first component being independent of the vehicle. The method further includes, in response to the vehicle not supporting the first component, acquiring a second component of the vehicle based on the scene information, the second component being functionally associated with the first component. The method also includes controlling the vehicle by executing the second component.

[0005] In a second aspect of this disclosure, an apparatus for controlling a vehicle is provided. The apparatus includes a scene information acquisition module configured to acquire scene information associated with a first component, the first component being independent of the vehicle. The apparatus also includes a second component acquisition module configured to acquire a second component of the vehicle, functionally associated with the first component, based on the scene information, in response to the vehicle not supporting the first component. The apparatus further includes a control module configured to control the vehicle by executing the second component.

[0006] In a third aspect of this disclosure, a controller is provided. The controller includes one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement a method for controlling a vehicle. The method includes acquiring scene information associated with a first component, and the first component being independent of the vehicle. The method further includes, in response to the vehicle not supporting the first component, acquiring a second component of the vehicle based on the scene information, the second component being functionally associated with the first component. The method further includes controlling the vehicle by executing the second component.

[0007] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores computer-executable instructions, which are executed by a processor to implement a method for controlling a vehicle. The method includes acquiring scene information associated with a first component, the first component being independent of the vehicle. The method further includes, in response to the vehicle not supporting the first component, acquiring a second component of the vehicle based on the scene information, the second component being functionally associated with the first component. The method further includes controlling the vehicle by executing the second component.

[0008] It should be understood that the description in the Summary of the Invention section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0009] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram of an example environment in which several embodiments of the present disclosure may be implemented is shown;

[0011] Figure 2 A flowchart of a method for controlling a vehicle according to some embodiments of the present disclosure is shown;

[0012] Figure 3 Example diagrams of a system for controlling a vehicle according to some embodiments of the present disclosure are shown;

[0013] Figure 4 A flowchart of a method for performing a second component according to some embodiments of the present disclosure is shown;

[0014] Figure 5 A flowchart of a method for generating a knowledge graph according to some embodiments of the present disclosure is shown;

[0015] Figure 6 Block diagrams of apparatus for controlling a vehicle according to some embodiments of the present disclosure are shown; and

[0016] Figure 7 A schematic block diagram of a controller according to some embodiments of the present disclosure is shown. Detailed Implementation

[0017] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0018] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0019] It is understood that all user-related data involved in this technical solution should be obtained and used only after authorization from the user. This means that if it is necessary to use a user's personal information in this technical solution, the user's explicit consent and authorization are required before obtaining this data; otherwise, no related data collection and use will be carried out. It should also be understood that when implementing this technical solution, relevant laws and regulations should be strictly followed in the process of data collection, use, and storage, and necessary technical measures should be taken to protect user data security and ensure the secure use of data.

[0020] As mentioned above, intelligent scene functions in vehicles allow users to trigger multiple vehicle components with a single click using simple voice or interface commands to achieve specific scene modes. However, to adapt to different vehicle models, developers need to write and test scene logic separately for each model, which not only increases development complexity but also raises maintenance costs. Furthermore, the implementation of intelligent scenes relies on specific component resources. While a user can use a scene on one vehicle model, it may fail on another due to a lack of corresponding hardware configuration or functional support. The system typically only provides error messages or pre-disables the option on the interface, resulting in a poor user experience. Moreover, while some vehicle models may lack the components specified for a particular scene, they may possess other functional components that can achieve similar effects. However, due to a lack of intelligent analysis and alternative strategies, these existing resources cannot be effectively utilized, leading to functional redundancy and wasted hardware resources.

[0021] Therefore, embodiments of this disclosure propose a scheme for controlling a vehicle. In embodiments of this disclosure, the method includes acquiring scene information associated with a first component, and the first component being independent of the vehicle. The method further includes, in response to the vehicle not supporting the first component, acquiring a second component of the vehicle based on the scene information, the second component being functionally associated with the first component. The method also includes controlling the vehicle by executing the second component. Through the method of embodiments of this disclosure, when the vehicle lacks a component associated with scene information, other functionally associated components can be acquired, thereby improving the user experience.

[0022] Figure 1 A schematic diagram of an example environment 100 in which various embodiments of this disclosure may be implemented is shown. For example... Figure 1 As shown, example environment 100 includes vehicle 102, which refers to any type of motorized or non-motorized vehicle capable of carrying people and / or goods and being mobile. Figure 1 As shown, vehicle 102 is illustrated as a car. It should be understood that although vehicle 102 is... Figure 1 The vehicle is illustrated as a sedan, but this is merely exemplary and far from limited to this; examples may also include buses, trucks, motorcycles, and electric vehicles. In some embodiments of this disclosure, vehicle 102 may include a controller, for example, a domain controller for the vehicle or an Advanced Driver Assistance Systems (ADAS) controller.

[0023] In environment 100, the controller of vehicle 102 can acquire scene information 104. Scene information 104 can include scene modes, which can be specific states reached by the vehicle. One scene mode can correspond to one scene script. The scene script defines a series of actions that the vehicle needs to perform, which can include adjusting the state of vehicle components. The scene script corresponding to scene information 104 can be pre-stored in the vehicle or obtained from a cloud server. Different vehicle models can be configured with the same set of scene scripts. Users can input scene information 104 through voice or a visual interface. In some examples, users can input scene requirements by issuing a voice command such as "turn on nap mode". In other examples, the vehicle's visual interface (e.g., the central control touch screen) can display one or more preset scene options. For example, preset scene options can include "changing room scene", "welcome scene", "sunshade scene" and "intelligent beauty scene", etc. Users can input corresponding scene requirements by selecting a preset scene option on the interface.

[0024] like Figure 1 As shown, scene information 104 is associated with component 106 (also referred to as the first component), and component 106 is independent of vehicle 102. Component 106 associated with scene information 104 is not specific to any particular vehicle model. For example, when scene information 104 is a "sunshade scene," component 106 could be a sunshade associated with the "sunshade scene," however, not all vehicles are equipped with sunshades. In environment 100, vehicle 102 does not support component 106, but it supports component 108, which is functionally associated with component 106. In some examples, if the scene requirement is to determine whether a seat is occupied, component 106 could be a seat occupancy sensor, and the associated component 108 could be a seatbelt or an in-vehicle occupant camera. In other examples, if the scene requirement is to determine the intensity of rain, component 106 could be a rain sensor, and the associated component 108 could be a windshield wiper. For example, if vehicle 102 does not have a sunshade, the controller of vehicle 102 can obtain component 108 (also referred to as a second component) included in vehicle 102 based on scene information 104. For example, component 108 could be a dimming awning functionally associated with the sunshade. In some examples, component 108 can be obtained by a model deployed in vehicle 102 based on scene information 104. The model can be a deep learning model that, after being trained on specific training data, is capable of inference. The model can be a multilayer perceptron model or other machine learning models implemented using neural network technology to obtain alternative components.

[0025] The vehicle 102 obtains the execution result 110 through the execution component 108. The execution result 110 can be the vehicle state after the scenario is implemented. For example, the execution result 110 can be "the sunroof glass turns dark and the light intensity inside the vehicle decreases".

[0026] In this way, vehicle 102 obtains component 108, which is functionally associated with component 106, so that there is no need to develop and maintain scene logic separately for each vehicle model. Only a unified scene definition needs to be maintained to adapt to all vehicle models. When users switch between different vehicle models, they can use the same set of scene instructions to achieve scene experience, thereby realizing unified scene configuration across vehicle models.

[0027] Figure 2 A flowchart of a method 200 for controlling a vehicle according to some embodiments of the present disclosure is shown. Method 200 can be performed by the vehicle. For example, method 200 can be performed by… Figure 1 Vehicle 102 is executing. (For example...) Figure 2 As shown, in box 202, method 200 includes acquiring scene information, which is associated with a first component and is independent of the vehicle. For example, in... Figure 1 In the environment 100 shown, vehicle 102 can acquire scene information 104, which is associated with component 106, and component 106 is independent of vehicle 102. Scene information 104 may include scene modes, which can be specific states reached by the vehicle. One scene mode can correspond to one scene script, which defines a series of actions that the vehicle needs to perform, including adjusting the state of vehicle components. The scene script corresponding to scene information 104 can be pre-stored in the vehicle or obtained from a cloud server. Different vehicle models can be configured with the same set of scene scripts. Users can input scene information 104 through voice or a visual interface. In some examples, users can input scene requirements by issuing a voice command such as "turn on nap mode". In other examples, the vehicle's visual interface (e.g., a central control touchscreen) can display one or more preset scene options. For example, preset scene options may include "changing room scene", "welcome scene", "sunshade scene", and "intelligent beauty scene", etc. Users can input corresponding scene requirements by selecting a preset scene option on the interface. When scene information 104 is a "sunshade scene", component 106 can be a sunshade curtain associated with the "sunshade scene".

[0028] In box 204, method 200 includes determining whether the vehicle supports the first component. If the vehicle supports the first component, the vehicle is controlled by executing the first component. If the vehicle does not support the first component, box 206 is executed, where a second component of the vehicle is obtained based on scene information. The second component is functionally associated with the first component. For example, in... Figure 1 In the environment 100 shown, the component 106 associated with the scene information 104 is not specific to a particular vehicle model. For example, when the scene information 104 is a "sunshade scene," component 106 could be a sunshade associated with the "sunshade scene," however, not all vehicles are equipped with sunshades. If vehicle 102 does not support component 106, for example, if vehicle 102 does not have a sunshade, then the controller of vehicle 102 can obtain component 108 (also referred to as a second component) included in vehicle 102 based on the scene information 104. Component 108 is functionally associated with component 106. For example, component 108 could be a dimming awning functionally associated with a sunshade.

[0029] In some examples, a model deployed on the vehicle can acquire the second component based on scene information. This model can be a deep learning model trained on specific training data, capable of inference. It can be a multilayer perceptron model or other machine learning models using neural network technology to acquire the replacement component. In some examples, the model can include a knowledge base, which can be a dynamic knowledge graph, a network containing semantic relationships. The knowledge base can include at least one of the following: vehicle model information, a function list, or function parameters. The vehicle model information is associated with the Vehicle Identification Number (VIN). The function list and parameters can be structured data, for example, ambient lighting: {Color: RGB (Red, Green, Blue) full color, Brightness: 0-100%, Area: Supports independent zone control}.

[0030] In box 208, method 200 includes controlling the vehicle by executing a second component. For example, in... Figure 1 In the environment 100 shown, the controller of vehicle 102 can control vehicle 102 through the execution component 108. For example, by executing the dimming sunroof, the sunroof glass of the vehicle can be darkened to reduce the light intensity inside the vehicle.

[0031] In this way, method 200 can obtain another component that is functionally related to the component, so that there is no need to develop and maintain scene logic separately for each vehicle model. Only a unified scene definition needs to be maintained to adapt to all vehicle models. When users switch between different vehicle models, they can use the same set of scene instructions to achieve the scene experience, thereby realizing a unified scene configuration across vehicle models.

[0032] Figure 3 Example diagrams of a system 300 for controlling a vehicle according to some embodiments of the present disclosure are shown. Figure 3As shown, system 300 may include a scenario application module 302, a vehicle networking control unit 304, a cloud 306, and left domain 322, right domain 324, and rear domain 326. The scenario application module 302 can process user scenario requirements, generate control commands for different domains, and drive the execution of components in the vehicle. In some embodiments, the scenario application module 302 can drive all vehicle body and cockpit hardware under the left, right, and rear three-area controllers based on the Controller Area Network (CAN) / Scalableservice-Oriented Middleware over IP (SomeIP) in-vehicle communication protocol. The vehicle networking control unit 304 can act as a communication gateway between the vehicle and the cloud 306, connecting the two systems. It can achieve data interaction between the vehicle and the cloud through an in-vehicle telematics box (TBOX), uploading vehicle operation data and scenario usage data, and receiving configuration updates and scenario definitions from the cloud 306. The cloud-based 306 can be used to provide backend support, such as data statistics, vehicle model adaptation, and remote operation and maintenance management.

[0033] like Figure 3 As shown, the scene application module 302 may include a vehicle-side inference module 308 and a scene execution engine 310. The scene execution engine 310 can provide an interaction channel with the user via voice or a user interface. For example, the interface may be a large in-vehicle screen, allowing the user to interact with it via touch. The scene execution engine 310 can also serve as an input source for the system 300, receiving natural language commands and scene selections from the user to obtain the user's scene requirements, such as... Figure 3 As shown, the scene execution engine 310 may include a scene script 316 and a scene parsing module 318. The scene parsing module 318 can perform semantic parsing on the scene information input by the user and extract the scene intent. It can parse ambiguous user commands into standardized scene requirement tags. For example, if the user issues a command for "rest mode", the scene parsing module 318 can break it down into a sequence of commands such as "recline the seat, close the windows, adjust to a comfortable temperature, dim the lights, and turn off unnecessary sound sources". The scene script 316 may include a series of scene-related condition listening and execution actions. It can define complete trigger conditions, execution sequence, component control parameters, priority, linkage logic, etc. Each scene can correspond to one scene script. For example, the scene script for the "welcome scene" may include action commands such as "unlock the vehicle, turn on the exterior lights, automatically recline the seat, and unfold the rearview mirror".

[0034] like Figure 3As shown, the vehicle-side inference module 308 may include a deep learning model. After being trained on specific training data, the model can perform inference. The model may be a multilayer perceptron model or other machine learning models implemented using neural network technology to obtain alternative parts. For example, it may be a lightweight Large Language Model (LLM) deployed on the vehicle side, which can be used for semantic extraction, model inference, and intelligent recommendation. In some examples, the model may include a knowledge base. The knowledge base may include at least one of vehicle model information, a function list, or function parameters. The vehicle model information is associated with the Vehicle Identification Number (VIN). The function list and parameters may be structured data, such as ambient lighting: {color: RGB (Red, Green, Blue) full color, brightness: 0-100%, area: supports independent control of zones}. In some embodiments of this disclosure, the vehicle-side inference module 308 may include a knowledge graph module 314 and an inference engine 312. The knowledge graph module 314 may include vehicle-specific structured knowledge, which can be a network containing semantic relationships. The knowledge graph module 314 can initiate a vehicle configuration information request to the vehicle database 320 of the vehicle network control unit 304, and complete the construction and dynamic updating of the knowledge graph by receiving the vehicle configuration list. The inference engine 312 can perform intelligent inference based on the semantic information of the scene output by the scene parsing module 318, combined with the knowledge of the knowledge graph module 314. For example, when the first component is unavailable, the inference engine 312 can query all components with similar functions in the knowledge graph, obtain alternative components, and dynamically optimize the scene execution logic to generate an executable scene script 316. In some embodiments, the inference engine 312 may output a prompt message (also referred to as a first prompt) indicating whether the alternative component is confirmed to be executed. This prompt message may include at least one of voice, text, or image. For example, the prompt message may be broadcast through the vehicle's voice system stating, "The current vehicle does not have a sunshade function; it is recommended to adjust the dimming sunroof to a dark state to achieve a sunshade effect." Based on the prompt message output by the inference engine 312, the user can input a command to confirm the execution of the alternative component (also referred to as a first command) through voice or interface interaction. For example, the vehicle's large screen may provide a confirmation button interface, allowing the user to confirm via touch or voice command. If the user confirms the execution of the alternative component, the scenario requirement is met by executing the alternative component. If the user refuses to execute the alternative component, the inference engine 312 may continue to match other alternative solutions or terminate the current scenario requirement.

[0035] In some embodiments of this disclosure, the vehicle network control unit 304 may include an on-board database 320, which may store configuration information for all vehicle models and the vehicle itself. The scenario application module 302 may read the vehicle's configuration list from the on-board database 320 when the vehicle is powered on, using the vehicle's unique VIN code as the unit. The vehicle's configuration list may include mappings between vehicle functional domains and vehicle components, and may include a function list and its detailed parameters to form a vehicle signal matrix. Then, the scenario application module 302 may classify the vehicle's functional components based on the vehicle's configuration information, form mapping relationships between functions, and map the mapping relationships between functions and vehicle model information into a knowledge graph to establish association relationships between vehicle models.

[0036] like Figure 3 As shown, system 300 may also include a left domain 322, a right domain 324, and a rear domain 326, which can be the controller execution layer of the whole vehicle domain. These domains receive control commands issued by the scene execution engine 310 via the CAN / SomeIP vehicle communication protocol. Different domains include different functional components in the vehicle. They can be controlled according to the physical zoning design logic of the vehicle's area controller, enabling control based on physical location. This shortens control links and wiring harness lengths, improving system response efficiency. For example, left domain 322 may include windows, exterior lights, rearview mirrors, and vehicle speed; right domain 324 may include core cabin comfort components such as seats, sunroof, wipers, and air conditioning; and rear domain 326 is responsible for functional components such as pedals, refrigerator, armrest box, and tailgate. System 300 generates control commands for components in the vehicle through scene scripts 316 in the scene execution engine 310, controlling the execution of these components and achieving cross-domain collaborative control.

[0037] In this way, the system 300 can intelligently analyze the vehicle's configuration list and the user's scenario requirements through the vehicle-side inference module 308, and automatically recommend alternative execution components. This can solve the problem of incompatibility in the same scenario on different models due to configuration differences. In addition, through model inference, the vehicle's functions can be fully explored, avoiding functional redundancy and resource waste. Furthermore, car manufacturers do not need to develop and maintain scenario logic separately for each model. They only need to maintain a unified scenario definition and vehicle-side model to adapt to all models, thereby reducing development and maintenance costs.

[0038] Figure 4 A flowchart illustrating a method for performing a second component according to some embodiments of the present disclosure is shown. Method 400 can be performed by a vehicle. For example, method 400 can be performed by… Figure 1 Vehicle 102 is executing. (For example...) Figure 4 As shown in box 402, method 400 may include semantic information for obtaining scene information. For example, in... Figure 1In the environment 100 shown, vehicle 102 can collect user voice commands or interface interaction commands. It can recognize user voice commands through a voice assistant or trigger a scene selection interface through the vehicle's interface buttons. In some examples, vehicle 102 can perform speech recognition and natural language processing on user commands, converting voice or interface commands into structured voice information and extracting the user's scene requirements.

[0039] In box 404, method 400 may include retrieving a knowledge graph from a model based on semantic information to obtain a second component of the vehicle. For example, in... Figure 1 In the environment 100 shown, vehicle 102 can use the vehicle-side model to combine user scenario requirements with a knowledge graph to reason and find semantically similar and functionally matching alternative components. The knowledge graph stores a functional relationship network between vehicle components. When the first component is unavailable, a search can be performed in the knowledge graph to find all semantically similar second components that can achieve the same scenario requirement. For example, for the scenario requirement of "reducing light intensity," the vehicle configuration can be queried first, and it can be found that the vehicle is not equipped with a sunshade (the first component). Then, nodes strongly related to the "shading" function can be queried in the knowledge graph, and the following candidate may be found: a dimming awning (function: adjusts light transmittance to directly block sunlight). Then, the model can combine semantic information to reason and recommend the dimming awning as the second component to achieve "shading."

[0040] In box 406, method 400 may include obtaining a scene script from a model based on the second component and scene information, for example, in... Figure 1 In the environment 100 shown, the vehicle 102 can obtain the scene script through the vehicle-side model based on the component 108 and the scene information 104. The scene script can be a sequence of instructions including specific parameters, action order and condition judgment.

[0041] In box 408, method 400 may include executing a second component based on a scene script, for example, in... Figure 1 In the environment 100 shown, vehicle 102 can, based on scene scripts, transform abstract instructions in the scene scripts into low-level control instructions for different domains and monitor the execution status. For example, by controlling the dimming sunroof, the interior light can be reduced.

[0042] In this way, Method 400 can adapt to the differences in component resources of different car models without the need to develop and maintain scenario logic separately for different car models, thereby reducing development and maintenance costs. Furthermore, by retrieving knowledge graphs through the model, the accuracy of model reasoning can be improved, thereby further enhancing the user experience.

[0043] Figure 5A flowchart of a method for generating a knowledge graph according to some embodiments of the present disclosure is shown. Method 500 can be performed by a vehicle. For example, method 500 can be performed by... Figure 1 Vehicle 102 is executing. (For example...) Figure 5 As shown in block 502, method 500 may include acquiring vehicle configuration information, which may include a mapping between vehicle functions and vehicle components. In some embodiments, after the vehicle is powered on, it uses the vehicle's unique VIN code as an index to read the list of functions supported by the vehicle model and their detailed parameters from the cloud, forming the vehicle's signal matrix. For example, the list of functions read by the vehicle may include: navigation module, audio module, air conditioning module, sunshade module, dimming sunroof module, etc. The vehicle may also acquire parameter information such as energy consumption limits, execution conditions, adjustable gears, and signal channels corresponding to each function. In some embodiments, when the vehicle's configuration information is updated, for example, when a new component is added to the vehicle, the vehicle can automatically acquire the latest vehicle function data, thereby ensuring the accuracy of the configuration information.

[0044] In box 504, method 500 may include classifying vehicle components based on configuration information. In some embodiments, components may be classified according to functional attributes, physical location, linkage logic, etc. For example, seats, air conditioners, sunroofs, and ambient lighting may be classified as cabin comfort components according to functional attributes, and vehicle components may be divided into left domain, right domain, rear domain, etc. according to physical location.

[0045] In box 506, method 500 may include generating a knowledge graph based on classification. For example, the knowledge graph may include entity nodes, relationship edges, and attribute labels. In some embodiments, the knowledge graph may include vehicle model information, functional relationships, etc., mapping vehicle model information to the knowledge graph to establish relationships between vehicle models, and classifying and summarizing vehicle functions to form mapping relationships between functions.

[0046] In this way, Method 500 can dynamically construct a knowledge graph corresponding to vehicle configuration, providing data support for subsequent model reasoning and multi-component collaborative linkage.

[0047] Figure 6 A block diagram of a device 600 for controlling a vehicle according to some embodiments of the present disclosure is shown. Figure 6 As shown, the device includes a scene information acquisition module 602, configured to acquire scene information associated with a first component, and the first component being independent of the vehicle. The device also includes a second component acquisition module 604, configured to acquire a second component of the vehicle based on the scene information in response to the vehicle not supporting the first component. The second component is functionally associated with the first component. The device further includes a control module 606, configured to control the vehicle by executing the second component.

[0048] In some embodiments, the vehicle includes a knowledge base, which includes at least one of vehicle model information, a list of features, or feature parameters.

[0049] In some embodiments, the knowledge base includes a knowledge graph, and the device 600 further includes a configuration information acquisition module configured to acquire vehicle configuration information, the configuration information including a mapping between vehicle functions and vehicle components. The device 600 also includes a classification module configured to classify vehicle components based on the configuration information. The device 600 further includes a knowledge graph generation module configured to generate a knowledge graph based on the classification.

[0050] In some embodiments, the second component acquisition module 604 includes a model usage module configured to acquire the vehicle's second component based on scene information in response to the vehicle not supporting the first component.

[0051] In some embodiments, the model using module includes a semantic information acquisition module, configured to acquire semantic information of the scene information. The model using module also includes a semantic information using module, configured to retrieve the second component of the vehicle from a knowledge graph based on the semantic information.

[0052] In some embodiments, the device 600 further includes a scene script acquisition module, configured to acquire a scene script from the model based on the second component and scene information. The device 600 also includes a scene script usage module, configured to execute the second component based on the scene script.

[0053] In some embodiments, the device 600 further includes a first prompt output module configured to output a first prompt, the first prompt being used to indicate the confirmation execution of the second component, the first prompt including at least one of voice, text, or image.

[0054] In some embodiments, the device 600 further includes a first instruction acquisition module configured to acquire a first instruction, the first instruction including at least one of a voice instruction or an interface input instruction. The device 600 also includes a second component execution module configured to execute a second component in response to the first instruction instructing the execution of the second component.

[0055] In some embodiments, the device 600 further includes a second prompt output module configured to output a second prompt, the second prompt being used to provide feedback on the execution result of the second component, the second prompt including at least one of voice, text, or image.

[0056] It is understood that by utilizing the device 600 of this disclosure, at least one of the many advantages achievable by the methods or processes described above can be realized. For example, the device 600 can intelligently analyze the vehicle's configuration list and the user's scenario requirements through the vehicle-side model, and automatically recommend alternative execution components, thereby solving the problem of incompatibility in the experience caused by configuration differences on different vehicle models for the same scenario. In addition, through model reasoning, the vehicle's functions can be fully explored, avoiding functional redundancy and resource waste. Furthermore, automakers do not need to develop and maintain scenario logic separately for each vehicle model; they only need to maintain a unified scenario definition and vehicle-side model to adapt to all vehicle models, thereby reducing development and maintenance costs.

[0057] Figure 7 A block diagram of a controller 700 that can implement various embodiments of the present disclosure is shown. The controller 700 may, for example, be disposed in a vehicle. Reference Figure 7 As shown, the controller 700 includes a processor 701, which can perform various appropriate actions and processes based on computer program instructions loaded into random access memory (RAM) 703 according to computer program instructions stored in read-only memory (ROM) 702. The RAM 703 may also store various programs and data required for the operation of the controller 700. The processor 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0058] Processor 701 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 701 performs the various methods and processes described above, such as method 200. For example, in some embodiments, method 200 may be implemented as a computer software program tangibly contained in a machine-readable medium. In some embodiments, part or all of the computer program may be loaded and / or mounted to controller 700 via ROM 702. When the computer program is loaded into RAM 703 and executed by processor 701, one or more steps of method 200 described above may be performed. Alternatively, in other embodiments, processor 701 may be configured to perform method 200 by any other suitable means (e.g., by means of firmware).

[0059] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload programmable logic devices (CPLDs), and so on.

[0060] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0061] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. Furthermore, although operations are depicted in a specific order, this should be understood as requiring that such operations be performed in the specific order shown or in sequential order, or requiring that all illustrated operations be performed to achieve the desired result. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the foregoing discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single implementation. Conversely, various features described in the context of a single implementation may also be implemented individually or in any suitable sub-combination in multiple implementations.

[0062] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A method for controlling a vehicle, comprising: Acquire scene information, which is associated with a first component and the first component is independent of the vehicle; In response to the vehicle not supporting the first component, a second component of the vehicle is obtained based on the scenario information, the second component being functionally associated with the first component; as well as The vehicle is controlled by executing the second component.

2. The method according to claim 1, wherein the vehicle includes a knowledge base, and the knowledge base includes at least one of vehicle model information, a function list, or function parameters.

3. The method according to claim 2, wherein the knowledge base includes a knowledge graph, and the method further includes: Obtain the configuration information of the vehicle, which includes the mapping between vehicle functions and vehicle components; Based on the configuration information, the vehicle components are classified; as well as The knowledge graph is generated based on the classification.

4. The method of claim 3, wherein in response to the vehicle not supporting the first component, obtaining the second component of the vehicle based on the scenario information comprises: In response to the vehicle not supporting the first component, the model obtains the second component of the vehicle based on the scene information.

5. The method of claim 4, wherein in response to the vehicle not supporting the first component, obtaining the second component of the vehicle by the model based on the scene information comprises: Obtain the semantic information of the scene information; as well as Based on the semantic information, the second component of the vehicle is obtained by retrieving the knowledge graph through the model.

6. The method of claim 5, further comprising: Based on the second component and the scene information, the scene script is obtained through the model; as well as Based on the scenario script, the second component is executed.

7. The method according to claim 1, further comprising: Output a first prompt, which is used to instruct the second component to confirm the execution. The first prompt may include at least one of voice, text, or image.

8. The method of claim 7, further comprising: Obtain a first instruction, wherein the first instruction includes at least one of a voice instruction or a user interface input instruction; as well as In response to the first instruction instructing the execution of the second component, the second component is executed.

9. The method according to claim 1, further comprising: A second prompt is output, which is used to provide feedback on the execution result of the second component. The second prompt may include at least one of voice, text, or image.

10. A device for controlling a vehicle, comprising: A scene information acquisition module is configured to acquire scene information, which is associated with a first component and the first component is independent of the vehicle. The second component acquisition module is configured to acquire a second component of the vehicle based on the scenario information in response to the vehicle not supporting the first component. The second component is functionally associated with the first component. as well as The control module is configured to control the vehicle by executing the second component.

11. A controller, comprising: At least one processor; as well as A memory coupled to the at least one processor and having instructions stored thereon, which, when executed by the at least one processor, cause the controller to perform the method according to any one of claims 1-9.

12. A computer-readable storage medium having stored thereon computer-executable instructions, wherein the computer-executable instructions are executed by a processor to implement the method according to any one of claims 1 to 9.

Images