Vehicle control method, device, equipment, vehicle, chip and storage medium

Abstract

This disclosure relates to a vehicle control method, apparatus, device, vehicle, chip, and storage medium, belonging to the field of intelligent driving technology. The method includes: acquiring input information for vehicle control; performing intent recognition on the input information to determine the user's vehicle control intent; determining a target vehicle control command from a set of vehicle control commands based on the user's vehicle control intent; and executing a vehicle control process related to the target vehicle control command. Leveraging the reasoning capabilities of a large language model, it can recognize flexible, varied, and comprehensive vehicle control intents, thereby accurately mapping diverse vehicle control intents to different vehicle control commands. When users control the vehicle using vehicle-related apps, they are not limited by the constraints of the limited controls displayed on the interface and can quickly and conveniently complete precise vehicle control based on the user's vehicle control intent. Furthermore, through intent recognition capabilities, diversified expansion of vehicle control functions can be achieved.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent driving technology, and in particular to a vehicle control method, device, electronic device, vehicle, chip, and storage medium. Background Technology

[0002] As intelligent connected vehicles become increasingly feature-rich, controlling them via applications (APPs) has become a standard function. Users can send control commands to their vehicles through these apps, allowing them to operate the vehicles without being inside the cabin, thus improving convenience. However, with the diversification of intelligent connected vehicle functions, achieving precise vehicle control through convenient operation within vehicle-specific apps has become a key concern. Summary of the Invention

[0003] This disclosure provides a vehicle control method, apparatus, electronic device, vehicle, chip, and storage medium to at least address the problem of how to achieve precise vehicle control through convenient operation in a vehicle-related app.

[0004] The technical solution disclosed herein is as follows:

[0005] According to a first aspect of the present disclosure, a vehicle control method is provided, comprising: Obtain input information for vehicle control; The input information is subjected to intent recognition to determine the user's intent to control the vehicle; Based on the user's vehicle control intention, determine the target vehicle control command from the set of vehicle control commands; The vehicle control process related to the target vehicle control command is executed on the vehicle.

[0006] According to a second aspect of the present disclosure, a vehicle control method is provided, comprising: Receive input information for vehicle control; The input information is subjected to intent recognition to determine the user's intent to control the vehicle; Based on the user's vehicle control intention, determine the target vehicle control command from the set of vehicle control commands; Trigger the vehicle to execute the vehicle control process related to the target vehicle control command.

[0007] According to a second aspect of the present disclosure, a vehicle control method is provided, comprising: Collect input information for vehicle control; The input information is sent to the server, and the input information is used by the server to perform intent recognition in order to determine the user's intent to control the vehicle; The system receives a target vehicle control command sent by the server. The target vehicle control command is determined based on the user's vehicle control intention and is used to trigger the vehicle to execute a vehicle control process related to the target vehicle control command.

[0008] According to a fourth aspect of the present disclosure, a vehicle control device is provided, comprising: The acquisition module is configured to acquire input information for vehicle control. The first determining module is configured to perform intent recognition on the input information to determine the user's vehicle control intent; The second determining module is configured to determine the target vehicle control instruction from the set of vehicle control instructions based on the user's vehicle control intention; The control module is configured to execute vehicle control procedures related to the target vehicle control command.

[0009] According to a fifth aspect of the present disclosure, a vehicle control device is provided, suitable for a server, comprising: The receiving module is configured to receive input information for vehicle control. The recognition module is configured to perform intent recognition on the input information to determine the user's intent to control the vehicle; The determination module is configured to determine the target vehicle control command from the set of vehicle control commands based on the user's vehicle control intention; The trigger module is configured to execute the vehicle control process related to the target vehicle control command.

[0010] According to a sixth aspect of the present disclosure, a vehicle control device is provided, comprising: The data acquisition module is configured to collect input information for vehicle control. The transceiver module is configured to send the input information to the server, receive the target vehicle control command sent by the server, and send the target vehicle control command to the vehicle. The input information is used to perform intent recognition through the server to determine the user's vehicle control intent, and the user's vehicle control intent is used to determine the target vehicle control instruction from the set of vehicle control instructions. The target vehicle control command is used to instruct the vehicle to perform a vehicle control process related to the target vehicle control command.

[0011] According to a seventh aspect of the present disclosure, a vehicle is provided, including a processor and a memory for storing processor-executable instructions; The processor is configured to implement the steps of the vehicle control method described in the first to third aspects of the present disclosure to control the vehicle.

[0012] According to an eighth aspect of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements the steps of the vehicle control method described in the first to third aspects of the present disclosure.

[0013] According to a ninth aspect of the present disclosure, a computer-readable storage medium is provided having computer program instructions stored thereon, which, when executed by a processor, implement the steps of the vehicle control method described in the first to third aspects of the present disclosure.

[0014] According to a tenth aspect of the present disclosure, a chip is provided, the chip including an interface circuit and a processing circuit coupled to each other, the interface circuit being used to input or output signals, and the processing circuit being configured to implement the steps of the vehicle control method described in the first to third aspects of the present disclosure.

[0015] According to an eleventh aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the vehicle control method described in the first to third aspects of the present disclosure.

[0016] The technical solutions provided by the embodiments of this disclosure bring at least the following beneficial effects: Leveraging the reasoning capabilities of large language models, the system can recognize flexible, diverse, and comprehensive vehicle control intentions. This allows for the mapping of these intentions to control commands, enabling users to control their vehicles via apps without being limited by the app's interface. Users can quickly and easily input and output their control intentions, achieving precise vehicle control. Furthermore, the intent recognition capabilities of large language models support the diversified expansion of vehicle control functions, allowing apps to support all executable vehicle control capabilities, thereby comprehensively improving user convenience and experience.

[0017] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0019] Figure 1 This is a schematic flowchart illustrating a vehicle control method according to an exemplary embodiment; Figure 2This is a schematic flowchart illustrating a vehicle control method according to another exemplary embodiment; Figure 3 This is an interactive schematic diagram of vehicle control according to another exemplary embodiment; Figure 4 This is a schematic flowchart illustrating a vehicle control method according to another exemplary embodiment; Figure 5 This is a schematic diagram illustrating a vehicle control function operation interface according to another exemplary embodiment; Figure 6 This is a schematic flowchart illustrating a vehicle control method according to another exemplary embodiment; Figure 7 This is a schematic flowchart illustrating a vehicle control method according to another exemplary embodiment; Figure 8 This is a schematic flowchart illustrating a vehicle control method according to another exemplary embodiment; Figure 9 This is a schematic flowchart illustrating a vehicle control method according to another exemplary embodiment; Figure 10 This is an interactive schematic diagram illustrating a vehicle control method according to another exemplary embodiment; Figure 11 This is a schematic diagram of the structure of a vehicle control device according to an exemplary embodiment; Figure 12 This is a schematic diagram of the structure of a vehicle control device according to another exemplary embodiment; Figure 13 This is a schematic diagram of the structure of a vehicle control device according to another exemplary embodiment; Figure 14 This is a schematic diagram of the structure of an electronic device according to an exemplary embodiment; Figure 15 This is a schematic diagram of the structure of a vehicle according to an exemplary embodiment; Figure 16 This is a schematic diagram of the structure of a chip according to an exemplary embodiment. Detailed Implementation

[0020] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0021] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0022] The vehicle control method, apparatus, electronic device, vehicle, chip, and storage medium of the present disclosure are described below with reference to the accompanying drawings.

[0023] Figure 1 This is a schematic flowchart illustrating a vehicle control method according to an exemplary embodiment.

[0024] It should be noted that the vehicle control method of this disclosure is executed by a hardware device with data processing capabilities and / or the necessary software to drive the hardware device. For example, it can be executed by a vehicle control device of this disclosure, which can be configured in any electronic device to execute the vehicle control method of this disclosure.

[0025] In any embodiment of this application, the electronic device may include a terminal, a vehicle (such as an in-vehicle terminal or in-vehicle controller), a chip, in-vehicle services, terminal devices, and servers. Optionally, the in-vehicle controller may include a VCU (Vehicle Control Unit), which may include a smart cockpit domain controller or a smart driving domain controller. In-vehicle services may include noise reduction services and smart driving services. Optionally, a vehicle-related app for vehicle control may be installed on the terminal device, which may include a user device, a mobile phone, a tablet, etc. Optionally, the server may be a cloud server, a distributed system server, or a server incorporating blockchain technology.

[0026] In any embodiment of this application, the chip can be integrated into an electronic device. The chip includes a Central Processing Unit (CPU), an Image Signal Processing (ISP), an Application-Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Field-Programmable Gate Array (FPGA), a System-on-Chip (SOC), a Reduced Instruction Set Computer (RISC), etc., which will not be listed here.

[0027] like Figure 1 As shown, the vehicle control method of this disclosure embodiment may include, but is not limited to, the following steps: S101, Obtain input information for vehicle control.

[0028] In some embodiments, the input information may include, but is not limited to: Voice information used for vehicle control; Text information used for vehicle control; The target control's control identification information and / or control description information, wherein the target control is the control that is operated on from among a plurality of pre-configured candidate controls for vehicle control.

[0029] In some embodiments, if the vehicle control method of this disclosure is executed by an application, it is understood that the application is a vehicle-related APP with vehicle control capabilities. A vehicle-related APP is an APP developed by a car manufacturer and possesses certain functions, such as the ability to collect input information for vehicle control, as well as the ability to process and send the input information. Optionally, the vehicle-related APP can be uploaded to an app store or a server or webpage related to the car manufacturer, and users can download and install the vehicle-related APP from the app store, the server, or the webpage.

[0030] In some embodiments, the application may invoke the information acquisition component of the terminal device to acquire input information for vehicle control. For example, if the input information is voice information for vehicle control, the information acquisition component is a voice acquisition component. Optionally, the voice acquisition component may be a microphone built into the terminal device, or a wired or wireless headset connected to the terminal device.

[0031] In some embodiments, a user can click or manipulate a control on the function operation page of the vehicle control app. The clicked or manipulated control is referred to as the target control, and the control identifier information and / or control description information of the target control are used as input information. It is understood that the function operation page of the vehicle control app can sequentially arrange icons of a limited number of candidate controls for vehicle control, such as icons for unlocking, locking, opening windows, and closing windows. The target control is the control that is manipulated from among the pre-configured multiple candidate controls for vehicle control.

[0032] In some embodiments, the process of acquiring voice information for vehicle control includes: waking up the voice assistant associated with the application, calling the application interface reserved for the voice assistant, and acquiring the voice information collected by the voice assistant through the reserved application interface. By inputting voice information through the voice assistant, the input information can be conveniently collected, thereby enabling remote control of the vehicle.

[0033] In some embodiments, if the vehicle control method of this disclosure is executed by a server, it can receive input information sent by an application. The application can call the information acquisition component of the terminal device to acquire input information for vehicle control and send the input information to the server.

[0034] In some embodiments, if the vehicle control method of this disclosure is executed by a vehicle, it can receive input information sent by an application. The application can call the information acquisition component of the terminal device to acquire the input information for vehicle control and send the input information to the vehicle.

[0035] In some embodiments, the application can communicate with the server and the vehicle through different communication links to send input information to the server and the vehicle respectively.

[0036] In some embodiments, the input information may carry the user's vehicle control intent, which can be a vehicle control intent described in natural language, such as "Please lower the vehicle a little." Optionally, the input information can be entered via keyboard typing, voice input, etc. It is understood that input information obtained through typing can be text information for vehicle control. Input information obtained through voice input can be voice information for vehicle control.

[0037] S102, perform intent recognition on the input information to determine the user's intent to control the vehicle.

[0038] In some embodiments, the input information can be fed into a pre-trained Large Language Model (LLM) for intent recognition, that is, the input information can be understood and reasoned through the large language model to obtain the user's vehicle control intent.

[0039] In some embodiments, if the vehicle control method of this disclosure is executed by an application, a lightweight large language model can be deployed on the terminal device where the application is located. After the input information is collected, the lightweight large language model can be called to understand and reason about the input information to obtain the user's vehicle control intention.

[0040] In some embodiments, if the vehicle control method of this disclosure is executed by a server, a fully pre-trained large language model can be deployed on the server. After obtaining the input information, the full large language model can be called to understand and reason about the input information to obtain the user's vehicle control intention.

[0041] In some embodiments, if the vehicle control method of this disclosure is executed by a vehicle, a lightweight large language model can be deployed on the vehicle. When input information is collected, the lightweight large language model can be invoked to understand and reason about the input information to obtain the user's vehicle control intention.

[0042] Understandably, deploying a lightweight large language model on terminal devices and vehicles can improve the efficiency of intent recognition and save time in transmitting input information to vehicle control commands. Conversely, deploying a full-scale large language model on servers can improve the accuracy of intent recognition, enabling precise vehicle control.

[0043] S103, based on the user's vehicle control intention, determines the target vehicle control command from the set of vehicle control commands.

[0044] In some embodiments, the vehicle control instruction set is a collection of candidate vehicle control instructions stored within the execution entity, which may include one or more candidate vehicle control instructions.

[0045] In some embodiments, after obtaining the user's vehicle control intention, a candidate vehicle control instruction that matches the user's vehicle control intention can be obtained from the set of vehicle control instructions and used as the target vehicle control instruction.

[0046] S104 executes the vehicle control process related to the target vehicle control command.

[0047] In some embodiments, a target vehicle control command can be sent to the vehicle, thereby causing the vehicle to respond to the target vehicle control command and execute a vehicle control process related to the target vehicle control command.

[0048] In some embodiments, if the vehicle control method of this disclosure is executed by an application, the application can send a target vehicle control command to the vehicle. Optionally, the application can send the target vehicle control command to the vehicle through the communication link between the terminal device and the vehicle.

[0049] In some embodiments, if the vehicle control method of this disclosure is executed by a server, the server can send a target vehicle control command to the vehicle. Optionally, the server can send the target vehicle control command to the vehicle through the communication link between the server and the vehicle.

[0050] In some embodiments, if the vehicle control method of this disclosure is executed by a vehicle, the vehicle can determine the actuator corresponding to the target vehicle control command, and then send the target vehicle control command to the actuator through the communication link between the vehicle and the actuator.

[0051] In this embodiment, leveraging the reasoning capabilities of a large language model, flexible and comprehensive vehicle control intentions can be identified. This allows for the mapping of diverse vehicle control intentions to control commands, enabling users to control their vehicles using vehicle-related apps without being limited by the app's interface. Users can quickly and conveniently input and output their vehicle control intentions, achieving precise vehicle control. Furthermore, the intent recognition capabilities of the large language model support diverse expansion of vehicle control functions, allowing the app to support all executable vehicle control capabilities, thereby comprehensively improving user convenience and experience.

[0052] Figure 2 This is a schematic flowchart illustrating a vehicle control method according to another exemplary embodiment.

[0053] like Figure 2 As shown, the vehicle control method of this disclosure embodiment may include, but is not limited to, the following steps: S201, Obtain input information for vehicle control.

[0054] The implementation method of step S201 can be any of the implementation methods in the various embodiments of this application, and will not be described in detail here.

[0055] S202, perform intent recognition on the input information to determine the user's intent to control the vehicle.

[0056] The implementation method of step S202 can be any of the implementation methods in the embodiments of this application, and will not be described in detail here.

[0057] S203, determine the description information of each candidate vehicle control command in the vehicle control command set.

[0058] In some embodiments, a set of vehicle control instructions and description information of each candidate vehicle control instruction in the set can be stored in advance within the execution entity. Optionally, the set of vehicle control instructions can be a list of control instructions, as shown in Table 1:

[0059] It is understood that each element in Table 1 exists independently. These elements are listed in the same table as an example, but this does not mean that all elements in the table must exist simultaneously as shown in the table. The value of each element is independent of the values ​​of any other element in Table 1. Therefore, those skilled in the art will understand that the value of each element in Table 1 is an independent embodiment.

[0060] In some embodiments, the set of vehicle control commands can be updated accordingly based on updates to the vehicle's intelligent functions, thereby meeting the diverse expansion needs of vehicle functions.

[0061] S204, Based on the user's vehicle control intent and the description information of the candidate vehicle control commands, determine the target vehicle control command from the set of vehicle control commands.

[0062] In some embodiments, the user's vehicle control intent can be matched with the description information of candidate vehicle control instructions to obtain candidate vehicle control instructions that match the user's vehicle control intent, which are then used as the target vehicle control instructions.

[0063] In some embodiments, the semantic similarity between the user's vehicle control intent and the description information of candidate vehicle control commands is obtained. Further, based on the semantic similarity, a target vehicle control command is determined from the set of vehicle control commands. Optionally, the candidate vehicle control command with the highest semantic similarity is selected as the target vehicle control command.

[0064] For example, if the input information is "Please help me lower the vehicle," the large language model can determine that the user's vehicle control intent corresponding to this input information is "lower the vehicle suspension." After obtaining this user's vehicle control intent, semantic similarity can be calculated between it and the description information of each candidate vehicle control command in Table 1. After determining the semantic similarity, the candidate vehicle control command with the highest semantic similarity can be selected from the set of vehicle control commands and designated as the target vehicle control command. In this example, the description information of the candidate vehicle control command "003" has the highest semantic similarity to the user's vehicle control intent "lower the vehicle suspension," and therefore, candidate vehicle control command "003" is selected as the target vehicle control command.

[0065] S205, executes vehicle control procedures related to the target vehicle control command.

[0066] The implementation method of step S205 can be any of the implementation methods in the embodiments of this application, and will not be described in detail here.

[0067] In this embodiment, leveraging the reasoning capabilities of a large language model, flexible and comprehensive vehicle control intentions can be identified. This allows for the mapping of diverse vehicle control intentions to control commands, enabling users to control their vehicles using vehicle-related apps without being limited by the app's interface. Users can quickly and conveniently input and output their vehicle control intentions, achieving precise vehicle control. Furthermore, the intent recognition capabilities of the large language model support diverse expansion of vehicle control functions, allowing the app to support all executable vehicle control capabilities, thereby improving overall user convenience and experience. Moreover, based on voice data collection within the app, remote voice control can be switched from the system level to the app level, providing support for controlling vehicles via vehicle-related apps on different brand terminal devices.

[0068] Figure 3 This is a schematic diagram illustrating an interaction for vehicle control according to another exemplary embodiment, such as... Figure 3 As shown, the interaction process for vehicle control includes a vehicle-related app, the vehicle, and a server (or cloud server).

[0069] In some embodiments, users can install vehicle-related apps on their terminal devices. It is understood that vehicle-related apps are apps developed by automakers that have certain functions, such as the ability to collect input information for vehicle control, as well as the ability to process and send that input information.

[0070] In some embodiments, vehicle-related apps can send vehicle control commands directly to the vehicle via a first communication link, i.e., wireless communication. Optionally, the first communication link may include, but is not limited to, short-range wireless communication methods such as Bluetooth, Ultra-Wideband (UWB), and Near Field Communication (NFC).

[0071] In some embodiments, vehicle-related apps can send vehicle control commands to the vehicle network server via a second communication link, i.e., network communication. Optionally, the second communication link may include, but is not limited to, network communication methods such as cellular communication and Wireless Fidelity (WiFi).

[0072] In some embodiments, the vehicle network server can send vehicle control commands to the vehicle via a third communication link, i.e., a network communication method. This third communication link may include, but is not limited to, network communication methods such as cellular communication and WiFi.

[0073] In some embodiments, the user's vehicle control commands may include, but are not limited to, unlocking, locking, turning on the air conditioning, and turning off the air conditioning.

[0074] Figure 4 This is a schematic flowchart illustrating a vehicle control method according to another exemplary embodiment.

[0075] like Figure 4 As shown, the vehicle control method of this disclosure embodiment is applicable to a server and may include, but is not limited to, the following steps: S401 receives input information for vehicle control.

[0076] In some embodiments, input information for vehicle control is received from an application.

[0077] In some embodiments, the application is a vehicle-related app installed by the user on a terminal device. It is understood that a vehicle-related app is an app developed by a car manufacturer that has certain functions, such as the ability to collect input information for vehicle control, as well as the ability to process and send that input information.

[0078] In some embodiments, the input information may include, but is not limited to: Voice information used for vehicle control; Text information used for vehicle control; The target control's control identification information and / or control description information, wherein the target control is the control that is operated on from among a plurality of pre-configured candidate controls for vehicle control.

[0079] In some embodiments, the application may invoke the information acquisition component of the terminal device to acquire input information for vehicle control. For example, if the input information is voice information for vehicle control, the information acquisition component is a voice acquisition component. Optionally, the voice acquisition component may be a microphone built into the terminal device, or a wired or wireless headset connected to the terminal device.

[0080] like Figure 5 The image shown is the operation page for vehicle control functions in a vehicle-related app. Figure 5 As shown, the operation page can arrange a limited number of candidate control icons for vehicle control in sequence. For example, it can include icons for unlocking, locking, opening windows, closing windows, etc.

[0081] In some embodiments, users can control the corresponding function of the vehicle by directly clicking the icon of one of the candidate controls. In scenarios where vehicle control is performed through a function operation page, the target control being operated can be detected, and the control identification information and / or control description information of the target control can be used as input information.

[0082] In some embodiments, users can wake up the voice assistant associated with the application and call the application interface reserved for the voice assistant. Through the reserved application interface, the user can obtain the voice information collected by the voice assistant and input the voice information through the voice assistant, thereby realizing convenient collection of input information and enabling remote control of the vehicle.

[0083] It should be noted that specific function operation pages often have a limited number of candidate controls for vehicle control. However, as vehicle control functions become increasingly sophisticated, the required number of controls far exceeds the number of candidate controls pre-configured on the page. For example, a vehicle might support adjusting the chassis suspension height via control commands to lower or raise the vehicle's chassis. Figure 5 As shown, the function operation page of vehicle-related apps lacks a corresponding control icon for suspension adjustment, which may prevent users from conveniently and efficiently controlling the vehicle through the application. To solve this problem, in this embodiment, the application can collect input information, and through the vehicle control intentions expressed in the input information, flexible and efficient control of the vehicle can be achieved.

[0084] In some embodiments, after an application collects input information, it can send the input information to a server, and the server can receive the input information sent by the application.

[0085] In some embodiments, the input information may carry the user's vehicle control intent, which can be a vehicle control intent described in natural language, such as "Please lower the vehicle a little." Optionally, the input information can be entered via keyboard typing, voice input, etc. It is understood that input information obtained through typing can be text information for vehicle control. Input information obtained through voice input can be voice information for vehicle control.

[0086] S402 performs intent recognition on the input information to determine the user's intent to control the vehicle.

[0087] In some embodiments, the input information can be fed into a pre-trained Large Language Model (LLM) for intent recognition, that is, the input information can be understood and reasoned through the large language model to obtain the user's vehicle control intent.

[0088] In some embodiments, after obtaining input information, a large language model deployed on the server can be invoked to understand and reason about the input information to obtain the user's vehicle control intention.

[0089] S403 determines the target vehicle control command from the set of vehicle control commands based on the user's vehicle control intention.

[0090] In some embodiments, the vehicle control instruction set is a collection of candidate vehicle control instructions stored within the execution entity, which may include one or more candidate vehicle control instructions.

[0091] In some embodiments, after obtaining the user's vehicle control intention, a candidate vehicle control instruction that matches the user's vehicle control intention can be obtained from the set of vehicle control instructions and used as the target vehicle control instruction.

[0092] S404 triggers the vehicle to execute the vehicle control process related to the target vehicle control command.

[0093] In some embodiments, a target vehicle control command can be sent to the vehicle, thereby causing the vehicle to respond to the target vehicle control command and execute a vehicle control process related to the target vehicle control command.

[0094] In some embodiments, the server can send a target vehicle control command to the vehicle. Optionally, the server can send the target vehicle control command to the vehicle through a third communication link between the server and the vehicle.

[0095] In some embodiments, the server may send a target vehicle control command to the application, and the application may further forward the target vehicle control command to the vehicle.

[0096] In some embodiments, such as Figure 3 As shown, the server can send target vehicle control commands to the vehicle-related app via a second communication link between the server and the app. Furthermore, the vehicle-related app sends target vehicle control commands to the vehicle via a first communication link with the vehicle.

[0097] In this embodiment, leveraging the reasoning capabilities of a large language model, flexible and comprehensive vehicle control intentions can be identified. This allows for the mapping of diverse vehicle control intentions to control commands, enabling users to control their vehicles using vehicle-related apps without being limited by the app's interface. Users can quickly and conveniently input and output their vehicle control intentions, achieving precise vehicle control. Furthermore, the intent recognition capabilities of the large language model support diverse expansion of vehicle control functions, allowing the app to support all executable vehicle control capabilities, thereby comprehensively improving user convenience and experience.

[0098] Figure 6This is a schematic flowchart illustrating a vehicle control method according to another exemplary embodiment.

[0099] like Figure 6 As shown, the vehicle control method of this disclosure embodiment is applicable to a server and may include, but is not limited to, the following steps: S601 receives input information for vehicle control sent by the application.

[0100] In some embodiments, voice information for vehicle control sent by an application is received. Optionally, the application collects voice information for vehicle control through the voice acquisition component of its terminal device and sends it to the server via a second communication link.

[0101] In some embodiments, text information for vehicle control sent by the application is received. Optionally, the application collects the text information for vehicle control via a text input component and sends it to the server via a second communication link. Optionally, the text input component can be a displayed text input dialog box, allowing text input via a keyboard.

[0102] In some embodiments, the application receives control identification information and / or control description information of a target control, wherein the target control is the control to be operated on from a plurality of pre-configured candidate controls for vehicle control, such as... Figure 5 As shown, the target control can be a window control. When the user clicks the window control, the application can determine the control identifier and / or control description of the window control as input information and send it to the server through the second communication link.

[0103] In some embodiments, users can wake up the voice assistant associated with the application and call the application interface reserved for the voice assistant. Through the reserved application interface, the user can obtain the voice information collected by the voice assistant and input the voice information through the voice assistant, thereby realizing convenient collection of input information and enabling remote control of the vehicle.

[0104] S602 performs intent recognition on the input information to determine the user's intent to control the vehicle.

[0105] The implementation method of step S602 can be any of the implementation methods in the various embodiments of this application, and will not be described in detail here.

[0106] S603, determine the description information of each candidate vehicle control command in the vehicle control command set.

[0107] In some embodiments, a set of vehicle control instructions and description information of each candidate vehicle control instruction in the set can be pre-stored in the server. Optionally, the set of vehicle control instructions can be a list of control instructions, as shown in Table 1, which will not be elaborated here.

[0108] S604: Based on the user's vehicle control intent and the description information of the candidate vehicle control commands, determine the target vehicle control command from the set of vehicle control commands.

[0109] In some embodiments, the user's vehicle control intent can be matched with the description information of candidate vehicle control instructions to obtain candidate vehicle control instructions that match the user's vehicle control intent, which are then used as the target vehicle control instructions.

[0110] In some embodiments, the semantic similarity between the user's vehicle control intention and the description information of the candidate vehicle control instructions is obtained, and further, the target vehicle control instruction is determined from the set of vehicle control instructions based on the semantic similarity.

[0111] For example, if the input information is "Please help me lower the vehicle," the large language model can determine that the user's vehicle control intent corresponding to this input information is "lower the vehicle suspension." After obtaining this user's vehicle control intent, semantic similarity can be calculated between it and the description information of each candidate vehicle control command in Table 1. After determining the semantic similarity, the candidate vehicle control command with the highest semantic similarity can be selected from the set of vehicle control commands and designated as the target vehicle control command. In this example, the description information of the candidate vehicle control command "003" has the highest semantic similarity to the user's vehicle control intent "lower the vehicle suspension," and therefore, candidate vehicle control command "003" is selected as the target vehicle control command.

[0112] S605 triggers the vehicle to execute the vehicle control process related to the target vehicle control command.

[0113] The implementation method of step S605 can be any of the implementation methods in the various embodiments of this application, and will not be described in detail here.

[0114] In this embodiment, leveraging the reasoning capabilities of a large language model, flexible and comprehensive vehicle control intentions can be identified. This allows for the mapping of diverse vehicle control intentions to control commands, enabling users to control their vehicles using vehicle-related apps without being limited by the app's interface. Users can quickly and conveniently input and output their vehicle control intentions, achieving precise vehicle control. Furthermore, the intent recognition capabilities of the large language model support diverse expansion of vehicle control functions, allowing the app to support all executable vehicle control capabilities, thereby improving overall user convenience and experience. Moreover, based on voice data collection within the app, remote voice control can be switched from the system level to the app level, providing support for controlling vehicles via vehicle-related apps on different brand terminal devices.

[0115] Figure 7 This is a flowchart illustrating a vehicle control method according to another exemplary embodiment. The vehicle control method of this disclosure is applicable to applications, and in some embodiments, the application is a vehicle-related APP installed by a user on a terminal device. It is understood that a vehicle-related APP is an APP developed by a car manufacturer with certain functions, such as the ability to collect input information for vehicle control, as well as the ability to process and send the input information.

[0116] like Figure 7 As shown, the vehicle control method of this disclosure embodiment may include, but is not limited to, the following steps: S701 collects input information for vehicle control.

[0117] In some embodiments, the input information may include, but is not limited to: Voice information used for vehicle control; Text information used for vehicle control; The target control's control identification information and / or control description information, wherein the target control is the control that is operated on from among a plurality of pre-configured candidate controls for vehicle control.

[0118] In some embodiments, the application may invoke the information acquisition component of the terminal device to acquire input information for vehicle control. For example, if the input information is voice information for vehicle control, the information acquisition component is a voice acquisition component. Optionally, the voice acquisition component may be a microphone built into the terminal device, or a wired or wireless headset connected to the terminal device.

[0119] like Figure 5 The image shown is the operation page for vehicle control functions in a vehicle-related app. Figure 5 As shown, the operation page can arrange a limited number of candidate control icons for vehicle control in sequence. For example, it can include icons for unlocking, locking, opening windows, closing windows, etc.

[0120] In some embodiments, users can control the corresponding function of the vehicle by directly clicking the icon of one of the candidate controls. In scenarios where vehicle control is performed through a function operation page, the target control being operated can be detected, and the control identification information and / or control description information of the target control can be used as input information.

[0121] In some embodiments, users can wake up the voice assistant associated with the application and call the application interface reserved for the voice assistant. Through the reserved application interface, the user can obtain the voice information collected by the voice assistant and input the voice information through the voice assistant, thereby realizing convenient collection of input information and enabling remote control of the vehicle.

[0122] S702 sends input information to the server.

[0123] In some embodiments, the input information is used for intent recognition via a large language model in the server to determine the user's intent to control the vehicle.

[0124] In some embodiments, the user's vehicle control intent is used to determine the target vehicle control instruction from the set of vehicle control instructions.

[0125] In some embodiments, after collecting input information, the application can send the input information to the server through a second communication link with the server.

[0126] In some embodiments, the input information can be fed into a pre-trained Large Language Model (LLM) for intent recognition, that is, the input information can be understood and reasoned through the large language model to obtain the user's vehicle control intent.

[0127] In some embodiments, after obtaining input information, the server can call a large language model deployed locally to understand and reason about the input information to obtain the user's vehicle control intention.

[0128] In some embodiments, the vehicle control instruction set is a collection of candidate vehicle control instructions stored within the execution entity, which may include one or more candidate vehicle control instructions.

[0129] In some embodiments, after obtaining the user's vehicle control intention, the server can obtain candidate vehicle control instructions that match the user's vehicle control intention from the set of vehicle control instructions, and use them as target vehicle control instructions.

[0130] In some embodiments, the server obtains the semantic similarity between the user's vehicle control intent and the description information of candidate vehicle control commands. Further, based on the semantic similarity, it determines the target vehicle control command from the set of vehicle control commands. Optionally, the candidate vehicle control command with the highest semantic similarity is selected as the target vehicle control command.

[0131] S703 receives the target vehicle control command sent by the server, wherein the target vehicle control command is used to instruct the vehicle to perform the vehicle control process related to the target vehicle control command.

[0132] In some embodiments, such as Figure 3 As shown, vehicle-related apps receive target vehicle control commands through a second communication link with the server.

[0133] S704 sends target vehicle control commands to the vehicle.

[0134] In some embodiments, such as Figure 3As shown, vehicle-related apps send target vehicle control commands to the vehicle through the first communication link between the app and the vehicle.

[0135] In this embodiment, leveraging the reasoning capabilities of a large language model, flexible and comprehensive vehicle control intentions can be identified. This allows for the mapping of diverse vehicle control intentions to control commands, enabling users to control their vehicles using vehicle-related apps without being limited by the app's interface. Users can quickly and conveniently input and output their vehicle control intentions, achieving precise vehicle control. Furthermore, the intent recognition capabilities of the large language model support diverse expansion of vehicle control functions, allowing the app to support all executable vehicle control capabilities, thereby comprehensively improving user convenience and experience.

[0136] Figure 8 This is a schematic flowchart illustrating a vehicle control method according to another exemplary embodiment.

[0137] like Figure 8 As shown, the vehicle control method of this disclosure embodiment is applicable to an application and may include, but is not limited to, the following steps: S801, in response to the operation of the pre-configured information acquisition control, starts the information acquisition component and acquires input information through the information acquisition component.

[0138] In some embodiments, voice capture controls and / or text capture controls can be added to the vehicle control function operation page of a vehicle-related app, such as... Figure 9 As shown.

[0139] In some embodiments, a user can click the voice acquisition control, and in response to the voice acquisition control being operated, the voice acquisition component is activated, and the voice acquisition component acquires voice information for vehicle control as input information.

[0140] In some embodiments, a user can tap to wake up the voice assistant and then use the voice assistant to invoke the voice acquisition control. Furthermore, the user can obtain the voice information collected by the voice assistant through the application programming interface reserved for the voice assistant.

[0141] In some embodiments, a user can click the text acquisition control, and in response to the text acquisition control being operated, the text input component is activated, and text information for vehicle control is acquired through the text input component as input information.

[0142] In this embodiment of the application, by adding one or both of the above two collection components to the function operation page, users can flexibly and conveniently collect input information carrying the intention to control the vehicle.

[0143] S802 sends input information to the server.

[0144] In some embodiments, the input information is used for intent recognition via a large language model in the server to determine the user's intent to control the vehicle.

[0145] In some embodiments, the user's vehicle control intent is used to determine the target vehicle control instruction from the set of vehicle control instructions.

[0146] The implementation method of step S802 can be any of the implementation methods in the various embodiments of this application, and will not be described in detail here.

[0147] S803 receives the target vehicle control command sent by the server, wherein the target vehicle control command is used to instruct the vehicle to perform the vehicle control process related to the target vehicle control command.

[0148] S804 sends the target vehicle control command to the vehicle.

[0149] The implementation of steps S803 to S804 can be any of the implementation methods in the embodiments of this application, and will not be described in detail here.

[0150] In this embodiment, leveraging the reasoning capabilities of a large language model, flexible and comprehensive vehicle control intentions can be identified. This allows for the mapping of diverse vehicle control intentions to control commands, enabling users to control their vehicles using vehicle-related apps without being limited by the app's interface. Users can quickly and conveniently input and output their vehicle control intentions, achieving precise vehicle control. Furthermore, the intent recognition capabilities of the large language model support diverse expansion of vehicle control functions, allowing the app to support all executable vehicle control capabilities, thereby improving overall user convenience and experience. Moreover, based on voice data collection within the app, remote voice control can be switched from the system level to the app level, providing support for controlling vehicles via vehicle-related apps on different brand terminal devices.

[0151] Figure 10 This is an interactive schematic diagram illustrating a vehicle control method according to another exemplary embodiment.

[0152] like Figure 10 As shown, the vehicle control method of this disclosure embodiment may include, but is not limited to, the following steps: S1001, the application collects input information.

[0153] In some embodiments, the application is a vehicle-related app installed by the user on a terminal device. It is understood that a vehicle-related app is an app developed by a car manufacturer that has certain functions, such as the ability to collect input information for vehicle control, as well as the ability to process and send that input information.

[0154] S1002, the application sends input information to the server.

[0155] In some embodiments, the server is a cloud server, which may be deployed with a pre-trained large language model.

[0156] S1003, the server uses a large language model to perform intent recognition on the input information to obtain the user's vehicle control intent.

[0157] S1004, the server determines the target vehicle control command based on the user's vehicle control intention.

[0158] S1005, the server sends the target vehicle control command to the application.

[0159] S1006, the application sends the target vehicle control command to the vehicle.

[0160] The implementation methods of steps S1001 to S1006 can be any of the implementation methods in the embodiments of this application, and will not be described in detail here.

[0161] In this embodiment, leveraging the reasoning capabilities of a large language model, flexible and comprehensive vehicle control intentions can be identified. This allows for the mapping of diverse control intentions to control commands, enabling users to control their vehicles using vehicle-related apps without being limited by the app's interface. Users can quickly and conveniently input and output their control intentions, achieving precise vehicle control. Furthermore, the intent recognition capabilities of the large language model support diverse expansion of vehicle control functions, allowing the app to support all executable vehicle control capabilities, thus improving overall user convenience and experience. Moreover, based on voice data collection within the app, remote voice control can be switched from the system level to the app level, supporting vehicle control via vehicle-related apps on different brand terminal devices.

[0162] Figure 11 This is a schematic diagram illustrating the structure of a vehicle control device according to an exemplary embodiment. (Refer to...) Figure 11 The vehicle control device 1100 of this embodiment includes an acquisition module 1101, a first determination module 1102, a second determination module 1103, and a control module 1104.

[0163] The acquisition module 1101 is configured to acquire input information for vehicle control. The first determining module 1102 is configured to perform intent recognition on the input information to determine the user's vehicle control intent; The second determining module 1103 is configured to determine the target vehicle control instruction from the set of vehicle control instructions based on the user's vehicle control intention; The control module 1104 is configured to execute a vehicle control process related to the target vehicle control command.

[0164] In some embodiments, the input information is at least one of the following: Voice information used for vehicle control; Text information used for vehicle control; The target control includes control identification information and / or control description information, wherein the target control is the control that is operated on from among a plurality of pre-configured candidate controls for vehicle control.

[0165] In some embodiments, the acquisition module 1101 is further configured to wake up the voice assistant and call the application programming interface reserved for the voice assistant; and acquire the voice information collected by the voice assistant through the reserved application programming interface.

[0166] In some embodiments, the second determining module 1103 is further configured to determine the description information of each candidate vehicle control instruction in the vehicle control instruction set; and determine the target vehicle control instruction from the vehicle control instruction set based on the user's vehicle control intention and the description information of the candidate vehicle control instructions.

[0167] In some embodiments, the second determining module 1103 is further configured to perform the following: obtain the semantic similarity between the user's vehicle control intention and the description information of the candidate vehicle control instructions; and determine the target vehicle control instruction from the set of vehicle control instructions based on the semantic similarity.

[0168] In this embodiment, leveraging the reasoning capabilities of a large language model, flexible and comprehensive vehicle control intentions can be identified. This allows for the mapping of diverse vehicle control intentions to control commands, enabling users to control their vehicles using vehicle-related apps without being limited by the app's interface. Users can quickly and conveniently input and output their vehicle control intentions, achieving precise vehicle control. Furthermore, the intent recognition capabilities of the large language model support diverse expansion of vehicle control functions, allowing the app to support all executable vehicle control capabilities, thereby improving overall user convenience and experience. Moreover, based on voice data collection within the app, remote voice control can be switched from the system level to the app level, providing support for controlling vehicles via vehicle-related apps on different brand terminal devices.

[0169] Figure 12 This is a schematic diagram illustrating the structure of a vehicle control device according to another exemplary embodiment. (Refer to...) Figure 12The vehicle control device 1200 of this embodiment includes a receiving module 1201, an identification module 1202, a determining module 1203, and a triggering module 1204.

[0170] The receiving module 1201 is configured to receive input information for vehicle control; The recognition module 1202 is configured to perform intent recognition on the input information to determine the user's vehicle control intent; The determination module 1203 is configured to determine the target vehicle control command from the set of vehicle control commands based on the user's vehicle control intention; Trigger module 1204 is configured to trigger the vehicle to execute the vehicle control process related to the target vehicle control command.

[0171] In some embodiments, the receiving module 1201 is further configured to perform at least one of the following operations: Receive voice information for vehicle control; Receive text messages for vehicle control; Receive control identification information and / or control description information of the target control, wherein the target control is the control to be operated among a plurality of pre-configured candidate controls for vehicle control.

[0172] In some embodiments, the voice information is collected by a voice assistant.

[0173] In some embodiments, the receiving module 1201 is further configured to receive the input information sent by the application through a second communication link.

[0174] In some embodiments, the trigger module 1204 is further configured to perform at least one of the following operations: The target vehicle control command is sent to the application via a second communication link, wherein the target vehicle control command is sent to the vehicle via a first communication link between the application and the vehicle to instruct the vehicle to execute a vehicle control process related to the target vehicle control command; The target vehicle control command is sent to the vehicle via a third communication link to instruct the vehicle to execute the vehicle control process related to the target vehicle control command.

[0175] In some embodiments, the determining module 1203 is further configured to execute: Determine the description information of each candidate vehicle control command in the set of vehicle control commands; Based on the user's vehicle control intent and the description information of the candidate vehicle control commands, the target vehicle control command is determined from the set of vehicle control commands.

[0176] In some embodiments, the determining module 1203 is further configured to execute: Obtain the semantic similarity between the user's vehicle control intent and the description information of the candidate vehicle control commands; The target vehicle control command is determined from the set of vehicle control commands based on the semantic similarity.

[0177] In this embodiment, leveraging the reasoning capabilities of a large language model, flexible and comprehensive vehicle control intentions can be identified. This allows for the mapping of diverse vehicle control intentions to control commands, enabling users to control their vehicles using vehicle-related apps without being limited by the app's interface. Users can quickly and conveniently input and output their vehicle control intentions, achieving precise vehicle control. Furthermore, the intent recognition capabilities of the large language model support diverse expansion of vehicle control functions, allowing the app to support all executable vehicle control capabilities, thereby improving overall user convenience and experience. Moreover, based on voice data collection within the app, remote voice control can be switched from the system level to the app level, providing support for controlling vehicles via vehicle-related apps on different brand terminal devices.

[0178] Figure 13 This is a schematic diagram illustrating the structure of a vehicle control device according to another exemplary embodiment. (Refer to...) Figure 13 The vehicle control device 1300 disclosed herein includes a data acquisition module 1301 and a transceiver module 1302.

[0179] The acquisition module 1301 is configured to acquire input information for vehicle control. The transceiver module 1302 is configured to send the input information to the server, receive the target vehicle control command sent by the server, and send the target vehicle control command to the vehicle. The input information is used to perform intent recognition through the server to determine the user's vehicle control intent, and the user's vehicle control intent is used to determine the target vehicle control instruction from the set of vehicle control instructions. The target vehicle control command is used to instruct the vehicle to perform a vehicle control process related to the target vehicle control command.

[0180] In some embodiments, the acquisition module 1301 is further configured to activate the information acquisition component in response to the operation of a pre-configured information acquisition control; and to acquire the input information through the information acquisition component.

[0181] In some embodiments, the acquisition module 1301 is further configured to perform at least one of the following operations: In response to the operation of the voice acquisition control, the voice acquisition component is activated, and voice information for vehicle control is acquired through the voice acquisition component as the input information; In response to the text acquisition control being operated, a text input component is activated, and text information for vehicle control is acquired through the text input component as the input information.

[0182] In some embodiments, the acquisition module 1301 is further configured to respond to the wake-up information of the voice assistant, wake up the voice assistant; call the application programming interface reserved for the voice assistant; and obtain the voice information acquired by the voice assistant through the reserved application programming interface as the input information.

[0183] In some embodiments, the acquisition module 1301 is further configured to perform an operation in response to a target control being operated on among a plurality of pre-configured candidate controls for vehicle control, and to determine the control identifier and / or control description information of the target control as the input information.

[0184] In some embodiments, the transceiver module 1302 is further configured to send the input information to the server via a second communication link.

[0185] In some embodiments, the transceiver module 1302 is further configured to receive the target vehicle control command sent by the server through the second communication link.

[0186] In some embodiments, the transceiver module 1302 is further configured to send the target vehicle control command to the vehicle via a first communication link after receiving the target vehicle control command sent by the server.

[0187] In this embodiment, leveraging the reasoning capabilities of a large language model, flexible and comprehensive vehicle control intentions can be identified. This allows for the mapping of diverse vehicle control intentions to control commands, enabling users to control their vehicles using vehicle-related apps without being limited by the app's interface. Users can quickly and conveniently input and output their vehicle control intentions, achieving precise vehicle control. Furthermore, the intent recognition capabilities of the large language model support diverse expansion of vehicle control functions, allowing the app to support all executable vehicle control capabilities, thereby comprehensively improving user convenience and experience.

[0188] To implement the above embodiments, this disclosure also proposes an electronic device, such as... Figure 14 As shown, the electronic device 1400 includes a processor 1401 and a memory 1402 for storing processor-executable instructions; wherein the processor 1401 is configured to implement embodiments of the present disclosure. Figure 1-10 The steps of the vehicle control method shown are for controlling the vehicle.

[0189] Figure 15This is a schematic diagram illustrating the structure of a vehicle according to an exemplary embodiment. For example, vehicle 1500 can be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicles. Vehicle 1500 can be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.

[0190] Reference Figure 15 The vehicle 1500 may include various subsystems, such as an infotainment system 1510, a perception system 1520, a decision control system 1530, a drive system 1540, and a computing platform 1550. The vehicle 1500 may also include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and component of the vehicle 1500 can be interconnected via wired or wireless means.

[0191] In some embodiments, the infotainment system 1510 may include a communication system, an entertainment system, and a navigation system, etc.

[0192] The perception system 1520 may include several sensors for sensing information about the environment surrounding the vehicle 1500. For example, the perception system 1520 may include a global positioning system (which may be a GPS system, a BeiDou system, or another positioning system), an inertial measurement unit (IMU), a lidar, a millimeter-wave radar, an ultrasonic radar, and a camera device.

[0193] The decision control system 1530 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0194] The drive system 1540 may include components that provide powered motion to the vehicle 1500. In one embodiment, the drive system 1540 may include an engine, an energy source, a transmission system, and wheels. The engine may be one or a combination of internal combustion engines, electric motors, and compressed air engines. The engine is capable of converting energy provided by the energy source into mechanical energy.

[0195] Some or all of the functions of the vehicle 1500 are controlled by a computing platform 1550. The computing platform 1550 may include at least one processor 1551 and a memory 1552, the processor 1551 being able to execute instructions 1553 stored in the memory 1552.

[0196] Processor 1551 can be any conventional processor, such as a commercially available CPU. Processors may also include graphics processing units (GPUs), field-programmable gate arrays (FPGAs), systems-on-chips (SoCs), application-specific integrated circuits (ASICs), or combinations thereof.

[0197] The memory 1552 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0198] In addition to instruction 1553, memory 1552 can also store data, such as road maps, route information, vehicle position, direction, speed, and other data. The data stored in memory 1552 can be used by computing platform 1550.

[0199] In this embodiment of the disclosure, processor 1551 may execute instructions 1553 to implement all or part of the steps of the vehicle control method provided in this disclosure.

[0200] To implement the above embodiments, this disclosure also proposes a computer-readable storage medium storing computer program instructions thereon, which, when executed by a processor, implement the steps of the vehicle control method provided in this disclosure.

[0201] Alternatively, the computer-readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0202] To implement the above embodiments, this disclosure also proposes a chip including an interface circuit and a processing circuit coupled to each other, wherein the interface circuit is used to input or output signals, and the processing circuit is configured to implement the steps of the vehicle control method provided in this disclosure.

[0203] Figure 16 This is a schematic diagram illustrating the structure of a chip according to an exemplary embodiment. See also... Figure 16 The diagram shown is a schematic representation of the structure of chip 1600, but it is not limited to this.

[0204] Chip 1600 includes processing circuitry 1601, which is configured to execute any of the above vehicle control methods.

[0205] In some embodiments, chip 1600 further includes one or more interface circuits 1602. Optionally, interface circuit 1602 is connected to memory 1603, and interface circuit 1602 can be used to receive signals from memory 360 or other devices, and interface circuit 1602 can be used to send signals to memory 360 or other devices. For example, interface circuit 1602 can read instructions stored in memory 1603 and send the instructions to processing circuit 1601.

[0206] In some embodiments, the interface circuit 1602 performs at least one of the communication steps such as sending and / or receiving in the above method, while the processing circuit 1601 performs other steps.

[0207] In some embodiments, the terms interface circuit, interface, transceiver pin, transceiver, etc., can be used interchangeably.

[0208] In some embodiments, chip 1600 further includes one or more memories 1603 for storing instructions. Optionally, all or part of the memories 1603 may be located outside of chip 1600.

[0209] To implement the above embodiments, this disclosure also proposes a computer program product, including a computer program that, when executed by a processor, implements the steps of the vehicle control method provided in this disclosure.

[0210] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0211] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A vehicle control method, characterized in that, The method includes: Obtain input information for vehicle control; The input information is subjected to intent recognition to determine the user's intent to control the vehicle; Based on the user's vehicle control intention, determine the target vehicle control command from the set of vehicle control commands; The vehicle control process related to the target vehicle control command is executed on the vehicle.

2. The method according to claim 1, characterized in that, The input information is at least one of the following: Voice information used for vehicle control; Text information used for vehicle control; The target control includes control identification information and / or control description information, wherein the target control is the control that is operated on from among a plurality of pre-configured candidate controls for vehicle control.

3. The method according to claim 2, characterized in that, The process of acquiring voice information for vehicle control includes: Wake up the voice assistant and invoke the application programming interface reserved for the voice assistant; The voice information collected by the voice assistant is obtained through the reserved application programming interface.

4. The method according to any one of claims 1-3, characterized in that, The step of determining the target vehicle control command from the set of vehicle control commands based on the user's vehicle control intention includes: Determine the description information of each candidate vehicle control command in the set of vehicle control commands; Based on the user's vehicle control intent and the description information of the candidate vehicle control commands, the target vehicle control command is determined from the set of vehicle control commands.

5. The method according to claim 4, characterized in that, The step of determining the target vehicle control command from the set of vehicle control commands based on the user's vehicle control intent and the description information of the candidate vehicle control commands includes: Obtain the semantic similarity between the user's vehicle control intent and the description information of the candidate vehicle control commands; The target vehicle control command is determined from the set of vehicle control commands based on the semantic similarity.

6. A vehicle control method, characterized in that, The method includes: Receive input information for vehicle control; The input information is subjected to intent recognition to determine the user's intent to control the vehicle; Based on the user's vehicle control intention, determine the target vehicle control command from the set of vehicle control commands; Trigger the vehicle to execute the vehicle control process related to the target vehicle control command.

7. The method according to claim 6, characterized in that, Receiving input information for vehicle control includes at least one of the following operations: Receive voice information for vehicle control; Receive text messages for vehicle control; Receive control identification information and / or control description information of the target control, wherein the target control is the control to be operated among a plurality of pre-configured candidate controls for vehicle control.

8. The method according to claim 7, characterized in that, The voice information was collected by a voice assistant.

9. The method according to claim 7, characterized in that, The receiving of input information for vehicle control includes: The input information is received by the application via a second communication link.

10. The method according to claim 9, characterized in that, The process of triggering the vehicle to execute the vehicle control command related to the target vehicle control instruction includes one of the following operations: The target vehicle control command is sent to the application via the second communication link, wherein the target vehicle control command is sent to the vehicle via the first communication link between the application and the vehicle to instruct the vehicle to execute a vehicle control process related to the target vehicle control command; The target vehicle control command is sent to the vehicle via a third communication link to instruct the vehicle to execute the vehicle control process related to the target vehicle control command.

11. The method according to any one of claims 6-10, characterized in that, The step of determining the target vehicle control command from the set of vehicle control commands based on the user's vehicle control intention includes: Determine the description information of each candidate vehicle control command in the set of vehicle control commands; Based on the user's vehicle control intent and the description information of the candidate vehicle control commands, the target vehicle control command is determined from the set of vehicle control commands.

12. The method according to claim 11, characterized in that, The step of determining the target vehicle control command from the set of vehicle control commands based on the user's vehicle control intent and the description information of the candidate vehicle control commands includes: Obtain the semantic similarity between the user's vehicle control intent and the description information of the candidate vehicle control commands; The target vehicle control command is determined from the set of vehicle control commands based on the semantic similarity.

13. A vehicle control method, characterized in that, The method includes: Collect input information for vehicle control; The input information is sent to the server, and the input information is used to perform intent recognition through the server to determine the user's vehicle control intent. The user's vehicle control intent is used to determine the target vehicle control instruction from the set of vehicle control instructions. The system receives a target vehicle control command sent by the server and sends the target vehicle control command to the vehicle. The target vehicle control command is used to instruct the vehicle to execute a vehicle control process related to the target vehicle control command.

14. The method according to claim 13, characterized in that, The input information collected for vehicle control includes: The information collection component is activated in response to the operation of a pre-configured information collection control. The input information is collected by the information collection component.

15. The method according to claim 14, characterized in that, The collection of input information for vehicle control includes at least one of the following operations: In response to the operation of the voice acquisition control, the voice acquisition component is activated, and voice information for vehicle control is acquired through the voice acquisition component as the input information; In response to the text acquisition control being operated, a text input component is activated, and text information for vehicle control is acquired through the text input component as the input information.

16. The method according to claim 15, characterized in that, The input information collected for vehicle control includes: In response to the wake-up message from the voice assistant, the voice assistant is activated; Call the application programming interface reserved for the voice assistant; The reserved application programming interface is used to obtain the voice information collected by the voice assistant, which is then used as the input information.

17. The method according to claim 13, characterized in that, The input information collected for vehicle control includes: In response to the operation of a target control among a plurality of pre-configured candidate controls for vehicle control, the control identifier and / or control description information of the target control are determined as the input information.

18. The method according to any one of claims 13-17, characterized in that, Sending the input information to the server includes: The input information is sent to the server via a second communication link.

19. The method according to any one of claims 13-17, characterized in that, The step of receiving the target vehicle control command sent by the server includes: Receive the target vehicle control command sent by the server through the second communication link.

20. The method according to any one of claims 13-17, characterized in that, After receiving the target vehicle control command sent by the server, the process further includes: The target vehicle control command is sent to the vehicle via the first communication link.

21. A vehicle control device, characterized in that, The device includes: The acquisition module is configured to acquire input information for vehicle control. The first determining module is configured to perform intent recognition on the input information to determine the user's vehicle control intent; The second determining module is configured to determine the target vehicle control instruction from the set of vehicle control instructions based on the user's vehicle control intention; The control module is configured to execute vehicle control procedures related to the target vehicle control command.

22. The apparatus according to claim 21, characterized in that, The input information is at least one of the following: Voice information used for vehicle control; Text information used for vehicle control; The target control includes control identification information and / or control description information, wherein the target control is the control that is operated on from among a plurality of pre-configured candidate controls for vehicle control.

23. The apparatus according to claim 22, characterized in that, The acquisition module is also configured to execute: Wake up the voice assistant and invoke the application programming interface reserved for the voice assistant; The voice information collected by the voice assistant is obtained through the reserved application programming interface.

24. A vehicle control device, characterized in that, The device includes: The receiving module is configured to receive input information for vehicle control. The recognition module is configured to perform intent recognition on the input information to determine the user's intent to control the vehicle; The determination module is configured to determine the target vehicle control command from the set of vehicle control commands based on the user's vehicle control intention; The trigger module is configured to execute the vehicle control process related to the target vehicle control command.

25. The apparatus according to claim 24, characterized in that, The receiving module is also configured to perform at least one of the following operations: Receive voice information for vehicle control; Receive text messages for vehicle control; Receive control identification information and / or control description information of the target control, wherein the target control is the control to be operated among a plurality of pre-configured candidate controls for vehicle control.

26. The apparatus according to claim 25, characterized in that, The voice information is collected through the voice assistant associated with the application.

27. A vehicle control device, characterized in that, The device includes The data acquisition module is configured to collect input information for vehicle control. The transceiver module is configured to send the input information to the server, receive the target vehicle control command sent by the server, and send the target vehicle control command to the vehicle. The input information is used to perform intent recognition through the server to determine the user's vehicle control intent, and the user's vehicle control intent is used to determine the target vehicle control instruction from the set of vehicle control instructions. The target vehicle control command is used to instruct the vehicle to perform a vehicle control process related to the target vehicle control command.

28. The apparatus according to claim 27, characterized in that, The acquisition module is also configured to execute: The information collection component is activated in response to the operation of a pre-configured information collection control. The input information is collected by the information collection component.

29. The apparatus according to claim 27, characterized in that, The acquisition module is also configured to execute: In response to the operation of a target control among a plurality of pre-configured candidate controls for vehicle control, the control identifier and / or control description information of the target control are determined as the input information.

30. The apparatus according to claim 28, characterized in that, The acquisition module is also configured to execute: In response to the wake-up message from the voice assistant, the voice assistant is activated; Call the application programming interface reserved for the voice assistant; The reserved application programming interface is used to obtain the voice information collected by the voice assistant, which is then used as the input information.

31. A vehicle, characterized in that, include: The processor, and the memory used to store processor-executable instructions; The processor is configured as follows: Implement the steps of the method according to any one of claims 1-5, 6-12, or 13-20 to perform main control of the vehicle.

32. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements the steps of the method according to any one of claims 1-5, 6-12, or 13-20.

33. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When executed by a processor, the program instructions implement the steps of the method as described in any one of claims 1-5, 6-12, or 13-20.

34. A chip, characterized in that, The chip includes an interface circuit and a processing circuit coupled to each other. The interface circuit is used to input or output signals, and the processing circuit is configured to implement the steps of the method according to any one of claims 1-5, 6-12, or 13-20.

35. A computer program product, characterized in that, Includes a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1-5, 6-12, or 13-20.

Images