Vehicle control method, server, and computer-readable storage medium

Abstract

The application discloses a vehicle control method, a server and a computer readable storage medium. The method comprises: acquiring current vehicle external perception information, wherein the current vehicle external perception information comprises user perception information and environment perception information; determining user demand according to the current vehicle external perception information; determining a target function point according to the user demand based on a preset knowledge base; determining a target operation instruction according to the target function point; and issuing the target operation instruction to the vehicle to control the vehicle to execute the target operation instruction. In this way, the user demand obtained according to the current vehicle external perception information is processed based on the preset knowledge base, the target function point and the corresponding target operation instruction for completing the user demand are determined, and therefore the vehicle function can be effectively controlled, and the efficiency, safety and user experience of driving are improved.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, and in particular to a vehicle control method, a server, and a computer-readable storage medium. Background Technology

[0002] In related technologies, in-vehicle voice assistants facilitate human-computer interaction with users, making operation more convenient. However, due to the surge in the number of devices in vehicles, in-vehicle voice assistants need to manage and control more functions. When reasoning about user voice requests, in-vehicle voice assistants are prone to misusing certain functions, causing functional conflicts and affecting the user experience. Summary of the Invention

[0003] This application provides a vehicle control method, a server, and a computer-readable storage medium.

[0004] This application provides a vehicle control method, the method comprising:

[0005] Acquire current external perception information of the vehicle, which includes user perception information and environmental perception information;

[0006] Based on the current external perception information of the vehicle, determine the user's needs;

[0007] Based on a pre-set knowledge base, the target functional points are determined according to the user's needs;

[0008] Based on the target function points, determine the target operation instructions;

[0009] The target operation command is sent to the vehicle to control the vehicle to execute the target operation command.

[0010] In this way, the server acquires the current external perception information of the vehicle, including user perception information and environmental perception information. Next, based on this information, the server determines the user's needs. Then, based on a pre-defined knowledge base, the server determines the target functional points based on these needs. The server then determines the target operation instructions based on these functional points. Finally, the server sends the target operation instructions to the vehicle to control it to execute them. Thus, by processing the user needs obtained from the current external perception information based on a pre-defined knowledge base, and determining the target functional points and corresponding operation instructions to fulfill those needs, the server can effectively control vehicle functions, improving driving efficiency, safety, and user experience.

[0011] In some implementations, determining the target functional points based on a preset knowledge base and the user's needs includes:

[0012] Based on a pre-built list of vehicle function points, candidate function points are determined according to the user's needs;

[0013] Based on the preset knowledge base, the target function point is determined according to the user needs and the candidate function points.

[0014] Thus, based on a pre-built list of vehicle function points, the server determines candidate function points according to user needs. Then, based on a pre-defined knowledge base, the server determines the target function point based on both the user needs and the candidate function points. In this way, through the pre-built list of vehicle function points and the pre-defined knowledge base, the server can accurately understand and match diverse user needs and determine the target function point that meets those needs.

[0015] In some implementations, determining the target function point based on the preset knowledge base, according to the user requirements and the candidate function points, includes:

[0016] Based on the candidate function points, obtain the current state perception information of the vehicle components corresponding to the candidate function points;

[0017] Based on the preset knowledge base, candidate function description information corresponding to the candidate function points is obtained according to the candidate function points;

[0018] The target function is determined based on the user requirements, the candidate function points, the current state awareness information, and the candidate function description information.

[0019] In this way, the server obtains the current state perception information of the vehicle components corresponding to the candidate function points. Next, based on a pre-defined knowledge base, the server obtains the candidate function description information corresponding to the candidate function points. Finally, the server determines the target function point based on user requirements, candidate function points, current state perception information, and candidate function description information. Thus, by integrating the current state perception information of the vehicle components corresponding to the candidate function points and the candidate function description information, the server can accurately match user requirements, select the appropriate target function point, and avoid inappropriate function operations.

[0020] In some implementations, determining the target function point based on the user requirements, the candidate function points, the current state awareness information, and the candidate function description information includes:

[0021] Based on the preset function point relationship, the target function point is determined from the candidate function points according to the current state perception information and the candidate function description information. The preset function point relationship includes the preset priority relationship and preset conflict relationship between each function point in the vehicle function point list.

[0022] The step of determining the target operation instruction based on the target function point includes:

[0023] Based on the user requirements and the target functional points, the target operation instructions are determined.

[0024] Thus, based on the preset function point relationships, the server determines the target function point from the candidate function points according to the current state perception information and candidate function description information. The preset function point relationships include the preset priority relationships and preset conflict relationships between the function points in the vehicle function point list. Next, the server determines the target operation instruction according to the user's needs and the target function point. In this way, by considering the priority and conflict relationships between function points, the server can intelligently select the appropriate function point, improving the accuracy and efficiency of function matching.

[0025] In some implementations, determining the target operation instruction based on the user requirements and the target functional point includes:

[0026] Based on a pre-defined large language model, the target operation instruction is determined according to the user requirements, the target function points, and the target function description information corresponding to the target function points.

[0027] Thus, based on a pre-defined large language model, the server determines the target operation instruction according to user needs, the target functional point, and the corresponding target functional description information. In this way, by using the pre-defined large language model and target functional description information, the server can accurately understand user needs, determine the target operation instruction, reduce misunderstandings and erroneous operations, and improve the user experience.

[0028] In some implementations, the preset knowledge base is constructed through the following steps:

[0029] Vehicle knowledge is classified and processed to obtain vehicle perception information and vehicle function information. The vehicle perception information includes external vehicle perception information and status perception information of vehicle components. The external vehicle perception information includes environmental perception information and user perception information. The user perception information includes voice requests, actions and / or user information. The user information includes user gender, user age, quantity information and / or location information in the vehicle cabin.

[0030] Based on the vehicle function information, function points and corresponding function description information are determined. The function description information includes function definition information, application scenario information, and mutual exclusion information between the sub-function points included in the function point.

[0031] Based on the vehicle perception information and the functional points, determine the functional point-vehicle component relationship;

[0032] Based on the preset vehicle function relationships and the function points, determine the preset function point relationships;

[0033] The preset knowledge base is constructed based on the functional point-vehicle component relationship and the functional point relationship.

[0034] Thus, the pre-defined knowledge base is constructed through the following steps: Vehicle knowledge is categorized to obtain vehicle perception information and vehicle function information. Vehicle perception information includes external vehicle perception information and state perception information of vehicle components. External vehicle perception information includes environmental perception information and user perception information. User perception information includes voice requests, actions, and / or user information, including user gender, age, number of users, and / or location information within the vehicle cabin. Next, based on the vehicle function information, function points and corresponding function description information are determined. Function description information includes function definition information, application scenario information, and mutual exclusion information between sub-function points included in the function point. Then, based on the vehicle perception information and function points, the function point-vehicle component relationship is determined. Subsequently, based on the pre-defined vehicle function relationships and function points, the pre-defined function point relationships are determined. Finally, the pre-defined knowledge base is constructed based on the function point-vehicle component relationships and the function point relationships. In this way, through the above steps, a pre-defined knowledge base can be constructed. This knowledge base includes the relationship between function points and vehicle components, as well as the relationship between pre-defined function points. This helps the server understand user needs and provide clear target operation instructions, which are then sent to the vehicle to complete vehicle control and process user requests, thereby improving the user experience. Furthermore, by collecting user perception information, the server can provide more personalized services based on this information.

[0035] In some implementations, the vehicle function relationships include vehicle function priority relationships and vehicle function conflict relationships. The step of determining the preset function point relationships based on the preset vehicle function relationships and the function points includes:

[0036] Based on the vehicle function priority relationship and the function points, determine the preset priority relationship in the preset function point relationship;

[0037] Based on the vehicle function conflict relationship and the function points, determine the preset conflict relationship in the preset function point relationship.

[0038] Thus, based on the vehicle function priority relationships and function points, a preset priority relationship is determined within the preset function point relationships. Next, based on the vehicle function conflict relationships and function points, a preset conflict relationship is determined within the preset function point relationships. In this way, by clearly defining the relationships between function points, the system can efficiently manage vehicle functions while ensuring driving safety.

[0039] In some embodiments, the method further includes:

[0040] The numerical information and / or gear information in the vehicle perception information are rewritten to generate sensory information describing the numerical information and / or gear information.

[0041] In this way, the numerical information and / or gear information in the vehicle's perceived information are rewritten to generate perceptual information describing the numerical information and / or gear information. This rewriting of the numerical information and / or gear information helps the server intuitively understand user needs, thereby improving the user experience.

[0042] In some embodiments, the method further includes:

[0043] The function points that target the same vehicle component and are mutually exclusive are merged.

[0044] In this way, mutually exclusive functional points targeting the same vehicle component are merged. This reduces redundancy of identical knowledge in similar functions within the preset database, thereby lowering the memory resources consumed by the preset database.

[0045] This application provides a server, which includes a processor and a memory. The memory stores a computer program, and when the computer program is executed by the processor, it implements the vehicle control method described above.

[0046] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the vehicle control method described above.

[0047] Additional aspects and advantages of embodiments of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of embodiments of this application. Attached Figure Description

[0048] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, wherein:

[0049] Figure 1 This is one of the schematic flowcharts of a vehicle control method according to certain embodiments of this application;

[0050] Figure 2 This is a schematic diagram of the current vehicle external perception information processing flow according to certain embodiments of this application;

[0051] Figure 3 This is a second schematic flowchart of a vehicle control method according to certain embodiments of this application;

[0052] Figure 4 This is a third schematic flowchart of a vehicle control method according to certain embodiments of this application;

[0053] Figure 5 This is the fourth flowchart of a vehicle control method according to certain embodiments of this application;

[0054] Figure 6 This is the fifth of the flowcharts illustrating a vehicle control method according to certain embodiments of this application;

[0055] Figure 7 This is a schematic flowchart of a vehicle control method according to certain embodiments of this application, number six.

[0056] Figure 8 This is the seventh flowchart of a vehicle control method according to certain embodiments of this application;

[0057] Figure 9 This is the eighth flowchart of a vehicle control method according to certain embodiments of this application;

[0058] Figure 10 This is the ninth flowchart of a vehicle control method according to certain embodiments of this application. Detailed Implementation

[0059] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the embodiments of this application, and should not be construed as limiting the embodiments of this application.

[0060] In today's automotive industry, in-vehicle voice assistants have become a common technology, greatly improving user convenience and driving experience through human-machine interaction. With the development of vehicle technology, the number of devices in vehicles is increasing daily, including but not limited to navigation systems, entertainment systems, air conditioning controls, seat adjustments, and window controls.

[0061] The increasing number of devices necessitates the management and control of a growing number of functions by in-vehicle voice assistants. This necessitates higher levels of intelligence and stronger functional coordination capabilities from these assistants. However, in practical applications, in-vehicle voice assistants are prone to erroneously using certain functions when reasoning about user voice requests, leading to functional conflicts and impacting user experience. For example, when a user simultaneously requests to activate both seat heating and ventilation, if the in-vehicle voice assistant fails to correctly understand the user's intent, it may activate both functions at the same time, causing interference between seat heating and ventilation and affecting user comfort.

[0062] Based on the above issues, please refer to Figure 1 This application provides a vehicle control method, the method comprising:

[0063] 011: Obtain current external perception information of the vehicle;

[0064] 012: Determine user needs based on current external perception information of the vehicle;

[0065] 013: Based on a pre-set knowledge base, determine the target functional points according to user needs;

[0066] 014: Determine the target operation instructions based on the target function points;

[0067] 015: Send the target operation command to the vehicle to control the vehicle to execute the target operation command.

[0068] This application also provides a server, including a memory and a processor. The vehicle control method of this application can be implemented by the server of this application. Specifically, the memory stores a computer program, and the processor is used to acquire current external perception information of the vehicle and determine user needs based on the current external perception information. The processor is also used to determine target function points based on a preset knowledge base and user needs, and to determine target operation instructions based on the target function points. Finally, it sends the target operation instructions to the vehicle to control the vehicle to execute the target operation instructions.

[0069] This application also provides a vehicle control device. The vehicle control method of this application can be implemented by the vehicle control device of this application. Specifically, the vehicle control device includes an acquisition module, a determination module, and a distribution module. The acquisition module is used to acquire current external perception information of the vehicle. The determination module is used to determine user needs based on the current external perception information of the vehicle. The determination module is also used to determine target function points based on a preset knowledge base and user needs. The determination module is also used to determine target operation instructions based on the target function points. The distribution module is used to distribute the target operation instructions to the vehicle to control the vehicle to execute the target operation instructions.

[0070] Specifically, current vehicle external perception information refers to data collected by the vehicle through its sensors and systems regarding the vehicle's external environment and user status, including user perception information and environmental perception information. User perception information refers to data and information collected by the vehicle through its sensors and systems regarding vehicle users (such as drivers and passengers). Environmental perception information refers to data and information collected by the vehicle through its onboard sensors, cameras, and other detection devices regarding the environment surrounding the vehicle, including external environmental information and internal environmental information. External environmental information includes weather, light, temperature, and air quality, while internal environmental information includes temperature, air quality, and humidity.

[0071] User requirements refer to the expectations and instructions from vehicle users regarding vehicle functions, performance, or services in a specific context, as obtained by the server.

[0072] A pre-defined knowledge base refers to a database containing a large amount of structured information, which provides the information foundation for supporting system decision-making and operation, i.e., processing user needs and determining target operation instructions. By analyzing user needs and the vehicle's current external perception information, the server can determine the most suitable functional points from the pre-defined knowledge base and generate corresponding operation instructions.

[0073] A target function point refers to a specific function point selected from a pre-set knowledge base in a vehicle's intelligent system based on user needs and environmental conditions. The target function point represents the service that needs to be executed after the user leaves the vehicle. For example, if a user requests the vehicle to automatically adjust the temperature, the system will determine "Air Conditioning Adjustment: Increase Temperature" as the target function point from the pre-set knowledge base based on current environmental perception information (such as the temperature difference between the inside and outside of the vehicle, or the interior temperature being lower). It should be noted that there may be multiple target function points, but this is not limited here.

[0074] A target operation command refers to a specific instruction generated in a vehicle's intelligent system based on user needs and the current state perception information of vehicle components, according to a specific function point (i.e., a target function point) selected from a preset knowledge base. This instruction guides the vehicle to perform a specific operation or service to meet the user's needs. For example, if the user's need is "request the vehicle to automatically adjust the temperature," the target function point is "air conditioning temperature: increase," and the current air conditioning setting is 20℃ with a fan speed of "2," the target operation command might be "increase the temperature to 26℃, adjust the fan speed to: 3." It should be noted that there may be multiple target operation commands, which are not limited here.

[0075] Please see Figure 2 The server obtains the current external perception information of the vehicle. That is, the server collects the current external perception information of the vehicle through the vehicle's external perception system. The current external perception information of the vehicle includes user perception information and environmental perception information.

[0076] Next, the server analyzes the collected external perception information of the vehicle to determine the user's needs. For example, when the vehicle's external perception system detects raindrops and an open driver's side window, and the user expresses "I feel cold" in voice, the server analyzes this information and identifies the user's need as "to increase the interior temperature."

[0077] Then, based on a pre-set knowledge base, the server determines the target function based on user needs. Continuing the example above, if the server determines the target function based on the user's need to "increase the car's interior temperature," then the determined target function is "open / close the driver's side window."

[0078] The server then determines the target operation instruction based on the target function point. Continuing the example above, based on the target function point "driver's window [open, close]", the generated target operation instruction is "close the driver's window".

[0079] Finally, the server sends the target operation command to the vehicle to control the vehicle to execute the target operation command.

[0080] In summary, in the vehicle control method and server provided in this application, the server acquires current external perception information of the vehicle, including user perception information and environmental perception information. Next, the server determines user needs based on the current external perception information. Then, based on a preset knowledge base, the server determines target function points based on the user needs. The server then determines target operation instructions based on the target function points. Finally, the server sends the target operation instructions to the vehicle to control the vehicle to execute the target operation instructions. In this way, by processing user needs obtained from the current external perception information based on a preset knowledge base, and determining the target function points and corresponding target operation instructions to fulfill the user needs, vehicle functions can be effectively controlled, improving driving efficiency, safety, and user experience.

[0081] Please see Figure 3 In some implementations, step 013 (based on a preset knowledge base, determining the target functional points according to user needs) includes:

[0082] 0131: Based on a pre-built list of vehicle function points, candidate function points are determined according to user needs;

[0083] 0132: Based on a pre-set knowledge base, determine the target function points according to user needs and candidate function points.

[0084] In some implementations, the determining module is also used to determine candidate function points based on a pre-built list of vehicle function points and user requirements, and to determine target function points based on a preset knowledge base, user requirements, and candidate function points.

[0085] In some implementations, the processor is also configured to determine candidate function points based on a pre-built list of vehicle function points and user requirements, and to determine target function points based on a preset knowledge base, according to user requirements and candidate function points.

[0086] Specifically, the pre-built vehicle function point list refers to a detailed list encompassing all possible functions of the vehicle. Created during the design and development phase of the vehicle's intelligent system, it details all functions the vehicle can perform, including primary and sub-functions. When the server receives a user request, it identifies and selects possible candidate function points based on this list. Then, combining the current state perception information of the corresponding vehicle components and the user's specific needs, the server determines the most suitable target function point from the candidate list. Furthermore, the vehicle function point list forms the basis for building a pre-defined knowledge base, providing a reference framework for the system's functional scope.

[0087] Please refer to the following: Figure 2 The server filters possible candidate functions from a pre-built list of vehicle functions based on the user's needs. Continuing with the example above, based on the user's need to "increase the interior temperature", the candidate functions are determined to be "driver's side window [open, close], air conditioning temperature [heat up, cool down], and air conditioning fan speed [accelerate, decelerate]".

[0088] Next, based on a pre-set knowledge base, the server further analyzes the relationship between user needs and candidate function points to determine the target function point that best meets the user's needs. Continuing with the example above, based on the user need "increase the interior temperature" and the candidate function points "driver's side window [open, close], air conditioning temperature [heat up, cool down], and air conditioning fan speed [accelerate, decelerate]", the target function point is determined to be "driver's side window [open, close]".

[0089] In this way, through a pre-built list of vehicle function points and a preset knowledge base, the server can accurately understand and match the diverse needs of users and determine the target function points for user needs.

[0090] Please see Figure 4 In some implementations, step 0132 (determining the target function point based on a preset knowledge base, user needs, and candidate function points) includes:

[0091] 01321: Based on the candidate function points, obtain the current state perception information of the vehicle components corresponding to the candidate function points;

[0092] 01322: Based on a preset knowledge base, obtain candidate function description information corresponding to the candidate function points;

[0093] 01323: Determine the target function based on user needs, candidate function points, current state awareness information, and candidate function description information.

[0094] In some implementations, the determining module is further configured to: acquire current state perception information of vehicle components corresponding to candidate function points; acquire candidate function description information corresponding to candidate function points based on a preset knowledge base; and determine the target function point based on user requirements, candidate function points, current state perception information, and candidate function description information.

[0095] In some implementations, the processor is further configured to: acquire current state perception information of vehicle components corresponding to candidate function points; acquire candidate function description information corresponding to candidate function points based on a preset knowledge base; and determine a target function point based on user requirements, candidate function points, current state perception information, and candidate function description information.

[0096] Specifically, the current state perception information of vehicle components refers to the specific working state or performance data of various vehicle components or systems at a certain moment, collected by the vehicle's built-in sensors and monitoring systems, including tire status such as tire pressure, temperature, and wear.

[0097] Candidate function description information refers to the detailed explanation and description of each candidate function point in the vehicle's intelligent system. For example, for the function point of "opening the car window," its candidate function description information might include: Definition: Lowering the car window glass to allow air circulation between the inside and outside of the vehicle or to facilitate viewing the outside situation. Applicable scenario 1: Ventilation. Positive impact: Promotes air circulation inside the vehicle, improving comfort. Negative impact: May generate noise and wind resistance at high speeds, affecting the driving experience. Applicable scenario 2: Viewing the outside. Positive impact: Facilitates observation of the outside situation, improving safety. Negative impact: May reduce privacy inside the vehicle. Optional operation 1: Open all. Definition: Fully lower all car windows. Optional operation 2: Open partially. Definition: Select one or more car windows to partially lower. Optional operation 3: Open only the driver's side window. Definition: Lower only the driver's side window.

[0098] Please refer to the following: Figure 2 The server obtains the current status perception information of the corresponding vehicle components based on the candidate function points. For example, if the candidate function point includes "air conditioning temperature [heating up, cooling down]", the server will obtain the current status information of the air conditioning system.

[0099] Next, based on a pre-defined knowledge base, the server retrieves the corresponding functional description information for each candidate function. This description information helps the server better understand the role and applicable situations of each candidate function.

[0100] Finally, the server integrates user needs, candidate function points, current status awareness information, and candidate function description information to determine the target function point that best meets user needs.

[0101] In this way, by integrating the current state perception information of vehicle components corresponding to the candidate function points and the candidate function description information, the server can accurately match user needs, select the appropriate target function points, and avoid inappropriate function operations.

[0102] Please see Figure 5 In some implementations, step 01323 (determining the target function point based on user requirements, candidate function points, current state awareness information, and candidate function description information) includes:

[0103] 013231: Based on the preset functional point relationships, the target functional point is determined from the candidate functional points according to the current state perception information and the candidate functional description information;

[0104] Step 014 (Determine the target operation instruction based on the target function point) includes:

[0105] 0141: Determine the target operation instructions based on user needs and target functionalities.

[0106] In some implementations, the determining module is further configured to determine the target function point from the candidate function points based on preset function point relationships, current state perception information, and candidate function description information; and to determine the target operation instruction based on user needs and the target function point.

[0107] In some implementations, the processor is further configured to determine a target function point from candidate function points based on preset function point relationships, current state awareness information, and candidate function description information; and to determine a target operation instruction based on user requirements and the target function point.

[0108] Specifically, the preset function point relationship refers to the predefined mutual relationship between function points in a vehicle intelligent system, including priority relationship and conflict relationship. It can be set according to the functional characteristics and operation logic of the vehicle. The purpose is to ensure that the system can make reasonable decisions when executing functions, avoid conflicts between functions, and optimize the operation process.

[0109] Please refer to the following: Figure 2The server analyzes the priority and conflict relationships between candidate function points based on preset function point relationships. For example, when the user's requirement is "to lower the temperature," the identified candidate function points are "seat ventilation [open, close], windows [open, close], air conditioning [open, close]." Since opening the windows may affect the efficiency of the air conditioning when it is turned on, opening the windows and turning on the air conditioning are considered to be in conflict, and for the user's requirement of lowering the temperature, turning on the air conditioning has a higher priority. Therefore, when analyzing whether candidate function points are available, the server first analyzes the "air conditioning [open, close] and seat ventilation [open, close]" function points.

[0110] Next, the server combines the current state awareness information and the candidate function description information to determine the target function from the candidate function points. This process takes into account the priority and conflict relationships between function points to ensure that the selected function point not only meets the user's needs but also can be effectively executed in the current state of the vehicle.

[0111] Finally, the server determines the target operation instructions based on user needs and target functionalities.

[0112] In this way, by considering the priority and conflict relationships between functional points, the server can intelligently select appropriate functional points, improving the accuracy and efficiency of functional matching.

[0113] Please see Figure 6 In some implementations, step 0141 (determining the target operation instruction based on user requirements and target function points) includes:

[0114] 01411: Based on the preset large language model, determine the target operation instructions according to user needs, target function points, and target function description information corresponding to the target function points.

[0115] In some implementations, the determining module is used to determine the target operation instruction based on a preset large language model, according to user needs, target function points, and target function description information corresponding to the target function points.

[0116] In some implementations, the processor is also used to determine target operation instructions based on a preset large language model, according to user requirements, target function points, and target function description information corresponding to the target function points.

[0117] For details, please refer to [link / reference]. Figure 2The server first analyzes the user's needs and filters candidate functions that match them from a pre-defined list of functions. Next, based on a pre-defined knowledge base, the server further analyzes the relationship between the user's needs and the candidate functions to determine the target function that best meets the user's requirements. Then, the server obtains the target function description information corresponding to the target function, which helps the server more accurately understand and execute the target function. Finally, based on a pre-defined large language model, the server determines the target operation instruction based on the user's needs, the target function, and the corresponding target function description information. Continuing the example above, the generated target operation instruction is "Close the driver's side window".

[0118] In this way, by using a pre-defined large language model and target function description information, the server can accurately understand user needs, determine target operation instructions, reduce misunderstandings and erroneous operations, and improve user experience.

[0119] Please see Figure 7 In some implementations, the preset knowledge base is constructed through the following steps:

[0120] 021: Classify and process vehicle knowledge to obtain vehicle perception information and vehicle function information;

[0121] 022: Based on the vehicle function information, determine the function points and the corresponding function description information;

[0122] 023: Determine the relationship between function points and vehicle components based on vehicle perception information and function points;

[0123] 024: Determine the preset function point relationships based on the preset vehicle function relationships and function points;

[0124] 025: Construct a pre-defined knowledge base based on the relationships between function points and vehicle components, and the relationships between function points.

[0125] In some embodiments, the vehicle control device further includes a database construction module, which is used to classify and process vehicle knowledge to obtain vehicle perception information and vehicle function information. Based on the vehicle function information, it determines function points and corresponding function description information. It also determines the function point-vehicle component relationships based on the vehicle perception information and function points. The database construction module is further used to determine preset function point relationships based on preset vehicle function relationships and function points, and to construct a preset knowledge base based on the function point-vehicle component relationships and function point relationships.

[0126] In some implementations, the processor is further configured to classify vehicle knowledge to obtain vehicle perception information and vehicle function information. Based on the vehicle function information, it determines function points and corresponding function description information. It also determines the function point-vehicle component relationships based on the vehicle perception information and function points. The processor is further configured to determine preset function point relationships based on preset vehicle function relationships and function points. Finally, it constructs a preset knowledge base based on the function point-vehicle component relationships and function point relationships.

[0127] Specifically, classification processing refers to the systematic organization and categorization of vehicle knowledge during the construction of a pre-defined knowledge base. This includes dividing vehicle-related knowledge into vehicle perception information and vehicle functional information to facilitate better management and use of this information. Vehicle perception information refers to information collected by the vehicle through various sensors and monitoring systems, including external vehicle perception information and vehicle component status perception information. Vehicle component status perception information involves the working status of various vehicle components, such as engine temperature and tire pressure. Vehicle functional information refers to the various functions that the vehicle can perform, including function points and corresponding functional description information. Functional description information includes function definition information, application scenario information, and functional mutual exclusion information. Function definition information explains the specific meaning of each function point. Application scenario information describes the possible application scenarios of the function point, including the positive and negative impacts of the function point in each scenario. Functional mutual exclusion information describes the functional mutual exclusion relationships between the sub-function points included in the function point.

[0128] Location information within the vehicle cabin refers to whether a passenger is using a particular seat, i.e., whether a passenger is sitting in that seat. The system collects user voice requests, actions, and user information such as gender, age, number of passengers, and location through in-vehicle sensors, cameras, and other devices. Subsequently, the server integrates and analyzes the collected user perception information. Based on this integrated and analyzed information, the server identifies the user's specific needs, such as adjusting the air conditioning temperature or playing specific music. In this way, by collecting user perception information, the server can provide more personalized services based on that information.

[0129] Function point-vehicle component relationship refers to the correlation between each function point and specific vehicle components in a vehicle's intelligent system. For example, function point: automatic climate control. Related components: air conditioning system (including compressor, evaporator, temperature sensor, etc.), vehicle temperature sensor, ambient temperature sensor. Relationship explanation: The automatic climate control function requires the air conditioning system to operate and also needs data from both inside and outside the vehicle's temperature sensors to determine the air conditioning temperature and fan speed.

[0130] Predefined function point relationships refer to the predefined interrelationships between different functions in a vehicle's intelligent system. These relationships include priority and conflict relationships, ensuring the system makes rational decisions when executing functions, avoiding conflicts, and optimizing operational processes. For example, consider the relationship between automatic climate control and opening windows. The relationship type is conflict. Explanation: When the automatic climate control is running, opening windows may interfere with the air conditioning's effectiveness because it causes unstable interior temperatures. Therefore, the system needs to choose between these two functions to avoid energy waste and functional conflicts.

[0131] The pre-defined knowledge base is constructed through the following steps: Vehicle knowledge is categorized to obtain vehicle perception information and vehicle function information. Vehicle perception information includes external vehicle perception information and state perception information of vehicle components. External vehicle perception information includes environmental perception information and user perception information. User perception information includes voice requests, actions, and / or user information, including user gender, age, number of users, and / or location information within the vehicle cabin. Next, based on the vehicle function information, function points and corresponding function description information are determined. Function description information includes function definition information, application scenario information, and mutual exclusion information between sub-function points included in the function point. Then, based on the vehicle perception information and function points, the function point-vehicle component relationship is determined. Subsequently, based on the pre-defined vehicle function relationships and function points, pre-defined function point relationships are determined. Finally, the pre-defined knowledge base is constructed based on the function point-vehicle component relationships and the function point relationships.

[0132] In this way, through the above steps, a preset knowledge base can be built. This preset knowledge base includes the relationship between function points and vehicle parts and the relationship between preset function points. It can help the server understand user needs and provide good target operation instructions, so as to send the target operation instructions to the vehicle to complete vehicle control, process user needs, and thus improve user experience.

[0133] Please see Figure 8 In some implementations, vehicle function relationships include vehicle function priority relationships and vehicle function conflict relationships. Step 024 (determining preset function point relationships based on preset vehicle function relationships and function points) includes:

[0134] 0241: Based on the vehicle function priority relationship and function points, determine the preset priority relationship in the preset function point relationship;

[0135] 0242: Based on the vehicle function conflict relationship and function points, determine the preset conflict relationship in the preset function point relationship.

[0136] In some implementations, the database construction module is used to determine a preset priority relationship in a preset function point relationship based on vehicle function priority relationships and function points, and to determine a preset conflict relationship in a preset function point relationship based on vehicle function conflict relationships and function points.

[0137] In some implementations, the processor is further configured to determine a preset priority relationship within a preset function point relationship based on vehicle function priority relationships and function points, and to determine a preset conflict relationship within a preset function point relationship based on vehicle function conflict relationships and function points.

[0138] Specifically, vehicle function priority relationship refers to the predefined priority order between different functions in a vehicle intelligent system, which ensures that when multiple functions are activated at the same time or there are potential conflicts, the system can automatically determine which functions should be executed first according to the preset priority.

[0139] Vehicle function conflict refers to the potential interference or contradiction between different functions in a vehicle's intelligent system. When these functions are activated simultaneously, it may lead to system performance degradation, resource contention, or security risks.

[0140] First, based on the vehicle's function priority relationships and function points, the importance and safety of different functions are assessed to determine which functions should have higher execution priority when multiple functions are activated simultaneously. For example, safety functions (such as automatic emergency braking) are usually given higher priority. After determining the function priorities, these priority relationships need to be applied to specific function points.

[0141] Next, based on the vehicle's functional conflict relationships and functional points, identify which functions might interfere with each other or have adverse effects when executed simultaneously. After identifying potential conflicts, these conflict relationships need to be specified for each functional point.

[0142] These two steps establish a clear functional relationship framework for the vehicle's intelligent system. This framework includes the priority order between functional points and their potential conflicts, which helps the system make reasonable decisions during operation. It ensures that the vehicle's operation meets the user's needs while also taking into account the coordination and compatibility between functions, thereby improving the accuracy and safety of operation.

[0143] By clearly defining the relationships between functional points, the system can efficiently manage vehicle functions while ensuring driving safety.

[0144] Please see Figure 9 In some implementations, the method further includes:

[0145] 026: Rewrite the numerical information and / or gear information in the vehicle perception information to generate sensory information describing the numerical information and / or gear information.

[0146] In some implementations, the database construction module is used to rewrite the numerical information and / or gear information in the vehicle perception information to generate sensory information describing the numerical information and / or gear information.

[0147] In some implementations, the processor is also used to rewrite the numerical information and / or gear information in the vehicle perception information to generate sensory information describing the numerical information and / or gear information.

[0148] Specifically, first, the server identifies numerical information and gear information in the vehicle's perceived information, including numerical data such as vehicle speed, engine speed, fuel level, and temperature.

[0149] Next, the server rewrites these numerical and gear information, converting them into more intuitive and easily understood descriptions. For example, 120 km / h is converted to "high-speed driving," and 10 km / h is converted to "slow movement." The interior temperature of 30 degrees Celsius is converted to "very hot," and the exterior temperature of 38 degrees Celsius is converted to "extremely hot." Through this rewriting process, the server generates perceptual information describing the numerical and gear information.

[0150] In this way, by rewriting the numerical information and / or gear information in the vehicle perception information, the server can intuitively understand the user's needs, thereby improving the user experience.

[0151] Please see Figure 10 In some implementations, the method further includes:

[0152] 027: Merge mutually exclusive function points that target the same vehicle component.

[0153] In some implementations, the database building module is used to merge mutually exclusive function points for the same vehicle component.

[0154] In some implementations, the processor is also used to merge mutually exclusive function points targeting the same vehicle component.

[0155] Specifically, first, the server identifies multiple functionalities for the same vehicle component and determines whether there is a mutual exclusion relationship between them. A mutual exclusion relationship means that these functionalities cannot be activated or executed simultaneously. For example, for vehicle seats, heating and ventilation functions may be operationally mutually exclusive because activating both functions at the same time may be inappropriate or unnecessary.

[0156] Next, the server merges the identified mutually exclusive function points. The purpose of merging is to integrate these function points into a higher-level function point for easier management and execution. The merged function point will be able to intelligently select the appropriate sub-function point to execute based on vehicle status and user needs. For example, opening and closing the driver's side window is merged into "Driver's Side Window [Open, Close]"; opening and closing the passenger side window is merged into "Passenger Side Window [Open, Close]"; and turning on and off ambient lighting is merged into "Ambient Lighting [On, Off]".

[0157] Finally, the merged function point information needs to be updated in the preset knowledge base to ensure that the system can correctly reference these merged function points in subsequent operations and decisions.

[0158] In this way, redundancy of the same knowledge in similar functions in the preset database can be reduced, and the memory resources consumed by the preset database can be reduced.

[0159] This application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it implements the steps of the vehicle control method described above.

[0160] It is understood that a computer program includes computer program code. Computer program code can be in the form of source code, object code, executable files, or some intermediate form. Computer-readable storage media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, external hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), and software distribution media, etc.

[0161] In this specification, the terms "specifically," "furthermore," "particularly," "understandably," etc., refer to specific features, structures, materials, or characteristics described in connection with embodiments or examples that are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0162] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of executable request code comprising one or more steps for implementing a particular logical function or process, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order according to the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0163] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A vehicle control method, characterized in that, The method includes: Acquire current external perception information of the vehicle; Based on the current external perception information of the vehicle, determine the user's needs; Based on a pre-built list of vehicle function points, candidate function points are determined according to the user's needs; Based on the candidate function points, obtain the current state perception information of the vehicle components corresponding to the candidate function points; Based on a preset knowledge base, candidate function description information corresponding to the candidate function points is obtained. The target function is determined based on the user requirements, the candidate function points, the current state awareness information, and the candidate function description information. Based on the target function points, determine the target operation instructions; The target operation command is sent to the vehicle to control the vehicle to execute the target operation command.

2. The vehicle control method according to claim 1, characterized in that, The step of determining the target function point based on the user needs, the candidate function points, the current state awareness information, and the candidate function description information includes: Based on the preset function point relationship, the target function point is determined from the candidate function points according to the current state perception information and the candidate function description information. The preset function point relationship includes the preset priority relationship and preset conflict relationship between each function point in the vehicle function point list. The step of determining the target operation instruction based on the target function point includes: Based on the user requirements and the target functional points, the target operation instructions are determined.

3. The vehicle control method according to claim 2, characterized in that, The step of determining the target operation instruction based on the user requirements and the target functional points includes: Based on a pre-defined large language model, the target operation instruction is determined according to the user requirements, the target function points, and the target function description information corresponding to the target function points.

4. The vehicle control method according to claim 1, characterized in that, The preset knowledge base is constructed through the following steps: Vehicle knowledge is classified and processed to obtain vehicle perception information and vehicle function information. The vehicle perception information includes external vehicle perception information and status perception information of vehicle components. The external vehicle perception information includes environmental perception information and user perception information. The user perception information includes voice requests, actions and / or user information. The user information includes user gender, user age, quantity information and / or location information in the vehicle cabin. Based on the vehicle function information, function points and corresponding function description information are determined. The function description information includes function definition information, application scenario information, and mutual exclusion information between the sub-function points included in the function point. Based on the vehicle perception information and the functional points, determine the functional point-vehicle component relationship; Based on the preset vehicle function relationships and the function points, a preset function point relationship is determined. The preset function point relationship includes the preset priority relationship and preset conflict relationship between each function point in the vehicle function point list. The preset knowledge base is constructed based on the functional point-vehicle component relationship and the preset functional point relationship.

5. The vehicle control method according to claim 4, characterized in that, The vehicle function relationships include vehicle function priority relationships and vehicle function conflict relationships. The step of determining the preset function point relationships based on the preset vehicle function relationships and the function points includes: Based on the vehicle function priority relationship and the function points, determine the preset priority relationship in the preset function point relationship; Based on the vehicle function conflict relationship and the function points, determine the preset conflict relationship in the preset function point relationship.

6. The vehicle control method according to claim 4, characterized in that, The method further includes: The numerical information and / or gear information in the vehicle perception information are rewritten to generate sensory information describing the numerical information and / or gear information.

7. The vehicle control method according to claim 4, characterized in that, The method further includes: The function points that target the same vehicle component and are mutually exclusive are merged.

8. A server, characterized in that, The server includes a processor and a memory, the memory storing a computer program that, when executed by the processor, implements the vehicle control method according to any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the steps of the method as described in any one of claims 1-7.

Images