Vehicle control method, server and computer readable storage medium

Abstract

The invention discloses a vehicle control method, a server and a computer readable storage medium. The method includes receiving perception information. And determining a planning function group according to the sensing information. And determining a target instruction group according to the planning function group and the sensing information. And controlling the vehicle according to the target instruction group. Therefore, by analyzing the sensing information, the planning function group is actively determined, and the target instruction group is determined according to the planning function group, so that the vehicle is controlled, and the user experience is improved.

Description

Technical Field

[0001] The present 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 Art

[0002] In the related art, a car voice assistant is used to interact with the user to facilitate the user's operation. However, this type of car voice assistant can only respond passively after the user issues a command, and lacks the ability to actively provide services or suggestions, which affects the user experience. Summary of the invention

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

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

[0005] receiving sensory information;

[0006] Determining a planning function group according to the perception information;

[0007] Determining a target instruction group according to the planning function group and the perception information;

[0008] The vehicle is controlled according to the target instruction group.

[0009] In this way, the server receives the perception information. Then, the server determines the planning function group according to the perception information. Finally, the server determines the target instruction group according to the planning function group and the perception information, and controls the vehicle according to the target instruction group. In this way, by analyzing the perception information, actively determining the planning function group, and determining the target instruction group according to the planning function group, the vehicle can be controlled, thereby improving the user experience.

[0010] In some embodiments, the perception information includes user perception information and environment perception information, and determining the planning function group according to the perception information includes:

[0011] Determining a user intention according to the user perception information, wherein the user perception information includes a user voice request and / or a user behavior;

[0012] Based on a preset function knowledge base, determining a first candidate function group according to the user intention and the environmental perception information;

[0013] The planned function group is determined according to the first candidate function group.

[0014] In this way, the server determines the user intention based on the user perception information, and the user perception information includes the user voice request and / or the user behavior. Then, the server determines the first candidate function group based on the preset function knowledge base, the user intention and the environmental perception information. Finally, the server determines the planning function group based on the first candidate function group. In this way, by analyzing the user perception information and the environmental perception information, understanding the user intention, and determining the planning function group based on the preset function knowledge base, the vehicle can be controlled and the user experience can be improved.

[0015] In some embodiments, the preset function knowledge base includes a plurality of preset function points and a high-frequency voice request expression associated with each of the preset function points, and the determining the first candidate function group based on the preset function knowledge base according to the user intention and the environmental perception information includes:

[0016] In a case where the user perception information includes the user voice request, determining an instruction fit value of each of the preset function points relative to the user intention according to the user intention and the high-frequency voice request expression;

[0017] Determining, according to the user intention, the environment perception information and the preset function points, a functional effective value of each preset function point relative to the user intention;

[0018] Determining a ranking score of the preset function point according to the instruction fitting value and the function effectiveness value;

[0019] The first candidate function group is determined according to the ranking score.

[0020] In this way, when the user perception information includes the user voice request, the server determines the instruction fit value of each preset function point relative to the user intention according to the user intention and high-frequency voice request expression. Next, the server determines the functional effectiveness value of each preset function point relative to the user intention according to the user intention, environmental perception information and preset function points. Then, the server determines the ranking score of the preset function point based on the instruction fit value and the functional effectiveness value. Finally, the server determines the first candidate function group based on the ranking score. In this way, by analyzing the user voice request and the current environmental information, the instruction fit value and functional effectiveness value of each preset function point relative to the user intention are determined, and the first candidate function group is determined according to the ranking score, thereby realizing the control of the vehicle and improving the user experience.

[0021] In some implementations, determining the instruction fit value of each of the preset function points relative to the user intent based on the user intent and the high-frequency voice request expression includes:

[0022] Calculating the similarity between the user intention and the plurality of high-frequency voice request expressions to obtain a plurality of similarity values, wherein the plurality of high-frequency voice request expressions are associated with the same preset function point;

[0023] The maximum value among the plurality of similarity values ​​is determined as the instruction matching value.

[0024] In this way, the server calculates the similarity between the user's intention and multiple high-frequency voice request expressions, and obtains multiple similarity values, where the multiple high-frequency voice request expressions are associated with the same preset function point. Then, the server determines the maximum value of the multiple similarity values ​​as the instruction fit value. In this way, by calculating the similarity between the user's intention and multiple high-frequency voice request expressions, and selecting the maximum similarity value as the instruction fit value, the degree of match between the user's intention and the preset function point can be accurately judged, thereby improving the understanding ability and user experience of the smart cockpit system.

[0025] In some implementations, determining the first candidate function group based on a preset function knowledge base according to the user intention and the environmental perception information includes:

[0026] In the case where the user perception information is the user behavior, determining a functional effective value of each of the preset function points relative to the user intention according to the user intention, the environment perception information and the preset function points;

[0027] Determining the ranking score of the preset function point according to the function effective value;

[0028] The first candidate function group is determined according to the ranking score.

[0029] In this way, when the user perception information is user behavior, the server determines the functional effectiveness value of each preset function point relative to the user intention based on the user intention, environmental perception information and preset function points. Then, the server determines the ranking score of the preset function point based on the functional effectiveness value. Finally, the server determines the first candidate function group based on the ranking score. In this way, by analyzing the user behavior and the current environmental information, the functional effectiveness value of each preset function point relative to the user intention is determined, and the first candidate function group is determined based on the ranking score, thereby achieving control of the vehicle and improving the user experience.

[0030] In some implementations, determining the planned function group according to the first candidate function group includes:

[0031] Determining a second candidate function group according to the first candidate function group based on a preset security rule and the triggering position information of the user perception information;

[0032] The planned function group is determined according to the second candidate function group.

[0033] In this way, based on the preset safety rules and the trigger location information of the user perception information, the server determines the second candidate function group according to the first candidate function group. Then, the server determines the planning function group according to the second candidate function group. In this way, the first candidate function group is screened by the preset safety rules and the trigger location information to form the second candidate function group, and the final planning function group, i.e., the planning function group, is determined according to the second candidate function group, thereby ensuring driving safety and meeting user needs.

[0034] In some embodiments, determining the second candidate function group based on the preset security rule and the trigger location information of the user perception information and the first candidate function group includes:

[0035] Screening the first candidate function group according to the preset safety rule to determine a first temporary execution function group and a first temporary suggestion function group;

[0036] Screening the first temporary execution function group according to the trigger position information to determine a second temporary execution function group and a second temporary suggestion function group;

[0037] determining the execution sub-function group according to the second temporary execution function group;

[0038] Determining the suggested sub-function group according to the first temporary suggested function group and the second temporary suggested function group;

[0039] The second candidate function group is determined according to the execution sub-function group and the suggestion sub-function group.

[0040] In this way, the server screens and processes the first candidate function group according to the preset safety rules to determine the first temporary execution function group and the first temporary recommendation function group. Next, the server screens and processes the first temporary execution function group according to the trigger location information to determine the second temporary execution function group and the second temporary recommendation function group. Then, the server determines the execution sub-function group based on the second temporary execution function group. Subsequently, the server determines the recommendation sub-function group based on the first temporary recommendation function group and the second temporary recommendation function group. Finally, the server determines the second candidate function group based on the execution sub-function group and the recommendation sub-function group. In this way, the first candidate function group is subdivided into multiple temporary function groups through preset safety rules and trigger location information, and the final execution sub-function group and recommendation sub-function group are determined based on the temporary function groups, thereby achieving control of the vehicle, improving user experience, and ensuring driving safety.

[0041] In some implementations, determining the planned function group according to the second candidate function group includes:

[0042] Based on a historical database, the planned function group is determined according to the second candidate function group.

[0043] Thus, based on the historical database, the server determines the planning function group according to the second candidate function group. In this way, through the historical database, according to the user's feedback behavior on the planning function group, the construction of the planning function group is optimized, personalized decision-making and autonomous learning are achieved, thereby improving the user experience.

[0044] In some embodiments, the history database includes an intent and a history planning function group associated with the intent, the history planning function group includes a history execution sub-function group and a history suggestion sub-function group, and the history database is updated according to the following steps:

[0045] When the number of times a preset function point in the historical suggestion sub-function group is adopted reaches a first preset adoption number threshold, adjusting the preset function point to the historical execution sub-function group to update the historical database;

[0046] In the case where the number of times the execution function point associated with the vehicle control instruction for the intended execution is adopted reaches a second preset adoption number threshold, adjusting the preset function point to the historical suggestion sub-function group to update the historical database, the execution function point does not exist in the historical execution sub-function group and does not exist in the historical suggestion sub-function group;

[0047] When the number of rejections of the preset function point in the execution sub-function group reaches a first preset rejection number threshold, adjusting the preset function point to the suggestion sub-function group to update the history database; and / or

[0048] When the rejection count of the preset function point in the suggested sub-function group reaches a second preset rejection count threshold, the preset function point is removed from the second candidate function group to update the history database.

[0049] In this way, the historical database includes the intention and the historical planning function group associated with the intention, the historical planning function group includes the historical execution sub-function group and the historical suggestion sub-function group, and the historical database is updated according to the following steps: First, when the number of adoptions of the preset function point in the historical suggestion sub-function group reaches the first preset adoption number threshold, the preset function point is adjusted to the historical execution sub-function group to update the historical database. Second, when the number of adoptions of the execution function point associated with the vehicle control instruction executed for the intention reaches the second preset adoption number threshold, the preset function point is adjusted to the historical suggestion sub-function group to update the historical database, and the execution function point does not exist in the historical execution sub-function group and does not exist in the historical suggestion sub-function group. Third, when the number of rejections of the preset function point in the execution sub-function group reaches the first preset rejection number threshold, the preset function point is adjusted to the suggestion sub-function group to update the historical database. Fourth, when the number of rejections of the preset function point in the suggestion sub-function group reaches the second preset rejection number threshold, the preset function point is removed from the second candidate function group to update the historical database. In this way, by analyzing the number of adoptions and rejections by users, the historical database can be dynamically adjusted to achieve personalized decision-making and autonomous learning, thereby improving user experience.

[0050] In some embodiments, the perception information includes current vehicle perception information, and determining the target instruction group according to the planning function group and the perception information includes:

[0051] Determining first executability of the preset function points in the execution sub-function group one by one according to the current vehicle perception information;

[0052] Determine the first preset function point in the execution sub-function group whose first executability is executable as a target execution function point;

[0053] Determining the target execution instruction according to the target execution function point;

[0054] The target instruction group is determined according to the target execution instruction.

[0055] In this way, the server determines the first executableness of the preset function points in the execution sub-function group one by one according to the current vehicle perception information. Then, the server determines the first preset function point in the execution sub-function group whose first executableness is executable as the target execution function point. Subsequently, the server determines the target execution instruction according to the target execution function point. Finally, the server determines the target instruction group according to the target execution instruction. In this way, by analyzing the current vehicle perception information, determining the executable function points, and generating the target instruction group, the vehicle can be controlled and the user experience can be improved.

[0056] In some embodiments, determining a target instruction group according to the planning function group and the perception information includes:

[0057] Determining, according to the current vehicle perception information, second executability of the preset function points in the suggested sub-function group one by one;

[0058] Determine the preset function point whose second executability is executable in the execution sub-function group as a target recommended function point;

[0059] Determining the target suggestion instruction according to the target suggestion function point;

[0060] The target instruction group is determined according to the target suggested instruction.

[0061] In this way, the server determines the second executability of the preset function points in the recommended sub-function group one by one according to the current vehicle perception information. Then, the server determines the preset function points in the execution sub-function group whose second executability is executable as the target recommended function points. Then, the server determines the target recommended instructions according to the target recommended function points. Finally, the server determines the target instruction group according to the target recommended instructions. In this way, by analyzing the current vehicle perception information, determining the executable recommended function points, and generating the target instruction group, the vehicle can be controlled and the user experience can be improved.

[0062] In certain embodiments, the method further comprises:

[0063] In the case that both the first executable and the second executable are not executable, feedback information is generated to guide the user to perform a clarification operation according to the feedback information.

[0064] In this way, when both the first executable function and the second executable function are not executable, the server generates feedback information to guide the user to perform clarification operations according to the feedback information. In this way, by providing feedback information and guiding the user to perform clarification operations, the user is helped to solve the problem of the function not being executable, thereby improving the user experience.

[0065] An embodiment of the present application provides a server, which includes a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the above-mentioned vehicle control method is implemented.

[0066] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the vehicle control method described above are implemented.

[0067] Additional aspects and advantages of the embodiments of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0069] Figure 1 It is one of the flowcharts of the vehicle control method of certain embodiments of the present application;

[0070] Figure 2 This is a second flow chart of a vehicle control method according to certain embodiments of the present application;

[0071] Figure 3 This is a third flow chart of a vehicle control method according to certain embodiments of the present application;

[0072] Figure 4 This is a fourth flow chart of a vehicle control method according to certain embodiments of the present application;

[0073] Figure 5 This is a fifth flow chart of a vehicle control method according to certain embodiments of the present application;

[0074] Figure 6 This is the sixth flow chart of the vehicle control method of certain embodiments of the present application;

[0075] Figure 7 This is the seventh flow chart of the vehicle control method of certain embodiments of the present application;

[0076] Figure 8 This is a flowchart of a vehicle control method according to some embodiments of the present application;

[0077] Fig. 9 This is a ninth flowchart of a vehicle control method according to certain embodiments of the present application;

[0078] Fig.10 FIG10 is a flowchart of a vehicle control method according to certain embodiments of the present application;

[0079] Fig.11 This is a flow chart eleven of a vehicle control method according to certain embodiments of the present application;

[0080] Fig.12 This is the twelfth flow chart of the vehicle control method of certain embodiments of the present application. DETAILED DESCRIPTION

[0081] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions from beginning to end. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the embodiments of the present application, and cannot be understood as limiting the embodiments of the present application.

[0082] In today's automotive industry, in-vehicle voice assistants have become a common technology that greatly improves the user's operating convenience and driving experience through human-computer interaction. However, traditional in-vehicle voice assistant systems can usually only respond passively after the user issues a command, which means that they lack the ability to actively provide services or suggestions, which greatly limits the improvement of user experience.

[0083] For example, the lack of active interaction, traditional in-vehicle voice assistants usually do not actively communicate with users, they can only respond after the user issues a command. This passive interaction method limits the flexibility of the system and cannot provide more personalized services.

[0084] Lack of personalized services. Traditional in-car voice assistants are often unable to provide personalized services based on users' personal preferences and habits, and the system cannot provide users with a more intimate and convenient driving experience.

[0085] Based on the above questions, please refer to Figure 1 , the embodiment of the present application provides a vehicle control method, the method comprising:

[0086] 01: Receive perception information;

[0087] 02: Determine the planning function group based on the perception information;

[0088] 03: Determine the target instruction group based on the planned function group and perception information;

[0089] 04: Control the vehicle according to the target instruction group.

[0090] The embodiment of the present application also provides a server, including a memory and a processor. The vehicle control method of the embodiment of the present application can be implemented by the server of the embodiment of the present application. Specifically, a computer program is stored in the memory, and the processor is used to receive perception information. And according to the perception information, a planning function group is determined. And according to the planning function group and the perception information, a target instruction group is determined, and the vehicle is controlled according to the target instruction group.

[0091] The embodiment of the present application also provides a vehicle control device. The vehicle control method of the embodiment of the present application can be implemented by the vehicle control device of the embodiment of the present application. Specifically, the vehicle control device includes a receiving module and a determining module. The receiving module is used to receive perception information. The determining module is used to determine the planning function group according to the perception information. The determining module is also used to determine the target instruction group according to the planning function group and the perception information, and control the vehicle according to the target instruction group.

[0092] Specifically, perception information refers to data collected by various sensors and systems of the vehicle, which is used to understand and respond to user needs and the environment around the vehicle, including user perception information and environmental perception information.

[0093] User perception information refers to data and information about vehicle users (such as drivers and passengers) collected by the vehicle through its sensors and systems, including user voice requests and user behavior. User voice requests refer to requests made by users through voice commands, such as "navigate to the nearest gas station" or "play music." User behavior refers to the user's operations and behavior patterns, such as adjusting seats, switching driving modes, using touch screens, etc. In some embodiments, user perception information also includes user physiological information, such as heart rate, facial expressions, etc., which can help the system assess the user's emotions and comfort.

[0094] Environmental perception information refers to the data and information about the vehicle and the surrounding environment collected by the vehicle through its sensors, cameras and other detection equipment, including the state perception information of the functions of the on-board equipment and the current environmental status information of the vehicle. State perception information involves the functional status of various devices inside the vehicle, such as whether information systems such as the navigation system, entertainment system, and communication system are running, and their current settings and status. Or whether comfort systems such as air conditioning, seat heating / ventilation, and window control are activated, and their current temperature, wind speed and other settings. It can also be whether driving assistance systems such as adaptive cruise control, lane keeping assist, and automatic parking systems are enabled, as well as their current parameters and status. Environmental status information involves traffic conditions, weather conditions, and road conditions.

[0095] The planned function group refers to the function list that is considered to best meet the user's intention or needs through analysis and judgment based on the user's current status and needs, as well as environmental perception and vehicle functional status, and can meet the user's current needs and optimize the vehicle's performance and passenger experience. For example, when the user's request is "turn on ventilation", the system will determine the planned function group as "seat ventilation, air conditioning ventilation and window ventilation" based on the current environmental perception information.

[0096] User demand refers to the expectations and instructions of vehicle users regarding vehicle functions, performance or services in specific situations obtained by the server.

[0097] The target instruction group refers to a series of specific instructions determined by the system based on the planned function group and the current perception information of the vehicle, which can control various systems and equipment of the vehicle to achieve the function points defined in the planned function group. For example, when the user's request is "turn on the ventilation", the system will determine the planned function group as "seat ventilation, air conditioning ventilation and window ventilation" based on the current environmental perception information, and then determine the target instruction group based on the current state perception information of the vehicle's equipment, which may be "execution instruction: turn on the driver's seat ventilation; recommended instruction: turn on the passenger seat ventilation".

[0098] The server receives perception information, namely, user perception information and environment perception information collected by the server through various sensors of the vehicle.

[0099] Next, based on the received perception information, the server analyzes and determines the planned function group that needs to be executed in the current situation. For example, when the user request is "turn on ventilation", the server will analyze this information and determine the planned function group as "seat ventilation, air conditioning ventilation and window ventilation".

[0100] Then, based on the planned function group and the perception information, the system further determines the specific target instruction group for controlling the vehicle's related systems, such as air conditioning, seat heating, navigation, etc. Continuing with the above example, after the server determines that the planned function group is "seat ventilation, air conditioning ventilation, and window ventilation", it determines that the target instruction group may be "execution instruction: turn on the driver's seat ventilation; suggestion instruction: turn on the passenger seat ventilation" based on the state perception information of the current vehicle's equipment.

[0101] Finally, according to the target instruction group, the server sends instructions to each control system of the vehicle to achieve control of the vehicle.

[0102] In summary, in the vehicle control method and server provided in the embodiment of the present application, the server receives the perception information. Then, the server determines the planning function group based on the perception information. Finally, the server determines the target instruction group based on the planning function group and the perception information, and controls the vehicle according to the target instruction group. In this way, by analyzing the perception information, actively determining the planning function group, and determining the target instruction group based on the planning function group, the vehicle can be controlled, thereby improving the user experience.

[0103] See also Figure 2 In some implementations, the perception information includes user perception information and environment perception information. Step 02 (determining a planning function group according to the perception information) includes:

[0104] 021: Determine user intent based on user perception information;

[0105] 022: Based on the preset function knowledge base, according to the user intention and environmental perception information, determine the first candidate function group;

[0106] 023: Determine a planning function group based on the first candidate function group.

[0107] In some embodiments, the determination module is further used to determine the user intention according to the user perception information, and to determine the first candidate function group according to the user intention and the environment perception information based on the preset function knowledge base, and to determine the planning function group according to the first candidate function group.

[0108] In some embodiments, the processor is further configured to determine the user intention based on the user perception information, determine the first candidate function group based on the preset function knowledge base and the user intention and the environment perception information, and determine the planned function group based on the first candidate function group.

[0109] Specifically, the preset function knowledge base refers to a database that includes multiple functions and high-frequency voice request expressions associated with them, which can support the decision-making and operation of the system, that is, provide the information basis required to process user needs and determine the first candidate function group. By analyzing user perception information and environmental perception information, the server can determine the most appropriate function point from the preset knowledge base and generate corresponding operation instructions.

[0110] User voice requests refer to specific requests or commands conveyed by the user to the vehicle through voice commands. They can be simple operating instructions such as "turn on the air conditioning" or "play music", or more complex queries or requests such as "Where is the nearest gas station?" or "Help me find a good restaurant."

[0111] User behavior refers to the various operations and activities performed by users in the vehicle, including touching the screen, pressing buttons, adjusting seats, etc.

[0112] The first candidate function group refers to a group of function points that are initially screened from a preset function knowledge base based on the user's intention and environmental perception information. These function points are considered to be the most likely options to meet the user's current needs.

[0113] The smart cockpit system first needs to understand the user's voice request and behavior to determine the user's intention. Continuing with the above example, based on the user's voice request "turn on the ventilation", the user's intention is determined to be "turn on the ventilation".

[0114] Next, based on the preset function knowledge base, the server selects possible function combinations from the function knowledge base according to the user's intention and environmental perception information to form a first candidate function group. Continuing with the above example, according to the user's demand "turn on ventilation" and the preset function knowledge base, the first candidate function group is determined to be "seat ventilation, air conditioning ventilation, window ventilation, sunroof ventilation and air purifier ventilation".

[0115] Finally, the server further determines the final planning function group based on the first candidate function group. Continuing with the above example, the server determines the planning function group as "seat ventilation, air conditioning ventilation, window ventilation, sunroof ventilation, and air purifier ventilation" based on the first candidate function group "seat ventilation, air conditioning ventilation, window ventilation, and air purifier ventilation".

[0116] In this way, by analyzing user perception information and environmental perception information, understanding user intentions, and determining the planned function group based on the preset function knowledge base, the vehicle can be controlled and the user experience can be improved.

[0117] See also Figure 3 In some embodiments, the preset function knowledge base includes a plurality of preset function points and a high-frequency voice request expression associated with each preset function point. Step 022 (determining a first candidate function group based on the preset function knowledge base, according to user intention and environmental perception information) includes:

[0118] 0221: In the case where the user perception information includes a user voice request, determining the instruction fit value of each preset function point relative to the user intention based on the user intention and the high-frequency voice request expression;

[0119] 0222: Determine the functional effectiveness value of each preset function point relative to the user's intention based on the user's intention, environmental perception information and preset function points;

[0120] 0223: Determine the ranking score of the preset function points based on the instruction fit value and function effectiveness value;

[0121] 0224: Determine the first candidate functional group based on the ranking score.

[0122] In some embodiments, the determination module is further used to determine the instruction fit value of each preset function point relative to the user's intention according to the user's intention and the high-frequency voice request expression when the user perception information includes the user's voice request. And determine the functional effectiveness value of each preset function point relative to the user's intention according to the user's intention, the environmental perception information and the preset function point. The determination module is also used to determine the ranking score of the preset function point according to the instruction fit value and the functional effectiveness value. And determine the first candidate function group according to the ranking score.

[0123] In some embodiments, the processor is further configured to determine the instruction fit value of each preset function point relative to the user's intention according to the user's intention and the high-frequency voice request expression when the user perception information includes the user's voice request. And determine the functional effectiveness value of each preset function point relative to the user's intention according to the user's intention, the environmental perception information and the preset function point. And determine the ranking score of the preset function point according to the instruction fit value and the functional effectiveness value, and determine the first candidate function group according to the ranking score.

[0124] Specifically, high-frequency voice request expressions refer to some specific words or sentences that users often use during voice interaction to express operating instructions or requests for vehicle functions. For example, high-frequency voice request expressions associated with the "turn on the air conditioner" function may include "cooling", "blowing", "turn on the air conditioner", etc.

[0125] The command fit value is used to measure the degree of match between the user's command and the recognized preset function point. When the server receives the user's voice command, it compares the command with the preset function points in the preset function knowledge base to determine which function point best matches the user's intention. Specifically, it refers to the "text similarity" between the user's command and the high-frequency voice request expression of the vehicle function, which is used to measure the degree of match between the user's command and the function recognized by the system. The value range is 0-1, and the higher the value, the higher the degree of match between the command and the function. The command fit value is usually calculated based on the semantic content and contextual information of the user's voice request. A high command fit value means that the user's voice request is very consistent with a certain function point, so the function point is likely to be the operation the user wants to perform.

[0126] The functional effectiveness value is used to measure the degree to which a preset function point satisfies user needs, and can be used to evaluate the applicability and effect of the preset function point in the current vehicle state and environment. Specifically, it refers to the "effectiveness" of being able to realize user intentions or user needs, which is used to measure the degree to which a certain function point satisfies user needs. The value range is 0.5-1. The higher the value, the more effective the function point is and the better it can meet user needs. The server will determine whether the function point can be effectively executed and achieve the expected effect based on the current perception information of the vehicle (such as vehicle speed, temperature, weather, etc.). For example, if the vehicle is in a high-speed driving state, the functional effectiveness value of the function point "open the windows for ventilation" may be low, because opening the windows at high speeds may cause greater wind noise and unsafe factors.

[0127] The ranking score refers to a score obtained after a comprehensive evaluation of the candidate functions according to multiple dimensions during the construction of the first candidate function group, which is used to determine the ranking of the preset function points obtained by screening in the first candidate function group. In some embodiments, the ranking score is calculated as follows: Among them, T represents the instruction fitting value, a t represents the linear weight of the instruction fit value, b t represents the power weight of the instruction fit value, N represents the effective value of the function, a n The linear weight representing the effective value of the function, b n The power weight representing the effective value of the function. When the weight of a dimension is 0, the corresponding value is 1 (no gain).

[0128] It should be noted that in some embodiments, the ranking of the first candidate function group can also be obtained directly by order fusion, that is, directly focusing on the ranking without caring about the specific value, sorting and fusion by ranking dimension, which is suitable for processing scenarios that only require ranking but do not require accurate scoring. The advantage of this method is that it can get rid of the influence of scale differences between sub-modules, but the disadvantage is that a lot of information will be lost.

[0129] When the user perception information includes voice requests, the system will calculate the instruction fit value of each preset function point relative to the user's intention based on the user's intention and high-frequency voice request expression. The instruction fit value reflects the degree of match between the user request and the function point.

[0130] Next, the server calculates the functional effectiveness value of each preset function point relative to the user intention based on the user intention, environmental perception information and preset function points. The functional effectiveness value reflects the effectiveness of each function point in meeting user needs in the current environment.

[0131] The server then combines the instruction fit value and the function effectiveness value to calculate a ranking score for each preset function point.

[0132] Finally, the server selects the first few preset function points with the highest scores from the preset function points according to the ranking scores to form a first candidate function group.

[0133] In this way, by analyzing the user's voice request and the current environmental information, the command fit value and function effectiveness value of each preset function point relative to the user's intention are determined, and the first candidate function group is determined according to the ranking score, thereby achieving control of the vehicle and improving the user experience.

[0134] See also Figure 4 In some implementations, step 0221 (determining the instruction fit value of each preset function point relative to the user's intention based on the user's intention and the high-frequency voice request expression) includes:

[0135] 02211: Calculate the similarity between the user's intention and multiple high-frequency voice request expressions to obtain multiple similarity values;

[0136] 02212: Determine the maximum value among multiple similar values ​​as the instruction fitting value.

[0137] In some embodiments, the determination module is further used to calculate the similarity between the user intention and multiple high-frequency voice request expressions to obtain multiple similarity values, and determine the maximum value of the multiple similarity values ​​as the instruction matching value.

[0138] In some embodiments, the processor is further configured to calculate the similarity between the user's intention and multiple high-frequency voice request expressions to obtain multiple similarity values, and determine the maximum value of the multiple similarity values ​​as the instruction fit value.

[0139] Specifically, the association of multiple high-frequency voice request expressions with the same preset function point means that each preset function point can be associated with multiple high-frequency voice request expressions. For example, the "turn on air conditioning" function can be associated with multiple high-frequency voice request expressions such as "cooling", "blowing" and "turn on air conditioning".

[0140] For each preset function point, the server uses natural language processing technology to calculate the semantic similarity between all the associated high-frequency voice request expressions and the user's intention. For example, algorithms such as the bag-of-words model, TF-IDF, and neural networks are used to analyze the text content of the user's voice request and the text content of the high-frequency voice request expressions.

[0141] Next, the server selects the largest one from these similarity values ​​as the instruction fitting value of the preset function point, and the instruction fitting value represents the similarity between the user intention and the high-frequency voice request expression that best matches the preset function point.

[0142] In this way, by calculating the similarity between user intention and multiple high-frequency voice request expressions, and selecting the largest similarity value as the command fitting value, the degree of match between user intention and preset function points can be accurately judged, thereby improving the understanding ability and user experience of the smart cockpit system.

[0143] See also Figure 5 In some implementations, step 022 (determining a first candidate function group based on a preset function knowledge base, according to user intent and environmental perception information) includes:

[0144] 0224: In the case where the user perception information is user behavior, determining the functional effective value of each preset function point relative to the user intention based on the user intention, the environmental perception information and the preset function points;

[0145] 0225: Determine the ranking score of the preset function points based on the effective value of the function;

[0146] 0226: Determine the first candidate functional group based on the ranking score.

[0147] In some embodiments, the determination module is used to determine the functional effectiveness value of each preset function point relative to the user intention according to the user intention, the environmental perception information and the preset function point when the user perception information is the user behavior. And determine the ranking score of the preset function point according to the functional effectiveness value. And determine the first candidate function group according to the ranking score.

[0148] In some embodiments, the processor is further configured to determine, when the user perception information is user behavior, the function effectiveness value of each preset function point relative to the user intention according to the user intention, the environment perception information and the preset function point, and determine the ranking score of the preset function point according to the function effectiveness value, and determine the first candidate function group according to the ranking score.

[0149] Specifically, when the user perception information is user behavior, that is, the user perception information does not include a user voice request, the server determines the functional effectiveness value of each preset function point relative to the user intention based on the user intention, the environmental perception information, and the preset function point. Then, the server directly determines the ranking score of the preset function point based on the functional effectiveness value. Finally, the server determines the first candidate function group based on the ranking score.

[0150] In this way, by analyzing user behavior and current environmental information, the functional effectiveness value of each preset function point relative to the user's intention is determined, and the first candidate function group is determined according to the ranking score, thereby achieving control of the vehicle and improving the user experience.

[0151] See also Figure 6 In some embodiments, step 023 (determining a planning function group according to the first candidate function group) includes:

[0152] 0231: determining a second candidate function group according to the first candidate function group based on the preset security rule and the trigger position information of the user perception information;

[0153] 0232: Determine a planning function group based on the second candidate function group.

[0154] In some embodiments, the determination module is further configured to determine the second candidate function group according to the first candidate function group based on the preset safety rules and the trigger position information of the user perception information, and determine the planned function group according to the second candidate function group.

[0155] In some embodiments, the processor is further configured to determine a second candidate function group according to the first candidate function group based on the preset safety rules and the trigger position information of the user perception information, and determine a planned function group according to the second candidate function group.

[0156] Specifically, preset safety rules refer to built-in safety standards and restrictions that are used to ensure that the use of vehicle functions meets safety standards and avoids potential dangerous situations. That is, when building a planning function group, you need to consider which preset function points may pose risks to the user's driving safety or scare the user. By classifying functions with safety risks into a suggestion set, the possibility of users being disturbed or frightened during driving can be effectively reduced, ensuring driving safety. For example, the seat massage function is suddenly turned on while driving at high speed, or while the vehicle is driving, it is prohibited to perform functions such as making calls and viewing videos. These functions will be directly divided into the suggestion set, and then decide whether to give suggestions based on other weight rankings or other data information.

[0157] The trigger location information of user perception information means that the function will give priority to users in the trigger location, and users in other locations will tend to be recommended. Based on the trigger location information, more personalized function recommendations can be provided. For example, when the user sits in the co-pilot seat, the probability of turning on the co-pilot seat massage function will be higher, thereby improving the user experience.

[0158] The server first screens the first candidate function group according to the preset safety rules. Continuing with the above example, when the vehicle is currently in a high-speed driving state, opening the sunroof may generate large wind noise and unsafe factors, so the preset function point of sunroof ventilation is excluded.

[0159] Next, consider the triggering position information of the user perception information, that is, the position of the user in the vehicle (such as the driver's seat, the front passenger seat, etc.). Continuing with the above example, if the server detects that the driver or passenger is far from the sunroof, other functions closer to the user, such as seat ventilation or air conditioning ventilation, may be prioritized, rather than sunroof ventilation.

[0160] In this way, the first candidate function group is screened by preset safety rules and trigger location information to form a second candidate function group, and the final planned function group, i.e., the planned function group, is determined based on the second candidate function group, thereby ensuring driving safety and meeting user needs.

[0161] See also Figure 7 In some embodiments, step 0231 (determining the second candidate function group according to the first candidate function group based on the preset security rule and the triggering position information of the user perception information) includes:

[0162] 02311: Screening the first candidate function group according to the preset safety rules to determine the first temporary execution function group and the first temporary suggestion function group;

[0163] 02312: screening the first temporary execution function group according to the trigger position information to determine the second temporary execution function group and the second temporary suggestion function group;

[0164] 02313: Determine an execution sub-function group according to the second temporary execution function group;

[0165] 02314: Determine a suggested sub-function group according to the first temporary suggested function group and the second temporary suggested function group;

[0166] 02315: Determine a second candidate function group according to the execution sub-function group and the suggestion sub-function group.

[0167] In some embodiments, the determination module is further used to screen the first candidate function group according to the preset safety rules to determine the first temporary execution function group and the first temporary suggestion function group. And the first temporary execution function group is screened according to the trigger position information to determine the second temporary execution function group and the second temporary suggestion function group. The determination module is also used to determine the execution sub-function group according to the second temporary execution function group. And the suggestion sub-function group is determined according to the first temporary suggestion function group and the second temporary suggestion function group. And the second candidate function group is determined according to the execution sub-function group and the suggestion sub-function group.

[0168] In some embodiments, the processor is further configured to screen the first candidate function group according to a preset safety rule to determine a first temporary execution function group and a first temporary suggestion function group. And screen the first temporary execution function group according to the trigger position information to determine a second temporary execution function group and a second temporary suggestion function group. The processor is further configured to determine an execution sub-function group according to the second temporary execution function group. And determine a suggestion sub-function group according to the first temporary suggestion function group and the second temporary suggestion function group. And determine a second candidate function group according to the execution sub-function group and the suggestion sub-function group.

[0169] Specifically, the server screens the first candidate function group according to the preset safety rules, and determines the first temporary execution function group and the first temporary recommendation function group. Continuing with the above example, the first candidate function group "seat ventilation, air conditioning ventilation, window ventilation, sunroof ventilation and air purifier ventilation" is screened according to the preset safety rules. Since the vehicle is traveling at high speed, window ventilation is considered to require further confirmation by the user, and sunroof ventilation is considered unsafe. Therefore, the first temporary execution function group "seat ventilation, air conditioning ventilation and air purifier ventilation" is determined to be and the first temporary recommendation function group is "window ventilation".

[0170] Next, the server screens the first temporary execution function group according to the trigger location information to determine the second temporary execution function group and the second temporary recommendation function group. Continuing with the above example, seat ventilation may be directly executed because the user sits directly on the seat, while air conditioning ventilation and air purifier ventilation may be recommended for execution because they have an impact on the entire vehicle interior environment. Therefore, the second temporary execution function group is determined to be "seat ventilation" and the second temporary recommendation function group is determined to be "air conditioning ventilation and air purifier ventilation".

[0171] Then, the server determines the execution sub-function group according to the second temporary execution function group. Continuing with the above example, the second temporary execution function group "seat ventilation" is determined as the execution sub-function group "seat ventilation".

[0172] Subsequently, the server determines a recommended sub-function group according to the first temporary recommended function group and the second temporary recommended function group. Continuing with the above example, according to the first temporary recommended function group "window ventilation" and the second temporary recommended function group "air conditioning ventilation and air purifier ventilation", the recommended sub-function group is determined to be "air conditioning ventilation, window ventilation and air purifier ventilation".

[0173] Finally, the server determines the second candidate function group according to the executed sub-function group and the suggested sub-function group. Continuing with the above example, according to the executed sub-function group "seat ventilation" and the suggested sub-function group "air conditioning ventilation, window ventilation and air purifier ventilation", the second candidate function group is determined to be "seat ventilation (execution), air conditioning ventilation (suggestion), window ventilation (suggestion) and air purifier ventilation (suggestion)".

[0174] In this way, by presetting safety rules and triggering location information, the first candidate function group is subdivided into multiple temporary function groups, and the final execution sub-function group and recommended sub-function group are determined according to the temporary function groups, thereby achieving control of the vehicle, improving user experience, and ensuring driving safety.

[0175] See also Figure 8 In some embodiments, step 0232 (determining a planning function group according to the second candidate function group) includes:

[0176] 02321: Based on the historical database and the second candidate functional group, determine the planning functional group.

[0177] In some embodiments, the determination module is further configured to determine the planned function group based on the second candidate function group based on a historical database.

[0178] In some embodiments, the processor is further configured to determine the planned function group according to the second candidate function group based on the historical database.

[0179] Specifically, the history database refers to a database that stores the user's past usage habits, preferences, and behaviors. The database includes the user's intentions and the historical planning function groups associated with these intentions, that is, the function combinations that the user has used in different situations, and records the frequency, preference, time, etc. of the user's use of the functions.

[0180] The server first accesses the history database, which contains information such as the user's past interaction records, function usage preferences, common operation modes, etc.

[0181] Next, the server analyzes and matches each function in the second candidate function group with the data in the history database.

[0182] Finally, based on the analysis results of the historical data, the server selects the function that best matches the user's historical preferences and behavior patterns from the second candidate function group to form a planned function group.

[0183] Continuing with the above example, if in the historical database, the user refuses the server to determine the air purifier ventilation function point every time he needs to turn on the ventilation, then the preset function point "air purifier ventilation" will be removed from the second candidate function group. Therefore, the final planning function group is "seat ventilation (execution), air conditioning ventilation (recommendation) and window ventilation (recommendation)".

[0184] In this way, through the historical database, according to the user's feedback behavior on the planning function group, the construction of the planning function group is optimized, personalized decision-making and autonomous learning are achieved, thereby improving the user experience.

[0185] See also Fig. 9 In some embodiments, the history database includes an intent and a history planning function group associated with the intent, the history planning function group includes a history execution sub-function group and a history suggestion sub-function group, and the history database is updated according to the following steps:

[0186] 023211: when the number of times a preset function point in the historical suggestion sub-function group is adopted reaches a first preset adoption number threshold, adjusting the preset function point to the historical execution sub-function group to update the historical database;

[0187] 023212: when the number of times the execution function point associated with the vehicle control instruction intended to be executed is adopted reaches a second preset adoption number threshold, adjusting the preset function point to the historical suggestion sub-function group to update the historical database;

[0188] 023213: when the number of rejections of the preset function point in the execution sub-function group reaches a first preset rejection number threshold, adjusting the preset function point to the suggestion sub-function group to update the history database; and / or

[0189] 023214: When the number of rejections of a preset function point in the proposed sub-function group reaches a second preset rejection threshold, remove the preset function point from the second candidate function group to update the history database.

[0190] In certain embodiments, the vehicle control device further includes a database update module, which is used to adjust the preset function point to the historical execution sub-function group when the number of times the preset function point in the historical suggestion sub-function group is adopted reaches a first preset adoption number threshold, so as to update the historical database. And when the number of times the execution function point associated with the vehicle control instruction for intended execution is adopted reaches a second preset adoption number threshold, the preset function point is adjusted to the historical suggestion sub-function group to update the historical database. The database update module is also used to adjust the preset function point to the suggestion sub-function group when the number of times the preset function point in the execution sub-function group is rejected reaches a first preset rejection number threshold, so as to update the historical database. And when the number of times the preset function point in the suggestion sub-function group is rejected reaches a second preset rejection number threshold, the preset function point is removed from the second candidate function group to update the historical database.

[0191] In certain embodiments, the processor is further configured to adjust the preset function point to the historical execution sub-function group when the number of times the preset function point in the historical suggestion sub-function group is adopted reaches a first preset adoption number threshold, so as to update the historical database. And when the number of times the execution function point associated with the vehicle control instruction intended to be executed is adopted reaches a second preset adoption number threshold, the preset function point is adjusted to the historical suggestion sub-function group to update the historical database. The processor is further configured to adjust the preset function point to the suggestion sub-function group when the number of times the preset function point in the execution sub-function group is rejected reaches a first preset rejection number threshold, so as to update the historical database. And when the number of times the preset function point in the suggestion sub-function group is rejected reaches a second preset rejection number threshold, the preset function point is removed from the second candidate function group to update the historical database.

[0192] Specifically, first, if the number of adoptions of a preset function point in a historical suggestion sub-function group reaches a first preset adoption threshold, the server will deem the function to be very important to the user and will adjust the function point to the historical execution sub-function group. That is, the next time a similar scenario occurs, the system will directly execute the function without the need for the user to confirm again. For example, users often say "I'm hot" when entering a vehicle, and the system recommends the "turn on the air conditioner" function to the user based on semantic understanding. Historical data: The historical database records the user's behavior of adopting the "turn on the air conditioner" suggestion many times. Update: Promote "turn on the air conditioner" from the "suggestion" group to the "execution" group. The next time the user enters the vehicle and says "I'm hot", the system will directly turn on the air conditioner without the user's confirmation.

[0193] Second, if the execution function point associated with the vehicle control instruction executed for a specific intent is adopted the number of times reaching the second preset adoption number threshold, the function point is adjusted to the historical suggestion sub-function group. The user says "I'm tired" after a long drive, and the system recommends the "seat massage" function to the user based on semantic understanding. Historical data: The historical database records the user's behavior of choosing to execute the "turn on music" function after receiving the "seat massage" suggestion. Update: Promote "turn on music" from the "candidate function group" to the "suggestion" group. The next time the user enters the vehicle and says "I'm tired", the system will recommend the "turn on music" function.

[0194] Third, if the number of rejections for a preset function point in the execution sub-function group reaches the first preset rejection threshold, the function point is adjusted to the suggestion sub-function group. When the user says "close the windows" when it is raining, the system directly executes the "close windows" function based on semantic understanding. Historical data: The historical database records the user's behavior of opening the windows after closing them many times. Update: Adjust "close windows" from the "execution" group to the "suggestion" group. The next time the user enters the vehicle and says "close the windows", the system will ask the user if he really needs to close the windows.

[0195] Fourth, if the number of rejections of a preset function point in the recommended sub-function group reaches the second preset rejection threshold, that is, when the user ignores the function recommended by the system many times, the system will consider that the function is not important to the user, and remove the function point from the second candidate function group. For example, the user often says "I'm cold" in cold weather, and the system recommends the "seat heating" function to the user based on semantic understanding. Historical data: The historical database records the user's behavior of ignoring the "seat heating" recommendation many times. Update: Remove "seat heating" from the "recommendation" group. The next time the user enters the vehicle and says "I'm cold", the system will no longer recommend the "seat heating" function.

[0196] In this way, by analyzing the number of times users adopt and reject solutions, the historical database can be dynamically adjusted to achieve personalized decision-making and autonomous learning, thereby improving user experience.

[0197] See also Fig.10 In some embodiments, the perception information includes current vehicle perception information. Step 03 (determining a target instruction group according to the planning function group and the perception information) includes:

[0198] 031: Determine first executability of preset function points in the execution sub-function group one by one according to the current vehicle perception information;

[0199] 032: Determine the first preset function point with the first executable property as executable in the execution sub-function group as the target execution function point;

[0200] 033: Determine the target execution instructions according to the target execution function points;

[0201] 034: Execute instructions according to the target and determine the target instruction group.

[0202] In some embodiments, the determination module is further used to determine the first executableness of the preset function points in the execution sub-function group one by one according to the current vehicle perception information. And determine the first preset function point in the execution sub-function group whose first executableness is executable as the target execution function point. The determination module is also used to determine the target execution instruction according to the target execution function point. And determine the target instruction group according to the target execution instruction.

[0203] In some embodiments, the processor is further configured to determine the first executableness of the preset function points in the execution sub-function group one by one according to the current vehicle perception information, and to determine the first preset function point in the execution sub-function group whose first executableness is executable as the target execution function point. The processor is further configured to determine the target execution instruction according to the target execution function point, and to determine the target instruction group according to the target execution instruction.

[0204] Specifically, the current vehicle perception information refers to the status information about each device of the vehicle itself obtained by the vehicle through sensors and other devices.

[0205] Target execution instructions refer to specific instructions determined and generated based on the user's intention, the vehicle's current state and environmental perception information, which are used to control the vehicle's related systems or devices to perform specific operations.

[0206] According to the current vehicle perception information, determine whether the preset function points in the execution sub-function group are executable one by one. The executable depends on the current vehicle status and environment. For example, if the temperature inside the car is already very low, the "turn on the air conditioner" function cannot be executed. Find the first executable preset function point in the execution sub-function group and determine it as the target execution function point.

[0207] Next, according to the target execution function point, the instructions required to execute the function are determined. Finally, the target execution instructions are added to the target instruction group to form the final target instruction group.

[0208] Continuing with the above example, the vehicle obtains the current vehicle perception information from the sensor: "Seat occupancy information: the main and front passenger seats are occupied; wake-up sound zone: main driver's seat; air conditioning on state: off; window open state: on; seat ventilation state: off". Because the first in the planning function group is "seat ventilation" and the seat ventilation is off, the target execution function point is determined to be "seat ventilation". Subsequently, according to the target execution function point "seat ventilation", the target execution instruction is determined to be "turn on the main driver's seat ventilation".

[0209] In this way, by analyzing the current vehicle perception information, determining the executable function points, and generating the target instruction group, the vehicle can be controlled and the user experience can be improved.

[0210] See also Fig.11 In some embodiments, step 03 (determining a target instruction group according to the planning function group and the perception information) includes:

[0211] 035: Determine the second executability of the preset function points in the suggested sub-function group one by one according to the current vehicle perception information;

[0212] 036: Determine the preset function point with the second executable degree as executable in the execution sub-function group as the target recommended function point;

[0213] 037: Determine the target suggestion instructions based on the target suggestion function points;

[0214] 038: Determine the target instruction group based on the target recommended instructions.

[0215] In some embodiments, the determination module is further used to determine the second executability of the preset function points in the suggested sub-function group one by one according to the current vehicle perception information. And determine the preset function points in the execution sub-function group whose second executability is executable as target suggested function points. The determination module is also used to determine the target suggested instruction according to the target suggested function point. And determine the target instruction group according to the target suggested instruction.

[0216] In some embodiments, the processor is further configured to determine the second executability of the preset function points in the suggested sub-function group one by one according to the current vehicle perception information, and to determine the preset function points in the execution sub-function group whose second executability is executable as target suggested function points. The processor is further configured to determine the target suggested instruction according to the target suggested function point, and to determine the target instruction group according to the target suggested instruction.

[0217] Specifically, the target suggestion instruction refers to a specific instruction determined and generated based on the user's intention, the vehicle's current state and environmental perception information, which is used to suggest that the relevant systems or devices controlling the vehicle perform specific operations.

[0218] According to the current vehicle perception information, determine whether the preset function points in the execution sub-function group are executable one by one. The executable depends on the current vehicle status and environment. For example, if the temperature inside the car is already very low, the "turn on the air conditioner" function cannot be executed. Find the first executable preset function point in the recommended sub-function group and determine it as the target recommended function point.

[0219] Next, according to the target suggested function point, the instructions required to execute the function are determined to generate the target suggested instructions. Finally, the target suggested instructions are added to the target instruction group to form the final target instruction group.

[0220] Continuing with the above example, the vehicle obtains the current vehicle perception information from the sensor as follows: "Seat occupancy information: Passenger seat and front passenger seat occupied; Wake-up sound zone: Passenger seat; Air conditioning on status: off; Window opening status: open; Seat ventilation status: off". Because the first ranked sub-function group is "Air conditioning on" and the air conditioning on status is off, the target recommended function point is determined to be "Air conditioning ventilation". Subsequently, based on the target recommended function point "Air conditioning ventilation", the target recommended instruction is determined to be "Turn on the air conditioning internal circulation".

[0221] Finally, the target instruction group determined was "turn on the driver's seat ventilation (execution); turn on the air conditioning internal circulation (recommendation)".

[0222] In this way, by analyzing the current vehicle perception information, determining the executable recommended function points, and generating a target instruction group, the vehicle can be controlled and the user experience can be improved.

[0223] See also Fig.12 In some embodiments, the method further comprises:

[0224] 039: When both the first executability and the second executability are not executable, feedback information is generated to guide the user to perform clarification operations according to the feedback information.

[0225] In some embodiments, the vehicle control device further includes a generation module, and the generation module is used to generate feedback information when both the first executableness and the second executableness are not executable, so as to guide the user to perform a clarification operation according to the feedback information.

[0226] In some embodiments, the processor is further configured to generate feedback information when both the first executableness and the second executableness are not executable, so as to guide the user to perform a clarification operation according to the feedback information.

[0227] Specifically, feedback information refers to the information provided by the system to users to inform them of the system's understanding and response to their requests or operations. It can guide users to clarify or rephrase their requests if the user's requests are not correctly understood.

[0228] When both the first executability and the second executability are not executable, it means that the system cannot determine the user's needs based on the current information and needs further clarification from the user. The system can provide multiple ways to guide the user to clarify, such as: voice interaction: asking the user what operation needs to be performed. Or, text prompt: prompting the user to enter instructions or select a function. Or, image display: displaying a list of optional functions for the user to choose.

[0229] For example, if the user is drowsy in the car, the smart cockpit system will determine the function points of "turn on the ventilation system" and "play refreshing music" based on the user behavior and current environmental information to form the first candidate function group.

[0230] According to the preset safety rules and trigger position information, the second candidate function group is formed, including the functions of "turn on the ventilation system" and "play refreshing music". Based on the historical database, "play refreshing music" is promoted to the execution sub-function group. According to the current vehicle perception information, it is judged that the functions of "turn on the ventilation system" and "play refreshing music" are not executable. For example, the vehicle is driving and the temperature inside the car is already very low. The system generates feedback information, prompting the user "The ventilation or music playing functions cannot be executed at present. What do you need to do?" The user can reply "I want to adjust the seat position" by voice or text, and the system performs the corresponding operation according to the user's instructions.

[0231] In this way, by providing feedback and guiding users to clarify operations, we can help users solve problems where functions cannot be executed and improve user experience.

[0232] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the vehicle control method described above are implemented.

[0233] It is understood that a computer program includes computer program code. The computer program code may be in source code form, object code form, executable file or some intermediate form. Computer readable storage media may include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), and software distribution medium.

[0234] In the description of this specification, the descriptions with reference to the terms "specifically", "further", "particularly", "understandably", etc. are intended to mean that the specific features, structures, materials or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms are not intended to refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0235] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code that includes one or more executable requests for implementing specific logical functions or steps of a process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0236] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A vehicle control method, characterized in that: The method comprises: receiving sensory information; Determining a planning function group according to the perception information; Determining a target instruction group according to the planning function group and the perception information; The vehicle is controlled according to the target instruction group.

2. The method according to claim 1, characterized in that The perception information includes user perception information and environment perception information, and determining the planning function group according to the perception information includes: Determining a user intention according to the user perception information, wherein the user perception information includes a user voice request and / or a user behavior; Based on a preset function knowledge base, determining a first candidate function group according to the user intention and the environmental perception information; The planned function group is determined according to the first candidate function group.

3. The method according to claim 2, characterized in that The preset function knowledge base includes a plurality of preset function points and a high-frequency voice request expression associated with each of the preset function points. The determining of the first candidate function group based on the preset function knowledge base and according to the user intention and the environmental perception information includes: In a case where the user perception information includes the user voice request, determining an instruction fit value of each of the preset function points relative to the user intention according to the user intention and the high-frequency voice request expression; Determining, according to the user intention, the environment perception information and the preset function points, a functional effective value of each preset function point relative to the user intention; Determining a ranking score of the preset function point according to the instruction fitting value and the function effectiveness value; The first candidate function group is determined according to the ranking score.

4. The method according to claim 3, characterized in that The determining, according to the user intention and the high-frequency voice request expression, the instruction fitting value of each preset function point relative to the user intention includes: Calculating the similarity between the user intention and the plurality of high-frequency voice request expressions to obtain a plurality of similarity values, wherein the plurality of high-frequency voice request expressions are associated with the same preset function point; The maximum value among the plurality of similarity values ​​is determined as the instruction matching value.

5. The method according to claim 2, characterized in that: The determining, based on a preset function knowledge base and according to the user intention and the environmental perception information, a first candidate function group includes: In the case where the user perception information is the user behavior, determining a functional effective value of each of the preset function points relative to the user intention according to the user intention, the environment perception information and the preset function points; Determining the ranking score of the preset function points according to the function effective value; The first candidate function group is determined according to the ranking score.

6. The method according to claim 2, characterized in that The determining the planned function group according to the first candidate function group includes: Determining a second candidate function group according to the first candidate function group based on a preset security rule and the triggering position information of the user perception information; The planned function group is determined according to the second candidate function group.

7. The method according to claim 6, characterized in that The determining of the second candidate function group based on the preset security rule and the trigger position information of the user perception information and the first candidate function group includes: Screening the first candidate function group according to the preset safety rule to determine a first temporary execution function group and a first temporary suggestion function group; Screening the first temporary execution function group according to the trigger position information to determine a second temporary execution function group and a second temporary suggestion function group; determining the execution sub-function group according to the second temporary execution function group; Determining the suggested sub-function group according to the first temporary suggested function group and the second temporary suggested function group; The second candidate function group is determined according to the execution sub-function group and the suggestion sub-function group.

8. The method according to claim 7, characterized in that The determining the planned function group according to the second candidate function group includes: Based on a historical database, the planned function group is determined according to the second candidate function group.

9. The method according to claim 8, characterized in that The historical database includes an intention and a historical planning function group associated with the intention, the historical planning function group includes a historical execution sub-function group and a historical suggestion sub-function group, and the historical database is updated according to the following steps: When the number of times a preset function point in the historical suggestion sub-function group is adopted reaches a first preset adoption number threshold, adjusting the preset function point to the historical execution sub-function group to update the historical database; In the case where the number of times the execution function point associated with the vehicle control instruction for the intended execution is adopted reaches a second preset adoption number threshold, adjusting the preset function point to the historical suggestion sub-function group to update the historical database, the execution function point does not exist in the historical execution sub-function group and does not exist in the historical suggestion sub-function group; When the number of rejections of the preset function point in the execution sub-function group reaches a first preset rejection number threshold, adjusting the preset function point to the suggestion sub-function group to update the history database; and / or When the rejection count of the preset function point in the suggested sub-function group reaches a second preset rejection count threshold, the preset function point is removed from the second candidate function group to update the history database.

10. The method according to claim 7, characterized in that The perception information includes current vehicle perception information, and determining the target instruction group according to the planning function group and the perception information includes: Determining first executability of the preset function points in the execution sub-function group one by one according to the current vehicle perception information; Determine the first preset function point in the execution sub-function group whose first executability is executable as a target execution function point; Determining the target execution instruction according to the target execution function point; The target instruction group is determined according to the target execution instruction.

11. The method according to claim 10, characterized in that The step of determining a target instruction group according to the planning function group and the perception information includes: Determining, according to the current vehicle perception information, second executability of the preset function points in the suggested sub-function group one by one; Determine the preset function point whose second executability is executable in the execution sub-function group as a target recommended function point; Determining the target suggestion instruction according to the target suggestion function point; The target instruction group is determined according to the target suggested instruction.

12. The method according to claim 11, characterized in that The method further comprises: In the case that both the first executable and the second executable are not executable, feedback information is generated to guide the user to perform a clarification operation according to the feedback information.

13. A server, characterized in that: The server includes a processor and a memory, wherein a computer program is stored in the memory. When the computer program is executed by the processor, the method according to any one of claims 1 to 12 is implemented.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 12 are implemented.

Images