Vehicle-mounted function guiding method and device, vehicle and program product

Abstract

The invention discloses a vehicle-mounted function guiding method and device, a vehicle and a program product, and is applied to the technical field of vehicle control, and the method comprises the steps: obtaining the current attribute data and use habit data of a guiding object; performing identification processing according to the current attribute data to obtain intention prediction information of the guide object; wherein the intention prediction information is used for indicating whether the guiding object intends to operate at least one vehicle-mounted function or not; if the intention prediction information indicates that the guide object intends to operate at least one vehicle-mounted function, obtaining a target vehicle-mounted function and initial guide information according to the intention prediction information and the current attribute data; correcting the initial guide information by using the use habit data to obtain target guide information; and performing guidance control on the target vehicle-mounted function based on the target guidance information. According to the invention, the guiding precision of the vehicle-mounted function can be improved, so that the use experience of the vehicle-mounted function is improved.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to an on-board function guidance method, device, vehicle, and program product. Background Technology

[0002] With the development of vehicle technology and the advancement of intelligent connectivity technology, in-vehicle functions have become increasingly rich and complex. This brings great convenience to older car users, but new car users are usually unfamiliar with various in-vehicle functions and their operation, requiring them to spend a lot of time and energy to learn and adapt. Therefore, this also brings new challenges to new car users.

[0003] Currently, the functional guidance provided to users is usually divided into three types: paper user manuals that come with the vehicle, electronic manuals in the vehicle, and functional guidance interfaces displayed by the central control system. The guidance information in these methods is usually pre-set, which leads to a series of inconveniences for users when using in-vehicle functions. Summary of the Invention

[0004] This application provides a vehicle function guidance method, device, vehicle, and program product to improve the guidance accuracy of vehicle functions, thereby enhancing the user experience of vehicle functions.

[0005] On the one hand, embodiments of this application provide a method for guiding in-vehicle functions, including the following steps: Retrieve the current attribute data and usage habit data of the bootstrap object; Based on the current attribute data, identification processing is performed to obtain the intent prediction information of the guided object; wherein, the intent prediction information is used to indicate whether the guided object intends to operate at least one in-vehicle function; If the intent prediction information indicates that the guided object intends to operate at least one of the vehicle functions, then the target vehicle function and initial guidance information are obtained based on the intent prediction information and the current attribute data. The initial guidance information is corrected using the aforementioned usage habit data to obtain the target guidance information; The target vehicle function is guided and controlled based on the target guidance information.

[0006] On the other hand, embodiments of this application provide an in-vehicle function guidance device, including: The acquisition module is used to obtain the current attribute data and usage habit data of the bootstrap object; The first processing module is used to perform identification processing based on the current attribute data to obtain the intent prediction information of the guided object; wherein, the intent prediction information is used to indicate whether the guided object intends to operate at least one in-vehicle function; The second processing module is used to obtain the target vehicle function and initial guidance information based on the intent prediction information and the current attribute data if the intent prediction information indicates that the guided object intends to operate at least one of the vehicle functions. The third processing module is used to modify the initial guidance information using the usage habit data to obtain the target guidance information; The fourth processing module is used to guide and control the target vehicle function based on the target guidance information.

[0007] In another aspect, embodiments of this application provide a vehicle, including: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the vehicle function guidance method described above.

[0008] In another aspect, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the aforementioned vehicle function guidance method.

[0009] According to an embodiment of this application, a method, apparatus, vehicle, and program product for guiding in-vehicle functions are provided. The method acquires current attribute data and usage habit data of the guided object; performs identification processing based on the current attribute data to obtain intention prediction information of the guided object; wherein, the intention prediction information is used to indicate whether the guided object intends to operate at least one in-vehicle function; if the intention prediction information indicates that the guided object intends to operate at least one in-vehicle function, then, based on the intention prediction information and the current attribute data, a target in-vehicle function and initial guidance information are obtained; the initial guidance information is corrected using usage habit data to obtain target guidance information; and guidance control is performed on the target in-vehicle function based on the target guidance information. The technical solution according to the embodiment of this application can improve the guidance accuracy of in-vehicle functions, provide personalized and accurate function guidance services for the guided object, meet the actual function guidance needs of the guided object for in-vehicle functions, and thus enhance the user experience when using in-vehicle functions.

[0010] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the description, claims and drawings. Attached Figure Description

[0011] Figure 1 This is a flowchart of an in-vehicle function guidance method provided in this application; Figure 2 This is a diagram illustrating the specific implementation process of an in-vehicle function guidance method provided in this application; Figure 3 This is a structural diagram of an in-vehicle function guidance device provided in this application; Figure 4 This is an example image of a vehicle provided in this application. Detailed Implementation

[0012] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0013] The present application will be further described below with reference to the accompanying drawings and specific embodiments. The described embodiments should not be considered as limitations on the present application, and all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of the present application.

[0014] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0015] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0016] With the development of vehicle technology and the advancement of intelligent connectivity technology, in-vehicle functions have become increasingly rich and complex. This brings great convenience to older car users, but new car users are usually unfamiliar with various in-vehicle functions and their operation, requiring them to spend a lot of time and energy to learn and adapt. Therefore, this also brings new challenges to new car users.

[0017] Currently, the methods of providing function guidance to users are generally divided into three types: paper user manuals included with the vehicle, electronic manuals in the vehicle, and function guidance interfaces displayed on the central control system. These methods are relatively traditional and simplistic. Specifically, paper user manuals are usually voluminous and complex, making it difficult for users to quickly find the information they need. Some vehicles are equipped with electronic manuals in the vehicle, which improves the convenience of information retrieval to some extent, but users still need to actively search and read them, lacking initiative and specificity. Some vehicles' central control systems display a simple function guidance interface upon initial startup, but this interface is often one-off and cannot be adjusted and updated in real time according to the user's actual usage and needs. Moreover, these guides are mostly based on text and static images, making them rather dull and unlikely to attract user interest or attention.

[0018] Furthermore, the guidance information provided by the three function guidance methods mentioned above is usually pre-set. However, users' needs and understanding of in-vehicle functions often vary. These methods do not fully consider the individual differences and usage habits of different users, and cannot achieve personalized customization or meet specific user guidance needs. This leads to a series of inconveniences for users when using in-vehicle functions.

[0019] In response to this, embodiments of this application provide a vehicle function guidance method, device, vehicle, and program product, aiming to improve the guidance accuracy of vehicle functions and thus enhance the user experience of vehicle functions.

[0020] First, the following will describe in detail, with reference to the accompanying drawings, a vehicle function guidance method provided by the embodiments of this application.

[0021] In all specific embodiments of this disclosure, when processing is required based on data such as physiological attribute data, usage habit data, and sample information, the permission or consent of the subject is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. Additionally, when embodiments of this disclosure require obtaining data such as the physiological attribute data and usage habit data of the subject, separate permission or consent from the subject is obtained through pop-ups or redirection to a confirmation page. Only after obtaining the subject's separate permission or consent are the necessary data, such as physiological attribute data, usage habit data, and sample information, required for the proper functioning of the embodiments of this disclosure.

[0022] This application provides a vehicle-mounted function guidance method that can be applied to a terminal, a server, or software running on either a terminal or a server. The terminal can be a tablet, laptop, desktop computer, etc., but is not limited to these. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. Furthermore, the server can be a node server in a blockchain network, but is not limited to these. Blockchain is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms.

[0023] Reference Figure 1 , Figure 1 This is a flowchart of an in-vehicle function guidance method provided in this application, which may include the following steps S101-S105.

[0024] S101, Obtain physiological attribute data and usage habit data of the guided object.

[0025] It should be noted that the "guided target" refers to the user who is located inside the vehicle and may have functional guidance needs.

[0026] In this step, facial images and operation action images of the guided object within the current time period (which includes multiple preset times, starting from the start of this vehicle) are obtained as physiological attribute data. That is, the physiological attribute data includes facial image sequences and operation action image sequences. The facial image sequence includes facial images from multiple preset times, while the operation action image sequence includes operation action images from multiple preset times. Together, they represent the actual operation of the guided object.

[0027] Simultaneously, the type, number of operation steps, and operation difficulty of the guidance information (i.e., historical guidance information) of the vehicle functions operated by the guided user in the past time period are obtained as usage habit data. The past time period refers to the time period before the current vehicle startup, which represents the historical operation of the guided user. The type of guidance information may include at least one of voice type, light type, and video type. The definition of the number of operation steps and operation difficulty will be explained in the following embodiments.

[0028] S102, based on physiological attribute data, perform identification processing to obtain the intention prediction information of the guided object.

[0029] It should be noted that the intent prediction information is used to indicate whether the guided object intends to operate at least one in-vehicle function. If so, it means that the guided object has a need for function guidance; otherwise, it means that the guided object does not have a need for function guidance.

[0030] In this step, identification processing is performed based on physiological attribute data to determine whether the person being guided intends to operate at least one in-vehicle function, thereby obtaining the person's intention prediction information. Here, intention prediction is achieved by fully considering multi-dimensional data related to the person's current operation, which can accurately determine whether the person needs guidance for in-vehicle functions, thus helping to provide personalized and accurate function guidance services.

[0031] S103, if the intent prediction information indicates that the guided object intends to operate at least one vehicle function, then the target vehicle function and initial guidance information are obtained based on the intent prediction information and physiological attribute data.

[0032] It should be noted that the target in-vehicle function refers to the in-vehicle function that the user expects to operate. Furthermore, the initial guidance information refers to guidance information tailored to the user's actual functional guidance needs. This information may include guidance type and guidance content. The guidance type may include at least one of voice, light, and video types, while the guidance content refers to the content used to guide the user in operating the target in-vehicle function, such as specific operating steps.

[0033] It is understandable that the initial boot information is the initial boot information, not the final boot information.

[0034] In this step, if the identification process detects that the target intends to operate at least one in-vehicle function, it indicates that the target has a need for function guidance; otherwise, it indicates that the target does not have a need for function guidance. When a need for function guidance is detected, the target in-vehicle function is determined based on intent prediction information and physiological attribute data, and its initial guidance information is further determined.

[0035] Here, considering that the guidance needs of the target user for in-vehicle functions directly reflect the in-vehicle functions that the target user actually expects to operate, and that the target user's actual operation is directly related to the guidance information, for example, the guidance information will increase the frequency and depth of guidance for in-vehicle functions that the user is not familiar with, while reducing or eliminating the guidance for familiar in-vehicle functions, therefore, based on the identification results of the aforementioned steps, combining physiological attribute data to determine the target in-vehicle function and its initial guidance information can accurately locate the in-vehicle function that the target user expects to operate, and accurately determine the content and type of guidance information according to the target user's actual operation, thereby helping to provide personalized and accurate function guidance services.

[0036] S104, use usage habit data to correct the initial guidance information to obtain the target guidance information.

[0037] It should be noted that target guidance information refers to guidance information that is both aligned with the actual functional guidance needs and usage habits of the target audience. Its definition is similar to that of the initial guidance information mentioned above, and will not be repeated here.

[0038] It is understandable that the target guidance information is the final guidance information.

[0039] In this step, the initial guidance information is revised based on the user's usage habits to obtain the target guidance information. The essence of this revision process is to dynamically adjust the guidance information according to the user's usage habits, thereby ensuring that the final guidance information perfectly matches the user's actual functional guidance needs and operating habits, thus improving the accuracy of the content and type of the guidance information.

[0040] S105, guides and controls the target vehicle functions based on target guidance information.

[0041] In this step, the target guidance content is displayed to the user through at least one of the following methods: voice, light, and video. This allows for guided control of the target in-vehicle function, providing personalized and precise guidance services. For example, when the user is unfamiliar with a certain function, the vehicle can provide clear and concise voice prompts explaining the specific operating steps; and / or, by using flashing ambient lighting or specific area lighting indicators, the user can be guided to focus on the area where the in-vehicle function is located; and / or, by playing vivid video demonstrations on the central control screen, the user can more intuitively understand how to operate the in-vehicle function.

[0042] Therefore, through the above steps, the embodiments of this application can improve the guidance accuracy of vehicle functions, provide personalized and accurate function guidance services for the guided users, meet the actual function guidance needs of the guided users for vehicle functions, and thus enhance the user experience when using vehicle functions.

[0043] The steps described above will be explained in further detail below.

[0044] In some implementations, the above-mentioned identification processing based on physiological attribute data to obtain the intention prediction information of the guided object may include: Feature extraction is performed based on physiological attribute data to obtain the current attribute feature sequence; Intent prediction is performed based on the current attribute feature sequence to obtain intent prediction information.

[0045] In this embodiment, firstly, a current attribute feature sequence is extracted from physiological attribute data. This current attribute feature sequence may include a current facial action unit (AU) feature sequence, a current catch light feature sequence, and a current action feature sequence, thereby comprehensively and accurately capturing facial action unit features, catch light features, and action features associated with the guided user's intention to operate in-vehicle functions. Then, intention prediction is performed based on the above three types of feature sequences to identify whether the guided user intends to operate at least one in-vehicle function, thereby obtaining intention prediction information and accurately locating the guided user's functional guidance needs.

[0046] Here, in feature extraction, based on the definition of facial action units (FAUs) in the Facial Action Coding System (FACS), FAUs provide detailed and objective descriptions of the activation state and movement details of facial muscles or muscle groups. For example, AU12 (Lip Corner Puller) describes the action of pulling the corners of the mouth, which is highly correlated with the activation of the zygomaticus major muscle. One or more FAUs can be combined in various ways to form a facial expression (FE). For example, AU6 (Cheek Raiser), AU7 (Lid Tightener), AU12 (Lip Corner Puller), and AU25 (Lips Part) can be combined to form an FE categorized as "happy." Since facial expressions reflect the operational intentions of the guided object to a certain extent, extracting FAU features from facial image sequences helps improve the accuracy of predicting the intentions of the guided object.

[0047] Accordingly, the current facial action unit feature sequence can include facial action unit features at multiple preset time points. For each preset time point, the process is as follows: First, a Multi-Task Cascaded Convolutional Network (MTCNN) is used to detect faces in the facial images at the preset time points, obtaining the face regions at those times. Then, a pre-trained facial unit recognition model is used to recognize the face regions at the preset time points, obtaining the facial action unit numbers (e.g., AU12, AU6, etc.) as the facial action unit features at those times. This feature extraction process effectively improves the accuracy of facial unit feature extraction. The facial unit recognition model is trained using multiple preset face image samples and their corresponding label information. The label information refers to the facial action unit information contained within the face image samples. By traversing multiple preset time points of facial images, facial action unit features at multiple preset time points can be obtained, thus forming a facial action unit feature sequence.

[0048] Here, in feature extraction, catchlight refers to the bright spot formed in the eyes due to light reflection. By observing the catchlight of the guided object at different times, the location of the vehicle function that the guided object intends to operate can be accurately tracked. Therefore, extracting relevant feature information of catchlight from facial image sequences helps to improve the accuracy of predicting the guided object's intention.

[0049] Accordingly, the current catchlight feature sequence can include catchlight features at multiple preset time points. For facial images at each preset time point, the process is as follows: First, a multi-task cascaded convolutional neural network is used to perform face detection and facial keypoint localization on the facial images at the preset time points, obtaining the left and right eye center keypoints at the preset time points. Based on this, the left and right eye regions at the preset time points are cropped using methods such as the OpenCV image processing library and the Canny edge detection algorithm. Then, for each eye region, small regions with high brightness values ​​(brightness values ​​greater than a preset threshold) are found within the eye region based on pixel intensity threshold segmentation or connected component analysis techniques, and opening operations are performed to remove isolated small points and smooth the boundaries, thereby obtaining the catchlight regions at the preset time points. Afterward, the catchlight regions of the left and right eye regions at the preset time points are spatially resized (Resize) to a one-dimensional vector, which serves as the catchlight features at the preset time points. Through the above feature extraction operations, the extraction accuracy of catchlight features can be effectively improved. By traversing facial images at multiple preset times, the eye light features at multiple preset times can be obtained, thus forming the current eye light feature sequence.

[0050] Here, in feature extraction, the operation action refers to the pose of the guided object at a preset time. It directly reflects whether the guided object intends to operate a certain vehicle function and the guided object's proficiency in operating a certain vehicle function. Therefore, extracting relevant feature information of the operation action from the operation action image sequence helps to improve the accuracy of the guided object's intention prediction.

[0051] Accordingly, the current action feature sequence can include action features at multiple preset times. For the operation action images at each preset time, the following steps are taken: First, the MediaPipe model is used to extract key points from the operation action images at the preset times, obtaining the shoulder, elbow, wrist, hip, knee, and ankle key points on one side at the preset times. Then, the elbow joint angle on one side at the preset times is determined using the shoulder, elbow, and wrist key points, and the knee joint angle on one side at the preset times is determined using the hip, knee, and ankle key points. Specifically, the vectors of the current joint and its parent joint are calculated, as well as the vectors of the current joint and its child joint. The angle between these two vectors is then calculated as the angle. For the elbow joint angle, the parent joint is the shoulder key point, the current joint is the elbow key point, and the child joint is the wrist key point; for the knee joint angle, the parent joint is the hip key point, the current joint is the knee key point, and the child joint is the ankle key point. Finally, the elbow joint angle and the knee joint angle are combined as the action features at the preset times. Thus, by using MediaPipe key point extraction and geometric angle calculation, action features with clear physiological significance can be efficiently extracted in normal operating scenarios, more accurately reflecting the operational behavior characteristics of the guided object, thereby further improving the accuracy of action feature extraction.

[0052] Here, in intent prediction, the current facial motion unit feature sequence, current eye movement feature sequence, and current action feature sequence are concatenated and input into a pre-trained intent prediction model to obtain intent prediction information. The intent prediction model is trained using multiple preset first sample information and corresponding label information for each first sample. The first sample information can include facial motion unit features, eye movement features, and action features at multiple sample times, with labels of one or zero. One indicates an intent to operate at least one in-vehicle function, while zero indicates no intent to operate any in-vehicle function. Furthermore, the specific type of intent prediction model can be flexibly set according to actual conditions, such as a convolutional neural network model, but is not limited to this. The intent prediction model can identify whether the guided object intends to operate at least one in-vehicle function at the next preset time (i.e., the first future time).

[0053] Therefore, through the above steps, this embodiment fully considers the high correlation between facial motion units, eye light and operation actions and whether the guided object intends to operate at least one vehicle function. Intent prediction is achieved based on these multi-dimensional data, which can improve the accuracy of the guided object's intent prediction and thus accurately locate the guided object's functional guidance needs.

[0054] In some implementations, obtaining the target in-vehicle function and initial guidance information based on intent prediction information and physiological attribute data may include: Voice queries are performed based on intent prediction information to obtain the dialogue content; Based on the dialogue content, the target in-vehicle function is obtained; Based on physiological attribute data, proficiency is identified to obtain the operational proficiency information of the guided object; Based on the operator proficiency information and the target vehicle functions, determine the initial guidance information.

[0055] It should be noted that the operation proficiency information indicates the degree of proficiency of the guided object in operating a certain vehicle function. It can include the number of operations and the duration of operation. The more operations and the longer the duration, the less proficient the object is in operating the function, and vice versa.

[0056] In this embodiment, if the intention of the guided user is predicted to operate at least one in-vehicle function during intent prediction, a preset question is first output in voice form, such as "What function do you need to operate?". The guided user can then respond with a corresponding voice message, such as "I need to adjust the angle of the rearview mirror," and so on. The question information and its corresponding response can be integrated into a dialogue. This voice inquiry method facilitates quick and further capture of the guided user's actual needs for in-vehicle functions. Then, speech recognition is performed based on the dialogue content to extract features associated with the in-vehicle function and locate the target in-vehicle function accordingly. Simultaneously, the guided user's operational proficiency information is identified based on physiological attribute data associated with the user, thereby accurately determining the user's proficiency level when operating the in-vehicle function. Finally, initial guidance information is determined based on the operational proficiency information obtained in the aforementioned steps and the target in-vehicle function, making the initial guidance information more closely match the actual situation of the guided user operating a particular in-vehicle function.

[0057] Therefore, through the above steps, this implementation method can quickly and accurately locate the in-vehicle function that the guided user wants to operate through a simple inquiry method. Considering that the user's proficiency in operating the in-vehicle function is directly related to the guidance information, the user's proficiency in operating the in-vehicle function is first accurately located through physiological attribute data. Then, based on this, the content and type of guidance information are accurately located in combination with the target in-vehicle function, thereby effectively improving the accuracy of the initial guidance information and helping to provide personalized and accurate function guidance services.

[0058] In some implementations, obtaining the target in-vehicle function based on the dialogue content may include: Feature extraction is performed on the dialogue content to obtain speech features; Function recognition is performed based on voice features to obtain the target in-vehicle function.

[0059] In this embodiment, firstly, speech recognition and feature extraction are performed on the dialogue content. The aim is to extract speech segments related to vehicle parts (e.g., rearview mirrors) and operational behaviors (e.g., adjustments) from the dialogue content through speech recognition, and then convert these speech segments into corresponding speech features through feature extraction, thereby comprehensively capturing feature information highly correlated with in-vehicle functions (e.g., rearview mirror adjustment). Next, the speech features are input into a pre-trained function recognition model. The function recognition model identifies the target in-vehicle function, thereby accurately locating the in-vehicle function that the user intends to operate. The function recognition model is a model obtained through multiple preset second sample information and corresponding label information for each second sample information. The second sample information is the speech feature sample, and its label information indicates the type of in-vehicle function. Furthermore, the specific type of function recognition model can be flexibly set according to actual conditions; for example, the proficiency recognition model can be a convolutional neural network model, support vector machine, etc., but it is not limited to these.

[0060] Here, in feature extraction, the dialogue content is first preprocessed, such as through noise reduction and standardization, to obtain preprocessed dialogue content. Then, Google's Speech-to-Text API is called to convert the preprocessed dialogue content into corresponding text data, and keywords related to vehicle parts and / or operational behaviors are identified from the text data. By calling Google's Speech-to-Text API, speech recognition and keyword recognition can be quickly achieved. Google's Speech-to-Text API supports real-time speech recognition and automatically labels required keywords during speech recognition. For example, if the dialogue content is "What function do you need to operate?" or "I need to adjust the angle of the rearview mirror", it is converted into the text "What function do you need to operate? I need to adjust the angle of the rearview mirror", and the keywords related to vehicle parts ("rearview mirror") and operational behaviors ("adjust") are labeled. Then, in the preprocessed dialogue content, the speech segments containing keywords related to vehicle parts and / or operational behaviors are identified as speech segments associated with vehicle parts and operational behaviors, and these are converted into Mel-Frequency Cepstral Coefficients (MFCCs) to obtain speech features. This feature extraction method can effectively improve the extraction accuracy of feature information that is highly related to vehicle functions.

[0061] Therefore, through the above steps, the dialogue content implicitly contains key information about the vehicle function that the guided object intends to operate. Accordingly, this embodiment extracts features from the dialogue content obtained from the inquiry to obtain voice features that are highly related to the vehicle function, and identifies the target vehicle function accordingly. This can accurately locate the vehicle function that the guided object wants to operate, thereby ensuring that the subsequent guidance information is completely consistent with the vehicle function that the guided object wants to operate.

[0062] In some implementations, the above-mentioned skill proficiency identification based on physiological attribute data to obtain the operational proficiency information of the guided object may include: The physiological attribute data is processed to extract features, resulting in the current action feature sequence; Based on the current action feature sequence, proficiency is identified to obtain operation proficiency information.

[0063] In this embodiment, firstly, the current action feature sequence is extracted from physiological attribute data to comprehensively and accurately capture feature information related to the proficiency of the guided object in operating the vehicle functions. The description of extracting the current action feature sequence can be found in the previous embodiment and will not be repeated here. Then, the current action feature sequence is input into a pre-trained proficiency recognition model to obtain operation proficiency information, namely the number of operations and the duration of the operation, thereby accurately quantifying the proficiency of the guided object in operating the vehicle functions. The proficiency recognition model is trained using multiple preset third sample information and the corresponding label information for each third sample information. The third sample information can include action features at multiple sample times, and its label information is operation proficiency information (i.e., the number of operations and the duration of the operation). Furthermore, the specific type of proficiency recognition model can be flexibly set according to actual conditions; for example, the proficiency recognition model can be a convolutional neural network model, but it is not limited to this. The proficiency recognition model can identify the proficiency of the guided object in operating a certain vehicle function.

[0064] As can be seen, through the above steps, the guided object's operation actions directly reflect the guided object's proficiency in operating a certain vehicle function. Therefore, this embodiment realizes the recognition of operation proficiency information by fully considering the guided object's operation actions, which can effectively improve the recognition accuracy of the guided object's operation proficiency information and thus accurately quantify the guided object's actual operation.

[0065] In some implementations, determining the initial guidance information based on operational proficiency information and the target vehicle functionality may include: Acquire multiple guidance information for the target vehicle function and the guidance complexity information for each guidance information; Based on the guidance complexity information of each guidance message, the guidance message that matches the operation proficiency information is selected from multiple guidance messages as the initial guidance message.

[0066] In this embodiment, firstly, multiple guidance information for the target vehicle function and guidance complexity information for each guidance information are determined. The guidance complexity information is used to indicate the complexity of the guidance information and may include: (1) the number of operation steps, which refers to the total number of operation steps contained in the guidance information. The maximum number of operation steps is ten. If there are more than ten operation steps, the maximum number of operation steps is taken, i.e., the value is ten. (2) the operation difficulty, which refers to the maximum number of operation behaviors in all operation steps. For example, if the operation behavior of one operation step is only clicking a button, i.e., the number of operation behaviors is one, and the operation behavior of another operation step is a combination of clicking a button and inputting parameters, i.e., the number of operation behaviors is two, then two is selected as the value of operation difficulty. The maximum value of operation difficulty is ten. If the maximum number of operation behaviors in all operation steps is greater than ten, the maximum value of operation difficulty is taken, i.e., the value is ten. It should be understood that the guidance information can be preset according to the actual situation and the type of vehicle function.

[0067] Then, the number of operations and the duration of operations in the proficiency information are weighted and summed to obtain the total proficiency of the guided object. This total proficiency comprehensively covers the actual operation status of the guided object. A higher total proficiency indicates a less proficient object, and vice versa. Subsequently, the guidance complexity range corresponding to the total proficiency of the guided object is retrieved by traversing the database. This range reflects the maximum acceptable guidance complexity (upper limit) and minimum acceptable guidance complexity (lower limit) based on the object's proficiency level. It should be understood that the database pre-stores multiple preset total proficiency samples and the corresponding guidance complexity ranges for each sample.

[0068] Simultaneously, the number of operation steps and the difficulty of operation in the guidance complexity information of each guidance message are weighted and summed to obtain the total complexity of each guidance message. The total complexity can comprehensively cover the actual complexity of the guidance message. Among them, the higher the total complexity, the more complex the guidance message is, and the more unfavorable it is to the actual operation of the guided object. Conversely, the lower the total complexity, the simpler the guidance message is, and the more favorable it is to the actual operation of the guided object.

[0069] Next, guidance information whose total complexity falls outside the guidance complexity range is filtered out. This means that guidance information is unacceptable to the guidance object based on the guidance object's operational proficiency. Meanwhile, the remaining guidance information is determined as candidate guidance information, which means that guidance information is acceptable to the guidance object based on the guidance object's operational proficiency. This completes the initial screening of guidance information.

[0070] Finally, the candidate guidance information with the lowest overall complexity is selected as the final initial guidance information. This ensures that the initial guidance information is within the acceptable range for the guidance object and has the lowest operational complexity. It closely matches the actual functional guidance needs of the guidance object, which helps guide the guidance object to quickly operate the required vehicle functions.

[0071] Therefore, through the above steps, the guidance complexity information of each guidance message indicates the complexity of the guidance information, while the operation proficiency information indicates the proficiency of the guided user in operating the vehicle functions. By quantifying the matching degree between the proficiency of the guided user in operating the vehicle functions and the complexity of various guidance messages, and thereby locating the initial guidance information of the target vehicle function, the accuracy of the initial guidance information can be effectively improved, making the initial guidance information fit the actual functional guidance needs of the guided user, thus helping to provide personalized and accurate functional guidance services.

[0072] In some implementations, the above-described process of correcting the initial guidance information using user habit data to obtain the target guidance information may include: Based on usage data and the target vehicle function, determine at least one candidate guidance information for the target vehicle function; The target guidance information is determined based on the initial guidance information and at least one candidate guidance information.

[0073] It should be noted that candidate guidance information refers to guidance information that conforms to the target vehicle function and fits the user's usage habits. Its definition is similar to that of the initial guidance information and target guidance information in the aforementioned embodiments, and will not be repeated here.

[0074] In this embodiment, considering that the initial guidance information tends to meet the actual functional guidance needs of the guided object, it may not conform to the behavioral habits of the guided object when operating the vehicle function. This makes it difficult for the guided object to quickly learn how to use the vehicle function. Therefore, in order to improve the matching degree between the final target guidance information and the actual functional guidance needs and usage habits of the guided object, usage habit data is used to modify the guidance type and guidance content of the initial guidance information.

[0075] First, analyze usage habit data to identify the most frequently occurring types as target types. For example, if image-based guidance messages appeared eight times, text-based guidance messages appeared five times, and voice-based guidance messages appeared ten times, then voice-based guidance messages are identified as the target type. Simultaneously, calculate the average number of operation steps across all historical guidance messages as the target number of steps, and calculate the average difficulty level across all historical guidance messages as the target difficulty level. This allows for accurate identification of the user's past habits when using the feature guidance service, such as the types they habitually use, the number of operation steps they are accustomed to, and the level of difficulty they are accustomed to.

[0076] Then, the sum of the target number of steps and one is determined as the upper limit of the step number range, and the difference between the target number of steps and one is determined as the lower limit of the step number range, thus forming the step number range. Similarly, the sum of the target difficulty and one is determined as the upper limit of the difficulty range, and the difference between the target difficulty and one is determined as the lower limit of the difficulty range, thus forming the difficulty range. This helps to filter out guidance information that matches the user's habits and the target vehicle functions in subsequent steps.

[0077] Next, multiple guidance information for the target vehicle function and guidance complexity information for each guidance information are obtained. From the multiple guidance information, guidance information whose number of operation steps is within the range of the number of steps, whose operation difficulty is within the range of the difficulty, and whose type belongs to the target is selected as candidate guidance information. In this way, at least one candidate guidance information is obtained, so that the candidate guidance information is both in line with the target vehicle function and in line with the user habits of the guided object.

[0078] Finally, determine if any candidate guidance information is identical to the initial guidance information. If so, it means the initial guidance information perfectly matches the user's actual functional guidance needs and usage habits, and in this case, the initial guidance information is output as the target guidance information. Otherwise, it means the initial guidance information only matches the user's actual functional guidance needs, but not their usage habits. In this case, the guidance type and content of the initial guidance information need to be dynamically adjusted to obtain the final target guidance information.

[0079] Regarding the guidance type, if the guidance type of the initial guidance information differs from the target type, the guidance type of the initial guidance information is modified to the target type; otherwise, the guidance type of the initial guidance information is not modified. For the guidance content, it typically includes the number of operation steps and the content of those steps. The operational difficulty mentioned in the preceding embodiments reflects the practical difficulty of the operational steps. Therefore, candidate guidance information with the fewest number of operation steps, the fewest parameters in the operational steps, and the lowest operational difficulty is first determined. For example, the candidate guidance information with the fewest number of operation steps is selected first, then the candidate guidance information with the fewest parameters in the operational steps is selected from among them, and then the candidate guidance information with the lowest operational difficulty is further selected from among them. Subsequently, the guidance content of the initial guidance information is directly replaced with the guidance content of this candidate guidance information. The initial guidance information after the guidance type and guidance content are replaced is used as the target guidance information.

[0080] Therefore, through the above steps, this implementation method first uses data on the user habits of the guided user to determine candidate guidance information that is both consistent with the target in-vehicle function and consistent with the user's user habits. Then, based on the guidance type and content of the candidate guidance information, the guidance type and content of the initial guidance information are dynamically adjusted to obtain the target guidance information. This ensures that the target guidance information is consistent with the user's actual functional guidance needs and also with the user's user habits, such as the type of operation they are accustomed to, the number of operation steps they are accustomed to, and the difficulty of operation they are accustomed to. This improves the guidance accuracy of the in-vehicle function, provides personalized and accurate functional guidance services to the user, meets the user's actual functional guidance needs for the in-vehicle function, and enhances the user's experience when using the in-vehicle function.

[0081] To facilitate understanding of the in-vehicle function guidance method described above, an example of its practical application is provided below. (Refer to...) Figure 2 The specific process for implementing in-vehicle function guidance in this application is as follows: S01, Boot Trigger: The user enters the vehicle and starts the vehicle.

[0082] S02, Data Acquisition: The system collects facial and action images of the user within one minute to serve as physiological attribute data, thereby recording the user's actions within that minute. Simultaneously, it obtains the type, number of steps, and difficulty of the guidance information (i.e., historical guidance information) for in-vehicle functions operated by the user in past time periods as usage habit data.

[0083] S03, Intent Prediction: The current attribute feature sequence is extracted from the physiological attribute data. This sequence may include the current facial motion unit feature sequence, the current eye movement feature sequence, and the current action feature sequence. These three sequences are concatenated and input into a pre-trained intent prediction model to obtain intent prediction information. This information indicates whether the guided object intends to operate at least one in-vehicle function. If the intent prediction information indicates that the guided object intends to operate at least one in-vehicle function, the process jumps to step S04; otherwise, it returns to step S02, thus implementing a loop judgment.

[0084] S04, Functions and Guidance Positioning: S041, Functional Positioning: The system outputs pre-set question information in voice form, such as "What function do you need to operate?" The user can then respond with corresponding voice information, such as "I need to adjust the angle of the rearview mirror." This process continues, and the question information and its corresponding response information can be integrated into dialogue content. Subsequently, features are extracted from the dialogue content to obtain voice features, which are then input into a pre-trained function recognition model to obtain the target in-vehicle function.

[0085] S042, Guiding Positioning: First, the current action feature sequence is extracted from the physiological attribute data. The current action feature sequence is then input into a pre-trained proficiency recognition model to obtain operation proficiency information, namely the number of operations and the duration of operations. Subsequently, the number of operations and the duration of operations in the operation proficiency information are weighted and summed to obtain the total operation proficiency of the guided object. The guidance complexity range corresponding to the total operation proficiency of the guided object is then retrieved by traversing the database.

[0086] Simultaneously, multiple guidance information for the target vehicle function and guidance complexity information for each guidance information are obtained. The guidance complexity information includes the number of operation steps and the difficulty of operation. The number of operation steps and the difficulty of operation in the guidance complexity information of each guidance information are weighted and summed to obtain the total complexity of each guidance information.

[0087] Finally, guide information whose total complexity falls outside the range of guide complexity is filtered out, and the remaining guide information is determined as candidate guide information. The candidate guide information with the lowest total complexity is selected as the final initial guide information.

[0088] S05, Guide Correction: First, user habit data is analyzed to identify the most frequently occurring type as the target type. The average number of operation steps across all historical guidance information is calculated as the target number of steps, and the average difficulty of operation across all historical guidance information is calculated as the target difficulty. Next, the sum of the target number of steps and one is used to define the upper limit of the step number range, and the difference between the target number of steps and one is used to define the lower limit of the step number range. Similarly, the sum of the target difficulty and one is used to define the upper limit of the difficulty range, and the difference between the target difficulty and one is used to define the lower limit of the difficulty range. Then, multiple guidance messages for the target in-vehicle function and their guidance complexity information are obtained. Guidance messages with operation steps within the target number range, operation difficulty within the target difficulty range, and belonging to the target type are selected as candidate guidance messages. Finally, if any candidate guidance message matches the initial guidance message, the initial guidance message is output as the target guidance message; otherwise, dynamic adjustments are made to obtain the target guidance message.

[0089] During dynamic adjustment, if the initial guidance information's guidance type differs from the target type, the guidance type of the initial guidance information is corrected to the target type; otherwise, the guidance type of the initial guidance information is not modified. Simultaneously, candidate guidance information with the fewest operation steps, the fewest parameters in the operation steps, and the lowest operation difficulty is first determined. Then, the guidance content of the initial guidance information is directly replaced with the guidance content of this candidate guidance information. The initial guidance information after the guidance type and content replacement is used as the target guidance information.

[0090] S06, Boot Control: By displaying target guidance content to the user through at least one of the following methods—voice, light, or video—the system can guide and control the target in-vehicle function, providing personalized and precise in-vehicle function guidance services. For example, when the user is unfamiliar with operating a certain function, the vehicle can provide clear and concise voice prompts to explain the specific operating steps; and / or, by using flashing ambient lighting or specific area lighting indicators, the system can guide the user to focus on the area where the in-vehicle function is located; and / or, by playing vivid video demonstrations on the central control screen, the user can more intuitively understand how to operate the in-vehicle function.

[0091] Optionally, after this guidance control, the data from this guidance control is added to the existing training data, and the model involved in the above embodiments is retrained (e.g., using federated learning or ordinary training methods) to optimize the guidance control.

[0092] In addition, refer to Figure 3This application also provides a vehicle function guidance device, which may include: Module 201 is used to obtain the current attribute data and usage habit data of the bootstrap object; The first processing module 202 is used to perform identification processing based on the current attribute data to obtain the intention prediction information of the guided object; wherein, the intention prediction information is used to indicate whether the guided object intends to operate at least one vehicle function; The second processing module 203 is used to obtain the target vehicle function and initial guidance information based on the intent prediction information and the current attribute data if the intent prediction information indicates that the guided object intends to operate at least one vehicle function. The third processing module 204 is used to correct the initial guidance information using usage habit data to obtain the target guidance information; The fourth processing module 205 is used to guide and control the target vehicle functions based on the target guidance information.

[0093] The content of the above method embodiments is applicable to the device embodiments. The specific functions implemented by the device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0094] Furthermore, refer to Figure 4 This application provides a vehicle that may include: At least one processor 401; At least one memory 402 is used to store at least one program; When at least one program is executed by at least one processor 401, the at least one processor 401 implements the above-described vehicle function guidance method.

[0095] The aforementioned vehicles can be private cars, such as sedans, sport utility vehicles (SUVs), multi-purpose vehicles (MPVs), or pickup trucks, or commercial vehicles, such as vans, buses, small trucks, or large trailers, or gasoline vehicles or new energy vehicles such as hybrid or pure electric vehicles.

[0096] The aforementioned memory 402, as a non-transitory network system, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory 402 may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 402 may optionally include memory 402 remotely located relative to processor 401, and these remote memories 402 can be connected to processor 401 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0097] The aforementioned memory 402 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). Memory 402 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in memory 402 and called by processor 401 to execute the methods of the embodiments of this application.

[0098] The processor 401 described above can be implemented using a general-purpose central processing unit (CPU), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0099] In some embodiments, the vehicle may further include: Input / output interfaces are used to implement information input and output; The communication interface is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). The bus transmits information between various components of the device (such as processor 401, memory 402, input / output interface and communication interface); The processor 401, memory 402, input / output interface, and communication interface can communicate with each other within the device via a bus.

[0100] The content of the above method embodiments is applicable to this vehicle embodiment. The specific functions implemented in this vehicle embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0101] Finally, this application provides a computer program product, including a computer program that, when executed by a processor, implements the above-described vehicle function guidance method.

[0102] The content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0103] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this application are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0104] Furthermore, although this application is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding this application. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional technology for an engineer. Therefore, those skilled in the art can implement the application set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of this application, which is determined by the full scope of the appended claims and their equivalents.

[0105] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several programs to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0106] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequential list of executable programs for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, a program execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can retrieve and execute a program from or in conjunction with such a program execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain, store, communicate, propagate, or transmit a program for use by or in conjunction with a program execution system, apparatus, or device.

[0107] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0108] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable program execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0109] In the foregoing description of this specification, the references to terms such as "one embodiment," "another embodiment," or "some embodiments," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0110] Although embodiments of this application have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the claims and their equivalents.

[0111] The above is a detailed description of the preferred embodiments of this application, but this application is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application, and these equivalent modifications or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A vehicle function guidance method, characterized in that, Includes the following steps: Retrieve the current attribute data and usage habit data of the bootstrap object; Based on the current attribute data, identification processing is performed to obtain the intent prediction information of the guided object; wherein, the intent prediction information is used to indicate whether the guided object intends to operate at least one in-vehicle function; If the intent prediction information indicates that the guided object intends to operate at least one of the vehicle functions, then the target vehicle function and initial guidance information are obtained based on the intent prediction information and the current attribute data. The initial guidance information is corrected using the aforementioned usage habit data to obtain the target guidance information; The target vehicle function is guided and controlled based on the target guidance information.

2. The method according to claim 1, characterized in that, The step of performing identification processing based on the current attribute data to obtain the intent prediction information of the guided object includes: Based on the current attribute data, feature extraction is performed to obtain the current attribute feature sequence; Intent prediction is performed based on the current attribute feature sequence to obtain the intent prediction information.

3. The method according to claim 1, characterized in that, The step of obtaining the target in-vehicle function and initial guidance information based on the intent prediction information and the current attribute data includes: Based on the intent prediction information, a voice inquiry is performed to obtain the dialogue content; Based on the dialogue content, the target in-vehicle function is obtained; Based on the current attribute data, the proficiency of the user is identified to obtain the operational proficiency information of the user being guided. The initial guidance information is determined based on the operation proficiency information and the target vehicle function.

4. The method according to claim 3, characterized in that, The process of obtaining the target in-vehicle function based on the dialogue content includes: The dialogue content is subjected to feature extraction to obtain speech features; Based on the voice features, function recognition is performed to obtain the target vehicle function.

5. The method according to claim 3, characterized in that, The step of identifying proficiency based on the current attribute data to obtain the operational proficiency information of the guided object includes: The current attribute data is subjected to feature extraction processing to obtain the current action feature sequence; Based on the current action feature sequence, proficiency is identified to obtain the operation proficiency information.

6. The method according to claim 3, characterized in that, The step of determining the initial guidance information based on the operation proficiency information and the target vehicle function includes: Obtain multiple guidance information for the target vehicle function and guidance complexity information for each of the guidance information; Based on the guidance complexity information of each of the guidance information, the guidance information that matches the operation proficiency information is determined from the multiple guidance information as the initial guidance information.

7. The method according to claim 1, characterized in that, The step of modifying the initial guidance information using the usage habit data to obtain the target guidance information includes: Based on the usage habit data and the target vehicle function, at least one candidate guidance information for the target vehicle function is determined; The target guidance information is determined based on the initial guidance information and at least one of the candidate guidance information.

8. A vehicle function guidance device, characterized in that, include: The acquisition module is used to obtain the current attribute data and usage habit data of the bootstrap object; The first processing module is used to perform identification processing based on the current attribute data to obtain the intent prediction information of the guided object; wherein, the intent prediction information is used to indicate whether the guided object intends to operate at least one in-vehicle function; The second processing module is used to obtain the target vehicle function and initial guidance information based on the intent prediction information and the current attribute data if the intent prediction information indicates that the guided object intends to operate at least one of the vehicle functions. The third processing module is used to modify the initial guidance information using the usage habit data to obtain the target guidance information; The fourth processing module is used to guide and control the target vehicle function based on the target guidance information.

9. A vehicle, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the vehicle function guidance method as described in any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the vehicle function guidance method as described in any one of claims 1-7.

Images