Vehicle control method based on behavior habits and vehicle

Abstract

The invention provides a vehicle control method based on behavioral habits and a vehicle, and the method comprises the steps: obtaining the identity information of a target user, calling behavioral habit models corresponding to the identity information, and when the number of the behavioral habit models is at least two and the vehicle functions corresponding to the at least two behavioral habit models are conflicted, controlling the target user according to the behavioral habit models. Determining a first target behavioral habit model from at least two behavioral habit models with vehicle function conflicts according to a preset use logic, and obtaining a first behavioral habit prediction result corresponding to the first target behavioral habit model from at least two behavioral habit prediction results, the vehicle adjustment is controlled according to the first behavioral habit prediction result, and the mode of determining the first target behavioral habit model from the at least two behavioral habit models by using the preset use logic can accurately select the used behavioral habit model when the vehicle functions have conflicts; and the problem that the vehicle cannot be effectively adjusted when vehicle functions have conflicts is avoided.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a vehicle control method and a vehicle based on behavior habits. Background Art

[0002] Different users often have different behavioral habits when using the vehicle's functions, so it is necessary to adapt the corresponding behavioral habits to control vehicle adjustments.

[0003] However, the vehicle functions corresponding to the adapted behavioral habits in the related art may conflict with each other, so that the vehicle cannot be effectively adjusted. Summary of the invention

[0004] In view of this, the purpose of this application is to propose a vehicle control method and vehicle based on behavioral habits, so as to solve the problem in the prior art that the vehicle functions corresponding to the adapted behavioral habits will conflict, thereby making it impossible to effectively adjust the vehicle.

[0005] Based on the above purpose, the first aspect of the present application provides a vehicle control method based on behavior habits, comprising:

[0006] Obtain the target user's identity information;

[0007] Retrieving a behavior habit model corresponding to the identity information and determining the number of behavior habit models, wherein the behavior habit model corresponds to adjusting at least one function of the vehicle;

[0008] When the number of behavior habit models is at least two, obtaining first current driving environment data corresponding to the target user, inputting the first current driving environment data into at least two behavior habit models, and respectively outputting at least two corresponding behavior habit prediction results through the at least two behavior habit models;

[0009] When a conflict in vehicle functions corresponding to at least two behavior habit models is determined according to the at least two behavior habit prediction results, obtaining preset usage logics of at least two behavior habit models of the conflict in vehicle functions;

[0010] According to the preset usage logic, a first target behavior habit model is determined from at least two behavior habit models of the vehicle function conflict, and a first behavior habit prediction result corresponding to the first target behavior habit model is obtained from the at least two behavior habit prediction results, and vehicle adjustment is controlled according to the first behavior habit prediction result.

[0011] Optionally, the preset usage logic of the at least two behavior habit models sets corresponding priorities for the at least two behavior habit models;

[0012] The determining of a first target behavior habit model from at least two behavior habit models of conflicting vehicle functions according to the preset usage logic includes:

[0013] According to the priority, a behavior habit model with the highest priority is selected from at least two behavior habit models as the first target behavior habit model.

[0014] Optionally, after controlling the vehicle adjustment according to the first behavior habit prediction result, the method further includes:

[0015] Collecting a first training data set corresponding to the target user, the first training data set including first vehicle function status data and first driving environment data;

[0016] Using the first vehicle function status data and the second driving environment data to train the first target behavior habit model to obtain a trained first target behavior habit model;

[0017] The correspondence between the trained first target behavior habit model and the identity information corresponding to the target user is stored in a preset behavior habit model database, and the trained first target behavior habit model is used as a new first target behavior habit model. At the same time, the correspondence between the first target behavior habit model before training and the identity information corresponding to the target user is stored in the behavior habit model database.

[0018] Optionally, after storing the correspondence between the first target behavior habit model before training and the identity information corresponding to the target user in the behavior habit model database, the method further includes:

[0019] Acquire a current first target behavior habit model corresponding to the identity information of the target user;

[0020] When the current behavior habit model is the new first target behavior habit model and a switching instruction is received, the new first target behavior habit model is switched to the first target behavior habit model before training; or,

[0021] When the current behavior habit model is the first target behavior habit model before training and a switching instruction is received, the first target behavior habit model before training is switched to the new first target behavior habit model.

[0022] Optionally, the method further comprises:

[0023] When there is no identity information corresponding to the target user, new identity information is created and a preset behavior habit model is obtained;

[0024] Collecting a second training data set corresponding to the target user, the second training data set including second vehicle function status data and second driving environment data;

[0025] The preset behavior habit model is trained using the second vehicle function status data and the second driving environment data to obtain a trained preset behavior habit model, and the correspondence between the trained preset behavior habit model and the new identity information corresponding to the target user is stored in a preset behavior habit model database.

[0026] Optionally, each behavior habit model is pre-stored in a preset behavior habit model database, and the method further includes:

[0027] Performing cluster analysis on each behavior habit model stored in the behavior habit model database to obtain multiple category groups;

[0028] displaying the behavioral habit models classified into the plurality of category groups;

[0029] Receive a selection instruction for a second target behavior habit model, obtain second current driving environment data, input the second current driving environment data into the second target behavior habit model, output a second behavior habit prediction result through the second target behavior habit model, and control vehicle adjustment according to the second behavior habit prediction result, wherein the second target behavior habit model is at least one of the behavior habit models classified into the multiple category groups.

[0030] Optionally, the cluster analysis is performed on each behavior habit model stored in the behavior habit model database to obtain a plurality of category groups, including:

[0031] Acquiring third driving environment data;

[0032] Based on the third driving environment data, prediction is performed using various behavior habit models to obtain multiple behavior habit prediction results;

[0033] Combining the third driving environment data with each behavior habit prediction result to obtain a plurality of classification features;

[0034] Cluster analysis is performed on multiple classification features to obtain multiple category groups.

[0035] Optionally, the third driving environment data is combined with each behavior habit prediction result to obtain multiple classification features, including:

[0036] combining the third driving environment data with each behavior habit prediction result to form a plurality of initial classification features;

[0037] Performing dimensionality reduction processing on the multiple initial classification features to obtain multiple first-dimensional classification features;

[0038] The multiple first-dimensional classification features are mapped to multiple second-dimensional classification features, and the multiple second-dimensional classification features are used as the multiple classification features, wherein the dimension of the second-dimensional classification features is higher than the dimension of the second-dimensional classification features.

[0039] Optionally, after displaying the behavior habit models classified into the multiple category groups, the method further includes:

[0040] receiving scores for the behavior habit models classified into the plurality of category groups and stored in the behavior habit model database;

[0041] The behavior habit models classified into the plurality of category groups are reclassified according to the scores of the behavior habit models classified into the plurality of category groups.

[0042] Based on the same inventive concept, the second aspect of the present application provides a vehicle for executing the method described in the first aspect.

[0043] As can be seen from the above, the vehicle control method and vehicle based on behavior habits provided by the present application obtain the identity information of the target user, retrieve the behavior habit model corresponding to the identity information, and determine the number of behavior habit models. The behavior habit model corresponds to adjusting at least one function of the vehicle. When the number of behavior habit models is at least two, the first current driving environment data corresponding to the target user is obtained, and the first current driving environment data is input into at least two behavior habit models. The at least two behavior habit models respectively output the corresponding at least two behavior habit prediction results. When it is determined that the vehicle functions corresponding to the at least two behavior habit models conflict according to the at least two behavior habit prediction results, the preset usage logic of the at least two behavior habit models of the vehicle function conflict is obtained, and the first target behavior habit model is determined from the at least two behavior habit models of the vehicle function conflict according to the preset usage logic, and the first behavior habit prediction result corresponding to the first target behavior habit model is obtained from the at least two behavior habit prediction results. The vehicle adjustment is controlled according to the first behavior habit prediction result. The method of determining the first target behavior habit model from the at least two behavior habit models of the vehicle function conflict using the preset usage logic can realize the accurate selection of the behavior habit model to be used when there is a conflict in the vehicle function, thereby avoiding the problem that the vehicle cannot be effectively adjusted when there is a conflict in the vehicle function. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 A flowchart of a vehicle control method based on behavioral habits according to an embodiment of the present application;

[0046] Figure 2 A schematic diagram of the structure of a vehicle control device based on behavior habits according to an embodiment of the present application;

[0047] Figure 3 A schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0049] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0050] In the related art, different users often have different behavioral habits when using the vehicle functions. For example, different users (such as drivers or passengers) often have different driving / riding habits. Taking the driver as an example, when he starts the vehicle, he generally ensures that the seat and rearview mirror are in a suitable configuration. Then, people who like to listen to music may turn on the music player immediately, people who like to listen to books may first open the audiobook software, and others may directly open the map for navigation, or drive away without doing anything.

[0051] Furthermore, when the temperature and humidity change, different drivers will have different reactions. For example, when the temperature reaches 30°, some people may immediately turn on the air conditioner for cooling, while others may choose to open the car windows. More specifically, at the same temperature, each person will set the air conditioner temperature, air volume, partition, or the window position and size to open differently.

[0052] Therefore, if the vehicle can adapt to the behavioral habits of each driver, it will greatly improve the driver's exclusive experience of the vehicle. However, there will be conflicts in the vehicle functions corresponding to the adapted behavioral habits, making it impossible to effectively adjust the vehicle.

[0053] Vehicle function conflict refers to the mutual exclusion of control states corresponding to vehicle functional components. For example, the vehicle functions corresponding to the same driver's behavior habits are opening the vehicle windows and turning on the vehicle air conditioner. At this time, there is a functional conflict between opening the vehicle windows and turning on the vehicle air conditioner.

[0054] In addition, the vehicle can also be controlled by an intelligent vehicle control system, which makes corresponding response adjustments based on preset conditions. However, the preset conditions are fixed, will not change, and cannot be applied to all users.

[0055] The embodiment of the present application proposes a vehicle control method based on behavior habits, which uses a preset usage logic to determine a first target behavior habit model from at least two behavior habit models with conflicting vehicle functions, so as to accurately select the behavior habit model to be used when there is a conflict in vehicle functions, thereby avoiding the problem that the vehicle cannot be effectively adjusted when there is a conflict in vehicle functions, such as Figure 1 As shown, including:

[0056] Step 101, obtaining the identity information of the target user.

[0057] In this step, the identity information refers to information used to distinguish the user's personal identity.

[0058] Identity information includes, but is not limited to, the user's name, date of birth, identification number, personal biometric information, address or telephone number.

[0059] For example, the identity information is a face code (Identity document, id), a camera is used to capture a face image of a target user, and then face recognition is performed based on the face image, so as to find the corresponding face code based on the face recognition result.

[0060] Or the identity information is a fingerprint code (Identity document, id), the fingerprint information of the target user is collected through a fingerprint collection sensor, and a neural network is used to pre-train fingerprint feature extraction to obtain a multi-layer feedforward neural network model (BP network, Back Propagation network) that can extract fingerprint features, and based on the fingerprint information, the fingerprint features are extracted through the multi-layer feedforward neural network model to obtain the fingerprint features of the target user, thereby finding the corresponding fingerprint code according to the obtained fingerprint features.

[0061] The target user can be a driver or a passenger, and the driver is preferred here.

[0062] Step 102 retrieves a behavior habit model corresponding to the identity information and determines the number of behavior habit models, wherein the behavior habit model corresponds to adjusting at least one function of the vehicle.

[0063] In this step, the behavior habit model corresponding to the identity information is retrieved. The behavior habit model has been trained in advance, and the training process is as follows:

[0064] The training data set corresponding to the target user is collected by means of tracking points, and the trained initial model is used as the behavior habit model corresponding to the target user. The training data set includes vehicle function status data and driving environment data.

[0065] Among them, the vehicle function status data can be: 1) vehicle information: vehicle speed, steering wheel angle, seat status, window status, air conditioning status, etc., 2) application information: navigation, music, etc.

[0066] Driving environment data can be: 1) weather information: temperature, humidity, air quality, sunny, rainy, foggy, etc.; 2) spatiotemporal information: time, location, season, etc.; 3) external vehicle information: road environment, traffic flow, etc.; 4) other information: vehicle intelligent monitoring system (VIMs) results, etc.

[0067] The behavior habit model refers to a model for predicting a user's possible vehicle function operation based on driving environment data.

[0068] For example, the behavioral habit model predicts whether the car windows are open, if open, how wide the windows are open, how long the windows are open, or the order in which the windows are opened.

[0069] Alternatively, the behavior habit model may predict whether the air conditioner is turned on, and if so, how the air conditioner mode is set, how the air conditioner temperature is adjusted, how long the air conditioner is turned on, or the order in which the air conditioner is turned on.

[0070] The behavior habit model corresponding to the identity information is retrieved, and the number of the behavior habit models is determined, so as to determine whether there is a possibility of vehicle function conflict according to the number of the behavior habit models.

[0071] Step 103, when the number of behavior habit models is at least two, obtain the first current driving environment data corresponding to the target user, input the first current driving environment data into at least two behavior habit models, and respectively output at least two corresponding behavior habit prediction results through the at least two behavior habit models.

[0072] In this step, when the number of behavioral habit models corresponding to the identity information of the target user is at least two, the first current driving environment data is respectively input into at least the at least two behavioral habit models, and the at least two behavioral habit models output the corresponding at least two behavioral habit models, so as to judge whether there is a vehicle function conflict between the at least two behavioral habit models based on the at least two behavioral habit models.

[0073] Step 104, when the vehicle function conflict corresponding to at least two behavior habit models is determined according to the at least two behavior habit prediction results, the preset usage logic of the at least two behavior habit models of the vehicle function conflict is obtained.

[0074] In this step, when the vehicle function conflict corresponding to at least two behavior habit models is determined based on at least two behavior habit prediction results, the preset usage logic of the at least two behavior habit models of the vehicle function conflict is obtained, wherein the preset usage logic is used to represent the usage rules of the at least two behavior habit models of the vehicle function conflict.

[0075] For example, the behavioral habit model can be a model for predicting the use of windows (window opening, window opening position, sunroof), a model for predicting the use of air conditioning (temperature, wind speed, air purification, negative ions, steering wheel heating), a model for predicting the use of ambient lights (switch, mode, brightness), a model for predicting driving position adjustment (seat position, rearview mirror, head-up display system (Head Up Display, HUD), the height of the head-up display system, the brightness of the head-up display system, the angle of the head-up display system), a model for predicting the use of in-vehicle applications (Application, APP), a model for predicting vehicle driving mode settings (off-road mode, four-wheel drive mode, steering mode, suspension mode, drive mode), a model for predicting the use of smart screen savers (start-up time, display mode, automatic switching time, pattern selection, screen saver switch), a model for predicting vehicle control settings (automatic parking, automatic headlights, smart start and stop, steering wheel power mode, head-up display system switch) or a model for predicting system settings (music settings (equalizer settings-treble settings, equalizer settings-mid-range settings, equalizer settings-bass settings), central control screen brightness, theme switching).

[0076] The vehicle function indicates the control state corresponding to the vehicle function component, for example, all control operations for the vehicle window, including at least one of the following:

[0077] Control the opening of vehicle windows, the degree of opening of windows, and the position of windows that need to be opened.

[0078] All control operations of the air conditioner include at least one of the following:

[0079] Control the vehicle's air conditioning, wind speed, temperature, and air conditioning mode.

[0080] Vehicle function conflict refers to the mutual exclusion of control states corresponding to vehicle functional components. For example, the vehicle functions corresponding to the same driver's behavior habits are opening the vehicle windows and turning on the vehicle air conditioner. At this time, there is a functional conflict between opening the vehicle windows and turning on the vehicle air conditioner.

[0081] Among them, whether there is a vehicle function conflict between at least two behavior habit models can be determined by inputting driving environment data into the at least two behavior habit models and judging whether there is a vehicle function conflict between the at least two behavior habit models based on corresponding behavior habit prediction results.

[0082] For example, the driving environment data is that the temperature reaches 30°, and the at least two behavior habit models are respectively a model for predicting the use of air conditioning and a model for predicting the use of windows. The temperature reaching 30° is input into the model for predicting the use of air conditioning, and the output behavior habit prediction result is to turn on the air conditioner. The temperature reaching 30° is input into the model for predicting the use of windows, and the output behavior habit prediction result is to open the windows. At this time, there is a conflict between "opening the windows" and "turning on the air conditioner", and it is determined that there is a vehicle function conflict between the model for predicting the use of air conditioning and the model for predicting the use of windows.

[0083] As an optional embodiment, when predicting the behavior habits of the target user, the behavior habit model may be implemented using a decision tree model.

[0084] The usage of vehicle functions of the same category can be predicted by the same decision tree model. For example, the window opening, window position, and sunroof can be represented by a decision tree model for predicting window usage.

[0085] Among them, for different decision tree models, the required input data and quantity will be different. The selection of input data can be completed by the decision tree model, or it can be determined in advance by humans.

[0086] It can be understood that in the above embodiment, the decision tree model is used to predict the behavior habits of the target user, but in fact, other models can also be used to predict the behavior habits of the target user. These models, for example, can be random forest models, iterative algorithm classifiers (ADABOOST), deep learning models (transformer), etc.

[0087] And the vehicle functions corresponding to at least two behavioral habit models conflict. For example, the prediction result of the model used to predict the use of windows is that the windows need to be opened, and the prediction result of the model used to predict the use of air conditioners is that the air conditioner needs to be turned on. At this time, the two behaviors of "opening the windows" and "turning on the air conditioner" are in conflict.

[0088] The preset usage logic is used to represent usage rules of at least two behavior habit models that conflict with vehicle functions.

[0089] For example, at least two behavior habit models of vehicle function conflict are a model for predicting window usage and a model for predicting air conditioning usage, and one of the models for predicting window usage and air conditioning usage is selected for use.

[0090] Alternatively, when there is a conflict in vehicle functions, a model for predicting window usage is used / a model for predicting air conditioning usage is used.

[0091] Alternatively, the model for predicting window usage at a first preset time (for example, 30 minutes) is first used, and then the model for predicting air conditioning usage at a second preset time (for example, 20 minutes) is used; or the model for predicting air conditioning usage at a first preset time is first used, and then the model for predicting window usage at a second preset time is used, wherein the first preset time and the second preset time are set according to specific circumstances.

[0092] Step 105, determining a first target behavior habit model from at least two behavior habit models of the vehicle function conflict according to the preset usage logic, and obtaining a first behavior habit prediction result corresponding to the first target behavior habit model from the at least two behavior habit prediction results, and controlling vehicle adjustment according to the first behavior habit prediction result.

[0093] In this step, a more accurate first target behavior habit model is determined according to the preset usage logic. The first target behavior habit model represents the model finally determined for predicting the target user's behavior habits. Then, the first current driving environment data is input into the first target behavior habit model. The first target behavior habit model outputs a first behavior habit prediction result. The vehicle is controlled according to the first behavior habit prediction result. The first behavior habit prediction result represents the control state that the user may set for the vehicle's functional components. For example, the first behavior habit prediction result is to control the opening of the cockpit window, and the opening degree is set to 60 percent.

[0094] The method of determining the first target behavior habit model from at least two behavior habit models by using preset usage logic can achieve accurate selection of the behavior habit model to be used when there is a conflict in vehicle functions, thereby avoiding the problem that the vehicle cannot be effectively adjusted when there is a conflict in vehicle functions.

[0095] Through the above scheme, by obtaining the identity information of the target user, calling the behavior habit model corresponding to the identity information, and determining the number of behavior habit models, the behavior habit model corresponds to adjusting at least one function of the vehicle. When the number of behavior habit models is at least two, the first current driving environment data corresponding to the target user is obtained, the first current driving environment data is input into at least two behavior habit models, and at least two corresponding behavior habit prediction results are output by the at least two behavior habit models respectively. When it is determined that the vehicle functions corresponding to the at least two behavior habit models conflict according to the at least two behavior habit prediction results, the preset usage logic of the at least two behavior habit models of the vehicle function conflict is obtained, and the first target behavior habit model is determined from the at least two behavior habit models of the vehicle function conflict according to the preset usage logic, and the first behavior habit prediction result corresponding to the first target behavior habit model is obtained from the at least two behavior habit prediction results, and the vehicle adjustment is controlled according to the first behavior habit prediction result. The method of determining the first target behavior habit model from at least two behavior habit models using the preset usage logic can realize the accurate selection of the behavior habit model to be used when there is a conflict in vehicle functions, thereby avoiding the problem that the vehicle cannot be effectively adjusted when there is a conflict in vehicle functions.

[0096] In some embodiments, the preset usage logic of the at least two behavior habit models sets corresponding priorities for the at least two behavior habit models.

[0097] In step 105, determining a first target behavior habit model from at least two behavior habit models of conflicting vehicle functions according to the preset usage logic includes:

[0098] According to the priority, a behavior habit model with the highest priority is selected from at least two behavior habit models as the first target behavior habit model.

[0099] In the above scheme, when the preset usage logic represents the priority, based on the priorities corresponding to at least two behavior habit models of conflicting vehicle functions, the behavior habit model with the highest priority among the at least two behavior habit models is selected as the first target behavior habit model to be used in the end more accurately.

[0100] According to the preset priorities of at least two behavioral habit models of vehicle function conflict and in accordance with the priority order of at least two behavioral habit models of vehicle function conflict, the prediction result output by the behavioral habit model with the highest priority among the at least two behavioral habit models of vehicle function conflict is used as the input of the behavioral habit model with the lowest priority to determine the final vehicle response result. For example, the at least two behavioral habit models of vehicle function conflict are a model for predicting window usage and a model for predicting air-conditioning usage. The prediction result of the model for predicting window usage is that the window needs to be opened, and the prediction result of the model for predicting air-conditioning usage is that the air-conditioning needs to be turned on. At this time, there is a conflict between the two behaviors of "opening the window" and "turning on the air-conditioning".

[0101] When the priority of the model used to predict the use of air conditioning is higher than that of the model used to predict the use of windows, the input of the model used to predict the use of windows will receive the information that the air conditioning should be turned on at this time. At this time, the behavior of "opening the window" will be judged as invalid. At this time, the air conditioning should be turned on and the behavior of "opening the window" will be judged as invalid as the final vehicle response result, and there will be no functional conflict between opening the window and turning on the air conditioner at the same time.

[0102] This enables self-correction between the behavioral habits predicted by each behavioral habit model.

[0103] In some embodiments, at step 105, after controlling the vehicle adjustment according to the first behavior habit prediction result, the method further includes:

[0104] Step A1, collecting a first training data set corresponding to the target user, wherein the first training data set includes first vehicle function status data and first driving environment data.

[0105] Step A2: Use the first vehicle function status data and the first driving environment data to train the first target behavior habit model to obtain a trained first target behavior habit model.

[0106] Step A3, storing the correspondence between the trained first target behavior habit model and the identity information corresponding to the target user into a preset behavior habit model database, and using the trained first target behavior habit model as a new first target behavior habit model, while storing the correspondence between the first target behavior habit model before training and the identity information corresponding to the target user in the behavior habit model database.

[0107] In the above solution, the preset behavior habit database can be stored in the cloud or in the vehicle, with the cloud being preferred.

[0108] When the model update function is turned on, a first training data set corresponding to the target user is collected by means of tracking points and temporarily stored in the vehicle computer or the cloud. The first training data set is uploaded to the cloud, and the first target behavior habit model is trained and updated in the cloud using the first training data set. The correspondence between the trained first target behavior habit model and the identity information corresponding to the target user is stored in a preset behavior habit model database and sent to the vehicle computer. The first training data set includes first vehicle function status data and first driving environment data. The first vehicle function status data can be: 1) vehicle information: vehicle speed, steering wheel angle, seat status, window status, air conditioning status, etc., 2) application information: navigation, music, etc.

[0109] The first driving environment data may be: 1) weather information: temperature, humidity, air quality, sunny, rainy, foggy, etc.; 2) spatiotemporal information: time, location, season, etc.; 3) external vehicle information: road environment, traffic flow, etc.; 4) other information: vehicle intelligent monitoring system (VIMs) results, etc.

[0110] Among them, during the training and updating process of the first target behavior habit model, it is necessary to determine whether the first target behavior habit model in the training process meets the convergence conditions. Generally speaking, when the first target behavior habit model in the training process changes very little, it can be considered to be converged. At this time, the converged model (that is, the new first target behavior habit model) needs to be uniformly stored in the cloud and stored in the preset behavior habit model database to meet the subsequent analysis and clustering of a large number of stored behavior habit models.

[0111] The correspondence between the first target behavior habit model before training and the identity information corresponding to the target user is stored in the behavior habit model database, so that the target user can reuse the first target behavior habit model before updating.

[0112] In some embodiments, in step A3, after storing the correspondence between the first target behavior habit model before training and the identity information corresponding to the target user in the behavior habit model database, the method further includes:

[0113] Step B1, obtaining a current first target behavior habit model corresponding to the identity information of the target user.

[0114] Step B2, when the current behavior habit model is the new first target behavior habit model and a switching instruction is received, the new first target behavior habit model is switched to the first target behavior habit model before training; or,

[0115] Step B3, when the current behavior habit model is the first target behavior habit model before training and a switching instruction is received, the first target behavior habit model before training is switched to the new first target behavior habit model.

[0116] In the above solution, multiple behavior habit models can be stored in the behavior habit model database and switched.

[0117] If the current behavior habit model is an updated new first target behavior habit model, when a switching instruction is received, the updated new first target behavior habit model is switched to the first target behavior habit model before the update.

[0118] If the current behavior habit model is the first target behavior habit model before updating, when a switching instruction is received, the first target behavior habit model before updating is switched to the new first target behavior habit model after updating.

[0119] In some embodiments, the method further comprises:

[0120] Step C1, when there is no identity information corresponding to the target user, new identity information is created and a preset behavior habit model is obtained.

[0121] Step C2, collecting a second training data set corresponding to the target user, wherein the second training data set includes second vehicle function status data and second driving environment data.

[0122] Step C3, using the second vehicle function status data and the second driving environment data to train the preset behavior habit model to obtain a trained preset behavior habit model, and storing the correspondence between the trained preset behavior habit model and the new identity information corresponding to the target user into a preset behavior habit model database.

[0123] In the above scheme, if there is no identity information corresponding to the target user, it means that the user has never been stored or has never driven. At this time, new identity information of the target user is created, and the default behavior habit model (i.e., the preset behavior habit model) is used to inquire whether to train the default behavior habit model. After receiving the confirmation training instruction, the second training data set corresponding to the target user is collected. The preset behavior habit model is trained with the second training data set to obtain a trained preset behavior habit model, and the correspondence between the trained preset behavior habit model and the new identity information corresponding to the target user is stored in the preset behavior habit model database, so that the user can realize the adaptive adaptation of the behavior habit according to the correspondence between the stored preset behavior habit model and the new identity information corresponding to the target user when using the vehicle next time, thereby controlling the vehicle for adjustment.

[0124] Among them, the second training data set includes second vehicle function status data and second driving environment data, and the second vehicle function status data can be: 1) vehicle information: vehicle speed, steering wheel angle, seat status, window status, air conditioning status, etc., 2) application information: navigation, music, etc.

[0125] The second driving environment data can be: 1) weather information: temperature, humidity, air quality, sunny, rainy, foggy, etc.; 2) time and space information: time, place, season, etc.; 3) external vehicle information: road environment, traffic flow, etc.; 4) other information: vehicle intelligent monitoring system (VIMs) results, etc.

[0126] In some embodiments, each behavior habit model is stored in advance in a preset behavior habit model database, and the method further includes:

[0127] Step D1, performing cluster analysis on each behavior habit model stored in the behavior habit model database to obtain multiple category groups.

[0128] Step D2, displaying the behavior habit models classified into the multiple category groups.

[0129] Step D3, receiving a selection instruction for a second target behavior habit model, acquiring second current driving environment data, inputting the second current driving environment data into the second target behavior habit model, outputting a second behavior habit prediction result through the second target behavior habit model, and controlling vehicle adjustment according to the second behavior habit prediction result, wherein the second target behavior habit model is at least one of the behavior habit models classified into the multiple category groups.

[0130] In the above scheme, cluster analysis is performed on each behavior habit model stored in the behavior habit model database to obtain multiple category groups, and the behavior habit models classified into the multiple category groups are displayed for recommendation to users who use the vehicle. Category groups include: comfort (playing light and soothing music, soft ambient lighting, air-conditioning settings that match the weather, etc.), economy (opening windows when hot, changing driving modes, etc.), etc.

[0131] In addition, users can upload more personalized and interesting behavior habit models that they have adjusted themselves to the behavior habit model library stored in the cloud for other users to try. However, if there are extreme behaviors in the behavior habit models uploaded by users (such as always turning the air conditioner to the coldest / hottest), there are clear management measures, such as limiting the air conditioner adjustment range or prohibiting such users from uploading habit models and handling related behavior habit models in a timely manner. Users can also download and experience other users' behavior habit models from the cloud, which can enhance the user's driving experience and convenience.

[0132] In some embodiments, step D1 comprises:

[0133] Step D11, obtaining third driving environment data.

[0134] Step D12, performing predictions based on the third driving environment data through various behavior habit models to obtain multiple behavior habit prediction results.

[0135] Step D13, combining the third driving environment data with each behavior habit prediction result to obtain multiple classification features.

[0136] Step D14, performing cluster analysis on the multiple classification features to obtain multiple category groups.

[0137] In the above scheme, the behavior habit model is represented by f(·). First, the third driving environment data and the output behavior corresponding to the behavior habit model are encoded and represented as X (i.e., the third driving environment data) and Y (i.e., the behavior habit prediction result), respectively, where X includes the vehicle condition data under various circumstances. Different behavior habit models will have different responses to X, i.e., Y=f(X). In this way, [X, Y] can be used as the feature of the behavior habit model for subsequent analysis.

[0138] Among them, the third driving environment data can be: 1) weather information: temperature, humidity, air quality, sunny, rainy, foggy, etc.; 2) time and space information: time, place, season, etc.; 3) external vehicle information: road environment, traffic flow, etc.; 4) other information: vehicle intelligent monitoring system (VIMs) results, etc.

[0139] Perform cluster analysis on [X, Y] corresponding to all behavioral habit models, and classify each behavioral habit model according to the final cluster center. At the same time, calculate the distance between the behavioral habit model and each cluster center and annotate the corresponding category score (such as comfort index, economic index, etc.).

[0140] Among them, K-means clustering algorithm (K-means) can be used for clustering analysis, and the process is as follows:

[0141] Select any classification feature from all classification features as the cluster center for cluster analysis.

[0142] Obtaining the distance between each of the other classification features except the classification feature that is the cluster center of the cluster analysis processing and the classification feature that is the cluster center of the cluster analysis processing;

[0143] Assign each other classification feature to the nearest cluster center based on the total distance;

[0144] When all other classification features are assigned, the cluster center is updated, and the new distances between each new other classification feature except the new classification feature as the updated cluster center and the new classification feature as the updated cluster center after cluster analysis are obtained, and the new other classification features are assigned according to all the new distances;

[0145] When the preset termination condition of the cluster analysis process is reached, a plurality of category groups are obtained.

[0146] In addition, some behavioral habit models with obvious behaviors in the behavioral habit model database can be labeled in advance (such as radical, moderate, and economical) and used as labels for classification or clustering.

[0147] In some real-time examples, step D13 includes:

[0148] Step D131, combining the third driving environment data and each behavior habit prediction result to form a plurality of initial classification features.

[0149] Step D132, performing dimensionality reduction processing on the multiple initial classification features to obtain multiple first dimensional classification features.

[0150] Step D133, mapping the multiple first dimension classification features to multiple second dimension classification features, using the multiple second dimension classification features as the multiple classification features, and the dimension of the second dimension classification features is higher than the dimension of the second dimension classification features.

[0151] In the above scheme, the initial [X, Y] dimension is generally high. Here, the feature [X, Y] can be reduced in dimension through principal component analysis (PCA) or neural network methods, and mapped to a high-dimensional space that is more suitable for model category division. The result after mapping is recorded as m([X, Y]) (i.e., classification feature).

[0152] In some embodiments, after step D2, the method further comprises:

[0153] Step E1, receiving scores for the behavior habit models classified into the multiple category groups stored in the behavior habit model database.

[0154] Step E2, reclassifying the behavior habit models classified into the multiple category groups according to the scores of the behavior habit models classified into the multiple category groups.

[0155] In the above scheme, behavioral habit models classified into various category groups are recommended to users. After the user selects at least one of the recommended behavioral habit models, the behavioral habit model can be scored according to the user's own usage experience, and then the behavioral habit models classified into multiple category groups can be reclassified according to the user's score.

[0156] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.

[0157] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0158] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a vehicle control device based on behavioral habits.

[0159] refer to Figure 2 , the vehicle control device based on behavior habits comprises:

[0160] The identity information acquisition module 201 is used to acquire the identity information of the target user;

[0161] A behavior habit model retrieval module 202, used to retrieve a behavior habit model corresponding to the identity information and determine the number of behavior habit models, wherein the behavior habit model corresponds to adjusting at least one function of the vehicle;

[0162] The behavior habit prediction result output module 203 is used for obtaining the first current driving environment data corresponding to the target user when the number of the behavior habit models is at least two, inputting the first current driving environment data into at least two behavior habit models, and outputting at least two corresponding behavior habit prediction results through the at least two behavior habit models respectively;

[0163] The preset usage logic acquisition module 204 is used to acquire the preset usage logic of the at least two behavior habit models of the vehicle function conflict when the vehicle function conflict corresponding to the at least two behavior habit models is determined according to the at least two behavior habit prediction results;

[0164] The control and adjustment module 205 is used to determine a first target behavior habit model from at least two behavior habit models of vehicle function conflict according to the preset usage logic, and obtain a first behavior habit prediction result corresponding to the first target behavior habit model from the at least two behavior habit prediction results, and control vehicle adjustment according to the first behavior habit prediction result.

[0165] In some embodiments, the preset usage logic of the at least two behavior habit models sets corresponding priorities for the at least two behavior habit models;

[0166] The control and regulation module 205 is specifically used for:

[0167] According to the priority, a behavior habit model with the highest priority is selected from at least two behavior habit models with conflicting vehicle functions as the first target behavior habit model.

[0168] In some embodiments, the behavior-habit-based vehicle control device further includes a model training module. After the vehicle is adjusted according to the first behavior habit prediction result, the model training module is specifically used to:

[0169] Collecting a first training data set corresponding to the target user, the first training data set including first vehicle function status data and first driving environment data;

[0170] Using the first vehicle function status data and the first driving environment data to train the first target behavior habit model to obtain a trained first target behavior habit model;

[0171] The correspondence between the trained first target behavior habit model and the identity information corresponding to the target user is stored in a preset behavior habit model database, and the trained first target behavior habit model is used as a new first target behavior habit model. At the same time, the correspondence between the first target behavior habit model before training and the identity information corresponding to the target user is stored in the behavior habit model database.

[0172] In some embodiments, the behavior-habit-based vehicle control device further includes a model switching module. After the correspondence between the first target behavior habit model before training and the identity information corresponding to the target user is stored in the behavior habit model database, the model switching module is specifically used to:

[0173] Acquire a current first target behavior habit model corresponding to the identity information of the target user;

[0174] When the current behavior habit model is the new first target behavior habit model and a switching instruction is received, the new first target behavior habit model is switched to the first target behavior habit model before training; or,

[0175] When the current behavior habit model is the first target behavior habit model before training and a switching instruction is received, the first target behavior habit model before training is switched to the new first target behavior habit model.

[0176] In some embodiments, the behavior-habit-based vehicle control device further includes a storage module, and the storage module is specifically used for:

[0177] When there is no identity information corresponding to the target user, new identity information is created and a preset behavior habit model is obtained;

[0178] Collecting a second training data set corresponding to the target user, the second training data set including second vehicle function status data and second driving environment data;

[0179] The preset behavior habit model is trained using the second vehicle function status data and the second driving environment data to obtain a trained preset behavior habit model, and the correspondence between the trained preset behavior habit model and the new identity information corresponding to the target user is stored in a preset behavior habit model database.

[0180] In some embodiments, each behavior habit model is pre-stored in a preset behavior habit model database, and the behavior habit-based vehicle control device further includes a selected adjustment module, and the selected adjustment module includes:

[0181] A cluster analysis processing unit, used to perform cluster analysis on each behavior habit model stored in the behavior habit model database to obtain a plurality of category groups;

[0182] A display unit, configured to display the behavior habit models classified into the plurality of category groups;

[0183] A selection adjustment unit is used to receive a selection instruction of a second target behavior habit model, obtain second current driving environment data, input the second current driving environment data into the second target behavior habit model, output a second behavior habit prediction result through the second target behavior habit model, and control vehicle adjustment according to the second behavior habit prediction result, wherein the second target behavior habit model is at least one of the behavior habit models classified into the multiple category groups.

[0184] In some embodiments, the cluster analysis processing unit includes:

[0185] A driving environment data acquisition subunit, used to acquire third driving environment data;

[0186] A prediction subunit, configured to perform predictions based on the third driving environment data through various behavior habit models to obtain a plurality of behavior habit prediction results;

[0187] A classification feature acquisition subunit, used for combining the third driving environment data with each behavior habit prediction result to obtain a plurality of classification features;

[0188] The cluster analysis processing subunit is used to perform cluster analysis on multiple classification features to obtain multiple category groups.

[0189] In some embodiments, the classification feature acquisition subunit is specifically used to:

[0190] combining the third driving environment data with each behavior habit prediction result to form a plurality of initial classification features;

[0191] Performing dimensionality reduction processing on the multiple initial classification features to obtain multiple first-dimensional classification features;

[0192] The multiple first-dimensional classification features are mapped to multiple second-dimensional classification features, and the multiple second-dimensional classification features are used as the multiple classification features, wherein the dimension of the second-dimensional classification features is higher than the dimension of the second-dimensional classification features.

[0193] In some embodiments, the behavior-habit-based vehicle control device further includes a category updating module. After displaying the category of the at least one behavior habit model, the category updating module is specifically used to:

[0194] receiving scores for the behavior habit models classified into the plurality of category groups and stored in the behavior habit model database;

[0195] The behavior habit models classified into the plurality of category groups are reclassified according to the scores of the behavior habit models classified into the plurality of category groups.

[0196] For the convenience of description, the above device is described in terms of functions divided into various modules. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0197] The device of the above embodiment is used to implement the corresponding vehicle control method based on behavior habits in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0198] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the behavior-habit-based vehicle control method described in any of the above embodiments is implemented.

[0199] Figure 3 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 301, a memory 302, an input / output interface 303, a communication interface 304, and a bus 305. The processor 301, the memory 302, the input / output interface 303, and the communication interface 304 are connected to each other in communication within the device through the bus 305.

[0200] The processor 301 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an 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 specification.

[0201] The memory 302 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 302 can store operating systems and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 302 and called and executed by the processor 301.

[0202] The input / output interface 303 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.

[0203] The communication interface 304 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0204] The bus 305 comprises a pathway for transmitting information between the various components of the device (eg, the processor 301 , the memory 302 , the input / output interface 303 , and the communication interface 304 ).

[0205] It should be noted that, although the above device only shows the processor 301, the memory 302, the input / output interface 303, the communication interface 304 and the bus 305, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0206] The electronic device of the above-mentioned embodiment is used to implement the corresponding vehicle control method based on behavior habits in any of the above-mentioned embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0207] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the behavior-habit-based vehicle control method as described in any of the above embodiments.

[0208] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0209] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the vehicle control method based on behavioral habits as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0210] Based on the same inventive concept, this embodiment provides a vehicle corresponding to the behavior-habit-based vehicle control device or electronic device or storage medium of any of the above-mentioned embodiments, and the vehicle is equipped with a behavior-habit-based vehicle control device or electronic device or storage medium that can implement the behavior-habit-based vehicle control method of any of the above-mentioned embodiments.

[0211] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0212] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0213] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0214] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of the present application.

Claims

1. A vehicle control method based on behavioral habits, characterized in that: include: Obtain the target user's identity information; Retrieving a behavior habit model corresponding to the identity information and determining the number of behavior habit models, wherein the behavior habit model corresponds to adjusting at least one function of the vehicle; When the number of behavior habit models is at least two, obtaining first current driving environment data corresponding to the target user, inputting the first current driving environment data into at least two behavior habit models, and respectively outputting at least two corresponding behavior habit prediction results through the at least two behavior habit models; When a conflict in vehicle functions corresponding to at least two behavior habit models is determined according to the at least two behavior habit prediction results, obtaining preset usage logics of at least two behavior habit models of the conflict in vehicle functions; According to the preset usage logic, a first target behavior habit model is determined from at least two behavior habit models of the vehicle function conflict, and a first behavior habit prediction result corresponding to the first target behavior habit model is obtained from the at least two behavior habit prediction results, and vehicle adjustment is controlled according to the first behavior habit prediction result.

2. The method according to claim 1, characterized in that The preset usage logic of the at least two behavior habit models sets corresponding priorities for the at least two behavior habit models; The determining of a first target behavior habit model from at least two behavior habit models of conflicting vehicle functions according to the preset usage logic includes: According to the priority, a behavior habit model with the highest priority is selected from at least two behavior habit models with conflicting vehicle functions as the first target behavior habit model.

3. The method according to claim 1, characterized in that: After controlling the vehicle adjustment according to the first behavior habit prediction result, the method further includes: Collecting a first training data set corresponding to the target user, the first training data set including first vehicle function status data and first driving environment data; Using the first vehicle function status data and the first driving environment data to train the first target behavior habit model to obtain a trained first target behavior habit model; The correspondence between the trained first target behavior habit model and the identity information corresponding to the target user is stored in a preset behavior habit model database, and the trained first target behavior habit model is used as a new first target behavior habit model. At the same time, the correspondence between the first target behavior habit model before training and the identity information corresponding to the target user is stored in the behavior habit model database.

4. The method according to claim 3, characterized in that After storing the correspondence between the first target behavior habit model before training and the identity information corresponding to the target user in the behavior habit model database, the method further includes: Acquire a current first target behavior habit model corresponding to the identity information of the target user; When the current behavior habit model is the new first target behavior habit model and a switching instruction is received, the new first target behavior habit model is switched to the first target behavior habit model before training; or, When the current behavior habit model is the first target behavior habit model before training and a switching instruction is received, the first target behavior habit model before training is switched to the new first target behavior habit model.

5. The method according to claim 1, characterized in that: The method further comprises: When there is no identity information corresponding to the target user, new identity information is created and a preset behavior habit model is obtained; Collecting a second training data set corresponding to the target user, the second training data set including second vehicle function status data and second driving environment data; The preset behavior habit model is trained using the second vehicle function status data and the second driving environment data to obtain a trained preset behavior habit model, and the correspondence between the trained preset behavior habit model and the new identity information corresponding to the target user is stored in a preset behavior habit model database.

6. The method according to claim 1, characterized in that Each behavior habit model is stored in advance in a preset behavior habit model database, and the method further includes: Performing cluster analysis on each behavior habit model stored in the behavior habit model database to obtain multiple category groups; displaying the behavioral habit models classified into the plurality of category groups; Receive a selection instruction for a second target behavior habit model, obtain second current driving environment data, input the second current driving environment data into the second target behavior habit model, output a second behavior habit prediction result through the second target behavior habit model, and control vehicle adjustment according to the second behavior habit prediction result, wherein the second target behavior habit model is at least one of the behavior habit models classified into the multiple category groups.

7. The method according to claim 6, characterized in that The clustering analysis is performed on each behavior habit model stored in the behavior habit model database to obtain multiple category groups, including: Acquiring third driving environment data; Based on the third driving environment data, prediction is performed using various behavior habit models to obtain multiple behavior habit prediction results; Combining the third driving environment data with each behavior habit prediction result to obtain a plurality of classification features; Cluster analysis is performed on multiple classification features to obtain multiple category groups.

8. The method according to claim 7, characterized in that The third driving environment data is combined with each behavior habit prediction result to obtain multiple classification features, including: combining the third driving environment data with each behavior habit prediction result to form a plurality of initial classification features; Performing dimensionality reduction processing on the multiple initial classification features to obtain multiple first-dimensional classification features; The multiple first-dimensional classification features are mapped to multiple second-dimensional classification features, and the multiple second-dimensional classification features are used as the multiple classification features, wherein the dimension of the second-dimensional classification features is higher than the dimension of the second-dimensional classification features.

9. The method according to claim 6, characterized in that After displaying the behavior habit models classified into the plurality of category groups, the method further includes: receiving scores for the behavior habit models classified into the plurality of category groups and stored in the behavior habit model database; The behavior habit models classified into the plurality of category groups are reclassified according to the scores of the behavior habit models classified into the plurality of category groups.

10. A vehicle, characterized in that: Used to execute the method described in any one of claims 1 to 9.

Images