Intelligent vehicle-mounted application adjusting method and system based on driving scene

Abstract

The invention discloses an intelligent vehicle-mounted application adjusting method and system based on a driving scene, and relates to the field of vehicle-mounted application, and the method comprises the steps: obtaining current real-time driving data, current external environment information and current position information, and matching a user behavior mode of a current vehicle in a preset behavior mode database according to the current real-time driving data, identifying a driving scene of a current vehicle according to the current external environment information and the current position information, and predicting an information type and a presentation mode required by a current driver according to the user behavior mode and the driving scene, and determining an information presentation mode and information presentation time in a preset application database according to the information type and the presentation mode, and presenting all the vehicle-mounted applications according to the information presentation mode and the information presentation time, and by implementing the method, the driving experience of a driver can be improved in a complex driving scene.

Description

Technical Field

[0001] The present application relates to the field of vehicle-mounted applications, and in particular to a method and system for adjusting intelligent vehicle-mounted applications based on driving scenarios. Background Art

[0002] With the rapid development of smart car technology, in-vehicle application systems have become an indispensable part of modern cars. These systems not only provide basic functions such as navigation and entertainment, but also provide drivers with a variety of real-time information and auxiliary functions, improving driving experience and safety.

[0003] In the relevant technologies, most in-vehicle application systems adopt a fixed information presentation method. These systems usually display various types of information to the driver in a unified form at a preset time point or when a specific event is triggered. For example, during driving, the system may periodically display data such as vehicle speed and fuel consumption, or issue a voice prompt when approaching a turning point on the navigation path.

[0004] However, in complex driving scenarios, this approach may lead to a poor driver experience. For example, on congested urban roads, frequent navigation prompts may increase the driver's irritability, while on familiar roads, repeated information may distract the driver's attention. In addition, different drivers have different needs for information, and the existing preset information delivery method is difficult to make timely and appropriate adjustments to these complex situations. Summary of the invention

[0005] The present application provides a method and system for adjusting intelligent in-vehicle applications based on driving scenarios, which are used to improve the driver's driving experience in complex driving scenarios.

[0006] In the first aspect, the present application provides an intelligent in-vehicle application adjustment method based on driving scenarios, which is applied to an intelligent in-vehicle application adjustment system, and the method includes: obtaining current real-time driving data, current external environment information and current location information; identifying a user behavior pattern that matches the current vehicle in a preset behavior pattern database based on the current real-time driving data; identifying the driving scene of the current vehicle based on the current external environment information and the current location information; predicting the type of information and presentation method required by the current driver based on the user behavior pattern and the driving scene, the information type is a classification of prompt information that needs to be transmitted to the current driver, and the presentation method is a presentation method for transmitting the prompt information to the current driver, and the prompt information is transmitted by the in-vehicle application; determining an information presentation mode and an information presentation time in a preset application database based on the information type and the presentation method, the information presentation mode is a presentation form of the in-vehicle application, and the information presentation time is a presentation time point of the in-vehicle application; presenting all in-vehicle applications based on the information presentation mode and the information presentation time.

[0007] By adopting the above technical solution, it is possible to obtain current real-time driving data, external environment information and location information, so as to fully understand the driving status and surrounding conditions of the vehicle. Based on these data, the system matches the user behavior pattern in the preset behavior pattern database, determines the information presentation mode and time in the preset application database, and finally presents the in-vehicle application according to this information, so that the display of the in-vehicle application can be personalized according to the user's behavior pattern and driving scene. For example, in congested road scenes, the frequency and method of navigation prompts can be intelligently adjusted according to the driver's habits and current scenes to avoid excessive prompts that increase the driver's irritability; on familiar roads, the display of repeated information can be reduced to avoid distracting the driver's attention, thereby improving the driving experience and safety.

[0008] In combination with some embodiments of the first aspect, in some embodiments, the step of identifying and matching the user behavior pattern of the current vehicle in a preset behavior pattern database based on the current real-time driving data specifically includes: obtaining historical driving data within a preset time period; performing cluster analysis on the historical driving data to obtain multiple driving behavior characteristics; constructing a user driving behavior model based on the driving behavior characteristics, and inputting the current real-time driving data into the user driving behavior model to obtain current driving behavior characteristics; searching the preset behavior pattern database for the preset behavior pattern with the highest similarity to the current driving behavior characteristics, and using the preset behavior pattern as the user behavior pattern of the current vehicle.

[0009] By adopting the above technical solution, the historical driving data within the preset time period is first obtained, and a cluster analysis is performed on it to obtain multiple driving behavior features, and then a user driving behavior model is constructed. The current real-time driving data is input into the model to obtain the current driving behavior features, and then the preset behavior pattern with the highest similarity to the feature is searched in the preset behavior pattern database as the user behavior pattern of the current vehicle, so that the system can accurately identify the user's driving habits, such as frequent lane changes, constant speed driving, etc. Based on these accurately identified user behavior patterns, the driver's needs can be more accurately predicted, and information services that are more in line with the driver's habits can be provided.

[0010] In combination with some embodiments of the first aspect, in some embodiments, the step of identifying the driving scene of the current vehicle based on the current external environment information and the current position information specifically includes: obtaining real-time image data and sound data within a preset distance around the current vehicle based on the current external environment information; analyzing the real-time image data based on an image recognition algorithm to obtain road information within a preset distance around the current vehicle, and performing spectral analysis on the sound data to identify noise information within a preset distance around the current vehicle; fusing the road information, the noise information and the current time information to obtain a multi-dimensional environmental vector feature; and inputting the multi-dimensional environmental vector feature into a preset scene classification model to obtain the category of the current driving scene.

[0011] By adopting the above technical solution, real-time image data and sound data within a preset distance around the vehicle are obtained according to the current external environment information, the image is analyzed by the image recognition algorithm to obtain road information, and the sound data is subjected to spectral analysis to identify noise information. This information is fused with the current time information to obtain a multi-dimensional environmental vector feature, and finally input into a preset scene classification model to obtain the category of the current driving scene, so that the system can accurately perceive the environmental conditions around the vehicle, such as whether the road is congested, whether there is construction noise around, etc.

[0012] In combination with some embodiments of the first aspect, in some embodiments, the step of predicting the type of information and the presentation method required by the current driver based on the user behavior pattern and the driving scene specifically includes: combining the current driving behavior characteristics in the user behavior pattern and the current driving scene category in the driving scene to form a current driving state feature vector; calculating the similarity between the current driving state feature vector and a driving state feature vector preset in a driver demand database based on a cosine similarity algorithm; selecting the information type and presentation method corresponding to the preset driving state feature vector with the highest similarity as the prediction result, and the information type and the presentation method are obtained by inputting the preset driving state feature vector into a preset prediction model.

[0013] By adopting the above technical solution, the current driving behavior characteristics in the user behavior pattern and the current driving scene category in the driving scene are combined to form a current driving state feature vector, and then the similarity between the vector and the driving state feature vector preset in the driver demand database is calculated according to the cosine similarity algorithm. Finally, the information type and presentation method corresponding to the preset driving state feature vector with the highest similarity are selected as the prediction result, so that the system can comprehensively consider the user's driving behavior and the current scene, and accurately predict the information type and presentation method required by the driver.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the step of presenting all in-vehicle applications according to the information presentation mode and the information presentation time, the method also includes: obtaining the physiological indicator data and operating behavior data of the current driver; calculating the degree of distraction of the current driver based on the driver's physiological indicator data and the operating behavior data; when the degree of distraction exceeds a preset degree threshold, adjusting the information presentation time so that the presentation time of the current key in-vehicle application is extended to the preset presentation time, and the current key in-vehicle application is the preset in-vehicle application presented within the current time.

[0015] By adopting the above technical solution, after obtaining the physiological indicator data and operating behavior data of the current driver, the behavior change index of the current driver is calculated according to the steering wheel change angle, lane deviation times and vehicle speed change frequency data in the operating behavior data, and then the degree of distraction is calculated in combination with the preset first weight, the behavior change index, the preset second weight and the physiological indicator data. When the degree of distraction exceeds the preset threshold, the information presentation time is adjusted to extend the presentation time of the current key in-vehicle application, which helps to ensure that the driver has enough time to obtain important information when his attention is not focused, thereby reducing potential risks caused by untimely information acquisition.

[0016] In combination with some embodiments of the first aspect, in some embodiments, the step of calculating the degree of distraction of the current driver based on the physiological indicator data and the operational behavior data specifically includes: obtaining the steering wheel change angle, the number of lane departures and the vehicle speed change frequency data based on the operational behavior data, and calculating the behavior change index of the current driver based on the steering wheel change angle, the number of lane departures and the vehicle speed change frequency data; calculating the degree of distraction based on a preset first weight, a behavior change index, a preset second weight and the physiological indicator data.

[0017] By adopting the above technical solution, the behavior change index is calculated according to the specific indicators in the operation behavior data, and the degree of distraction is calculated in combination with the preset weights and physiological indicator data. It is possible to accurately quantify the driver's attention state. By accurately evaluating the degree of distraction, the information presentation strategy can be adjusted more specifically. For example, when it is calculated that the driver's degree of distraction is high, key safety-related information can be displayed first and its presentation time can be extended to ensure that the driver can pay attention to these important information in time, thereby effectively reducing the possibility of accidents caused by inattention and improving driving safety and reliability.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after the step of presenting all in-vehicle applications according to the information presentation mode and the information presentation time, the method also includes: obtaining abnormal event information during vehicle driving, the abnormal event information including traffic accident information, road construction information and traffic congestion information; evaluating the priority of the abnormal event information according to preset evaluation rules to obtain the priority of all the abnormal event information; determining the presentation time of each abnormal event information according to the priority corresponding to the abnormal event information; and presenting the prompt information containing the abnormal event information on the in-vehicle application according to the presentation time.

[0019] By adopting the above technical solution, abnormal event information during vehicle driving is obtained, including traffic accident information, road construction information and traffic congestion information, and the priority of these abnormal event information is evaluated according to preset evaluation rules to obtain the priority of all abnormal event information. The presentation time of each abnormal event information is determined according to the priority corresponding to the abnormal event information, and the prompt information containing the abnormal event information is presented on the vehicle-mounted application according to the presentation time, so that the system can timely and accurately convey important abnormal event information to the driver.

[0020] In a second aspect, an embodiment of the present application provides an intelligent in-vehicle application adjustment system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the intelligent in-vehicle application adjustment system to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions. When the above-mentioned computer program product runs on an intelligent vehicle-mounted application adjustment system, the above-mentioned intelligent vehicle-mounted application adjustment system executes the method described in the first aspect and any possible implementation method of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium comprising instructions. When the instructions are executed on an intelligent vehicle-mounted application adjustment system, the intelligent vehicle-mounted application adjustment system executes the method described in the first aspect and any possible implementation method of the first aspect.

[0023] It can be understood that the intelligent vehicle application adjustment system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. This application obtains current real-time driving data, external environment information and location information to fully understand the driving status and surrounding conditions of the vehicle. Based on these data, the system matches the user behavior pattern in the preset behavior pattern database, determines the information presentation mode and time in the preset application database, and finally presents the in-vehicle application based on this information, so that the display of the in-vehicle application can be personalized according to the user's behavior pattern and driving scene. For example, in congested road scenes, the frequency and method of navigation prompts can be intelligently adjusted according to the driver's habits and current scenes to avoid excessive prompts that increase the driver's irritability; on familiar roads, the display of repeated information can be reduced to avoid distracting the driver's attention, thereby improving the driving experience and safety.

[0025] 2. This application first obtains historical driving data within a preset time period, performs cluster analysis on it to obtain multiple driving behavior features, and then constructs a user driving behavior model. The current real-time driving data is input into the model to obtain the current driving behavior features, and then the preset behavior pattern with the highest similarity to the feature is searched in the preset behavior pattern database as the user behavior pattern of the current vehicle, so that the system can accurately identify the user's driving habits, such as frequent lane changes, constant speed driving and other characteristics. Based on these accurately identified user behavior patterns, the driver's needs can be more accurately predicted, and information services that are more in line with the driver's habits can be provided.

[0026] 3. This application calculates the behavior change index based on specific indicators in the operating behavior data, and then calculates the degree of distraction by combining preset weights and physiological indicator data. It can accurately quantify the driver's attention state. By accurately evaluating the degree of distraction, the information presentation strategy can be adjusted more specifically. For example, when it is calculated that the driver's degree of distraction is high, key safety-related information can be displayed first and its presentation time can be extended to ensure that the driver can pay attention to these important information in a timely manner, thereby effectively reducing the possibility of accidents caused by inattention and improving driving safety and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a flow chart of a method for adjusting an intelligent vehicle application based on a driving scenario in an embodiment of the present application; Figure 2 is another flow chart of the intelligent vehicle application adjustment method based on the driving scenario in the embodiment of the present application; Figure 3 It is a schematic diagram of the structure of a physical device of the intelligent vehicle-mounted application adjustment system in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more of the listed items.

[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0030] The following is a description of the process of the method provided by this implementation. Figure 1 , which is a flow chart of the intelligent vehicle application adjustment method based on the driving scenario in an embodiment of the present application.

[0031] S101, obtaining current real-time driving data, current external environment information and current location information.

[0032] Among them, the current real-time driving data refers to the driving status information of the vehicle at the current moment, including vehicle speed, acceleration, steering wheel angle, etc. The current external environment information refers to the environmental conditions around the vehicle, such as weather, light, road conditions, etc. The current location information is used to indicate the geographic location of the vehicle, usually including latitude and longitude coordinates.

[0033] This step is usually performed continuously during the driving process of the vehicle to obtain the vehicle's status and environmental information in real time. Specifically, the system collects the vehicle's real-time driving data through the vehicle's onboard sensor network, such as speed sensors, acceleration sensors, steering wheel angle sensors, etc.; obtains external environmental information through external cameras, radars and other devices; and uses GPS modules or other positioning systems to obtain the vehicle's current location information.

[0034] In some embodiments, data acquisition and processing can be achieved in a variety of ways: Optionally, the system can set a fixed sampling frequency, such as collecting data once per second, and store the collected data in a temporary cache after preliminary processing, and filter and fuse the collected data to remove outliers and redundant information; finally, package the processed data into a standard format and prepare to transmit it to subsequent modules for use. Optionally, the system can also acquire data in an event-triggered manner, that is, when a specific event (such as sudden braking or sharp turning) is detected, the data acquisition process is immediately triggered to acquire higher frequency and more detailed data; then these high-frequency data are quickly analyzed to extract key features; finally, these feature data are fused with the conventionally collected data to form a more comprehensive data set. It is understandable that other methods can also be used to acquire and process data, such as using distributed sensor networks or cloud-based collaborative processing, which are not limited here.

[0035] S102: Identify a user behavior pattern that matches the current vehicle in a preset behavior pattern database according to the current real-time driving data.

[0036] The preset behavior pattern database refers to a pre-established database containing a variety of typical driving behavior patterns. The user behavior pattern represents the driver's driving habits and characteristics, such as aggressive, conservative, etc.

[0037] This step is usually performed after obtaining sufficient real-time driving data, with the purpose of identifying the current driver's driving style and habits. Specifically, the system first extracts features from the current real-time driving data obtained to obtain key features that can represent driving behavior, compares these features with various patterns in the preset behavior pattern database, calculates the similarity, and selects the behavior pattern with the highest similarity as the user behavior pattern of the current vehicle.

[0038] In some embodiments, the recognition and matching of behavior patterns can be achieved in a variety of ways: Optionally, the system can use machine learning algorithms, such as support vector machines (SVM) or random forests, to classify real-time driving data, use historical data to train classification models, use different driving behavior patterns as classification labels, input the current real-time driving data into the trained model, and the classification results output by the model are the matched user behavior patterns. Optionally, the system can also use fuzzy logic methods for matching, define a series of fuzzy rules to describe the characteristics of different behavior patterns; then, convert the current real-time driving data into a fuzzy set, apply fuzzy reasoning to calculate the membership of each behavior pattern, and select the behavior pattern with the highest membership as the matching result. It is understandable that other methods can also be used to achieve the recognition and matching of behavior patterns, such as using neural networks or reinforcement learning methods, which are not limited here.

[0039] S103: Identify a current driving scene of the vehicle according to the current external environment information and the current position information.

[0040] The driving scene refers to the specific driving environment and conditions of the vehicle. The current external environment information indicates the real-time environmental conditions around the vehicle, including weather, light, road type, etc. The current location information is used to indicate the geographic location of the vehicle, usually including longitude and latitude coordinates.

[0041] This step is usually performed immediately after obtaining the latest external environment information and location information, in order to accurately determine the current driving environment of the vehicle. Specifically, the system first classifies and extracts features of the current external environment information, such as identifying road types, traffic conditions, weather conditions, etc. Then, combined with the current location information, the geographic information system (GIS) database is queried to obtain more detailed geographic environment information; then, this information is integrated and analyzed to construct a multi-dimensional scene feature vector; finally, this feature vector is input into a pre-trained scene classification model to obtain the category of the current driving scene.

[0042] In some embodiments, the recognition of driving scenes can be achieved in a variety of ways: Optionally, the system can use a rule-based method for scene recognition. First, a rule base containing various driving scene features is established, such as "If the vehicle speed is greater than 100km / h and the road type is a closed road, it is determined to be a highway scene"; then, the currently acquired external environment information and location information are input into this rule base; then, the system checks each rule one by one to see if the conditions are met; finally, according to the rules that meet the conditions, the current driving scene type is determined. Optionally, the system can also use deep learning methods for scene recognition. First, a multimodal deep neural network is constructed that can process images, texts, and numerical data at the same time; then, the processed external environment information (such as road images, weather data) and location information are input into this network; then, the neural network extracts high-dimensional features through multi-layer convolution and fully connected layers; finally, the most likely driving scene category is output through the softmax layer. It can be understood that other methods can also be used to achieve driving scene recognition, such as using ensemble learning methods or semi-supervised learning algorithms, which are not limited here.

[0043] S104. Predicting the type of information and presentation method required by the current driver based on the user behavior pattern and the driving scenario, the information type is a classification of prompt information that needs to be delivered to the current driver, the presentation method is a presentation method for delivering the prompt information to the current driver, and the prompt information is delivered by an in-vehicle application.

[0044] Among them, user behavior mode refers to the driver's driving habits and characteristics. Driving scenario refers to the specific driving environment and conditions of the vehicle. Information type refers to the classification of prompt information that needs to be delivered to the driver, such as navigation information, safety warnings, vehicle condition reminders, etc. Presentation mode is used to indicate the specific method of delivering prompt information to the driver, such as voice broadcast, screen display, head-up display, etc. Prompt information refers to various information and reminders that the in-vehicle application needs to deliver to the driver.

[0045] This step is usually performed immediately after identifying the user behavior pattern and driving scenario, with the goal of providing the driver with the most appropriate information service for the current situation. Specifically, the system first fuses the user behavior pattern and driving scenario information to form a comprehensive state vector; then, this state vector is input into a pre-trained prediction model, which can predict the type of information the driver may need based on historical data and current status; then, the system determines the most appropriate way to present information based on the predicted information type, combined with the current driving scenario and user preferences; finally, the system passes the prediction results to the corresponding in-vehicle applications so that they can deliver information to the driver according to the predicted type and method.

[0046] In some embodiments, the prediction of information type and presentation mode can be achieved in a variety of ways: Optionally, the system can use a reasoning method based on a knowledge graph. First, a knowledge graph containing the relationship between user behavior, driving scenarios, information type and presentation mode is constructed; then, the current user behavior pattern and driving scenario are input into the knowledge graph as query conditions; then, the graph reasoning algorithm, such as path sorting or relationship prediction, is used to find the information type and presentation mode that are most relevant to the current situation; finally, the reasoning result is used as the prediction output. Optionally, the system can also use a reinforcement learning method for prediction. First, the entire prediction process is modeled as a Markov decision process, in which the state is a combination of user behavior and driving scenarios, and the action is to select the information type and presentation mode; then, an algorithm such as Q-learning or policy gradient is used to train an agent that can maximize long-term rewards; then, in actual use, the current state is input into the trained agent; finally, the action output by the agent is the predicted information type and presentation mode. It can be understood that other methods can also be used to predict information type and presentation mode, such as using a Bayesian network or a sequence model of an attention mechanism, which is not limited here.

[0047] S105. Determine an information presentation mode and an information presentation time in a preset application database according to the information type and the presentation method, wherein the information presentation mode is a presentation form of the in-vehicle application, and the information presentation time is a presentation time point of the in-vehicle application.

[0048] The preset application database refers to a pre-established database containing various in-vehicle application information. The information type indicates the classification of prompt information that needs to be delivered to the driver, and the information presentation mode is used to indicate the specific display form of the in-vehicle application, such as full-screen display, pop-up window prompt, background broadcast, etc. The information presentation time refers to the specific time point when the in-vehicle application is displayed, which can be immediate display, delayed display, or display triggered by specific conditions, etc.

[0049] This step is usually performed immediately after the information type and presentation method are determined, with the purpose of providing more specific guidance for the display of in-vehicle applications. Specifically, the system first searches for matching records in the preset application database based on the determined information type and presentation method. The system analyzes these matching records, considers the current driving scene, user preferences and other factors, and selects the most suitable information presentation mode. The system determines the best information presentation time based on the current driving status, information urgency, etc. The system passes the determined information presentation mode and information presentation time as parameters to the relevant in-vehicle application modules.

[0050] In some embodiments, the information presentation mode and presentation time can be determined in a variety of ways: Optionally, the system can adopt a rule-based decision tree method. First, a decision tree containing various conditions and corresponding decisions is constructed, the conditions include information type, presentation method, driving scene, etc., and the decisions include different presentation modes and times; then, the current information type, presentation method, etc. are used as inputs, and the traversal starts from the root node of the decision tree; then, according to the conditions of each node, the corresponding branch is selected until the leaf node is reached; finally, the decision corresponding to the leaf node is the determined presentation mode and time. Optionally, the system can also use a scenario-based recommendation algorithm. First, each scenario in the historical data (including information type, presentation method, driving environment, etc.) is mapped to the corresponding presentation mode and time; then, for the current scenario, its similarity with the historical scenario is calculated; then, several historical scenarios with the highest similarity are selected, and their corresponding presentation modes and times are extracted; finally, the final presentation mode and time are selected from these candidate solutions by weighted average or voting. It is understandable that other methods may be used to determine the information presentation mode and presentation time, such as using a neural network or a fuzzy logic system, which is not limited here.

[0051] S106: Present all vehicle-mounted applications according to the information presentation mode and the information presentation time.

[0052] Among them, information presentation mode refers to the specific presentation form of the in-vehicle application. Information presentation time refers to the specific time point when the in-vehicle application is presented. All in-vehicle applications refer to all applications in the vehicle that may provide information or services to the driver, including but not limited to navigation systems, music players, vehicle condition monitoring, safety warning systems, etc. Presentation refers to displaying the content of the application to the driver in a specific way.

[0053] Specifically, the system first adjusts the interface layout, interaction method, etc. of all relevant in-vehicle applications according to the determined information presentation mode; then, the system arranges the display sequence of all applications according to the determined information presentation time to ensure that important information can be presented in a timely manner while avoiding information conflicts; then, the system prioritizes all applications to ensure that the most important information can be processed and displayed first when resources are limited; finally, the system starts the corresponding application and presents information according to the set mode and time.

[0054] In some embodiments, the presentation of all vehicle-mounted applications can be achieved in a variety of ways: Optionally, the system can adopt a central controller mode. First, a central controller is established to manage the status and priority of all vehicle-mounted applications; then, according to the determined presentation mode and time, the central controller generates a detailed display plan, including the display content, location, time, etc. of each application; then, the central controller sends control instructions to each application, requiring them to prepare and display according to the plan; finally, the central controller monitors the execution of each application in real time, and makes adjustments and interventions when necessary to ensure the consistency of the overall presentation effect. Optionally, the system can also use a distributed collaboration mode. First, the presentation mode and time information are broadcast to all vehicle-mounted applications; then, each application independently determines its own display strategy based on the received information, including whether to display, how to display, etc.; then, each application communicates and coordinates through a preset protocol to resolve possible conflicts; finally, all applications are presented according to the coordinated results, and status information is continuously exchanged to adapt to possible changes. It can be understood that other methods can also be used to achieve the presentation of all vehicle-mounted applications, which are not limited here.

[0055] The following is a more detailed description of the process of the method provided by this implementation. Figure 2 , which is another flow chart of the intelligent vehicle application adjustment method based on the driving scenario in an embodiment of the present application.

[0056] S201, obtaining current real-time driving data, current external environment information and current location information.

[0057] It can be understood that this step is similar to step S101 and will not be described in detail here.

[0058] S202: Identify a user behavior pattern that matches the current vehicle in a preset behavior pattern database according to the current real-time driving data.

[0059] This step specifically includes: Get historical driving data within a preset time period.

[0060] In this step, historical driving data refers to the driving record information of the vehicle in the past period of time, including detailed data such as speed, direction, location, time, etc. The preset time period can be set by the system, such as the last 3 months or the last six months. Obtaining historical driving data within the preset time period is an important basis for building a driver user portrait. Specifically, the system needs to be connected to the data recording module on the car, which will continuously save the vehicle's driving information. The system can read all the original driving data collected within the specified time period from the memory of the module for the set time range. These data may include the vehicle's speed, direction, positioning coordinates, timestamp, and whether there are marks for sudden acceleration, sudden braking, and other events. Obtaining driving data for a sufficiently long period of time can more comprehensively reflect the driver's driving habits and behavioral characteristics.

[0061] Cluster analysis is performed on the historical driving data to obtain multiple driving behavior characteristics.

[0062] In this step, cluster analysis is performed on the read historical driving data to discover patterns and features in driver behavior, such as frequent lane changes, frequent speeding, and other behavioral features. Machine learning clustering algorithms can be used to analyze the data, such as K-means clustering, hierarchical clustering, and other algorithms. Data points with similar behavior patterns are aggregated into the same category based on relevant variables such as vehicle speed, direction change, and time distribution. Repeating the clustering process will eventually result in multiple classes, each representing a major driving behavior feature. These specific features can assess whether the driver is more stable and cautious or more aggressive. With these detailed user portrait features, the driver's personalized user behavior can be modeled more accurately.

[0063] A user driving behavior model is constructed according to the driving behavior characteristics, and the current real-time driving data is input into the user driving behavior model to obtain the current driving behavior characteristics.

[0064] In this step, after obtaining multiple behavioral features of the driver, a user-defined driving behavior model can be trained using these labeled feature data. The model can be constructed using various machine learning algorithms, such as support vector machines, neural networks, etc. After the model training is completed, when new real-time driving data of the vehicle is obtained, these real-time data can be input into the driving behavior model, and the model will output a matching score, indicating the degree of matching between the current data and a certain feature in the model. In this way, the current behavioral features of the driver can be judged and identified, the driver's behavior can be continuously evaluated and monitored, and the driver's profile can be dynamically updated.

[0065] The preset behavior pattern database is searched for a preset behavior pattern with the highest similarity to the current driving behavior feature, and the preset behavior pattern is used as the user behavior pattern of the current vehicle.

[0066] In this step, the preset behavior pattern database is searched for the preset behavior pattern with the highest similarity to the current driving behavior feature, and the preset behavior pattern is used as the user behavior pattern of the current vehicle.

[0067] The preset behavior pattern database refers to a database that stores a variety of typical driving behavior patterns. The current driving behavior characteristics are characteristics that reflect the current driver's behavior habits obtained based on cluster analysis. Similarity is an indicator used to represent the size of the difference between two patterns. The user behavior pattern represents the driving habits formed by a specific driver over a long period of time.

[0068] The purpose of this step is to find a pattern that is closest to the current driver's behavior in the preset behavior pattern database and set it as the user profile of the driver. Specifically, the system will calculate the similarity index between the current driver's behavior characteristics and each preset pattern stored in the database, and can use algorithms such as cosine similarity and correlation coefficient to calculate the distance between feature vectors. After obtaining the similarity score, the system selects a preset pattern with the highest similarity and the smallest difference with the current driver's behavior feature vector, and sets this pattern as the long-term driving behavior pattern of the current user, and stores it in the user portrait module. In this way, by matching with the standard pattern library, the personalized user portraits of different drivers can be more accurately portrayed, providing input for subsequent behavior prediction and application adjustment.

[0069] S203: Identify a current driving scene of the vehicle according to the current external environment information and the current position information.

[0070] This step specifically includes: Real-time image data and sound data within a preset distance around the current vehicle are acquired according to the current external environment information.

[0071] In this step, the current external environment information may include data such as temperature and humidity. The preset distance is the range of the vehicle surrounding that needs to be paid attention to, such as 50 meters. The image data is the picture or video around the vehicle obtained by the camera. The sound data is the sound around the vehicle collected by the microphone.

[0072] The purpose of this step is to obtain image and sound data of the vehicle's surrounding environment in order to perceive the surrounding conditions. Specifically, the system can collect image information from different directions such as the front, rear, and sides through cameras installed around the vehicle body; at the same time, it uses precise microphones inside and outside the vehicle to collect surrounding sounds; the collection range can be set to within 50 meters of the vehicle. Obtaining a large amount of real-time dynamic data about the surrounding environment is conducive to more accurate judgment of the vehicle's current driving environment.

[0073] The real-time image data is analyzed based on an image recognition algorithm to obtain road information within a preset distance around the current vehicle, and the sound data is spectrally analyzed to identify noise information within a preset distance around the current vehicle.

[0074] In this step, the image recognition algorithm can analyze the image content and extract information. Road information includes road type, lane markings, etc. Spectral analysis can identify different noises from sound signals. Noise information is the type of sound present in the surrounding area.

[0075] The purpose of this step is to extract feature information useful for environmental judgment from the collected image and sound data. Specifically, computer vision algorithms can be used to analyze images to identify road information such as road type, lane lines, and traffic signs; audio analysis can be performed on the recorded sound data to determine whether it is urban traffic noise or construction noise through spectral characteristics. Obtaining road information and noise information helps to restore the specific environment around the vehicle.

[0076] The road information, the noise information and the current time information are fused to obtain a multi-dimensional environment vector feature.

[0077] In this step, the time information reflects the current time point, such as the morning rush hour or the evening rush hour. The multi-dimensional environment vector feature is a feature vector describing the environment obtained by integrating the above information.

[0078] The purpose of this step is to construct a feature vector that contains multiple aspects of the environment. Specifically, the analyzed road type, noise type, and current time point can be uniformly encoded and constructed into a vector that fully reflects the environmental conditions around the vehicle.

[0079] The multi-dimensional environmental vector feature is input into a preset scene classification model to obtain the category of the current driving scene.

[0080] In this step, the multi-dimensional environment vector feature is a feature vector that reflects the vehicle's surrounding environment by combining road information, noise information, and time information. The preset scene classification model is a pre-trained model in the system that can classify the driving environment. The driving scene category is the type of the current environment output by the model, such as a busy commercial area, a suburban road, etc.

[0081] The purpose of this step is to determine the type of driving scene the vehicle is currently in through an intelligent model. Specifically, the system pre-collects sample data labeled with different driving scenes, and uses a machine learning algorithm to train a scene classification model, which can input an environmental feature vector and output a scene category. At runtime, the system obtains the multi-dimensional vector features representing the current environment and inputs them into the pre-trained scene classification model. The model can calculate the matching probability of the input vector with the known scene category, and output one or several possible current scene categories, such as "urban area", "highway", etc.

[0082] S204. Predicting the type of information and presentation method required by the current driver based on the user behavior pattern and the driving scenario, the information type is a classification of prompt information that needs to be delivered to the current driver, the presentation method is a presentation method for delivering the prompt information to the current driver, and the prompt information is delivered by an in-vehicle application.

[0083] This step specifically includes: The current driving behavior feature in the user behavior pattern and the current driving scene category in the driving scene are combined to form a current driving state feature vector.

[0084] In this step, the user behavior pattern contains the driver's personalized driving characteristics. The driving scene category is the identified scene type. Combining the two into a vector can represent the current driving state. The purpose of this step is to construct a driving state vector that combines user characteristics and scene information. Specifically, the system encodes the identified user driving behavior characteristics (such as active, stable, etc.) and scene categories (such as suburbs, urban areas) into a vector that comprehensively represents the current user's driving state.

[0085] The similarity between the current driving state feature vector and a driving state feature vector preset in the driver demand database is calculated according to the cosine similarity algorithm.

[0086] In this step, the driver demand database contains a large number of demand sample feature vectors under different driving states. The cosine similarity algorithm can calculate the angle difference between two vectors. The higher the similarity, the greater the similarity. The purpose of this step is to calculate the similarity between the current driving state vector and the standard state sample. Specifically, the system compares the currently constructed driving state vector with the standard state sample vector in the database and calculates the cosine similarity between the two. Samples with high similarity indicate that the current state is close to the standard sample state, that is, the driver demand is also close to the corresponding standard demand.

[0087] The information type and presentation method corresponding to the preset driving state feature vector with the highest similarity are selected as the prediction result, and the information type and the presentation method are obtained by inputting the preset driving state feature vector into a preset prediction model.

[0088] In this step, the driver demand database contains a large number of demand sample feature vectors under different driving states. The cosine similarity algorithm can calculate the angle difference between two vectors. The higher the similarity, the greater the similarity. The purpose of this step is to calculate the similarity between the current driving state vector and the standard state sample. Specifically, the system compares the currently constructed driving state vector with the standard state sample vector in the database and calculates the cosine similarity between the two. Samples with high similarity indicate that the current state is close to the standard sample state, that is, the driver demand is also close to the corresponding standard demand.

[0089] S205. Determine an information presentation mode and an information presentation time in a preset application database according to the information type and the presentation method, wherein the information presentation mode is a presentation form of the in-vehicle application, and the information presentation time is a presentation time point of the in-vehicle application.

[0090] It can be understood that this step is similar to step S105 and will not be described in detail here.

[0091] S206: Present all vehicle-mounted applications according to the information presentation mode and the information presentation time.

[0092] It can be understood that this step is similar to step S106 and will not be described in detail here.

[0093] S207: Acquire the physiological index data and operation behavior data of the current driver.

[0094] Physiological index data refers to various parameters that can reflect the driver's physiological state, such as heart rate, blood pressure, skin galvanic response and other physiological signals. Operational behavior data refers to various behavioral data generated by the driver during the driving operation, such as the force and angle of stepping on the accelerator, turning the steering wheel, the number of brakes, etc. The purpose of obtaining these two types of data is to provide information support for a comprehensive assessment of the driver's attention state. Specifically, the system can collect the driver's heart rate, blood pressure, skin galvanic response and other physiological parameters through pressure, displacement, contact and other sensors installed in multiple locations such as the steering wheel, seat, seat belt, etc. These parameters can reflect the driver's excitement, tension, fatigue and other physiological states; at the same time, various sensors on the car can detect parameters such as vehicle speed, throttle opening, brake pedal force, steering wheel angle and speed.

[0095] S208, acquiring steering wheel change angle, lane deviation number and vehicle speed change frequency data according to the operation behavior data, and calculating the current driver's behavior change index according to the steering wheel change angle, the lane deviation number and the vehicle speed change frequency data; The steering wheel change angle refers to the total angle of the steering wheel rotation per unit time. The number of lane departures refers to the total number of times the vehicle deviates from or exceeds the current lane line per unit time. The speed change frequency refers to the total frequency of significant changes in the vehicle speed per unit time. These three parameters can more intuitively reflect the changes in the driver's operating behavior. The behavior change index is a comprehensive evaluation index. By counting and weighting the values ​​of these three parameters, it can be judged whether the driver's driving behavior tends to be stable or whether there are frequent abnormal operations. Specifically, the system can preset a time period, such as 10 seconds, to detect and accumulate the steering wheel rotation angle, lane departure times, and speed fluctuation frequency during this period in real time, and then perform weighted calculations on the three according to the set calculation formula or model to obtain a quantitative parameter of the behavior change index. The larger the index value, the more frequent the driver's operation changes and the more unstable the behavior, which usually means that the attention is more distracted. Conversely, a small index value indicates that the driving behavior is stable and the attention is more focused.

[0096] S209: Calculate the degree of distraction according to the preset first weight, the behavior change index, the preset second weight and the physiological indicator data.

[0097] The degree of distraction is an indicator for evaluating whether the driver is concentrating or not, and a numerical result can be obtained by calculation. The behavior change index has been obtained in the previous step. Physiological index data such as skin galvanic response and heart rate variability can also reflect the state of attention. The first weight and the second weight are two weight coefficients preset by the system, which are used to balance the contribution of the behavioral index and the physiological index to the degree of distraction. The specific calculation method can adopt the principle of weighted average: degree of distraction = (first weight of behavioral change index + second weight of physiological index) / (first weight + second weight). The setting of the weight coefficient needs to be pre-defined in combination with the actual situation. For example, the behavioral index weight can be set larger. The larger the value of the degree of distraction obtained in the end, the less focused the driver is and the more likely it is to make driving errors.

[0098] S210. When the degree of distraction exceeds a preset threshold, the information presentation time is adjusted so that the presentation time of the current key in-vehicle application is extended to the preset presentation time. The current key in-vehicle application is the preset in-vehicle application presented within the current time.

[0099] The distraction level is an indicator to evaluate the driver's concentration. The larger the value, the more distracted the driver is. The preset level threshold is a critical value pre-set in the system to determine whether the distraction level is too high. The information presentation time is the length of time that the in-vehicle application displays information to the driver. Key in-vehicle applications are important applications that have a greater impact on driving safety.

[0100] The purpose of this step is to automatically extend the information presentation time of key safety applications when the system detects that the driver's attention is too distracted, ensuring that the driver can fully obtain this important information. Specifically, the system will detect and calculate the driver's degree of distraction in real time and compare it with the preset threshold. When the degree of distraction is higher than the threshold, it indicates that the driver's attention is not focused enough. At this time, the system will automatically lock the key applications displayed in the current time period, such as blind spot detection applications, front collision warning applications, etc., and extend the information presentation time of these applications to ensure that it exceeds a preset standard time length, such as extending to 5 seconds.

[0101] S211. Acquire abnormal event information during vehicle driving, where the abnormal event information includes traffic accident information, road construction information, and traffic congestion information.

[0102] Abnormal event information refers to unusual events encountered during vehicle driving, which may affect vehicle traffic. Specific information may include: traffic accidents on the road ahead, road construction leading to partial road closures, and congestion on distant roads causing slow traffic.

[0103] The purpose of this step is to allow the system to obtain timely information on various abnormal events that may affect the passage of vehicles. Specifically, the system can connect with the intelligent traffic management system to obtain information on traffic accidents, road construction and other blockages; connect with the navigation system to obtain real-time road conditions; and can also actively monitor abnormal conditions ahead through on-board cameras and sensors. By integrating the abnormal event information obtained from various channels, the system can fully grasp various abnormal conditions that may occur around the vehicle and accurately obtain abnormal event information.

[0104] S212: Evaluate the priority of the abnormal event information according to a preset evaluation rule to obtain the priority of all the abnormal event information.

[0105] The preset evaluation rules are a series of standards and judgment rules for the priority evaluation of abnormal event information pre-set in the system. Priority is a ranking level of the relative importance of a certain abnormal event information.

[0106] The purpose of this step is to enable the system to intelligently determine the severity and priority of abnormal event information. Specifically, the system will evaluate and determine the acquired event information based on various preset rules. These rules may include the impact of the event on the route, the distance from the vehicle's current location, the duration of the event, etc. The system will comprehensively judge these factors and sort all event information according to priority, so that more serious and more urgent events will be given higher priority, thereby guiding subsequent response operations.

[0107] S213: Determine the presentation time of each abnormal event information according to the priority corresponding to the abnormal event information.

[0108] The priority of abnormal event information is a ranking of the relative importance of a certain abnormal event information. The presentation time is the duration of displaying the abnormal event information to the driver.

[0109] The purpose of this step is to reasonably determine the presentation time of each event information based on the priority of the abnormal event information obtained in the previous evaluation. Specifically, the system will give different presentation time lengths according to the priority of the event. The event information with the highest priority and the greatest impact will be presented longer to ensure that the driver can fully obtain this key information. The presentation time of event information with a slightly lower priority is relatively shorter.

[0110] S214: Present prompt information including the abnormal event information on the in-vehicle application according to the presentation time.

[0111] The presentation time is the length of time that the prompt information is displayed for each abnormal event information. The prompt information is a text, image or voice prompt containing abnormal event information. The in-vehicle application is an application that realizes the information presentation function.

[0112] The purpose of this step is to display the abnormal event information in the form of prompt information according to a predetermined time length. Specifically, the system will load prompt information in the form of text, voice, video, etc., which contains specific abnormal event information, onto the corresponding vehicle application interface. Then, the system can control the display time length of these prompt information and display them according to the presentation time requirements previously determined for each event information.

[0113] The following describes the intelligent vehicle application adjustment system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of a physical device structure of an intelligent vehicle-mounted application adjustment system in an embodiment of the present application.

[0114] It should be noted that Figure 3 The structure of the intelligent vehicle-mounted application adjustment system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0115] like Figure 3 As shown, the intelligent vehicle application adjustment system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0116] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0117] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0118] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0119] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0120] Specifically, the intelligent vehicle-mounted application adjustment system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the intelligent vehicle-mounted application adjustment method based on the driving scenario provided in the above embodiment is implemented.

[0121] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the intelligent vehicle-mounted application adjustment system described in the above embodiment; or may exist independently without being assembled into the intelligent vehicle-mounted application adjustment system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the intelligent vehicle-mounted application adjustment system, the intelligent vehicle-mounted application adjustment system implements the intelligent vehicle-mounted application adjustment method based on driving scenarios provided in the above embodiment.

[0122] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0123] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0124] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A method for adjusting intelligent vehicle applications based on driving scenarios, characterized in that: Applied to an intelligent vehicle-mounted application adjustment system, the method comprises: Obtain current real-time driving data, current external environment information and current location information; Identify a user behavior pattern that matches the current vehicle in a preset behavior pattern database according to the current real-time driving data; Identifying a current driving scene of the vehicle according to the current external environment information and the current position information; Predicting the type of information and the presentation method required by the current driver according to the user behavior pattern and the driving scenario, wherein the type of information is the classification of prompt information that needs to be delivered to the current driver, and the presentation method is the presentation method of delivering the prompt information to the current driver, and the prompt information is delivered by the in-vehicle application; Determining an information presentation mode and an information presentation time in a preset application database according to the information type and the presentation method, wherein the information presentation mode is a presentation form of the in-vehicle application, and the information presentation time is a presentation time point of the in-vehicle application; All vehicle-mounted applications are presented according to the information presentation mode and the information presentation time.

2. The method according to claim 1, characterized in that The step of identifying a user behavior pattern matching the current vehicle in a preset behavior pattern database according to the current real-time driving data specifically includes: Obtain historical driving data within a preset time period; Performing cluster analysis on the historical driving data to obtain multiple driving behavior features; Constructing a user driving behavior model according to the driving behavior characteristics, and inputting the current real-time driving data into the user driving behavior model to obtain current driving behavior characteristics; The preset behavior pattern database is searched for a preset behavior pattern with the highest similarity to the current driving behavior feature, and the preset behavior pattern is used as the user behavior pattern of the current vehicle.

3. The method according to claim 1, characterized in that: The step of identifying the current driving scene of the vehicle according to the current external environment information and the current position information specifically includes: Acquire real-time image data and sound data within a preset distance around the current vehicle according to the current external environment information; Analyzing the real-time image data based on an image recognition algorithm to obtain road information within a preset distance around the current vehicle, and performing spectrum analysis on the sound data to identify noise information within a preset distance around the current vehicle; Fusing the road information, the noise information and the current time information to obtain a multi-dimensional environment vector feature; The multi-dimensional environment vector feature is input into a preset scene classification model to obtain the category of the current driving scene.

4. The method according to claim 1, characterized in that: The step of predicting the type of information and presentation method required by the current driver based on the user behavior pattern and the driving scenario specifically includes: Combining the current driving behavior feature in the user behavior pattern with the current driving scene category in the driving scene to form a current driving state feature vector; Calculating the similarity between the current driving state feature vector and a driving state feature vector preset in a driver demand database according to a cosine similarity algorithm; The information type and presentation method corresponding to the preset driving state feature vector with the highest similarity are selected as the prediction result, and the information type and the presentation method are obtained by inputting the preset driving state feature vector into a preset prediction model.

5. The method according to claim 1, characterized in that After the step of presenting all vehicle-mounted applications according to the information presentation mode and the information presentation time, the method further includes: Acquiring physiological index data and operation behavior data of the current driver; Calculating the current driver's attention distraction degree according to the driver's physiological index data and the operating behavior data; When the degree of distraction exceeds a preset threshold, the information presentation time is adjusted so that the presentation time of the current key in-vehicle application is extended to the preset presentation time. The current key in-vehicle application is a preset in-vehicle application presented in the current time.

6. The method according to claim 5, characterized in that The step of calculating the current driver's degree of distraction based on the physiological index data and the operating behavior data specifically includes: Acquire the steering wheel change angle, lane deviation number and vehicle speed change frequency data according to the operation behavior data, and calculate the behavior change index of the current driver according to the steering wheel change angle, lane deviation number and vehicle speed change frequency data; The degree of distraction is calculated according to the preset first weight, the behavior change index, the preset second weight and the physiological indicator data.

7. The method according to claim 6, characterized in that After the step of presenting all vehicle-mounted applications according to the information presentation mode and the information presentation time, the method further includes: Acquire abnormal event information during vehicle driving, wherein the abnormal event information includes traffic accident information, road construction information and traffic congestion information; Evaluate the priority of the abnormal event information according to a preset evaluation rule to obtain the priority of all the abnormal event information; Determine the presentation time of each abnormal event information according to the priority corresponding to the abnormal event information; The prompt information including the abnormal event information is presented on the in-vehicle application according to the presentation time.

8. An intelligent vehicle application adjustment system, characterized in that: The intelligent in-vehicle application adjustment system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the intelligent in-vehicle application adjustment system to execute the method described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on the intelligent vehicle application adjustment system, the intelligent vehicle application adjustment system executes the method as claimed in any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product runs on an intelligent vehicle-mounted application adjustment system, the intelligent vehicle-mounted application adjustment system is enabled to execute the method according to any one of claims 1 to 7.

Images