Automobile Product Interaction Design System Based on Multidimensional User Experience Data Analysis

Abstract

The present invention provides an automotive product interaction design system based on multi-dimensional user experience data analysis, which relates to the field of automotive engineering technology. It includes a master control system, and the master control system contains a data collection and preprocessing module, a user behavior analysis module, a user portrait generation module, an interaction design optimization module, a real-time feedback and adjustment module, and a visualization and interaction feedback module. Through the comprehensive analysis of multi-dimensional user experience data, the present invention can identify users' preferences and needs in real time and dynamically adjust the interaction interface. This personalized design not only improves users' driving comfort, but also enhances users' sense of belonging and satisfaction with the vehicle. In addition, the intelligent function of the system can learn users' behavior patterns and continuously optimize the interaction experience to ensure that every driving is tailor-made.

Description

Technical Field

[0001] The present invention relates to the technical field of automotive engineering, and specifically to an automotive product interaction design system based on multi-dimensional user experience data analysis. Background Art

[0002] In today's automotive industry, user experience has become one of the core elements in design and manufacturing. With the rapid development of intelligence and digitalization, many automotive manufacturers have started to use advanced technical means to enhance the user interaction experience. Among them, user interaction design systems based on data analysis have gradually become a hot topic in the industry. These systems usually rely on big data, artificial intelligence, and machine learning technologies, and provide personalized functions and services by analyzing users' behaviors, preferences, and feedback. For example, intelligent voice assistants equipped in some high-end cars can understand natural language and perform multiple operations according to the driver's instructions, thus improving driving convenience and safety.

[0003] However, there are still many problems in the application of existing technologies:

[0004] 1. Most existing user interaction systems can only perform simple pattern recognition and cannot deeply understand users' complex behaviors and emotional states. Many systems have a slow processing speed for user feedback, resulting in a delay for users during operation and affecting the overall experience.

[0005] 2. Users' expectations for the interaction experience are constantly increasing, and traditional design methods are difficult to meet the personalized and diverse needs. Many existing systems do not fully consider the driving experience of users in different environments, resulting in users not being able to obtain ideal support in specific situations. For example, a driver may need stronger visual support when driving at night, and more flexible navigation prompts in a congested urban environment.

[0006] Therefore, there is an urgent need for an innovative automotive product interaction design system that can integrate multi-dimensional user experience data for in-depth analysis and real-time response. Summary of the Invention

[0007] Technical Problems to be Solved

[0008] In view of the deficiencies of the existing technology, the present invention provides an automotive product interaction design system based on multi-dimensional user experience data analysis, which solves the following problems:

[0009] 1. Solves the problem that although many systems can collect and process a large amount of data, they are still insufficient in real-time analysis and response to user needs.

[0010] 2. Solves the problem that many systems have a slow processing speed for user feedback, resulting in a delay for users during operation and affecting the overall experience.

[0011] 3. It solves the problem that as users' expectations for interactive experience continue to rise, traditional design methods are difficult to meet the personalized and diverse needs. Many existing systems do not fully consider the driving experience of users in different environments, resulting in users not being able to obtain ideal support in specific situations.

[0012] Technical solutions

[0013] To achieve the above objectives, the present invention is realized through the following technical solutions: An automotive product interaction design system based on multi-dimensional user experience data analysis, including a master control system, which contains a data collection and preprocessing module, a user behavior analysis module, a user portrait generation module, an interaction design optimization module, a real-time feedback and adjustment module, and a visualization and interaction feedback module;

[0014] Sp1. The data collection and preprocessing module cleans and preprocesses user data through rule-based data cleaning, anomaly detection algorithms, and data normalization techniques, and extracts user features through principal component analysis, independent component analysis, and feature selection techniques to provide high-quality data for subsequent analysis;

[0015] Sp2. The user behavior analysis module uses K-means clustering, DBSCAN, and hierarchical clustering algorithms to perform clustering analysis on user behaviors, and combines Markov chains, hidden Markov models, and sequence pattern mining techniques to deeply explore the behavior patterns of users in different situations, thereby identifying user needs;

[0016] Sp3. The user portrait generation module uses decision trees, support vector machines, and random forest classification algorithms to generate user portraits, and combines graph embedding algorithms such as Node2Vec, GraphSAGE, and relational network embedding to provide comprehensive personalized portraits for users;

[0017] Sp4. The interaction design optimization module realizes the optimization of interaction design through collaborative filtering, content recommendation, and model-based recommendation algorithms, and at the same time applies genetic algorithms, particle swarm optimization, and constraint optimization techniques to improve the user experience on the basis of meeting multi-objective requirements;

[0018] Sp5. The real-time feedback and adjustment module uses Q-learning, deep Q-network, and policy gradient method reinforcement learning algorithms to dynamically adjust the system response according to the real-time data of users, and combines ARIMA, LSTM, and Prophet time series prediction algorithms to identify changes in user needs in advance;

[0019] Sp6. The visualization and interaction feedback module uses data visualization technologies such as data aggregation, heat map analysis, and dynamic interactive chart generation to intuitively display user behavior and feedback. Combining sentiment analysis based on dictionaries, machine learning classifiers, and deep learning models, it provides real-time sentiment analysis of user feedback.

[0020] Sp7. Data interaction between the data collection and preprocessing module, user behavior analysis module, user profile generation module, interaction design optimization module, real-time feedback and adjustment module, and visualization and interaction feedback module is carried out through standardized interfaces. The master control system stores and processes data through the cloud platform, supporting the analysis and real-time response of large-scale user data.

[0021] Preferably, the data collection and preprocessing module realizes real-time reception and processing of data through multiple data sources to enhance the comprehensiveness and effectiveness of data. The data collection and preprocessing module obtains vehicle operation data in real time through in-vehicle sensors, where the operation data includes vehicle speed, acceleration, and steering angle. In application, the driving style (aggressive or smooth) of the user is inferred through the data change of the acceleration sensor, providing a reference for subsequent interaction design. For users with an aggressive driving style, the interaction prompt for vehicle power response is optimized.

[0022] Preferably, the user behavior analysis module uses a variety of clustering and sequence analysis algorithms to form an in-depth understanding of user behavior patterns and reveal potential changes in user needs. The K-means clustering algorithm in the user behavior analysis module groups users based on driving operation habits, that is, the frequency and amplitude of acceleration and braking.

[0023] Preferably, the user profile generation module uses a dynamic update mechanism to ensure that the user profile continuously reflects the user's personalized characteristics and preferences by dynamically updating the user profile. The user profile generation module monitors the user's online behavior in real time. When the user searches for a new destination using the in-vehicle navigation system during driving, the system immediately records this behavior and updates the user's interest preference tags according to the type of destination. Nearby outdoor sports equipment stores or relevant activity information are recommended on the home page of the in-vehicle display, and at the same time, convenient routes to outdoor places are preferentially displayed in the navigation system.

[0024] Preferably, the interaction design optimization module uses an intelligent integration mechanism to integrate user feedback and make intelligent adjustments to interaction elements to improve the quality of the user experience. The interaction design optimization module not only considers the user's direct evaluation of the existing interaction functions of the vehicle but also analyzes the text descriptions of the vehicle usage experience on channels such as social media and online forums through natural language processing technology.

[0025] Preferably, the real-time feedback and adjustment module integrates an anomaly detection mechanism to identify abnormal patterns of user behavior and generate corresponding feedback information. The anomaly detection mechanism in the real-time feedback and adjustment module adopts a method based on a statistical model. For the driving behavior data of users, a statistical distribution model of normal driving behavior is established, including the mean and standard deviation of vehicle speed, and the frequency distribution of the steering wheel rotation angle. At the same time, machine learning algorithms are combined for anomaly detection.

[0026] Preferably, the visualization and interactive feedback module supports diverse data visualization forms. The visualization and interactive feedback module supports interactive dashboard visualization and adopts map visualization technology. Combining with the in-vehicle navigation system, it displays the user's driving trajectory, frequently visited locations, and surrounding point-of-interest information in the form of a map.

[0027] Preferably, the master control system combines machine learning algorithms to optimize the data processing and analysis process. It uses an image recognition algorithm based on deep learning to analyze the image data captured by the in-vehicle camera, and automatically identifies different driving scenarios and traffic conditions on urban roads, highways, and rural roads.

[0028] Preferably, the master control system has flexible expansion capabilities and can quickly integrate new data sources and analysis functions according to new requirements. The master control system adopts a microservices architecture and splits the data collection and preprocessing module, user behavior analysis module, user portrait generation module, interaction design optimization module, real-time feedback and adjustment module, and visualization and interactive feedback module into independent microservices.

[0029] Preferably, data interaction between the data collection and preprocessing module, user behavior analysis module, user portrait generation module, interaction design optimization module, real-time feedback and adjustment module, and visualization and interactive feedback module is carried out through standardized interfaces, and a Web service interface based on the RESTful architecture is adopted.

[0030] Beneficial effects

[0031] The present invention provides an automotive product interaction design system based on multi-dimensional user experience data analysis, having the following beneficial effects:

[0032] 1. Through the comprehensive analysis of multi-dimensional user experience data, the present invention can identify the preferences and needs of users in real time and dynamically adjust the interaction interface. This personalized design not only improves the driving comfort of users, but also enhances the sense of belonging and satisfaction of users with the vehicle. In addition, the intelligent functions of the system can learn the behavior patterns of users and continuously optimize the interaction experience to ensure that every driving is customized.

[0033] 2. Through the real-time feedback and adjustment module, the system can issue an alarm in a timely manner when the user's behavior is abnormal, effectively improving driving safety. This early warning mechanism not only focuses on the user's operation behavior but also combines environmental changes for intelligent decision-making to ensure a high level of safety throughout the driving process. In addition, the system's instant feedback function can quickly respond to user needs, providing timely guidance and assistance to users and enhancing overall driving safety.

[0034] 3. Through the integrated user profile generation and interaction design optimization module, the invention can systematically analyze user feedback and promote the continuous improvement of product design. By analyzing historical data, the system can not only identify potential design defects but also predict future changes in user needs, thus providing data support for automobile manufacturers to help them continuously optimize product design and functions in a highly competitive market. This data-driven approach enables automotive products to quickly adapt to market changes, improving the enterprise's innovation ability and market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 is the processing flow chart of the overall control system of the present invention;

[0036] Figure 2 is the hardware composition diagram of the overall control system of the present invention;

[0037] Figure 3 is the bar chart of user experience simulation analysis of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention. Specific Embodiment 1:

[0040] As Figures 1-3 shown, an automotive product interaction design system based on multi-dimensional user experience data analysis includes an overall control system, which contains a data collection and preprocessing module, a user behavior analysis module, a user profile generation module, an interaction design optimization module, a real-time feedback and adjustment module, and a visualization and interaction feedback module;

[0041] Sp1. The data collection and preprocessing module cleans and preprocesses user data through rule-based data cleaning, anomaly detection algorithms, and data normalization techniques, and extracts user features through principal component analysis, independent component analysis, and feature selection techniques to provide high-quality data for subsequent analysis;

[0042] Sp2. The user behavior analysis module uses K-means clustering, DBSCAN, and hierarchical clustering algorithms to perform clustering analysis on user behaviors. Combining Markov chains, hidden Markov models, and sequence pattern mining techniques, it deeply mines the behavior patterns of users in different scenarios to identify user needs.

[0043] Sp3. The user profile generation module uses decision trees, support vector machines, and random forest classification algorithms to generate user profiles. Combining graph embedding algorithms such as Node2Vec, GraphSAGE, and relational network embedding, it provides comprehensive personalized profiles for users.

[0044] Sp4. The interaction design optimization module realizes the optimization of interaction design through collaborative filtering, content recommendation, and model-based recommendation algorithms. At the same time, applying genetic algorithms, particle swarm optimization, and constraint optimization techniques, it improves the user experience on the basis of meeting multi-objective requirements.

[0045] Sp5. The real-time feedback and adjustment module uses Q-learning, deep Q-networks, and policy gradient method reinforcement learning algorithms to dynamically adjust the system response according to the real-time data of users. Combining ARIMA, LSTM, and Prophet time series prediction algorithms, it identifies changes in user needs in advance.

[0046] Sp6. The visualization and interaction feedback module uses data aggregation, heat map analysis, and dynamic interactive chart generation data visualization techniques to intuitively display user behaviors and feedback. Combining dictionary-based sentiment analysis, machine learning classifiers, and deep learning models, it provides real-time sentiment analysis of user feedback.

[0047] Sp7. Data is exchanged between the data collection and preprocessing module, user behavior analysis module, user profile generation module, interaction design optimization module, real-time feedback and adjustment module, and visualization and interaction feedback module through standardized interfaces. The total control system stores and processes data through the cloud platform, supporting the analysis and real-time response of large-scale user data.

[0048] The data collection and preprocessing module realizes real-time data reception and processing through multiple data sources to enhance the comprehensiveness and effectiveness of the data. The data collection and preprocessing module obtains vehicle operation data in real time through on-board sensors, where the operation data includes vehicle speed, acceleration and steering angle. When applied, the user's driving style (aggressive or smooth) is inferred through the data changes of the acceleration sensor, providing a reference for subsequent interactive design. For users with aggressive driving styles, the interactive prompts of the vehicle's dynamic response are optimized, and on-board infotainment data is integrated, including the user's frequency of use of music and navigation functions, operating habits and preference settings. At the same time, the vehicle is equipped with a telematics unit to receive vehicle remote diagnostic data and data on the user's interaction with the vehicle through mobile phone applications.

[0049] At the same time, data caching technology is used. During the peak period of data reception, data is first temporarily stored in the cache and then processed according to priority. For critical safety-related data (such as brake system fault signals), they are processed and analyzed immediately to ensure vehicle safety. For general data (such as temperature change records in the car), they can be processed when system resources are idle to improve data processing efficiency and the overall response performance of the system. Data fusion algorithms are used to integrate data from different sensors and data sources. For example, data such as vehicle speed, engine speed, and accelerator pedal opening are fused to calculate the real-time power and torque of the vehicle, so as to have a more comprehensive understanding of the vehicle's operating status and the user's driving needs.

[0050] The user behavior analysis module uses a variety of clustering and sequence analysis algorithms to form an in-depth understanding of user behavior patterns and reveal potential changes in user needs. The K-means clustering algorithm in the user behavior analysis module groups users based on their driving operation habits, that is, the frequency and amplitude of acceleration and braking. Users who frequently accelerate and brake suddenly are classified into one category, and their behavioral characteristics are analyzed. The DBSCAN (density clustering algorithm) is used to cluster behavior patterns under different road conditions and different time periods. At the same time, a hierarchical model of user behavior is constructed through a hierarchical clustering algorithm. The evolution of user behavior is analyzed from macro to micro. When applied, users are first divided into three categories according to their overall driving style: aggressive, robust and conservative. Then, each major category is further subdivided according to the frequency of turn signal use and parking habits.

[0051] Among them, based on the analysis of the sequence and transition probability of user operation behaviors, the Markov chain combines the emotional state data of users (such as recognizing emotions by analyzing the facial expressions or intonation of users through in-vehicle cameras) for comprehensive analysis. For example, if it is found that the transition probability of operation behaviors changes under the emotions of fatigue or anxiety, such as frequently switching music or frequently adjusting the air conditioner temperature, the system can intelligently adjust the in-vehicle environment settings, such as playing soothing music, automatically adjusting the air conditioner temperature and wind speed to a suitable comfortable state, and at the same time providing warm voice prompts to remind users to pay attention to rest or adjust the driving state, so as to improve the safety and comfort of driving.

[0052] The user portrait generation module adopts a dynamic update mechanism to ensure that the user portrait continuously reflects the personalized characteristics and preferences of users by dynamically updating the user portrait. The user portrait generation module monitors the online behaviors of users in real time. When the user searches for a new destination using the in-vehicle navigation system during driving, the system immediately records this behavior and updates the user's interest preference tags according to the type of destination. It recommends nearby outdoor sports equipment stores or relevant activity information on the home page of the in-vehicle display screen, and at the same time preferentially displays the convenient routes to outdoor places in the navigation system and provides detailed prompts for relevant information such as surrounding parking lots and rest areas. By monitoring the long-term change trends of data such as the user's average vehicle speed, acceleration distribution, and braking frequency for habit analysis, the user portrait generation module uses decision tree algorithms to construct a user classification decision tree based on the user's age, gender, occupation, driving behavior data, and the characteristics of vehicle usage scenarios. Support vector machine algorithms are used to analyze the user's preferences for vehicle appearance and interior styles, collect data on the user's choices and evaluations of vehicle colors, seat materials, and dashboard styles, as well as the user's likes and comments on vehicle exterior designs on social media. Through random forest classification algorithms, comprehensively considering the user's consumption behaviors and vehicle usage habits, the consumption potential and loyalty of users are evaluated and classified. Analyze the user's vehicle maintenance frequency, whether they have purchased original factory parts or value-added services, and their participation in vehicle brand activities. For users with high consumption potential and high loyalty, they are marked as "high-quality customers" in the user portrait. For this part of users, the system provides exclusive after-sales service discounts. In the user portrait generation module, graph embedding algorithms such as Node2Vec, GraphSAGE, and relational network embedding are combined to mine the social relationships and interest associations between users.

[0053] For example, for users aged between 30 and 40, with the occupation of office workers and often driving during the morning and evening rush hours on weekdays, the decision tree may classify them as "urban commuting users". For this user group, in the user profile, details are recorded about their high attention to traffic information, certain requirements for vehicle comfort, and the need to conveniently answer calls and process work-related information during driving. Based on these profile features, the system optimizes the real-time traffic condition reporting function in the in-vehicle infotainment system to make it more accurate and timely; adjusts the automatic adjustment modes of the seats and air conditioners to provide a more comfortable driving environment; and integrates an intelligent voice assistant to support users in answering calls, sending text messages, and querying work-related information through voice commands, improving the convenience and safety during driving.

[0054] Support vector machines can build user aesthetic preference models. For example, if it is found that users have a higher preference tendency for simple and modern interior designs and bright and vivid body colors, it is marked as "modern minimalist aesthetic preference" in the user profile. When vehicle manufacturers launch new interior upgrade kits or special body color options, the system can, based on the user profile, targetedly push relevant information to these users and preferentially display options that match their aesthetic preferences in the virtual showroom or vehicle configuration interface, improving users' satisfaction and participation in vehicle personalization customization.

[0055] When mining the social relationships and interest associations among users, for example, if it is found that multiple users often travel together (through vehicle Bluetooth connection records or analysis of common travel destinations), and they have certain similarities in their preferences for vehicle functions, the system can construct a user social network graph and use graph embedding algorithms to integrate the relationships and common interest features of these users into the user profile. Based on this social relationship and interest association, the system can launch social interaction functions, such as allowing users to share travel plans, route recommendations, and driving experiences in the in-vehicle system; at the same time, according to the common interests of the user group, recommend relevant peripheral activities or preferential information of cooperative merchants to them. For example, for user groups who like outdoor sports, recommend discount information on tickets for nearby outdoor sports events or related equipment, further enriching users' driving experiences and life services, and enhancing users' perception of the use value and satisfaction of the vehicle interaction system.

[0056] The interaction design optimization module adopts an intelligent integration mechanism to integrate user feedback and make intelligent adjustments to interaction elements to improve the quality of the user experience. The interaction design optimization module not only considers users' direct evaluations of the existing vehicle interaction functions but also analyzes text descriptions of users' vehicle usage experiences on channels such as social media and online forums through natural language processing technology.

[0057] For example, using sentiment analysis algorithms, dissatisfaction with the smooth operation of the vehicle's central control screen and specific improvement suggestions are extracted from the user's comments, such as "I hope the response speed of the central control screen can be faster, and there should be no lag when switching menus." The system classifies and quantifies this feedback information, converting it into specific interactive design optimization metrics, such as setting the goal of shortening the operation response time of the central control screen and the requirement of increasing the menu switching frame rate. Then, the screen display driver and the animation effects of the interactive interface are optimized accordingly to improve the interactive smoothness of the central control screen and meet the user's expectations.

[0058] For the intelligent adjustment of interactive elements, the module makes personalized settings based on the user's usage scenarios and habits. For example, according to the user's habit of often driving at night and the feedback on the dashboard brightness, the system automatically adjusts the night display mode of the dashboard. At night, the overall brightness of the dashboard is reduced to avoid overly bright light from irritating the user's eyes. At the same time, the display contrast and font size of key information on the dashboard (such as vehicle speed, engine speed, fuel level, etc.) are optimized to make it clearer and easier to read.

[0059] Using the analysis results of user behavior data, the layout of the vehicle's interactive interface is optimized. If it is found that when the user operates a certain function button, they need to frequently switch interfaces or click multiple times to complete a task, it indicates that the current interface layout may not be reasonable enough. For example, in the vehicle's multimedia playback interface, the user often needs to search and switch music playlists in multiple sub-menus. The system can, based on this behavior analysis, redesign the layout of the multimedia playback interface, set the commonly used playlists as quick access entries and directly display them on the main interface, or use intelligent prediction algorithms to automatically recommend suitable playlists according to the user's historical play records and current time, location, etc., and display them in a prominent position, reducing the user's operation steps and time, and improving the interaction efficiency and user experience.

[0060] In terms of meeting safety goals, the interaction design optimization module is closely integrated with the vehicle's safety system. For example, when the vehicle's forward collision warning system detects a possible collision risk, it not only alerts the user through sound and visual alarms but also optimizes the display method and content of the alarms. On the in-vehicle display screen, intuitive graphics and concise text are used to indicate the source direction, distance, and estimated time of the collision risk. At the same time, the vehicle's braking system and throttle response are automatically adjusted to a safer state to prevent the user from exacerbating the danger due to misoperation. Moreover, based on the user's feedback and acceptance of different types of safety prompts, the way and intensity of the safety prompts are adjusted personalized. For example, for some users who are more sensitive to alarms, a milder but still effective prompt method can be provided, such as reminding the user to pay attention to safety through seat vibration or slight light flashing. At the same time, in the vehicle settings, the user is allowed to adjust the way of safety prompts according to their own preferences to achieve the best balance between safety effects and user experience.

[0061] In terms of enhancing comfort goals, the module focuses on optimizing the interaction design of the vehicle's interior environment. According to the user's feedback on the temperature, humidity, and air quality inside the vehicle, the operating parameters of the air conditioning system and air purification system are automatically adjusted. For example, if the user manually sets the in-vehicle temperature to a lower value during multiple driving processes, the system can infer that the user has a preference for a lower temperature. In subsequent driving, the preset air conditioning temperature is automatically adjusted to the temperature range the user is accustomed to, while optimizing the air outlet mode and wind speed of the air conditioner to avoid direct blowing on the user and causing discomfort. In addition, by collaborating with seat suppliers, an intelligent seat adjustment function is introduced. Based on the user's sitting posture and body pressure distribution data, the shape and support strength of the seat are automatically adjusted to provide a more comfortable driving sitting posture and reduce the fatigue caused by long-term driving. Moreover, in terms of vehicle noise control, using the user's feedback on the in-vehicle noise level, the vehicle's sound insulation materials and sealing design are optimized, and at the same time, the in-vehicle noise is further reduced through active noise cancellation technology to create a quieter and more comfortable driving environment for the user.

[0062] In terms of enhancing the convenience goal, the interactive design optimization module is committed to simplifying the vehicle's operating procedures and providing convenient service access. For example, through deep integration with smartphones, the vehicle's keyless entry and start functions are seamlessly connected to the phone. Users only need to bring their phones close to the vehicle, and the system will automatically identify and unlock the door, while starting the vehicle's personalized settings, such as adjusting the seat position, playing the user's favorite music, etc. In the in-vehicle navigation system, a variety of third-party application services are integrated, such as online ordering, gas station payment, and parking reservation. Users can operate these applications directly through the in-vehicle display during driving without using a mobile phone, which improves the convenience and safety of operation. In addition, based on the user's daily travel habits and common destinations, intelligent recommendations for related services and information are made, such as automatically prompting nearby supermarket discount information or recommending dinner restaurant options when the user is approaching the end of get off work and driving towards home, providing more convenience for the user's life and improving the user's overall satisfaction and dependence on the vehicle interaction system.

[0063] In terms of meeting personalized demand goals, the module uses user portraits and user behavior data to provide each user with a customized interactive experience. For example, based on the user's music preferences, a personalized music playlist is automatically created for the user and highlighted on the homepage of the in-vehicle display. For users who like a sense of technology, a cooler vehicle information display interface and interactive driving data visualization charts are provided, such as real-time display of the vehicle's power output curve, energy recovery, etc. At the same time, users are allowed to customize the vehicle's interactive interface theme and color according to their preferences, and choose from a variety of preset themes or upload their favorite pictures as the background, so that the vehicle's interactive interface is more in line with the user's personality and aesthetics, and enhance the user's emotional connection and sense of belonging to the vehicle.

[0064] The real-time feedback and adjustment module integrates an anomaly detection mechanism to identify abnormal patterns of user behavior and generate corresponding feedback information. The anomaly detection mechanism in the real-time feedback and adjustment module adopts a statistical model-based method. For the user's driving behavior data, a statistical distribution model of normal driving behavior is established, including the mean and standard deviation of the vehicle speed, and the frequency distribution of the steering wheel rotation angle. At the same time, a machine learning algorithm is combined for anomaly detection. The machine learning algorithm chooses to use the isolation forest algorithm to divide the data by constructing a random binary tree, and isolates abnormal data points in the shallower layer of the tree. In the user behavior analysis, for the user's operation sequence and time interval data of various vehicle functions, abnormal operation behaviors that are significantly different from the normal pattern are identified.

[0065] By real-time monitoring of the user's driving data, if it is found that the current vehicle speed exceeds multiple standard deviations of the normal range, or the steering wheel makes abnormally frequent large rotations within a short period of time, the system will determine that the driving behavior is abnormal. At this time, the module will immediately trigger the alarm system, send a warning message to the user, and at the same time record the abnormal data for further analysis. This anomaly detection method based on a statistical model can quickly and accurately identify behaviors that significantly deviate from the normal driving mode, providing strong support for ensuring driving safety in a timely manner.

[0066] The visualization and interaction feedback module supports diverse forms of data visualization. It supports interactive dashboard visualization and uses map visualization technology. In combination with the in-vehicle navigation system, it displays the user's driving trajectory, frequently visited locations, and information about surrounding points of interest in the form of a map.

[0067] The master control system combines machine learning algorithms to optimize the data processing and analysis process. It uses an image recognition algorithm based on deep learning to analyze the image data captured by the in-vehicle camera, automatically identifying different driving scenarios and traffic conditions on urban roads, highways, and rural roads.

[0068] The master control system classifies and stores the corresponding data, and adopts different preprocessing strategies for data in different scenarios. For data in the urban road scenario, it focuses on the density of pedestrians and vehicles and the changes in traffic lights, and performs more refined feature extraction and cleaning on this data to improve the accuracy of subsequent analysis. Through this intelligent data screening and classification, it can make more effective use of data resources, reduce unnecessary data processing workload, and at the same time improve the quality and usability of the data, providing more targeted data support for subsequent user behavior analysis and interaction design optimization.

[0069] In the user behavior analysis module, the reinforcement learning algorithm is used to continuously optimize the behavior analysis model. For example, through the deep reinforcement learning algorithm, the system continuously learns and adjusts its understanding and prediction of user behavior during the interaction with the user. The system dynamically adjusts the parameters of the clustering algorithm and the structure of the sequence analysis model according to the user's real-time feedback and behavior changes to better adapt to the personalized behavior patterns of different users. For example, when it is found that the user's driving habits have changed significantly within a certain period of time (such as changing from frequently driving long distances to mainly driving short distances within the city), the reinforcement learning algorithm will automatically trigger the retraining and optimization of the user behavior analysis model, adjusting the clustering categories and feature weights, so that the model can more accurately capture the user's new behavior patterns and needs, thereby providing a more timely and accurate basis for interaction design optimization and enhancing the adaptability and personalization of the user experience.

[0070] In the interactive design optimization module, a recommendation system algorithm based on machine learning is adopted to achieve more accurate interactive design recommendations. For example, using collaborative filtering algorithms, based on the interactive design choices of user groups with similar behavior patterns and preferences, suitable interactive interface layouts, function settings, and operation methods are recommended for the current user. By analyzing a large amount of user feedback on the use of different interactive design elements and satisfaction data, the system can discover potential associations and preference patterns among users. When a new user uses the system, the system recommends optimized interactive design solutions based on their initial behavior characteristics and similarity to other users. At the same time, combined with content recommendation algorithms, relevant functions and information are recommended according to the user's specific behavior and current situation. For example, when the user is driving on the highway, the system recommends appropriate cruise control settings, rest area information, and relevant safety tips based on the user's driving speed, navigation destination, and historical behavior, improving the pertinence and practicality of the interactive design, enhancing the convenience and satisfaction of the user's interaction with the vehicle.

[0071] Through the comprehensive application of machine learning algorithms, the system can achieve more automated and intelligent data analysis and decision-making. For example, in the real-time feedback and adjustment module, the system can automatically determine whether to adjust the vehicle's performance parameters or provide specific prompt information based on the user's real-time driving data and behavior patterns without manual intervention. When the system detects that the user is in a fatigued driving state, based on the judgment of the machine learning model, it automatically reduces the volume of the in-car music, adjusts the air conditioner temperature to a suitable waking state, simultaneously displays a fatigued driving warning icon on the dashboard, and prompts the user to pay attention to rest through voice. This intelligent automatic adjustment ability not only improves driving safety and comfort but also reflects the system's real-time perception and precise response to user needs, greatly enhancing the intelligent level and user experience of the entire interactive design system.

[0072] Innovatively introduce advanced machine learning technologies such as Generative Adversarial Networks (GANs) to generate virtual user behavior data and scenarios for expanding the dataset and conducting simulation tests. Through GANs, the system can generate virtual user data with various different characteristics and behavior patterns, which can be used to train and validate various machine learning models, improving the generalization ability and stability of the models. At the same time, using the generated virtual scenario data, such as driving scenarios under different traffic conditions and weather conditions, the system can conduct simulation tests and evaluations of interaction design in a virtual environment, discovering potential problems and optimization points in advance without conducting a large number of experiments in actual driving, saving time and costs, while also enhancing the innovation ability and reliability of interaction design. For example, by simulating driving scenarios in bad weather, test the interaction design effects of functions such as the vehicle's windshield wiper control and automatic headlight adjustment, and optimize according to the test results to ensure that when actually encountering bad weather, users can operate these functions more conveniently and safely, further improving the intelligent level of vehicle interaction design and the ability to handle complex scenarios.

[0073] It should be noted that there are attachments Figure 3 It can clearly show the comparison results of user satisfaction. Among them, the horizontal axis (X-axis): represents the user number. The values from 1 to 100 represent different user individuals. Each number corresponds to a user, showing the satisfaction data of each user.

[0074] The vertical axis (Y-axis): represents the satisfaction score, ranging from 0 to 1. The satisfaction score of each user is a value within this range. The closer it is to 1, the higher the user satisfaction; the closer it is to 0, the lower the satisfaction. Specific Embodiment Two:

[0076] As Figures 1-3 shown, the key algorithms mentioned in Embodiment One are analyzed in detail below, including their core mathematical formulas and explanations as well as specific application descriptions:

[0077] I. Data Collection and Preprocessing Module:

[0078] 1. Rule-based Data Cleaning:

[0079] When the system collects user data, it checks each data point. If a null value is found, the data point is directly deleted to ensure the accuracy of subsequent analysis. Automatically clear invalid or incomplete user data through set rules (such as time range, data type, etc.) to ensure the data quality for subsequent analysis.

[0080] 2. Anomaly Detection Algorithm (Z-score):

[0081] Formula:

[0082] Z: Standard score, X: Data point to be detected, μ: Mean of the data, σ: Standard deviation of the data.

[0083] Application description: In the preprocessing stage, calculate the Z-score of all data points. If the absolute value of the Z-score is greater than the set threshold, the data point is considered an outlier and processed. Use statistical methods or machine learning algorithms (such as Isolation Forest) to identify and remove outliers to prevent them from affecting subsequent analysis and model training.

[0084] 3. Data normalization (Min-Max Normalization):

[0085] Formula:

[0086] X′: Normalized data point, X: Original data point, X min : Minimum value in the dataset, X max : Maximum value in the dataset.

[0087] Application description: Reduce the dimensionality of the data, simplify the dataset by extracting the main features, improve the calculation efficiency, and at the same time retain most of the information for subsequent analysis.

[0088] 4. Principal Component Analysis (PCA)

[0089] Steps:

[0090] 1. Calculate the covariance matrix of the data 2. Calculate the eigenvalues and eigenvectors of the covariance matrix; 3. Select the top k eigenvectors to construct the projection matrix; 4. Projection: Z = X · W, where W is the matrix composed of eigenvectors.

[0091] Application description: Reduce the dimensionality of the data through PCA, extract the most representative user features for subsequent analysis, reduce the dimensionality of the data, simplify the dataset by extracting the main features, improve the calculation efficiency, and at the same time retain most of the information for subsequent analysis.

[0092] II. User Behavior Analysis Module:

[0093] 1. K-Means Clustering:

[0094] Formula: Update the cluster center:

[0095] C k : Center of the k-th cluster, N k : Number of points in the k-th cluster, S k : All points in the k-th cluster.

[0096] Loss function:

[0097] Application description: The system performs K-means clustering on user behavior data to identify different types of user groups, facilitating the design of subsequent personalized services. Users are grouped according to behavioral characteristics (such as click-through rate, access duration, etc.) to help identify different user groups and facilitate subsequent targeted design.

[0098] 2. DBSCAN:

[0099] Parameters: ∈\epsi lon∈ (neighborhood radius), MinPts (minimum number of points).

[0100] Application description: Through density clustering, identify dense user behavior patterns and isolated user behaviors, helping the system understand the behavioral differences of users in specific scenarios.

[0101] 3. Markov chain:

[0102] Transition probability: P(X t+1 = j|X t = i) = p ij

[0103] X t : current state, X t+1 : next state, p ij : probability of transitioning from state i to state j.

[0104] Application description: Used to analyze the transition behavior of users between different operations, helping to identify common paths when users use the product, analyzing the transition probability between different interaction steps, and identifying common behavioral paths to optimize the user interaction process.

[0105] 4. Hidden Markov Model (HMM):

[0106] Formula: P(O|λ) = ∑ q P(O|q,λ)P(q|λ)

[0107] O: observation sequence, λ: model parameters, q: state sequence.

[0108] Application description: Through HMM, infer the potential intentions and needs of users, predict the future behavior of users based on the observed behavior sequence, model the behavior sequence of users in specific situations, identify potential state changes, and help understand user needs.

[0109] III. User profile generation module

[0110] 1. Decision tree

[0111] Basic formula: Information gain: IG(D,A) = H(D) - H(D|A)

[0112] H(D): Entropy of dataset D, H(D|A): Entropy under the condition of attribute A.

[0113] Application description: Analyze user characteristics through decision trees to generate user portraits, enabling the system to perform personalized recommendations based on user attributes, and generating a visual decision tree model based on user characteristics and behavior data for quickly identifying user types and preferences.

[0114] 2. Support Vector Machine (SVM):

[0115] Formula: Optimization problem:

[0116] w: Hyperplane normal vector, x i : Input feature, y i : Label (1 or -1), b: Bias term.

[0117] Application description: Use SVM to classify user data to help generate a classified portrait of the user for personalized services.

[0118] 3. Random Forest:

[0119] Formula: The output of each tree is:

[0120] f i (x): Prediction of the i-th tree, N: Number of trees.

[0121] Application description: Improve the accuracy and robustness of the user portrait through the voting mechanism of multiple decision trees.

[0122] 4. Graph Embedding Algorithm (such as Node2Vec):

[0123] Formula: Optimization objective: max∑ u∈V Σ v∈N(u) logσ(u T v)

[0124] V: Set of nodes, N(u): Neighbors of node u, σ: Sigmoid function.

[0125] Application description: Map users and behaviors to a low-dimensional space through the graph embedding algorithm to generate a richer personalized portrait for users.

[0126] IV. Interaction Design Optimization Module

[0127] 1. Collaborative Filtering:

[0128] Formula: Predicted score:

[0129]

[0130] The predicted score of user u for item i, N(i): the set of items similar to item i, w ij : the similarity between items i and j, r u,j : the actual score of user u for item j.

[0131] Application description: Based on the user's historical behavior and scores, recommend appropriate interaction design solutions to enhance the user experience.

[0132] 2. Genetic algorithm:

[0133] Formula: Fitness function: f(x) = Evaluate(x)

[0134] Application description: Through evolutionary strategies, optimize the multi-objective requirements in the interaction design to achieve a better user experience.

[0135] 3. Particle Swarm Optimization (PSO):

[0136] Formula:

[0137] Update formula: v i = wv i + c1r1(pbest i - x i ) + c2r2(gbest - x i )

[0138] v i : the velocity of particle i, x i : the particle position, pbest i : the best position of particle i, gbest: the global best position.

[0139] Application description: By optimizing the design parameters, improve the overall effect of the interaction design.

[0140] V. Real-time Feedback and Adjustment Module

[0141] 1. Q-learning:

[0142] Update formula:

[0143]

[0144] Q(s,a): the value of state s and action a, r: the reward after executing the action in the current state, α: the learning rate, which controls the influence of new information on old information, γ: the discount factor, which evaluates the importance of future rewards, s′: the next state after executing action a.

[0145] Application Description: The system monitors user behavior in real time and updates policies to optimize the user experience. For example, if the user performs poorly in a certain interaction design, the system can dynamically adjust the design to improve the experience.

[0146] 2. Deep Q-Network (DQN)

[0147] Core formula: Loss function:

[0148]

[0149] where L: Loss function value, used to measure the difference between the prediction of the current Q-network and the target.

[0150] E: Expectation symbol, representing the average error over all possible state-action pairs.

[0151] r: Immediate reward value of the current action, which is the return obtained by the system after taking action a in state s; γ: Discount factor, with a value range of 0 to 1.

[0152] max a′ Q(s′, a′): Target Q value, representing the maximum Q value when choosing the optimal action a′ in the next state s′, used to estimate future rewards.

[0153] Q(s, a): Q value estimate of the current Q-network for state s and action a.

[0154] (r + γmax a′ Q(s′, a′) - Q(s, a)) 2 : Square of the difference between the target and the prediction. The smaller this value, the closer the prediction of the Q-network is to the true optimal value.

[0155] 3. Policy Gradient Method:

[0156] Update formula:

[0157]

[0158] θ: Policy parameter, J(θ): Performance metric of the policy.

[0159] Application Description: It directly improves the effect of the user interaction experience by optimizing the policy parameters and is applicable to the optimization of complex policies.

[0160] 4. Time Series Forecasting (ARIMA)

[0161] Y t = c + φ1Y t-1 + φ2Y t-2 + θ1∈ t-1 + θ2∈ t-2 + ∈ t

[0162] Y t : Observed value at the current moment, c: Constant term, φ: Autoregressive coefficient, θ: Moving average coefficient, ∈: White noise.

[0163] Application description: Analyze the historical data of user behavior, predict future changes in user needs, and adjust the system response in advance.

[0164] 5. Long Short-Term Memory Network (LSTM):

[0165] f t = σ(W f · [h t-1 , x t + b f )

[0166] Application description: Process time series data, capture long-term dependencies in user behavior, and is suitable for predicting changes in user needs and performing.

[0167] 6. Prophet:

[0168] Combined with trends, seasonality, and holiday effects for prediction:

[0169] y(t) = g(t) + s(t) + h(t)

[0170] g(t): Trend part, s(t): Seasonal part, h(t): Holiday effect.

[0171] Application description: Used to analyze and predict trend changes in user interactions, and help the system adjust the design according to the prediction results. Specific Example Three:

[0173] As Figures 1-3 shown, the following is a description of the specific application logic steps of each module and algorithm in the automotive product interaction design system based on multi-dimensional user experience data analysis:

[0174] 1. Data collection and preprocessing module

[0175] Application logic steps:

[0176] Data collection: Real-time collection of user behavior data from various sensors inside and outside the vehicle, user operation records, and other vehicle networking data sources.

[0177] Data cleaning and anomaly detection: Use rule-based data cleaning and anomaly detection algorithms to remove redundant, inconsistent, or abnormal data.

[0178] Rule-based cleaning: Define rules to remove invalid data, such as sensor error data points.

[0179] Anomaly Detection: Apply statistical or machine learning methods to detect data points that deviate from normal behavior.

[0180] Data Normalization: Use normalization techniques (such as Min-Max normalization) to unify data to the same scale and reduce the impact of dimensionality.

[0181] Feature Extraction: Utilize principal component analysis (PCA), independent component analysis (ICA), or feature selection algorithms to extract the most valuable features for user behavior analysis, reduce data dimensionality, and improve the efficiency of subsequent analysis.

[0182] 2. User Behavior Analysis Module

[0183] Application Logic Steps:

[0184] User Behavior Clustering: Use K-means, DBSCAN, and hierarchical clustering algorithms to perform clustering analysis on user behavior and identify typical user behavior patterns.

[0185] K-means Clustering: Divide user data into several behavior categories by specifying the number of clusters.

[0186] DBSCAN Clustering: Do not specify the number of clusters, suitable for discovering behavior groups with different noises and densities.

[0187] Hierarchical Clustering: Construct a hierarchical structure in user data to analyze different behavior patterns hierarchically.

[0188] Behavior Pattern Mining: Utilize Markov chains, hidden Markov models (HMMs), and sequential pattern mining techniques to analyze the temporal characteristics of user behavior.

[0189] Markov Chain: Analyze the transition probabilities of user behavior in different scenarios to help the system predict user behavior.

[0190] HMM: Used to mine hidden user behavior patterns and reveal potential rules of user operations.

[0191] Sequential Pattern Mining: Analyze the frequent sequential patterns of user behavior to provide reference for system design.

[0192] 3. User Portrait Generation Module

[0193] Application Logic Steps:

[0194] User Classification: Use classification algorithms such as decision trees, support vector machines (SVMs), and random forests to generate user portraits and identify user characteristics.

[0195] Decision Tree: Establish a rule tree to assign user characteristics based on user behavior and help the system distinguish different types of users.

[0196] SVM: Classify user data in a high-dimensional space to identify user preferences in certain behaviors.

[0197] Random Forest: Determine the user classification result through voting of multiple decision tree models to generate an accurate user profile.

[0198] Graph Embedding: Use graph embedding algorithms such as Node2Vec and GraphSAGE to model user relationship data and discover user group characteristics.

[0199] Node2Vec: Convert user relationships into vector representations to reveal similarities between users.

[0200] GraphSAGE: Combine neighbor node information to construct user graph embeddings and discover similar behavior characteristics of users.

[0201] Relational Network Embedding: Establish a social relationship graph and obtain social characteristics between users through embedding algorithms to improve the accuracy of the profile.

[0202] 4. Interaction Design Optimization Module

[0203] Application Logic Steps: Based on the user profile and behavior patterns, use collaborative filtering, content recommendation, and model-based recommendation algorithms to provide personalized recommendations.

[0204] Collaborative Filtering: Recommend suitable interaction design options based on the preferences of similar users.

[0205] Content Recommendation: Recommend relevant content or functional modules according to user preference characteristics to improve the interaction friendliness of the system.

[0206] Model-Based Recommendation: Use machine learning models to predict functions or interface layouts that users may be interested in.

[0207] Optimization Algorithms: Design interaction solutions under multi-objective optimization through techniques such as genetic algorithms, particle swarm optimization (PSO), and constraint optimization.

[0208] Genetic Algorithm: Select the optimal interaction design by simulating evolution to ensure that the design meets multi-dimensional user needs.

[0209] PSO: Search for the optimal parameter combination in the interaction design space to ensure that the design scheme achieves the expected user experience.

[0210] Constraint Optimization: Optimize the design scheme under limited conditions to ensure that the design complies with physical or design limitations.

[0211] 5. Real-Time Feedback and Adjustment Module

[0212] Application Logic Steps:

[0213] Reinforcement Learning: Based on real-time user feedback, use Q-learning, Deep Q-Network (DQN), and policy gradient algorithms to adjust system responses.

[0214] Q-learning: Update system behavior according to users' immediate feedback to gradually improve the system.

[0215] DQN: Predict user response behavior in a complex state space and optimize interaction design strategies.

[0216] Policy Gradient Algorithm: Dynamically adjust policies according to users' preference directions to enhance the user interaction experience.

[0217] Time Series Prediction: Combine time series models such as ARIMA, LSTM, and Prophet to predict future changes in user needs and make system responses in advance.

[0218] ARIMA: Analyze users' historical behavior data to predict short-term user behavior trends.

[0219] LSTM: Process behavior data with long-term dependencies to predict changes in user needs in complex scenarios.

[0220] Prophet: Combine seasonal change characteristics to predict users' interaction needs at different time nodes.

[0221] All modules in this system conduct data interaction through standardized interfaces. The master control system realizes data storage and processing through the cloud platform and supports the system's analysis of and real-time response to large-scale user data. Specific Embodiment Four:

[0223] As Figures 1-3 shown, the hardware composition of the core module in the master control system is as follows:

[0224] 1. Hardware Composition of the Data Collection and Preprocessing Module

[0225] Multimodal Sensor Array: Includes biometric sensors for the driver (such as heart rate sensors and galvanic skin response sensors) and environmental sensors (such as temperature, humidity, light intensity, etc.). These sensors can collect data on the user's physiological state inside the vehicle and the surrounding environment in real time, ensuring coverage of different user behaviors and situations.

[0226] Camera System: Mainly includes an in-built driver face camera and an external driving record camera, which help capture the user's facial expressions, head postures, and driving behaviors. The in-built camera is responsible for identifying information such as the driver's gaze direction and emotional changes, and the external camera can record the external road conditions.

[0227] Driving Behavior Detector: It includes a steering wheel pressure sensor, accelerator and brake pedal sensors, a steering angle sensor, and a vehicle speed sensor. These hardware components can capture the details of the user's driving operations and provide basic data for user behavior analysis.

[0228] Data Acquisition Terminal: It is used to collect data from sensors and cameras in real time. The acquisition terminal usually includes a microcontroller or an embedded computing module (such as Raspberry Pi, NVIDIA Jetson, etc.), which is responsible for integrating various types of data and transmitting them to the data processing module.

[0229] 2. Hardware Composition of User Behavior Analysis Module: (1) High-performance Computing Server: It is used to process massive amounts of user data and support complex clustering analysis and time series pattern mining. The server can select high-performance hardware with multi-core processors and high memory. Typical configurations include Intel Xeon processors, NVIDIA Tesla GPUs, etc. It can be deployed in the cloud or locally to achieve fast data processing and behavior pattern recognition. (2) FPGA or ASIC Hardware Accelerator: It supports large-scale matrix operations and parallel processing, and is used to execute computationally intensive algorithms such as clustering algorithms and Markov chains, hidden Markov models. FPGA hardware is suitable for accelerating matrix calculations, while ASIC can be used for specific deep learning model inference tasks to improve the computational efficiency of the model. (3) Embedded AI Chip: Embedded chips with built-in AI accelerators (such as Google Coral TPU, Edge TPU) can be applied to some real-time behavior analysis requirements, enabling edge computing in the vehicle, reducing data latency, and at the same time reducing the dependence on cloud computing.

[0230] 3. Hardware Composition of User Portrait Generation Module

[0231] Graph Processing Server: This module requires a high-performance graph computing server, mainly used for executing graph embedding algorithms (such as Node2Vec, GraphSAGE, etc.) and processing user relationship graphs and behavior data. The graph processing server can use a CPU with a large memory capacity and a multi-GPU architecture. Typical hardware configurations include high-end NVIDIA A100 GPUs, which are suitable for processing large-scale graph data.

[0232] Storage System: It is used to store user characteristics, behavior data, and generated user portrait information. The storage system uses a high-performance SSD array or distributed storage (such as Hadoop Distributed File System) to ensure fast reading and writing of user data under a large amount of data.

[0233] User Feature Database: Manages and stores user portraits based on NoSQL databases (such as MongoDB, Cassandra, etc.), suitable for large-scale and diverse data storage requirements, providing fast query capabilities and data management.

[0234] 4. Hardware Composition of the Interaction Design Optimization Module

[0235] Recommendation Algorithm Server: Used to run collaborative filtering, content recommendation, and model-based recommendation algorithms. This server requires high-efficiency parallel processing capabilities. Typical hardware choices include multi-core CPUs and high-performance GPUs, supporting the training and inference operations of recommendation models.

[0236] Multi-Objective Optimization Processor: Used to execute optimization algorithms such as genetic algorithms and particle swarm optimization (PSO). This module can process multi-objective optimization through FPGA or GPU-accelerated hardware to ensure the best results in interaction design. The main task of this processor is to accelerate complex optimization calculation processes to be able to adapt to user needs in real time.

[0237] Touch Screen and Display: As the terminal interface for system-user interaction, a car central control screen with a high-resolution touch display is an essential hardware. The screen provides a user selection interface and displays recommended content or personalized interaction design options. The screen is usually configured in the center console position for easy user operation and feedback.

[0238] 5. Hardware Composition of the Real-Time Feedback and Adjustment Module

[0239] Real-Time Data Feedback System: Combining in-vehicle real-time data acquisition hardware and wireless communication modules (such as 5G modules) can ensure the rapid transmission of data, facilitating the implementation of real-time feedback mechanisms.

[0240] Deep Learning Acceleration Hardware: Used for deep learning inference processing of DQN and policy gradient algorithms. NVIDIA Drive AGX or similar deep learning accelerators can accelerate the real-time operation of reinforcement learning algorithms in the vehicle, enabling dynamic prediction and rapid response to user needs.

[0241] Time Series Data Processor: Used for prediction requirements of time series models such as ARIMA and LSTM. The time series data processor can choose edge computing devices with embedded AI chips or implement customized acceleration based on FPGA to ensure high-efficiency computing capabilities during time series prediction.

[0242] Communication Module: Includes Wi-Fi, 4G / 5G, and Bluetooth modules for communicating with cloud platforms or other devices to ensure rapid data transmission and support remote control. The communication module can transmit the real-time feedback of users to the cloud analysis system or control system for timely adjustment.

[0243] 6. Hardware Composition of Visualization and Interactive Feedback Module

[0244] Data Processing and Rendering Server: It is used to generate visualization content such as dynamic interactive charts and heat map analysis. Typical configurations include high-performance computing servers with multiple GPUs, which are suitable for real-time processing and rendering of a large amount of user data.

[0245] Touch Screen: A high-resolution in-vehicle display, usually a touch screen, which is used to display visualization data of user behavior, heat maps, and user feedback, etc. The screen should have anti-reflection characteristics and high brightness to ensure visual effects under different lighting conditions.

[0246] Emotion Analysis Acceleration Module: It processes the emotional content in user feedback through an emotion analysis accelerator (such as a dedicated NLP chip or TPU module). This module can quickly analyze the emotional state in user feedback, so as to realize dynamic adjustment of the user experience. GPUs or Edge TPU modules that support emotion analysis can be used to analyze the emotion of user text feedback in real time.

[0247] Audio Output and Input Devices: They are used to receive user voice feedback and provide voice prompts. It includes a microphone and a speaker system, which can be used to collect user voice feedback and provide voice feedback on the results of user emotion analysis or system interaction prompts.

[0248] Hardware Composition of the Master Control System

[0249] Cloud Platform Server Cluster: Based on the cloud computing architecture, it provides data storage, processing, and model training resources. The cloud platform server cluster can be configured with multiple high-performance computing servers and distributed storage devices (such as Amazon AWS, Google Cloud, or Microsoft Azure) to support efficient data management and model training.

[0250] Data Storage and Backup System: It is used for the secure storage and backup of all data in the system, including distributed storage devices and backup servers. The distributed storage device can be based on Hadoop HDFS or AWS S3 to achieve long-term storage and backup of large-scale data.

[0251] Network Communication Module: It ensures smooth data transmission between system modules. The communication module includes Ethernet, 5G base stations, or fiber optic network devices to quickly transmit data between the cloud platform, the vehicle, and the user terminal.

[0252] It should be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "comprising a reference structure" does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0253] Although embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An automotive product interaction design system based on multi-dimensional user experience data analysis, including a master control system, characterized in that: The overall control system includes a data collection and preprocessing module, a user behavior analysis module, a user portrait generation module, an interaction design optimization module, a real-time feedback and adjustment module, and a visualization and interaction feedback module; Sp1. The data collection and preprocessing module cleans and preprocesses user data through rule-based data cleaning, anomaly detection algorithms, and data normalization techniques, and extracts user features through principal component analysis, independent component analysis, and feature selection techniques to provide high-quality data for subsequent analysis; Sp2. The user behavior analysis module uses K-means clustering, DBSCAN, and hierarchical clustering algorithms to perform clustering analysis on user behavior, and combines Markov chain, hidden Markov model, and sequence pattern mining techniques to deeply explore the behavior patterns of users in different scenarios, thereby identifying user needs; Sp3. The user portrait generation module uses decision tree, support vector machine, and random forest classification algorithms to generate user portraits, and combines Node2Vec, GraphSAGE, and relational network embedding graph embedding algorithms to provide comprehensive personalized portraits for users; Sp4. The interaction design optimization module realizes the optimization of interaction design through collaborative filtering, content recommendation, and model-based recommendation algorithms, and applies genetic algorithms, particle swarm optimization, and constraint optimization techniques to improve the user experience while meeting multi-objective requirements; Sp5. The real-time feedback and adjustment module uses Q-learning, deep Q-network, and policy gradient method reinforcement learning algorithms to dynamically adjust the system response according to the real-time data of users, and combines ARIMA, LSTM, and Prophet time series prediction algorithms to identify changes in user needs in advance; Sp6. The visualization and interaction feedback module generates data visualization techniques such as data aggregation, heat map analysis, and dynamic interactive charts to intuitively display user behavior and feedback, and combines dictionary-based sentiment analysis, machine learning classifiers, and deep learning models to provide real-time sentiment analysis of user feedback; Sp7. The data collection and preprocessing module, the user behavior analysis module, the user portrait generation module, the interaction design optimization module, the real-time feedback and adjustment module, and the visualization and interaction feedback module all perform data interaction through standardized interfaces. The overall control system stores and processes data through a cloud platform, supporting the analysis and real-time response of large-scale user data.

2. The automotive product interaction design system based on multi-dimensional user experience data analysis according to claim 1, characterized in that: The data collection and preprocessing module realizes real-time reception and processing of data through multiple data sources to enhance the comprehensiveness and effectiveness of data. The data collection and preprocessing module obtains vehicle operation data in real time through in-vehicle sensors, where the operation data includes vehicle speed, acceleration, and steering angle. During application, the driving style of the user is inferred from the data changes of the acceleration sensor, providing a reference for subsequent interaction design. For users with an aggressive driving style, the interaction prompt for optimizing vehicle power response is provided. At the same time, in-vehicle infotainment data is integrated, including the usage frequency, operation habits, and preference settings of the user for music and navigation functions. Meanwhile, a vehicle telematics unit is equipped to receive vehicle remote diagnostic data and data of the user's interaction with the vehicle through the mobile application via Telematics. When a vehicle fails, the behavior record of the user querying the fault information through the mobile application is used to optimize the vehicle fault prompt and diagnostic interaction process. The data collection and preprocessing module simultaneously adopts stream data processing technology when receiving data in real time to process the data in a timely manner. When the data enters the system, preliminary screening and classification are immediately carried out, and different types of data are assigned to the corresponding processing queues. The vehicle operation data directly related to driving safety is preferentially subjected to anomaly detection to ensure that potential safety hazards during vehicle driving can be discovered and processed in a timely manner.

3. The automotive product interaction design system based on multi-dimensional user experience data analysis according to claim 2, wherein: The user behavior analysis module adopts a variety of clustering and sequence analysis algorithms to form an in-depth understanding of the user behavior pattern and reveal potential changes in user needs. In the user behavior analysis module, the K-means clustering algorithm groups users based on driving operation habits, that is, the frequency and amplitude of acceleration and braking, and classifies users with frequent hard acceleration and hard braking into one category to analyze their behavior characteristics. The DBSCAN density clustering algorithm is used to analyze the clustering behavior patterns in different road conditions and different time periods. At the same time, a hierarchical clustering algorithm is used to construct a hierarchical structure model of user behavior to analyze the evolution of user behavior from macro to micro. During application, users are first divided into three categories: aggressive, steady, and conservative according to the overall driving style, and then further subdivided according to the turn signal usage frequency and parking habits in each major category.

4. The automotive product interaction design system based on multi-dimensional user experience data analysis according to claim 3, characterized in that: The user profile generation module adopts a dynamic update mechanism to dynamically update the user profile, ensuring that it continuously reflects the user's personalized characteristics and preferences. The user profile generation module monitors the user's online behavior in real time. When the user searches for a new destination using the in-vehicle navigation system during driving, the system immediately records this behavior and updates the user's interest preference tags according to the type of destination. It recommends nearby outdoor sports equipment stores or relevant activity information on the home page of the in-vehicle display, and at the same time preferentially displays convenient routes to outdoor places in the navigation system and provides detailed tips on relevant information such as surrounding parking lots and rest areas. By monitoring the long-term change trends of the user's average vehicle speed, acceleration distribution, and braking frequency data for habit analysis, the user profile generation module uses a decision tree algorithm to construct a user classification decision tree based on the user's age, gender, occupation, driving behavior data, and the characteristics of the vehicle usage scenario. The support vector machine algorithm is used to analyze the user's preferences for vehicle appearance and interior style, collecting data on the user's choices and evaluations of vehicle color, seat material, and dashboard style, as well as the user's likes and comments on vehicle exterior design on social media. Through the random forest classification algorithm, considering the user's consumption behavior and vehicle usage habits comprehensively, the user's consumption potential and loyalty are evaluated and classified. Analyze the user's vehicle maintenance frequency, whether they have purchased original factory parts or value-added services, and their participation in vehicle brand activities. For users with high consumption potential and high loyalty, they are marked as "high-quality customers" in the user profile. For this part of users, the system provides exclusive after-sales service discounts. The user profile generation module combines Node2Vec, GraphSAGE, and relational network embedding graph embedding algorithms to mine the social relationships and interest associations between users.

5. The automotive product interaction design system based on multi-dimensional user experience data analysis according to claim 4, characterized in that: The interaction design optimization module adopts an intelligent integration mechanism to integrate user feedback and perform intelligent adjustments on interaction elements to improve the quality of the user experience. The interaction design optimization module not only considers the user's direct evaluation of the existing interaction functions of the vehicle, but also analyzes the text descriptions of the vehicle usage experience on social media and online forum channels through natural language processing technology.

6. The automotive product interaction design system based on multi-dimensional user experience data analysis according to claim 5, wherein: The real-time feedback and adjustment module integrates an anomaly detection mechanism to identify abnormal patterns of user behavior and generate corresponding feedback information. The anomaly detection mechanism in the real-time feedback and adjustment module adopts a method based on a statistical model. For the user's driving behavior data, a statistical distribution model of normal driving behavior is established, including the mean and standard deviation of vehicle speed, and the frequency distribution of the steering wheel rotation angle. At the same time, machine learning algorithms are combined for anomaly detection. The machine learning algorithm selects the isolation forest algorithm to partition the data by constructing a random binary tree, isolating abnormal data points in the shallower layer of the tree. In user behavior analysis, for the operation sequence and time interval data of the user's various functions of the vehicle, abnormal operation behaviors that are significantly different from the normal mode are identified.

7. The automotive product interaction design system based on multi-dimensional user experience data analysis according to claim 6, characterized in that: The visualization and interactive feedback module supports diverse data visualization forms. The visualization and interactive feedback module supports interactive dashboard visualization and adopts map visualization technology. Combined with the in-vehicle navigation system, it displays the user's driving trajectory, frequently visited locations, and surrounding point-of-interest information in the form of a map.

8. The automotive product interaction design system based on multi-dimensional user experience data analysis according to claim 7, characterized in that: The overall control system combines machine learning algorithms to optimize the data processing and analysis process. It uses an image recognition algorithm based on deep learning to analyze the image data captured by the in-vehicle camera, automatically identifying different driving scenarios and traffic conditions on urban roads, highways, and rural roads.

9. The automotive product interaction design system based on multi-dimensional user experience data analysis according to claim 8, characterized in that: The overall control system has flexible expansion capabilities and can quickly integrate new data sources and analysis functions according to new requirements. The overall control system adopts a microservices architecture, splitting the data collection and preprocessing module, user behavior analysis module, user profile generation module, interaction design optimization module, real-time feedback and adjustment module, and visualization and interactive feedback module into independent microservices, and designing a plug-in expansion mechanism that allows third-party developers or suppliers to add new functions and analysis capabilities to the system by developing plug-ins.

10. The automotive product interaction design system based on multi-dimensional user experience data analysis according to claim 1, characterized in that: Data interaction between the data collection and preprocessing module, user behavior analysis module, user profile generation module, interaction design optimization module, real-time feedback and adjustment module, and visualization and interactive feedback module is carried out through standardized interfaces, using Web service interfaces based on the RESTful architecture.

Images