Intelligent driving teaching guiding method

Abstract

The invention relates to an intelligent driving teaching guiding method, and relates to the technical field of intelligent driving. The method comprises the following steps: generating user tags according to multi-dimensional user information, wherein the user tags comprise a basic attribute tag, a driving experience tag, a technical adaptability tag and a learning preference tag; matching a learning path according to the user tag, wherein the learning path comprises teaching content, a teaching sequence, a teaching form and teaching difficulty; in the learning process of the user, learning operation data is collected in real time, and the learning operation data comprises learning time, a test result of a teaching test and an interaction behavior; and dynamically adjusting the learning path based on a reinforcement learning algorithm and the learning operation data. According to the invention, personalized intelligent driving teaching guidance can be provided for the user, and the learning efficiency and experience of the user for intelligent driving are improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to an intelligent driving teaching guidance method. Background Art

[0002] At present, with the increasing popularity of intelligent driving technology, drivers' familiarity with and operating skills of intelligent driving functions have become crucial. Intelligent driving functions, such as adaptive cruise control, lane keeping assist, and automatic parking, can reduce the burden on drivers, but they also require drivers to have certain knowledge and skills to ensure that they can safely and effectively take over vehicle control in an emergency. Therefore, before the vehicle's intelligent driving functions are activated and put into use, drivers need to undergo systematic learning and examinations.

[0003] However, current teaching guidance methods have limitations. For example, some tutorials rely too much on written materials and lack guidance on actual simulated operations. Or the teaching process is too cumbersome and abstract, which is not conducive to novice users to quickly grasp the key points and master intelligent driving technology. Or the teaching process is too basic and is not suitable for drivers who have already mastered the basic intelligent driving functions. In short, the current teaching guidance methods cannot provide targeted teaching guidance methods suitable for drivers in different situations. Summary of the invention

[0004] Based on this, it is necessary to provide an intelligent driving teaching guidance method to address the above technical issues.

[0005] In a first aspect, a smart driving teaching guidance method is provided, the method comprising:

[0006] Generating user tags according to multi-dimensional user information, wherein the user tags include basic attribute tags, driving experience tags, technical adaptability tags, and learning preference tags;

[0007] Matching a learning path according to the user tag, the learning path including teaching content, teaching sequence, teaching form and teaching difficulty;

[0008] During the user's learning process, learning operation data is collected in real time, and the learning operation data includes learning time, test results of teaching tests, and interactive behaviors;

[0009] The learning path is dynamically adjusted based on a reinforcement learning algorithm and the learning operation data.

[0010] As an optional implementation manner, matching the learning path according to the user tag includes:

[0011] Matching a corresponding teaching strategy template according to the user tag;

[0012] The teaching content, the teaching sequence, the teaching format and the teaching difficulty are determined according to the teaching strategy template.

[0013] As an optional implementation, the teaching form includes text teaching form, video teaching form and simulated driving teaching form.

[0014] As an optional implementation, the method further includes:

[0015] A corresponding relationship between the teaching strategy template and the user tag is established.

[0016] As an optional implementation manner, before generating the user tag according to the multi-dimensional user information, the method further includes:

[0017] The multi-dimensional user information is extracted based on the collected user registration information, driving habit questionnaire, driving behavior data, personal preference data and learning demand data.

[0018] As an optional implementation manner, the real-time collection of learning operation data during the user learning process includes:

[0019] Obtain the user's learning time and learning stage completion progress;

[0020] Record the user's test results, including the correctness of the answers and the types of errors;

[0021] Analyze the user's interactive behavior, including click times and operating habits.

[0022] As an optional implementation manner, the dynamically adjusting the learning path based on the reinforcement learning algorithm and the learning operation data includes:

[0023] Based on the learning operation data, construct a state space, wherein the state space is used to describe the current learning state of the user;

[0024] Defining an action set of the reinforcement learning algorithm, the action set including adjusting the teaching content, changing the teaching sequence, and modifying the teaching difficulty;

[0025] Calculating a reward value according to the learning operation data and a preset reward function;

[0026] The strategy update mechanism of the reinforcement learning algorithm is utilized to select the optimal action according to the current learning state and the reward value, and dynamically adjust the learning path.

[0027] As an optional implementation, the teaching test includes a theoretical test, a simulated driving operation test and a real-scene evaluation test.

[0028] As an optional implementation, the method further includes:

[0029] When the user passes the teaching test, the user is granted a virtual reward and the smart driving function is unlocked.

[0030] As an optional implementation, a social interaction function is embedded in the learning path, and the social interaction function includes sharing of learning progress and communication with peer users.

[0031] In a second aspect, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, and when the processor executes the computer program, the method steps described in any one of the first aspects are implemented.

[0032] According to a third aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method steps described in any one of the first aspects are implemented.

[0033] The present application provides a method for guiding intelligent driving teaching. The technical solution provided by the embodiment of the present application brings at least the following beneficial effects. The method includes: generating user tags according to multi-dimensional user information, wherein the user tags include basic attribute tags, driving experience tags, technical adaptability tags and learning preference tags; matching learning paths according to the user tags, wherein the learning paths include teaching content, teaching sequence, teaching form and teaching difficulty; collecting learning operation data in real time during the user learning process, wherein the learning operation data includes learning time, test results of teaching tests and interactive behaviors; and dynamically adjusting the learning path based on the reinforcement learning algorithm and the learning operation data. The present application improves learning efficiency and user experience through personalized learning paths and dynamic adjustment mechanisms, ensuring that the learning path always meets the needs of users. The problem of lack of personalization and dynamic adaptability in traditional teaching methods is solved. Learning content can be customized according to user characteristics, and learning progress can be adjusted in real time to avoid being too simple or overly challenging, thereby improving learning efficiency. At the same time, through a variety of teaching forms, the learning preferences of different users are met, and the fun of learning and the sense of participation of users are improved. The introduction of the reinforcement learning algorithm enables the teaching path to be continuously optimized, ensuring that users are always in the most suitable learning state during the learning process, thereby improving the overall learning effect and user satisfaction.

[0034] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 A flowchart of an intelligent driving teaching guidance method provided in an embodiment of the present application;

[0037] Figure 2 A flowchart of a learning path matching method provided in an embodiment of the present application;

[0038] Figure 3 A flowchart of a method for acquiring learning operation data provided in an embodiment of the present application;

[0039] Figure 4 A flowchart of a method for adjusting a learning path provided in an embodiment of the present application;

[0040] Figure 5 A schematic diagram of an example method and module for intelligent driving teaching guidance provided in an embodiment of the present application;

[0041] Figure 6 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0043] The following will describe in detail an intelligent driving teaching guidance method provided by an embodiment of the present application in combination with a specific implementation method. Figure 1 A flowchart of an intelligent driving teaching guidance method provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the specific steps are as follows:

[0044] Step 101 , generating user tags according to multi-dimensional user information, wherein the user tags include basic attribute tags, driving experience tags, technical adaptability tags, and learning preference tags.

[0045] In implementation, we can first obtain multi-dimensional information of users by collecting their registration information, driving habit questionnaires, driving behavior data, personal preference data, and learning demand data. By cleaning, organizing, and encoding the multi-dimensional information of users to form a data set that can be used for analysis, we can use clustering algorithms to group user data and generate personalized labels for users, including basic attribute labels (such as age and gender), driving experience labels (such as driving experience and driving habits), technical adaptability labels (such as familiarity with smart devices), and learning preference labels (such as preference for teaching methods). These labels provide a basis for subsequent learning path matching to ensure that the teaching content is highly consistent with user characteristics. For example, users can be classified according to age groups to obtain user labels, such as novice drivers (20-30 years old), experienced drivers (30-50 years old), etc. Users can also be divided into "technical novices" and "technical proficients" based on their adaptability to technology. Users can also be divided into "novice drivers", "conventional drivers", and "experienced drivers" based on driving experience and driving behavior data. Users can also be divided into "visual learners", "hands-on operators", and "theoretical learners" based on their personal preferences. User satisfaction and needs can also be classified based on user feedback information. During the cluster analysis process, users can be clustered into different driving style groups based on their driving behavior data, such as cautious, aggressive, and robust. The system can also analyze the correlation between user attributes and learning preferences. For example, it is found that young users are more receptive to new intelligent driving functions, while older users prefer traditional driving methods. It is also possible to develop a user label system and classification standards based on the experience of experts in the field of intelligent driving. The following is a specific implementation example of label classification:

[0046] Basic attribute tags: age, gender, occupation, educational background, driving experience, etc.

[0047] Driving proficiency labels: novice driver, ordinary driver, experienced driver (can be divided according to driving age, mileage, accident record and other indicators).

[0048] Driving habit labels: cautious, aggressive, and stable (can be divided according to driving behavior data, such as average speed, acceleration and deceleration frequency, number of emergency brakes, etc.).

[0049] Common driving scene labels: urban roads, highways, rural roads, etc.

[0050] Smart device usage experience labels: rich, average, and lacking (can be divided according to the frequency and proficiency of users in using devices such as smartphones and tablets).

[0051] Learning ability labels: fast learner, medium learner, slow learner (can be assessed based on the speed and efficiency of users learning other skills).

[0052] Teaching method labels: visual, auditory, and kinesthetic (can be divided according to the user's preference for different learning methods).

[0053] Content preference tags: theoretical knowledge, practical operation, case analysis, etc.

[0054] Intelligent driving function usage intention label: interest level in different intelligent driving functions: for example, interest level in adaptive cruise control, lane keeping assist, automatic parking and other functions.

[0055] Acceptance level labels: active acceptance, hesitation, resistance and rejection.

[0056] As an optional implementation, the following method is also included before step 101:

[0057] Multi-dimensional user information is extracted based on the collected user registration information, driving habit questionnaire, driving behavior data, personal preference data and learning needs data.

[0058] During implementation, the system can extract multi-dimensional user information from the collected registration information, driving habit questionnaires, driving behavior data, personal preference data, and learning needs data. For example, basic information: including age, gender, occupation, educational background, etc. This information helps to understand the user's basic situation and learning ability. Driving experience: the user's driving age, road conditions that they often drive on, etc., are used to evaluate the user's driving proficiency. Technical familiarity: the user's familiarity with and operating ability of smart devices, such as whether they often use smartphones and whether they are familiar with touch operations. Personal preferences: users' learning preferences for smart driving functions, such as preference for learning through videos or text instructions. Behavioral data: users' behavioral performance during the interactive learning process of smart driving teaching, such as reaction time to smart driving functions, operation frequency, etc. Feedback information: user feedback on smart driving teaching guidance, including satisfaction, improvement suggestions, etc.

[0059] Step 102, matching the learning path according to the user tag, the learning path includes teaching content, teaching sequence, teaching form and teaching difficulty.

[0060] In implementation, the system can match appropriate teaching strategy templates based on the generated user tags. These strategy templates include a variety of teaching content, teaching sequence, teaching form and teaching difficulty. Based on the user's tag information, the system can tailor the most suitable learning path for each user.

[0061] As an optional implementation, Figure 2 A flowchart of a learning path matching method provided in an embodiment of the present application, such as Figure 2 As shown, the specific steps of matching the learning path according to the user tag in step 102 are as follows:

[0062] Step 201, matching the corresponding teaching strategy template according to the user tag.

[0063] In implementation, the system can select the most suitable strategy template from the preset teaching strategy template library by analyzing user tags (such as basic attributes, driving experience, technical adaptability and learning preferences). Each teaching strategy template is designed according to the needs of different user types, covering a variety of teaching content, teaching sequence, teaching methods and difficulty settings. For example, if the user tag is "novice driver" and "visual learner", the teaching strategy template of "basic introduction-mainly visual teaching" is matched. If the user tag is "old driver" and "interested in automatic parking function", the teaching strategy template of "basic must-learn-automatic parking-mainly case analysis" is matched.

[0064] Step 202, determining the teaching content, teaching sequence, teaching format and teaching difficulty according to the teaching strategy template.

[0065] In implementation, the system can further refine the teaching content, teaching sequence, teaching form and teaching difficulty according to the selected teaching strategy template. The teaching content includes necessary theoretical knowledge, driving skills training and emergency operation, etc. The complete learning content can include 4 modules (such as basic, driving, parking and safety modules). Each module contains at least 4 or more scene content teaching and small tests. After each module content is learned, a module test is provided. The basic module is a required module, and the other 3 modules are advanced modules, which can be selected according to needs. Only after learning the basic module can you choose to continue learning the other 3 advanced modules. After learning each advanced module, the corresponding intelligent driving function is enabled. After all 4 modules are learned, the entire learning process is completed and ended, and the user turns on all intelligent driving functions. The teaching order is determined according to the user's learning level, ensuring that the basic content is learned first, and then entering the advanced module. The teaching form includes text, video and simulated driving and other forms. The system can adapt according to the user's learning preferences (such as users like video tutorials or interactive exercises). The difficulty of teaching is dynamically adjusted according to the user's driving experience and technical adaptability, ensuring that the learning process is neither too simple nor beyond the user's ability. For example, for users with poor technical adaptability, the system can provide more graphic teaching and operation guidance, while for users with strong technical adaptability, more simulated driving exercises and challenging tasks are pushed, gradually increasing the difficulty to ensure a gradual learning process.

[0066] As an optional implementation method, the teaching form includes text teaching form, video teaching form and simulated driving teaching form.

[0067] In practice, the text teaching form provides concise text instructions to help users quickly understand driving principles and theoretical knowledge. This form is particularly suitable for users who are familiar with theoretical learning, and can convey key information in concise text content. The video teaching form presents teaching content through vivid images and sounds, and presents the driving operation process and precautions more intuitively. This form is suitable for visual learners, and they can improve their understanding and memory by watching video demonstrations. For example, the video can show how to operate the steering wheel correctly or how to deal with emergencies in traffic, allowing users to imitate and learn actual operations during the viewing process. The simulated driving teaching form provides a virtual driving environment, and users can perform operation training in simulated driving scenarios. This form is suitable for kinesthetic learners, and can deepen their understanding and improve their operating skills through actual operations. For example, in a simulated environment, users can simulate various scenarios by driving a virtual vehicle, such as urban road driving, highway driving, or night driving, and the system will provide real-time feedback based on the user's performance to help them optimize their operating skills. These teaching forms can be flexibly selected based on the user's tag information (such as learning preferences). For example, if the user prefers video learning, the system can give priority to video teaching, and if the user prefers hands-on operation, the system tends to provide simulated driving training.

[0068] As an optional implementation method, a corresponding relationship between the teaching strategy template and the user tag may also be established.

[0069] In implementation, as an optional implementation method, a corresponding relationship between the teaching strategy template and the user tag can also be established.

[0070] In implementation, the system can match the corresponding teaching strategy template according to different dimensions of user tags (such as basic attributes, driving experience, technical adaptability, learning preferences, etc.). The teaching strategy template is a pre-designed teaching plan that sets the corresponding teaching content, teaching sequence, teaching form and teaching difficulty according to the characteristics of different users. For example, for novice drivers, the teaching strategy template may include starting from basic driving operations and gradually transitioning to complex driving skills. For drivers with certain experience, the strategy template may give priority to providing learning content for advanced driving skills or intelligent driving functions. Specifically, the system can match user tags with defined teaching strategy templates through a preset user tag matching algorithm. First, obtain the user's registration information, driving behavior data, learning needs and other information to generate a comprehensive user portrait. Then, the system compares the user portrait with the preset teaching strategy template and selects the most suitable learning path for the user. In this way, the teaching path can accurately reflect the personalized needs of each user and provide the most suitable learning plan. For example, if the user tag shows that the user has high technical adaptability but prefers simulated driving, the system can select a strategy template that emphasizes video teaching and simulated driving practice, while setting the teaching difficulty above the current level to ensure a balance between challenge and learning effect.

[0071] Step 103, during the user's learning process, learning operation data is collected in real time, and the learning operation data includes learning time, test results of teaching tests, and interactive behaviors.

[0072] In practice, the system can continuously monitor and record the user's learning progress, collect learning time, answer accuracy, error type and interactive behavior data. These data provide real-time performance of users in the learning process, helping the system evaluate learning effects and difficulties. For example, if a user frequently makes mistakes in the test of a certain learning module, the system can identify the user's weak link and adjust the learning content or sequence for them to ensure the effectiveness of learning.

[0073] As an optional implementation, Figure 3 A flowchart of a method for acquiring learning operation data provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, in step 103, during the user learning process, the specific steps of collecting learning operation data in real time are as follows:

[0074] Step 301, obtaining the user's learning time and learning stage completion progress.

[0075] In implementation, the system can calculate the time spent by the user in each learning stage by monitoring the timestamp of the user entering the learning module and the timestamp of exiting the learning module. The progress of the learning stage completion is updated in real time by tracking the proportion of tasks or tests completed by the user in a specific module. For example, if a module contains 5 learning tasks and the user completes 3 tasks, the system will record the completion progress as 60%. Through these data, the system can evaluate the user's learning rhythm and efficiency, and then adjust the teaching path. For example: When a user is learning in the "Basic Driving Skills" module, the system records the start time as 9:00, the end time as 9:45, and the total learning time as 45 minutes. At the same time, the module contains 4 teaching tasks, the user completes 3 of them, and the system updates the progress to 75%.

[0076] Step 302, recording the user's test results, the test results including the correct answer rate and error types.

[0077] In implementation, the system can evaluate the teaching tests completed by users, including the number of questions the user answered correctly and the specific types of incorrect questions. For example, some errors may be concentrated in specific knowledge points. The system can mark these problems and strengthen the relevant content in the subsequent teaching path. At the same time, the system uses statistical analysis to generate the user's overall learning performance, such as accuracy trends and learning difficulties, to optimize the learning path. For example: A user answered 15 questions in the "Basic Knowledge of Intelligent Driving" test, answered 12 questions correctly, and the correct answer rate was 80%. The system analysis found that its errors were concentrated in the knowledge related to the "lane keeping system", and then added more explanations and exercises about this knowledge point in the subsequent teaching.

[0078] Step 303: Analyze the user's interactive behavior, which includes the number of clicks and operating habits.

[0079] In implementation, the system can analyze the user's operating habits by recording the number of clicks, sliding operations, and task switching frequency in the interface. For example, frequent clicks may indicate that the user is interested in or confused about the current content, and a long stay may indicate that the content is difficult or there is a need for in-depth learning. The system can adjust the presentation of teaching content through these behavioral data, such as providing more intuitive prompts or optimizing the interface layout to enhance the user experience. For example: When a user was watching a teaching video, he paused and rewound 5 times and clicked on the prompt function of related knowledge points 3 times. The system can determine that the user has some difficulty in understanding this content, so it sets the knowledge point as a "key knowledge point" and provides relevant reinforcement exercises and tests in subsequent modules.

[0080] As an optional implementation method, the teaching test includes a theoretical test, a simulated driving operation test and a real-scene evaluation test.

[0081] As an optional implementation, if the user passes the teaching test, the user is granted a virtual reward and the smart driving function is unlocked.

[0082] In implementation, the system can detect the user's completion of teaching tests in real time, and grant virtual rewards, such as virtual badges, points or level upgrades, to the user after the user passes all test modules. These rewards can not only enhance the user's sense of learning achievement, but also motivate the user to continue to participate in subsequent learning. At the same time, the system can unlock actual functions related to intelligent driving, such as adaptive cruise control, lane keeping assist or automatic parking functions, as a verification and incentive for the user's learning results. This incentive mechanism combines the positive reinforcement principle in psychology, so that users can get instant feedback after learning and completing goals, thereby improving user experience and participation enthusiasm. For example: After a user completes the three-part teaching test of "Basic Knowledge of Intelligent Driving", "Simulated Driving Operation" and "Real Scene Evaluation", the system automatically grants the user the "Intelligent Driving Pioneer" badge and adds 200 points. The system can also unlock the adaptive cruise control function, allowing users to try this function in the intelligent driving system. At the same time, users can view their reward records and unlocked function history on their personal page to further enhance their sense of learning participation and trust in the system.

[0083] Step 104: dynamically adjust the learning path based on the reinforcement learning algorithm and the learning operation data.

[0084] In implementation, the system can construct the user's current learning state based on the collected learning operation data, and make dynamic adjustments in combination with the reinforcement learning algorithm. By defining the state space and action set of reinforcement learning (such as adjusting teaching content, sequence and difficulty), the system can calculate the reward value based on real-time learning data and the preset reward function, thereby determining the best adjustment strategy. The reinforcement learning algorithm continuously updates the strategy, enabling the system to optimize the learning path based on the user's learning progress and feedback, thereby maximizing the user's learning efficiency and participation. For example, if the user performs well in a certain module, the system can speed up the progress and enter more advanced content. If the user performs poorly in a certain part, the system will reduce the difficulty or repeat the training to ensure that the user's learning path is the most suitable for their current level.

[0085] As an optional implementation, Figure 4 A flow chart of a method for adjusting a learning path provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, the specific steps of dynamically adjusting the learning path based on the reinforcement learning algorithm and the learning operation data in step 104 are as follows:

[0086] Step 401: construct a state space based on the learning operation data, where the state space is used to describe the current learning state of the user.

[0087] In implementation, the state space is the core component of the reinforcement learning algorithm, which is used to comprehensively describe the dynamic state of the user during the learning process. The system can construct a multidimensional state space through real-time collected learning operation data, including learning time, answer accuracy, error type, and interactive behavior. For example, the state can include the user's current learning module, current learning efficiency (such as answering time per question), test pass rate, etc. The construction of the state space provides the algorithm with a clear picture of the user's learning, which is helpful for subsequent decision optimization. For example: A user is currently learning the "Advanced Driver Assistance System Module", and his state space can be expressed as: current module = "Advanced Driver Assistance System", answer accuracy = 80%, average answer time = 20 seconds, number of clicks = 15, operation habits = normal.

[0088] Step 402, defining an action set of the reinforcement learning algorithm, the action set including adjusting teaching content, changing teaching sequence, and modifying teaching difficulty.

[0089] In implementation, the action set is a set of strategies that the algorithm can adopt to adjust the learning path to suit the actual needs of the user. Each action corresponds to a learning path adjustment method. For example, "adjusting the teaching content" means switching to content that the user is more interested in; "changing the teaching order" means giving priority to displaying content related to the user's current status; "modifying the teaching difficulty" means increasing or decreasing the complexity of the current teaching content. The action set ensures that users neither feel that learning is too simple nor lose interest in learning due to excessive difficulty by designing reasonable strategies. If the user shows a high accuracy rate in answering questions in the current module (over 90%), the algorithm can execute the action of "increasing the difficulty of teaching". If the user makes similar error types in multiple tests continuously, the algorithm can execute "adjusting the teaching content" and switch to the relevant basic knowledge module.

[0090] Step 403: Calculate the reward value according to the learning operation data and the preset reward function.

[0091] In implementation, the reward function is used to measure whether a certain learning path adjustment is effective. The reward value can be calculated by comprehensive learning efficiency, test scores, and user engagement. The reward function is designed to improve the user's learning effect and experience. For example, the reward value may be proportional to the user's correct answer rate and inversely proportional to the answer time. When the user's learning efficiency improves or the learning interest increases, the reward value is higher. Through the feedback of the reward value, the algorithm can continuously optimize and adjust the strategy. The reward function can be defined as: reward value = first weight (such as 0.5) × correct answer rate - second weight (such as 0.3) × average answer time + third weight (such as 0.2) × number of clicks. If the user's correct answer rate is 85%, the average answer time is 15 seconds, and the number of clicks is 10, the reward value is calculated as:

[0092] Reward value = 0.5×85-0.3×15+0.2×10=42.5.

[0093] Step 404, using the strategy update mechanism of the reinforcement learning algorithm, select the optimal action according to the current learning state and reward value, and dynamically adjust the learning path.

[0094] In implementation, the reinforcement learning algorithm selects the optimal action through the policy update mechanism to adjust the user's learning path in the direction of maximizing the reward value. The policy update mechanism can be Q-learning or deep Q network (DQN), which continuously optimizes action selection by iteratively learning historical data. The current state and reward value are input into the algorithm, and the algorithm outputs the optimal action (such as "adjusting the teaching order") and updates the learning path in real time. For example: the user's current state is "Advanced Driver Assistance System Module, Answering Correct Rate = 75%, Average Answering Time = 25 seconds", and the algorithm calculates the reward value and finds that the expected reward value of the "Adjusting the Teaching Order" action is the highest. The system then adjusts the module to a later order and gives priority to the user to complete the learning of the "Basic Driving Safety Knowledge" module.

[0095] As an optional implementation, a social interaction function is embedded in the learning path, and the social interaction function includes sharing of learning progress and communication with users of the same level.

[0096] In implementation, the social interaction function can provide users with a communication and interaction platform with other learners, increasing user participation and learning motivation. Through learning progress sharing, users can share their learning achievements with other learners. This social function can promote users' learning enthusiasm and motivate them to continue working hard. In addition, the peer communication function enables users to interact with peers with similar learning progress or abilities, exchange experiences, discuss problems, and enhance the atmosphere of collective learning. For example: in the intelligent driving teaching platform, after the user completes each learning module, the system can automatically generate a learning progress report, and the user can share it with the learning group on the platform to show his or her learning achievements. At the same time, the system can provide user recommendations based on similar learning progress, and encourage peer users to communicate with each other, such as through forums, chat rooms or online Q&A, to answer each other's questions encountered in the learning process.

[0097] As an optional implementation, Figure 5 A schematic diagram of an example method and module for intelligent driving teaching guidance provided in an embodiment of the present application, such as Figure 5 As shown, the specific steps are as follows:

[0098] Step 501, generating user tags: generating user tags through multi-dimensional information such as user registration information, driving habit questionnaire, driving behavior data, personal preferences and learning needs.

[0099] Step 502, personalized learning path customization: Based on user tags, a machine learning algorithm is used to generate a personalized learning path for each user, including teaching content, teaching sequence, teaching form and teaching difficulty.

[0100] Step 503, interactive teaching guidance: designing an interactive teaching guidance interface.

[0101] Step 504, real-time feedback and adjustment: during the user's learning process, the user's learning operation data is collected in real time, and the learning path is adjusted dynamically.

[0102] Step 505, testing and certification: After the user completes the learning path, provide advanced testing to evaluate the user's mastery and provide corresponding certification.

[0103] The embodiment of the present application provides a method for guiding intelligent driving teaching, the method comprising: generating user tags according to multi-dimensional user information, the user tags including basic attribute tags, driving experience tags, technical adaptability tags and learning preference tags; matching learning paths according to user tags, the learning paths including teaching content, teaching sequence, teaching form and teaching difficulty; in the user learning process, real-time collection of learning operation data, the learning operation data including learning time, test results of teaching tests and interactive behaviors; dynamically adjusting the learning path based on reinforcement learning algorithm and learning operation data. The embodiment of the present application improves learning efficiency and user experience through personalized learning paths and dynamic adjustment mechanisms. The method first generates user tags according to the user's multi-dimensional information (such as registration information, driving habits, personal preferences, etc.), including basic attributes, driving experience, technical adaptability and learning preferences, and then matches the learning path according to these tags, covering teaching content, sequence, form and difficulty. During the learning process, the system collects the user's learning operation data (such as learning time, test results and interactive behaviors) in real time, and dynamically adjusts the learning path using reinforcement learning algorithm. Reinforcement learning calculates the reward value according to the user's learning progress and feedback, and adjusts the teaching content, sequence and difficulty to ensure that the learning path always meets the user's needs. This method solves the problem of lack of personalization and dynamic adaptability in traditional teaching methods. It can customize learning content according to user characteristics, adjust learning progress in real time, avoid being too simple or overly challenging, and improve learning efficiency. At the same time, through a variety of teaching methods (text, video, simulated driving, etc.), it meets the learning preferences of different users, improves the fun of learning and the user's sense of participation. The introduction of reinforcement learning algorithms enables the continuous optimization of teaching paths, ensuring that users are always in the most suitable learning state during the learning process, thereby improving the overall learning effect and user satisfaction.

[0104] It should be understood that although Figures 1 to 5 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figures 1 to 5 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0105] It can be understood that the same / similar parts between the various embodiments of the above method in this specification can refer to each other, and each embodiment focuses on the differences from other embodiments. For related points, please refer to the description of other method embodiments.

[0106] In one embodiment, a computer device is provided, such as Figure 6 As shown, it includes a memory and a processor, the memory stores a computer program that can be run on the processor, and the processor implements the above-mentioned method steps of intelligent driving teaching guidance when executing the computer program.

[0107] In one embodiment, a computer-readable storage medium stores a computer program, which implements the steps of the above-mentioned intelligent driving teaching guidance method when executed by a processor.

[0108] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0109] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0110] It should also be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data for analysis, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0111] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0112] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0113] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. An intelligent driving teaching guidance method, characterized in that: The method comprises: Generating user tags according to multi-dimensional user information, wherein the user tags include basic attribute tags, driving experience tags, technical adaptability tags, and learning preference tags; Matching a learning path according to the user tag, the learning path including teaching content, teaching sequence, teaching form and teaching difficulty; During the user's learning process, learning operation data is collected in real time, and the learning operation data includes learning time, test results of teaching tests, and interactive behaviors; The learning path is dynamically adjusted based on a reinforcement learning algorithm and the learning operation data.

2. The method according to claim 1, characterized in that: The matching of the learning path according to the user tag includes: Matching a corresponding teaching strategy template according to the user tag; The teaching content, the teaching sequence, the teaching format and the teaching difficulty are determined according to the teaching strategy template.

3. The method according to claim 2, characterized in that: The teaching methods include text teaching, video teaching and simulated driving teaching.

4. The method according to claim 2, characterized in that: The method further comprises: A corresponding relationship between the teaching strategy template and the user tag is established.

5. The method according to claim 1, characterized in that: Before generating the user tag according to the multi-dimensional user information, the method further includes: The multi-dimensional user information is extracted based on the collected user registration information, driving habit questionnaire, driving behavior data, personal preference data and learning demand data.

6. The method according to claim 1, characterized in that During the user learning process, real-time collection of learning operation data includes: Obtain the user's learning time and learning stage completion progress; Record the user's test results, including the correctness of the answers and the types of errors; Analyze the user's interactive behavior, including click times and operating habits.

7. The method according to claim 1, characterized in that The dynamically adjusting the learning path based on the reinforcement learning algorithm and the learning operation data includes: Based on the learning operation data, construct a state space, wherein the state space is used to describe the current learning state of the user; Defining an action set of the reinforcement learning algorithm, the action set including adjusting the teaching content, changing the teaching sequence, and modifying the teaching difficulty; Calculating a reward value according to the learning operation data and a preset reward function; The strategy update mechanism of the reinforcement learning algorithm is utilized to select the optimal action according to the current learning state and the reward value, and dynamically adjust the learning path.

8. The method according to claim 1, characterized in that The teaching test includes a theoretical test, a simulated driving operation test and a real-scene evaluation test.

9. The method according to claim 1, characterized in that: The method further comprises: When the user passes the teaching test, the user is granted a virtual reward and the smart driving function is unlocked.

10. The method according to claim 1, characterized in that The learning path is embedded with a social interaction function, which includes sharing of learning progress and communication with peer users.

Images