Personalized learning system and method for driving training theory examination

Abstract

The invention provides a driving training theory test personalized learning system and method, and the system comprises a personalized learning decision module which is used for generating a personalized learning path of a student based on the multi-dimensional learning data of the student and a traffic regulation knowledge graph; the personalized learning path comprises a plurality of personalized learning nodes; the multi-modal interaction virtual partner training module is used for providing question analysis for the trainees in a multi-modal interaction mode when the trainees learn the individual learning nodes; the multi-mode interaction mode comprises a voice interaction mode and a visual interaction mode; and the emotional intelligent feedback module is used for determining the learning emotion of the student based on the learning state of the student during learning at each personalized learning node and a preset emotion recognition model, and adjusting the teaching style and the content difficulty of the personalized learning node based on the learning emotion. According to the invention, personalized customization of the learning path and interaction ability and emotion perception ability in the training partner process are realized, and the learning efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence education technology, and in particular to a personalized learning system and method for a driving training theory test. Background Art

[0002] As people's living standards improve, the use of family cars increases. Simultaneously, more and more people are studying for driver's licenses. To improve the success rate and efficiency of the driver's license test, students must complete theoretical driving training before the actual test. Traditional driving training theory learning methods rely on offline training, but learning efficiency is low and study time is inflexible. To address these technical issues, driving test software has emerged.

[0003] Existing driving test software provides a massive question bank for students to study, but its learning paths are relatively rigid, with simple feedback on correct answers, and it is unable to customize differentiated learning paths for students. For example, when studying traffic laws, students are required to complete questions in a uniform order regardless of their mastery of key knowledge points such as fine details and traffic sign recognition, resulting in low learning efficiency. Furthermore, driving test software only provides a question bank and cannot adjust learning paths based on student status, resulting in a decrease in student motivation and further low learning efficiency.

[0004] Therefore, there is an urgent need to provide a personalized learning system and method for driving training theory examination, which can realize the formulation of personalized learning paths, improve students' learning enthusiasm, and thus improve learning efficiency, so as to increase the pass rate of theoretical examination. Summary of the Invention

[0005] In view of this, it is necessary to provide a personalized learning system and method for driving training theory test to solve the technical problems existing in the existing technology, such as the rigid learning path and weak interactivity, which lead to low learning efficiency of students and low pass rate of theoretical test.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides a personalized learning system for a driving training theory test, comprising: A personalized learning decision module is used to generate a personalized learning path for a student based on the student's multi-dimensional learning data and the traffic regulations knowledge graph; the personalized learning path includes multiple personalized learning nodes; A multimodal interactive virtual training module is used to provide the student with question analysis through a multimodal interactive method when the student is learning each personalized learning node; the multimodal interactive method includes a voice interactive method and a visual interactive method; The emotional intelligent feedback module is used to determine the student's learning mood based on the student's learning status when learning at each personalized learning node and a preset emotion recognition model, and adjust the teaching style and the content difficulty of the personalized learning node based on the learning mood.

[0007] In a possible implementation, the personalized learning decision module includes a student portrait construction unit and a personalized learning path determination unit; The student portrait construction unit is used to obtain the multidimensional learning data, cluster the multidimensional learning data based on a clustering algorithm to obtain the group category of the students, and input the group category and the multidimensional learning data into a decision tree model to obtain a student portrait; The personalized learning path determination unit is used to determine the starting point of the learning path based on the student portrait, and perform a path search in the traffic regulations knowledge graph based on a graph search algorithm and the starting point of the learning path to obtain the personalized learning path.

[0008] In one possible implementation, the multi-dimensional learning data includes student answering data and learning behavior data. The student answering data includes answering time, accuracy rate and wrong question distribution, and the learning behavior data includes learning time, learning frequency and learning period.

[0009] In a possible implementation, the personalized learning decision module further includes a learning path updating unit; The learning path updating unit is used to obtain real-time learning status data of the student when learning at each personalized learning node, and update the personalized learning path based on the real-time learning status data.

[0010] In a possible implementation, the real-time learning status data includes learning progress and the degree of mastery of knowledge points.

[0011] In a possible implementation, the multimodal interactive virtual training module includes an interactive mode determination unit and a virtual training unit; The interaction mode determination unit is used to determine the multimodal interaction mode based on the learning scenario and the learner's ability to understand the knowledge of the personalized learning node; The virtual training unit is used to provide question analysis for the student based on the multimodal interaction method.

[0012] In a possible implementation, the system further includes a dynamic visual feedback module; The dynamic visual feedback module is used to push anthropomorphic dynamic emoticons and animations in real time according to the student's answering status data; the answering status data includes the number of consecutive correct answers and the number of consecutive incorrect answers.

[0013] In a possible implementation, the system further includes a learning adjustment module; The learning adjustment module is used to push interesting knowledge to the student when the student's learning efficiency decreases while learning along the personalized learning path.

[0014] In one possible implementation, the system further includes a driving test professional knowledge question and answer module; The driving test professional knowledge question and answer module is used to respond to the student's driving test knowledge questions, determine the question intention of the driving test knowledge questions based on RAG technology and historical questions, and determine the question and answer responses corresponding to the driving test knowledge questions based on the question intention.

[0015] In a second aspect, the present invention further provides a personalized learning method for a driving training theory test, which is applicable to the personalized learning system for a driving training theory test described in any one of the possible implementations above, and the method comprises: Generate a personalized learning path for the student based on the student's multi-dimensional learning data and traffic regulations knowledge graph; the personalized learning path includes multiple personalized learning nodes; When the student is learning each of the personalized learning nodes, the student is provided with question analysis through a multimodal interaction method; the multimodal interaction method includes a voice interaction method and a visual interaction method; The learning mood of the student is determined based on the learning state of the student when learning at each personalized learning node and a preset emotion recognition model, and the teaching style and the content difficulty of the personalized learning node are adjusted based on the learning mood.

[0016] The beneficial effects of the present invention are as follows: the personalized learning system for the driving training theory test provided by the present invention realizes the generation of personalized learning paths by setting a personalized decision-making module, can realize the differentiation and personalized customization of learning paths, truly teach students in accordance with their aptitude, improve the adaptability of personalized learning paths to students, and thus improve learning efficiency and improve their theoretical test pass rate. Secondly, the present invention realizes interactivity when learning personalized learning nodes by setting a multimodal interactive virtual training module, so that the training process has an interactive ability similar to that of a real coach, improves the students' understanding of the analysis of the questions, increases the sense of participation in the learning process, and thus can further improve learning efficiency. Further, the present invention realizes the learning emotion perception of students in the learning process of personalized learning nodes by setting an emotional intelligent feedback module, so that the personalized learning system for the driving training theory test has an emotional perception ability similar to that of a real coach, and at the same time, after determining the students' learning emotions, the teaching style and the content difficulty of the personalized learning nodes can be adjusted based on the learning emotions, achieving the purpose of adjusting the learning strategy according to the learning emotions, achieving adaptive optimization in the learning process, effectively improving learning efficiency, and also significantly enhancing the fun of the learning process.

[0017] In summary, this invention enables personalized training throughout the entire process, from learning paths and coaching to feedback. This reduces wasted learning time, improves students' learning efficiency, and ultimately increases the pass rate for theoretical exams. Furthermore, it promotes the transition of driving training systems from traditional teaching models to intelligent, personalized ones, improving the teaching quality of personalized learning systems for driving training theory exams. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 A schematic structural diagram of an embodiment of the personalized learning system for driving training theory test provided by the present invention; Figure 2 This is a flow chart of an embodiment of the personalized learning method for the driving training theory test provided by the present invention. DETAILED DESCRIPTION

[0020] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0021] It should be understood that the schematic drawings are not drawn to scale. The flowcharts used in the present invention illustrate operations implemented according to some embodiments of the present invention. It should be understood that the operations of the flowcharts can be implemented out of sequence, and steps that have no logical contextual relationship can be reversed in order or implemented simultaneously. In addition, those skilled in the art, guided by the content of the present invention, can add one or more other operations to the flowcharts or remove one or more operations from the flowcharts. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and / or processor systems and / or microcontroller systems.

[0022] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0023] The embodiments of the present invention are proposed based on the following problems with existing driving test theory learning systems. First, the learning path in existing driving test theory learning systems is relatively rigid. There are two ways to set the learning path: one is to directly set it as the same learning path for all students, and the other is to generate a learning path based on the learning preferences input by the students, such as difficulty and desired knowledge points. Both methods have in common that the learning path does not change during the subsequent learning process. However, as learning time passes, students' learning interest and attention will fluctuate. The existing technology does not consider this technical problem, resulting in low learning efficiency for students. Second, existing driving test theory learning systems are unable to effectively respond to students' attention when they experience a decrease in attention or other situations, that is, the students' interactive experience is poor. Third, existing driving test theory learning systems use text analysis for question analysis. For some difficult questions, students cannot effectively understand the knowledge points through text analysis alone, which further reduces learning efficiency.

[0024] Based on the above technical problems existing in the prior art, the present invention provides a personalized learning system and method for driving training theory test, which are described below.

[0025] Figure 1 This is a schematic diagram of the embodiment of the personalized learning system for driving training theory test provided by the present invention, as shown in FIG. Figure 1 As shown, the driving training theory test personalized learning system 10 includes: a personalized learning decision module 100, a multimodal interactive virtual training module 200 and an emotional intelligent feedback module 300; The personalized learning decision module 100 is used to generate a personalized learning path for a student based on the student's multi-dimensional learning data and traffic regulations knowledge graph; the personalized learning path includes multiple personalized learning nodes.

[0026] Among them, personalized learning nodes can be different traffic regulations, and the learning content of personalized learning nodes includes but is not limited to video explanations of regulations, special exercises on regulations and simulated exams derived from traffic regulations.

[0027] It should be noted that the personalized learning path also includes the total learning time of the path and the node learning time of each personalized learning node. By setting the personalized learning path to include the total path learning time and the total node learning time, the student's learning progress can be controlled. For example, if there is still one month before the theoretical examination, the total path learning time can be ensured to be less than or equal to one month to ensure that all knowledge is learned before the theoretical examination. At the same time, by setting the total node learning time, a shorter time can be allocated for simple knowledge and a longer time for more difficult knowledge, thereby improving the rationality of time allocation.

[0028] It should be understood that the traffic regulations knowledge graph can be constructed in advance based on traffic regulations.

[0029] The multimodal interactive virtual training module 200 is used to provide students with question analysis through multimodal interaction when they are learning each personalized learning node; the multimodal interaction method includes voice interaction and visual interaction.

[0030] Specifically, the voice interaction method can provide question analysis as follows: after the student answers the question, a voice message such as "This traffic sign question, a triangle with a yellow background and a black border with an exclamation mark, means beware of danger. In actual driving, you must be vigilant when you see this sign!" is generated, simulating the voice of a real coach to achieve the purpose of analyzing the question for the student through voice.

[0031] The visual interaction method can provide question analysis by showing students relevant traffic scene animations. For example, when a traffic police officer gives a no-passing gesture, an animated sign prompting vehicles to pass can be shown in the animation to help students better understand the knowledge points.

[0032] It should be noted that in actual application scenarios, voice interaction and visual interaction methods can be integrated, and relevant traffic scene animations can be displayed simultaneously during voice explanations to further improve students' speed and depth of understanding of knowledge points.

[0033] The emotional intelligent feedback module 300 is used to determine the student's learning mood based on the student's learning status when learning at each personalized learning node and a preset emotion recognition model, and adjust the teaching style and content difficulty of the personalized learning node based on the learning mood.

[0034] In a specific embodiment of the present invention, the emotion recognition model may be a model such as a Long Short-Term Memory (LSTM) network.

[0035] It should be understood that the learning status includes but is not limited to changes in answering speed and fluctuations in error rate. By inputting the learning status into the emotion recognition model, the student's learning mood can be obtained.

[0036] Learning emotions include, but are not limited to, fatigue and confidence. When a student's answering speed slows down significantly and their error rate increases, their learning emotion is fatigue. When a student's answering speed increases and their error rate decreases, their learning emotion is confidence.

[0037] Specifically, when students are experiencing fatigue, the teaching style is adjusted to a gentle one, using gentle, encouraging language to soothe them. The difficulty of the content in personalized learning nodes is reduced, and simple questions are provided to help students rebuild their confidence. When students are experiencing confidence, the teaching style is adjusted to an inspirational one, using motivational language to encourage students to learn more and more difficult content. The difficulty of personalized learning nodes is also increased, helping them to learn deeper knowledge at these learning nodes.

[0038] It should be noted that the architecture of the personalized learning system 10 for the driving training theory test in this embodiment of the present invention consists of a front-end learning app, a back-end server cluster, and a data transmission network. The front-end learning app is used to develop a user-friendly, easy-to-use mobile application, integrating multimodal interaction. It features a simple and intuitive answering interface, a vivid animation display area, and a clear and smooth voice interaction portal, providing students with an immersive learning experience. Furthermore, personalized learning settings are provided, allowing students to customize their virtual driving instructor's voice style, teaching preferences, and other aspects. The back-end server cluster carries out core functions such as model training and inference, data storage and management, and system service scheduling. Distributed storage technology is used to manage student learning data and knowledge graph data, and cloud computing technology is used to achieve efficient model training and fast inference, ensuring that the system can stably and efficiently handle a large number of concurrent learning requests from students. The data transmission network is used to establish a secure and reliable data transmission channel, using encryption technology to ensure the security and integrity of student learning data during transmission. High-speed network technologies such as 5G are used to enable real-time data transmission between the front-end app and the back-end server, ensuring that the virtual driving instructor can promptly respond to student operations and learning needs.

[0039] Compared with the prior art, the driving training theory test personalized learning system 10 provided by the embodiment of the present invention realizes the generation of personalized learning paths by setting a personalized learning decision module 100, which can realize the differentiation and personalized customization of learning paths, truly achieve teaching students in accordance with their aptitude, improve the adaptability of personalized learning paths to students, and thus improve learning efficiency and increase their theoretical test pass rate. Secondly, the embodiment of the present invention realizes interactivity when learning personalized learning nodes by setting a multimodal interactive virtual training module 200, so that the training process has interactive capabilities similar to those of a real coach, improves students' understanding of question analysis, increases their sense of participation in the learning process, and thus further improves learning efficiency. Furthermore, the embodiment of the present invention realizes the perception of students' learning emotions during the learning process of personalized learning nodes by setting an emotional intelligent feedback module 300, so that the driving training theory test personalized learning system has emotional perception capabilities similar to those of a real coach. At the same time, after determining the student's learning emotions, the teaching style and the content difficulty of the personalized learning nodes can be adjusted based on the learning emotions, achieving the purpose of adjusting learning strategies according to learning emotions, realizing adaptive optimization in the learning process, effectively improving learning efficiency, and significantly enhancing the fun of the learning process.

[0040] In summary, the present invention implements personalized training throughout the entire process, from learning paths and coaching to feedback. This reduces wasted learning time, improves students' learning efficiency, and ultimately increases the pass rate for theoretical exams. Furthermore, it promotes the transition of driving training systems from traditional teaching models to intelligent, personalized ones, improving the teaching quality of personalized learning systems for driving training theoretical exams.

[0041] In some embodiments of the present invention, Figure 1 As shown, the personalized learning decision module 100 includes a student portrait construction unit 110 and a personalized learning path determination unit 120; The student portrait construction unit 110 is used to obtain multi-dimensional learning data, and cluster the multi-dimensional learning data based on a clustering algorithm to obtain group categories of students, input the group categories and multi-dimensional learning data into a decision tree model to obtain student portraits.

[0042] The clustering algorithm may be K-Means.

[0043] The group category can be the cluster label for each cluster after clustering. In a specific embodiment of the present invention, the group categories may include high-efficiency (high login frequency, high online time, high practice accuracy, and high grades); high-efficiency (medium-high login frequency, medium-high online time, medium practice accuracy, and medium grades); low-activity (low login frequency, low online time, low practice accuracy, and low grades); and low-efficiency (medium-high login frequency, medium-low online time, low practice accuracy, and low grades).

[0044] Among them, the group category can be set or adjusted in advance according to the actual application scenario and is not specifically limited here.

[0045] The personalized learning path determination unit 120 is used to determine the starting point of the learning path based on the student portrait, and perform path search in the traffic regulations knowledge graph based on the graph search algorithm and the starting point of the learning path to obtain a personalized learning path.

[0046] Among them, the graph search algorithm can be the A-star algorithm.

[0047] It should be noted that to ensure that the personalized learning path matches the exam date, in some embodiments of the present invention, the target learning period must be considered when generating the personalized learning path. The target learning period must be related to the time until the exam. For example, if the exam is 10 days away, the target learning period must be less than or equal to 10 days, that is, the total duration of the personalized learning path must be less than or equal to 10 days.

[0048] The embodiment of the present invention first uses clustering to discover the natural grouping of students from a macro perspective, and then uses a decision tree to deeply explore the micro-feature combinations and key decision-making rules of each group, and finally forms accurate and understandable student portrait labels and descriptions, providing strong data support for the generation of personalized learning paths. It is a key technical means to achieve "teaching students in accordance with their aptitude" and improve learning outcomes.

[0049] In a specific embodiment of the present invention, the multi-dimensional learning data includes student answering data and learning behavior data. The student answering data includes answering time, accuracy rate and wrong question distribution, and the learning behavior data includes learning time, learning frequency and learning period.

[0050] The embodiment of the present invention comprehensively considers the above-mentioned multi-dimensional learning data, further ensuring the matching degree between the developed personalized learning path and the students.

[0051] Since students may not be fully matched with their personalized learning paths due to external factors or different knowledge systems mastered by individuals during their learning process, in order to solve this technical problem, in some embodiments of the present invention, such as Figure 1 As shown, the personalized learning decision module 100 further includes a learning path updating unit 130; The learning path updating unit 130 is used to obtain real-time learning status data of the learner when learning at each personalized learning node, and update the personalized learning path based on the real-time learning status data.

[0052] The embodiment of the present invention realizes dynamic adjustment of the personalized learning path by updating the personalized learning path according to real-time learning status data, ensures the scientificity and adaptability of the personalized learning path, and further improves the learning efficiency of students.

[0053] It should be noted that real-time learning status data includes learning progress and the degree of mastery of knowledge points.

[0054] Among them, learning progress is an adjustment in the time dimension. For example, the total duration of a personalized learning path is 10 days, and each day has a corresponding personalized learning node. If a student does not study on a certain day for various reasons, his or her learning progress is not the expected learning progress. At this time, the personalized learning path will be adjusted to achieve learning of the knowledge of all personalized learning nodes in the personalized learning path.

[0055] The degree of mastery of knowledge points is an adjustment to the dimension of individual knowledge differences. For example, if the personalized learning nodes for fine-related regulations and traffic sign-related regulations in a personalized learning path both have a learning duration of 1 day, and the student understands fine-related regulations quickly but traffic sign-related regulations slowly, the learning duration for the fine-related regulations node can be adjusted to 0.5 days, and the learning duration for the traffic sign-related regulations node can be adjusted to 1.5 days.

[0056] In actual application scenarios, traffic signs such as left turn and right turn are relatively easy to understand. In this case, in order to save resources, there is no need to use both voice interaction and visual interaction to provide students with question analysis. Instead, only voice interaction is needed. For some difficult questions, both voice interaction and visual interaction can be used to provide students with question analysis, thereby improving students' ability to understand the questions. In order to achieve the degree of fit between the multimodal interaction method and the actual situation, in some embodiments of the present invention, such as Figure 1 As shown, the multimodal interactive virtual training module 200 includes an interactive mode determination unit 210 and a virtual training unit 220; The interaction mode determining unit 210 is used to determine the multimodal interaction mode based on the learning scenario and the learner's ability to understand the knowledge of the personalized learning node.

[0057] Specifically, when the learning scenario is simple and the students have a strong ability to understand the knowledge of personalized learning nodes, the multimodal interaction method is voice interaction. When the learning scenario is complex or the students have a weak ability to understand the knowledge of personalized learning nodes, the multimodal interaction method is voice interaction and visual interaction.

[0058] The virtual training unit 220 is used to provide question analysis for students based on a multimodal interaction method.

[0059] The embodiment of the present invention determines the interaction mode according to the two dimensions of the learning scenario and the student's ability to understand the knowledge of the personalized learning node, thereby improving the adaptability of the interaction mode to the student, ensuring that the student understands the questions while avoiding resource waste.

[0060] In order to further improve students' learning enthusiasm, in some embodiments of the present invention, Figure 1 As shown, the driving training theory test personalized learning system 10 also includes a dynamic visual feedback module 400; The dynamic visual feedback module 400 is used to push anthropomorphic dynamic emoticons and animations in real time based on the student's answering status data; the answering status data includes the number of consecutive correct answers and the number of consecutive incorrect answers.

[0061] Specifically, when students answer questions correctly continuously, encouraging animations such as likes and cheers will be displayed on the interactive interface; when they answer questions incorrectly continuously, motivational dynamic icons such as "Come on" and "Think" will be displayed on the interactive interface to enhance the interest of learning and emotional resonance.

[0062] The embodiment of the present invention can enhance the interest and emotional resonance in the learning process by providing a dynamic visual feedback module 400, thereby improving students' learning enthusiasm and further improving learning efficiency.

[0063] After studying for a long time, the learning efficiency of students will decrease. To solve this technical problem, in some embodiments of the present invention, Figure 1 As shown, the driving training theory test personalized learning system 10 also includes a learning adjustment module 500; The learning adjustment module 500 is used to push interesting knowledge to the student when the student's learning efficiency decreases while learning along the personalized learning path.

[0064] Among them, interesting knowledge includes but is not limited to interesting knowledge about traffic regulations and driving safety, etc., which can relieve learning pressure, adjust learning status and improve learning enthusiasm.

[0065] The above modules are all passive learning, that is, students learn based on the generated personalized learning path. In the actual learning process, students often have questions about the questions. Therefore, in order to achieve active learning of students, in some embodiments of the present invention, such as Figure 1 As shown, the driving training theory test personalized learning system 10 also includes a driving test professional knowledge question and answer module 600; The driving test professional knowledge question and answer module 600 is used to respond to students' driving test knowledge questions, determine the question intention of the driving test knowledge questions based on RAG technology and historical questions, and determine the question and answer responses corresponding to the driving test knowledge questions based on the question intention.

[0066] Among them, the questions about driving test knowledge can be asked in the form of text or voice, which increases its diversity.

[0067] The embodiment of the present invention supports students' active learning by providing a method for replying to students' questions, further improving students' learning enthusiasm and learning efficiency, thereby further improving the pass rate of theoretical examinations.

[0068] In summary, the personalized learning system for driving training theory exams provided by the embodiments of the present invention 1. Significantly improves learning efficiency and exam pass rate: through the personalized learning guidance and dynamic learning path planning of virtual coaches, students can focus on their weak knowledge points, avoid ineffective learning, and effectively help students master driving training theory knowledge quickly and efficiently. 2. Enhances learning experience and enthusiasm: The multimodal emotional interaction design makes the learning process interesting and interactive, and the real-time encouragement and personalized guidance of virtual coaches can effectively relieve students' learning pressure and enhance their learning confidence and enthusiasm. 3. Promotes the intelligent upgrade of the driving training industry: The embodiments of the present invention provide a new intelligent learning solution for the driving training industry, promote the in-depth application of AI technology in the field of driving training, and promote the transformation of the driving training industry from the traditional teaching model to the intelligent and personalized teaching model, thereby improving the overall teaching quality and service level of the industry.

[0069] Correspondingly, the embodiment of the present invention further provides a personalized learning method for driving training theory test, which is applicable to the personalized learning system for driving training theory test in any of the above embodiments, such as Figure 2 As shown, the personalized learning methods for the driving training theory test include: S201. Generate a personalized learning path for the student based on the student's multi-dimensional learning data and traffic regulations knowledge graph; the personalized learning path includes multiple personalized learning nodes; S202: When students are learning each personalized learning node, the system provides them with question analysis through multimodal interaction, which includes voice interaction and visual interaction. S203: Determine the student's learning mood based on the student's learning status when learning at each personalized learning node and a preset emotion recognition model, and adjust the teaching style and the content difficulty of the personalized learning node based on the learning mood.

[0070] It should be noted that the personalized learning method for the driving training theory test provided in the above embodiment can implement the technical solution described in the above embodiment of the personalized learning system for the driving training theory test. The principles or specific implementation details of the above steps can be found in the corresponding content in the above embodiment of the personalized learning system for the driving training theory test, and will not be described one by one here.

[0071] Those skilled in the art will appreciate that all or part of the process flow of the above-described method embodiment can be implemented by instructing related hardware (such as a processor, controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a magnetic disk, an optical disk, a read-only memory, or a random access memory.

[0072] The above is a detailed introduction to a personalized learning system and method for a driving training theory test provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A personalized learning system for driving training theory test, characterized by: include: A personalized learning decision module, configured to generate a personalized learning path for a student based on the student's multi-dimensional learning data and traffic regulations knowledge graph; The personalized learning path includes multiple personalized learning nodes; A multimodal interactive virtual training module is used to provide the student with question analysis through a multimodal interactive method when the student is learning each personalized learning node; the multimodal interactive method includes a voice interactive method and a visual interactive method; The emotional intelligent feedback module is used to determine the student's learning mood based on the student's learning status when learning at each personalized learning node and a preset emotion recognition model, and adjust the teaching style and the content difficulty of the personalized learning node based on the learning mood.

2. The personalized learning system for driving training theory test according to claim 1 is characterized in that: The personalized learning decision module includes a student portrait construction unit and a personalized learning path determination unit; The student portrait construction unit is used to obtain the multidimensional learning data, cluster the multidimensional learning data based on a clustering algorithm to obtain the group category of the students, and input the group category and the multidimensional learning data into a decision tree model to obtain a student portrait; The personalized learning path determination unit is used to determine the starting point of the learning path based on the student portrait, and perform a path search in the traffic regulations knowledge graph based on a graph search algorithm and the starting point of the learning path to obtain the personalized learning path.

3. The personalized learning system for driving training theory test according to claim 1 or 2, characterized in that: The multi-dimensional learning data includes student answering data and learning behavior data. The student answering data includes answering time, accuracy rate and wrong question distribution. The learning behavior data includes learning time, learning frequency and learning period.

4. The personalized learning system for driving training theory test according to claim 1 is characterized in that: The personalized learning decision module also includes a learning path updating unit; The learning path updating unit is used to obtain real-time learning status data of the student when learning at each personalized learning node, and update the personalized learning path based on the real-time learning status data.

5. The personalized learning system for driving training theory test according to claim 4 is characterized in that: The real-time learning status data includes learning progress and the degree of mastery of knowledge points.

6. The personalized learning system for driving training theory test according to claim 1 is characterized in that: The multimodal interactive virtual training module includes an interactive mode determination unit and a virtual training unit; The interaction mode determination unit is used to determine the multimodal interaction mode based on the learning scenario and the learner's ability to understand the knowledge of the personalized learning node; The virtual training unit is used to provide question analysis for the student based on the multimodal interaction method.

7. The personalized learning system for driving training theory test according to claim 1 is characterized in that: The system also includes a dynamic visual feedback module; The dynamic visual feedback module is used to push anthropomorphic dynamic emoticons and animations in real time according to the student's answering status data; the answering status data includes the number of consecutive correct answers and the number of consecutive incorrect answers.

8. The personalized learning system for driving training theory test according to claim 1 is characterized in that: The system also includes a learning adjustment module; The learning adjustment module is used to push interesting knowledge to the student when the student's learning efficiency decreases while learning along the personalized learning path.

9. The personalized learning system for driving training theory test according to claim 1 is characterized in that: The system also includes a driving test professional knowledge question and answer module; The driving test professional knowledge question and answer module is used to respond to the student's driving test knowledge questions, determine the question intention of the driving test knowledge questions based on RAG technology and historical questions, and determine the question and answer responses corresponding to the driving test knowledge questions based on the question intention.

10. A personalized learning method for driving training theory test, characterized by: The personalized learning system for driving training theory test according to any one of claims 1 to 9, wherein the method comprises: Generate a personalized learning path for the student based on the student's multi-dimensional learning data and traffic regulations knowledge graph; the personalized learning path includes multiple personalized learning nodes; When the student is learning each of the personalized learning nodes, the student is provided with question analysis through a multimodal interaction method; the multimodal interaction method includes a voice interaction method and a visual interaction method; The learning mood of the student is determined based on the learning state of the student when learning at each personalized learning node and a preset emotion recognition model, and the teaching style and the content difficulty of the personalized learning node are adjusted based on the learning mood.

Images