Novel learning method based on time management

Abstract

The invention discloses a novel learning method based on time management, relates to the field of educational training and time management, and mainly solves the problems that the learning forms are not concentrated, the learning efficiency is low and the systematicness of the learning process is poor. Designing an intelligent learning path for the user; dynamically adjusting the learning time of the user; personalized content pushing is provided for the user; social contact and learning among the users are enhanced; learning achievement evaluation and system feedback are carried out, and learning resources in different forms are integrated through a multi-modal learning platform so as to meet learning requirements of different users; the learning time of the user is adjusted in real time through the time dynamic management module, so that the learning efficiency of the user is improved; related learning resources are recommended to the user through an intelligent recommendation algorithm, so that systematic learning of the user is met.

Description

Technical Field

[0001] The present invention relates to the technical field of education training and time management, and in particular to a new learning method based on time management. Background Art

[0002] With the rapid development of the Internet and digital media, learning resources are unprecedentedly abundant. From online courses to virtual laboratories, learners can obtain the knowledge they need anytime and anywhere. At the same time, with the growing offline sales team and the rapid development of the company's business, the popularization and promotion of technology applications in the sales team is particularly important. However, the traditional centralized learning method is often limited by time and place, and it is difficult to adapt to the busy work rhythm of sales staff. Therefore, how to effectively use fragmented time and learn through scientific time management methods has become the key to improving the overall quality of the sales team. In the existing learning methods, the learning form is too scattered and cannot meet the learning needs of different users; in the existing learning methods, there is a lack of management of learning time, rhythm and plan, which affects learning efficiency; in the existing learning methods, when recommending content to users, it is impossible to accurately push it according to user needs, and the learning system is too scattered.

[0003] Therefore, the present invention provides a new learning method based on time management, which integrates different forms of learning resources through a multimodal learning platform to meet the learning needs of different users; adjusts the user's learning time in real time through a time dynamic management module to improve the user's learning efficiency; and recommends relevant learning resources to users through an intelligent recommendation algorithm to meet the user's systematic learning needs. Summary of the invention

[0004] The purpose of the present invention is to solve the problems of unfocused learning, low learning efficiency and poor systematicness of learning process in the prior art, and to propose a new learning method based on time management.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A new learning method based on time management includes the following steps:

[0007] Step 1: Integrate multimodal learning resources;

[0008] Integrate learning materials in the form of text, audio, video, animation and interactive simulation through a multimodal learning platform to meet the learning needs of different users;

[0009] Step 2: Design intelligent learning paths for users;

[0010] The learning path planning module designs intelligent learning paths for users and dynamically adjusts learning content based on user needs and learning progress to help users plan long-term learning goals and integrate career development paths;

[0011] Step 3: Dynamically adjust user learning time;

[0012] Adjust the user's study time in real time through the time dynamic management module and the user's work schedule, study habits and efficiency cycle to ensure efficient use of study time;

[0013] Step 4: Provide personalized content push to users;

[0014] The content recommendation module deeply analyzes user behavior and learning content, and recommends relevant learning resources to users to enhance their learning experience and enthusiasm;

[0015] Step 5: Strengthen social interaction and learning among users;

[0016] Introducing social elements through interactive collaboration modules to encourage interaction and collaboration between users to improve learning outcomes through discussion and shared experiences;

[0017] Step 6: Learning outcome evaluation and system feedback;

[0018] The platform evaluates user learning outcomes through the assessment and feedback module and provides users with learning effect analysis to adjust learning paths and time management strategies.

[0019] As a further description of the above technical solution, the multimodal learning platform includes a user interface, a content selection unit, a device support unit and a privacy protection unit. The user interface uses the front-end framework React and hypertext markup language HTML to provide users with an interactive interface with the platform to achieve interaction between users and the platform; the content selection unit collects text, audio, video, animation and interactive simulation types of learning materials through the database MySQL, server-side language Python and API interface to achieve different learning styles and needs; the device support unit uses the cross-platform mobile application development framework React Native to adapt the user interface to different device screens, including mobile phones, tablets and PCs; the privacy protection unit protects user data from illegal access through the SSL / TLS protocol to protect user data information security.

[0020] As a further description of the above technical solution, the learning path planning module includes a learning goal setting unit, an intelligent path generation unit and a learning progress tracking unit. The learning goal setting unit sets the user's short-term and long-term learning goals through a questionnaire survey; the intelligent path generation unit plans the optimal learning path through the Dijkstra algorithm; the learning progress tracking unit stores the user's learning data through MongoDB, and tracks the progress of the user's learning activities, completed courses and test scores.

[0021] As a further description of the above technical solution, the time dynamic management module includes a schedule synchronization unit, a dynamic adjustment unit and a notification unit. The schedule synchronization unit synchronizes schedules between different devices and platforms in real time through the cloud server storage center to balance the user's work and study time; the dynamic adjustment unit uses AI intelligent analysis of the user's current availability and work status, and adjusts the study plan and schedule in real time to efficiently utilize the user's fragmented time; the notification unit reminds the user of schedule matters through application push and SMS.

[0022] As a further description of the above technical solution, the content recommendation module includes a user portrait unit, a preference analysis unit and a push unit. The user portrait unit describes the characteristics of the user portrait by analyzing the user's learning history, browsing content records and behavior patterns; the preference analysis unit predicts and identifies the user's potential preferences through an intelligent recommendation algorithm to provide the user with more comprehensive knowledge; the push unit pushes personalized learning content through a platform interactive page, the output end of the user portrait unit is connected to the input end of the preference analysis unit, and the output end of the preference analysis unit is connected to the input end of the push unit.

[0023] As a further description of the above technical solution, the implementation steps of the intelligent recommendation algorithm are:

[0024] a) Data collection and preprocessing

[0025] Collect user behavior data, including articles, pictures, videos and interactive content viewed by users, and perform data cleaning on the collected data, including removing outliers and filling missing values, to ensure the integrity and accuracy of the data;

[0026] b) User project matrix construction

[0027] Create a user-item matrix, where each row represents a user and each column represents a learning item. The values ​​in the matrix represent the interaction intensity between the user and the item, and process the high-dimensional sparse matrix through matrix decomposition;

[0028] c) Similarity calculation

[0029] The similarity between the user and the learning item is calculated by a similarity comparison function, and the formula expression of the similarity comparison function is:

[0030]

[0031] In formula (1), T i represents the similarity comparison function, α i represents the similarity between users, β i represents the similarity between items, ρ represents the function similarity comparison factor, i represents the function comparison order, and n represents the function comparison order termination value. Represents the function similarity comparison coefficient;

[0032] d) Prediction score

[0033] For the target user, find the K users most similar to him / her, and predict the target user's rating based on these users' ratings of the unrated learning items. At the same time, for the unrated items of the target user, find the K items most similar to the items, and predict the target user's rating of the unrated items based on the target user's ratings of these items.

[0034] e) Recommendation generation

[0035] Sort all unrated items by predicted score, and select the N items with the highest scores as the recommendation list;

[0036] f) Result evaluation and optimization

[0037] The recommendation effect is evaluated according to the evaluation function, and the algorithm parameters are adjusted by the similarity threshold to optimize the recommendation effect. The formula expression of the evaluation function is:

[0038]

[0039] In formula (2), P represents the evaluation function, N represents the total number of items to be evaluated, p represents the order of the items to be evaluated, and μ p represents the user's true rating of item p, γ p represents the user's predicted rating for item p, represents the item scoring error;

[0040] g) Real-time updates and feedback

[0041] Based on the user's real-time behavior data, the user-item matrix is ​​updated and user feedback on recommended content is collected for algorithm model iteration and optimization.

[0042] As a further description of the above technical solution, the interactive collaboration module includes a document sharing unit, a forum discussion unit and a module management unit. The document sharing unit realizes collaborative editing through the API interface of the cloud storage service to improve team collaboration efficiency; the forum discussion unit provides a discussion platform through the client group system to promote the sales team's work efficiency and service level; the module management unit reviews and manages the pictures and video content posted by users through natural language processing NLP to provide users with a safe and reliable learning environment.

[0043] As a further description of the above technical solution, the evaluation and feedback module includes an evaluation unit, a personalized feedback unit and a strategy optimization unit. The evaluation unit analyzes the user's learning performance and progress by collecting user tests and performance results; the personalized feedback unit sends the evaluation results to the user in the form of a personalized report; the strategy optimization unit integrates the evaluation results and feedback information through a machine learning algorithm to optimize the user's learning content, process and time. The output end of the evaluation unit is connected to the input end of the personalized feedback unit, and the output end of the personalized feedback unit is connected to the input end of the strategy optimization unit.

[0044] Compared with the prior art, the present invention provides a new learning method based on time management, which has the following beneficial effects.

[0045] 1. The present invention integrates different forms of learning resources through a multimodal learning platform to meet the learning needs of different users.

[0046] 2. The present invention adjusts the user's learning time in real time through a time dynamic management module to improve the user's learning efficiency.

[0047] 3. The present invention recommends relevant learning resources to users through an intelligent recommendation algorithm to meet the users' systematic learning needs.

[0048] Other advantages, objectives and features of the present invention will be described in part in the following description; and in part, will be apparent to those skilled in the art based on an examination of the following; or, may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to understand and grasp the technical solution more intuitively and clearly, when describing the embodiments of the present invention or the prior art, drawings are often used to supplement and illustrate. It should be noted that the drawings are only one way of expressing the embodiments of the present invention or the prior art. In fact, the technical solution can also have other implementation methods and changes, which all fall within the protection scope of the present invention. Therefore, technicians can design other drawings as needed to implement the technical solution of the present invention, among which,

[0050] Figure 1 The figure is a schematic diagram of the steps of implementing the process of the present invention.

[0051] Figure 2 Schematic diagram of the structure of the multimodal platform of the present invention.

[0052] Figure 3 It is a structural diagram of the time dynamic management module of the present invention.

[0053] Figure 4 It is a structural schematic diagram of the content recommendation module of the present invention.

[0054] Figure 5 Schematic diagram of the steps of the intelligent recommendation algorithm of the present invention.

[0055] Figure 6 It is a schematic diagram of the structure of the evaluation and feedback module of the present invention. DETAILED DESCRIPTION

[0056] The following will clearly and completely describe the technical solutions in the embodiments of this invention through the accompanying drawings in the embodiments of this invention. Obviously, the described embodiments are only part of the embodiments of this invention, not all of the embodiments. At the same time, the description of well-known structures and technologies is omitted in the following description to avoid unnecessary confusion of the concepts of the present invention.

[0057] like Figure 1-Figure 6 As shown in the figure, a new learning method based on time management includes the following steps:

[0058] Step 1: Integrate multimodal learning resources;

[0059] Integrate learning materials in the form of text, audio, video, animation and interactive simulation through a multimodal learning platform to meet the learning needs of different users;

[0060] Step 2: Design intelligent learning paths for users;

[0061] The learning path planning module designs intelligent learning paths for users and dynamically adjusts learning content based on user needs and learning progress to help users plan long-term learning goals and integrate career development paths;

[0062] Step 3: Dynamically adjust user learning time;

[0063] Adjust the user's study time in real time through the time dynamic management module and the user's work schedule, study habits and efficiency cycle to ensure efficient use of study time;

[0064] Step 4: Provide personalized content push to users;

[0065] The content recommendation module deeply analyzes user behavior and learning content, and recommends relevant learning resources to users to enhance their learning experience and enthusiasm;

[0066] Step 5: Strengthen social interaction and learning among users;

[0067] Introducing social elements through interactive collaboration modules to encourage interaction and collaboration between users to improve learning outcomes through discussion and shared experiences;

[0068] Step 6: Learning outcome evaluation and system feedback;

[0069] The platform evaluates user learning outcomes through the assessment and feedback module and provides users with learning effect analysis to adjust learning paths and time management strategies.

[0070] In the above embodiment, the multimodal learning platform includes a user interface, a content selection unit, a device support unit and a privacy protection unit. The user interface uses the front-end framework React and hypertext markup language HTML to provide users with an interactive interface with the platform to achieve interaction between users and the platform; the content selection unit collects text, audio, video, animation and interactive simulation types of learning materials through the database MySQL, server-side language Python and API interface to achieve different learning styles and needs; the device support unit uses the cross-platform mobile application development framework React Native to adapt the user interface to different device screens, including mobile phones, tablets and PCs; the privacy protection unit protects user data from illegal access through the SSL / TLS protocol to protect user data information security.

[0071] In a specific embodiment, the multimodal learning platform is composed of four core modules: the user interface, the content selection unit, the device support unit and the privacy protection unit, which together build a seamless, safe and personalized learning environment. The user interface adopts the cutting-edge front-end framework React and hypertext markup language HTML to ensure the responsiveness and visual effects of the interface. This design not only improves the user experience, but also realizes the intuitive interaction between the user and the platform, making the learning process smoother and more natural. The content selection unit efficiently stores and manages massive learning resources through the database MySQL, and combines the server-side language Python and API interface to realize the intelligent classification and integration of multiple types of learning materials such as text, audio, video, animation and interactive simulation. This unit not only meets different learning styles and needs, but also customizes the learning path for each user through the intelligent recommendation algorithm, making personalized learning possible. The device support unit ensures the perfect adaptation of the user interface on different devices through the cross-platform mobile application development framework React Native, so that whether it is a mobile phone, tablet or PC, you can enjoy a consistent learning experience. This design breaks the device restrictions and allows learning to happen anytime, anywhere, without being bound by space. The privacy protection unit protects user data security through the SSL / TLS protocol. It encrypts all data transmission processes, effectively preventing data leakage during transmission and ensuring the absolute security of user information. This measure allows users to enjoy convenient learning while also feeling the platform's respect and protection for personal privacy. It improves the learning efficiency and effectiveness of sales staff and promotes the improvement of the sales team's operational efficiency and service level.

[0072] In the above embodiment, the learning path planning module includes a learning goal setting unit, an intelligent path generation unit and a learning progress tracking unit. The learning goal setting unit sets the user's short-term and long-term learning goals through a questionnaire survey; the intelligent path generation unit plans the optimal learning path through the Dijkstra algorithm; the learning progress tracking unit stores the user's learning data through MongoDB, and tracks the user's learning activities, completed courses and test scores.

[0073] In a specific embodiment, the learning path planning module jointly constructs a personalized learning navigation system by combining the learning goal setting unit, the intelligent path generation unit and the learning progress tracking unit. The learning goal setting unit first deeply explores the learning needs and interests of each user through a series of carefully designed questionnaires, which is not limited to short-term skill improvement, but also focuses on long-term career planning and knowledge system construction. In this link, users can clearly outline the learning blueprint of sales personnel and clarify the direction of progress. The intelligent path generation unit uses the Dijkstra algorithm, a classic path search technology, to combine the learning goals set by the user to select the optimal learning path from the learning resources. This algorithm can be dynamically adjusted to optimize the path in real time according to the user's learning progress and feedback, ensuring that each step points to the goal while taking into account efficiency and effect. The learning progress tracking unit relies on MongoDB, a high-performance database, to record the user's learning activities in all aspects, from participation in each course to analysis of test scores, and the formation of learning habits. Through deep mining of data, the system can intelligently identify the user's learning bottlenecks and advantages, adjust the learning strategy in time, and ensure that each user can steadily move forward in the rhythm that best suits him or her. The learning path planning module not only makes the learning process targeted and planned, but also makes personalized learning possible through the application of intelligent technology, providing the sales team with a safe, reliable and efficient learning environment, thereby promoting the company's business development and improving its market competitiveness.

[0074] In the above embodiment, the time dynamic management module includes a schedule synchronization unit, a dynamic adjustment unit and a notification unit. The schedule synchronization unit synchronizes schedules between different devices and platforms in real time through a cloud server storage center to balance the user's work and study time; the dynamic adjustment unit uses AI to intelligently analyze the user's current availability and work status, and adjusts the study plan and schedule in real time to efficiently utilize the user's fragmented time; the notification unit reminds the user of schedule matters through application push and text messages.

[0075] In a specific embodiment, in today's fast-paced and efficient era, the time dynamic management module, as a powerful assistant for personal life and work management, is using innovative scientific and technological means to create a personalized and intelligent time management solution for users. The schedule synchronization unit relies on the advanced cloud server storage center to achieve real-time schedule synchronization across devices and platforms. No matter where the user is, with just a click, you can seamlessly switch between mobile phones, computers, tablets and other devices to view or adjust your schedule. This function not only breaks the limitations of physical space, but also builds a bridge between work and study, ensuring that users find a balance in their busy lives and plan every minute reasonably. The dynamic adjustment unit, based on deep learning and analysis of AI technology, can intelligently evaluate the user's current availability and work status, and then adjust the learning plan and schedule in real time. It can identify the user's fragmented time, such as commuting, waiting, etc., and transform these "micro time" into efficient learning or rest opportunities to maximize time utilization. Through dynamic adjustment, make full use of fragmented time for learning and improve overall business quality. The notification unit reminds users of upcoming schedules in a timely manner through application push and SMS. Whether it is a meeting, course, or personal affairs, users can receive notifications at the first time to avoid missing any important moments. The diversified reminder methods of the notification unit ensure the timeliness and accuracy of information transmission, allowing users to maintain a clear sense of time even when they are busy. The time dynamic management module builds a comprehensive and intelligent time management system with three core functions: schedule synchronization, dynamic adjustment and notification. It not only helps users manage their schedules efficiently, but also realizes the personalization and intelligence of time utilization through the deep involvement of AI technology, so that every user can find their own balance point in the fast-paced life and enjoy the convenience and freedom brought by time management.

[0076] In the above embodiment, the content recommendation module includes a user portrait unit, a preference analysis unit and a push unit. The user portrait unit describes the characteristics of the user portrait by analyzing the user's learning history, browsing content records and behavior patterns; the preference analysis unit predicts and identifies the user's potential preferences through an intelligent recommendation algorithm to provide the user with more comprehensive knowledge; the push unit pushes personalized learning content through a platform interactive page, and the output end of the user portrait unit is connected to the input end of the preference analysis unit, and the output end of the preference analysis unit is connected to the input end of the push unit.

[0077] In a specific embodiment, the user portrait unit is the basis of the entire recommendation system. It deeply analyzes the user's learning history, such as course completion, learning time, participation, etc., combined with the user's browsing content records, including browsing frequency, dwell time, click depth, etc., and the user's behavior pattern, such as learning time period preference, learning method selection, etc., to describe the user's multi-dimensional and three-dimensional characteristics. This process not only captures the user's current learning interests and needs, but also provides insight into the user's potential interests; the preference analysis unit uses the intelligent recommendation algorithm based on the user portrait to predict and identify the user's potential preferences. The intelligent recommendation algorithm can mine content that matches the user's interests from a large amount of learning resources. At the same time, through continuous learning and self-optimization, the preference analysis unit can continuously adjust and optimize the recommendation strategy as the user's learning behavior evolves, ensure the accuracy and novelty of the recommended content, and provide users with more comprehensive and in-depth knowledge exploration. The push unit will accurately push the carefully screened and personalized learning content to users through the platform's interactive pages, such as home page recommendations, learning path suggestions, course cards, etc. Intelligent adjustment of push time, frequency and form ensures that users receive the content they are most interested in at the most appropriate time and in the most appropriate way, greatly improving their learning experience and efficiency. Through this series of intelligent operations, the content recommendation module not only meets the learning needs of users, but also stimulates their learning interest, providing users with a personalized, high-quality learning experience.

[0078] In the above embodiment, the implementation steps of the intelligent recommendation algorithm are:

[0079] a) Data collection and preprocessing

[0080] Collect user behavior data, including articles, pictures, videos and interactive content viewed by users, and perform data cleaning on the collected data, including removing outliers and filling missing values, to ensure the integrity and accuracy of the data;

[0081] b) User project matrix construction

[0082] Create a user-item matrix, where each row represents a user and each column represents a learning item. The values ​​in the matrix represent the interaction intensity between the user and the item, and process the high-dimensional sparse matrix through matrix decomposition;

[0083] c) Similarity calculation

[0084] The similarity between the user and the learning item is calculated by a similarity comparison function, and the formula expression of the similarity comparison function is:

[0085]

[0086] In formula (1), T i represents the similarity comparison function, α i represents the similarity between users, β i represents the similarity between items, ρ represents the function similarity comparison factor, i represents the function comparison order, and n represents the function comparison order termination value. Represents the function similarity comparison coefficient;

[0087] d) Prediction score

[0088] For the target user, find the K users most similar to him / her, and predict the target user's rating based on these users' ratings of the unrated learning items. At the same time, for the unrated items of the target user, find the K items most similar to the items, and predict the target user's rating of the unrated items based on the target user's ratings of these items.

[0089] e) Recommendation generation

[0090] Sort all unrated items by predicted score, and select the N items with the highest scores as the recommendation list;

[0091] f) Result evaluation and optimization

[0092] The recommendation effect is evaluated according to the evaluation function, and the algorithm parameters are adjusted by the similarity threshold to optimize the recommendation effect. The formula expression of the evaluation function is:

[0093]

[0094] In formula (2), P represents the evaluation function, N represents the total number of items to be evaluated, p represents the order of the items to be evaluated, and μ p represents the user's true rating of item p, γ p represents the user's predicted rating for item p, represents the item scoring error;

[0095] g) Real-time updates and feedback

[0096] Based on the user's real-time behavior data, the user-item matrix is ​​updated and user feedback on recommended content is collected for algorithm model iteration and optimization.

[0097] In a specific embodiment, the role of the intelligent recommendation algorithm is to predict new content or projects that users may be interested in by analyzing the user's historical behavior and preferences, thereby providing personalized recommendation services. The steps involved in implementing the intelligent recommendation system include: data collection and preprocessing, building a user-project matrix, using matrix decomposition, similarity calculation, and predictive scoring algorithms to generate a recommendation list, and ensuring the accuracy and timeliness of recommendations through continuous optimization and real-time updates. The intelligent recommendation algorithm solves the problem of information overload, helping users quickly find projects that they may be interested in among a large amount of optional content; improves user experience by providing customized content recommendations, saving users time and energy in finding information; increases the visibility and user stickiness of content providers. Through the recommendation algorithm, content providers can better match user interests and improve content acceptance and dissemination effects. The similarity comparison function calculates the similarity α between all users. i , the similarity between items β i , function similarity contrast factor ρ and function similarity contrast coefficient Calculate the similarity between the user and the learning project to determine the user's interest preference; the evaluation function is based on the user's real score μ for the project p p , the user's predicted rating γ for item p p and item rating error The recommendation effect is evaluated, and the algorithm parameters are adjusted through the similarity threshold to optimize the recommendation effect. At the same time, the difference between the intelligent recommendation algorithm and the traditional recommendation algorithm is shown in Table 1:

[0098] Table 1 Differences between intelligent recommendation algorithms and traditional algorithms

[0099]

[0100] In summary, the accuracy and recall rate of the intelligent recommendation algorithm are better than those of the traditional recommendation algorithm. It can be seen that the intelligent recommendation algorithm is the best choice for the present invention.

[0101] In the above embodiment, the interactive collaboration module includes a document sharing unit, a forum discussion unit and a module management unit. The document sharing unit realizes collaborative editing through the API interface of the cloud storage service to improve the efficiency of team collaboration; the forum discussion unit provides a discussion platform through the client group system to promote the work efficiency and service level of the sales team; the module management unit reviews and manages the pictures and video content posted by users through natural language processing NLP to provide users with a safe and reliable learning environment.

[0102] In a specific embodiment, the document sharing unit realizes real-time sharing and collaborative editing of documents by seamlessly connecting with the top cloud storage service and using its powerful API interface. Team members can access, edit and save documents anytime and anywhere, greatly improving the efficiency of team collaboration. This function is particularly suitable for cross-regional project teams to ensure real-time synchronization and efficient circulation of information. The forum discussion unit relies on the independently developed client group system to provide a professional and efficient discussion platform for the sales team. Here, team members can share sales skills and discuss market trends to improve operational efficiency and service levels. The real-time and interactive nature of the forum promotes internal communication and knowledge sharing within the team, optimizes sales strategies, and improves team cohesion. The module management unit uses cutting-edge natural language processing (NLP) technology to perform intelligent review and management of pictures and video content uploaded by users. NLP technology can identify and filter inappropriate or sensitive content, ensure the purity and security of the platform, and create a healthy and positive learning and communication environment for users. This function not only guarantees the quality of platform content, but also reflects our high attention to user safety and experience. In summary, the interactive collaboration module builds an efficient and secure collaboration platform through the three functions of document sharing, forum discussion and content review. It not only improves team collaboration efficiency and promotes the sharing of knowledge and experience, but also creates a safe and reliable learning and communication space for users.

[0103] In the above embodiment, the evaluation and feedback module includes an evaluation unit, a personalized feedback unit and a strategy optimization unit. The evaluation unit analyzes the user's learning performance and progress by collecting user tests and performance results; the personalized feedback unit sends the evaluation results to the user in the form of a personalized report; the strategy optimization unit integrates the evaluation results and feedback information through a machine learning algorithm to optimize the user's learning content, process and time. The output end of the evaluation unit is connected to the input end of the personalized feedback unit, and the output end of the personalized feedback unit is connected to the input end of the strategy optimization unit.

[0104] In a specific embodiment, the evaluation unit collects and analyzes the performance of users in various tests, homework and daily learning in real time through intelligent algorithms, including not only quantitative indicators such as accuracy and completion, but also deeply mines behavioral data in the learning process, such as problem-solving time, knowledge point mastery, learning preferences, etc., to comprehensively evaluate the user's learning status and progress trajectory. The personalized feedback unit generates a personalized learning report for each user based on the analysis results of the evaluation unit. The report not only presents the learning results, but also deeply analyzes the weaknesses and advantages in the learning process, provides targeted improvement suggestions, and ensures that users receive feedback in time through multiple channels such as emails and APP notifications, stimulates learning motivation, and clarifies the direction of efforts. The strategy optimization unit uses advanced machine learning algorithms to integrate evaluation results and user feedback, intelligently optimize learning strategies, and dynamically adjust course content, learning paths and review plans according to each user's learning habits, progress and effects, to ensure accurate matching of learning content, efficient advancement of learning process, and reasonable planning of learning time. Through the operation of the evaluation and feedback module, a closed loop from data collection to personalized feedback and then to strategy optimization is realized, providing users with a dynamically adjusted and continuously optimized learning environment.

[0105] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

[0106] In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples without contradiction.

[0107] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A new learning method based on time management, characterized in that: The steps include: Step 1: Integrate multimodal learning resources; Integrate learning materials in the form of text, audio, video, animation and interactive simulation through a multimodal learning platform to meet the learning needs of different users; Step 2: Design intelligent learning paths for users; The learning path planning module designs intelligent learning paths for users and dynamically adjusts learning content based on user needs and learning progress to help users plan long-term learning goals and integrate career development paths; Step 3: Dynamically adjust user learning time; Adjust user learning time in real time through the time dynamic management module and the user's work schedule, learning habits and efficiency cycle to ensure efficient use of learning time; Step 4: Provide personalized content push to users; The content recommendation module deeply analyzes user behavior and learning content, and recommends relevant learning resources to users to enhance their learning experience and enthusiasm; Step 5: Strengthen social interaction and learning among users; Introducing social elements through interactive collaboration modules to encourage interaction and collaboration between users to improve learning outcomes through discussion and shared experiences; Step 6: Learning outcome evaluation and system feedback; The platform evaluates user learning outcomes through the assessment and feedback module and provides users with learning effect analysis to adjust learning paths and time management strategies.

2. A new learning method based on time management according to claim 1, characterized in that: The multimodal learning platform includes a user interface, a content selection unit, a device support unit and a privacy protection unit. The user interface uses the front-end framework React and the hypertext markup language HTML to provide users with an interactive interface with the platform to achieve interaction between users and the platform; The content selection unit collects text, audio, video, animation and interactive simulation types of learning materials through the database MySQL, server-side language Python and API interface to achieve different learning styles and needs; the device support unit adapts the user interface to different device screens, including mobile phones, tablets and PCs, through the cross-platform mobile application development framework React Native; the privacy protection unit protects user data from illegal access through the SSL / TLS protocol to protect user data information security.

3. A new learning method based on time management according to claim 1, characterized in that: The learning path planning module includes a learning goal setting unit, an intelligent path generation unit and a learning progress tracking unit. The learning goal setting unit sets the user's short-term and long-term learning goals through a questionnaire survey; the intelligent path generation unit plans the optimal learning path through the Dijkstra algorithm; the learning progress tracking unit stores the user's learning data through MongoDB and tracks the user's learning activities, completed courses and test scores.

4. A new learning method based on time management according to claim 1, characterized in that: The time dynamic management module includes a schedule synchronization unit, a dynamic adjustment unit and a notification unit. The schedule synchronization unit synchronizes schedules between different devices and platforms in real time through a cloud server storage center to balance the user's work and study time; The dynamic adjustment unit uses AI to intelligently analyze the user's current availability and work status, and adjusts the learning plan and schedule in real time to efficiently utilize the user's fragmented time; the notification unit reminds the user of schedule matters through application push and SMS.

5. A new learning method based on time management according to claim 1, characterized in that: The content recommendation module includes a user portrait unit, a preference analysis unit and a push unit. The user portrait unit describes the characteristics of the user portrait by analyzing the user's learning history, browsing content records and behavior patterns; The preference analysis unit predicts and identifies the user's potential preferences through an intelligent recommendation algorithm, providing the user with more comprehensive knowledge; The push unit pushes personalized learning content through a platform interactive page, the output end of the user portrait unit is connected to the input end of the preference analysis unit, and the output end of the preference analysis unit is connected to the input end of the push unit.

6. A new learning method based on time management according to claim 5, characterized in that: The implementation steps of the intelligent recommendation algorithm are: a) Data collection and preprocessing Collect user behavior data, including articles, pictures, videos and interactive content viewed by users, and perform data cleaning on the collected data, including removing outliers and filling missing values, to ensure the integrity and accuracy of the data; b) User project matrix construction Create a user-item matrix, where each row represents a user and each column represents a learning item. The values ​​in the matrix represent the interaction intensity between the user and the item, and process the high-dimensional sparse matrix through matrix decomposition; c) Similarity calculation The similarity between the user and the learning item is calculated by a similarity comparison function, and the formula expression of the similarity comparison function is: In formula (1), T i represents the similarity comparison function, α i represents the similarity between users, β i represents the similarity between items, ρ represents the function similarity comparison factor, i represents the function comparison order, and n represents the function comparison order termination value. Represents the function similarity comparison coefficient; d) Prediction score For the target user, find the K users most similar to him / her, and predict the target user's rating based on these users' ratings of the unrated learning items. At the same time, for the unrated items of the target user, find the K items most similar to the items, and predict the target user's rating of the unrated items based on the target user's ratings of these items. e) Recommendation generation Sort all unrated items by predicted score, and select the N items with the highest scores as the recommendation list; f) Result evaluation and optimization The recommendation effect is evaluated according to the evaluation function, and the algorithm parameters are adjusted by the similarity threshold to optimize the recommendation effect. The formula expression of the evaluation function is: In formula (2), P represents the evaluation function, N represents the total number of items to be evaluated, p represents the order of the items to be evaluated, and μ p represents the user's true rating of item p, γ p represents the user's predicted rating for item p, represents the item scoring error; g) Real-time updates and feedback Based on the user's real-time behavior data, the user-item matrix is ​​updated and user feedback on recommended content is collected for algorithm model iteration and optimization.

7. A new learning method based on time management according to claim 1, characterized in that: The interactive collaboration module includes a document sharing unit, a forum discussion unit and a module management unit. The document sharing unit realizes collaborative editing through the API interface of the cloud storage service to improve team collaboration efficiency; the forum discussion unit provides a discussion platform through the client group system to promote the sales team's work efficiency and service level; the module management unit reviews and manages the pictures and video content posted by users through natural language processing (NLP) to provide users with a safe and reliable learning environment.

8. The new learning method based on time management according to claim 1 is characterized in that: The evaluation and feedback module includes an evaluation unit, a personalized feedback unit and a strategy optimization unit. The evaluation unit analyzes the user's learning performance and progress by collecting user tests and performance results; the personalized feedback unit sends the evaluation results to the user in the form of a personalized report; The strategy optimization unit integrates the evaluation results and feedback information through a machine learning algorithm to optimize the user's learning content, process and time. The output end of the evaluation unit is connected to the input end of the personalized feedback unit, and the output end of the personalized feedback unit is connected to the input end of the strategy optimization unit.

Images