Learning management information processing system, control method for information processing device, and program

Abstract

The present invention addresses the problem of providing a learning management information processing system, a control method for an information processing device, and a program that make it possible to achieve continuous learning by presenting an action map corresponding to a user's learning progress.　A learning management information processing system 100 comprises: an action map acquisition unit 32 that acquires an action map in which a plurality of tasks for achieving a learning target of a user are hierarchically set; a learning progress analysis unit 33 that monitors a learning progress of the user and analyzes a learning progress status including whether or not a learning interruption has been performed; an action map adjustment unit 34 that adjusts tasks of the action map set for the user on the basis of the analysis result of the learning progress and presents the adjusted tasks to the user; and a sharing processing unit 35 that shares information relating to the action map with participants belonging to a community in which the user participates. The problem is thus solved.

Description

Learning Management Information Processing System, Control Method for Information Processing Apparatus, and Program

[0001] The present invention relates to a learning management information processing system, a control method for an information processing apparatus, and a program.

[0002] Conventionally, a technique for making a learning proposal according to the progress of learning for a user who is learning has been known. For example, Patent Document 1 describes this type of technique.

[0003] Patent Document 1 relates to a learning support method executed by a server computer that has a storage device storing a plurality of teaching materials composed of a plurality of units and is connectable to a learner's client computer. In Patent Document 1, teaching material keyword information in which keywords corresponding to teaching materials are set and unit keyword information in which keywords corresponding to units are set are stored in the storage device, and when response information indicating that the degree of understanding of the learner who is learning a unit of a teaching material regarding the unit is in a predetermined state is notified from the client computer, a storage procedure for accumulating history information associating the unit and the response information in the storage device, a specifying procedure for specifying keywords corresponding to the units included in the history information based on the unit keyword information, and a selecting procedure for selecting teaching materials corresponding to each keyword specified in the specifying procedure based on the teaching material keyword information are described as being executed by the server computer.

[0004] Japanese Patent Application Laid-Open No. 2003-280510

[0005] Each learner has not presented an action map reflecting these conditions despite differences in learning ability, time available for learning, field of interest, age, etc., and the results faced by the learner have not necessarily been obtained. Even if an action map is presented, learning may be interrupted because the presented action map is not suitable for the user. There has been room for improvement in the prior art from the perspective of presenting an action map according to the learning situation of the user.

[0006] This invention has been made in view of the above circumstances, and aims to provide a learning management information processing system, an information processing device control method, and a program that can enable continuous learning by presenting an action map according to the user's learning progress.

[0007] To achieve the above objective, one aspect of the present invention is a learning management information processing system comprising: action map acquisition means for acquiring an action map in which a plurality of tasks for achieving a user's learning objectives are hierarchically set; learning progress analysis means for monitoring the user's learning progress and analyzing the learning progress status, including whether or not learning has been interrupted; action map adjustment means for adjusting the tasks of the action map set for the user based on the results of the learning progress analysis and presenting them to the user; and sharing processing means for sharing information about the action map with participants belonging to a community in which the user participates.

[0008] Furthermore, one aspect of the present invention is a control method for an information processing device, which includes: an action map acquisition step of acquiring an action map in which a plurality of tasks for achieving a user's learning goals are hierarchically set; a learning progress analysis step of monitoring the user's learning progress and analyzing the learning progress status, including whether or not learning has been interrupted; an action map adjustment step of adjusting the tasks of the action map set for the user based on the results of the learning progress analysis and presenting them to the user; and a sharing processing step of sharing information about the action map with participants belonging to a community in which the user participates.

[0009] Furthermore, one aspect of the present invention is a program for causing a computer to execute the following steps: an action map acquisition step of acquiring an action map in which a plurality of tasks for achieving a user's learning goals are hierarchically set; a learning progress analysis step of monitoring the user's learning progress and analyzing the learning progress status, including whether or not learning has been interrupted; an action map adjustment step of adjusting the tasks of the action map set for the user based on the results of the learning progress analysis and presenting them to the user; and a sharing processing step of sharing information about the action map with participants belonging to a community in which the user participates.

[0010] According to the present invention, it is possible to provide a learning management information processing system, an information processing device control method, and a program that enable continuous learning by presenting an action map according to the user's learning progress.

[0011] This figure shows a learning management information processing system according to one embodiment of the present invention. This is a block diagram showing the hardware configuration of the information processing device according to this embodiment. This is a functional block diagram showing an example of the functional configuration of the information processing device according to this embodiment. This figure shows an example of an action map. This figure shows an example of the content of a task in an action map. This figure shows an example of user data and analysis results for analyzing learning progress. This figure shows an example of individual analysis of the user's learning progress. This figure shows an example of automatic intervention by the system. This figure shows an example of an improvement plan in which tasks are subdivided according to the user's learning progress. This figure shows an example of learning pattern analysis and subdivision plan. This figure shows an example of an action map after adjustment processing. This figure shows an example of a report generated by the shared processing unit. This is a flowchart showing an example of the flow of optimization processing performed by the learning management information processing system. This figure shows a part of the task confirmation screen of the action map. This figure shows a part of the task confirmation screen of the action map.

[0012] One embodiment of the present invention will be described below with reference to the drawings.

[0013] <System Configuration> First, the overall system configuration will be explained. Figure 1 is a diagram showing a learning management information processing system 100 according to one embodiment of the present invention.

[0014] The learning management information processing system 100 provides a platform to support users' learning through an online learning site. The platform provides various learning content such as qualification courses, skills courses in sales and marketing, musical instrument courses, and cooking courses. Learning support includes providing necessary learning information such as lecture videos, audio, and electronic learning materials, as well as managing learning schedules. The platform is used by both teachers who create courses and students.

[0015] The learning management information processing system 100 is implemented by an information processing device 1 that exchanges various types of information with each of the user terminals 2-1 to 2-n via a communication network such as the Internet. The information processing device 1 is a computer that provides various types of learning-related information to each of the user terminals 2-1 to 2-n and functions as a server.

[0016] User terminals 2-1 to 2-n are computers used by users of the learning management information processing system 100. Typically, a user is a learner (user) who is engaged in learning. A user may also be a supporter or teacher who assists learners using information provided by the learning management information processing system 100.

[0017] Furthermore, users can participate in communities set up on the learning management information processing system 100 according to common learning goals, organizations, etc. Users who participate in a community can receive information relevant to that community.

[0018] User terminals 2-1 to 2-n consist of personal computers, tablets, smartphones, etc. User terminals 2-1 to 2-n may send and receive various types of information via a web browser, or they may send and receive various types of information with the information processing device 1 using pre-installed programs. In the following description, items common to user terminals 2-1 to 2-n may be simply referred to as user terminal 2.

[0019] <Hardware Configuration> Next, an example of the hardware comprising the information processing device 1 will be described. Figure 2 is a block diagram showing the hardware configuration of the information processing device 1 according to this embodiment. The information processing device 1 includes a CPU (Central Processing Unit) 11 as a processor, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a bus 14, an input / output interface 15, an output unit 16, an input unit 17, a storage unit 18, a communication unit 19, and a drive 20.

[0020] The CPU 11 executes various processes according to the program recorded in the ROM 12 or the program loaded from the storage unit 18 into the RAM 13. The RAM 13 also stores data necessary for the CPU 11 to execute various processes. The CPU 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output interface 15 is also connected to this bus 14.

[0021] The input / output interface 15 is connected to an output unit 16, an input unit 17, a storage unit 18, a communication unit 19, and a drive 20. The output unit 16 consists of a display, speakers, etc., and outputs various information as images and sounds. The input unit 17 consists of a keyboard, mouse, etc., and inputs various information. The storage unit 18 consists of a hard disk, DRAM (Dynamic Random Access Memory), etc., and stores various data. The communication unit 19 communicates with other devices via a network, including the Internet.

[0022] A removable media 21, such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, is appropriately mounted on the drive 20. Programs read from the removable media 21 by the drive 20 are installed in the storage unit 18 as needed. The removable media 21 can also store various data stored in the storage unit 18, just like the storage unit 18.

[0023] The hardware configuration described here is merely an example. The computer described in this embodiment, including the information processing device 1, may have the same configuration as that shown in Figure 2, or it may have a different configuration. Furthermore, the computer may be composed of two or more computers. The user terminal 2 in Figure 1 is, for example, a smartphone, tablet, or personal computer having a configuration similar to the hardware configuration shown in Figure 2.

[0024] <Functional Configuration> Next, the functional configuration of the information processing device 1 will be described. Figure 3 is a functional block diagram showing an example of the functional configuration of the information processing device 1 according to this embodiment.

[0025] The information processing device 1 of this embodiment works in conjunction with a natural language processing model 5, a machine learning model 6, or a machine learning model 7 to provide information to support learning to a user using a user terminal 2 via a communication network.

[0026] Natural Language Processing Model 5 is a Large Language Model (LLM) that has been trained to interpret natural language and provide responses. Natural Language Processing Model 5 can be a general-purpose model or one that has been fine-tuned for learning support.

[0027] Machine learning model 6 is a model that learns from training data using supervised or unsupervised learning and can make predictions and classifications that match the objective. Machine learning model 7 is a model that learns from training data using reinforcement learning and can make predictions and classifications that match the objective. Machine learning models 6 and 7 may be trained using deep learning.

[0028] The information processing device 1 has a database 90 that stores various types of information used to support learning. Information such as user information, action maps, action map change history, and activity logs are stored. User information includes information about the user such as username, age, gender, and learning status, and is registered in association with the user ID. Action maps are information that identifies the content of the action maps presented to the user to support learning, and are registered individually for each user. Change history is information that shows the change history, such as version information of the action map, and is associated with the action map. Activity logs are information that shows the user's actions on the learning management information processing system 100.

[0029] Next, the functional parts of the information processing device 1 will be described. The information processing device 1 includes an action map generation unit 31, an action map acquisition unit 32, a learning progress analysis unit 33, an action map adjustment unit 34, a sharing processing unit 35, a change management unit 36, and an effectiveness evaluation processing unit 37, all of which are functional parts implemented on the processor (CPU 11).

[0030] The action map generation unit 31 is an action map generation means that generates an action map to achieve the learning goals of the learning user.

[0031] An action map is constructed by breaking down learning objectives into a hierarchical structure of multiple actions. An action map is a learning roadmap that hierarchically (step-by-step) organizes the path to achieving learning objectives through specific tasks. Tasks include the goals the user should achieve, the actions the user should take, and the challenges set for the user.

[0032] An action map visualizes progress, allowing learners to easily and clearly understand "what needs to be done now" based on the completion status of each step. In this embodiment, the action map is structured in a hierarchical manner, broken down step by step from major goals to intermediate goals, then to small tasks, and finally to specific actions. Each task in the action map may include explanations and self-check functions.

[0033] Figure 4 shows an example of an action map. Figure 5 shows an example of the content of tasks in the action map. In the example in Figure 4, the highest level of learning objective is set as "Mastering Python Programming." The next level after the highest level is divided into intermediate objectives such as "Mastering Basic Grammar," "Data Structures and Algorithms," and "Web Development Fundamentals." Further down the levels, it is subdivided into specific learning topics such as "Variables and Types," "Conditional Branching," and "Loops." Each level is designed to make it easy for learners to grasp the overall picture. In addition, the relationships and dependencies between each level are clearly shown, making it possible to visually understand the order and importance of learning.

[0034] In the Python Programming Master example, the lowest level presents specific actions and tasks. In the example in Figure 5, for instance, under the topic "Basics of the for statement," specific tasks such as "Learn the syntax of the for statement," "Create a simple loop program," and "Understand nested loops" are placed. Each task is accompanied by an estimated time required, difficulty level, and links to learning resources (text, videos, practice problems, etc.). Learners can select and complete these tasks according to their own pace and preferences. Furthermore, progress is automatically recorded upon task completion and reflected in the achievement level at higher levels.

[0035] The method for generating an action map will now be explained. The action map generation unit 31 sets the user's learning objectives and generates an action map that reflects the learning status of the learning user based on those objectives.

[0036] The setting of learning objectives by the action map generation unit 31 will now be explained. The action map generation unit 31 acquires input information for setting the user's learning objectives and sets learning objectives according to that input information. The input information includes, for example, the search trends of the user and other users, unique needs, the user's interests, the user's skill level, available time, learning style, and combinations thereof, as well as text information such as the user's search history and the history of conversations with the user. The learning objectives are set by the action map generation unit 31 so that they are clear, achievable, and challenging goals for the user.

[0037] This section explains how to set learning objectives when the input information is the user's search history. The action map generation unit 31 estimates what the user is interested in based on the user's search history. For example, it obtains information that the user is browsing sites related to women's clothing, desserts, cooking, restaurants, and craft classes. Furthermore, it obtains information from the user ID that the user is a male in his 20s. From this information, the action map generation unit 31 determines that the user is trying to please her and sets the learning objective to "make her happy".

[0038] This section describes how to set learning objectives when the input information is a history of conversations with the user. The action map generation unit 31 obtains the learning user's interests, current skill level, long-term career goals, etc., from the conversation history. The action map generation unit 31 combines open-ended questions and specific questions to draw out the learning user's true needs and potential. The action map generation unit 31 also analyzes the learning user's responses and concretizes the learning objectives based on criteria such as specificity, measurability, achievability, relevance to learning objectives, and deadlines, and proposes them to the user. The user can further refine the learning objectives by engaging in further conversations with the action map generation unit 31 regarding its proposals.

[0039] The action map generation unit 31 may use a natural language processing model 5 to analyze the user's input information. This analysis not only extracts keywords but also performs contextual understanding, sentiment analysis, and intent estimation. For example, in response to inputs such as "I want to make her happy" and "I want to learn programming," the natural language processing model 5 generates additional questions to extract information about the learning user's romantic experience, cooking experience, baking experience, interest in specific food fields, programming experience, interest in specific languages, and application fields (web development, data analysis, etc.). The natural language processing model 5 also checks the consistency of the user's answers and clarifies any inconsistencies or ambiguities with appropriate questions.

[0040] Next, the generation of an action map based on learning objectives by the action map generation unit 31 will be described. Based on the learning objectives and the user's learning status, the action map generation unit 31 generates a customized action map that reflects the user's current skill level, available time, and learning style.

[0041] The action map is generated based on a hierarchical structure, with the learning objective at the top level and progressively becoming more detailed from there. The action map is implemented as a tree structure data model within the database 90. Each node corresponding to a task represents an objective, topic, or task, and the hierarchy is expressed through parent-child relationships. Nodes representing tasks include attributes such as title, description, hierarchy level, list of child nodes, completion status, estimated time required, and difficulty level. This tree structure enables efficient data retrieval and updating. For example, it becomes easy to quickly retrieve all tasks related to a specific intermediate objective or to propagate the completion status of tasks to higher levels of the hierarchy. Furthermore, this structure can be dynamically modified according to the progress of learning, allowing for the flexible addition of new branches (subgoals and tasks) and the deletion of unnecessary branches. The information processing device 1 sets prerequisite attributes for each task node and automatically verifies that the prerequisites are met when the user starts a task. For example, the "Loop" task has the completion of "Variables and Types" set as a prerequisite. If the user accesses a task without meeting the prerequisites, a list of missing prerequisite tasks is presented, and a recommended learning order is suggested. However, if the user explicitly selects otherwise, it is possible to start a task ignoring the prerequisites, ensuring flexibility in learning. The action map generation unit 31 analyzes the dependencies between tasks and identifies task groups that can be executed in parallel. Tasks that share the same parent node and have no mutual dependencies are marked as being executable in parallel. In the user interface, these tasks are displayed side by side, and the user can freely choose the order according to their interests and available time. This process increases the degree of freedom in learning while maintaining the necessary order.

[0042] Furthermore, an expand / collapse function is implemented for each node, and this function is implemented for nodes at each level on the action map operation screen (user interface) displayed on user terminal 2. This allows learning users to check the details of actions and tasks as needed, or to view the overall picture. When expanded, data from child nodes is retrieved asynchronously to provide smooth usability. In addition, the learning user's last viewing state (which nodes were expanded) is saved and reproduced on the next access, supporting continuous learning.

[0043] At the highest level, a broad learning objective is set, such as "Make her happy," and at the next level, it becomes "Give her a delicious homemade dessert." Further down, it is broken down into specific topics such as "Make a chocolate cake," and even further down, into "Make the sponge" and "Make the cream." Each level makes it easy to grasp the overall picture. Each level can be broken down into more detailed subtasks and actions. At the lowest level, specific actions and tasks are presented. For example, under "Make the sponge," specific tasks such as "Prepare the ingredients for the batter (chocolate, butter, eggs)," "Prepare before mixing," "Mixing method and order," "Prepare and put into the mold," "Set the oven," and "Check when it's done baking" are placed. Each task is accompanied by an estimated time required, points to note, links to websites where the mold and oven can be purchased, etc. Learning users can select and perform these tasks.

[0044] The case where the action map generation unit 31 uses the natural language processing model 5 to generate an action map will be described. The action map generation unit 31 transmits a prompt including an instruction to generate an action map that is subdivided into specific tasks as it proceeds to lower levels with respect to the top-level learning objective and the main milestones to the natural language processing model 5, and generates an action map. The content of the prompt is not particularly limited. For example, the action map generation unit 31 may, by means of a hierarchical structure, issue an instruction to generate an action map to the natural language processing model 5 by means of a prompt, enabling the user to grasp the overall picture while at the same time allowing for detailed progress management. Alternatively, the action map generation unit 31 may issue an instruction to generate an action map to the natural language processing model 5 by means of a prompt, in which the links and dependencies between each layer are clearly expressed in a tree structure in order to facilitate understanding of the learning order and priority.

[0045] Next, an example of using the action map registered in the database 90 will be described. The database 90 includes a learning objective and the action maps of other learning users who have obtained good results based on the learning objective. The database 90 may include, in addition to the action maps of successful learning users, best practices designed by experts and action maps based thereon.

[0046] When a learning objective is set, the action map generation unit 31 refers to the database 90 to obtain an action map similar to the set learning objective. Action maps of learning users who have achieved similar learning objectives in the past are extracted from the database 90. The one with the highest success rate or the one that best suits the characteristics of the learning user may be selected from the extracted action maps. Multiple evaluation indicators such as actions, tasks, or learning completion rate, goal achievement degree, satisfaction degree, etc. may be used for the selection. The evaluation indicators are preset in the action map, for example.

[0047] The action map generation unit 31 generates an action map customized for the user based on the learning goal, the action map of successful examples, and the individual situation of the user. The individual situation of the user includes available time, learning style, existing knowledge, etc. This action map includes, for example, major milestones, recommended information sources or learning resources, predicted problems and their solutions, etc.

[0048] Also, the action map generation unit 31 considers the personal situation (work situation, family responsibilities, other time constraints) of the learning user and determines the depth of the achievable action map. For example, for users who can work on tasks or learning full-time, a more detailed and focused action map is provided, while for users with many time constraints, a compact map focusing on core concepts is proposed. Also, considering the quantity and quality of available learning resources (online courses, books, mentorship, etc.), the depth at which they can be effectively utilized is set. For example, the action map generation unit 31 analyzes the available learning time of the user and executes a process to determine the granularity of tasks. First, the average learning session time of the user in the past 7 days is calculated. Next, based on 50% of this average time, the tasks are decomposed so that the estimated time required for each task is below this reference time. For example, for a user with an average learning time of 40 minutes, each task is decomposed into units of 20 minutes or less. By this process, a structure is realized in which the user can complete at least one task in one learning session. Furthermore, the action map generation unit 31 calculates the appropriate number of hierarchical levels from the complexity of the learning goal and the available time of the user. Specifically, the total estimated time until the learning goal is achieved is divided by the learnable time per week of the user to calculate the learning period. If the learning period is within 4 weeks, the hierarchy is composed with 3 levels, within 12 weeks with 4 levels, and for longer than that, 5 levels as the upper limit. Between each level, the number of tasks at the lower level is adjusted to be 3 to 5 times that of the upper level.

[0049] The action map generation unit 31 may generate an action map using a machine learning model 6. The machine learning model 6 is constructed, for example, by machine learning that takes learning goals and the individual circumstances of learning users as input data and an action map as output data.

[0050] The action map acquisition unit 32 is an action map acquisition means that acquires the action map set by the action map generation unit 31 for a learning user whose learning progress is being monitored.

[0051] The learning progress analysis unit 33 is a learning progress analysis means that monitors the user's learning progress and analyzes the learning progress, including whether or not learning has been interrupted. The learning progress analysis unit 33 can automatically identify actions that have interrupted learning. The learning progress of the learning user is monitored in real time by the learning progress analysis unit 33.

[0052] The learning progress analysis unit 33 continuously tracks user activity. This includes task start and completion times, viewing time for each learning resource, answer status of practice problems, and the frequency and length of tasks or learning sessions.

[0053] The learning progress analysis unit 33 acquires user activity based, for example, on the activity log on the user terminal 2. The activity log on the user terminal 2 includes website page views, click events, time spent on the site, etc. The learning progress analysis unit 33 receives this event data and processes and stores it in real time. The data showing user activity is stored in the database 90. The learning progress analysis unit 33 processes the event data in real time and performs immediate analysis and response. The data showing user activity is collected in an anonymized form, protecting individual privacy while enabling detailed analysis of learning patterns. Subjective comprehension and difficulty ratings based on the user's self-report are also collected. This data is recorded in the database 90 in real time, enabling immediate analysis and intervention.

[0054] The learning progress analysis unit 33 detects interruptions or delays in performance based on data collected from the user. The definition of an interruption identified by the learning progress analysis unit 33 can be customized for each user. For example, conditions for identifying an interruption can be set to "no login for 7 consecutive days" or "more than half of the scheduled tasks are incomplete." In addition, behavior that is different from the user's past patterns (such as a sudden decrease in learning time) may also be detected as an indication of an interruption.

[0055] When the learning progress analysis unit 33 detects an interruption, it performs a multifaceted analysis to identify possible causes. The analysis considers the difficulty of the previous task, the relevance of the learning content, its consistency with the user's interests, and external factors (such as vacation periods or busy work periods). It also compares the interruption pattern with similar users or interruption patterns in the profiles of other learning users. For example, the learning progress analysis unit 33 determines an interruption in a specific task on the action map based on the following combined conditions: Firstly, the estimated time required for the task has been significantly exceeded but it has not been completed; secondly, there have been multiple accesses to the same task but no progress has been made; and thirdly, there is an attempt to access a higher-level task by skipping lower-level tasks. When these conditions are detected, the unit analyzes the relevant task and its context and instructs the action map adjustment unit 34 to subdivide the task or add supplementary explanations. The learning progress analysis unit 33 evaluates the interruption risk in three stages. In the first stage, it detects stagnation at the task level. Specifically, it records cases where the same task is accessed three or more times but not marked as complete as a "task-level interruption risk." In the second stage, progress at the parent node level is evaluated, and a "topic-level interruption risk" is identified if the completion rate of child tasks is less than 20% for two weeks. In the third stage, a "goal-level interruption risk" is identified if the overall progress toward the highest-level learning objective is less than 5% for one month, and different intervention strategies are activated for each stage.

[0056] The learning progress analysis unit 33 implements detailed progress tracking and visualization functions in conjunction with the hierarchical action map. The completion status of each node (goal, topic, task) of an action or task is automatically aggregated from lower to higher levels. Progress is visually represented, for example, with a bar, allowing the learning user to grasp the overall progress and detailed achievement status at a glance. Furthermore, it provides time-series progress graphs and comparisons between planned and actual progress, offering information useful for adjusting the learning pace and managing time. These visualizations help maintain the learning user's motivation and improve their self-management skills.

[0057] Figure 6 shows an example of user data and analysis results for analyzing learning progress. Figure 7 shows an example of individual analysis of a user's learning progress. As shown in Figures 6 and 7, the learning progress analysis unit 33 collects user input information in real time and generates analysis results based on the collected input information. The analysis results of the learning progress analysis unit 33 are aggregated as a learning history for each user and form the basis for subsequent optimization processes.

[0058] In this embodiment, the learning progress analysis unit 33 uses a machine learning model 6 to infer interruption patterns. The machine learning model 6 learns the user's normal behavior patterns and identifies behaviors that deviate from these as signs of interruption. The machine learning model 6 also compares with groups of users with similar profiles to assess interruption risk at both the individual and group levels. The machine learning model 6 is periodically retrained to adapt to changing learning patterns. The detected interruption risk is quantified as a risk score, and an alert is generated if it exceeds a threshold.

[0059] The machine learning model 6 may utilize deep learning for training. The machine learning model 6 performs semantic comprehension, sentiment analysis, and topic extraction on the user's text output (essays, reports, comments, etc.). It also analyzes the frequency of technical terms and sentence complexity to evaluate the user's comprehension and expressive abilities. These analysis results are represented for each user, for example, as skill vectors, forming multidimensional skill information.

[0060] The learning progress analysis unit 33 may infer interruption patterns using the natural language processing model 5. The learning progress analysis unit 33 continuously collects and analyzes completed tasks, generated outputs (texts, projects, etc.), quiz and test results, etc., for each user or learning user. The learning progress analysis unit 33 uses the natural language processing model 5 to evaluate comprehension, vocabulary complexity, and grasp of key concepts on the text data. The natural language processing model 5 also tracks time-series data such as learning speed, review frequency, and error rate changes to evaluate learning progress and efficiency.

[0061] The learning progress analysis unit 33 may automatically intervene for users whose learning progress has stalled and is therefore deemed to have been interrupted. Figure 8 shows an example of automatic intervention by the system. Figure 8 shows an example in which the system notifies users who have been deemed to have been interrupted in real time in the form of a message. The message in Figure 8 is automatically sent, for example, on the third day when no user login is detected, and the format of the message is not particularly limited. The message may be sent in the user's message box on the learning management information processing system 100, or it may be sent to a registered email address.

[0062] The action map adjustment unit 34 is an action map adjustment means that adjusts the action map according to the analysis results of the learning progress analysis unit 33. The action map adjustment unit 34 comprehensively analyzes the learning user's past learning content, generated output, and progress data, and dynamically optimizes the action map. The action map adjustment unit 34 identifies the learning user's learning patterns, strengths, and weaknesses, and adjusts the action map based on these insights.

[0063] The action map adjustment unit 34 adjusts the difficulty level of the action map tasks in real time, for example, and presents tasks that match the current ability level of the target user. Furthermore, the action map adjustment unit 34 dynamically generates or modifies content according to the user's level of understanding and preferences. For example, to explain the same concept, it automatically selects and presents the most effective approach for the user or learner, such as abstract theory, concrete examples, or visual diagrams. This maintains the user's or learner's motivation and effective learning at all times.

[0064] The action map adjusted by the action map adjustment unit 34 adds relevant advanced content when high performance is observed in a particular topic, or conversely, suggests additional support resources or different approaches in areas where the user is experiencing difficulties. The adjustment process by the action map adjustment unit 34 is performed continuously in line with the user's learning progress. This continuous optimization process ensures that the learning experience is always adapted to the learning user's growth and changing needs.

[0065] The action map adjustment unit 34, when a user's learning progress is interrupted, reflects the cause of the interruption, which has been analyzed from multiple angles, into the improvement measures for the action map. This analysis takes into account the difficulty level of the learning content, the clarity of the tasks, the learning user's level of interest, and external factors (time management, stress, etc.).

[0066] The action map adjustment unit 34 takes the analysis results indicating the cause of the interruption and the user's profile data as input to generate personalized improvement suggestions. The action map adjustment unit 34 combines pre-created suggestion templates with dynamically generated improvement content for the action map to create natural-sounding sentences. The suggested improvement action map includes specific action items, expected effects, and a timeline for execution. In addition, the most effective communication style (encouraging words, presentation of objective data, suggestion of challenges, etc.) may be selected based on the user's past response data. The generated suggestions are not only presented directly to the user but are also shared with human mentors as needed, forming the basis for additional support.

[0067] In this embodiment, a dynamic difficulty adjustment mechanism is incorporated into each node of actions and tasks in the hierarchical action map. The action map adjustment unit 34 continuously analyzes performance indicators such as the learning user's progress speed, task completion rate, and quiz and test scores, and automatically adjusts the difficulty of actions or tasks to match each learning user's ability level and learning curve. For example, if a user shows high performance in a particular topic, more challenging actions or tasks may be added or the difficulty level increased by the child nodes of that topic. Conversely, in areas where the user is presumed to be experiencing difficulty, additional supplementary explanations or practice problems are provided. For example, the action map adjustment unit 34 dynamically adjusts the granularity of tasks based on the user's actual learning performance. Specifically, if three consecutive tasks are completed in more than 150% of the estimated time, it automatically subdivides the subsequent tasks. This subdivision analyzes the content of the original task and divides it into independently understandable conceptual units. For example, a 30-minute task called "Understanding Data Structures" is divided into three 10-minute tasks: "List Basics," "Tuple Basics," and "Dictionary Basics." Furthermore, the action map adjustment unit 34 reconfigures the entire hierarchical structure if the user's learning speed differs significantly from the initial expectations. For users who are progressing more than 50% faster than planned, it integrates some intermediate levels and presents tasks at larger conceptual units. Conversely, for users who are progressing slowly, it inserts new intermediate levels to enable learning in small steps. This reconfiguration aims to maintain motivation while appropriately managing the user's cognitive load.

[0068] The improvement suggestions presented to the user by the adjustment process of the action map adjustment unit 34 will be explained. As shown in Figures 9 to 11, the improvement suggestions presented to the user include proposed task changes, proposed analysis and subdivision of learning patterns, proposed changes to the action map, or combinations thereof. Figure 9 is a diagram showing an example of an improvement suggestion in which tasks are subdivided according to the user's learning progress. Figure 9 shows an improvement suggestion in which an existing task is subdivided, as presented by the action map adjustment unit 34. The improvement suggestion in Figure 9 proposes subdividing the task in Figure 5 according to the learning progress. Figure 10 is a diagram showing an example of learning pattern analysis and subdivision plan. Figure 10 shows an analysis of learning patterns and a proposed task subdivision as an improvement suggestion presented by the action map adjustment unit 34. Figure 11 is a diagram showing an example of an action map after the adjustment process. Figure 11 shows an improvement suggestion in which the action map set by the user is subdivided by the action map adjustment unit 34. The action map in Figure 11 is a subdivision of the action map in Figure 4. For example, the effectiveness evaluation processing unit 37 calculates several indicators to quantitatively evaluate the effectiveness of the action map. First, it calculates the "task completion efficiency" by dividing the actual completion time by the estimated time. Second, it measures the score of a confirmation test taken one week after completion as the "knowledge retention rate." Third, it calculates the active rate for 30 days after the action map is presented as the "learning continuation rate." These indicators are combined to calculate the effectiveness score of each action map configuration, which is then used for future optimization.

[0069] The action map adjustment unit 34 can perform adjustment processing using the machine learning model 7 and the natural language processing model 5.

[0070] This section describes how adjustment processing is performed using a machine learning model 7 constructed through reinforcement learning. In reinforcement learning, rewards such as point allocation are set based on a combination of indicators such as learning progress, improvement in understanding, and learning user satisfaction. The machine learning model 7 is continuously updated using individual data from each learning user and provides an action map and description of the action map (= content) with a personalized and optimal learning path. The machine learning model 7 proposes improvements to the personalized action map based on the analysis results of learning progress. This includes adjusting the plan, providing additional support resources, and interventions to improve motivation (such as setting achievable small goals).

[0071] Here's an example of how rewards are set. For instance, if a user spends too little time on each subdivided action, the reward is reduced because the task is too subdivided. Conversely, if a user spends too much time on each subdivided action, or continues to interrupt the process, the reward is also reduced because the task is not subdivided sufficiently. The machine learning model 7 uses previously shared user learning progress to simulate the user's learning steps and calculate the reward. The model then refines the level and accuracy of the action subdivisions through trial and error to increase the reward. In other words, reinforcement learning is performed, which involves a series of processes including reward setting, simulation, and iterative learning.

[0072] When using the natural language processing model 5, the action map adjustment unit 34 sends the analysis results of the user's learning progress and prompts requesting modifications to the action map and tasks to prevent interruptions or to resume from interruptions to the natural language processing model 5. Based on the response from the natural language processing model 5, the unit makes suggestions for improvements to the action map and tasks, makes modifications, etc.

[0073] The sharing processing unit 35 is a sharing processing means that performs a sharing process to make the action map or the contents of the action map public to a predetermined range. The predetermined range includes, for example, communities in which the user participates, and supporters such as teachers who support the user's learning.

[0074] The shared processing unit 35 makes the action map and tasks open source, allowing for improvement and optimization across the entire community. This ensures continuous improvement in the quality and diversity of the action map, actions, and tasks, benefiting all learning users. Each action map, action, and task is version-controlled, allowing for tracking of improvement history.

[0075] Furthermore, the shared processing unit 35 of this embodiment has a collaborative learning function. The shared processing unit 35 adds a group learning function to the hierarchical action map. It enables multiple learning users to share specific nodes or subtrees and set up collaborative projects or group discussions. For example, a node called "Team Project" can be created, and multiple learning users can be assigned to it to work on tasks together. It also provides an opportunity for individual users to receive feedback from other learning users after completing their tasks. This allows for the benefits of collaborative learning while clearly tracking the progress and contributions of individual learning users.

[0076] The shared processing unit 35 makes the task content, related resources, evaluation criteria, etc., public to the community, allowing any community participant to view, suggest, and improve it. Suggestions and improvements include modifying the content, adding new resources, and adjusting evaluation criteria. Community participants can easily edit the content of actions or tasks and suggest improvements through a web-based interface. Suggested changes can be visually reviewed to facilitate understanding by other users. A comment function for suggestions and a function to approve / reject changes are also implemented. For example, suggestions may be submitted in the form of requests, and a decision on whether or not to adopt them may be made after review and discussion by community members.

[0077] Furthermore, a function to provide feedback on the effectiveness and difficulty of tasks will be implemented. Users who make outstanding contributions will be given incentives such as points and increased evaluations within the learning management information processing system to encourage continued participation. For example, the shared processing unit 35 will perform the following processing on improvement suggestions submitted by participants: It will compare the proposed changes to the task with the completion rate, time taken, and interruption rate of similar tasks stored in the database 90 and calculate a predicted value for the improvement effect. For example, if there is a suggestion to "add three actual code examples" to the "variables and types" task, it will refer to the improvement in the completion rate of tasks that have had code examples added in the past (an average improvement of 20%) and present it as the predicted effect of the proposal.

[0078] Each task is assigned a unique ID, and its change history is tracked by the version control function. Task metadata includes the creator, last modified date, difficulty level, estimated time required, prerequisites, and learning objectives. This open-sourcing allows for continuous improvement in the quality and diversity of tasks, and enables the maintenance of content that reflects the latest industry trends and best practices. For example, information such as "5-minute increments are optimal for learners after 10 PM," "Including competitive elements is effective for those with a sales background," and "People over 50 prefer text explanations to videos" is shared. For example, the sharing processing unit 35 analyzes the learning context of community members and shares only highly relevant information. Specifically, it quantifies the similarity of learning objectives, the current learning phase, and past learning patterns, and shares detailed learning patterns only among users whose similarity score is above a threshold. For example, a user in the "Basic Grammar" phase of "Python Programming Master" is given priority in being shown the success patterns of users who have recently completed the same phase.

[0079] The sharing processing unit 35 may share the user's learning progress in report format. Figure 12 shows an example of a report generated by the sharing processing unit 35. As shown in Figure 12, saving the user's learning progress and results in report format makes it easy to share the learning effectiveness of the action map with community participants.

[0080] Information regarding the change history and improvement suggestions for action maps and tasks shared by the shared processing unit 35 is registered in the database 90. This information can also be used in the adjustment process of the action map adjustment unit 34 and the action map generation process of the action map generation unit 31. For example, it can be used as training data for the machine learning model 7 used in the action map adjustment process so that modifications and improvement suggestions made by participants are reflected in the adjustment process when the next adjustment process is performed. Alternatively, this information can be added to the information retrieved from the database 90 in the action map generation process.

[0081] The change management unit 36 ​​is a change management means that manages the history of changes made to the action map. The change management unit 36 ​​provides the user with an interactive user interface, allowing the user to edit the action map in real time. The action map generation unit 31 presents the action map to the user terminal 2 in a format that the learning user can directly edit. An intuitive drag-and-drop function is implemented in the user interface so that the learning user can customize the action map to their own needs. The learning user can add, delete, change the order of, move to different levels of actions or tasks on the user terminal 2 using mouse or touch operations. Each action or task has attributes such as duration, difficulty level, and dependencies, and the interface is designed so that these can also be edited visually.

[0082] Furthermore, a change history function is implemented, allowing users to revert to previous versions. By analyzing the change history, the action map generation unit 31 gains a deeper understanding of the learning user's preferences and priorities, further optimizing future suggestions.

[0083] Operations performed on the user terminal 2 are transmitted to and synchronized with the information processing device 1 in real time. The change management unit 36 ​​analyzes in real time how the changes affect goal achievement and provides feedback. For example, if deleting a specific task may delay the acquisition of an important skill, the change management unit 36 ​​explains the impact and proposes an alternative. The analysis and recommendations from the change management unit 36 ​​may also be immediately displayed on the user terminal 2. For example, recommendations from the change management unit 36 ​​are presented when changes are made to balance the optimal configuration proposed by the action map generation unit 31 with the learning user's own customizations. When the order of actions or tasks is changed, a visualization is provided showing how it affects overall efficiency.

[0084] The change management unit 36 ​​manages action maps and tasks along with version information. Task content, related resources, metadata, etc., are treated as information, making the change history fully traceable. This makes it easy to revert to a state at any point in time and to check the differences between different versions. In addition, by saving the main content and sub-content separately, it becomes possible to maintain the main content while simultaneously providing and proposing experimental improvement proposals and alternative approaches.

[0085] The change management unit 36 ​​may use a machine learning algorithm to evaluate the quality of improvement suggestions for actions or tasks. A machine learning model 6, trained using a dataset of high-quality suggestions adopted in the past, evaluates the clarity, relevance, originality, etc., of the wording of new suggestions. It is also preferable to take into account the proposer's past contributions and community evaluations. The evaluation results are displayed together with the improvement suggestions.

[0086] The effectiveness evaluation processing unit 37 is an effectiveness evaluation processing means that performs evaluation processing to scientifically verify the effectiveness of the optimization strategy of the action map. For example, the effectiveness evaluation processing unit 37 randomly divides users or learning users into multiple groups and applies different optimization algorithms and settings to each group. Evaluation indicators include learning completion rate, goal achievement speed, long-term skill retention rate, and learning user satisfaction. The test period is set according to the nature of the learning content, and both short-term effects and long-term impacts are measured. The test results are analyzed using statistical methods, and strategies that show significant improvement are given priority for adoption.

[0087] <Processing Flow> Next, the processing flow by the learning management information processing system 100 will be explained with reference to Figure 13. Figure 13 is a flowchart showing an example of the optimization processing flow performed by the learning management information processing system 100.

[0088] In step S1, the action map generation unit 31 obtains learning objectives from input information such as the user's search history and the user's dialogue history.

[0089] In step S2, the action map generation unit 31 acquires the user's learning status and generates a customized action map for each user based on the learning goals and learning status. If action maps of other users are registered in the database 90, the action map generation unit 31 can generate the target user's action map by reflecting the action maps of other users.

[0090] In step S3, the action map acquisition unit 32 acquires the action map set for the user being monitored.

[0091] In step S4, the learning progress analysis unit 33 starts acquiring behavioral logs that indicate the user's learning progress.

[0092] In step S5, the learning progress analysis unit 33 analyzes the user's learning progress and determines whether the action map or task needs improvement. The learning progress analysis unit 33 determines that improvement is needed if an interruption has been detected or is likely to occur. As described above, the determination of whether improvement is needed may also be made by reflecting the information of other users if their information is registered in the database 90, or by utilizing the machine learning model 6.

[0093] The learning progress analysis unit 33 proceeds to step S6 if it determines that improvement is needed (step S5; Yes), and proceeds to step S7 if it determines that improvement is not needed (step S5; No).

[0094] In step S6, the action map adjustment unit 34 performs adjustment processing on the action map or tasks based on the analysis results of the learning progress analysis unit 33 and user information registered in the database 90, and presents them to the user. Past user data may also be used in the adjustment processing. The action map adjustment unit 34 transmits the updated action map, subdivided tasks, improvement suggestions, etc. to the user terminal 2.

[0095] In step S7, the sharing processing unit 35 performs a sharing process to share information about the action map with participants belonging to the community in which the monitored user participates.

[0096] In step S8, the shared processing unit 35 determines whether or not an improvement suggestion has been made in the community. If an improvement suggestion has been made, the process proceeds to step S9 (step S8; Yes); if no improvement suggestion has been made, the process proceeds to step S10 (step S8; No).

[0097] In step S9, the change management unit 36 ​​saves version information such as the changes in the proposed improvement and the change history to the database 90.

[0098] In step S10, the effectiveness evaluation processing unit 37 measures the learning effect on the action map and tasks and registers the measurement results in the database 90. The measurement results may be used to retrain the machine learning model 6 or the machine learning model 7. After the processing in step S10, the process returns to step S1.

[0099] <Display Example> Referring to Figures 14 and 15, the task confirmation screen of the action map displayed on the user terminal 2 will be explained. Figures 14 and 15 are examples of the display of the task confirmation screen of the action map. The confirmation screen that follows below Figure 14 is shown in Figure 15, and it is assumed that there is another screen (not shown) that follows below Figure 15.

[0100] The confirmation screen shown in Figures 14 and 15 includes a task display unit 101, a task description display unit 102, a video display unit 103, a checklist unit 104, an action map display unit 105, and a task content display unit 106.

[0101] The task display unit 101 displays the name of the task to be displayed in detail. The task description display unit 102 displays a description of the task. The video display unit 103 is an area for playing videos for learning about the target task. By selecting the video display unit 103, the user can play the actions associated with the task.

[0102] The checklist unit 104 displays the checklist set for the task. Whether or not the user has checked items in the checklist unit 104 is acquired by the learning progress analysis unit 33 as an action log. The action map display unit 105 displays a list of action maps to which the task belongs. The task content display unit 106 displays the specific content to be performed for the task. The unillustrated lower part of Figure 15 is assumed to contain text that further subdivides and explains the task.

[0103] As described above, the learning management information processing system 100 of this embodiment includes an action map acquisition unit 32 that acquires an action map in which multiple tasks for achieving the user's learning goals are set hierarchically; a learning progress analysis unit 33 that monitors the user's learning progress and analyzes the learning progress status, including whether or not learning has been interrupted; an action map adjustment unit 34 that adjusts the tasks of the action map set for the user based on the results of the learning progress analysis and presents them to the user; and a sharing processing unit 35 that shares information about the action map with participants belonging to the community in which the user participates.

[0104] Furthermore, the control method for the information processing device 1 of this embodiment includes an action map acquisition step of acquiring an action map in which multiple tasks for achieving the user's learning goals are hierarchically set; a learning progress analysis step of monitoring the user's learning progress and analyzing the learning progress status, including whether or not learning has been interrupted; an action map adjustment step of adjusting the tasks in the action map set for the user based on the results of the learning progress analysis and presenting them to the user; and a sharing process step of sharing information about the action map with participants belonging to the community in which the user participates.

[0105] Furthermore, the program of this embodiment causes a computer to execute the following steps: an action map acquisition step to acquire an action map in which multiple tasks for achieving the user's learning goals are hierarchically set; a learning progress analysis step to monitor the user's learning progress and analyze the learning progress status, including whether or not learning has been interrupted; an action map adjustment step to adjust the tasks in the action map set for the user based on the results of the learning progress analysis and present them to the user; and a sharing process step to share information about the action map with participants belonging to the community in which the user participates.

[0106] In this way, the control method or program for the learning management information processing system 100 and the information processing device 1 are configured to perform individual optimization of the action map using the collected and analyzed data as input. This optimization process aims to maintain an optimal learning experience and learning process by considering the strengths and weaknesses of the user or learning user and presenting tasks of appropriate difficulty. For example, if a user shows high performance in a particular area, more challenging tasks or advanced content will be added. Conversely, in areas where the user is finding it difficult, additional basic exercises or explanations using different approaches will be provided. In addition, new topics and practical projects will be proposed in response to changes in the user's or learning user's interests and goals. Optimization can be performed not only regularly (weekly or monthly) but also after important learning events (e.g., mock exams, regular exams), making it possible to maintain an action map that always reflects the latest learning status. Since the action map is continuously and dynamically optimized to match each user's individual needs, learning style, and progress, a more effective and satisfying learning experience is expected, and the achievement rate of learning goals is expected to improve.

[0107] Furthermore, the learning management information processing system 100 of this embodiment further includes an action map generation means that sets learning objectives based on user input information, including at least one of the user's search history and the user's dialogue history, and generates an action map that reflects the user's learning status. This makes it possible to generate an action map that reflects the user's learning status using the user's search history and the user's dialogue history.

[0108] Furthermore, the action map in this embodiment is composed of a tree-structured data model in which tasks are nodes, and tasks corresponding to nodes can be displayed in an expanded or collapsed state. This allows users to easily find the necessary information from the action map by expanding the necessary information or collapsing the unnecessary information.

[0109] Furthermore, the learning progress analysis unit 33 of this embodiment uses the machine learning model 6 to infer interruption patterns and proposes personalized improvement measures based on the cause of the interruption. This allows the machine learning model 6, which can find patterns in interrupted data, to propose improvement measures that enable users to continue learning. Additionally, by training the machine learning model 6 with data showing the learning status of a large number of users, it becomes possible to propose improvement measures before learning is interrupted.

[0110] Furthermore, the action map adjustment unit 34 of this embodiment adjusts the action map based on the results of the learning progress analysis using a machine learning model 7 constructed by reinforcement learning. This allows for the proposal of a support strategy tailored to the learning user using reinforcement learning, thereby promoting continued learning.

[0111] Furthermore, the shared processing unit 35 in this embodiment accepts modifications or suggestions for the action map from participants, and the action map adjustment unit 34 adjusts the action map so that the modifications or suggestions from participants are reflected. This allows the action map to be treated like open source, and the action map can be improved through collective intelligence.

[0112] Furthermore, the learning management information processing system 100 of this embodiment further includes a change management unit 36 ​​that stores the change history of tasks and manages the content of the changes along with the timing of the changes. This allows the action map to be checked for each version, improving user convenience.

[0113] With the functionality and implementation of the learning management information processing system 100 of this embodiment, the hierarchical action map goes beyond being merely a visualization tool for learning plans, becoming an adaptive, flexible, and interactive learning management information processing system 100. Users can effectively grasp and manage their entire learning process, from broad goals to specific actions, while enjoying a learning experience customized to their individual needs.

[0114] Although one embodiment of the present invention has been described above, the present invention is not limited to the embodiments described above, and any modifications, improvements, etc. that can achieve the objectives of the present invention are included in the present invention.

[0115] Furthermore, the series of processes described above can be executed by hardware or by software. In other words, the functional configuration described above is merely illustrative and not particularly limiting. That is, it is sufficient that the information processing device 1 is equipped with a function that can execute the series of processes described above as a whole, and the type of functional block used to realize this function is not particularly limited to the example above. Also, the location of the functional block is not particularly limited and can be arbitrary. For example, the functional block of the information processing device 1 may be transferred to another device, etc. Conversely, the functional block of another device may be transferred to a server, etc. Also, a single functional block may be composed of hardware alone, software alone, or a combination of both.

[0116] When a series of processes are executed by software, the programs that make up that software are installed on a computer or other device from a network or storage medium. The computer may be a computer built into dedicated hardware. Alternatively, the computer may be a computer capable of performing various functions by installing various programs, such as a server, a general-purpose smartphone, or a personal computer.

[0117] Such recording media containing programs may consist not only of removable media (not shown) distributed separately from the main device to provide the programs, but also of recording media provided pre-installed in the main device. Since programs can be distributed via a network, the recording media may be installed on or accessible from a computer connected to or capable of connecting to a network.

[0118] In this specification, the step of describing a program to be recorded on a recording medium includes not only processes that are performed chronologically in that order, but also processes that are not necessarily performed chronologically, but are executed in parallel or individually. Furthermore, in this specification, the term "system" refers to an overall system composed of multiple devices, means, etc.

[0119] 1. Information processing device 2. User terminal 5. Natural language processing model 6. Machine learning model 7. Machine learning model 31. Action map generation unit 32. Action map acquisition unit 33. Learning progress analysis unit 34. Action map adjustment unit 35. Shared processing unit 36. Change management unit 37. Effectiveness evaluation processing unit 90. Database 100. Learning management information processing system

Claims

1. A learning management information processing system comprising: an action map acquisition means for acquiring an action map in which multiple tasks are hierarchically set to achieve a user's learning objectives; a learning progress analysis means for monitoring the user's learning progress and analyzing the learning progress status, including whether or not learning has been interrupted; an action map adjustment means for adjusting the tasks in the action map set for the user based on the results of the learning progress analysis and presenting them to the user; and a sharing processing means for sharing information about the action map with participants belonging to a community in which the user participates.

2. The learning management information processing system according to claim 1, further comprising action map generation means for setting the learning objectives based on user input information including at least one of the user's search history and the user's dialogue history, and generating the action map that reflects the user's learning status.

3. The learning management information processing system according to claim 1, wherein the action map is composed of a tree structure data model with the tasks as nodes, and the tasks corresponding to the nodes can be displayed in an expanded or collapsed state.

4. The learning management information processing system according to claim 1, wherein the learning progress analysis means uses a machine learning model to infer interruption patterns and proposes personalized improvement measures based on the cause of the interruption.

5. The learning management information processing system according to claim 1, wherein the action map adjustment means adjusts the action map based on the analysis results of the learning progress using a machine learning model constructed by reinforcement learning.

6. The learning management information processing system according to claim 1, wherein the shared processing means receives modifications or suggestions for the action map by the participants, and the action map adjustment means adjusts the action map so that the modifications or suggestions by the participants are reflected.

7. The learning management information processing system according to claim 6, further comprising a change management unit that stores the change history of the task and manages the content of the changes along with the timing of the changes.

8. A control method for an information processing device, comprising: an action map acquisition step of acquiring an action map in which multiple tasks for achieving a user's learning objectives are hierarchically set; a learning progress analysis step of monitoring the user's learning progress and analyzing the learning progress status, including whether or not learning has been interrupted; an action map adjustment step of adjusting the tasks in the action map set for the user based on the results of the learning progress analysis and presenting them to the user; and a sharing processing step of sharing information about the action map with participants belonging to a community in which the user participates.

9. A program for causing a computer to perform the following steps: an action map acquisition step of acquiring an action map in which multiple tasks are hierarchically set up to achieve a user's learning objectives; a learning progress analysis step of monitoring the user's learning progress and analyzing the learning progress status, including whether or not learning has been interrupted; an action map adjustment step of adjusting the tasks in the action map set up for the user based on the results of the learning progress analysis and presenting them to the user; and a sharing processing step of sharing information about the action map with participants belonging to a community in which the user participates.

Images