Platform for creating learning content

Abstract

The invention is directed toward the creation of a platform for creating personalized and adaptive learning content. The claimed platform includes the following elements: a database capable of obtaining and storing data from external sources of information; a digital asset management system capable of obtaining and storing data from the database and managing the obtained data; a graph-based learning management system capable of managing a graph with the aid of artificial intelligence algorithms by analyzing and transforming the structure of the graph to provide personalized learning content using a learning content repository and the digital asset management system; a learning content repository capable of analyzing information obtained from the digital asset management system and adding identified information to at least one graph of the graph-based learning management system; an adaptive learning module capable of interacting with the graph-based learning management system and the learning content repository to create adaptive learning programmes using artificial intelligence algorithms; and an assessment module capable of interacting with the graph-based learning management system to create test assignments based on the created learning content and further capable of using artificial intelligence algorithms to adjust the level of difficulty of test assignments depending on successfully completed test assignments.

Description

[0001] EDUCATIONAL CONTENT CREATION PLATFORM

[0002] AREA OF TECHNOLOGY

[0003] This technical solution relates to the field of information technology, namely to platforms for creating personalized and adaptive educational content.

[0004] LEVEL OF TECHNOLOGY

[0005] A method for adaptive learning is known from information source US9626875B2, published on April 18, 2017. The method includes operations performed for dynamically grouping and regrouping students based on their tracked progress in interacting with digital educational learning objects; dynamically arranging the components and elements of a digital learning object taking into account pedagogical goals, pedagogical priorities, or pedagogical significance or elements; allowing a teacher to define differential stop lines for different groups of students; allowing a teacher to command that all student devices temporarily represent a single learning object; allowing a content publisher to receive aggregated feedback based on tracked progress; and allowing the content publisher to package the objects as portable, self-contained playback units.

[0006] The proposed solution differs from the prior art in that the proposed solution uses a graph learning management system with adaptive learning.

[0007] ESSENCE OF THE INVENTION

[0008] The technical challenge addressed by the proposed solution is the creation of a platform for educational content, using a graph-based learning management system and artificial intelligence algorithms to create personalized and adaptive educational content.

[0009] The technical result achieved by solving the above technical problem is the creation and updating of personalized and adaptive educational content.

[0010] The claimed technical result is achieved through the operation of a platform for creating educational content running on a computing device containing a processor and memory storing instructions executed by the processor, comprising: a database configured to receive and store data obtained from external information sources; a digital asset management system configured to receive and store data from the database and to manage the received data; a graph learning management system configured to manage the graph using artificial intelligence algorithms by analyzing and transforming the graph structure to provide personalized educational content using an educational content repository and a digital asset management system;an educational content repository configured to analyze information received from a digital asset management system and add the identified information to at least one graph of a graph learning management system; an adaptive learning module configured to interact with the graph learning management system and the educational content repository to create adaptive educational programs using artificial intelligence algorithms; an assessment module configured to interact with the graph learning management system to create test tasks based on the created educational content, and also configured to use artificial intelligence algorithms to adjust the difficulty level of the test tasks depending on the number of successfully completed test tasks.

[0011] DESCRIPTION OF DRAWINGS

[0012] The invention will be further described in accordance with the accompanying drawings, which are provided to illustrate the invention and in no way limit its scope. The following drawings are attached to the application:

[0013] Fig. 1 illustrates the diagram of the platform components.

[0014] DETAILED DESCRIPTION OF THE INVENTION

[0015] The following detailed description of the invention includes numerous implementation details to provide a clear understanding of the present invention. However, one skilled in the art will readily understand how the present invention may be used with or without these implementation details. In other instances, well-known methods, procedures, and components have not been described in detail to avoid obscuring the features of the present invention.

[0016] Furthermore, it will be clear from the foregoing description that the invention is not limited to the embodiment described. Numerous possible modifications, changes, variations, and substitutions, while preserving the spirit and form of the present invention, will be apparent to those skilled in the art.

[0017] The proposed platform provides knowledge management and uses an artificial intelligence-based approach to automate the creation and updating of educational content, which facilitates interactive learning.

[0018] The platform is designed to host a variety of educational programs in engineering, science, and technology. A strong emphasis is placed on lifelong learning, providing students with relevant knowledge and skills throughout their lives.

[0019] The platform for creating educational content includes the following modules (Fig. 1): a database, a digital asset management system, a graph learning management system, an educational content repository, an assessment module, an adaptive learning module, an identity and access management system, a gamification system, and a progress and motivation tracking system.

[0020] The platform collects data (information, metadata, knowledge) from information sources that have open and restricted access.

[0021] Information in the materials of this application includes, but is not limited to: lecture and article texts, video lessons and audio recordings, course information (titles, descriptions, course requirements), etc.

[0022] Metadata, in the materials of this application, means data that helps manage information, such as, but not limited to: user data (ID, educational level, specialization, etc.), course data (course ID, author, creation date, etc.), user progress data (module start and end time, grades, etc.).

[0023] In this application, knowledge refers to the practical application of information, such as, but not limited to, completing assignments, passing tests, participating in discussions and projects, etc.

[0024] The collected data is fed into the knowledge discovery and extraction system, which is then extracted and entered into the knowledge repository database. The knowledge discovery and extraction system also receives user data, including, but not limited to, test and assignment results, information on learning interactions and activities, and user reviews and comments.

[0025] A knowledge discovery and extraction system processes and analyzes large volumes of data to transform it into structured knowledge. The knowledge discovery and extraction system preprocesses the received data, removes noise, normalizes it, and converts it into a format convenient for analysis. Analysis involves identifying patterns and useful information using algorithms such as classification, regression, and clustering to analyze learning patterns and user behavior; natural language processing (NLP) to analyze text data to extract themes, as well as semantic analysis and parsing; and statistical analysis and data visualization methods to interpret and present the data. Data extraction is performed using predefined rules and templates to extract specific data, such as determining achievements and learning goals. Data extraction is also performed using criteria for data discovery and extraction:

[0026] • Relevance: Information is assessed for its relevance to the learning objectives and needs of users.

[0027] • Relevance: Selecting data that is relevant to current learning trends and standards.

[0028] • Validity: checking data for accuracy and reliability.

[0029] • Comprehensiveness: the desire to ensure that the knowledge extracted is as complete and comprehensive as possible, covering all aspects of the topic being studied.

[0030] The knowledge repository includes a database, a digital asset management system, and a content management system.

[0031] A content management system (CMS) allows you to create, manage, and modify website content without the need for specialized technical knowledge. A CMS allows you to manage the content of a website or educational platform portal, update educational materials and course information, assign access rights to different users for editing and publishing content, and integrate with other systems, such as databases and digital asset management systems.

[0032] The database is designed to retrieve and store data obtained from external sources. The digital asset management system uses MinlO to store and manage digital assets, including images, video files, and PDF presentations. This ensures efficient retrieval and secure access to these assets. The digital asset management system allows data to be stored on a distributed network, improving availability and query processing speed. When data is distributed across multiple nodes, the system can process queries in parallel, significantly accelerating asset retrieval. The digital asset management system supports horizontal scalability, allowing the system to increase the number of nodes for storing and processing data as needed. This ensures high performance even as data volumes increase.The digital asset management system uses load balancing algorithms to optimize the distribution of data and requests across different nodes. This helps minimize latency and maximize data processing speed. The digital asset management system provides data encryption capabilities both at rest and in transit. This helps protect data from unauthorized access and leakage. The digital asset management system supports role-based access policies, allowing you to control who can interact with stored data and how. This includes the ability to configure read, write, and delete permissions for different users or groups. The digital asset management system maintains access and change logs, allowing you to track who interacted with the data and when. This is essential for ensuring data security and meeting regulatory requirements.Authentication methods are used to access data, including access tokens, which provide an additional level of security when accessing data through the API.

[0033] A graph-based learning management system (LMS) capable of graph manipulation using artificial intelligence algorithms to analyze and transform graph structure to provide personalized educational content using an educational content repository and a digital asset management system. To prepare personalized educational content, the LMS retrieves assets from the content management system.

[0034] In this application, an asset refers to any media resource used in the content. This may include images, video files, audio files, documents, PDF presentations, and other types of digital files.

[0035] In this application, "content" refers to informational content, which is a structured and formatted combination of assets, including text and other elements, designed to convey knowledge, information, or entertainment. This could be an article, training module, blog, video lesson, etc. Content includes text, media assets, and other elements combined to achieve a specific purpose. Each content element is uniquely designed and targeted for a specific audience or purpose. Content is managed through a content management system, which allows for the creation, editing, and publication of informational materials.

[0036] Assets serve as building blocks for content creation. For example, an educational video (content) may use various images, audio tracks, and video clips (assets), which together form the final educational product. A graph-based learning management system can integrate assets from a content management system to create personalized and adaptive learning courses, thereby ensuring the flexibility and scalability of educational programs.

[0037] The system is built on a graph, where each learning element is represented by a vertex, and the connections between these elements are represented by edges. For example, graph vertices may include, but are not limited to:

[0038] • Program. A large structural unit that includes several courses;

[0039] • Course. A basic educational unit that may include several modules;

[0040] • Module. A part of a course containing specific topics or sections;

[0041] • Lesson. A single learning event or class within a module;

[0042] • Assignment. Specific learning tasks or projects given to users to reinforce the material; and graph edges may be, but are not limited to:

[0043] • Sequence: Ribs can indicate the order in which courses, modules, lessons, and assignments should be taken;

[0044] • Access conditions. Edges can also include conditions under which a user can move from one node to another, such as requirements for successfully completing previous assignments or modules to access the next. The graph allows for dynamic modification of the learning process by adding or removing elements and connections based on curriculum needs or student preferences. Using analytics on student progress, the system can adapt the curriculum, suggesting additional resources or assignments to deepen knowledge or provide additional practice.

[0045] The educational content repository is configured to analyze information obtained from the digital asset management system and add the identified information to at least one graph of the learning management system. In the educational content repository, which interacts with the digital asset management (DAM) system, information analysis occurs using the following methods and algorithms.

[0046] Metadata extraction. Algorithms extract metadata from assets, such as authorship data, creation dates, keywords, and tags that describe the content and context of the assets. Metadata extraction utilizes image recognition and text analysis technologies.

[0047] Content analysis. Natural language processing (NLP) and computer vision algorithms analyze the content of assets, identifying thematic and semantic relationships. Content analysis can include content classification, identifying key themes, sentiment analysis, and more.

[0048] Interaction analysis. Collecting and analyzing data on how users interact with assets, including views, downloads, and comments. Machine learning methods such as clustering and sequence analysis are used to identify patterns of user behavior and interests. Adaptive learning. Using learning and interaction data to customize learning materials and approaches. Machine learning algorithms adapt content in real time based on student feedback and performance.

[0049] Adding information to a graph learning management system involves the following steps.

[0050] Graph modification and expansion. New knowledge and data obtained from the DAM are used to update existing nodes or add new nodes and edges to the graph. This enables curriculum expansion and the addition of new modules or courses. Dependency management. New relationships and sequences between course elements are identified based on data analysis. This may include establishing prerequisites or recommended learning paths.

[0051] Personalized learning. Information about user interactions and preferences is used to customize learning paths in the graph, allowing for customized learning experiences for students.

[0052] Dynamic updating. The graph is updated in real time based on incoming data, allowing the educational process to quickly adapt to changes in the educational landscape and student needs.

[0053] The educational content repository utilizes a node-to-application architecture that supports recursive interactions to enhance content discovery and engagement. The educational content repository utilizes active learning strategies, leveraging resources such as forum discussions, collaborative projects, and other interactive tools within the platform.

[0054] An example of the use of the node-to-application architecture in the proposed solution

[0055] Online learning using an interactive video course on programming.

[0056] Nodes. In this case, nodes can be servers or containers, each of which stores specific parts of the course:

[0057] Node A contains video tutorials on the basics of programming.

[0058] Node B stores interactive tests and tasks.

[0059] Node C manages a forum where students discuss the course and help each other.

[0060] Applications. Client applications on user devices that access nodes to obtain the necessary resources:

[0061] The user application requests video tutorials from Node A.

[0062] When the user is ready to test, the application contacts Node B to download the tests.

[0063] To participate in discussions, the application connects to Node C.

[0064] The system can use information about how students interact with different nodes to adapt and optimize learning. For example, if users are struggling with a certain type of problem from Node B, the system can automatically suggest additional resources from Node A or C to deepen their understanding of the topic.

[0065] The advantages of this architecture include the ability to add new nodes with additional content or functionality without disrupting the main application. Low latency: Since applications access nodes directly, response times are reduced, which is especially critical in interactive and multimedia applications. Failure tolerance: The failure of one node does not necessarily lead to a complete system shutdown, as other nodes can continue to service requests.

[0066] The educational content repository serves as a dynamic wiki source, allowing the platform to adapt to the changing educational landscape and provide students with up-to-date knowledge.

[0067] Providing relevant knowledge on an educational platform, especially in the context of a constantly changing educational landscape, requires the use of advanced technologies and methodologies, such as:

[0068] 1. Adaptive learning

[0069] The platform uses machine learning algorithms to analyze students' educational progress and preferences. Based on this analysis, the system can adapt learning materials, providing personalized assignments, course recommendations, and additional resources tailored to the student's current knowledge level and interests.

[0070] 2. Continuous content updating

[0071] Editors and educational analysts regularly review and update educational materials to ensure they are in line with the latest scientific discoveries, technological innovations, and legislative changes. This includes updating lectures, videos, texts, and tests.

[0072] 3. Feedback from users

[0073] Collecting feedback from students and teachers. This information is used to improve content and teaching methods. For example, if many students are struggling with a particular topic, the platform can add additional learning materials or explanatory videos.

[0074] 4. Using graph technologies

[0075] Graph-based learning management systems, as mentioned earlier, allow for dynamic changes to the structure and content of training courses. This facilitates rapid adaptation to new requirements and the inclusion of new topics and materials.

[0076] 5. Application of active learning

[0077] Supporting learning through forum discussions, group projects, and other interactive forms of work helps students actively engage in the learning process, promoting a deep understanding of the material and the acquisition of relevant knowledge.

[0078] An adaptive learning module designed to interact with a graph learning management system and an educational content repository to create adaptive educational programs using artificial intelligence algorithms;

[0079] To build a model for constructing a learning path based on xAP1 data, the following algorithms are used:

[0080] Classification: This is an approach where algorithms such as decision trees, random forests, gradient boosting, or neural networks can be used to determine which learning modules or courses are most suitable for a particular user based on their previous interactions and achievements.

[0081] Clustering: Algorithms such as K-means or hierarchical clustering can help group users based on their learning behavior and preferences, allowing for the creation of personalized learning paths.

[0082] Recommender systems: Using collaborative filtering or content-based filtering methods, personalized recommendations for courses or learning materials can be created based on past behavior and similarities with other users.

[0083] Sequential modeling: Algorithms such as hidden Markov models (HMMs) or recurrent neural networks (RNNs) can be used to analyze sequences of learning activities and predict the next steps in learning.

[0084] Survival analysis: Can be used to analyze the time it takes users to complete different learning modules, which can help optimize learning paths and predict potential barriers.

[0085] To describe the process of training and evaluating an algorithm in the context of developing an adaptive learning system using xAPI (Experience API)-based data, the following key stages can be identified:

[0086] 1. Data preparation. At this stage, data on learners' interactions with educational content is collected and preprocessed. This data may include information on courses completed, assignments completed, study time, and other parameters reflecting the learning process. Data preparation also includes removing errors and omissions from the data, as well as normalizing and transforming it into a format suitable for processing by machine learning algorithms.

[0087] 2. Formation of training and test samples

[0088] At this stage, the completed dataset is split into two parts: a training set, which will be used to train the algorithm, and a test set, which will be used to evaluate the quality of the trained model. Splitting the data allows us to assess how well the model can adapt to new, previously unseen data, which is critical for creating an effective adaptive learning system.

[0089] 3. Training the algorithm

[0090] Using a training set, a machine learning algorithm is trained to predict optimal learning paths based on xAP1 data. The model can take into account various factors, such as user preferences, previous achievements, and areas requiring additional attention. The goal is to create personalized and adaptive learning paths that maximize learning efficiency for each individual.

[0091] 4. Evaluation of results

[0092] After training the algorithm, its effectiveness is tested on a test set. Results can be evaluated using various metrics, such as precision, recall, F-score, and others, depending on the specific goals of the system. This stage not only assesses the quality of the current model but also identifies potential areas for further improvement.

[0093] An assessment module capable of interacting with a graph-based learning management system to generate test assignments based on the created educational content, and capable of using artificial intelligence algorithms to adjust the difficulty level of test assignments based on successfully completed test tasks.

[0094] To adjust the difficulty level of test questions, the assessment module, which interacts with the graph-based learning management system, uses artificial intelligence algorithms based on the analysis of data on students' past experience and their current progress. The key algorithms include machine learning and adaptive testing.

[0095] Algorithms for adjusting test difficulty

[0096] 1. Adaptive testing (Computer Adaptive Testing, CAT)

[0097] Steps: Initialization: The initial difficulty level is set at the average level or based on the student's previous results.

[0098] User Response: The user answers the question and their response is analyzed.

[0099] Difficulty adjustment: if the answer is correct, the next question will be more difficult; if the answer is incorrect, it will be easier.

[0100] Evaluation and Analysis: Upon completion of the test, overall performance is assessed and conclusions are drawn about the student's knowledge.

[0101] 2. Machine learning algorithms

[0102] Steps:

[0103] Data collection: Data is collected on user performance, including number of attempts, response time, and error rate.

[0104] Model training: Using this data, a machine learning model is trained that can predict the optimal difficulty level for each user.

[0105] The model is used in real time to adapt test tasks to the abilities of each user.

[0106] Data for training algorithms

[0107] Historical performance data. This uses data on how students have previously performed on tasks of varying difficulty.

[0108] Demographic data. Can be used to identify learning trends based on age, educational level, and other factors.

[0109] Answers to questions. Detailed analysis of the time spent on each answer and the frequency of correct / incorrect answers.

[0110] These algorithms and data help create a truly personalized and adaptive assessment process that can effectively reflect and support the learning needs of each student, thereby improving overall learning effectiveness.

[0111] An identity and access management system (IAMS) is responsible for authentication, role management, and permissions to ensure user access and security. It provides robust protection against unauthorized access and guarantees data confidentiality in accordance with applicable standards. Protection against unauthorized access and the security of confidential data in an IAM system are ensured through the following key measures:

[0112] Authentication: Verifying user credentials using passwords.

[0113] Password Encryption: Using the bcrypt algorithm to securely store passwords.

[0114] Role and Permission Management: Assign and control access to resources based on a user's role.

[0115] SSL / TLS: Protects data during transmission over encrypted SSL / TLS connections.

[0116] Logging and Monitoring: Maintain logs of user actions to enable auditing and detection of unusual activity.

[0117] The gamification system utilizes game design elements and principles in a non-game context to enhance user engagement and learning. It includes features such as tokens (IU Talents), badges, leaderboards, and achievement levels that motivate learners to progress through the course. The system also offers assignments and quests for learners, encouraging them to delve deeper into topics and apply their acquired knowledge in practical situations.

[0118] Gamification systems in educational contexts are designed to leverage various aspects of human motivation. Here's an example of such a system, incorporating elements of game design:

[0119] An example of a gamification system in online education

[0120] 1. Tokens (III Talents)

[0121] Description: A virtual currency that users earn for actively participating in courses, completing assignments, and participating in discussions to encourage ongoing engagement and provide the ability to "purchase" access to additional materials or special courses.

[0122] 2. Icons

[0123] Description: Badges are awarded for achieving specific learning milestones, such as successfully completing a module or mastering a challenging topic, to keep students motivated through visual recognition of their progress.

[0124] 3. Leaderboards

[0125] Description: Displays student rankings based on their activity, performance, and engagement to introduce elements of competition and social comparison to motivate participants. 4. Achievement Levels

[0126] Description: A system of levels that students achieve as they progress through the course, each level requiring more effort and offering more rewards, to create a sense of progress and development, deepening students' commitment to the course.

[0127] 5. Tasks and quests

[0128] Description: Special project assignments that require practical application of knowledge. Quests may involve solving real-world problems or completing complex tasks. Completing assignments and quests encourages users to delve deeper into topics and actively apply their knowledge in non-standard and practical situations.

[0129] This gamification system integrates with the educational platform and uses data on student actions and performance to automatically manage rewards and display progress, making learning more engaging and motivating.

[0130] The progress tracking and motivation system monitors user achievements and progress, offering a rewards system to encourage and recognize success. It provides comprehensive analytics on student progress, helping students and their teachers identify strengths and areas for improvement.

[0131] The platform's progress tracking and motivation system uses a variety of methods to identify each student's strengths and areas for improvement.

[0132] 1. Regular testing

[0133] Students take regular tests and quizzes to assess their knowledge and skills in various topics. These test results provide information about which areas the student has mastered well and where they need additional support.

[0134] 2. Analysis of interactions with the course

[0135] The system analyzes how students interact with learning materials. This includes tracking which sections of the course have been completed, how much time students spent studying specific topics, and how often they return to specific learning materials.

[0136] 3. Performance Analytics: The system collects data on grades for assignments, projects, and tests. This helps identify patterns in performance and identify areas in which students perform well or poorly.

[0137] 4. Feedback from teachers

[0138] Instructors can provide personalized feedback to students based on their performance and participation in the course. This feedback is an important element in assessing students' strengths and learning needs.

[0139] The system integrates all of the above data to create a comprehensive profile of each student.

[0140] A computing system that provides the data processing necessary for the implementation of the claimed solution generally contains the following components: one or more processors, at least one memory, a data storage means, input / output interfaces, an input means, and network interaction means.

[0141] When executing machine-readable commands contained in the RAM, the processor of the device is configured to perform the basic computing operations necessary for the operation of the device or the functionality of one or more of its components.

[0142] Memory is typically implemented as RAM, where the necessary software logic is loaded to provide the required functionality. When implementing the proposed solution, the memory capacity required for its implementation is allocated.

[0143] The data storage device can be a HDD, SSD, RAID array, network storage, flash memory, etc. It enables long-term storage of various types of information, such as the aforementioned files with user / passenger data sets, databases containing records of time intervals measured for each user, user IDs, etc.

[0144] Interfaces are standard means for connecting and operating peripherals and other devices, such as USB, RS232, RJ45, COM, HDMI, PS / 2, Lightning, etc.

[0145] The choice of interfaces depends on the specific device implementation, which may be a personal computer, mainframe, server cluster, thin client, smartphone, laptop, etc. A keyboard can be used as a data input device in any embodiment of the system implementing the described method. The keyboard hardware can be any known hardware implementation: it could be a built-in keyboard used on a laptop or netbook, or a separate device connected to a desktop computer, server, or other computing device.The connection can be either wired, in which the keyboard's cable is connected to a PS / 2 or USB port on the desktop computer's system unit, or wireless, in which the keyboard communicates wirelessly, such as via radio, with a base station, which is directly connected to the system unit, such as a USB port. In addition to the keyboard, input devices can also include a joystick, display (touchscreen), projector, touchpad, mouse, trackball, stylus, speakers, microphone, and so on.

[0146] Network communication tools are selected from a device that provides network data reception and transmission, such as an Ethernet card, WLAN / Wi-Fi module, Bluetooth module, BLE module, NFC module, IrDA, RFID module, GSM modem, etc. These tools facilitate data exchange via a wired or wireless data transmission channel, such as WAN, PAN, LAN, Intranet, Internet, WLAN, WMAN, or GSM.

[0147] The device components are connected via a common data bus.

[0148] In these application materials, a preferred disclosure of the implementation of the claimed technical solution was presented, which should not be used as limiting other particular embodiments of its implementation, which do not go beyond the scope of the requested scope of legal protection and are obvious to specialists in the relevant field of technology.

Claims

Formula 1. A platform for creating educational content, running on a computing device containing a processor and a memory storing instructions executed by the processor, comprising: a database configured to receive and store data obtained from external information sources; a digital asset management system configured to receive and store data from the database and to manage the received data; a graph learning management system configured to implement graph management using artificial intelligence algorithms by analyzing and transforming the graph structure to provide personalized educational content using an educational content repository and a digital asset management system;an educational content repository configured to analyze information received from a digital asset management system and add the identified information to at least one graph of a graph learning management system; an adaptive learning module configured to interact with the graph learning management system and the educational content repository to create adaptive educational programs using artificial intelligence algorithms; an assessment module configured to interact with the graph learning management system to create test tasks based on the created educational content, and also configured to use artificial intelligence algorithms to adjust the difficulty level of the test tasks depending on the number of successfully completed test tasks.

Images