Description:TECHNICAL FIELD

[0001] The present invention generally relates to educational technology and AI-driven learning systems. More specifically, the present invention relates to an artificial intelligence (AI)-based system and method for providing a collaborative learning and problem-solving environment.

BACKGROUND

[0002] Educators rely on case-based learning to build critical thinking, problem-solving, and teamwork skills. Specifically, the Harvard-style case study methodology, recognized as the gold standard in business, law, and management education, emphasizes open-ended, discussion-driven learning. However, educational institutions struggle to implement this approach effectively at scale.

[0003] Current classroom-based methods demand significant faculty involvement to facilitate discussions, making them resource-intensive and unsustainable for large classes. In online environments, platforms fail to provide real-time facilitation or adaptive guidance, which are critical for equitable participation and meaningful learning outcomes.

[0004] Further, existing online collaborative platforms such as Zoom, Microsoft Teams, and Google Classroom only enable basic communication and lack to provide learning support. Similarly, current AI-driven education tools focus on individualized pathways, offering content delivery, automated grading, or chat-based tutoring, but they do not optimize group-based problem-solving or enable structured collaboration. Even analytics-enabled education systems fail to address the core challenges of collaborative learning, as they typically track only surface-level activity data, such as time spent or course completion.

[0005] Consequently, institutions struggle to scale rich, discussion-driven pedagogy in large or remote classrooms, where faculty cannot provide the same level of personalized facilitation to every learner group. Group sessions often exhibit imbalanced participation, with certain learners dominating discussions while others remain disengaged, resulting in unequal learning outcomes. Furthermore, facilitation in existing systems remains static and non-adaptive. These systems do not respond dynamically to varying levels of engagement, learner knowledge profiles, or the changing dynamics of discussions, leading to limited support for meaningful and effective collaboration.

[0006] Few existing patent applications attempt to address the problems cited in the background as prior art over the presently disclosed subject matter and are explained as follows.

[0007] US11107362 assigned to EXPLOROS Inc entitled “system and method for collaborative instruction”, discloses a system and method for providing collaborative, digital learning experiences to a plurality of users on a plurality of user devices. The learning experience is divided into multiple scenes. Each scene may include one or more elements. Each element in the learning experience provides at least one item of media content to a user. Data associated with the user accessing an element in the learning experience may be received or recorded by the element.

[0008] US20240412654 assigned to Phillip Olla entitled “artificial intelligence driven educational method” discloses a method for providing personalized educational content. The method involves capturing a learner's initial learning preferences, styles, and knowledge to generate an AI Key unique to the learner; presenting the learner with educational material from an educator; dynamically updating the AI Key based on continuous learner interactions with the educational material and the learner's progress; utilizing the AI Key to inform AI-driven educational tools and services and an educator about the learner's personalized learning profile; and iteratively updating the educational material using the AI-driven educational tools and services and the educator's input to tailor the updated educational material to the learner based on the dynamically updated AI key. The method additionally prompts the educator to create or provide additional educational content tailored to the learner's personalized learning profile, the learner's interactions with the educational material, and the learner's progress. The educational material is generated by the educator or with assistance of AI.

[0009] However, these existing systems primarily focus on delivering digital experiences or personalized individual learning pathways without offering a comprehensive, structured framework for group learning.

[0010] Therefore, there exists a need for an Artificial intelligence (AI)-based system and method that enables a structured, role-based collaborative learning and problem-solving environment, providing real-time adaptive facilitation and analytics-driven insights. The system needs to seamlessly integrate with existing digital learning infrastructures, support both synchronous and asynchronous group learning, and deliver measurable individual and group performance data.

SUMMARY

[0011] The present invention discloses an Artificial Intelligence (AI)-based system for providing a collaborative learning and problem-solving environment. The system comprises at least one computing device, at least one database, at least one first user device associated with a learner, and at least one second user device associated with a teaching assistant, all in communication via a network. The computing device is configured to provide the collaborative learning and problem-solving environment and includes artificial intelligence (AI) and machine learning (ML) modules. The database is configured to store a plurality of learning and problem-solving sessions, learner profile data, and teaching assistant profile data. The user devices are configured to enable access to the collaborative learning and problem-solving environment for learners and teaching assistants.

[0012] The computing device comprises at least one memory configured to store a plurality of program modules and at least one processor configured to execute the program modules. The program modules include a content management module, a teaching assistant module, a learner module, a role assignment module, a collaborative workspace module, an AI-based facilitation module, an analytics module, and a dashboard module.

[0013] The content management module is configured to enable the teaching assistant to at least one of upload, create, and manage one or more learning activities, including case studies. The teaching assistant module is configured to enable the teaching assistant to select at least one case study and define one or more parameters, including a number of learners permitted to participate in the selected case study. The learner module is configured to enable learners to register for participation in at least one case study.

[0014] The role assignment module is configured to assign at least one role to each learner based on learner profile data and problem statement of the case study, and to form one or more learner groups for the selected case study. The role assignment module is further configured to dynamically adjust the assigned role during the collaborative learning and problem-solving session based on participation metrics or changes in group composition. Learner roles are selected from a group including, but not limited to, a problem analyst, a researcher, a solution designer, an evaluator, and a presenter. The learner profile data includes aptitude, knowledge, personality, technical skills, social consciousness, application skills, and career fitment.

[0015] The collaborative workspace module is configured to provide a collaborative environment for executing one or more collaborative learning and problem-solving sessions, including case studies, and to enable the learners to submit work data. The collaborative workspace module supports synchronous and asynchronous interactions including at least one of text, voice, or video communication. The collaborative environment further comprises shared tools including whiteboards, shared document spaces, and annotation tools for collaborative solution design.

[0016] The AI-based facilitation module is configured to monitor and analyze learner interactions during the collaborative learning and problem-solving session and generate facilitation outputs. The facilitation outputs include guidance directives comprising interrogative or guiding statements to steer the learning and problem-solving session toward targeted objectives. The AI-based facilitation module is further configured to automatically adjust the complexity of discussions and the intensity or frequency of facilitation interventions based on group dynamics and individual role performance metrics. The system is configured to utilize natural language processing (NLP) for analyzing work data from learners and generating adaptive facilitation output.

[0017] The analytics module is configured to evaluate individual and group contributions during the collaborative learning and problem-solving session and generate individual reports for each learner and group performance reports for each learner group. The analytics module is further configured to integrate the evaluated individual and group insights into each learner’s personalized learning pathway within an intelligent learning infrastructure, thereby enabling adaptive learning and targeted performance enhancement. The dashboard module is configured to present insight data and analytics data associated with at least one learning and problem-solving session.

[0018] In one embodiment, a method for providing a collaborative learning and problem-solving environment is disclosed. The method is implemented using the system comprising at least one computing device, at least one database, and user devices in communication via the network.

[0019] At one step, the content management module at the computing device enables the teaching assistant to at least one of upload, create, and manage one or more learning activities, including case studies. At another step, the teaching assistant module enables the teaching assistant to select at least one case study and define one or more parameters, including a number of learners permitted to participate in the selected case study. At another step, the learner module enables learners to register for participation in at least one case study.

[0020] At another step, the role assignment module assigns at least one role to each learner based on learner profile data and problem statement of the case study, and forms one or more learner groups for the selected case study. The module further dynamically adjusts the assigned role during the collaborative learning and problem-solving session based on participation metrics or changes in group composition.

[0021] At another step, the collaborative workspace module provides a collaborative environment for executing one or more collaborative learning and problem-solving sessions, including case studies, and enables learners to submit work data. The collaborative workspace module supports synchronous and asynchronous interactions including at least one of text, voice, or video communication and includes shared tools for collaborative solution design.

[0022] At another step, the AI-based facilitation module monitors and analyzes learner interactions during the collaborative learning and problem-solving session, and generates facilitation outputs, including guidance directives to steer the learning and problem-solving session toward targeted objectives. The module automatically adjusts the complexity of discussions and the intensity or frequency of facilitation interventions based on group dynamics and individual role performance metrics, and utilizes NLP for analyzing work data to generate adaptive facilitation outputs.

[0023] At another step, the analytics module evaluates individual and group contributions during the collaborative learning and problem-solving session and generates individual reports for each learner and group performance reports for each learner group. The module integrates the evaluated insights into each learner’s personalized learning pathway within an intelligent learning infrastructure to enable adaptive learning and targeted performance enhancement.

[0024] At another step, the dashboard module presents insight data and analytics data associated with at least one learning and problem-solving session. The system is further configured to interface with a collaborative web and cloud system via secure application programming interfaces (APIs) and encrypted communication protocols, wherein the collaborative web and cloud system comprises real-time collaboration frameworks for enabling real-time audio, video, and data communication during synchronous collaborative learning and problem-solving sessions.

[0025] The above summary contains simplifications, generalizations and omissions of detail and is not intended as a comprehensive description of the claimed subject matter but, rather, is intended to provide a brief overview of some of the functionality associated therewith. Other systems, methods, functionality, features and advantages of the claimed subject matter will be or will become apparent to one with skill in the art upon examination of the following figures and detailed written description.

BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The description of the illustrative embodiments can be read in conjunction with the accompanying figures. It will be appreciated that for simplicity and clarity of illustration, elements illustrated in the figures have not necessarily been drawn to scale. For example, the dimensions of some of the elements are exaggerated relative to other elements. Embodiments incorporating teachings of the present disclosure are shown and described with respect to the figures presented herein, in which:

[0027] FIG. 1 exemplarily illustrates an environment of an Artificial Intelligence (AI)-based system for providing a collaborative learning and problem-solving environment, according to an embodiment of the present invention.

[0028] FIG. 2 exemplarily illustrates a block diagram of the computing device connected to user devices, according to an embodiment of the present invention.

[0029] FIG. 3 exemplarily illustrates a flowchart of an example method providing the collaborative learning and problem-solving environment, according to an embodiment of the present invention.

[0030] FIG. 4 exemplarily illustrates a flowchart of an Artificial Intelligence (AI) -based method for providing the collaborative learning and problem-solving environment, according to another embodiment of the present invention.

[0031] FIG. 5 exemplarily illustrates a flowchart of a method for execution of the case study individually by the learners in the study group, according to an embodiment of the present invention.

[0032] FIG. 6 exemplarily illustrates a flowchart of a method for execution of the case study in a group collaborative mode, according to an embodiment of the present invention.

DETAILED DESCRIPTION OF EXAMPLE EMBODIMENTS

[0033] A description of embodiments of the present invention will now be given with reference to the Figures. It is expected that the present invention may be embodied in other specific forms without departing from its spirit or essential characteristics. The described embodiments are to be considered in all respects only as illustrative and not restrictive.

[0034] Referring to FIG. 1, the environment 100 of the system comprises at least one computing device 102 and at least one database 104 in communication with the computing device 102 via a network 106. The system further comprises a first user device 108 associated with a learner and a second user device 110 associated with a teaching assistant. The first user device 108 and the second user device 110 are in communication with the computing device 102 via the network 106. The first user device 108 and second user device 110 are also generally referred to as user device (108, 110).

[0035] The user device (108, 110) is configured to provide an interface to access the services provided by the computing device 102. The interface, for example, may be a platform that allows the user device (108, 110) to wirelessly connect and access the computing device 102 via the network 106. The user device (108, 110) includes workstations, desktops, laptops, personal digital assistants (PDAs), tablets, smartphones, or other computing devices capable of accessing and utilizing communication tools and applications.

[0036] The network 106 generally represents one or more interconnected networks, over which the computing device 102, the user device (108, 110) communicates with each other. The network 106 may include packet-based wide area networks such as the Internet, local area networks (LAN), private networks, wireless networks, satellite networks, cellular networks, paging networks, and the like. A person skilled in the art will recognize that the network 106 may also be a combination of more than one type of network. For example, the network 106 may be a combination of a LAN and the Internet. In addition, the network 106 may be implemented as a wired network, a wireless network, or a combination thereof.

[0037] The database 104 is in communication with the computing device 102. In one example, the database 104 resides in the computing device 102. In another example, the database 104 resides separately from the computing device 102. Regardless of the location, the database 104 comprises a memory to store and organize data for use by the computing device 102. The database 104 is configured to store information related to learning and problem-solving sessions, learners and teaching assistants including case studies, learner profile data, and teaching assistant profile data. The learner profile data includes aptitude, knowledge, personality, technical skills, social consciousness, application skills, and career fitment.

[0038] In one embodiment, the computing device 102 is at least one of a server, a general-purpose computer, a special-purpose computer, a workstation, a mainframe, a supercomputer and a server farm. Although the computing device 102 is illustrated as a single device, the functions performed by the computing device 102 could be performed using any suitable number of computing devices 102.

[0039] The computing device 102 is configured to enable the teaching assistant to at least one of upload, create, and manage one or more learning activities, including case studies. The case study includes, but not limited to, at least one of text, multimedia, simulation-based, or open-ended problem elements.

[0040] The computing device 102 is further configured to enable the teaching assistant to select at least one case study and define one or more parameters, including a number of learners permitted to participate in the selected case study. The computing device 102 is further configured to enable learners to register for participation in at least one case study selected by the teaching assistant.

[0041] The computing device 102 is further configured to assign at least one role to each learner based on learner profile data and problem statement of the case study, and form one or more learner groups for the selected case study. The role is selected from a group including, but not limited to, of a problem analyst, a researcher, a solution designer, an evaluator, and a presenter. The computing device 102 dynamically adapts role assignments during the session if a learner’s participation level falls below a defined threshold or if the group composition changes.

[0042] The problem analyst is assigned to identify key issues in the case study, the researcher is assigned to find supporting data, facts, and technical references, the solution designer is assigned to develop potential solutions, the evaluator is assigned to critically assess proposed solutions, and the presenter is assigned to summarize and present group findings.

[0043] The computing device 102 is further configured to provide a collaborative environment for executing one or more collaborative learning and problem-solving sessions, including case studies. The computing device 102 is configured to enable the learners to submit work data. The computing device 102 is configured to support synchronous and asynchronous interactions including at least one of text, voice, or video communication. The collaborative environment includes shared tools comprising whiteboards, shared document spaces, and annotation tools for collaborative solution design.

[0044] The computing device 102 is further configured to monitor and analyze learner interactions during the collaborative learning and problem-solving session and generate facilitation outputs. The facilitation outputs include guidance directives comprising interrogative or guiding statements to steer the learning and problem-solving session toward targeted objectives. The computing device 102 utilizes natural language processing (NLP) that analyses discussions in real time to detect reasoning gaps, off-topic interactions, or underdeveloped arguments. The system generates adaptive guidance prompts to foster deeper engagement and balanced participation among learners.

[0045] The computing device 102 is further configured to evaluate individual and group contributions during the collaborative learning and problem-solving session and generate individual reports for each learner and group performance report for each learner group. The reports include performance indicators such as quality of reasoning, novelty of ideas, relevance of supporting evidence, and overall collaboration effectiveness. These analytics are integrated into the learner’s personalized learning pathway within the intelligent learning infrastructure.

[0046] The computing device 102 is further configured to dynamically adjust the assigned role during a collaborative learning and problem-solving session based on participation metrics or changes in group composition.

[0047] The computing device 102 is further configured to present insight data and analytics data associated with at least one learning and problem-solving session for learners and teaching assistants. The insight data includes actionable intervention recommendations such as role reassignment, targeted feedback, or provision of additional learning resources. The analytics data includes quantifiable indicators such as individual participation levels, contribution balance across roles, engagement intensity, and collaboration quality scores.

[0048] The computing device 102 supports seamless integration with intelligent learning infrastructures, enabling collected data and generated insights to feed into adaptive learning pathways, enhancing subsequent sessions with progressively refined personalization.

[0049] The computing device 102 is configured to execute the system workflow seamlessly from initiation to feedback integration. At the outset, the computing device 102 is configured to enable the teaching assistant to create or select a case study and configure participation parameters. The computing device 102 is further configured to assign roles to learners based on their profiles, thereby forming balanced and diverse learner groups. The computing device 102 is further configured to enable learners to engage synchronously or asynchronously within the collaborative workspace, leveraging shared tools for solution design and discussion. Throughout the session, the computing device 102 is configured to monitor and analyze discussions, provide real-time, adaptive facilitation, and maintain collaborative balance through context-driven guidance. Upon completion of the session, the computing device 102 is configured to enable learners to consolidate their inputs into structured deliverables, such as reports or presentations, and evaluate contributions to generate updated performance analytics that refine the personalized learning pathways of all participants.

[0050] The computing device 102 is configured to provide advancements over existing systems. The computing device 102 is configured to automate and dynamically adapt role assignments, ensuring structured participation and engagement throughout collaborative learning and problem-solving sessions. The computing device 102 is further configured to incorporate Harvard-style, open-ended, multidisciplinary problem scenarios that foster deep critical analysis.

[0051] The computing device 102 is configured to use real-time NLP-driven adaptive facilitation to generate context-specific guidance that promotes balanced discussions and advanced reasoning. The computing device 102 is configured to implement contribution analytics that map role-specific inputs to measurable group outcomes, enabling data-driven insights into collaboration quality. Additionally, the computing device 102 is configured to integrate seamlessly with intelligent learning infrastructures, ensuring that insights and analytics from each session are incorporated into subsequent sessions for progressive refinement and personalization of the learning experience.

[0052] The computing device 102 is configured with multiple technological components to support intelligent, adaptive, and collaborative learning functionalities. The computing device 102 includes artificial intelligence (AI) and machine learning (ML) modules configured to utilize natural language processing (NLP) for analyzing learner inputs and generating adaptive facilitation outputs, implement machine learning algorithms for automated and dynamic role assignments based on competency data and performance analytics, and perform sentiment and engagement detection to monitor group dynamics and interaction quality in real time.

[0053] The computing device 102 is further configured to interface with a collaborative web and cloud system via secure application programming interfaces (APIs) and encrypted communication protocols. The collaborative web and cloud system comprises WebRTC or equivalent frameworks for enabling real-time audio, video, and data communication during synchronous collaborative learning and problem-solving sessions. The collaborative web and cloud system comprises real-time collaboration frameworks.

[0054] FIG. 2 exemplarily illustrates a block diagram 200 of the computing device 102 connected to user devices (108, 110), according to an embodiment of the present invention. The computing device 102 comprises at least one memory 204 configured to store a set of program modules and at least one processor 202. The processor 202 is configured to execute one or more program modules to perform one or more operations of the system. The program modules comprise a content management module 206, a teaching assistant module 208, a learner module 210, a role assignment module 212, a collaborative workspace module 214, an AI-based facilitation module 216, an analytics module 218 and a dashboard module 220.

[0055] The content management module 206 is configured to enable the teaching assistant to at least one of upload, create, and manage one or more learning activities, including case studies.

[0056] The teaching assistant module 208 is configured to enable the teaching assistant to select at least one case study and define one or more parameters, including a number of learners permitted to participate in the selected case study.

[0057] The learner module 210 is configured to enable learners to register for participation in at least one case study. The role assignment module 212 is configured to assign at least one role to each learner based on learner profile data and problem statement of the case study, and to form one or more learner groups for the selected case study.

[0058] The collaborative workspace module 214 is configured to provide a collaborative environment for executing one or more collaborative learning and problem-solving sessions, including case studies. The collaborative workspace module 214 is configured to enable the learners to submit work data. The collaborative workspace module 214 is configured to support both synchronous collaborative learning and problem-solving sessions, including live, real-time discussions, and asynchronous, time-flexible learning and problem-solving sessions

[0059] The AI-based facilitation module 216 is configured to monitor and analyze learner interactions during the collaborative learning and problem-solving session and generate facilitation outputs. The facilitation outputs include guidance directives comprising interrogative or guiding statements to steer the learning and problem-solving session toward targeted objectives.

[0060] The AI-based facilitation module 216 is configured to function as a virtual facilitator during the collaborative learning and problem-solving session. The computing device 102 is configured to analyze ongoing discussions and generate facilitation outputs, including context-aware guidance prompts. The guidance prompts include interrogative or directive statements configured to encourage deeper reasoning, identify and highlight overlooked aspects of the discussion, and maintain alignment of the collaborative learning and problem-solving session with predefined learning objectives. The AI-based facilitation module 216 identifies low participation learners and prompts the learners accordingly.

[0061] The AI-based facilitation module 216 is further configured to automatically adjust the complexity of discussions and the intensity or frequency of facilitation interventions based on group dynamics and individual role performance metrics.

[0062] The analytics module 218 is configured to evaluate individual and group contributions during the collaborative learning and problem-solving session and generate individual reports for each learner and group performance report for each learner group. The analytics module 218 tracks contributions for each role and evaluates performance metrics such as idea novelty, evidence quality, and collaboration score.

[0063] The dashboard module 220 is configured to present insight data and analytics data associated with at least one learning and problem-solving session. The dashboard module 220 is configured to present performance data, skill development metrics, and engagement analytics associated with at least one learning and problem-solving session for faculty and students.

[0064] The AI-based facilitation module 216 is configured to track individual learner inputs based on the roles assigned during the collaborative learning and problem-solving session. The analytics module 218 is further configured to quantify individual contributions, including but not limited to research depth, analytical reasoning, design inputs, and quality of peer evaluations. The analytics module 218 is further configured to analyze collective group performance by evaluating group synergy and the effectiveness of collaborative problem-solving. The analytics module 218 is configured to integrate the evaluated individual and group insights into each learner’s personalized learning pathway within the intelligent learning infrastructure, thereby enabling adaptive learning and targeted performance enhancement. The computing device 102 is configured to provide a structured, role-driven, and AI-facilitated collaborative learning and problem-solving environment that replicates the depth and engagement of in-person, discussion-driven learning and problem-solving sessions at scale, while enabling the generation of measurable individual and group learning outcomes.

[0065] FIG. 4 exemplarily illustrates a flowchart 400 of the Artificial Intelligence (AI)-based method for providing the collaborative learning and problem-solving environment, according to another embodiment of the present invention.

[0066] At step 402, the content management module 206 is configured to enable the teaching assistant to at least one of upload, create, and manage one or more learning activities, including case studies

[0067] At step 404, the teaching assistant module 208 is configured to enable the teaching assistant to select at least one case study and define one or more parameters, including a number of learners permitted to participate in the selected case study. The case study includes at least one of text, multimedia, simulation-based, and open-ended problem elements.

[0068] At step 406, the learner module 210 is configured to enable learners to register for participation in at least one case study.

[0069] At step 408, the role assignment module 212 is configured to assign at least one role to each learner based on learner profile data and problem statement of the case study, and to form one or more learner groups for the selected case study. The role assignment module 212 is further configured to dynamically adjust the assigned role during the collaborative learning and problem-solving session based on participation metrics or changes in group composition. The role is selected from a group including a problem analyst, a researcher, a solution designer, an evaluator, and a presenter.

[0070] At step 410, the collaborative workspace module 214 is configured to provide a collaborative environment for executing one or more collaborative learning and problem-solving sessions, including case studies. The collaborative workspace module is configured to enable the learners to submit work data. The work data includes learner response or sequential learner responses, which is explained in FIG. 5 and FIG. 6. The collaborative workspace module 214 is configured to support synchronous and asynchronous interactions including at least one of text, voice, or video communication. The collaborative environment includes shared tools comprising whiteboards, shared document spaces, and annotation tools for collaborative solution design.

[0071] At step 412, the AI-based facilitation module 216 is configured to monitor and analyze learner interactions during the collaborative learning and problem-solving session and generate facilitation outputs. The facilitation outputs include guidance directives comprising interrogative or guiding statements to steer the learning and problem-solving session toward targeted objectives.

[0072] At step 414, the analytics module 218 is configured to evaluate individual and group contributions during the collaborative learning and problem-solving session and generate individual reports for each learner and group performance report for each learner group. The analytics module 218 is configured to integrate the evaluated individual and group insights into each learner’s personalized learning pathway within an intelligent learning infrastructure, thereby enabling adaptive learning and targeted performance enhancement.

[0073] At step 416, the dashboard module 220 is configured to present insight data and analytics data associated with at least one learning and problem-solving session. The AI-based facilitation module 216 is configured to automatically adjust the complexity of discussions and the intensity or frequency of facilitation interventions based on group dynamics and individual role performance metrics. The system is configured to utilize natural language processing (NLP) for analyzing work data from learners and generating adaptive facilitation output.

[0074] The computing device 102 is further configured to interface with a collaborative web and cloud system via secure application programming interfaces (APIs) and encrypted communication protocols. The collaborative web and cloud system comprises real-time collaboration frameworks for enabling real-time audio, video, and data communication during synchronous collaborative learning and problem-solving sessions.

[0075] FIG. 5 exemplarily illustrates a flowchart 500 of a method for execution of the case study individually by the learners in the study group, according to an embodiment of the present invention. The learner module 210, the collaborative workspace module 214, and the AI-based facilitation module 216 are configured to enable execution of the case study individually by the learners in the study group. At step 502, the learner module 210 initiates the case study in an individual learner mode. At step 504, the collaborative workspace module 214 transmits an automated message to the learner to initiate a case sequence or the case study. At step 506, the learner module 210 receives a learner response from the learner corresponding to the case study. At step 508, the AI-based facilitation module 216 analyses the learner response and generate facilitation outputs including calibrated feedback and refined responses to the learner to progress the case study towards completion.

[0076] At decision block 510, the system determines whether the learner response is sufficient for completion of the case study. Upon determining sufficiency, the process terminates. If the learner response is not sufficient, the method proceeds to decision block 512, wherein it is determined whether a predefined iteration threshold has been reached. If the iteration threshold is not reached, the process loops back to step 506, enabling the learner to provide additional responses based on refined prompts provided at step 514. Upon determining that the predefined iteration threshold has been reached, the process terminates at step 516. Thus, the system enables an adaptive learning loop that ensures completion of the case study through sufficient learner responses or termination upon exhaustion of the allowed iterations. In one embodiment, the collaborative workspace module 214 and the AI-based facilitation module 216 are configured to create an adaptive learning loop by providing refined responses for the predefined threshold of iteration to progress the case study towards completion.

[0077] FIG. 6 exemplarily illustrates a flowchart 600 of a method for execution of the case study in a group collaborative mode, according to an embodiment of the present invention. Upon completion of the case study individually by the learners in the study group, the learner module 210, the collaborative workspace module 214, and the AI-based facilitation module 216 are further configured to execute the collaborative group mode.

[0078] At step 602, the case study is initiated in the group collaborative mode with participation of multiple learners. At step 604, the collaborative workspace module 214 collects learner responses of the learners from their respective individual learner modes. At step 606, the collaborative workspace module 214 collects sequential learner responses from each learner. The sequential learner response is configured to build upon or contrast to at least one prior learner response. At step 608, the AI-based facilitation module 216 analyses the sequential learner responses to calibrate inputs, highlight patterns, and ensure balanced participation across the learners. At step 610, the AI-based facilitation module 216 triggers completion of the collaborative learning and problem-solving session upon determining that sufficient interaction and analysis have occurred based on at least one of a predefined number of responses, a quality threshold of responses, and a convergence of learner ideas. The group case study session concludes, producing a consolidated outcome for the learner group.

[0079] Thus, FIG. 6 illustrates the transition from individual learner mode to group collaborative mode, enabling structured participation, balanced contributions, and an AI-facilitated convergence of ideas into a consolidated group outcome.

Example:
[0080] FIG. 3 exemplarily illustrates a flowchart 300 of an example method providing the collaborative learning and problem-solving environment, according to an embodiment of the present invention. The system 300 comprises a set of learner roles including, but not limited to, a problem analyst 302, a researcher 304, a solution designer 306, an evaluator 308, and a presenter 310. Each learner is assigned a role based on learner profile data and the defined parameters of the case study.

[0081] The problem analyst 302 is configured to identify key issues in the case study, the researcher 304 is configured to fetch supporting data, facts, and technical references, the solution designer 306 is configured to propose technical solutions, the evaluator 308 is configured to critique and compare proposed options, and the presenter 310 is configured to summarize and present the group solution.

[0082] The outputs from the assigned learner roles are provided to the AI-facilitated collaborative chat 312 to aggregate learner inputs, facilitate real-time discussion, and guide the conversation using context-aware prompts. The system provides AI nudges and adaptive prompts 314, which includes guidance prompts, adaptive interventions, and suggestions to steer the discussion toward targeted learning objectives while balancing participation among learners.

[0083] The AI nudges and adaptive prompts 314 are processed by the AI evaluation and aggregation engine 316, which is configured to evaluate individual and group contributions, quantify performance metrics such as idea novelty, analytical reasoning, and collaboration quality, and aggregate the insights for reporting purposes. Finally, the individual and group analytics 318 is generated to present personalized learning outcomes, performance dashboards, and engagement analytics for each learner and learner group, thereby enabling adaptive learning pathways and targeted skill development.

[0084] The system, as illustrated in FIG. 3, provides a structured, role-driven, and AI-facilitated collaborative learning and problem-solving environment, replicating the depth and interactivity of in-person case study sessions at scale while generating measurable individual and group learning outcomes.

[0085] The system including Intelligent Learning Infrastructure (ILI) personalizes learning through AI-driven personalized adaptive pathways, skill-mapping, and performance analytics. This invention enhances the ILI by integrating a role-based, AI-assisted collaborative case study mechanism. The system is configured to combine Harvard-style case study pedagogy with intelligent, adaptive support mechanisms to enhance collaborative education. By integrating intelligent learning platforms, collaborative learning frameworks, and adaptive educational analytics, the system provides a scalable, data-driven, and context-aware environment that ensures structured participation, balanced collaboration, and measurable learning outcomes.

[0086] The system is configured to enable educational institutions and online learning platforms to deliver structured, AI-facilitated, role-based collaborative learning and problem-solving sessions, including case studies, at scale. The system is further configured to ensure balanced participation, generate personalized feedback, and produce measurable individual and group learning outcomes. The system is particularly suitable for learning and problem-solving environments where problem-solving, critical thinking, and interdisciplinary teamwork skills are essential.

[0087] The system uses natural language processing and engagement analytics to pose real-time nudges, highlight overlooked aspects, and stimulate deeper group discussion. The system measures individual and group contributions and feeds insights back into the learner’s personalized learning pathway within Intelligent Learning Infrastructure (ILI). This approach transforms traditional, faculty-intensive case study pedagogy into a scalable, measurable, and adaptive online learning experience, optimized for students.

[0088] While the disclosure has been described with reference to exemplary embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the scope of the disclosure. In addition, many modifications may be made to adapt a particular system, device, or component thereof to the teachings of the disclosure without departing from the essential scope thereof. Therefore, it is intended that the disclosure not be limited to the particular embodiments disclosed for carrying out this disclosure, but that the disclosure will include all embodiments falling within the scope of the appended claims. Moreover, the use of the terms first, second, etc. do not denote any order or importance, but rather the terms first, second, etc. are used to distinguish one element from another.

[0089] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used herein, the singular forms “a,” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises” and/or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

[0090] The description of the present disclosure has been presented for purposes of illustration and description, but is not intended to be exhaustive or limited to the disclosure in the form disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope of the disclosure. The described embodiments were chosen and described in order to best explain the principles of the disclosure and the practical application, and to enable others of ordinary skill in the art to understand the disclosure for various embodiments with various modifications as are suited to the particular use contemplated.
, Claims:What is claimed is:

1. An Artificial Intelligence (AI)-based system for providing a collaborative learning and problem-solving environment, comprising:

at least one computing device comprising at least one processor and a memory storing a plurality of program modules, wherein the computing device is configured to provide the collaborative learning and problem-solving environment, wherein the computing device includes artificial intelligence (AI) and machine learning (ML) modules;

at least one database in communication with the computing device via a network, wherein the database is configured to store a plurality of learning and problem-solving sessions, a learner profile data, and teaching assistant profile data;

at least one first user device associated with a learner, in communication with the computing device via the network, configured to enable access to the learning and problem-solving environment, and

at least one second user device associated with a teaching assistant, in communication with the computing device via the network, configured to enable access to the learning and problem-solving environment,

wherein the module comprises:

a content management module configured to enable the teaching assistant to at least one of upload, create, and manage one or more learning activities, including case studies;

a teaching assistant module configured to enable the teaching assistant to select at least one case study and define one or more parameters, including a number of learners permitted to participate in the selected case study;

a learner module configured to enable learners to register for participation in at least one case study;

a role assignment module configured to assign at least one role to each learner based on learner profile data and problem statement of the case study, and to form one or more learner groups for the selected case study;

a collaborative workspace module configured to provide a collaborative environment for executing one or more collaborative learning and problem-solving sessions, including case studies, wherein the collaborative workspace module is configured to enable the learners to submit work data;

an AI-based facilitation module configured to monitor and analyze learner interactions during the collaborative learning and problem-solving session and generate facilitation outputs, wherein the facilitation outputs include guidance directives comprising interrogative or guiding statements to steer the learning and problem-solving session toward targeted objectives;

an analytics module configured to evaluate individual and group contributions during the collaborative learning and problem-solving session and generate individual reports for each learner and group performance report for each learner group, and

a dashboard module configured to present insight data and analytics data associated with at least one learning and problem-solving session.

2. The system of claim 1, wherein the role assignment module is further configured to dynamically adjust the assigned role during the collaborative learning and problem-solving session based on participation metrics or changes in group composition.

3. The system of claim 1, wherein the case study includes at least one of text, multimedia, simulation-based, and open-ended problem elements.

4. The system of claim 1, wherein the role is selected from a group including, but not limited to, a problem analyst, a researcher, a solution designer, an evaluator, and a presenter.

5. The system of claim 1, wherein the learner profile data includes aptitude, knowledge, personality, technical skills, social consciousness, application skills, and career fitment.

6. The system of claim 1, wherein the collaborative workspace module is configured to support synchronous and asynchronous interactions including at least one of text, voice, or video communication.

7. The system of claim 1, wherein the collaborative environment includes shared tools comprising whiteboards, shared document spaces, and annotation tools for collaborative solution design.

8. The system of claim 1, wherein the analytics module is configured to integrate the evaluated individual and group insights into each learner’s personalized learning pathway within an intelligent learning infrastructure, thereby enabling adaptive learning and targeted performance enhancement, and wherein the AI-based facilitation module is configured to automatically adjust the complexity of discussions and the intensity or frequency of facilitation interventions based on group dynamics and individual role performance metrics.

9. The system of claim 1, is configured to utilize natural language processing (NLP) for analyzing work data from learners and generating adaptive facilitation output.

10. The system of claim 1, wherein the computing device is further configured to interface with a collaborative web and cloud system via secure application programming interfaces (APIs) and encrypted communication protocols, and wherein the collaborative web and cloud system comprises real-time collaboration frameworks for enabling real-time audio, video, and data communication during synchronous collaborative learning and problem-solving sessions.

11. The system of claim 1, wherein the learner module, the collaborative workspace module, and the AI-based facilitation module are further configured to enable execution of the case study individually by the learners in the study group, wherein the execution involves:

initiate the case study in an individual learner mode through the learner module;

transmit, by the collaborative workspace module, an automated message to the learner to initiate a case sequence/ the case study;

receive, by the learner module, a learner response from the learner corresponding to the case study;

analyze, by the AI-based facilitation module, the learner response and generate facilitation outputs including calibrated feedback and refined responses to the learner to progress the case study towards completion;

create, by the collaborative workspace module and the AI-based facilitation module, an adaptive learning loop by providing refined responses for the predefined threshold of iteration to progress the case study towards completion, and

terminate, by the collaborative workspace module, the case study executed individually by the learner upon at least one of completion of the case study by the learner and expiration of a predefined threshold of iteration.

12. The system of claim 11, wherein, upon completion of the case study individually by the learners in the study group, the learner module, the collaborative workspace module, and the AI-based facilitation module are further configured to:

initiate the case study in a group collaborative mode with participation of multiple learners;

collect, by the collaborative workspace module, learner responses of the learners from their respective individual learner modes;

collect, by the collaborative workspace module, sequential learner responses from each learner, wherein the sequential learner response is a response build upon or contrast to at least one prior learner response;

analyze, by the AI-based facilitation module, the sequential learner responses to calibrate inputs, highlight patterns, and ensure balanced participation across the learners, and

trigger, by the AI-based facilitation module, completion of the collaborative learning and problem-solving session upon determining that sufficient interaction and analysis have occurred based on at least one of a predefined number of responses, quality thresholds of responses, or convergence of learner ideas.

13. An Artificial Intelligence (AI)-based method for providing a collaborative learning and problem-solving environment, comprising:

providing at least one computing device comprising at least one processor and a memory storing a plurality of program modules, at least one database in communication with the computing device via a network, at least one first user device associated with a learner and in communication with the computing device via the network, at least one second user device associated with a teaching assistant and in communication with the computing device via the network, wherein the computing device is configured to provide the collaborative learning and problem-solving environment and includes artificial intelligence (AI) and machine learning (ML) modules, wherein the database is configured to store a plurality of learning and problem-solving sessions, learner profile data, and teaching assistant profile data;

enabling, via a content management module at the computing device, the teaching assistant to at least one of upload, create, and manage one or more learning activities, including case studies;

enabling, via a teaching assistant module at the computing device, the teaching assistant to select at least one case study and define one or more parameters, including a number of learners permitted to participate in the selected case study;

enabling, via a learner module at the computing device, learners to register for participation in at least one case study;

assigning, via a role assignment module at the computing device, at least one role to each learner based on learner profile data and problem statement of the case study, and forming one or more learner groups for the selected case study;

providing, via a collaborative workspace module at the computing device, a collaborative environment for executing one or more collaborative learning and problem-solving sessions, including case studies, and enabling the learners to submit work data;

monitoring and analyzing, via an AI-based facilitation module at the computing device, learner interactions during the collaborative learning and problem-solving session and generating facilitation outputs, wherein the facilitation outputs include guidance directives comprising interrogative or guiding statements to steer the learning and problem-solving session toward targeted objectives;

evaluating, via an analytics module at the computing device, individual and group contributions during the collaborative learning and problem-solving session and generating individual reports for each learner and group performance reports for each learner group, and

presenting, via a dashboard module at the computing device, insight data and analytics data associated with at least one learning and problem-solving session.

14. The method of claim 13, further comprising the step of: dynamically adjusting, via the role assignment module at the computing device, the assigned role during the collaborative learning and problem-solving session based on participation metrics or changes in group composition.

15. The method of claim 13, wherein the case study includes at least one of text, multimedia, simulation-based, and open-ended problem elements, wherein the role is selected from a group including a problem analyst, a researcher, a solution designer, an evaluator, and a presenter, and wherein the learner profile data includes aptitude, knowledge, personality, technical skills, social consciousness, application skills, and career fitment.

16. The method of claim 13, further comprising the step of: supporting, via the collaborative workspace module at the computing device, synchronous and asynchronous interactions including at least one of text, voice, or video communication.

17. The method of claim 13, further comprising the step of: integrating, via the analytics module at the computing device, the evaluated individual and group insights into each learner’s personalized learning pathway within an intelligent learning infrastructure, thereby enabling adaptive learning and targeted performance enhancement, and

automatically adjusting, via the AI-based facilitation module at the computing device, the complexity of discussions and the intensity or frequency of facilitation interventions based on group dynamics and individual role performance metrics.

18. The method of claim 13, further comprising the step of: enabling execution of the case study individually by the learners in the study group, via the learner module, the collaborative workspace module, and the AI-based facilitation module, wherein the execution involves:

initiating the case study in an individual learner mode through the learner module;

transmitting, by the collaborative workspace module, an automated message to the learner to initiate a case sequence/ the case study;

receiving, by the learner module, a learner response from the learner corresponding to the case study;

analyzing, by the AI-based facilitation module, the learner response and generate facilitation outputs including calibrated feedback and refined responses to the learner to progress the case study towards completion;

creating, by the collaborative workspace module and the AI-based facilitation module, an adaptive learning loop by providing refined responses for the predefined threshold of iteration to progress the case study towards completion, and

terminating, by the collaborative workspace module, the case study executed individually by the learner upon at least one of completion of the case study by the learner and expiration of a predefined threshold of iteration.

19. The method of claim 18, wherein, upon completion of the case study individually by the learners in the study group, the learner module, the collaborative workspace module, and the AI-based facilitation module are further configured to execute one or more of following steps:

initiating the case study in a group collaborative mode with participation of multiple learners;

collecting, by the collaborative workspace module, learner responses of the learners from their respective individual learner modes;

collecting, by the collaborative workspace module, sequential learner responses from each learner, wherein the sequential learner response is a response build upon or contrast to at least one prior learner response;

analyzing, by the AI-based facilitation module, the sequential learner responses to calibrate inputs, highlight patterns, and ensure balanced participation across the learners, and

triggering, by the AI-based facilitation module, completion of the collaborative learning and problem-solving session upon determining that sufficient interaction and analysis have occurred based on at least one of a predefined number of responses, quality thresholds of responses, or convergence of learner ideas.