System and method for adaptive emotional assessment on a virtual reality (VR) -based platform

Abstract

Embodiments of the present disclosure relates to a system (102) and method (400) for information management on a VR-based platform. The system (102) delivers an integrated VR-based platform that supports immersive education, mental health assessment, and personalized therapeutic interventions. The system (102) verifies connectivity, loads user profiles, retrieves curriculum-aligned or wellness modules, and synchronizes one or more VR headsets (106) with a control tablet for unified session delivery. The system (102) streams selected content, manages start-pause-rewind-stop controls, and projects real-time VR visuals onto an analytics dashboard (112) for interactive teaching or therapy guidance. The system (102) tracks engagement, behavioural responses, physiological metrics, task performance, and emotional indicators throughout each session. AI algorithms process this multimodal data to generate academic wellness scores for students or mental health status scores for therapy users. Based on these results, the system (102) recommends targeted interventions such as guided relaxation, exposure therapy, or cognitive-behavioural modules.

Description

SYSTEM AND METHOD FOR INFORMATION MANAGEMENT ON A VIRTUAL REALITY (VR)-BASED PLATFORMTECHNICAL FIELD

[0001] The embodiments of the present disclosure generally relate to Virtual Reality (VR)-based learning technologies. More particularly, the present disclosure relates to a system and method for information management on a VR-based platform.BACKGROUND

[0002] Conventional VR tools for education, such as Google Expeditions, ClassVR, and Nearpod VR, offer immersive experiences but lack standardized curriculum alignment, strong teacher control, affordability, and built-in assessment features, limiting their use as core teaching resources. VR therapy platforms like Limbix, Psious, and XRHealth provide exposure and relaxation modules but are mostly clinical, not customizable for diverse age groups, and often fail to engage younger users. No existing system integrates both education and mental health into one platform, resulting in fragmented solutions, limited accessibility in schools, and poor scalability or modularity across grades, learning goals, and therapeutic needs.

[0003] To address these limitations, the present disclosure provides a novel system and method that overcomes shortcomings of the prior art.OBJECTS OF THE PRESENT DISCLOSURE

[0004] It is a primary object of the present disclosure to provide a system that offers guided mental health exercises, such as mindfulness, relaxation techniques, and exposure therapy, within a VR environment, providing user with a safe, controlled space for managing anxiety, phobias, and stress.

[0005] It is another object of the present disclosure to provide a system that enables complete control over VR sessions, allowing them to start, pause, and manage content, as well as monitor each user’s progress and engagement in real-time.SUMMARY

[0006] The present disclosure relates to the field of Virtual Reality (VR)-based learning technologies. More particularly, the present disclosure relates to a system and method for information management on a VR-based platform.

[0007] In an aspect, a system for information management on a VR-based platform is disclosed. The system may include a processor and a memory coupled to the processor. The memory may include processor-executable instructions, which, on execution, cause the processor to execute a sequence of tasks. The system may receive data selected from any or a combination of a vocal biomarker, a facial micro-expression, a pupil dilation level, a blink rate, an eye-movement rate, an interaction latency level on an integrated digital device, a background environmental noise level, and a self-reported mood input from a user. The system may generate an adaptive individual baseline by analyzing the received data. The system may detect user-specific behavioral and physiological patterns and deviations indicative of any or a combination of stress, cognitive load, and emotional fluctuation based on the adaptive individual baseline. The system may derive a score based on any or a combination of magnitude, frequency, and pattern of the detected deviations from the adaptive individual baseline. Furthermore, the system may recommend a context-specific intervention to the user based on the derived score.BRIEF DESCRIPTION OF DRAWINGS

[0008] FIG. 1 illustrates an exemplary representation of an architecture of the system, in accordance with an embodiment of the present disclosure.

[0009] FIG. 2 illustrates an exemplary representation the system, in accordance with an embodiment of the present disclosure.

[0010] FIG. 3 illustrates an exemplary representation of an operational workflow of the system, in accordance with an embodiment of the present disclosure.

[0011] FIG. 4 illustrates an exemplary flow diagram representation of a method of information management on a VR-based platform, in accordance with an embodiment of the present disclosure.DETAILED DESCRIPTION

[0012] In an aspect, a system for information management on a Virtual Reality (VR)- based platform is disclosed. The system may be integrated with a VR-based platform that unifies curriculum-aligned education, multimodal emotion sensing, and mental health support within a shared infrastructure. Further, the system may execute modules that access a VR content library, synchronize VR headsets, and project sessions onto an analytics dashboard. A control tablet may be used manage lessons or therapy. Biofeedback sensors and multimodal input data may be analysed by the system to derive wellbeing scores. These scores may beused to recommend personalized educational modules or therapeutic interventions for school, corporate, or remote users in practice.

[0013] FIG. 1 illustrates an exemplary representation of architecture of a system for information management on a VR-based platform, in accordance with an embodiment of the present disclosure.

[0014] Illustrated in Fig. 1 is an exemplary representation of an architecture 100 of a system 102 for information management on a VR-based platform (hereafter referred to as the system 100). The system 102 may be connected to a network 104, one or more VR headsets 106-2, 106-4. , .,106-N (individually referred to as one or more VR headsets 106), one or more users 108-1, 108-2... , 108-N (individually referred to as one or more users 108), and a centralized server 110. The system 102 may enable integrated management of VR content, multimodal emotion analytics, scoring, and personalized educational or therapeutic interventions.

[0015] In an embodiment of the present disclosure, the system 102 may offer an integrated solution for immersive learning and student well-being. The system 102 may combine curriculum-aligned VR content and mental wellness modules, creating a unified platform that addresses both academic and emotional needs. The system 102 may be integrated with a central VR content library that houses educational modules on subjects such as science, history, and geography, designed to meet grade-specific standards with interactive simulations. The VR content library may also include mental health modules for relaxation, guided mindfulness, exposure therapy, and cognitive-behavioural exercises, all customizable to suit individual needs.

[0016] In an embodiment of the present disclosure, a first user who may be a teacher may use a digital device, such as a control tablet, to manage VR sessions, with functions to start, pause, fast-forward, and monitor real-time student progress. The one or more VR headsets 106, synchronized with the digital device, may display teacher-directed content to students, keeping them focused on the lesson. The system 102 may be further integrated with an analytics dashboard 112 that may be a classroom smart board, allowing teachers to project VR content and interact with the VR content through annotations and highlights, merging VR's immersive qualities with traditional teaching methods. The analytics dashboard 112 may be implemented through two primary methods: casting and creating specific files. Casting may allow real-time mirroring of VR content onto the analytics dashboard 112, enabling the first user including teachers or therapists to monitor and guide sessions interactively. This approach may ensure seamless synchronization with ongoing VRactivities. Alternatively, creating specific files for the panel may involve pre-configured content tailored for the analytics dashboard 112, enhancing usability and providing structured lesson plans or therapy modules. This method is ideal for classrooms or therapy centres requiring non-VR demonstrations. Both options ensure flexibility, fostering engagement while accommodating diverse teaching and therapeutic needs.

[0017] In an embodiment of the present disclosure, for mental health applications, the VR-based platform of the system 102 may offer guided exercises with adjustable intensity levels to ensure comfort and effectiveness. The analytics dashboard 112 may track student engagement and responses, providing insights for both learning assessments and therapeutic outcomes. This data-driven approach may support customized learning paths and tailored therapeutic interventions, making the system 102 a versatile and adaptive tool in education and mental health. The system 102 may be scalable, allowing institutions to expand across grades and therapy requirements, making the system 102 a valuable resource for diverse educational and mental health needs.

[0018] In an embodiment of the present disclosure, the analytics dashboard 112 may provide real-time tracking of student engagement, learning progress, and emotional responses. The analytics dashboard 112 may display metrics from educational assessments, such as quiz scores and interaction data, to help teachers evaluate student understanding. For mental health applications, the analytics dashboard 112 may collect data on relaxation levels, engagement, and emotional responses during therapeutic sessions. The analytics dashboard 112 may also enable educators and mental health professionals to monitor trends over time, offering insights into each student’s academic and therapeutic development. This data may support adaptive learning and personalized mental health interventions.

[0019] In an embodiment of the present disclosure, the system 102 may implement a hybrid viewing feature that may allow seamless integration of the VR headsets 106 and the analytics dashboard 112 for group sessions. When there may be twenty users but only ten VR headsets available, the remaining ten users may view the VR content in real-time on the connected analytics dashboard 112. This may ensure inclusivity, enabling all participants to engage with the session without the need for individual VR devices. The analytics dashboard 112 may mirror the immersive content, maintaining synchronization with the VR headsets 116 for a unified experience. This feature may be particularly beneficial in classroom or group therapy settings, where resource limitations might exist. The system 102 may foster collaboration and collective learning while optimizing available hardware. By combiningimmersive VR and large-screen visualization, the system 102 may enhance accessibility and ensure that all users benefit from the educational or therapeutic content.

[0020] In an embodiment of the present disclosure, the system 102 may be integrated with an Al-based scoring framework that may enable the system 102 to generate scores by integrating data collection, processing, and analysis to provide actionable insights for mental wellness and curriculum-aligned education. For corporate employees, the system 102 may collect data from employee surveys that may include responses on workplace satisfaction, stress levels, work-life balance, and overall sentiment. The system 102 may also collect data on task completion rates, absenteeism, and performance evaluations as well as health data that may include healthcare usage patterns including insurance claims, wellness program participation, and sick leaves. The system 102 may collect data that may include metrics on workplace culture, inclusivity, and communication dynamics. For school students, the system 102 may collect data from behavioural assessments that may measure emotional states, attention span, and engagement levels through interactive tasks and questionnaires, academic data that may track student performance, participation, and comprehension in classroom activities, mental and physical health data, including signs of autism, ADHD, and neurodevelopmental disorders, and feedback from teachers and parents that may include subjective insights into a student’s behaviour and learning journey.

[0021] In an embodiment of the present disclosure, the system 102 may clean and standardize the data from diverse formats to ensure comparability and identify gaps or anomalies, such as missing data, and adjust scores accordingly to maintain fairness. The system 102 is further configured to assign weights to each metric based on its importance in the specific context (corporate or academic). For quantitative analysis the system 102 uses statistical models to evaluate measurable KPIs such as productivity, absenteeism, or academic scores. For qualitative analysis, the system 102 employs natural language processing (NLP) to analyse open-ended responses, sentiment in feedback, and behavioural patterns. Further, the system 102 tracks real-time metrics during VR sessions (e.g., engagement levels, response times, emotional reactions using biofeedback if available).

[0022] In an embodiment of the present disclosure, the system 102 may generate a corporate wellbeing score that may include a workplace productivity sub-score. The workplace productivity sub-score may be based on task completion rates, absenteeism, and output quality. Further, the system 102 may generate a sentiment sub-score that may be an evaluation of employee satisfaction and cultural feedback. Further, the system 102 may generate a healthcare impact sub-score based on an analysis of reductions in insuranceclaims, premiums, and sick leave usage. A final wellbeing score may combine these subscores using weighted averages. The system 102 may generate a school student score that may include an academic wellness sub-score which may incorporates academic performance and engagement. Further, the system 102 may generate a school student score that may include a mental and behavioural wellness sub-score that may consider emotional health, attention span, and behaviour patterns. Further, the system 102 may generate a school student score that may include neurodevelopmental insights sub-score which may help to identify potential concerns like autism or ADHD. The school student score may aggregate these subscores into a final grade aligned with regulatory standards.

[0023] In an embodiment of the present disclosure, the system 102 may match the scores to tailored interventions for school students or corporate employees. For example, low workplace productivity scores may trigger suggestions for relaxation VR sessions or teambuilding exercises in a corporate office. In another example, signs of ADHD in students may prompt additional educational modules or mindfulness sessions in a school. Further, the system 102 may adapt the recommendations to organizational or individual needs, using insights from scoring trends. The Al-based scoring framework of the system 102 may refine the scoring algorithm over time based on new data and feedback and adjust the scoring criteria dynamically to reflect evolving priorities or regulatory requirements. In the end, the system 102 may generate a detailed wellbeing score report highlighting areas of improvement, strengths, and actionable strategies for corporate clients or a health card for each student, providing a holistic view of academic and mental wellness, along with tailored interventions and curriculum enhancements in schools.

[0024] In an embodiment of the present disclosure, the system 102 may include a biofeedback feature via a biofeedback sensor 114 operatively coupled with the one or more VR headsets 106. The biofeedback sensor 114 may monitor and evaluate a physiological impact of Virtual Reality Exposure Therapy (VRET). By capturing vital health parameters such as pulse rate, respiratory rate, and heart rate, the system 102 may provide real-time insights into the user's stress levels, emotional state, and relaxation progress. These metrics may be analysed to assess the effectiveness of the VR sessions in achieving desired therapeutic outcomes, such as reducing anxiety or enhancing mindfulness. The biofeedback feature may ensure a personalized approach by dynamically adapting therapy sessions based on the user’s physiological responses. This feature adds a layer of scientific validation, making the therapy outcome measurable and transparent. By leveraging these insights, thesystem 102 may enable precise adjustments to content and intervention strategies, ensuring optimal mental health benefits for each individual user.

[0025] In an embodiment of the present disclosure, the biofeedback sensor 114 may be directly integrated with the VR headsets 106, and may be positioned strategically near the forehead or temples for consistent physiological data capture. The biofeedback sensor 114, such as photoplethysmography (PPG) sensors, may measure pulse rate by detecting blood flow variations, while infrared sensors can track temperature and respiratory changes. This embedded design may ensure non-intrusive monitoring, enabling real-time tracking of vital parameters like heart rate, pulse, and respiratory rate during Virtual Reality Exposure Therapy (VRET) sessions. The collected data may be used to evaluate the user’s physiological responses to VR stimuli, offering insights into stress levels, relaxation progress, or emotional engagement. By integrating biofeedback into the headset, the system 102 may enhance the personalization and effectiveness of therapeutic or educational interventions, ensuring an adaptive and immersive experience tailored to individual needs.

[0026] In an embodiment of the present disclosure, the system 102 may incorporate flexible biofeedback modules to capture vital health parameters, offering users multiple integration options for enhanced adaptability. One method may be through clip-on modules, detachable sensor units that attach directly to the VR headset frame, providing precise physiological measurements without altering the headset’s ergonomics. Another option may be elastic band attachments, featuring embedded sensors within a headband that fits seamlessly with the VR headset, ensuring comfort and stability during use. Further, the system 102 may support peripheral devices like wristbands, gloves, or chest straps, equipped with advanced sensors and connected wirelessly via Bluetooth or other technologies. These peripherals may extend biofeedback capabilities to track metrics such as heart rate, skin conductivity, or respiration. These modular options may allow the system 102 to adapt to various user preferences, ensuring comprehensive health monitoring while maintaining immersion and comfort during VR-based interventions. The system 102 may integrate biofeedback data to create a personalized and adaptive experience, enhancing the effectiveness of virtual reality-based therapy and education. By using machine learning algorithms or predefined thresholds, the system 102 may analyse physiological responses such as heart rate, respiratory rate, or skin conductivity in real time. For example, in phobia therapy, the system 102 may detect spikes in heart rate and dynamically reduce the intensity of the exposure, ensuring that the user remains engaged without being overwhelmed. Similarly, if heightened stress levels are identified, the system 102 may introduce calmingenvironments like serene landscapes or guided breathing exercises to help regulate emotions. This adaptive capability may ensure that each session is tailored to the user's needs, making interventions both safe and effective while fostering a supportive and immersive environment for mental health therapy and stress management

[0027] In an embodiment of the present disclosure, the system 102 may find diverse applications in mental health and wellness through its adaptive VR capabilities. Virtual Reality Exposure Therapy (VRET) may customize exposure scenarios to treat conditions such as anxiety, phobias, and PTSD, ensuring safe and progressive desensitization. For stress management, users may engage in interactive relaxation exercises within calming virtual environments, promoting mindfulness and emotional regulation. As a diagnostic tool, the system 102 may quantify stress levels and physiological responses, enabling accurate assessment of therapy outcomes and progress. These applications may leverage biofeedback and VRto deliver tailored, evidence -based interventions for improved mental well-being.

[0028] In an embodiment of the present disclosure, the system 102 may support various potential sensor attachments to enhance functionality and user adaptability. On-headset integration may involve embedding sensors within the VR headset frame, such as near the forehead or temples, ensuring reliable physiological measurements directly from contact points. Detachable sensor modules, like clip-on or magnetic units, may allow retrofitting of existing VR headsets, providing flexibility and cost-efficiency. Wearable accessories, including wristbands, finger sensors, or gloves, may connect wirelessly to the VR system, offering non-intrusive and comfortable options for users. A standalone external unit, such as a portable sensor box, may communicate with the headset and may serve as an independent, versatile solution for capturing biofeedback. These diverse attachment options may cater to different use cases and user preferences, ensuring seamless integration and enhanced performance across educational and therapeutic applications.

[0029] In an embodiment of the present disclosure, the system 102 may offer several key advantages to enhance the user experience and therapeutic effectiveness. Real-time adaptation may ensure VR content dynamically adjusts based on biofeedback, such as heart rate or stress levels, providing immediate customization for better outcomes, especially in therapy sessions. Broad compatibility may be achieved through detachable or external sensor modules, making the system versatile and usable with a wide range of VR platforms. Data- driven insights may be facilitated by capturing and analysing biofeedback data, offering objective metrics to assess the efficacy of therapy and refine intervention strategies. User comfort may be prioritized with lightweight, ergonomic designs for sensors and attachments,ensuring they do not disrupt the immersive VR experience. Together, these features may make the system 102 a robust and user-friendly solution for both educational and mental health applications.

[0030] FIG. 2 illustrates an exemplary representation of the system, in accordance with an embodiment of the present disclosure.

[0031] Illustrated in Fig. 2 is a representation 200 of the system 102 for information management on a VR-based platform. The system 102 may include one or more processor(s) 202. Among other capabilities, the one or more processor(s) 202 may be configured to fetch and execute computer-readable instructions stored in the memory 204. The memory 204 may store one or more computer-readable instructions or routines, which are fetched and executed to enable for information management on a VR-based platform. The system 102 may also include an interface(s) 206. The interface(s) 206 may act as a central control and monitoring tool for educators and mental health professionals, streamlining VR session management and ensuring effective use in both learning and therapy settings. Through a tablet-based control interface, the one or more first users who may be a teacher or a therapist may start, pause, rewind, and fast-forward VR content for all the connected VR headsets, maintaining full oversight of the session flow. The interface 206 may also enable real-time monitoring of progress of the one or more second users, allowing the one or more first users to adjust the experience according to individual needs and provide targeted support. Further, the interface 206 may facilitate smooth integration with the analytics dashboard 112, allowing projection of VR content for group interaction and annotation, blending VR immersion with traditional teaching. For mental health applications, the interface 206 may provide options to customize the intensity and duration of therapeutic modules, such as relaxation exercises and exposure therapy, to meet individual comfort levels. The interface 206 may centralize session control, progress tracking, and content customization, making the system 102 a powerful, user- friendly tool for educational and mental health applications.

[0032] In an embodiment of the present disclosure, the processing engine(s) 208 may be implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the processing engine(s) 208. The database 218 may include data that may either be stored or generated as a result of functionalities implemented by any of the components of the processing engine(s) 208. The processing engine(s) 208 may include an access module 210, a display module 212, a sync module 214, a score module 216, and other module(s) 218 that may implement functionalities supplementing applications or functions performed by the system 102 or the processingengine(s) 208. The access module 210 may retrieve curriculum-aligned educational content and mental health resources from the VR content library. The display module 212 may present selected VR content to the one or more first users and stream it to the connected VR headsets 106. The sync module 214 may establish and maintain real-time synchronization between the control tablet and the VR headsets 106. The score module 216 may generate mental health or engagement scores based on collected data and recommend corresponding interventions.

[0033] In an embodiment of the present disclosure, the system 102 may receive data selected from any or a combination of a vocal biomarker, a facial micro-expression, a pupil dilation level, a blink rate, an eye-movement rate, an interaction latency level on an integrated digital device, a background environmental noise level, and a self-reported mood input by using sensors embedded within the VR headsets 106 or by using peripherals interacting with the users 108. The system 102 may capture audio, video, and behavioural inputs during VR sessions and may forward processed metadata to the analytics dashboard 112, where emotional or cognitive indicators may be analysed and stored for further assessment.

[0034] In an embodiment of the present disclosure, the system 102 may generate an adaptive individual baseline by analysing multimodal data continuously collected through the VR headsets 106 during interactions with the users 108. The system 102 may process vocal, facial, behavioural, and environmental inputs over repeated sessions to identify stable physiological and emotional patterns unique to each user. These patterns may be compared across time to detect natural variations and establish personalized reference ranges. The analytics dashboard 112 may store and visualise these evolving baselines, allowing emotional, cognitive, and stress-related indicators to be interpreted relative to each user’s typical responses, thereby supporting accurate and fair assessments.

[0035] In an embodiment of the present disclosure, the system 102 may detect userspecific behavioural and physiological patterns by comparing real-time multimodal inputs collected through the VR headsets 106 with the adaptive individual baseline previously established for the users 108. The system 102 may analyse changes in vocal tone, facial micro-movements, gaze stability, blink rates, interaction latency, and biofeedback metrics to identify deviations from typical response ranges. These deviations may indicate rising stress, increased cognitive load, or emotional fluctuation. The analytics dashboard 112 may process and display these variations as quantified indicators, allowing the system 102 to determinewhen the user’s current state differs meaningfully from their learned behavioural and physiological norms.

[0036] In an embodiment of the present disclosure, the system 102 may derive a score by quantifying the magnitude, frequency, and pattern of deviations detected during real-time monitoring of the users 108 through the VR headsets 106. Each deviation may be evaluated against the adaptive individual baseline to determine how strongly and how often the user’s behavioural or physiological responses differ from their expected ranges. The system 102 may aggregate these deviation metrics using weighted calculations or machine learning models to produce a normalized emotional or cognitive score. The analytics dashboard 112 may process and present the computed score, reflecting the user’s moment-to-moment wellness or mental state.

[0037] In an embodiment of the present disclosure, the system 102 may recommend a context-specific intervention by interpreting the derived score in relation to predefined therapeutic or educational thresholds stored for the users 108. When the score indicates elevated stress, cognitive overload, or emotional fluctuation, the system 102 may select an appropriate response, such as initiating relaxation modules, guided breathing, exposuretherapy adjustments, or supportive educational content through the VR headsets 106. The analytics dashboard 112 may evaluate score trends and user history to refine the recommendation, ensuring the chosen intervention aligns with individual needs and the current session context. The recommended intervention may then be delivered or suggested directly to the user.

[0038] In an embodiment of the present disclosure, the system 102 may execute multimodal affective state estimation by using a deep convolutional neural network model trained on time -synchronized facial micro-expression video frames and log-mel spectrograms of vocal biomarkers captured through the VR headsets 106 during interactions with the users 108. The model may extract spatial features from facial cues and spectral features from vocal signals, learning patterns associated with stress, emotional shifts, or cognitive effort. These fused feature representations may be processed jointly to infer the user’s affective state in real time. The analytics dashboard 112 may display the resulting emotional indicators for monitoring and further analysis.

[0039] In an embodiment of the present disclosure, the system 102 may perform keystroke dynamics analysis by using a Bidirectional Long Short-Term Memory (BiLSTM) model trained on temporal sequences of keypress timestamps, interaction latencies, and pause distributions collected through the VR headsets 106 or an integrated digital interface used bythe users 108. The BiLSTM model may process these time-ordered inputs in both forward and backward directions, allowing it to learn sequential dependencies and behavioural rhythms that characterize each user’s typing or interaction pattern. The model may detect variations that reflect cognitive load, stress, or emotional fluctuation, and the analytics dashboard 112 may present these insights for interpretation.

[0040] In an embodiment of the present disclosure, the system 102 may execute adaptive individual baseline construction by using a Gaussian mixture model trained on historical distributions of user-specific vocal, facial, interaction, and ambient-noise feature vectors collected through the VR headsets 106 during repeated sessions with the users 108. The model may learn clusters that represent the user’s normal behavioural and physiological ranges, capturing natural variability across different emotional or cognitive states. When new multimodal data is received, the system 102 may compare it against these learned Gaussian components to determine how closely the current measurements align with typical patterns. The analytics dashboard 112 may update and display the evolving baseline for ongoing assessment.

[0041] In an embodiment of the present disclosure, the system 102 may perform stress, cognitive load, and emotional fluctuation classification by using a support vector machine model trained on fused physiological, behavioural, and self-report feature embeddings captured through the VR headsets 106 during interactions with the users 108. The model may map these multimodal embeddings into a high-dimensional feature space where optimal separating hyperplanes may be identified to distinguish between different emotional or cognitive states. When new data is received, the model may evaluate its position relative to these learned boundaries to classify the user’s current state. The analytics dashboard 112 may present these classifications in real time for monitoring and further interpretation.

[0042] In an embodiment of the present disclosure, the system 102 may execute VR- session engagement scoring by using a gradient boosting regression model trained on mappings between VR interaction logs, gaze tracking events, and expert-annotated engagement scores collected during sessions with the users 108. The model may learn how specific behavioural indicators, such as interaction frequency, gaze stability, focus duration, and response timing captured through the VR headsets 106 — correlate with expert-defined engagement levels. During a live session, the system 102 may process real-time interaction and gaze data to predict a continuous engagement score. The analytics dashboard 112 may display this score, allowing first users to monitor attention, involvement, and immersion.

[0043] In an embodiment of the present disclosure, the system 102 may perform corporate wellbeing score computation by using a random forest model trained on multidimensional vectors comprising task completion rates, absenteeism metrics, performance evaluations, and survey -derived sentiment indices collected from the users 108. The model may build multiple decision trees, each learning different patterns and relationships within these organizational and behavioural features to capture productivity trends, workplace satisfaction levels, and stress indicators. During inference, the system 102 may aggregate predictions from all trees to generate a stable and robust wellbeing score. The analytics dashboard 112 may present this computed score to provide actionable insights for corporate wellness planning.

[0044] In an embodiment of the present disclosure, the system 102 may execute sentiment and thematic extraction by using a transformer-based language model trained on domain-specific corpora of wellness, education, and workplace narratives submitted by the users 108. The model may process textual feedback by applying self-attention mechanisms that identify relationships between words, phrases, and contextual cues, allowing it to detect emotional tone, intent, and recurring themes with high precision. When new feedback is received, the system 102 may generate sentiment scores and thematic labels that reflect underlying concerns, satisfaction levels, or behavioural insights. The analytics dashboard 112 may display these extracted sentiments and themes for further review and decision-making.

[0045] In an embodiment of the present disclosure, the system 102 may perform clusterbased stratification of students and employees into risk cohorts by using a k-means clustering model trained on normalized wellness, performance, and engagement feature spaces collected from the users 108. The model may group data points by iteratively assigning each feature vector to the nearest cluster centroid and recalculating centroids until stable patterns emerge. These clusters may represent distinct behavioural or wellness profiles, such as low-risk, moderate-risk, or high-risk cohorts. When new feature data is received through the VR headsets 106 or related inputs, the system 102 may assign the user to the closest cluster, and the analytics dashboard 112 may display the resulting cohort classification for timely intervention.

[0046] FIG. 3 illustrates an exemplary representation of an operational workflow of the system, in accordance with an embodiment of the present disclosure.

[0047] Illustrated in Fig. 3 is a flow diagram representation of a method 300 for information management on a VR-based platform. The system 102 may facilitate accessing of the VR content library to obtain information comprising curriculum-aligned educationalresources and mental health resources at block 302. The system 102 may allow displaying of the obtained information to the one or more first users at block 304. The system 102 may enable synchronization with the VR headsets 106 to make the information accessible to the second users at block 306. The system 100 may allow conducting of a VR-based mental health assessment session of the one or more second users via the synchronized one or more VR headsets 106 at block 308. The system 102 may further facilitate generation of a score indicating a mental health status of the second users upon completion of the VR-based mental health assessment session at block 310. Thereafter, the system 100 may recommend a therapy package to the one or more second users based on the generated score at block 312.

[0048] FIG. 4 illustrates an exemplary flow diagram representation of a method of information management on a VR-based platform, in accordance with an embodiment of the present disclosure

[0049] Illustrated in Fig. 4 is a representation of a method 400 of information management on a VR-based platform. The method 400 may begin with receiving 402, by the processor 202, data selected from any or a combination of a vocal biomarker, a facial microexpression, a pupil dilation level, a blink rate, an eye-movement rate, an interaction latency level on an integrated digital device, a background environmental noise level, and a selfreported mood input from a user 108. The method 400 may proceed with generating 404, by the processor 202, an adaptive individual baseline by analyzing the received data. The method 400 may proceed with detecting 406, by the processor 202, user-specific behavioral and physiological patterns and deviations indicative of any or a combination of stress, cognitive load, and emotional fluctuation based on the adaptive individual baseline. The method 400 may proceed with deriving 408, by the processor 202, a score based on any or a combination of magnitude, frequency, and pattern of the detected deviations from the adaptive individual baseline. The method 400 may end with recommend 410, by the processor 202, a context-specific intervention to the user based on the derived score.

[0050] In an embodiment of the present disclosure, the system 102 may begin operation with accessing a VR content library that includes curriculum-aligned educational modules and mental health resources, followed by displaying selected content to teachers or therapists through a control tablet. The system 102 may then synchronize the VR headsets 106 so that students or users experience the same immersive lesson or therapeutic module in real time. During operation, the system 102 may monitor engagement, behavioural responses, and physiological indicators using integrated or peripheral sensors. Further, the system 102 may take the different types of data, including facial movements, vocal changes, interaction speed,gaze behaviour, and sensor-based physiological signals, and analyse them over time to understand what is “normal” for each user. This normal pattern may become an adaptive individual baseline of the user. Once the baseline is established, the system 102 may compare new incoming data to this baseline to see if the user is acting differently than usual. Any meaningful change in behaviour or physiology may indicate stress, increased cognitive effort, or an emotional shift. By detecting these deviations, the system 102 may understand the user’s mental and emotional state more accurately. The system 102 may derive scores by first quantifying how much the user’s real-time behavioural or physiological signals differ from their adaptive individual baseline. The magnitude may represent how large each deviation is, the frequency may represent how often these deviations occur, and the pattern may represent how these deviations evolve or cluster over time. The system 102 may convert these elements into numerical features and apply weighted formulas or a trained machine learning model to compute a consolidated score. For students, these values may combine into an academic wellness score, while for employees, the same calculations may yield a broader wellbeing score. The analytics dashboard 112 may visualise this data, enabling instructors or mental health professionals to understand each user’s progress, emotional state, or learning needs. Based on the derived score, the system 102 may recommend context-specific interventions, such as guided relaxation, exposure adjustments, or curriculum-aligned remediation. Throughout the session, the system 102 may dynamically adapt content intensity, pacing, and feedback to ensure safety, relevance, and personalized engagement, while storing session data for longitudinal tracking and future improvement.

[0051] In an embodiment of the present disclosure, the system 102 may verify connectivity, power levels, and readiness before loading user profiles containing permissions and preferences. The system 102 may access the VR content library, display available modules, and preload selected content such as 3D models and audio for faster access. The system 102 may then synchronize the VR headsets with the control tablet and establish a connection with the analytics dashboard 112 to enable dual display. A VR session may be initiated simultaneously on all headsets, with the system 102 managing content flow based on start, pause, rewind, fast-forward, or stop commands. Real-time projection on the analytics dashboard 112 may support annotations and interactive teaching. The system 102 may track the progress of the one or more second users, monitor interactions for issues like lag, and adjust module settings dynamically during mental health sessions. Data on engagement, task responses, and physiological metrics may be collected, followed by assessments to gauge comprehension or therapeutic responses. Aggregated results may be displayed on theanalytics dashboard 112. Emotional and behavioural data may be recorded for therapy effectiveness, and all session data may be securely stored for longitudinal analysis. The system 102 may suggest follow-up modules, adjust difficulty levels, update customized content, and reset all devices to standby mode. During VR-based mental health assessments, the system 102 may guide users through tailored scenarios while analysing physiological and behavioural patterns using Al to compute a Mental Health Status Score. Based on this score, the system 102 may recommend personalized therapy packages, generate immersive intervention plans, and continuously refine sessions using user and professional feedback, ensuring a data-driven, adaptive, and effective wellness experience.

[0052] In an embodiment of the present disclosure, specifications of the system 102 may include VR headset resolutions ranging from 1080p to 8K, fields of view between 90° and 120°, refresh rates from 60 Hz to 120 Hz, and latency levels between 20 ms and 50 ms, ensuring smooth and immersive experiences. Headsets may weigh 300 g to 700 g, offer 2 to 6 hours of battery life, and require 1 to 2.5 hours of charging. Audio may operate with 30 ms to 50 ms latency and volume levels from 70 dB to 100 dB. VR content may range from 1080p to 4K at 30 fps to 60 fps, with lesson durations between 10 and 60 minutes and therapeutic sessions from 5 to 30 minutes. Tablet interfaces may use 7-12 inch screens with 6-10 hour battery life, and smart boards may range from 65 to 85 inches with sub- 100 ms interactivity. User monitoring may include HRV between 50 bpm and 120 bpm, engagement tracking up to 100%, and updates every 10-30 minutes. The system 102 may support 1 to 50 concurrent users, provide 50 GB to 1 TB institutional storage, enable 5 GB to 50 GB per student, allow 5-60-minute therapy sessions with 1-5 difficulty levels, and ensure 99% uptime with AES- 256 security and multi-factor authentication.

[0053] In an example embodiment of the present disclosure, a teacher may prepare a curriculum-aligned VR lesson on “Cell Biology” using the control tablet to select the “Cell Structure and Function” module from the VR content library. The VR headsets may be presynced so students log in to view a 3D virtual cell tour. The teacher may highlight organelles like the nucleus or mitochondria on the smart board while explaining their functions. At the end, a quiz may be assigned and responses may be reviewed using real-time analytics.

[0054] In another example embodiment of the present disclosure, a mental health professional may conduct an exposure therapy session for arachnophobia by selecting a module with gradually intensifying spider encounters. The student may begin in a virtual room where the spider appears at a safe distance. The therapist may adjust proximity and pacing through the tablet interface, ensuring the student is not overwhelmed. Throughout thesession, responses may be monitored, and after completion, engagement and relaxation data may be reviewed to guide future therapeutic strategies.

[0055] In another example embodiment of the present disclosure, the system 102 may be used for a relaxation and mindfulness session to help students manage exam stress. A counsellor may select the “Guided Relaxation” module, leading students into a peaceful virtual forest or beach environment with breathing exercises delivered through audio prompts. The counsellor may adjust timing and flow through the tablet and may personalize cues for students preferring specific environments. After the session, comfort levels and stress-management improvement metrics may be reviewed to plan follow-up support.ADVANTAGES OF THE PRESENT DISCLOSURE

[0056] The present disclosure provides a system that integrates curriculum VR and mental wellness analytics into one unified adaptive platform.

[0057] The present disclosure provides a system that provides real-time biofeedback- driven personalization and explainable emotional scoring for interventions across contexts.

Claims

We Claim:

1. A system (102) for emotional assessment, the system (102) comprising: a processor (202); and a memory (204) coupled to the processor (202), wherein the memory (204) comprises processor-executable instructions, which on execution, cause the processor (202) to: receive data selected from any or a combination of a vocal biomarker, a facial micro-expression, a pupil dilation level, a blink rate, an eyemovement rate, an interaction latency level on an integrated digital device, a background environmental noise level, and a self-reported mood input from a user; generate an adaptive individual baseline by analyzing the received data; detect user-specific behavioral and physiological patterns and deviations indicative of any or a combination of stress, cognitive load, and emotional fluctuation based on the adaptive individual baseline; derive a score based on any or a combination of magnitude, frequency, and pattern of the detected deviations from the adaptive individual baseline; and recommend a context-specific intervention to the user based on the derived score.

2. The system (102) as claimed in claim 1, wherein the processor (202) executes multimodal affective state estimation by implementing a deep convolutional neural network model trained on time-synchronized facial micro-expression video frames and log-mel spectrograms of vocal biomarkers.

3. The system (102) as claimed in claim 1, wherein the processor (202) performs keystroke dynamics analysis by implementing a Bidirectional Long Short-Term Memory (BiLSTM) model trained on temporal sequences of keypress timestamps, interaction latencies, and pause distributions captured during digital tasks.

4. The system (102) as claimed in claim 1, wherein the processor (202) executes adaptive individual baseline construction by implementing a Gaussian mixture model trained on historical distributions of user-specific vocal, facial, interaction, and ambient-noise feature vectors.

5. The system (102) as claimed in claim 1, wherein the processor (202) performs stress, cognitive load, and emotional fluctuation classification by implementing a support vector machine model trained on fused physiological, behavioural, and self-report feature embeddings.

6. The system (102) as claimed in claim 1, wherein the processor (202) executes VR- session engagement scoring by implementing a gradient boosting regression model trained on mappings between VR interaction logs, gaze tracking events, and expert- annotated engagement scores.

7. The system (102) as claimed in claim 1, wherein the processor (202) performs corporate wellbeing score computation by implementing a random forest model trained on multidimensional vectors comprising task completion rates, absenteeism metrics, performance evaluations, and survey-derived sentiment indices.

8. The system (102) as claimed in claim 1, wherein the processor (202) executes sentiment and thematic extraction from employee and parent feedback by implementing a transformer-based language model trained on domain-specific corpora of wellness, education, and workplace narratives.

9. The system (102) as claimed in claim 1, wherein the processor (202) performs clusterbased stratification of students and employees into risk cohorts by implementing a k- means clustering model trained on normalized wellness, performance, and engagement feature spaces.

10. A method (400) for emotional assessment, the method (400) comprising steps of: receiving (402), by a processor (202), data selected from any or a combination of a vocal biomarker, a facial micro-expression, a pupil dilation level, a blink rate, an eye-movement rate, an interaction latency level on an integrated digital device, a background environmental noise level, and a self-reported mood input from a user; generating (404), by the processor (202), an adaptive individual baseline by analyzing the received data; detecting (406), by the processor (202), user-specific behavioral and physiological patterns and deviations indicative of any or a combination of stress, cognitive load, and emotional fluctuation based on the adaptive individual baseline;deriving (408), by the processor (202), a score based on any or a combination of magnitude, frequency, and pattern of the detected deviations from the adaptive individual baseline; and recommending (410), by the processor (202), a context-specific intervention to the user based on the derived score.

Images