DESC:FIELD OF THE INVENTION
Embodiment of the present invention relates to a system and method for measuring effective learning progress in a simulated learning environment and more particularly for measuring attention distribution, focus levels and distraction levels of a user when training in a simulated learning environment.
BACKGROUND OF THE INVENTION
Learning in a simulation environment have exhibited highly positive experience(s) for a user/trainee. Especially with advent of compelling Augmented Reality (AR), Virtual Reality (VR), Mixed Reality (MR) platforms, realistic interactive experiences can be achieved for almost all domains of technology. The user gets to experience an immersive and flow like rich state during his learning as real life like training sessions are generated in virtual world. With the simulated learning environment, the educational benefits of tutoring and training can be made more widely available. Often, a substantial investment is directed to the problem of creating AR/VR/MR based training systems that can approximate the effectiveness of human tutors.
However, as the virtual training progresses for prolonged hours, it becomes difficult to keep the user engaged and avoid distraction. So, even if the total training time of a user is reflected as 8-10 hours, his effective learning time may be much less. Other than observing long hours of training, a virtual training program has no way to infer whether a particular subtask skill or area of expertise is adequately familiar or whether the trainee would benefit from more practice. Indeed, a central issue in the development of virtualized training systems is the question of how to assess when and to what degree learning has occurred.
This may pose a problem in discerning exact learning and training levels attained by the user since the total screen time may not be a true indicator for the same. Learnings and trainings that are primarily performance based such as welding, painting, cutting a diamond or learning driving skills or repairing a jet engine require knowledge assimilation that contribute directly to trainee’s performance in reality. Perhaps, measuring attention and focus levels along with levels of skill adaptation are some of key factors to be considered for corrective assessment. Number of theories exist for measuring attention levels, flow and immersive state of a trainee/user that are testimony to the complex nature of the underlying mental state when learning or practicing a new skill set.
In addition, much of training enthusiasm and learner’s intrinsic motivation towards the activity may be diminished if no immediate/unambiguous feedback is provided as a measure of his skill upliftment, accuracy of action performed, control over his activity, engagement and engrossment levels, concentration and attention on his tasks. None of the existing methods have been successful in measuring such valuable and quality parameters of a user/trainee in real time, which will always question user’s ability to elicit same cognitive and behavioural skills in real time situations. The whole attempt of provisioning such realistic environment may prove futile if user actual performance data during practice portion of simulation is not credible and authentic enough to be relied upon by recruiters.
The present disclosure sets forth system and method for measuring attention and focus driven parameters during trainee’s learning sessions, embodying advantageous alternatives and improvements to existing simulation systems and methods, and that may address one or more of the challenges or needs mentioned herein, as well as provide other benefits and advantages.

OBJECT OF THE INVENTION
An object of the present invention is to provide a system and method for measuring attention distribution and focus levels in a simulated learning environment.
Another object of the present invention is to provide a distraction detection system and method for measuring effective learning during trainee’s training sessions.
Yet another object of the present invention is to provide a system and method that estimate user’s state with respect to attention concentration levels, alertness levels, distraction levels by correlating actions performed by the trainee with electrical brain signals and physiological parameters of the user.
Yet another object of the present invention is to provide a system and method that calculates effective training levels attained by the trainee in overall training sessions.
Yet another object of the present invention is to provide a system and method that provides instant, clear and unambiguous feedback to user regarding his real time performance levels and overall progress curve.
In yet another embodiment, the system and method that provides accurate reporting of effective learning and training undergone by the trainee thereby assisting in more correct assessment of trainee.
BRIEF DESCRIPTION OF THE DRAWINGS
So that the manner in which the above recited features of the present invention can be understood in detail, a more particular to the description of the invention, briefly summarized above, may be had by reference to embodiments, some of which are illustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only typical embodiments of this invention and are therefore not to be considered limiting of its scope, the invention may admit to other equally effective embodiments.
These and other features, benefits and advantages of the present invention will become apparent by reference to the following text figure, with like reference numbers referring to like structures across the views, wherein:
Fig. 1 illustrates a flow diagram for measuring progress in a simulated learning environment, in accordance with an embodiment of the present invention.
DETAILED DESCRIPTION
While the present invention is described herein by way of example using embodiments and illustrative drawings, those skilled in the art will recognize that the invention is not limited to the embodiments of drawing or drawings described and are not intended to represent the scale of the various components. Further, some components that may form a part of the invention may not be illustrated in certain figures, for ease of illustration, and such omissions do not limit the embodiments outlined in any way. It should be understood that the drawings and detailed description thereto are not intended to limit the invention to the particular form disclosed, but on the contrary, the invention is to cover all modifications, equivalents, and alternatives falling within the scope of the present invention as defined by the appended claims. As used throughout this description, the word "may" be used in a permissive sense (i.e., meaning having the potential to), rather than the mandatory sense, (i.e., meaning must). Further, the words "a" or "an" mean "at least one” and the word “plurality” means “one or more” unless otherwise mentioned. Furthermore, the terminology and phraseology used herein is solely used for descriptive purposes and should not be construed as limiting in scope. Language such as "including," "comprising," "having," "containing," or "involving," and variations thereof, is intended to be broad and encompass the subject matter listed thereafter, equivalents, and additional subject matter not recited, and is not intended to exclude other additives, components, integers or steps. Likewise, the term "comprising" is considered synonymous with the terms "including" or "containing" for applicable legal purposes. Any discussion of documents, acts, materials, devices, articles, and the like are included in the specification solely for the purpose of providing a context for the present invention. It is not suggested or represented that any or all of these matters form part of the prior art base or were common general knowledge in the field relevant to the present invention.
In this disclosure, whenever a composition or an element or a group of elements is preceded with the transitional phrase “comprising”, it is understood that we also contemplate the same composition, element or group of elements with transitional phrases “consisting of”, “consisting”, “selected from the group of consisting of, “including”, or “is” preceding the recitation of the composition, element or group of elements and vice versa.
The present invention is described hereinafter by various embodiments with reference to the accompanying drawings, wherein reference numerals used in the accompanying drawing correspond to the like elements throughout the description. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiment set forth herein. Rather, the embodiment is provided so that this disclosure will be thorough and complete and will fully convey the scope of the invention to those skilled in the art. In the following detailed description, numeric values and ranges are provided for various aspects of the implementations described. These values and ranges are to be treated as examples only and are not intended to limit the scope of the claims. In addition, a number of materials are identified as suitable for various facets of the implementations. These materials are to be treated as exemplary and are not intended to limit the scope of the invention.
In accordance with one general embodiment of present disclosure, the present system and method are directed to evaluating efficiency of mixed reality/augmented reality/virtual reality based simulation learning from measurable differences observed in enhanced cognitive skills-, attention retention, cognitive suppression, behavioural suppression, selective attention, convertible attention, distributive attention, interference control and the like. Accordingly, the system works by measuring the user's attention state level in real time and using the user's attention state to quickly train the learner to acquire correct cognitive skills. Focus is to help learner know and attain focused continuous attention for prolonged period of time.
In accordance with one exemplary embodiment, there may be continuous real time monitoring of brain activity to determine correlation between monitored brain activity exhibiting cognitive skills with learner’s activity performance parameters. The learner’s cognitive ability along with attentive ability may be measured from brain state and a correlation is derived to understand areas of improvement during skill development process. Accordingly, for a correlation value deviating/exceeding from a predetermined threshold value, a feedback mechanism is initiated that may guide the learner in real time to take corrective action - increasing focus and attentional awareness on task performed, concentrating efforts on task in hand to avoid any accidents/harm, performing task meticulously without being distracted, reactivating state of reduced alertness and the like.
In one example embodiment, neuroelectric signals may be measured and monitored. Neurophysiological system such as Electroencephalography (EEG), galvanometers, and electrocardiographs may be employed as instruments for monitoring the neuroelectric signals including brain's electrical activity. EEG is typically non-invasive in which the electrodes are placed along the scalp, but for certain applications, invasive electrodes may be used. EEG measures voltage fluctuations caused by ionic currents in neurons in the brain. The frequency intensity of detected EEG signals is calculated to estimate the alert and attentive state of learner.
In another example embodiment, the concentration and attention span of a learner may be measured using neuroimaging techniques, such as functional magnetic resonance imaging (fMRI) or functional near-infrared spectroscopy (fNIRS) may be utilized. In one preferred embodiment, using fNIRS allows for the investigation of brain reorganization with multimodal stimulation and real-time control of the changes occurring in brain activity.
Positron Emission Tomography (PET) brain-imaging data has shown that less cortical blood flow (implying less cortical activation) is observed after practice on complex tasks. All the above scientific approaches for inferring signals from biological brain provide an important insight into how these systems operate.
In one aspect of disclosure the user is monitored for enhancement in his activity performance by way of calculating a precision score. For instance, if the user is engaged in a skill training session for a given time period, he is observed on how closely he is following the instructions, and whether the resulting performance is getting better with each session and level enhancement. This precision score gives an objective understanding on how effectively the user is progressing towards skill development in a given trade.
Next, if the precision score obtained is lower than a predetermined threshold for that particular skill activity, the user is either made to repeat the activity or demoted to previous levels to improve upon his skills. However, if the precision score is above a predetermined threshold level, but somehow has become static with no significant improvement reported even after continued practice, the user is assessed for his cognitive inhibition. Say for instance, after certain levels and prolonged practice sessions, the user inspite of correctly performing the task has either obtained a plateau in his progress reports, or even if he is duly performing the activity, his attention is either divided or not sustainable for long training sessions. This distracted, alternating and divided attention levels are reported to be of marked value when skill level precision as close as 99.9% is required.
In such situations, measuring attention levels, focus state, distraction levels becomes extremely important to gauge if the user is sincerely and dedicatedly involved in the task being performed. Measuring the performance at such detailed level will help in achieving remarkable progress particularly in trades where excessive levels of focus and precision levels are required for prolonged time periods; say for example during medical surgical intervention.
In order to resolve this, in one significant aspect of present disclosure, the brain signal activity is mapped with the activity performed by the user to derive a precision score. Thereafter, the correlation score is primarily computed based on precision score and a mapping between the brain signals and activity performance combined with attention levels with which the user performs the training.
Defining user attention levels while undergoing a training session is a critical parameter of present disclosure. In one exemplary embodiment, visual impressions and underlying representations in user brain are decoded and reconstructed to derive a correspondence between the visual reconstructions and precision with which the activity is being performed by the user to understand user focus levels. For accomplishing such a challenging task, the semantic content of images is deduced for reconstructing brain images. In one working embodiment, deep generative models such as Latent Diffusion model is used for conditional image generation with high image resolution and semantic fidelity at reduced computational costs.
One of the Latent Diffusion model (LDM), known as Stable diffusion is utilized to represent latent signals within each layer of Diffusion model (DM) as specific components are mapped to distinct brain regions. Different components of deep learning models are used and correlated with brain processes to develop a predictive model of brain activity. The visual reconstruction from captured brain signals using LDM is achieved primarily in three steps. Broadly, the model is trained by constructing linear models that map brain signals to each LDM component.
Of the three steps, at first a latent representation of image presented from brain signals within early visual cortex (posterior part of visual cortex) is predicted. This latent representation is now processed by a decoder of an autoencoder to produce a coarse decoded image. The coarse decoded image is processed by an encoder of autoencoder and noise is added to it by a diffusion process. Further, latent text representations from brain signals within higher visual cortex (anterior part of visual cortex) are decoded. This is followed by adding noise and decoding latent text representations to be used as input for producing coarse decoded image. Finally, this coarse decoded image from latent text representation along with the coarse decoded image from latent image representation goes as an input to the decoding module of the autoencoder to produce a finally reconstructed image of high resolution.
This finally reconstructed image is mapped with user’s current activity to decipher if the user is thinking the same as he is doing. This is a vital piece of information to know what the user attention levels are and what are his distractions; if he is merely performing task having some other thought his performance is impeded basis his focus levels. Thus, user’s focused attention, sustained attention, cognitive inhibition, behavior inhibition, alternating attention levels can be deduced that helps in obtaining a condensed composite correlation score. The user’s activity performance is continually monitored for correctness to task stimuli and the user is rewarded on a scale of 0%-100% based on similarity of activity and reconstructed image data.
For example, for a correlation score more than 90% it can be inferred that a user is paying due attention to activity performed. The time period for which the focused levels remains consistent and above 90% shall indicate period of sustained attention. However, this threshold can be varied based on skill the user is being trained on. Next, the system provides a corrective feedback to the user in an event the correlation score is less than a threshold value. The user is then closely observed for his progression based on correlation score and all areas of improvement where the user lags in a particular trade are documented for detailed analysis.
The detailed analytical report is generated based on correlation score that shall provide insights on how long the user can hold his attention levels, what is his comfortable zone of practice where he scores maximum almost every time, tasks he find difficulty in improvising or skill type at which he usually falter, time span after which his attention gets usually divided, interest levels in improving his rank on scoreboard and the like based on a composite weighted score that can be obtained by combining precision score and correlation score. All performance indicators that assist in assessing user skill improvement are fed as parameters to a machine learning model (as will be explained later).
In next working embodiment, real time dynamic modification and optimization of parameters for enabling user improve his current skill accomplishment levels is suggested. The skill training activity may comprise a number of training parameters that describe certain aspects of that training and affect the execution or operation of that training activity. A measure of user’s progress in skill development is recorded; whether the user succeeded in performing indicated action or completing certain goals in the training session; how long it took the user to complete certain goals, how much time user invested in accomplishing a skill level; how often the user get stuck on same skill aspect; how long the user can perform while staying focused, average session time, average score, average attempts per level and the like.
Now in order to maintain or increase the level of user engagement and interest in skill development process, the system dynamically updates the deterministic performance parameters. Accordingly the difficulty levels are decided and upgraded based on analytics report. Embodiments of present disclosure proposes development of a predictive model using one or more machine learning algorithms. This model feeds on precision score, correlation score, parameter values to dynamically update the difficulty level of training session and improve user engagement. In one proposed embodiment, the model may be executed at the processing end of head mounted display or a dedicated computing unit (not positioned on the head mounted display but coupled thereto) may be deployed for parameter modification and ML algorithm implementation.
For example, the predictive model can be used to determine one or more metrics that indicate the level of user engagement with the training activity based on user log history and aforementioned indicative parameters. Different types of multiple algorithms may be used by predictive model system. For example, certain embodiments herein may use a logistical regression algorithm. However, among others, other algorithms are possible, such as linear regression algorithms, discrete selection algorithms, or generalized linear algorithms.
Further, machine learning algorithms may be used to adaptively develop and update predictive models over time based on new user input. Some non-limiting examples of machine learning algorithms that can be used to create and update parametric functions or predictive models include regression algorithms (such as, for example, Ordinary Least Squares Regression), learning vector quantization, decision tree algorithms (e.g. classification and regression trees), Bayesian algorithms Bayesian algorithms (e.g., Naive Bayes), clustering algorithms (e.g., k-means clustering), association rule learning algorithms, artificial neural network algorithms (such as For example, such as Perceptron, deep learning algorithms (e.g., Deep Boltzmann Machine), dimensionality reduction algorithms (e.g., Supervised and non-supervised machine learning, including Principal Component Analysis, and / or other machine learning algorithms. Algorithms (supervised and non-supervised machine learning algorithms).
In accordance with one working embodiment, an illustration of a welding and painting experience of a learner in an AR/VR facilitated simulated environment is demonstrated. Here the user is attempting to learn a spray painting skill for example in a virtual reality (VR) environment. The user is configured with a head mounted display over which he receives instructions and guidelines for performing spray painting on a given virtual object in a VR world. The user is provided with real world tools such as a spraying gun in order to have real, immersive experience of spray painting. To begin with, user basic skills such as angle at which the gun should be held, optimal distance from which the filling paint should be sprayed, firmness with which the gun should be held, amount of paint to be sprayed at a given time etc. are honed.
Once the user starts following the uploaded instructions, he is closely monitored in this learning and development process. The user brain activity is retrieved from any given neurophysiological system and a precision score is calculated based on similarity identified between the activity performed and threshold levels set for that activity. The user is now watched for his attention levels i.e. if the activity he is performing is what he is actually focusing on. This is achieved using Latent Diffusion Model as explained above and a composite correlation score is calculated from combined precision score and mapped attention levels.
In an event the user is unable to achieve optimal performance due to low precision score or alternating attention levels, the user is instantly instructed on the same. Additionally, this also helps the user to understand if he really lags the knack for honing the challenging skill or if these are his deviated focus levels that are impeding his progress. Based on the advancements made by the user during various phases of skill development, the parameters deterministic of user performance are recorded and dynamically updated such that the user is notified and upgraded on skill aspects that require major attention.
The degree of attention of learner performing the welding operation is computed based on a combination of parameters underlying different states of welding. For example, parameters are defined to determine if the welding gun is properly held by learner, if the filler material to be filled into the welding gun is cautiously handled; if the leaner is at correct position (horizontal or vertical) and angle from display or the virtual object during training session, etc.
For instance, in vertical position, the welding piece can be placed perpendicular to the display facing the learner, which is different from the horizontal position and is comparatively difficult. Likewise, in an overhead welding position, which is a difficult and different position when compared with the horizontal and vertical positions, correct posture and position of learner along with focused attentive state is minimally expected to avoid any accidents or injuries. Other factors may include scenarios of performing welding action at correct speed and correct manner as simulating welding gun is held at right angle, position and orientation with respect to virtual article in a defined three-dimensional work space.
In one significant embodiment, means to evaluate correctiveness of action performed based on an alert and attentive state of learner is proposed. The learner is evaluated for task achieved, compliance with expectations, degree to compliance so that the learner can be given feedback in real time for the mistakes done, reasons of mistakes, and the mode/manner in which the mistakes can be rectified. Learners can therefore, say on a user interface, view his/her performance and see the progress/decline in the learning curve.
The environments replicating real life dangerous situations are generated to prepare the learner perform optimally in all accidental or emergency situations. In such simulation environments, a hypothetical emergency situation can be created. In any case, this recreation aims to create the illusion of a typical emergency situation, so that the attentive skills along with cognitive presence of students can be realistically assessed to determine learner’s response to a critical situation, if any, arises in the future. This can help one determine if one is truly ready for action in real world besides assisting the evaluators making a more reasonable and well-rounded assessment of learner’s performance levels and deciding if the trainee is expert or naïve, challenged or bored, engaged or distracted, motivated or indifferent. Overall, subtle interpersonal cues to infer information about a trainee's mental state may be derived using features of proposed invention, which may otherwise difficult to discern in virtual training environment.
In one embodiment, attention levels or distraction levels may be measured based precision levels and attention levels being paid by the learner at task in hand. For example, the learner may be focused filling the welding gun while trying to weld at same time. Alternately, imagine a driving simulation scenario where the driving is intermittently diverted in selecting playlist or operating stereo, talking and so on. In these situations, attention levels may be measured from brain signals corresponding to interest levels indicated in performing such ancillary tasks other than the main task. For example, there may be situations when the attention lag is due to overall drowsiness or mid-morning dreams or reveries while still performing the main task.
In accordance with an embodiment, the head mounted display configured to be worn by user during skill training comprises of a processing unit that communicates with a memory unit configured to store machine-readable instructions. The machine-readable instructions may be loaded into the memory unit from a non-transitory machine-readable medium, such as, but not limited to, CD-ROMs, DVD-ROMs and Flash Drives. Alternately, the machine-readable instructions may be loaded in a form of a computer software program into the memory unit. The memory unit in that manner may be selected from a group comprising EPROM, EEPROM and Flash memory. Further, the processing unit is operably connected with the memory unit. In various embodiments, the processor is one of, but not limited to, a general-purpose processor, an application specific integrated circuit (ASIC) and a field-programmable gate array (FPGA). The head mounted display further comprises of a display unit that is configured to display all instructions or suggestions made to the user during the course of his training session.
In general, the word “module,” as used herein, refers to logic embodied in hardware or firmware, or to a collection of software instructions, written in a programming language, such as, for example, Java, C, or assembly. One or more software instructions in the modules may be embedded in firmware, such as an EPROM. It will be appreciated that modules may comprised connected logic units, such as gates and flip-flops, and may comprise programmable units, such as programmable gate arrays or processors. The modules described herein may be implemented as either software and/or hardware modules and may be stored in any type of computer-readable medium or other computer storage device.
Further, while one or more operations have been described as being performed by or otherwise related to certain modules, devices or entities, the operations may be performed by or otherwise related to any module, device or entity. As such, any function or operation that has been described as being performed by a module could alternatively be performed by a different server, by the cloud computing platform, or a combination thereof. It should be understood that the techniques of the present disclosure might be implemented using a variety of technologies. For example, the methods described herein may be implemented by a series of computer executable instructions residing on a suitable computer readable medium. Suitable computer readable media may include volatile (e.g., RAM) and/or non-volatile (e.g., ROM, disk) memory, carrier waves and transmission media. Exemplary carrier waves may take the form of electrical, electromagnetic or optical signals conveying digital data steams along a local network or a publicly accessible network such as the Internet.
It should also be understood that, unless specifically stated otherwise as apparent from the following discussion, it is appreciated that throughout the description, discussions utilizing terms such as "controlling" or "obtaining" or "computing" or "storing" or "receiving" or "determining" or the like, refer to the action and processes of a computer system, or similar electronic computing device, that processes and transforms data represented as physical (electronic) quantities within the computer system's registers and memories into other data similarly represented as physical quantities within the computer system memories or registers or other such information storage, transmission or display devices.
Various modifications to these embodiments are apparent to those skilled in the art from the description and the accompanying drawings. The principles associated with the various embodiments described herein may be applied to other embodiments. Therefore, the description is not intended to be limited to the embodiments shown along with the accompanying drawings but is to be providing broadest scope of consistent with the principles and the novel and inventive features disclosed or suggested herein. Accordingly, the invention is anticipated to hold on to all other such alternatives, modifications, and variations that fall within the scope of the present invention
,CLAIMS:We Claim:

1) A method for measuring progress in a simulated learning environment, comprising:
retrieving information from user brain activity and user’s activity performance;
computing a precision score based on comparing the user’s activity performance with one or more predetermined activity performance parameters;
computing user attention levels based on correspondence between visual reconstructions from the user brain and the precision score;
computing a correlation score based on combination of the computed user attention levels and the precision score; and
providing a corrective feedback to the user in real time in an event the correlation score is lower than a predetermined threshold.

2) The method, as claimed in claim 1, further comprising dynamically updating the user activity performance parameters to enable the user achieve improvisation across all aspects of the simulated learning environment.

3) The method, as claimed in claim 1, wherein the user brain activity is retrieved from neuroelectric signals that is obtained from EEG, galvanometers, electrocardiographs or any neuroimaging technique.

4) The method, as claimed in claim 1, wherein in an event the precision score is less than a predetermined threshold, the user is instructed to repeat one or more tasks for which the precision score is calculated as low.

5) The method, as claimed in claim 1, wherein the user attention level is computed from a Latent Diffusion model (LDM) that is used for conditional image generation with high image resolution and semantic fidelity.

6) The method, as claimed in claim 1, wherein the visual reconstructions from the user brain are obtained in steps of:
processing a latent representation of image presented from the brain signals within early visual cortex to produce a coarse decoded image therefrom;
processing the coarse decoded image obtained from the latent representation of image and adding noise thereto;
processing latent text representations from the brain signals within higher visual cortex and obtaining coarse decoded image therefrom; and
decoding the coarse decoded image from the latent representation of image and the coarse decoded image from the latent text representation to generate the visual reconstructions.

7) The method, as claimed in claim 1, wherein in an event the correlation score is below a predetermined threshold, the user is suggested to focus his attention levels towards enhancing his overall score for skill development in the simulated learning environment.

8) The method, as claimed in claim 1, further comprising providing a detailed analytics on user activity performance such as length of time for which the user has the attention levels more than the correlation score, user maximum scoring skill levels, skill aspects the user is expected to improvise upon, user interest levels in skill enhancement based on a combination of the precision score and the correlation score.

9) The method, as claimed in claim 2, wherein the user activity performance parameters are dynamically updated using a machine learning model that feeds on the precision score and the correlation score to update deterministic parameters for user performance evaluation.

10) The method, as claimed in claim 9, wherein the machine learning model may be selected from a group comprising linear regression algorithms, discrete selection algorithms, or generalized linear algorithms, decision tree, Bayesian algorithms, clustering algorithms, artificial neural network, dimensionality reduction algorithm or any other supervised and non-supervised machine learning algorithm.

11) A system for measuring progress in a simulated learning environment, comprising:
a neuroelectric signal capturing device configured to retrieve information from user brain activity and user’s activity performance;
a head mounted display comprising:
a processing unit configured to receive the user activity performance to:
compute a precision score based on comparing the user’s activity performance with one or more predetermined activity performance parameters;
compute user attention levels based on correspondence between visual reconstructions from the user brain and the precision score;
compute a correlation score based on combination of the computed user attention levels and the precision score; and
a display unit configured to display a corrective feedback to the user in real time in an event the correlation score is lower than a predetermined threshold.

12) The system, as claimed in claim 11, wherein the processing unit is further configured to dynamically update the user activity performance parameters to enable the user achieve improvisation across all aspects of the simulated learning environment.

13) The system, as claimed in claim 11, wherein the neuroelectric signals are obtained from EEG, galvanometers, electrocardiographs or from any other neuroimaging technique.

14) The system, as claimed in claim 11, wherein the display unit of the head mounted display is configured to instruct the user to repeat one or more tasks in an event the precision score for corresponding task is less than a predetermined threshold.

15) The system, as claimed in claim 11, wherein the processing unit is configured to compute the user attention level from a Latent Diffusion model (LDM) that is used for conditional image generation with high image resolution and semantic fidelity.

16) The system, as claimed in claim 11, wherein the processing unit is configured to obtain visual reconstructions from the user brain in steps of:
processing a latent representation of image presented from the brain signals within early visual cortex to produce a coarse decoded image therefrom;
processing the coarse decoded image obtained from the latent representation of image and adding noise thereto;
processing latent text representations from the brain signals within higher visual cortex and obtaining coarse decoded image therefrom; and
decoding the coarse decoded image from the latent representation of image and the coarse decoded image from the latent text representation to generate the visual reconstructions.

17) The system, as claimed in claim 11, wherein the display unit of the head mounted display is configured to suggest user to focus his attention levels towards enhancing his overall score for skill development in the simulated learning environment in an event the correlation score is below a predetermined threshold.

18) The system, as claimed in claim 11, wherein the display unit of the head mounted display is configured to display a detailed analytics on user activity performance such as length of time for which the user has the attention levels more than the correlation score, user maximum scoring skill levels, skill aspects the user is expected to improvise upon, user interest levels in skill enhancement based on a combination of the precision score and the correlation score.

19) The method, as claimed in claim 12, wherein the processing unit is configured to dynamically update user activity performance parameters using a machine learning model that feeds on the precision score and the correlation score to update deterministic parameters for user performance evaluation.

20) The system, as claimed in claim 19, wherein the machine learning model may be selected from a group comprising linear regression algorithms, discrete selection algorithms, or generalized linear algorithms, decision tree, Bayesian algorithms, clustering algorithms, artificial neural network, dimensionality reduction algorithm or any other supervised and non-supervised machine learning algorithm.