System and method for optimizing content engagement based on biosignal data of a subject

Abstract

A system (114) for dynamically optimizing content engagement for a subject (112) is disclosed. The system (114) includes a plurality of biosensor electrodes (102), a controller (106), and a recommendation engine (108). The biosensor electrodes (102) measure at least one physiological parameter, i.e., EEG signal, of the subject (112). The controller (106) detect response generated in a brain of the subject, while consuming the content, via at least one Artificial Intelligence Model, based on the EEG signal. The controller (106) performs filtering of the content and dynamically curate and recommend content based on the detected response via another Artificial Intelligence Model and transmits, simultaneously, a signal associated with the detected response to an engagement analysis engine to generate content neurofeedback insights. The recommendation engine optimize, dynamically, the content engagement and media delivery strategies via refining content recommendations, based on the content neurofeedback insights.

Description

SYSTEM AND METHOD FOR OPTIMIZING CONTENT ENGAGEMENT BASED ON BIOSIGNAL DATA OF A SUBJECT TECHNICAL FIELD

[0001] The present disclosure relates to a system and method for optimizing content engagement and media product delivery based on biosignals particularly electroencephalography (EEG) data of a subject. BACKGROUND

[0002] In today’s world, electroencephalogram (EEG) tests are used to study brain activity by recording electrical signals generated by neurons in the brain of human beings. The data generated from the EEG test is used in different fields, for example, neuroscience, medicine, and marketing, to generate and provide a desired result to a subject as per requirement.

[0003] However, conventional EEG test sessions are typically short and intermittent, mainly for clinical use, resulting in sparse data points that fail to capture the dynamic nature of brain activity. This limitation poses a significant challenge for prolonged neurological studies and the detection of subtle changes in brain function associated with various content perceived by the subject, etc.

[0004] The constrained accessibility of EEG devices has primarily restricted EEG data collection to research laboratories and clinical settings, while there are many other applications where this data can be used for more curated experiences and personalised engagements. Further, since there does not exist a robust system to collect vast dataset generated from large number of users to counterbalance any limitations in individual sensor accuracy, thereby limiting the development of a robust foundation for analyzing and monitoring the behavioural insights of the subject. progression of patients with neurological conditions such as epilepsy, seizures, and others.

[0005] Thus, there is a need to provide a system and method which seamlessly integrates brain activity tracking, machine learning, and artificial intelligence to empower recommendation engines with a profound understanding of consumer behaviour and preferences.SUMMARY

[0006] This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention. This summary is neither intended to identify key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.

[0007] The present disclosure discloses a system for dynamically optimizing content engagement for a subject. The system includes a plurality of biosensor electrodes, a controller, and a recommendation engine. The plurality of biosensor electrodes is in contact with at least one of a scalp and an ear canal of the subject consuming content from a user equipment (UE). The plurality of biosensor electrodes is configured to measure at least one physiological parameter of the subject. The at least one physiological parameter is Electroencephalogram (EEG) signal. The controller is in communication with the plurality of biosensor electrodes. The controller is configured to detect response generated in the brain of the subject, while consuming the content, via at least one Artificial Intelligence Model, based on the EEG signal. The controller is configured to perform filtering of the content and dynamically curate and recommend content based on the detected response via another Artificial Intelligence Model. The controller is configured to transmit, simultaneously, a signal associated with the detected response to an engagement analysis engine to generate content neurofeedback insights. The recommendation engine is in communication with the controller and the engagement analysis engine. The recommendation engine is configured to optimize, dynamically, the content engagement and media delivery strategies via refining content recommendations, based on the content neurofeedback insights.

[0008] The present disclosure discloses a method for dynamically optimizing content engagement for a subject. The method includes detecting response generated in a brain of the subject, while consuming content, via at least one Artificial Intelligence Model, based on EEG signal. The method includes performing filtering of the content and dynamically curate and recommend content based on the detected response via at least another Artificial Intelligence Model. Further, the method includes transmitting, simultaneously, a signal associated with the detected response to an engagement analysis engine to generate content neurofeedback insights. Furthermore, the method includes optimizing, dynamically, the content engagement and media delivery strategies via refining content recommendations, based on the content neurofeedback insights.

[0009] To further clarify the advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] These and other features, aspects, and advantages of the present invention will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein: Figure 1 illustrates a block diagram for a system configured to dynamically optimizing content engagement for a subject, in accordance with an embodiment of the present disclosure; Figures 2A-2D illustrate a device for capturing and monitoring electroencephalography (EEG) signals of the subject, in accordance with an embodiment of the present disclosure; Figure 3 illustrates a block diagram of controller of the system for capturing and monitoring electroencephalography (EEG) signals of the subject, in accordance with an embodiment of the present disclosure; and Figure 4A illustrates a flowchart depicting a method for optimizing content engagement and media product delivery based on electroencephalography (EEG) data of the subject, in accordance with an embodiment of the present disclosure; Figure 4B illustrates a flowchart depicting a method performed by the system for stimulus interlacing and delivering the interlaced content to the subject, in accordance with an embodiment of the present disclosure; Figures 4C and 4D illustrate an example block diagram depicting a probable output, in accordance with an embodiment of the present disclosure; and Figure 5 illustrates a flowchart depicting a method performed by the system for optimizing content engagement and media product delivery based on electroencephalography (EEG) data of the subject, in accordance with an embodiment of the present disclosure;

[0011] Further, skilled artisans will appreciate that elements in the drawings are illustrated for simplicity and may not have necessarily been drawn to scale. Furthermore, in terms of theconstruction of the device, a plurality of components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only those specific details that are pertinent to understanding the embodiments of the present invention so as not to obscure the drawings with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein. DETAILED DESCRIPTION OF FIGURES

[0012] For the purpose of promoting an understanding of the principles of the invention, reference will now be made to the embodiment illustrated in the drawings and specific language will be used to describe the same. It will nevertheless be understood that no limitation of the scope of the invention is thereby intended, such alterations and further modifications in the illustrated system, and such further applications of the principles of the invention as illustrated therein being contemplated as would normally occur to one skilled in the art to which the invention relates. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skilled in the art to which invention belongs. The system and examples provided herein are illustrative only and not intended to be limiting.

[0013] For example, the term “some” as used herein may be understood as “none” or “one” or “more than one” or “all.” Therefore, the terms “none,” “one,” “more than one,” “more than one, but not all” or “all” would fall under the definition of “some.” It should be appreciated by a person skilled in the art that the terminology and structure employed herein is for describing, teaching, and illuminating some embodiments and their specific features and elements and therefore, should not be construed to limit, restrict, or reduce the spirit and scope of the present disclosure in any way.

[0014] For example, any terms used herein, such as “includes,” “comprises,” “has,” “consists,” and similar grammatical variants do not specify an exact limitation or restriction, and certainly do not exclude the possible addition of a plurality of features or elements, unless otherwise stated. Further, such terms must not be taken to exclude the possible removal of the plurality of the listed features and elements, unless otherwise stated, for example, by using the limiting language including, but not limited to, “must comprise” or “needs to include.”

[0015] Whether or not a certain feature or element was limited to being used only once, it may still be referred to as “plurality of features” or “plurality of elements” or “at least one feature”or “at least one element.” Furthermore, the use of the terms “plurality of” or “at least one” feature or element do not preclude there being none of that feature or element, unless otherwise specified by limiting language including, but not limited to, “there needs to be plurality of…” or “plurality of elements is required.”

[0016] Unless otherwise defined, all terms and especially any technical and / or scientific terms, used herein may be taken to have the same meaning as commonly understood by a person ordinarily skilled in the art.

[0017] Reference is made herein to some “embodiments.” It should be understood that an embodiment is an example of a possible implementation of any features and / or elements of the present disclosure. Some embodiments have been described for the purpose of explaining plurality of the potential ways in which the specific features and / or elements of the proposed disclosure fulfil the requirements of uniqueness, utility, and non-obviousness.

[0018] Use of the phrases and / or terms including, but not limited to, “a first embodiment,” “a further embodiment,” “an alternate embodiment,” “one embodiment,” “an embodiment,” “multiple embodiments,” “some embodiments,” “other embodiments,” “further embodiment”, “furthermore embodiment”, “additional embodiment” or other variants thereof do not necessarily refer to the same embodiments. Unless otherwise specified, plurality of particular features and / or elements described in connection with plurality of embodiments may be found in one embodiment, or may be found in more than one embodiment, or may be found in all embodiments, or may be found in no embodiments. Although plurality of features and / or elements may be described herein in the context of only a single embodiment, or in the context of more than one embodiment, or in the context of all embodiments, the features and / or elements may instead be provided separately or in any appropriate combination or not at all. Conversely, any features and / or elements described in the context of separate embodiments may alternatively be realized as existing together in the context of a single embodiment.

[0019] The use of terms such as, but not limited to, “content,” “media,” and their variants may include a wide range of formats and materials. This may include audiovisual components, advertisements, promotional or marketing materials, informational disclosures, or any other communicative elements, as appropriate to the context.. These terms may be used interchangably and based on the context.

[0020] The present disclosure discloses a system and a method for optimizing content engagement and media product delivery based on electroencephalography (EEG) data. The system collects biosignal data from subjects interacting with content to analyze their cognitive and emotional responses. By leveraging this data, the system analyzes real-time neural responses to enable personalized content recommendations and emotion-based content filtering. Through advanced machine learning techniques, the system generates personalized models, extracts brainwave markers, and optimizes content curation, thereby enhancing subject engagement and satisfaction. Additionally, the system includes a decentralized EEG database on the blockchain, facilitating transparent and secure data exchange for advancing neurological ailment research (Epilepsy, Alzheimer's disease) and personalized consumer applications.

[0021] Any particular and all details set forth herein are used in the context of some embodiments and therefore should not necessarily be taken as limiting factors to the proposed disclosure.

[0022] Embodiments of the present invention will be described below in detail with reference to the accompanying drawings.

[0023] Figure 1 illustrates a block diagram for a system 114 configured to dynamically optimise content engagement for a subject 112.

[0024] In an embodiment, the system 114 may include a plurality of biosensor electrodes 102, a controller 104, an engagement analysis engine 106, and a recommendation engine 108. In such an embodiment, the plurality of biosensor electrodes 102 (referred to herein as an electrode 100), the controller 104 may be integrated in a wearable device 100 (referred to herein as a device 100), without departing from the scope of the present disclosure. In an embodiment, the system 114 may be communicatively coupled with the device 100, without departing from the scope of the present disclosure. In another embodiment, the system 114 may be deployed in the device 100, without departing from the scope of the present disclosure. Further, the engagement analysis engine 106 and the recommendation engine 108 may be based on a cloud server or a hardware based edge computing module, without departing from the scope of the present disclosure.

[0025] In an embodiment, the system 114 may be configured to detect responses generated in a brain of the subject 112, while consuming the content, via at least one Artificial Intelligence Model, based on Electroencephalogram (EEG) signal of the subject 112. The system 114 maybe configured to perform filtering of the content and dynamically curate and recommend content based on the detected response via another Artificial Intelligence Model. The system 114 may be configured to generate content neurofeedback insights. Further, the system 114 optimize, dynamically, the content engagement and media delivery strategies via refining content recommendations, based on the content neurofeedback insights. In an advantageous aspect, the system 114 provides the optimized content engagement to the subject 112, thus, the subject 112 receives content that aligns with their interests, needs, and preferences, thereby resulting in reduced wastage of time and increased satisfaction.

[0026] The constructional and functional details of the system 114, along with the device 100, are explained in the subsequent paragraphs.

[0027] Figures 2A-2D illustrate the electrode 102 in the device 100 for capturing and monitoring electroencephalography (EEG) signals of the subject 112 to optimize content engagement and media product delivery based on the EEG signals, in accordance with an embodiment of the present disclosure.

[0028] In an embodiment, the device 100 may be an ear wearable electronic device, for example, Earphones, headphones, etc. In another embodiment, the device 100 may be a head wearable electronic device, for example, an Augmented Reality / Virtual Reality (AR / VR) Set, or headband, without departing from the scope of the present disclosure.

[0029] In an embodiment, the electrode 102 may be disposed on the device 100. Further, the device 100 may include a plurality of sensors adapted to measure different physiological parameters of the subject. The electrode 102 may be in contact with at least one of a scalp and an ear canal of the subject 112, consuming content from a user equipment (UE) 116 (as shown in Figure 1). The electrode 102 may be in contact with the skin that is situated in close proximity of the skull , where the brainwave may be observed, which may either be in the scalp region, around the ear or the region of ear canal Further, the plurality of sensors and the electrode 102 capture subjects' brainwave responses to a tailored set of audiovisual stimuli, including imperceptible frequency embeddings, designed to elicit unique neural signatures, without departing from the scope of the present disclosure. In an embodiment, the subject 112 may be a user, without departing from the scope of the present disclosure.

[0030] Each electrode and each sensor may enable the non-intrusive acquisition of EEG signals. This facilitates the measurement of neural responses with greater accessibility andreduced complexity. Particularly, each electrode may be adapted to measure at least one physiological parameter of the subject 112, where the at least one physiological parameter may be the EEG signal. Further, the electrode 102 may provide the EEG signals to the controller 104. The controller 104, along with the engagement analysis engine 106, and the recommendation engine 108, may be adapted to monitor the EEG signals to optimize content engagement and media product delivery / media delivery strategies based on data from the EEG signals. The EEG signals provide a powerful window into human brain dynamics by capturing intricate spatiotemporal patterns and spectral signatures that reflect the underlying neural processes governing various aspects of human experience. The rich information encoded in the spatial distribution, temporal fluctuations, and frequency characteristics of the EEG signals offers a unique opportunity to investigate the neurobiological underpinnings of higher cognitive functions, emotional processing, and attentional mechanisms.

[0031] This ensures that by decoding neural signatures by the system 114, advertisers and content creators can optimize their strategies to resonate more effectively with target audiences, capitalizing on neuroscientific insights to tailor experiences with greater precision and inclusivity.

[0032] Further, the constructional detail of the controller 104 is explained in subsequent paragraphs.

[0033] Figure 3 illustrates a block diagram of the controller 104, in accordance with an embodiment of the present disclosure. Figure 4A illustrates a flowchart depicting a method 300 for optimization of the content engagement and media product delivery based on the EEG data and providing the optimized content engagement and media product delivery to the subject 112, in accordance with an embodiment of the present disclosure. Figure 4B illustrates a flowchart depicting a method performed by the system 114 for stimulus interlacing and delivering the interlaced content to the subject, in accordance with an embodiment of the present disclosure. Figures 4C and 4D illustrate an example block diagram depicting a probable output, in accordance with an embodiment of the present disclosure.

[0034] In an embodiment, the controller 104 may be adapted to communicate with the electrode 102.

[0035] The controller 104 includes a processor / controller 304, a memory 306, module(s) 308. The memory 306, in one example, may store the instructions to carry out the operations of the modules 308. The modules 308 and the memory 306 may be coupled to the processor 304.

[0036] The processor 304 can be a single processing unit or several units, all of which could include multiple computing units. The processor 304 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and / or any devices that manipulate signals based on operational instructions. Among other capabilities, the processor 304 is configured to fetch and execute computer-readable instructions and data stored in the memory 306. The processor 304 may include one or a plurality of processors. At this time, one or a plurality of processors may be a general-purpose processor, such as a central processing unit (CPU), an application processor (AP), or the like, a graphics-only processing unit such as a graphics processing unit (GPU), a visual processing unit (VPU), and / or an AI-dedicated processor such as a neural processing unit (NPU). The one or a plurality of processors control the processing of the input data in accordance with a predefined operating rule or artificial intelligence (AI) model stored in the non-volatile memory and the volatile memory. The predefined operating rule or machine learning model is provided through training or learning.

[0037] The memory 306 may include any non-transitory computer-readable medium known in the art including, for example, volatile memory, such as static random-access memory (SRAM) and dynamic random-access memory (DRAM), and / or non-volatile memory, such as read-only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes.

[0038] The modules 308, amongst other things, include routines, programs, objects, components, data structures, etc., which perform particular tasks or implement data types. The modules 308 may also be implemented as, signal processor(s), state machine(s), logic circuitries, and / or any other device or component that manipulates signals based on operational instructions.

[0039] Further, the modules 308 can be implemented in hardware, instructions executed by a processing unit, or by a combination thereof. The processing unit can comprise a computer, a processor, such as the processor 304, a state machine, a logic array, or any other suitable devices capable of processing instructions. The processing unit can be a general-purposeprocessor which executes instructions to cause the general-purpose processor to perform the required tasks or, the processing unit can be dedicated to performing the required functions. In another embodiment of the present disclosure, the modules 308 may be machine-readable instructions (software) which, when executed by the processor 304 / processing unit, perform any of the described functionalities. Further, the data serves, amongst other things, as a repository for storing data processed, received, and generated by one or more of the modules 308.

[0040] The modules 308 may perform different functionalities which may include, but may not be limited to provide the optimized content engagement and media product delivery to the subject. In an embodiment, the modules 308 may include a receiving module 310, a detecting module 312, a processing module 313, a generating module 314, a timestamping module 316, an identifying module 318, a determining module 320, a converting module 322, an analyzing module 324, a predicting module 326, a performing module 328, and a transmitting module 320. Each module 310-320 may be in communication with each other. Each module 310-320 may be adapted to perform operations to analyse the neurophysiological deviations as well as predict the occurrence of the physiological disorder as explained in subsequent paragraphs.

[0041] Further, in an embodiment, as shown at step 402, the electrode 102 may be configured to measure the at least one physiological data signals / parameter (referred to here as the EEG signals / biosignals) from the subject 112, where the subject 112 may be consuming any content along with advertisement through at least one of a display unit and an audio unit of the UE 116. During initialization, the subject 112 may be presented with a predetermined stimuli sequence (including fast-switching stimuli sequence) while the plurality of sensors records the subject’s biosignal data including but not limited to brainwave activity, heart rate, galvanic skin response, eye movements, and motion data to build a comprehensive multi-modal biometric profile. In an embodiment, the plurality of sensors may include an EEG sensor, and other biosensors, without departing from the scope of the present disclosure.

[0042] Further, the electrode 102 may be positioned to record electrical activity from distinct brain regions. These EEG signals may then be integrated in real time with diverse data associated with the subject 112 by using adaptive data blending methods. The data may include, but is not limited to, demographic details, online browsing patterns, social media interactions, and ethnographic insights. This combined approach supports sophisticated emotion tracking and refines the feedback loop for delivering emotionally resonant content, allowingpersonalized adjustments to stimuli based on each individual’s blended digital, behavioral, and biological profile.

[0043] Further, at step 404, the measured EEG signal may be provided to an EEG data stream and further transmitted to the receiving module 310.

[0044] Further, at step 406, the receiving module 310 may be configured to receive the measured EEG signal as an input from the EEG data stream. In an embodiment, the transmitting module 312 may be configured to transmit the EEG signal to the detecting module 312, where the detecting module 312 may operate by using an advanced Machine Learning model. This may include but not be limited to, a Foundational Artificial Intelligence (AI) model (referred to here as at least one AI model) as shown at step 408.

[0045] Particularly, at step 408, the detecting module 312 may be configured to detect response generated in a brain, i.e., the brain, of the subject 112 while consuming the content, based on the EEG signal. The detecting module 312 may be configured to detect the response via the at least one AI model, i.e., the foundational AI model. In such an embodiment, the detecting module 312, using the at least one AI model, also considers one or more inputs from a health unit as shown at step 410 to analyze the EEG signals. The health unit includes a plurality of biosensors, medical metrics of the subject 112, long term brain health monitoring module, physiological disorder trigger identification, etc. Following the analysis of EEG signals, the detecting module 312 may be configured to produce multiple output signals, which are relayed to both the health unit and the controller 104.

[0046] In an embodiment, upon detecting the response, a plurality of operations has been performed as mentioned in the subsequent paragraphs.

[0047] In an embodiment, upon detection of the response, at least one display element present on the display unit of the UE 116 may be adjusted dynamically. Particularly, to adjust the at least one display element, dynamically, the processing module 313 and the generating module 314 may be configured to perform at least one operation which are as follows:

[0048] The processing module 313 may be configured to adjust display elements in the UE 116 in real-time by resizing high-probability predicted options to increase visual salience, and spatially redistributing probable selections to minimize overlapping EEG signal interference via a dynamic interface.

[0049] Particularly, the processing module 313 may be configured to adjust, dynamically, the at least one display element present on the display unit of the UE 116 in the real-time based on the brain activity signals of the subject 112. The processing module 313 may be configured to adjust the at least one display element through altering narrative elements, including story paths, game progression, or scene pacing, using an adaptive narrative system that processes engagement levels derived from the neural activity of the subject. The processing module 313 may be configured to adjust the at least one display element through modifying audiovisual components, themes, or advertisements during displaying of the content to maintain engagement and emotional relevance, thereby creating highly customized, brain-responsive storytelling experiences tailored to the subject 112. The processing module 313 may be configured to adjust the at least one display element by detecting and resolving conflicting content elements, including third-party stimuli embedded within the content, by overwriting or adjusting the conflicting elements to ensure alignment with the preferences of the subject 112 or platform-defined objectives.

[0050] The processing module 313 may be configured to update a spatial layout of selectable display elements based on machine learning based transformer-derived outputs to accelerate a subject interaction via the dynamic interface. Further, the generating module 314 may be configured to generate a trigger to create a persona to deliver faster predictions based on learning a pattern of each subject via the dynamic interface.

[0051] Additionally, upon detecting the response, referring to Figure 4B, at step 409, the timestamping module 316 may be configured to timestamp the detected response based on the EEG signal. Upon timestamping the detected response, the receiving module 310 may be configured to receive the detected response in a stimulus interlacer of the controller 104. The stimulus interlacer receives the detected response, such that the stimulus interlacer performs a real-time adjustment of the audiovisual stimulus of the subject, based on the detected response.

[0052] The stimulus interlacer perform the real-time adjustment of the audiovisual stimulus based on, but is not limited to, at least one of modulating frequency, altering visual grating patterns, adjusting contrast, changing orientation, or introducing flickers to the content displayed on device 100, via neurophysiological markers and event-related potentials to refine analysis granularity.

[0053] In such an embodiment, based on the received detected response, at step 411, the stimulus interlacer may be configured to determine the plurality of adjustment parameters as mentioned above for interlacing. Thereafter, at step 413, the stimulus interlacer may be configured to interlace stimuli to the audio-visual content based on the plurality of adjustment parameters. Further, at step 415, the stimulus interlacer may be configured to deliver interlaced content to the UE 116 by performing the real-time adjustment of the audiovisual stimulus of the subject and subsequently monitor real-time response of the brain while the subject 112 consumes the interlaced content. Thereafter, based on the monitoring of the response, at step 419, the stimulus interlacer may be configured to generate neurofeedback insights / personalized neurocognitive profile for the subject 112.

[0054] The operation of the stimulus interlacer is explained in detail in the subsequent paragraphs.

[0055] Grating and audiovisual frequency modulation from the plurality of adjusting parameters may be defined as embedding imperceptible frequency patterns into auditory or visual stimuli to evoke neural oscillations synchronized with the encoded frequencies. This technique leverages neurophysiological markers such as the Frequency Following Response (FFR), which reflects auditory processing fidelity, and Visually Evoked Potentials (VEPs), which capture rhythmic brain responses to visual stimuli. These markers enable objective quantification of content perception efficacy, cognitive engagement, and emotional resonance, forming the basis for data-driven content optimization.

[0056] Additionally, the Event-Related Potentials (ERPs) to refine analysis granularity may be: for instance, the P300, a positive deflection ~300ms post-stimulus, which identifies attention-driven target selection in brain-computer interfaces (BCIs). Further, Rapid Invisible Frequency Tagging (RIFT) employs subliminal high-frequency flickers to tag on-screen elements, generating distinct neural signatures decoded via EEG. RIFT facilitates non-intrusive tracking of user attention to multimedia content, ensuring seamless integration of neural feedback into an adaptive media delivery model. Together, these methodologies provide a multimodal framework for real-time analysis of subconscious cognitive and affective responses, enhancing precision in content personalization and evaluation.

[0057] The stimulus interlacer transforms passive media into neuroresponsive experiences by seamlessly embedding imperceptible neural stimuli such as high-frequency visual flickers,spatial gratings, or subliminal audio modulations into audiovisual, visual, or auditory content. For visual stimuli, modulation parameters may include, but are not limited to, intensity, brightness, phase, frame rate, and color contrast, which may be adjusted individually or in tandem. For audio stimuli, modulation involves varying amplitude, frequency, or phase. In certain embodiments, synergistic integration of both visual and auditory stimuli is employed to enhance neural synchronization accuracy, leveraging cross-modal reinforcement to optimize engagement and biomarker detection.

[0058] Utilizing advanced techniques, for example, frequency masking and spatial-temporal modulation, the stimulus interlacer encodes stimuli outside human perceptual thresholds (e.g., flickers in peripheral screen regions or phase-shifted audio tones masked within ambient soundscapes). The stimulus interlacer encodes stimuli to evoke measurable neural oscillations (e.g., VEPs, FFR) without disrupting the user’s conscious experience. In context-aware implementations, machine learning algorithms analyze content structure such as scene transitions, visual focal points, or audio intensity to strategically place stimuli in high- engagement segments (e.g., embedding gratings in background textures during dialogue-heavy scenes). This dynamic interlacing may be applied continuously or intermittently, optimizing computational efficiency by targeting key moments (e.g., inserting stimuli during static video frames or low-motion sequences), while maintaining compatibility across video, audio, and image formats. By repurposing inherent content elements (e.g., leveraging ambient light variations as flickers or harmonics in background music for frequency modulation), the stimulus interlacer achieves native integration, ensuring stimuli blend seamlessly with original media to preserve artistic intent while enabling neuroresponsive tracking.

[0059] The adaptive capabilities of the stimulus interlacer extend to real-time content personalization, where stimuli-evoked neurofeedback such as P300 markers for attention peaks or N400 signals for semantic dissonance, is analyzed to dynamically reshape content flow. For instance, EEG signal responses to interlaced stimuli may trigger narrative adjustments, such as extending suspenseful scenes for users exhibiting high emotional arousal or rerouting story paths based on cognitive engagement levels. In streaming platforms, this enables branching narratives where plot trajectories, character interactions, or advertisement placements adapt mid-session to align with the user’s subconscious preferences. The system 114 further incorporates a neutralization submodule to detect and overwrite conflicting third-party stimuli (e.g., competing neuromarketing tags), ensuring a cohesive experience tailored to user-definedpreferences or platform objectives. This closed-loop interaction transforms content into an interactive medium, where neural data directly informs scene transitions, pacing, and thematic emphasis, creating hyper-personalized journeys unique to each user.

[0060] Implementation flexibility allows the stimulus interlacer to function as a software-based encoder integrated into streaming services for real-time processing or as a hardware accelerator (e.g., FPGA / GPU-driven chipsets in AR / VR headsets) for low-latency performance in immersive environments. In therapeutic or educational applications, the controller 104 with the help of stimulus interlacer may adjust content difficulty or emotional tone based on neurophysiological stress markers. Further, in advertising, the stimulus interlacer optimizes ad creatives in real time by testing subliminal stimuli efficacy across demographics. The interlaced stimuli also serve as invisible “tags,” enabling granular attribution of the engagement of the subject to specific content elements, such as quantifying which product placements or musical cues drive neural synchronization, thus providing creators and marketers with actionable insights.

[0061] In an embodiment, assessment of the neural responses evoked by the perception of embedded frequencies in the brain enables quantification of the synchronization between these frequencies and neural oscillations. This neurophysiological assessment may expand into the relationship between sensory perception and neural dynamics, providing valuable insight into the subject neural profiles. Analytical techniques such as cross-correlation analysis may be employed to compare the temporal waveform of the stimulus encoding the frequency components with the recorded neural activity. This comparison allows for the quantification of the degree of phase-locking and synchronization between the external stimuli and the brain's oscillatory patterns. The resulting coupling coefficient metric (CC Metric) facilitates the judicious selection of electrodes that optimally transduce the neural signals while preserving signal fidelity.

[0062] The visual stimuli may be encoded with frequencies spanning a spectrum of intensities, varying from low to high, which are relevant to the induced neurophysiological reactions. Electroencephalography (EEG) measurements may be employed to adjust the intensity of these patterns based on subject engagement and neurofeedback. This process may involve combining multiple frequencies and subsequent analysis to determine the suitable modulation.

[0063] Further, the controller 104 may be configured to calibrate and measure the EEG signal of the subject 112 using a controlled audiovisual stimulus. Initially, an audiovisual stimulus encoded with a predefined control signal frequency is presented to the subject 112 to evoke a targeted brainwave response. This response, encompassing all relevant biomarkers, is recorded and undergoes signal processing and analysis to establish a baseline EEG profile for the subject 112. Subsequently, a standardized unit response stimulus is designed to consistently elicit the same brainwave response, which is then used for ongoing EEG measurement. The controller 104 incorporates an adaptive feedback loop to continuously monitor and adjust the stimulus parameters in real-time, ensuring accurate modulation of the user's brainwave activity. Longitudinal data collection further refines the baseline and unit response measurements, enhancing the system's precision and reliability for personalized neurofeedback applications.

[0064] In an embodiment, the controller 104 presents the subject 112 with a specifically designed audiovisual stimulus to induce a targeted brainwave pattern. The resulting EEG responses may be rapidly recorded and analyzed to assess both the quality and reliability of electrode connections, ensuring optimal signal acquisition and the temporal alignment between stimuli and neural oscillations. This temporal alignment, termed Coupling Latency (CL), quantifies the time required for external stimuli to synchronize with the brain’s oscillatory activity, serving as a metric to gauge the subject’s engagement and attention span. By leveraging latency analysis, the controller 104 enhances electrode validation efficacy while enabling real-time neurofeedback, improving both EEG acquisition accuracy and personalized content adaptation based on attentional states.

[0065] The controller 104 dynamically embeds imperceptible frequencies into audiovisual content through real-time, localized processing of neurofeedback data. By analyzing the subject’s brain activity patterns, the controller 104 identifies critical neural responses and integrates tailored frequencies into the content, aligning with the subject’s neurophysiological profile. This adaptive modulation ensures stimuli remain subliminal while optimizing engagement and resonance based on real-time neural dynamics.

[0066] In an embodiment, upon the real-time adjustment of the audiovisual stimulus of the subject, the detecting module 312 may be configured to detect brainwave signal of the subject 112. The brainwave signal may include, but is not limited to, oscillatory neural responses generated by imperceptible visual stimuli embedded in the content being displayed on the UE 116, and transient neural responses triggered by salient events within the contents.

[0067] The identifying module 318 may be configured to identify the focus of the subject 112 on a selectable interface element based on a correlation of a timing of the brainwave signal with temporal markers in the content. The determining module 320 may be configured to determine, simultaneously, an intended selection of the subject 112 based on a combination of a frequency-based and event-based neural features. The converting module 322 may be configured to convert the intended selection into an interactive command through the dynamic interface.

[0068] Further, the analyzing module 324 may be configured to analyze sequential selection derived from the EEG signal based on a transformer based language model. The predicting module 326 may be configured to predict a probable output including at least one of subsequent words, icons, and actions based on contextual patterns derived from a neural activity of the subject 112, behavioral data of the subject 112, and supplementary sensor inputs of the subject 112 via the transformer based language model. The generating module 314 may be configured to generate a signal to display the probable outputs (as shown in Figure 4D) as prioritised selectable options, enabling progressive construction of inputs through iterative neural-driven selections through the dynamic interface. The generating module 314 may be configured to generate a personalized neurocognitive profile, accelerating prediction accuracy and response times based on learning, by the transformer based language model, longitudinal interaction patterns of the subject 112. In an example, referring to Figure 4C, the subject 112 who has typed “Switch on the” phrase already may be shown the most probable next words on the display device . This is done by the predicting module 326 which is configured to predict the probable output / probable outputs based on the contextual patterns derived from the neural activity of the subject 112, behavioral data of the subject 112, and supplementary sensor inputs of the subject 112 via the transformer based language model. Thereafter, the generating module 314 generates the signal to display the probable outputs (as shown in Figure 4D).

[0069] Alternatively, referring back to Figure 4A, the health unit subsequently evaluates the subject’s brain health status and generates a corresponding signal, directing the signal to the controller’s stimulus interlacer. This integration enables real-time adjustments to stimuli delivery, ensuring alignment with both neurophysiological dynamics and brain health metrics. Subsequently, the stimulus interlacer performs the real-time adjustment of the audiovisual stimulus based on the subject's brain health condition (EEG response).

[0070] In an embodiment, simultaneously, the performing module 328 may be configured to perform filtering of the content and dynamically curate and recommend content based on the detected response. The performing module 328 may be configured to perform the filtering of the content and dynamically curate and recommend content via another Artificial Intelligence model. In an embodiment, the another AI model may be a local AI model, without departing from the scope of the present disclosure. The performing module 328 dynamically shields users from potentially distressing material by preemptively filtering content based on personalized emotional intensity thresholds, ensuring a safe, controlled consumption environment while enhancing well-being. Leveraging multi-dimensional modeling of EEG-derived psychometric attributes, personality traits, and behavioral profiles, the content filtering unit predicts content gratification metrics to tailor delivered material. Subjects may further customize filtering parameters, such as sensitivity to emotional themes (e.g., violence) or cognitive engagement depth, to align with their desired affective experiences. By integrating these explicit user preferences with implicit, EEG-informed insights into inherent dispositions, the system refines content selection through a hybrid of adaptive rules and neurophysiological feedback, balancing user agency with data-driven personalization.

[0071] In such an embodiment, the performing module 328, using the local AI model, processes EEG-derived insights that capture the subject’s emotional and cognitive reactions during content consumption. These insights, conveyed through multiple output signals, enable the content filtering unit and creator insights unit to dynamically curate and recommend content, aligning with the subject’s engagement patterns and preferences derived from their consumption history. This ensures personalized content delivery that resonates with the subject’s neural and behavioral profile.

[0072] Further, the local AI model and the foundational AI model may form an edge computing architecture which may be employed to address the challenges of latency, energy consumption, and privacy in conventional cloud-based systems. This is achieved by enabling local processing (using the local AI model) of large datasets before communicating with a centralized AI model (the foundational AI Model) and securely storing data locally with encryption. In this architecture, bulk of the data processing may be performed locally, reducing the need for extensive data transmission, thereby lowering latency and conserving bandwidth and energy. By transmitting only essential insights to a central system, mainly the relevant training datasetsand the machine learning weights generated, the foundational AI Model may be constantly updated and tuned.

[0073] Additionally, the sensitive biosignal data, along with the local AI model's weights and biases, may be securely stored on the device 100 using advanced encryption techniques. Specifically, an encryption key is employed to encrypt this data, ensuring that the data remains protected from unauthorized access and potential misuse. This process ensures that even if the device 100 is compromised, the encrypted data and model parameters cannot be accessed or tampered with, without the corresponding decryption key, thereby enhancing data security and privacy.

[0074] Concurrently, the transmitting module 320 may be configured to transmit, simultaneously, a signal associated with the detected response to the engagement analysis engine 106 to generate content neurofeedback insights as shown at steps 412 and 414. The transmitting module 320 may be configured to transmit the signal based on an identification of regionally prevalent content consumption patterns across subjects. The content neurofeedback insights may indicate, but is not limited to, geographic and demographic content engagement insights based on neurofeedback patterns across subjects. Particularly, the transmitting module 320 may be configured to transmit, simultaneously, the signal associated with the detected response to the engagement analysis engine 106 to generate the geographic and demographic content engagement insights based on neurofeedback pattern across subjects

[0075] The content neurofeedback insights may be relayed to content providers as shown at step 416. These content providers utilize the content neurofeedback insights to refine content recommendations, which are then delivered to the recommendation engine 108 as shown at step 418. The recommendation engine 108 dynamically optimizes content engagement and media delivery strategies via refining content recommendations, based on the content neurofeedback insights. Particularly, the recommendation engine 108 dynamically optimizes content engagement and media delivery strategies by aligning outputs with the subject’s brainwave-derived preferences, ensuring tailored user experiences. Detailed operational mechanics of these processes are elaborated in subsequent sections.

[0076] The system 114 may be configured to enable subjects to voluntarily opt-in to contribute their EEG data, enriching the system’s 114 machine learning training datasets. In exchange, contributors gain exclusive access to premium content experiences unavailable to non-participants. The received EEG signals may be anonymized and aggregated into private data lakes, capturing a comprehensive spectrum of neurological responses across diverse cognitive states, emotional conditions, personality traits, and demographic cohorts during content interaction. This aggregated dataset enhances the scale and diversity of the training corpus, empowering robust model refinement and personalized content delivery aligned with nuanced neurobehavioral patterns.

[0077] Further, referring to steps 402 to 408, the system 114 may use machine learning (ML) and deep learning techniques to build highly personalized content consumption models for each subject. These personalized models correlate data from the EEG signals, which measure brain wave activity, with traditional metrics used for evaluating content consumption such as view- through rates, dwell times, explicit ratings, and feedback.

[0078] Further, by timestamping and correlating the EEG signals / brain wave patterns with the specific content being consumed, the system 114 may precisely map how different segments, scenes, characters, or creative elements within the content evoke changes in subject’s attention, memory encoding, motivation, and affective states.

[0079] Advanced visualization dashboards map these EEG response metrics onto specific scenes, characters, narrative arcs, and creative elements within the content. Creators may intuitively deconstruct the factors that drive peak immersion versus lulls in engagement. The creator may identify the pivotal creative choices and storytelling techniques that elicit target affective states, for example, suspense, awe, or sentimentality in viewers.

[0080] With this level of psychometric feedback derived from EEG biosignals, creators may make informed decisions to refine their creative process, leading to content that fosters stronger emotional connections with audiences. This empowers an iterative workflow where new creative directions may be rapidly validated through EEG prototypes before investing in full production cycles.

[0081] Further, in an embodiment, the system 114 leverages granular multimodal fusion of biosensing data including the EEG signal with content metadata to deconstruct the subconscious factors driving subject resonance. This enables optimizing content pacing, narratives, and delivery modes to sustain high engagement and align emotional responses toward the desired metrics across different subject segments.

[0082] Further, for new subjects with limited data, intelligent baseline recommendations leverage matching to the closest similar subject cluster neighborhoods exhibiting aligned neural signatures and content preferences.

[0083] Moreover, the availability of large datasets correlating EEG responses with creative content features enables training powerful machine learning models that can accurately predict and forecast EEG biomarker signatures and Quality of Experience (QoE) metrics for new content. This virtually eliminates the inconvenience, costs, and biases associated with provisioning extensive human test groups for evaluating new ad campaigns before launch.

[0084] For subject segments targeted for emotional regulation, EEG affective computing may be utilised to detect shifts in emotional states, for example, positive or negative emotional states. Based on these detections, content may be served that aligns with the subject's current emotional state, aiming to maintain emotional equilibrium and enhance the overall subject experience. This approach ensures that content delivery is dynamically adjusted to meet the diverse emotional needs of the subjects, fostering a more personalized and engaging viewing experience.

[0085] Further, the processes as explained above between the subject and the content provider may be performed by a decentralized blockchain-based database to reduce the centralisation of sensitive personal data in the hands of a certain entity - and their misuse without the approval of the user. The decentralized blockchain based database, in general, enables a secure and transparent exchange of anonymized electroencephalography (EEG) data between contributors and consumers. The system 114 utilizes a private permissioned blockchain network to maintain an immutable and auditable ledger of EEG data access logs. This provides complete transparency into which of the user's data was accessed at what duration by the various applications the user has given access to. Contributors may upload and tokenize their EEG datasets, which are encrypted and stored off-chain / locally in the device for privacy. Smart contracts approved by the users govern the terms, duration, and access control over these tokenized sensitive EEG data assets. Researchers, healthcare entities, content providers, and organizations can browse the dataset pool, review metadata about available datasets, and access the data using the tokens approved by the user.

[0086] Additionally, the system 114 may be used to establish neurofeedback biometric authentication. The system 114, by using signal processing and machine learning, extractsrobust neurometric and biological markers from EEG data. The EEG data may represent the subject's distinct multi-dimensional response pattern or "brainprint" to the stimuli sequence. This "brainprint" may be securely encoded and stored as the subject's biometric template. For subsequent authentication, the system 114 initiates the stimuli sequence and monitors the subject's real-time multi-modal biometric response via the plurality of sensors. Thus, by extracting features and comparing them against the enrolled biometric template using pattern matching algorithms.

[0087] Further, the system 114 may provide a platform access program that extends data- driven personalization capabilities through an optional premium subscription tier. Subscribers may gain exclusive access to advanced API endpoints that leverage the platform's state-of-the- art neural networks fine-tuned on the aggregated EEG datasets. These premium APIs may enable developers and enterprises to build highly contextualized and emotionally resonant applications tailored to their subjects' neurological profiles or according to the business strategy of the enterprise.

[0088] Further, the system 114 may be used in identifying seizure or epilepsy triggers by a Seizure or Epilepsy Trigger Identification Algorithm / Model. A machine learning algorithm for identifying potential seizure or epilepsy triggers in the content may be based on EEG data analysis. The algorithm / model is trained on a dataset comprising EEG recordings, seizure event logs, and contextual information such as environmental factors, activities, or stimuli present before or during seizure events. The algorithm employs advanced signal processing techniques and pattern recognition models to detect correlations between specific EEG features and seizure occurrences. By analyzing the subject's real-time EEG data, the algorithm may identify potential triggers or factors that may increase the risk of a seizure event, enabling timely intervention or avoidance of such triggers. The system 114 carefully regulates visual parameters such as flickering rates, brightness variations, contrast, geometric patterns, and colors present in the content, ensuring that the visual stimuli do not induce or exacerbate seizure episodes.

[0089] Additionally, the system 114 harnesses the behavioral data collected through gamified interactions to gain valuable insights into subject preferences and cognitive responses. By embedding imperceptible frequency modulations into the audiovisual content, the system 114 objectively assesses the effectiveness of content perception and cognition by analyzing the neural oscillations evoked by these modulations. This gamified approach not only cultivates asense of enjoyment and accomplishment for subjects but also promotes prolonged subject retention on the platform.

[0090] Further, the system 114 and a method performed by the system 114 may be configured for optimizing content recommendation by integrating various metrics of social media usage with EEG neurofeedback. This system 114 collects and analyzes extensive data on user interactions, engagement levels, and preferences across social media platforms, utilizing metrics such as time spent, likes, shares, comments, and click-through rates. Concurrently, users participate in EEG neurofeedback sessions where their brainwave responses to different types of content are recorded and analyzed. By correlating the EEG data with social media usage metrics within specific user cohorts, the system 114 identifies patterns and preferences that inform personalized content recommendations. Advanced machine learning algorithms process this combined data to dynamically adjust and optimize content delivery, ensuring that recommendations align with the user's cognitive and engagement profiles, thereby enhancing user satisfaction and engagement across digital platforms.

[0091] Furthermore, the system 114 functions as a neurofeedback-enabled platform specifically catering to meditation, stress regulation, and personalized music delivery aligned with the user's mood. The system 114 generates personalized instructions tailored to each individual which may manifest as prompts, songs, or other formats that are dynamically crafted based on the individual's real-time responses. Real-time monitoring of neurophysiological indicators, such as alpha, beta, and theta brainwave frequencies, enables precise delivery of prompts in accordance with the user's current state of calmness and attention. This empowers users to potentially optimize cognitive functions, refine concentration levels, and strengthen problem-solving capabilities. Additionally, the system's technical architecture facilitates seamless integration of advanced algorithms for adaptive learning and continual improvement of user experience, fostering long-term engagement and efficacy in neurofeedback-enhanced practices.

[0092] Further, the system 114 may continuously monitor brain waves and measure neural responses to specific frequency patterns embedded in devices or displays using highly switching stimuli, for example, Rapid Invisible Frequency Tagging (RIFT). By analyzing and correlating these brain-wave responses along with time stamps to the embedded frequencies, the system 114 may interpret the subject’s intended actions or commands based solely on brainwave activity. This method as performed by the system 114 reduces the necessity forphysical interaction with devices, significantly enhancing user independence and quality of life. This approach is particularly beneficial for subjects with disabilities that affect mobility or movement.

[0093] This architecture also enables hands-free, brain-driven input without reliance on physical movement or speech, offering a fundamentally new human-computer interaction paradigm, particularly benefiting individuals with mobility impairments.

[0094] Additionally, the system 114 may include an EEG sensor array, placed in device 100 that unobtrusively captures brain signals related to visual attention. A configurable screen displays a grid of selectable options, such as letters, words, or semantic icons. Each grid cell is associated with unique high-frequency RIFT flickers and occasional P300-inducing flashes. When a user fixates his focus on a cell, the EEG array detects both visually evoked potentials (from RIFT) and time-locked components such as P300.

[0095] These multimodal signals are transmitted to a local processing device (e.g., smartphone, tablet, or wearable computer) which may be equipped with GPU or neural processing accelerators. A real-time signal-processing pipeline extracts features, for example, frequency- domain and time-domain insights from the EEG data. A machine learning model, optionally a convolutional neural network, determines the most probable attended cell. Subsequently, a transformer-based language model predicts the next probable words or phrases, enabling progressive construction of sentences through iterative selections.

[0096] The system 114 employs a hybrid EEG decoding approach by simultaneously leveraging P300 and RIFT modalities. P300 potentials provide reliable event-based markers, while RIFT introduces frequency-specific steady-state signals corresponding to the user’s gaze focus. A fusion classifier integrates both time-locked and frequency-domain features to produce a unified probability distribution over selectable cells. This multimodal decoding enhances accuracy, reduces detection latency, and maintains robustness even when one of the neural signatures is weak. The approach effectively doubles the sampling speed compared to unimodal systems, ensuring practical real-time usability.

[0097] Further, the system 114 may also leverage other event-related potentials (ERPs) such as N400, P600, and N170. These additional neural markers enhance the precision and contextual understanding of user intent. For instance, the N400 component, a negative waveform peaking ~400 milliseconds post-stimulus, which reflects deflections associated withsemantic incongruities, may be used to detect errors in the generated sentences, enabling the system 114 to automatically flag or correct illogical word sequences in real-time. This drastically improves communication speed by reducing the cognitive effort and interaction steps required for error correction. Similarly, the P600, a late positive component (~600 ms+) is associated with syntactic reanalysis and can aid in grammar-aware sentence construction, while the N170, a negative event-related potential (ERP) at ~170 milliseconds may be used to reinforce recognition of alphanumeric characters and facial icons, further accelerating accurate selection.

[0098] To optimize user interaction, the grid interface is dynamically adaptive. Grid density, that is, the number of displayed cells, may be customized according to user preferences or system-determined strategies balancing cognitive load and vocabulary richness. Dynamic cell sizing is employed: cells corresponding to higher-probability predictions are rendered larger and more salient, while lower-probability options are minimized. Additionally, to reduce signal leakage and overlapping EEG responses, high-probability words or choices are spatially distributed farther apart across the grid. This spatial separation, combined with probabilistic resizing based on transformer-derived likelihoods, allows for clearer differentiation of attention signals and reduces decoding ambiguity.

[0099] This concept can be further developed by dividing the available display into multiple grids or regions with necessary buffer zones to mitigate signal interference between adjacent grids or tiles (signal leaching). For instance, a display system (comprising one or more screens) can be partitioned into 'n' distinct segments, each representing different actions, along with 'm' buffer tiles to function as control guides for recalibration and resetting the detection sensitivity. This advanced user input methodology enhances input capabilities in various applications such as spatial computing, augmented reality (AR), virtual reality (VR), gaming, advanced navigation controls, and industrial automation systems.

[0100] The system 114 also supports intelligent contrast-enhancing features such as color- based flickering mechanisms. By subtly modulating the flicker frequency and color contrast of grid cells, the visual salience of selections can be optimized, enhancing readability and distinguishability even for users with visual impairments or under varying ambient light conditions.

[0101] The system 114 also incorporates predictive correction algorithms that operate on EEG signal approximations rather than raw selections. This system 114 infers user intent based on choice selection patterns and contextual proximity by applying similar approximation models to EEG focus data factoring in confidence, trajectory, and timing, the system 114 can infer and auto-correct intended selections even in the presence of weak or ambiguous signals.

[0102] In one embodiment, all EEG decoding and language modeling occur locally on the user's device, utilizing edge AI techniques to minimize latency and ensure data privacy. The system 114 uses GPU acceleration or dedicated neural processing hardware to achieve real- time signal processing and transformer-based inference. This architecture supports instantaneous feedback upon user focus shifts, enabling communication speeds of multiple selections per minute. By operating fully offline, the system 114 preserves user autonomy and prevents reliance on network connectivity, making it suitable for both clinical and consumer environments.

[0103] Beyond sequential text input, the system 114 offers a non-linear, icon-based communication mode designed for users with disabilities or for enhanced efficiency. In this mode, grid cells display semantic icons representing entire concepts or common phrases. The selection of an icon triggers predictive sentence generation using the language model, substantially reducing the number of interactions needed to convey complex ideas. This feature parallels augmentative and alternative communication systems, but is controlled directly via EEG signals, enabling users to "think" commands or messages rapidly. The same adaptive grid mechanisms apply to icon mode, maintaining intuitive usability regardless of content type.

[0104] Key performance enhancements include the integration of autocomplete algorithms to minimize interaction steps, GPU-accelerated real-time EEG processing, combined P300 and RIFT stimulation for superior signal detection, reduced sampling times for faster interactions, and an optional auto-selection mode that triggers when the system’s confidence crosses a threshold, minimizing user effort. Dynamic spatial rearrangement of grid elements, where highly probable words are rendered larger and spatially separated from one another, further reduces selection errors and increases communication speed.

[0105] As the system 114 is used over time, it learns the unique EEG signatures, gaze patterns, and language preferences of each user. This longitudinal personalization allows the system 114 to make faster and more accurate predictions, reducing cognitive effort. At thepopulation level, aggregated usage data helps the model learn common language structures, visual attention behaviors, and selection trends, further accelerating the interface for all users. To maintain privacy while enhancing collective intelligence, the system 114 may be deployed using a federated learning model, where local devices train models individually and share only anonymized weight updates with a central system. This preserves user data integrity while continuously improving global performance.

[0106] This technology is particularly valuable for augmented and virtual reality (AR / VR) environments, where traditional input devices, for example, keyboards or touchscreens, are impractical or unavailable. The system 114 may seamlessly function as a cognitive input mechanism in AR / VR headsets by interpreting the user's EEG-based attention signals to select virtual buttons, trigger interface actions, or navigate menus including immersive palettes. Moreover, the system 114 may even emulate a full virtual keyboard, enabling thought-driven text input within extended reality applications. This brain-based interface eliminates the need for handheld controllers or gesture-based typing, significantly enhancing usability, immersion, and accessibility for AR / VR users across gaming, productivity, and assistive domains.

[0107] Particularly, the system 114 leverages EEG data and analysis to enhance content curation, prioritization, and delivery strategies across various media platforms. The system 114 employs advanced affective computing techniques to quantify subjects' emotional resonance with content stimuli by extracting robust neurological biomarkers of emotional valence, arousal, and engagement from the EEG signals. Content pieces that elicit strong positive emotional responses, immersive attention and desired affective states are consequently prioritized and promoted within subjects' personalized content feeds and recommendation engines. Furthermore, the long-term longitudinal analysis of subjects' EEG data by the system 114 enables accurate determination of their unique circadian rhythm patterns and fluctuations in alertness levels throughout the day. By modeling each subject's biological clock and periods of optimal cognitive performance versus relaxation phases, a personalized content delivery system dynamically curates and sequences content to align with the subject's current neurological state and innate chronobiological cycles.

[0108] Additionally, the system 114 incorporates advanced sleep sensing and sleep stage detection capabilities derived from EEG and other physiological data streams. For subjects experiencing insomnia, fragmented sleep, or general sleep cycle disruptions, the system 114 provides personalized recommendations for sleep-inducing audio-visual content, andmindfulness practices empirically validated to facilitate rapid sleep onset and high-quality restorative sleep episodes. These automated content curation engines, driven by EEG-powered affective profiling, chronobiology modeling, and sleep optimization, enable a highly engaging and customized content experience meticulously tailored to each subject's neurophysiological rhythms.

[0109] The method 500 includes a series of operations shown at step 502 through step 508 of Figure 5. The method 500 may be performed by the system 114 in conjunction with modules 308, the details of which are explained in conjunction with Figure 4, and the same are not repeated here for the sake of brevity in the present disclosure. The method 500 begins at step 502.

[0110] At step 502, the method 500 includes detecting response generated in the brain of the subject 112, while consuming content, via the at least one Artificial Intelligence Model, based on the EEG signal.

[0111] The method 500 includes adjusting, dynamically, at least one display element present on the display unit of UE 116 in the real-time based on the brain activity signals of the subject 112 through at least one of altering narrative elements, including story paths, game progression, or scene pacing, using an adaptive narrative system that processes engagement levels derived from the neural activity of the subject, modifying audiovisual components, themes, or advertisements during displaying of the content to maintain engagement and emotional relevance, thereby creating highly customized, brain-responsive storytelling experiences tailored to the subject 112 and detecting and resolving conflicting content elements, including third-party stimuli embedded within the content, by overwriting or adjusting the conflicting elements to ensure alignment with the preferences of the subject (112) or platform-defined objectives.

[0112] At step 504, the method 500 includes performing filtering of the content and dynamically curate and recommend content based on the detected response via the at least another Artificial Intelligence Model.

[0113] At step 506, the method 500 includes transmitting, simultaneously, the signal associated with the detected response to the engagement analysis engine 106 to generate content neurofeedback insights.

[0114] At step 508, the method 500 includes optimizing, dynamically, the content engagement and media delivery strategies via refining content recommendations, based on the content neurofeedback insights.

[0115] As would be gathered, the system 114 and the method 500 as disclosed, ensure satisfactory content engagement by the subject 112. Particularly, the system 114 and the method 500 ensure that the subject 112 stays longer, interacts more, and returns more often, resulting in higher retention and lower churn. The system 114 and the method 500 ensure better conversion rates by providing relevant content to the subject 112, which leads to higher chances of purchases, sign-ups, or desired actions, thus increasing the revenue of a content provider. The system 114 and the method 500 as disclosed, ensure smarter analytics and feedback, that is, the interaction of the subject 112 with the optimized content provides clearer signals for further optimization, resulting in continuous improvement through the machine learning.

[0116] While specific language has been used to describe the present disclosure, any limitations arising on account thereto, are not intended. As would be apparent to a person in the art, various working modifications may be made to the methods mentioned above in order to implement the inventive concept as taught herein. The drawings and the foregoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment.

Claims

We Claim:

1. A system (114) for dynamically optimizing content engagement for a subject (112), comprising: a plurality of biosensor electrodes (102) in contact with at least one of a scalp and an ear canal of the subject consuming content from a user equipment (UE) (116) and configured to measure at least one physiological parameter of the subject, wherein the at least one physiological parameter is Electroencephalogram (EEG) signal; a controller (104) in communication with the plurality of biosensor electrodes (102), the controller (104) is configured to: detect response generated in a the brain of the subject (112), while consuming the content, via at least one Artificial Intelligence model, based on the EEG signal; perform filtering of the content and dynamically curate and recommend content based on the detected response via another Artificial Intelligence model; and transmit, simultaneously, a signal associated with the detected response to an engagement analysis engine (106) to generate content neurofeedback insights; and a recommendation engine (108) in communication with the controller (104) and the engagement analysis engine (106), the recommendation engine (108) is configured to: optimize, dynamically, the content engagement and media delivery strategies via refining content recommendations, based on the content neurofeedback insights.

2. The system (114) as claimed in claim 1, wherein the EEG signal is integrated with data associated with the subject (112), wherein the data includes demographic details, online browsing patterns, social media interactions, and ethnographic insights.

3. The system (114) as claimed in claim 1, wherein upon the detecting the response, the controller (104) is configured to: adjust, dynamically, at least one display element present on a display unit of the user equipment.

4. The system (114) as claimed in claim 3, wherein to adjust, dynamically, the at least one display element, the controller (104) is configured to at least one of: adjusts display elements in the UE (116) in real-time by resizing high-probability predicted options to increase visual salience, and spatially redistributing probable selections to minimize overlapping EEG signal interference via a dynamic interface; update a spatial layout of selectable display elements based on machine learning based transformer-derived outputs to accelerate a subject interaction via the dynamic interface; and generate a trigger to create a persona to deliver faster predictions based on learning a pattern of each subject via the dynamic interface.

5. The system (114) as claimed in claim 1, wherein upon detecting the response, the controller (104) is configured to: timestamp the detected response based on the EEG signal.

6. The system (114) as claimed in claim 4, wherein upon timestamping the detected response, the controller (104) is configured to: receive, in a stimulus interlacer of the controller (104), the detected response such that the stimulus interlacer perform a real-time adjustment of the audiovisual stimulus of the subject (112), based on the detected response.

7. The system (114) as claimed in claim 5, wherein the stimulus interlacer perform the real- time adjustment of the audiovisual stimulus of the subject (112) based on at least one of modulating frequency, altering visual grating patterns, adjusting contrast, changing orientation, and introducing flickers to the content displayed on the UE (116), via neurophysiological markers, and event-related potentials to refine analysis granularity.

8. The system (114) as claimed in claim 5, wherein upon real-time adjustment of the audiovisual stimulus of the subject (112), the controller (104) is configured to: detect brainwave signal of the subject (112), wherein the brainwave signal comprises oscillatory neural responses generated by imperceptible visual stimuli embedded in the content being displayed on the UE (116), and transient neural responses triggered by salient events within the contents;identify focus of the subject (112) on a selectable interface element based on a correlation of a timing of the brainwave signal with temporal markers in the content; determine, simultaneously, an intended selection of the subject (112) based on a combination of a frequency-based and event-based neural features; and convert the intended selection into an interactive command through a dynamic interface.

9. The system (114) as claimed in claim 8, wherein the controller (104) is further configured to: analyze sequential selection derived from the EEG signal based on a transformer based language model; predict a probable output including at least one of subsequent words, icons, and actions based on contextual patterns derived from a neural activity of the subject (112), behavioral data of the subject (112), and supplementary sensor inputs of the subject (112) via the transformer based language model; generate a signal to display the probable outputs as prioritised selectable options, enabling progressive construction of inputs through iterative neural-driven selections through the dynamic interface; and generate a personalized neurocognitive profile, accelerating prediction accuracy and response times based on learning, by the transformer based language model, longitudinal interaction patterns of the subject (112).

10. The system (114) as claimed in claim 1, wherein to transmit, simultaneously, the signal to the engagement analysis engine (106), the controller (104) is configured to: transmit, simultaneously, the signal to the engagement analysis engine (106) to generate geographic and demographic content engagement insights based on neurofeedback pattern across subjects.

11. A method (500) for dynamically optimizing content engagement for a subject (112), comprising: detecting (502) response generated in a brain of the subject (112), while consuming content, via at least one Artificial Intelligence Model, based on EEG signal;performing (504) filtering of the content and dynamically curate and recommend content based on the detected response via at least another Artificial Intelligence Model; transmitting (506), simultaneously, a signal associated with the detected response to an engagement analysis engine (106) to generate content neurofeedback insights; and optimizing (508), dynamically, the content engagement and media delivery strategies via refining content recommendations, based on the content neurofeedback insights.

12. The method (500) as claimed in claim 11, wherein upon detecting the response, the method (500) comprises: adjusting, dynamically, at least one display element present on a display unit of a user equipment in a real-time based on brain activity signals of the subject (112) through at least one of: altering narrative elements, including story paths, game progression, or scene pacing, using an adaptive narrative system that processes engagement levels derived from a neural activity of the subject (112); modifying audiovisual components, themes, or advertisements during displaying of the content to maintain engagement and emotional relevance, thereby creating highly customized, brain-responsive storytelling experiences tailored to the subject (112); and detecting and resolving conflicting content elements, including third-party stimuli embedded within the content, by overwriting or adjusting the conflicting elements to ensure alignment with the preferences of the subject (112) or platform- defined objectives.

Images