A dynamic cognitive regulation system

Abstract

The application relates to the technical field of neuromodulation, in particular to a dynamic cognitive regulation system, which is suitable for dynamic cognitive regulation of different types of task paradigms. For dynamic cognitive regulation of each type of task paradigm, the system comprises the following modules: a cognitive function task module, which is used for establishing a mapping relationship between a task paradigm and a cognitive function and a mapping relationship between the cognitive function and a brain function area; a data analysis module, which analyzes cognitive function behavior data and cognitive function brain imaging data to obtain behavior indexes and brain imaging features; a regulation module, which performs cognitive regulation on a user according to regulation parameters set according to a cognitive aging risk probability judgment result of the user; and an evaluation module, which compares a current training result of the user with a historical training result to obtain an evaluation result, dynamically adjusts regulation parameters of a next round of cognitive regulation according to the evaluation result, and realizes dynamic monitoring and regulation of cognition.

Description

Technical Field

[0001] This application relates to the field of neuromodulation technology, and in particular to a dynamic cognitive modulation system. Background Technology

[0002] Cognition refers to a series of psychological and neural processes by which an individual acquires, processes, stores, and utilizes information; it is the process by which humans process information. Cognitive ability determines the speed and quality of an individual's information acquisition and processing, and is a prerequisite for the realization of higher functions such as learning, decision-making, emotion regulation, and social interaction. It not only supports basic activities in daily life but also directly affects an individual's adaptability and problem-solving abilities in complex environments. From the perspective of cognitive neuroscience, the series of cognitive processes are not the functional products of a single brain region, but rather a complex process achieved through the dynamic interaction of multiple functional systems distributed throughout the brain.

[0003] In recent years, non-invasive brain-computer interface (BCI) technology has shown broad application prospects in the field of cognitive function assessment and regulation. This technology, through electroencephalography (EEG) and near-infrared brain imaging (NIBI), enables real-time acquisition and analysis of brain neural activity without implantation, providing important tools for revealing the neural mechanisms of cognitive processes and their dynamic characteristics as they change with age. NIBI, in particular, utilizes the scattering and absorption characteristics of near-infrared light in biological tissues to detect changes in blood oxygen dynamics in the cerebral cortex, thereby indirectly reflecting the state of neural activity. Its devices are small, wearable, and have low requirements for movement, making them suitable for task-based measurements; they are also more suitable for long-term, repeated, and natural cognitive testing. However, existing NIBI-based solutions are mainly used for the detection or assessment of cognitive states. Their core function is to acquire neural activity information of users during cognitive tasks. However, these solutions typically separate cognitive state detection from subsequent training processes, and the detection results are mostly used for offline analysis or static evaluation. Summary of the Invention

[0004] The purpose of this application is to provide a dynamic cognitive regulation system. This system takes cognitive task induction as its core, is based on the joint analysis of functional near-infrared brain imaging data and behavioral data, and combines longitudinal individual modeling and group comparative analysis to achieve cognitive state assessment, risk warning and regulation effect feedback.

[0005] In some embodiments, this application provides a dynamic cognitive modulation system applicable to dynamic cognitive modulation of different task paradigms. For each type of task paradigm, the system includes the following modules: a cognitive function task module, used to set task parameters for the task paradigm, establish a mapping relationship between the task paradigm and cognitive function, and a mapping relationship between the cognitive function and brain functional areas, so as to map the cognitive function to brain functional areas; a cognitive function data acquisition module, used to collect cognitive function behavioral data and cognitive function brain imaging data of the user when completing the task paradigm in each round of cognitive modulation; and a data analysis module. The system comprises three modules: a module for analyzing cognitive function behavioral data to obtain behavioral indicators representing different cognitive function states and analyzing cognitive function brain imaging data to obtain brain imaging features of brain activation patterns related to cognitive function in each round of cognitive modulation within the task paradigm; a modulation module for executing cognitive modulation on the user based on modulation parameters set according to the user's cognitive aging risk probability judgment results in each round of cognitive modulation within the task paradigm; and an evaluation module for comparing the user's current training results with historical training results in each round of cognitive modulation within the task paradigm to obtain an evaluation result and dynamically adjusting the modulation parameters for the next round of cognitive modulation based on the evaluation result.

[0006] In some embodiments, the cognitive function task module further includes a function mapping unit, which is used to map the task paradigm to one or more cognitive functions. The function mapping unit includes a first mapping subunit, a second mapping subunit, and a fusion subunit. The first mapping subunit is used to evaluate the satisfaction of the task paradigm on each cognitive function to obtain a first mapping relationship. The second mapping subunit is used to obtain text information corresponding to the task paradigm and determine the frequency of occurrence of each cognitive function in the text information to obtain a second mapping relationship. The fusion subunit is used to fuse the first mapping relationship and the second mapping relationship to realize the mapping between the task paradigm and one or more cognitive functions.

[0007] In some embodiments, the cognitive function task module further includes a brain region mapping unit, which maps each cognitive function to one or more brain functional regions. The brain region mapping unit includes a brain activation map processing subunit and a brain region mapping subunit. The brain activation map processing subunit is used to acquire a brain activation map related to the cognitive function and process the brain activation map according to a preset activation threshold to obtain an activation status map. The brain region mapping subunit uses a brain region segmentation map to divide a standard space into several brain functional regions and registers the activation status map to the standard space to obtain the number of times the cognitive function is identified as activated in different brain functional regions. Based on the number, the mapping relationship between each cognitive function and one or more brain functional regions is obtained.

[0008] In some embodiments, the system further includes a data recording module, which includes an individual baseline unit, an individual development unit, a group baseline unit, and a group development unit. The individual baseline unit is used to collect and store the user's cognitive function behavioral data and cognitive function brain imaging data during the first cognitive modulation session, and to establish an individual-level initial cognitive function baseline model for the user. The individual development unit is used to continuously collect and store the user's cognitive function behavioral data and cognitive function brain imaging data during each subsequent modulation session, and to establish an individual-level individual development model of the trajectory of cognitive function changes over time for the user. The group baseline unit is used to construct a group-level initial cognitive function baseline model based on the individual baseline units of each user. The group development unit is used to construct a group-level group development model of the trajectory of cognitive function changes over time based on the group development units of each user.

[0009] In some embodiments, the system further includes an early warning module, which includes an individual longitudinal comparison unit, a longitudinal early warning unit, a group horizontal comparison unit, and a horizontal early warning unit. The individual longitudinal comparison unit compares the user's behavioral indicators and brain imaging features in the current round of cognitive regulation with the behavioral indicators and brain imaging features in the user's individual baseline unit to obtain the user's cognitive function change trend and the probability of cognitive aging risk. The longitudinal early warning unit determines that the user has a risk of cognitive aging and issues an early warning when the user's cognitive changes meet the risk conditions based on the change trend and the probability of cognitive aging risk. The group horizontal comparison unit compares the user's behavioral indicators and brain imaging features in the current round of cognitive regulation with the behavioral indicators and brain imaging features in the user group baseline unit to determine the individual's deviation from the group and determines the probability of cognitive aging risk based on the deviation. The horizontal early warning unit determines that the user has a risk of cognitive aging and issues an early warning when the user's cognitive changes meet the risk conditions based on the probability of cognitive aging risk.

[0010] In some embodiments, the control module further includes a control parameter setting unit and a cognitive control execution unit. The control parameter setting unit initializes and adjusts the control parameters, and the cognitive control execution unit performs cognitive control according to the determined control parameters. The control parameter setting unit is used to determine the stimulation location for cognitive control based on the user's current cognitive aging risk index and the mapping relationship between cognitive function and brain functional areas, and to adjust the stimulation intensity and duration within a preset safety range. The stimulation location is the brain functional area corresponding to high-risk cognitive function, and the cognitive control intensity and control time dynamically increase with the increase of the probability of cognitive aging risk.

[0011] In some embodiments, the system further includes a neurofeedback module, wherein the neurofeedback is used to reflect the immediate regulatory results of the modulation on the user's neural activity; the neurofeedback module is used to calculate the changes in neural indicators of the user before and after cognitive modulation training, and to map the changes in neural indicators to neurofeedback parameters; the neurofeedback parameters include the intensity of the neurofeedback signal, the duration of the neurofeedback, and the presentation mode of the neurofeedback, and to present the corresponding feedback information to the user.

[0012] In some embodiments, the intensity of the neural feedback signal is the difference in neural indicators of brain functional areas related to cognitive function before and after cognitive modulation; the duration of the neural feedback is dynamically adjusted by the intensity of the neural feedback signal within a safe range; the neural feedback is presented in a unimodal and multimodal manner, wherein the visual mode presents the activation status of the brain functional area represented by the visual neural feedback signal, the auditory mode presents the volume and frequency regulated by the auditory neural feedback signal, and the tactile mode presents the vibration intensity and frequency of the wristband regulated by the tactile neural feedback signal.

[0013] In some embodiments, the evaluation module further includes an adjustment unit; the adjustment unit is used to evaluate the regulation results based on changes in the user's cognitive aging risk and task performance after cognitive regulation and neurofeedback, and to adjust the regulation parameters of subsequent rounds of cognitive regulation tasks based on the evaluation results.

[0014] In some embodiments, the adjustment unit is further configured to increase the difficulty or training intensity of the cognitive regulation task when the regulation result meets the preset requirements and the risk of cognitive aging shows a downward trend, and to reduce the task difficulty, extend the task interval or reduce the training volume when the regulation result does not meet the preset requirements or fatigue signs appear.

[0015] In the above embodiments, the dynamic cognitive modulation system takes cognitive task induction as its core, relies on the joint analysis of functional near-infrared brain imaging data and behavioral data, and combines longitudinal individual modeling and group comparative analysis to achieve cognitive state assessment, risk warning, and feedback on modulation effects. Furthermore, by continuously assessing the user's cognitive aging risk and changes in neural state, it dynamically adjusts parameters such as neural stimulation intensity and duration within a preset safety range. This allows neural stimulation modulation to adaptively change according to the user's current cognitive state and modulation effect, thereby improving the targeting and effectiveness of modulation while ensuring safety. Attached Figure Description

[0016] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, wherein:

[0017] Figure 1 This is a schematic diagram of a dynamic cognitive regulation system provided in one embodiment of this application;

[0018] Figure 2 This is a schematic diagram of a cognitive function task library provided in one embodiment of this application;

[0019] Figure 3 This is a schematic diagram of a brain region segmentation atlas provided in one embodiment of this application;

[0020] Figure 4 This is a schematic diagram of the type of light stimulation provided in one embodiment of this application;

[0021] Figure 5 This is a detailed schematic diagram of a dynamic cognitive regulation system module provided in one embodiment of this application;

[0022] Figure 6 This is a schematic diagram of the structure of a computer device provided in one embodiment of this application. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0024] The technical solutions of the various embodiments of this application can be combined with each other, but only if they are based on the ability of a person skilled in the art to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such combination of technical solutions does not exist and is not within the scope of protection claimed by this application.

[0025] This solution does not aim to obtain disease diagnosis results or health status, but is a method for processing users' cognitive function data and thereby achieving dynamic cognitive regulation. All steps are performed by information processing methods such as computers.

[0026] It should be fully understood that the cognitive function data of users involved in this application (including but not limited to user cognitive function behavioral data and cognitive function brain imaging data, etc.) are all information and data authorized by the user or fully authorized by all parties. The use of user information should comply with the privacy policies and practices of the industry that are generally considered to meet or exceed the requirements for maintaining user privacy. The collection, use and processing of related data should comply with relevant laws, regulations and standards, and provide corresponding operation access points for users to choose to authorize or refuse.

[0027] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, specific embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0028] It should be noted that the neural modulation method provided in this application can specifically be light stimulation modulation, and other types of neural modulation methods can also be used in other embodiments, not limited to light stimulation. In the following embodiments, light stimulation is mainly used as an example of neural modulation.

[0029] In some embodiments, see Figure 1This application provides a dynamic cognitive regulation system 100, which is applicable to dynamic cognitive regulation of different types of task paradigms. For dynamic cognitive regulation of each type of task paradigm, the system includes the following modules.

[0030] The cognitive function task module 101 is used to set task parameters for a task paradigm, establish a mapping relationship between the task paradigm and cognitive functions, and a mapping relationship between cognitive functions and brain functional areas, so as to map the cognitive functions to brain functional areas.

[0031] The cognitive function data acquisition module 102 is used to collect cognitive function behavioral data and cognitive function brain imaging data of the user when completing the task paradigm in each round of cognitive modulation.

[0032] The data analysis module 103 is used to analyze the cognitive function behavioral data in each round of cognitive modulation in the task paradigm to obtain behavioral indicators representing different cognitive function states, and to analyze the cognitive function brain imaging data to obtain brain imaging features of brain activation patterns related to cognitive function.

[0033] The control module 104 is used to perform cognitive control on the user in each round of cognitive control in the task paradigm, based on the control parameters set by the user's cognitive aging risk probability judgment result.

[0034] The evaluation module 105 is used to compare the user's current training results with historical training results in each round of cognitive regulation in the task paradigm to obtain an evaluation result, and dynamically adjust the regulation parameters of the next round of cognitive regulation based on the evaluation result.

[0035] Specifically, the cognitive function task module 101 is used to construct, manage and organize a task paradigm system corresponding to different cognitive functions, and to establish a mapping relationship between task paradigms, cognitive functions and brain functional areas (brain regions).

[0036] In some embodiments, the cognitive function task module 101 includes four units: a cognitive function task parameter unit, a task library management unit, a function mapping unit, and a brain region mapping unit. The cognitive function task parameter unit is responsible for initializing and dynamically adjusting the parameter settings of various cognitive task paradigms. These parameters include at least one or more of the following: stimulus type, task difficulty, presentation frequency, response method, and number of trials. The task library management unit stores and manages multiple cognitive function-related task paradigms (experimental paradigms), which at least cover different cognitive function domains such as memory, attention, executive control, language, and spatial navigation. The function mapping unit establishes the mapping relationship between each task paradigm in the task library management unit and its corresponding cognitive function, enabling each task paradigm to be explicitly labeled as targeting one or more cognitive functions. The brain region mapping unit further maps the cognitive functions to corresponding brain functional areas or brain networks.

[0037] In some embodiments, such as Figure 2 As shown, this application also includes constructing a cognitive function task library. This library provides unified storage, organization, retrieval, and management of task paradigms for different cognitive functions, thereby constructing a structured, scalable, and reusable cognitive function task system. The cognitive function task library includes multiple types of cognitive paradigms, including the first paradigm, the second paradigm, and the nth paradigm (n is a positive integer greater than or equal to 1). The cognitive function task library adopts a multi-layered structured storage method, including at least the following information layers: task identifier layer, task logic layer, task parameter interface layer, and task tag layer.

[0038] The task identification layer assigns unique identification information to each task paradigm to distinguish and reference different cognitive tasks. This layer includes at least identification fields such as task number, task name, and task type. It is used to uniquely locate the specific task paradigm during task invocation, data recording, and subsequent analysis, thereby ensuring the consistency and traceability of tasks across different execution rounds and different system modules. Taking the DRM paradigm (Define-Research-Model paradigm) as an example, the task identification layer information for this task is "DRM paradigm".

[0039] The task logic layer describes the execution flow and structural rules of the task paradigm, including task phase division, trial structure, stimulus condition combination methods, and randomization rules, to define the complete execution logic of the cognitive task. Through the task logic layer, the system can present the task in a consistent flow across different users and operating environments, thus ensuring the stability and repeatability of the cognitive process induced by the task. Taking the DRM paradigm as an example, the task logic layer is divided into two parts. First, the user learns a series of semantically related words. Then, after a period of time, a testing phase is conducted, presenting the user with words and asking them to judge whether they are previously learned words. There are three types of test words: previously learned words, semantically related words that have not been previously learned, and words that have neither been learned nor semantically related.

[0040] The task parameter interface layer defines the parameter interfaces in the task paradigm that can be externally called and dynamically adjusted. These include parameter settings such as task difficulty, stimulus timing, number of trials, and stimulus interval, and define the value range and default configuration for each parameter. Through this layer, the system can generate task instances with different parameter configurations without changing the task's logical structure, adapting to different evaluation stages, individual states, or regulatory needs. Taking the DRM paradigm as an example, the task parameter interface layer includes encoding modality (the sensory modality of word presentation during the encoding stage, such as visual or auditory), presentation time (the time for word presentation, such as 2000 milliseconds), retrieval interval (the interval between encoding stages before entering the retrieval stage, such as 30 minutes), vocabulary size (the total number of vocabulary entries in the task, such as 8), and word count (the number of words in each vocabulary, such as 6).

[0041] The task labeling layer is used to functionally annotate task paradigms, associating each task with its corresponding cognitive functions and sub-functions, and indicating the cognitive function. Through this layer, the system can classify, summarize, and interpret behavioral and brain imaging data based on cognitive function dimensions during subsequent data analysis and risk assessment. Taking the DRM paradigm as an example, it first measures the user's ability to extract and process semantics, which is the primary cognitive function measured in this experimental paradigm; secondly, it can be used to measure the user's false memories and long-term memory; finally, the stimulus presentation is visual or auditory, which can be used to roughly measure the user's visual or auditory sensory information processing ability.

[0042] In some embodiments, the cognitive function task module further includes a function mapping unit, which maps the task paradigm to one or more cognitive functions. The function mapping unit includes a first mapping subunit, a second mapping subunit, and a fusion subunit. The first mapping subunit is used to evaluate the satisfaction level of the task paradigm on each cognitive function to obtain a first mapping relationship. The second mapping subunit is used to acquire text information corresponding to the task paradigm and determine the frequency of occurrence of each cognitive function in the text information to obtain a second mapping relationship. The fusion subunit is used to fuse the first mapping relationship and the second mapping relationship to achieve the mapping between the task paradigm and one or more cognitive functions.

[0043] In some embodiments, the functional mapping unit in this application is used to perform cognitive function mapping on each task paradigm in the cognitive function task library. Specifically, the cognitive function mapping on each task paradigm in the cognitive function task library is performed based on a pre-constructed functional mapping rule system. The functional mapping rule system adopts a combination of preset rules and literature priors. The preset rules correspond to the first mapping sub-unit, and the literature priors correspond to the second mapping sub-unit. The preset rules are professional judgments on the cognitive processes involved in different experimental paradigms introduced from the field of cognitive neuroscience as scores. The literature priors are used to determine the association between experimental paradigms and specific cognitive functions based on existing research results, and to calculate the number of occurrences of cognitive function-related keywords as scores.

[0044] Specifically, firstly, a series of cognitive functions are defined. As shown in the formula below.

[0045] (1)

[0046] Next, establish the first mapping relationship. For each specific cognitive task paradigm Experts need to assess its performance in each specific cognitive function. Degree of satisfaction Where 1 represents that the task fully possesses the attributes to test the cognitive function, and 0 represents that the task does not possess the attributes to test the cognitive function at all, establishing the first mapping relationship. As shown in the formula below.

[0047] (2)

[0048] Next, establish the second mapping relationship. For each specific cognitive task paradigm This involves acquiring textual information used in research employing this paradigm, specifically a collection of relevant literature containing only abstracts and keywords. Then, for each specific cognitive function... Calculate the number of times it appears in the document content. The second mapping relationship established As shown in the formula below.

[0049] (3)

[0050] Next, the first mapping relationship is normalized to obtain... The second mapping relationship is normalized to obtain ,in It is an adjustment factor, as shown in the formula below.

[0051] (4)

[0052] (5)

[0053] Finally, the first mapping relationship and the second mapping relationship are merged to obtain... ,pass Controlling the weights of preset rules and prior knowledge (first mapping relationship and second mapping relationship), when When the value is too large, it tends to be driven by preset rules (first mapping relationship). When the skewness is small, it is more inclined to be driven by literature priors (second mapping relationship), as shown in the following formula.

[0054] (6)

[0055] Using the cognitive function mapping method described above, each cognitive task paradigm is quantitatively modeled under two dimensions: preset rules and literature priors (first mapping relationship and second mapping relationship), and then weighted and fused in a unified normalized space to obtain the comprehensive score results of the task paradigm on each cognitive function dimension.

[0056] In the above embodiments, on the one hand, expert knowledge from the field of cognitive neuroscience is introduced through the first mapping subunit to ensure the theoretical rationality and stability of the cognitive function mapping results. On the other hand, the second mapping subunit combines statistical evidence from existing research literature to ensure that the mapping results reflect the functional orientation of the task paradigm in practical research applications. Furthermore, by adjusting the weight parameters, a flexible balance can be achieved between expert prior knowledge and literature evidence, making the cognitive function mapping process interpretable, controllable, and scalable, providing a unified and reliable functional prior basis for subsequent brain region mapping, cognitive state assessment, and regulatory decisions based on cognitive function.

[0057] In some embodiments, the cognitive function task module 101 further includes a brain region mapping unit, which maps each cognitive function to one or more brain functional regions. The brain region mapping unit includes a brain activation map processing subunit and a brain region mapping subunit. The brain activation map processing subunit is used to acquire a brain activation map related to the cognitive function and process the brain activation map according to a preset activation threshold to obtain an activation status map. The brain region mapping subunit uses a brain region segmentation map to divide a standard space into several brain functional regions and registers the activation status map to the standard space to obtain the number of times the cognitive function is identified as activated in different brain functional regions. Based on the number, the mapping relationship between each cognitive function and one or more brain functional regions is obtained.

[0058] Specifically, this application also includes brain region (brain functional area) mapping for cognitive functions. This brain region mapping is used to establish a correspondence between cognitive functions and specific brain functional areas or networks. The brain region mapping is based on findings from previous research and reproducible results. Specifically, for each specific cognitive function... Retrieve all studies related to this cognitive function, obtain their corresponding brain activation maps, and compile the activation maps from each study. Registered to the standard space template (MNI152NLin2009Asym), where, The standard spatial voxel set is shown in the formula below. Then, a pre-defined brain region segmentation atlas (Destrieux) is used to divide the standard space into several brain regions. The following formula and Figure 3 As shown, Figure 3 The brain regions are divided into areas for display, with different brain regions identified by numbers.

[0059] (7)

[0060] (8)

[0061] The obtained activation map is then processed according to the set activation threshold. The activation status map is obtained as shown in formula (9) below. From this, we can further obtain the activation status map for... (No. The cognitive function in the first The number of studies that identified activation in individual brain regions. Subsequently Normalization process is performed to obtain As shown in the following formula (11).

[0062] (9)

[0063] (10)

[0064] (11)

[0065] The brain region mapping method described above, based on research evidence, establishes a quantitative correspondence between cognitive functions and specific brain regions or brain functional networks. This method relies on a large number of reproducible functional magnetic resonance imaging (fMRI) studies, uniformly registering brain activation maps from different studies to a standard space and performing statistical analysis within a unified brain region segmentation framework. This eliminates differences in spatial representation and analytical scale between different studies.

[0066] By normalizing the number of studies on the activation of various brain functional areas under different cognitive functions, brain region mapping results that reflect the strength of the association between cognitive function and brain regions are obtained. These brain region mappings not only have a clear neuroimaging evidence basis but also possess good stability and scalability. The resulting cognitive function-brain region mapping results can serve as an important spatial prior for subsequent brain imaging data analysis, functional abnormality assessment, and selection of regulatory targets, providing reliable support for constructing cognitive function-based neural feedback and photostimulation modulation.

[0067] In another embodiment, this application also includes a task presentation module, which is used to visualize the specific task in a paradigm or present it to the user in a multimodal form according to the task paradigm parameters set in the cognitive function task module, and control the start, end and stimulus sequence of the task paradigm to ensure the standardization and repeatability of the experimental process.

[0068] Specifically, cognitive function tasks are presented to users in a standardized manner according to a preset task paradigm structure and task parameters, guiding users to complete the corresponding cognitive task paradigms. Based on a pre-built task identifier layer, task logic layer, task parameter interface layer, and task tag layer in the cognitive function task library, cognitive function tasks are uniformly configured and presented to ensure consistency, repeatability, and traceability of different cognitive tasks during execution. First, the corresponding cognitive task paradigm is retrieved from the cognitive function task library based on the task number and task name recorded in the task identifier layer. Then, based on the task execution structure defined in the task logic layer, the presentation flow of the cognitive task is generated. On this basis, the specific parameters of the cognitive task are further configured through the task parameter interface layer. The parameter configuration includes at least the task difficulty level, stimulus presentation duration, stimulus interval, number of trials, and task duration, and can be adjusted according to assessment needs or user status. Without changing the task logic structure, the parameter interface layer enables flexible control of the cognitive task load level to adapt to different cognitive assessment or training scenarios. Before or during task presentation, the cognitive function type corresponding to the current cognitive task is identified based on the cognitive function labels recorded in the task label layer. This, combined with the mapping results between tasks, cognitive functions, and brain regions obtained above, provides prior information for subsequent behavioral and brain imaging data analysis. After completing the task invocation, process generation, and parameter configuration, the task presentation module presents cognitive task stimuli to the user according to the generated task flow and guides the user to complete the corresponding operations.

[0069] In some embodiments, the cognitive function data acquisition module 102 of this application is used to collect cognitive function behavioral data and cognitive function brain imaging data when completing a task paradigm.

[0070] Specifically, the cognitive function data acquisition module 102 is used to collect data during task completion, which includes two parts: cognitive function behavioral data and cognitive function brain imaging data. Cognitive function behavioral data refers to the behavioral data generated by the user during task completion, including at least reaction time, accuracy rate, error type, and indicators related to task completion strategies. Cognitive function brain imaging data refers to the functional near-infrared brain imaging data generated by the user during task completion, reflecting changes in brain blood oxygen dynamics under different cognitive task conditions.

[0071] In one specific embodiment, cognitive function behavioral data and cognitive function brain imaging data are collected during the execution of the above-mentioned task. The cognitive function behavioral data is used to record the user's behavioral performance when completing the cognitive task, and includes at least the following data types: event tag data, used to record the attributes of various stimuli and additional events presented during the experiment; time stamp data, used to record the timestamps of the event tag data during the experiment; user reaction data, used to record the operation content of the reactor during the experiment; and user reaction time stamp data, used to record the timestamps of the user's reaction during the experiment.

[0072] The cognitive brain imaging data is functional near-infrared brain imaging (fNIRS), used to record changes in brain blood oxygenation dynamics under different cognitive task conditions. It includes oxyhemoglobin and deoxyhemoglobin signals, and is continuously acquired during the cognitive task to form corresponding time-series data.

[0073] In some embodiments of this application, neural stimulation may specifically be optical stimulation. Functional near-infrared brain imaging (FIN) is preferably used as a means of monitoring neural states, rather than electroencephalography (EEG). On the one hand, FIN reflects neural activity states by detecting changes in brain oxygenation dynamics, and is insensitive to optical stimulation and its interference, making it suitable for stable operation under optical stimulation conditions. On the other hand, FIN has good spatial localization capabilities, directly reflecting changes in metabolic responses of specific cortical brain regions during cognitive tasks and stimulus regulation processes, and typically exhibits higher stability and reproducibility in terms of temporal scale, spatial localization, and consistency across experimental conditions. Furthermore, FIN is suitable for long-term, continuous, and low-burden monitoring, which is beneficial for constructing a closed-loop control system for long-term cognitive regulation and monitoring.

[0074] The data analysis module 103 is used to analyze the cognitive function behavioral data in each round of cognitive modulation in the task paradigm to obtain behavioral indicators representing different cognitive function states, and to analyze the cognitive function brain imaging data to obtain brain imaging features of brain activation patterns related to cognitive function.

[0075] Specifically, the data analysis module includes a cognitive function analysis module and a brain imaging analysis module. The cognitive function analysis module calculates and analyzes the collected cognitive function behavioral data, outputting behavioral indicators that quantitatively characterize different cognitive function states, such as task performance scores, reaction speed indicators, and stability indicators. The brain imaging analysis module preprocesses, extracts features, and statistically analyzes the collected functional near-infrared brain imaging data to obtain brain activation patterns or functional connectivity features related to specific tasks and cognitive functions. In some embodiments, the cognitive function behavioral data is analyzed to obtain behavioral indicators characterizing different cognitive function states. These indicators include the proportion of correctly identifying or recalling presented words, semantic association-driven false memory tendency, and the efficiency of memory retrieval and conflict resolution processes. The cognitive function brain imaging data is analyzed to obtain brain activation maps characterizing different cognitive function states, and neural indicators of brain regions of interest are extracted from these maps.

[0076] In one specific embodiment, the collected cognitive function behavioral data is analyzed to obtain behavioral indicators that can characterize different cognitive function states. Taking the DRM paradigm as an example, the true memory rate refers to the proportion of users who correctly identify or recall presented words, and this indicator can be used to characterize true memory ability; the false memory rate refers to the proportion of users who misidentify bait words as presented words, and is used to characterize the tendency of false memory driven by semantic association; the reaction time-related indicator refers to the difference in reaction time when users identify true words and bait words, and is used to characterize the efficiency of memory retrieval and conflict resolution processes. The collected cognitive function brain imaging data is analyzed to obtain brain activation maps that can characterize different cognitive function states, and neural indicators of brain regions of interest are extracted from them. Taking the DRM paradigm as an example, by distinguishing between trials of true memory and trials of false memory, neural indicators related to true memory retrieval, neural indicators related to false memory generation, neural indicators related to true memory encoding, and neural indicators related to false memory encoding can be explored in the encoding and retrieval stages, respectively.

[0077] In some embodiments, the system further includes a data recording module, which comprises an individual baseline unit, an individual development unit, a group baseline unit, and a group development unit. The individual baseline unit is used to collect and store the user's cognitive function behavioral data and cognitive function brain imaging data during the first cognitive modulation session, and to establish an individual-level initial cognitive function baseline model for the user. The individual development unit is used to continuously collect and store the user's cognitive function behavioral data and cognitive function brain imaging data during each subsequent modulation session, and to establish an individual-level model of cognitive function state changes over time for the user. The group baseline unit is used to construct a group-level initial cognitive function baseline model based on the individual baseline units of each user. The group development unit is used to construct a group-level model of cognitive function state changes over time based on the group development units of each user.

[0078] In one specific embodiment, the individual-level data recording module of this application is used to record individual user data, comprising two units: an individual baseline unit and an individual development unit. The individual baseline unit refers to the initial data obtained when the user first runs the system, and the individual development unit refers to the developmental data obtained when the user runs the system a second or subsequent time. In one specific embodiment, the group-level data recording module of this application is used to record group user data, comprising two units: a group baseline unit and a group development unit. The group baseline unit refers to the aggregation and storage of data from each user's individual baseline unit to construct a group-level baseline reference model; the group development unit refers to the aggregation and storage of data from each user's individual development unit to construct a group-level development and change model.

[0079] Specifically, the individual baseline unit establishes an initial cognitive function reference state for each user at the individual level. This is used to record the data collected and analyzed during the user's first run of the system and completion of a cognitive task. The data includes at least: behavioral indicators derived from cognitive function behavioral data analysis, neural indicators derived from functional near-infrared brain imaging data analysis, task identification information corresponding to the data, and cognitive function tags.

[0080] The individual development unit is used to continuously record the trajectory of changes in a user's cognitive function state over time. When a user runs the system for the second or subsequent times, cognitive function-related data generated in subsequent runs is recorded in the individual development unit. The individual development unit stores development data generated by the user during multiple system runs. This development data maintains the same data structure as the individual baseline unit to facilitate time-series management and longitudinal comparison.

[0081] The group baseline unit aggregates and records the data stored in each user's individual baseline unit to construct a group-level cognitive function baseline reference model. This refers to aggregating and storing data from each user's individual baseline unit to build a group-level baseline reference model.

[0082] The group development unit aggregates and records data stored in each user's individual development unit to construct a group-level model of cognitive function changes. It refers to the aggregation and storage of data from each user's individual development unit to build a group-level development and change model.

[0083] The above embodiments include the structured storage of the analysis results obtained above. When a user runs the system for the first time and completes a cognitive task, the data collected and analyzed during that run is recorded in an individual baseline unit. This unit stores the user's initial cognitive state data upon first use of the system. Through the individual baseline unit, an initial cognitive function reference state is established for each user at the individual level. When a user runs the system for the second and subsequent runs, the cognitive function-related data generated in subsequent runs is recorded in an individual development unit. The individual development unit stores the development data generated by the user during multiple system runs. The development data maintains the same data structure as the individual baseline unit to facilitate time-series management and longitudinal comparison. Through the individual development unit, the system can continuously record the trajectory of changes in the user's cognitive function state over time. The data stored in each user's individual baseline unit is aggregated and recorded in a group baseline unit to construct a group-level cognitive function baseline reference model. The data stored in each user's individual development unit is aggregated and recorded in a group development unit to construct a group-level cognitive function change model.

[0084] In some embodiments, the system further includes an early warning module, which comprises an individual longitudinal comparison unit, a longitudinal early warning unit, a group horizontal comparison unit, and a horizontal early warning unit. The individual longitudinal comparison unit compares the user's behavioral indicators and brain imaging features in the current round of cognitive regulation with the behavioral indicators and brain imaging features in the user's individual baseline unit to obtain the user's cognitive function change trend and the probability of cognitive aging risk. The longitudinal early warning unit determines that the user has a risk of cognitive aging and issues an early warning when the user's cognitive changes meet the risk conditions based on the change trend and the probability of cognitive aging risk. The group horizontal comparison unit compares the user's behavioral indicators and brain imaging features in the current round of cognitive regulation with the behavioral indicators and brain imaging features in the user group baseline unit to determine the individual's deviation from the group and determines the probability of cognitive aging risk based on the deviation. The horizontal early warning unit determines that the user has a risk of cognitive aging and issues an early warning when the user's cognitive changes meet the risk conditions based on the probability of cognitive aging risk.

[0085] Specifically, the system also includes a cognitive aging early warning module. This module combines longitudinal changes at the individual user level with a lateral reference model at the group level to comprehensively assess the user's current cognitive function status and output corresponding cognitive aging risk warning results. This includes an individual longitudinal comparison unit and a group lateral comparison unit. The individual longitudinal comparison unit compares the cognitive function behavioral indicators and brain imaging features obtained by the user in the current running round with the corresponding data in their individual baseline unit to identify trends in various cognitive functions. When the changes exceed a preset threshold or show a continuous downward trend, it determines that the user has a potential risk of cognitive aging and issues a warning. The group lateral comparison unit compares the user with corresponding group data, calculates the individual's deviation from the group's contemporaneous data, and maps the deviation to a risk probability.

[0086] In another embodiment, this application further includes a cognitive aging early warning module. This module is used to provide early warning of cognitive aging and includes two units: an individual longitudinal comparison unit and a group horizontal comparison unit. The individual longitudinal comparison unit is responsible for longitudinally analyzing the user's current cognitive change trend based on the user's individual baseline data and individual development data, thereby assessing their cognitive aging risk. The group horizontal comparison unit is responsible for horizontally comparing the user's current cognitive state with the group baseline and group development data, thereby assessing the user's cognitive aging risk level relative to the group. By combining the longitudinal changes at the individual user level and the horizontal reference model at the group level, a comprehensive judgment is made on the user's current cognitive function status, and a corresponding cognitive aging risk early warning result is output.

[0087] Based on data from individual baseline units and individual development units stored in the individual data recording module, a longitudinal comparative analysis of the user's cognitive function status is performed to assess whether the user's cognitive function performance at different time points has significantly changed relative to their baseline state. The cognitive function behavioral indicators and brain imaging features obtained by the user in the current running round are compared with the corresponding data in their individual baseline unit to identify trends in various cognitive functions. When the changes exceed a preset threshold or show a continuous downward trend, it is determined that the user has a potential risk of cognitive aging, and a warning is issued. Specifically, Defined in user number No. The data stored during this system run includes behavioral and neurological indicators representing different cognitive functions, compared with the individual's previous data. By making comparisons, a standard score can be obtained. As shown in formula (12), where, This represents the standard deviation. Further, see formula (13), based on... Calculate the deviation of an individual from its past performance. If the user's historical number of runs is less than or equal to the minimum required number, skip this step.

[0088] (12)

[0089] (13)

[0090] Corresponding historical group data Compare and calculate individual Compared to the same period of the group, the deviation As shown in formulas (14) and (15), where, Indicates standard deviation, Represents the standard score.

[0091] (14)

[0092] (15)

[0093] Map the deviation to the probability of risk. ,in For pre-set thresholds, unless there are special requirements, the 75th percentile of the corresponding data for the group can be set as the threshold. The sensitivity of the alarm is shown in formula (16).

[0094] (16)

[0095] The control module 104 is used to perform cognitive control on the user in each round of cognitive control in the task paradigm, based on the control parameters set by the user's cognitive aging risk probability judgment result.

[0096] In some embodiments, the control module can be controlled by light stimulation. This module is used to provide light stimulation to the user and includes two units: a light stimulation parameter unit and a light stimulation execution unit. The light stimulation parameter unit is used to initialize and adjust the parameter settings of the light stimulation, including at least the stimulation wavelength, stimulation intensity, stimulation location, and stimulation duration. The light stimulation execution unit is responsible for providing light stimulation to the user based on the determined light stimulation parameters.

[0097] In some embodiments, the control module further includes a control parameter setting unit and a cognitive control execution unit. The control parameter setting unit initializes and adjusts the control parameters, and the cognitive control execution unit performs cognitive control according to the determined control parameters. The control parameter setting unit is used to determine the stimulation location for cognitive control based on the user's current cognitive aging risk index and the mapping relationship between cognitive function and brain functional areas, and to adjust the stimulation intensity and duration within a preset safety range. The stimulation location is the brain functional area corresponding to high-risk cognitive function, and the cognitive control intensity and control time dynamically increase with the increase of the probability of cognitive aging risk.

[0098] The parameter setting unit can specifically be a light stimulation parameter unit, which determines the stimulation location of light stimulation based on the user's current level of cognitive aging risk and the mapping relationship between cognitive function and brain regions. And within a preset safety range, the intensity of light stimulation Duration of light stimulation and the wavelength of light stimulation Isophotostimulation parameters Adaptive adjustment is performed. See formula (20) for the location of light stimulation. Target brain regions corresponding to high-risk cognitive functions Different types of light stimulation need to be adjusted according to the specific location, such as Figure 4 As shown. See formulas (19) and (20), light stimulation intensity With light stimulation time The probability of cognitive aging increases. Dynamic changes occur; the intensity of light stimulation increases with the probability of cognitive aging risk. and light stimulation time In the safe zone The risk of cognitive aging increases continuously. After assessing and issuing early warnings regarding the risk of cognitive aging, the system, based on the obtained probability judgment of cognitive aging risk, triggers the photostimulation module to regulate users with potential cognitive aging risks.

[0099] (17)

[0100] (18)

[0101] (19)

[0102] (20)

[0103] (twenty one)

[0104] The evaluation module 105 is used to compare the user's current training results with historical training results in each round of cognitive regulation in the task paradigm to obtain an evaluation result, and dynamically adjust the regulation parameters of the next round of cognitive regulation based on the evaluation result.

[0105] In one specific embodiment, the system further includes a neurofeedback module, wherein the neurofeedback is used to reflect the immediate regulatory results of the modulation on the user's neural activity; the neurofeedback module is used to calculate the changes in the user's neural indicators before and after cognitive modulation training, and map the changes in the neural indicators to neurofeedback parameters; the neurofeedback parameters include the intensity of the neurofeedback signal, the duration of the neurofeedback, and the presentation mode of the neurofeedback, and present the corresponding feedback information to the user.

[0106] The neurofeedback module provides neural feedback to the user and comprises two units: a neurofeedback parameter unit and a neurofeedback presentation unit. The neurofeedback parameter unit is responsible for initializing and adjusting a series of specific neural feedback parameters; the neurofeedback presentation unit is responsible for providing neural feedback to the user based on the predetermined neural feedback parameters.

[0107] In one specific embodiment, the neural feedback signal intensity is the difference in neural indicators of brain functional areas related to cognitive function before and after cognitive modulation; the duration of the neural feedback is dynamically adjusted by the neural feedback signal intensity within a safe range; the neural feedback is presented in a unimodal and multimodal manner, wherein the visual mode presents the activation status of the brain functional area represented by the visual neural feedback signal, the auditory mode presents the volume and frequency adjusted by the auditory neural feedback signal, and the tactile mode presents the vibration intensity and frequency of the wristband adjusted by the tactile neural feedback signal.

[0108] In the above embodiments, after completing the light stimulation modulation, the system further introduces a neurofeedback module to present neurofeedback information to the subject based on the changes in the subject's neural state before and after light stimulation. This neurofeedback reflects the immediate regulatory effect of light stimulation on the subject's neural activity, allowing the subject to intuitively perceive changes in their own neural state. The system collects and compares the subject's neural indicators, extracts the changes in neural state before and after light stimulation, and maps these changes to the intensity, duration, and presentation method of the feedback signal. The neurofeedback execution unit then presents the corresponding feedback information to the subject. Through this method, the system establishes a feedback pathway between light stimulation modulation and the subject's subjective perception, enhancing the subject's sense of participation and perception in the modulation process, thereby further improving the stability, individual adaptability, and long-term modulation effect of the closed-loop modulation system.

[0109] Specifically, see formula (22), neural feedback parameters Defined as the intensity of neural feedback signals Duration of neural feedback and neurofeedback presentation methods See formula (23). Defined as a neural indicator of brain regions related to cognitive function prior to the administration of light stimulation. Neural indicators of brain regions related to cognitive function after light stimulation The difference in neural indices; see formula (24), neural feedback signal strength. Defined as the difference in neural indices for cognitively related brain regions before and after light stimulation. The 2-norm, see formula (25), neural feedback duration Defined as within the safe zone Internal neural feedback signal strength Dynamic adjustment; see formula (26), neurofeedback presentation method It can be defined as a unimodal and multimodal form of presentation, where visual mode To visually represent the activation status of specific brain regions indicated by neural feedback signals, auditory patterns... The volume and frequency adjusted for auditory neural feedback signals, tactile patterns The vibration intensity and frequency of the wristband are adjusted to provide tactile feedback signals. The neurofeedback module presents neurofeedback information to the subject based on changes in the subject's neural state before and after light stimulation. The neurofeedback is used to reflect the immediate regulatory effect of light stimulation on the subject's neural activity, enabling the subject to intuitively perceive changes in their own neural state, as shown in formulas (22)-(26).

[0110] (twenty two)

[0111] (twenty three)

[0112] (twenty four)

[0113] (25)

[0114] (26)

[0115] In some embodiments, this application further includes an evaluation module 105, which is used to compare the user's current training results with historical training results in each round of cognitive regulation of the task paradigm to obtain an evaluation result, and dynamically adjust the regulation parameters of the next round of cognitive regulation based on the evaluation result.

[0116] The evaluation module can be understood as a module used to evaluate the effect of regulation. In each round of light stimulation training, it compares the user's current training effect with the historical training effect to obtain longitudinal training evaluation results and lateral training evaluation results.

[0117] In one specific embodiment, the evaluation module further includes an adjustment unit; the adjustment unit is used to evaluate the regulation results based on changes in the user's cognitive aging risk and task performance after cognitive regulation and neurofeedback, and to adjust the regulation parameters of subsequent rounds of cognitive regulation tasks based on the evaluation results.

[0118] In one specific embodiment, the adjustment unit is further configured to increase the difficulty or training intensity of the cognitive regulation task when the regulation result meets the preset requirements and the risk of cognitive aging shows a downward trend, and to reduce the task difficulty, extend the task interval or reduce the training volume when the regulation result does not meet the preset requirements or fatigue signs appear.

[0119] Specifically, the system comprehensively considers changes in the user's cognitive aging risk and task performance after light stimulation and neural feedback to evaluate the modulation effect and dynamically adjust the parameters of subsequent cognitive tasks based on the evaluation results. When the modulation effect is good and the risk of cognitive aging shows a downward trend, the system appropriately increases the difficulty of the cognitive task or the training intensity to enhance the challenge and effectiveness of cognitive training; when the modulation effect is insufficient or signs of fatigue appear, the system correspondingly reduces the task difficulty, extends the task interval, or reduces the training volume to ensure the safety and sustainability of task execution.

[0120] Specifically, the regulation effect module is used to calculate and evaluate the regulation effect of each user in each round. It includes two units: an individual longitudinal comparison unit and a group horizontal comparison unit. The individual longitudinal comparison unit is responsible for calculating and evaluating the user's current regulation effect based on the historical regulation effect of the data recording module (individual).

[0121] In one specific embodiment, through multiple rounds of light stimulation modulation and neural feedback, and reassessing the risk of cognitive aging after each round, the modulation parameters are gradually adjusted and the cognitive state is dynamically optimized. The parameter information for each round of modulation, as well as the level of cognitive aging risk before and after modulation, are stored in both the individual and group data recording modules, and the modulation effect is calculated. The modulation effect is defined as the numerical change in cognitive aging risk; a good modulation effect is expected to significantly reduce the level of cognitive aging risk.

[0122] Following multiple rounds of light stimulation modulation and neural feedback, the system further introduces an adaptive adjustment mechanism for cognitive task parameters based on the modulation effect. The system comprehensively considers changes in the user's cognitive aging risk and task performance after light stimulation and neural feedback, evaluates the modulation effect, and dynamically adjusts the parameters of subsequent cognitive tasks based on the evaluation results. When the modulation effect is good and the risk of cognitive aging shows a downward trend, the system appropriately increases the difficulty or training intensity of the cognitive task to enhance the challenge and effectiveness of cognitive training. When the modulation effect is insufficient or signs of fatigue appear, the system correspondingly reduces the task difficulty, extends the task interval, or reduces the training volume to ensure the safety and sustainability of task execution. Through this approach, the cognitive task itself becomes part of the closed-loop modulation system, achieving synergistic optimization between cognitive assessment, neural modulation, and task training, thereby improving the system's adaptability to changes in individual cognitive function and its long-term modulation effect.

[0123] Specifically, for each specific cognitive task paradigm In the task parameter interface layer, the direction of change and difficulty are predefined by experts. Taking the DRM paradigm as an example, the larger the vocabulary, the greater the task difficulty. When the task difficulty needs to be adjusted, the parameters in the task parameter interface layer are adjusted in the direction of the required difficulty change.

[0124] Cognition refers to a series of psychological and neural processes by which an individual acquires, processes, stores, and utilizes information; it is the process by which humans process information. Cognitive ability determines the speed and quality of an individual's information acquisition and processing, and is a prerequisite for the realization of higher functions such as learning, decision-making, emotion regulation, and social interaction. It not only supports basic activities in daily life but also directly affects an individual's adaptability and problem-solving abilities in complex environments. From the perspective of cognitive neuroscience, the series of cognitive processes are not the functional products of a single brain region, but rather a complex process achieved through the dynamic interaction of multiple functional systems distributed throughout the brain.

[0125] Photostimulation is a non-invasive neuromodulation technique that uses near-infrared or red light of specific wavelengths to irradiate the cerebral cortex, thereby regulating neural activity and metabolic states. In recent years, with a deeper understanding of mitochondrial function, neural metabolism, and cerebral blood flow regulation mechanisms, photostimulation has been gradually introduced into the field of cognitive neuroscience and is considered a regulatory technology with potential cognitive enhancement and neuroprotective effects. From a neurobiological perspective, this process does not directly induce neuronal firing, but rather provides a more favorable physiological environment for neural activity by regulating neuronal metabolism and excitability thresholds. Therefore, the effect of photostimulation is closer to state regulation than forced stimulation, which makes it safer and more tolerable in cognitive modulation applications.

[0126] However, existing systems lack a systematic task-inducing mechanism oriented towards cognitive modules, making it difficult to stably represent the overall cognitive state and different cognitive functions. In existing cognitive state detection and regulation technologies, cognitive tasks usually exist as an auxiliary condition, their main function being to trigger changes in the subject's neural activity. However, the cognitive tasks used in existing technologies are mostly single tasks or combinations of a few tasks, and task design often targets isolated task performance rather than cognitive function, lacking systematic design and theoretical completeness. Secondly, existing optical stimulation technologies lack adaptive regulation mechanisms based on neural states. In existing optical stimulation technologies, stimulation parameters are usually executed according to preset schemes, such as fixed wavelength, fixed intensity, or fixed stimulation rhythm. This type of stimulation does not depend on the user's real-time neural activity state during implementation, nor does it establish a feedback relationship between stimulation effect and neural response. Finally, existing technologies are difficult to support individualized regulation and evolution in long-term cognitive training. As mentioned in the background, existing near-infrared brain imaging-based technologies are mainly used for the detection or assessment of cognitive states, and their core function is to obtain information on the user's neural activity during cognitive tasks. However, such schemes typically separate cognitive state detection from subsequent regulation or training processes, and the detection results are mostly used for offline analysis or static evaluation.

[0127] like Figure 5As shown, this application provides a dynamic cognitive regulation system for cognitive function assessment, cognitive aging early warning, and closed-loop regulation. This system is centered on cognitive task induction, based on the joint analysis of functional near-infrared brain imaging data and behavioral data, and combines longitudinal individual modeling with group comparative analysis to achieve cognitive state assessment, risk warning, and feedback on regulation effects. Specifically, it includes the following modules: a cognitive function task module, a cognitive function data acquisition module, a data analysis module, a regulation module, and an assessment module, as detailed below.

[0128] The Cognitive Function Task Module is used to construct, manage, and organize experimental paradigms corresponding to different cognitive functions, and to establish mapping relationships between tasks, cognitive functions, and brain regions. It comprises four units: a Cognitive Function Task Parameter Unit, responsible for initializing and dynamically adjusting parameter settings for various cognitive experimental paradigms, including at least stimulus type, task difficulty, presentation frequency, response mode, and number of trials; a Task Library Management Unit, responsible for storing and managing multiple cognitive function-related experimental paradigms, covering at least different cognitive function domains such as memory, attention, executive control, language, and spatial navigation; a Function Mapping Unit, used to establish mapping relationships between each experimental paradigm in the Task Library Management Unit and its corresponding cognitive function, enabling each experimental paradigm to be clearly labeled as targeting one or more cognitive functions; and a Brain Region Mapping Unit, used to further map the cognitive functions to corresponding brain functional areas or brain networks.

[0129] The task presentation module is used to present specific tasks to users in a visual or multimodal form according to the experimental paradigm parameters set in the cognitive function task module, and to control the start, end and stimulus sequence of the task to ensure the standardization and repeatability of the experimental process.

[0130] The cognitive function data acquisition module is used to collect data when completing the experimental paradigm. It includes two parts: cognitive function behavioral data, which refers to the behavioral data generated by the user when completing the experimental task. The behavioral data includes at least reaction time, accuracy rate, error type and task completion strategy related indicators; and cognitive function brain imaging data, which refers to the functional near-infrared brain imaging data generated by the user during the completion of the experimental task, to reflect the changes in brain blood oxygen dynamics under different cognitive task conditions.

[0131] The cognitive function analysis module (data analysis module) is used to calculate and analyze the collected cognitive function behavioral data, outputting behavioral indicators that can quantitatively characterize different cognitive function states, such as task performance scores, reaction speed indicators, and stability indicators. The brain imaging analysis module is used to preprocess, extract features, and statistically analyze the collected functional near-infrared brain imaging data to obtain brain activation patterns or functional connectivity features related to specific tasks and cognitive functions.

[0132] The data recording module (individual) is used to record individual user data. It consists of two units: the individual baseline unit, which refers to the initial data obtained when the user runs the system for the first time; and the individual development unit, which refers to the development data obtained when the user runs the system for the second and subsequent times.

[0133] The data recording module (group) is used to record user group data. It consists of two units: the group baseline unit, which summarizes and stores the data in each user's individual baseline unit to build a baseline reference model at the group level; and the group development unit, which summarizes and stores the data in each user's individual development unit to build a development and change model at the group level.

[0134] The cognitive aging early warning module (early warning module) is used to provide early warnings of cognitive aging. It consists of two units: an individual longitudinal comparison unit, which is responsible for longitudinally analyzing the user's current cognitive change trend based on the user's individual baseline data and individual development data, thereby assessing the user's cognitive aging risk; and a group horizontal comparison unit, which is responsible for horizontally comparing the user's current cognitive state with the group baseline and group development data, thereby assessing the user's cognitive aging risk level relative to the group.

[0135] The photostimulation module (regulation module) is used to provide photostimulation to the user and includes two units: a photostimulation parameter unit (regulation parameter setting unit) for initializing and adjusting the parameter settings of the photostimulation, which includes at least the stimulation wavelength, stimulation intensity, stimulation location, and stimulation duration; and a photostimulation execution unit (cognitive regulation execution unit) responsible for providing photostimulation to the user based on the determined photostimulation parameters.

[0136] The neurofeedback module is used to provide neurofeedback to the user and consists of two units: a neurofeedback parameter unit, which is responsible for initializing and adjusting a series of specific neurofeedback parameters; and a neurofeedback presentation unit, which is responsible for providing neurofeedback to the user based on the determined neurofeedback parameters.

[0137] The regulation effect module is used to calculate and evaluate the regulation effect of each user in each round. It includes two units: an individual longitudinal comparison unit, which is responsible for calculating and evaluating the user's current regulation effect based on the historical regulation effect of the data recording module (individual); and a group horizontal comparison unit, which is responsible for calculating and evaluating the user's current regulation effect based on the group regulation effect of the data recording module (group).

[0138] The systematic task library and task induction mechanism built through the above system, oriented towards cognitive function, achieves stable representation of overall cognitive state and different cognitive functions. Unlike existing technologies that merely use cognitive tasks as auxiliary means to trigger neural activity, this application uses cognitive function as the core organizational unit, uniformly managing, mapping functions and brain regions of different experimental paradigms. This allows cognitive tasks to move beyond the measurement of single task performance and systematically characterize the user's cognitive state from a cognitive function perspective, thereby improving the completeness and theoretical consistency of cognitive assessment. Secondly, this application introduces an adaptive light stimulation control mechanism based on changes in neural state, overcoming the problems of fixed stimulation parameters and lack of feedback in existing light stimulation technologies. This invention continuously assesses the user's cognitive aging risk and changes in neural state, dynamically adjusting parameters such as light stimulation intensity and duration within a preset safety range. This enables light stimulation control to adaptively change according to the user's current cognitive state and the control effect, thereby improving the targeting and effectiveness of control while ensuring safety, and establishing a feedback relationship between stimulation effect and neural response. Furthermore, this application introduces a neural feedback mechanism, enabling users to perceive changes in their own neural state after light stimulation, thereby establishing a feedback pathway between stimulation regulation and the user's subjective experience. This neural feedback, by mapping changes in neural state into perceptible forms such as hearing or touch, enhances the perceptibility and participation of the regulation process, helps strengthen the user's understanding and cooperation with the regulation process, and further improves the stability of the closed-loop regulation system.

[0139] Furthermore, this application introduces an adaptive adjustment mechanism for cognitive task parameters based on the adjustment effect during multiple rounds of regulation, making the cognitive task itself an important component of the closed-loop regulation system. The system dynamically adjusts the difficulty, training intensity, and pace of the cognitive task according to changes in cognitive aging risk and task performance before and after regulation, thereby avoiding the problem of long-term fixed cognitive training parameters and difficulty in adapting to individual differences in existing technologies, and realizing individualized regulation and evolution of the cognitive training process. Finally, this application integrates cognitive state assessment, light stimulation regulation, neural feedback, and cognitive task regulation into the same closed-loop system, enabling the system not only to detect and assess cognitive states but also to support continuous regulation and dynamic optimization during long-term operation. Through the above technical solutions, this invention can better adapt to the state changes of different users during long-term cognitive training or regulation, enhancing the practicality and promotional value of the system in cognitive aging early warning, cognitive function maintenance, and long-term regulation application scenarios.

[0140] It is understood that the computer device used to implement the user interaction system solution provided in this application can be a server, and its internal structure diagram can be as follows: Figure 6As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage medium. The database stores relevant data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements the method provided in this application.

[0141] Those skilled in the art will understand that Figure 6 The structures shown are merely block diagrams of a portion of the structures related to the present application and do not constitute a limitation on the computer device to which the present application is applied. The computer device may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements. Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program may include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0142] It should be understood that the processor mentioned in the embodiments of this application can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0143] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0144] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A dynamic cognitive regulation system, characterized in that, The system is applicable to dynamic cognitive regulation of different task paradigms. For dynamic cognitive regulation of each task paradigm, the system includes the following modules: The cognitive function task module is used to set task parameters for a task paradigm, establish a mapping relationship between the task paradigm and cognitive functions, and a mapping relationship between cognitive functions and brain functional areas, so as to map the cognitive functions to brain functional areas. The cognitive function data acquisition module is used to collect cognitive function behavioral data and cognitive function brain imaging data of users when completing the task paradigm in each round of cognitive modulation. The data analysis module is used to analyze the cognitive function behavioral data in each round of cognitive modulation in the task paradigm to obtain behavioral indicators that characterize different cognitive function states, and to analyze the cognitive function brain imaging data to obtain brain imaging features of brain activation patterns related to cognitive function. The regulation module is used to perform cognitive regulation on the user in each round of cognitive regulation in the task paradigm, based on the regulation parameters set according to the user's cognitive aging risk probability judgment result. The evaluation module is used to compare the user's current training results with historical training results in each round of cognitive regulation in the task paradigm to obtain the evaluation result, and dynamically adjust the regulation parameters of the next round of cognitive regulation based on the evaluation result. The system further includes a data recording module, which comprises an individual baseline unit, an individual development unit, a group baseline unit, and a group development unit. The individual baseline unit collects and stores the user's cognitive function behavioral data and cognitive function brain imaging data during the first cognitive modulation session, and establishes an individual-level initial cognitive function baseline model for the user. The individual development unit continuously collects and stores the user's cognitive function behavioral data and cognitive function brain imaging data during each subsequent modulation session, and establishes an individual-level model of cognitive function state changes over time. The group baseline unit constructs a group-level initial cognitive function baseline model based on the individual baseline units of each user. The group development unit constructs a group-level model of cognitive function state changes over time based on the group development units of each user.

2. The system according to claim 1, characterized in that, The cognitive function task module further includes a function mapping unit, which is used to map the task paradigm to one or more cognitive functions. The function mapping unit includes a first mapping subunit, a second mapping subunit, and a fusion subunit. The first mapping subunit is used to evaluate the satisfaction of the task paradigm on each of the cognitive functions to obtain a first mapping relationship; The second mapping subunit is used to obtain text information corresponding to the task paradigm, and determine the frequency of occurrence of each cognitive function in the text information to obtain a second mapping relationship. The fusion subunit is used to fuse the first mapping relationship and the second mapping relationship to realize the mapping between the task paradigm and one or more cognitive functions.

3. The system according to claim 2, characterized in that, The cognitive function task module also includes a brain region mapping unit, which is used to map each cognitive function to one or more brain functional regions. The brain region mapping unit includes a brain activation map processing subunit and a brain region mapping subunit. The brain activation map processing subunit is used to acquire brain activation maps related to the cognitive function, and process the brain activation maps according to a preset activation threshold to obtain an activation status map. The brain region mapping subunit uses a brain region segmentation map to divide the standard space into several brain functional areas, and registers the activation map to the standard space to obtain the number of times the cognitive function is identified as activated in different brain functional areas. Based on the number, the mapping relationship between each cognitive function and one or more brain functional areas is obtained.

4. The system according to claim 1, characterized in that, The system also includes an early warning module, which includes an individual longitudinal comparison unit, a longitudinal early warning unit, a group lateral comparison unit, and a lateral early warning unit. The individual longitudinal comparison unit is used to compare the user's behavioral indicators and brain imaging features in the current round of cognitive regulation with the behavioral indicators and brain imaging features in the user's individual baseline unit to obtain the user's cognitive function change trend and the probability of cognitive aging risk. The longitudinal early warning unit is used to determine that the user has a risk of cognitive aging and to issue an early warning when the user's cognitive changes meet the risk conditions based on the changing trend and the probability of cognitive aging risk. The group horizontal comparison unit is used to compare the behavioral indicators and brain imaging characteristics of the user in the current round of cognitive regulation with the behavioral indicators and brain imaging characteristics in the user group baseline unit, to determine the deviation of the individual from the group, and to determine the probability of cognitive aging risk based on the deviation. The horizontal early warning unit is used to determine that a user has a risk of cognitive aging and to issue an early warning when the user's cognitive changes meet the risk conditions based on the probability of cognitive aging risk.

5. The system according to claim 1, characterized in that, The control module further includes a control parameter setting unit and a cognitive control execution unit. The control parameter setting unit initializes and adjusts the control parameters, and the cognitive control execution unit performs cognitive control according to the determined control parameters. The regulation parameter setting unit is used to determine the stimulation location of cognitive regulation based on the user's current cognitive aging risk index and the mapping relationship between cognitive function and brain functional areas, and to adjust the stimulation intensity and duration within a preset safety range. The stimulation sites are brain functional areas corresponding to high-risk cognitive functions, and the intensity and duration of cognitive regulation increase dynamically with the increase of the probability of cognitive aging risk.

6. The system according to claim 1, characterized in that, The system also includes a neurofeedback module, which is used to reflect the immediate regulatory results of the modulation on the user's neural activity; The neurofeedback module is used to calculate the changes in neural indicators of the user before and after cognitive regulation training, and to map the changes in neural indicators to neural feedback parameters. The neural feedback parameters include the intensity of neural feedback signals, the duration of neural feedback, and the presentation mode of neural feedback, and present the corresponding feedback information to the user.

7. The system according to claim 6, characterized in that, The intensity of the neural feedback signal is the difference in neural indicators of brain functional areas related to cognitive function before and after cognitive modulation; the duration of the neural feedback is dynamically adjusted by the intensity of the neural feedback signal within a safe range; the neural feedback is presented in a single-modal and multi-modal form, wherein the visual mode is the activation status of the brain functional area represented by the visual neural feedback signal, the auditory mode is the volume and frequency adjusted by the auditory neural feedback signal, and the tactile mode is the vibration intensity and frequency of the wristband adjusted by the tactile neural feedback signal.

8. The system according to claim 7, characterized in that, The evaluation module also includes an adjustment unit; The adjustment unit is used to evaluate the adjustment results based on changes in the user's cognitive aging risk and task performance after cognitive regulation and neurofeedback, and to adjust the regulation parameters of subsequent rounds of cognitive regulation tasks based on the evaluation results.

9. The system according to claim 8, characterized in that, The adjustment unit is also used to increase the difficulty or training intensity of the cognitive regulation task when the regulation result meets the preset requirements and the risk of cognitive aging shows a downward trend, and to reduce the task difficulty, extend the task interval or reduce the training volume when the regulation result does not meet the preset requirements or fatigue signs appear.

Images