An intelligent cognitive training method and system based on a portable BCI-AR

Abstract

The present application relates to the technical field of cognitive ability training, in particular to an intelligent cognitive training method and system based on a portable BCI-AR. The intelligent cognitive training method based on the portable BCI-AR comprises the following steps: performing cognitive ability testing according to a preset cognitive scale to obtain a cognitive testing result; matching the cognitive testing result and a cognitive game library to obtain a cognitive testing game and a cognitive training game; performing cognitive training by using the cognitive training game; testing by using the cognitive testing game before and after training respectively, and collecting electroencephalogram signals to obtain testing electroencephalogram signals; evaluating the testing electroencephalogram signals by using a preset neural network to obtain a training evaluation result; and analyzing the training evaluation result and a preset classification evaluation index to obtain a cognitive training evaluation result. The present application is a portable, efficient and accurate intelligent cognitive ability training method.

Description

Technical Field

[0001] This invention relates to the field of cognitive ability training technology, and in particular to an intelligent cognitive training method and system based on portable BCI-AR. Background Technology

[0002] Brain-Computer Interface (BCI) technology establishes a direct information exchange and signal control channel between the brain and external devices, enabling communication and interaction between brain activity and the outside world. This allows for the reading of brain information, control of external devices, and adjustment and control of brain activity. As a novel human-computer interaction technology, BCI detects neural activity in the brain, establishing a direct relationship between invisible neural activity and visible behavioral responses. It translates brain neural activity into motor commands to directly control external devices, thus bypassing the intermediate process of transmission from the brain to muscle tissue or peripheral nerves controlling muscle tissue. This technology is poised to become crucial for understanding the mechanisms of human brain neural information operation, overcoming brain diseases, and assisting human intelligent activities.

[0003] Brain-computer interfaces (BCIs) can also be used in clinical applications to assess changes in cognitive function, such as in cases of cognitive disorders, brain injury, or Alzheimer's disease, to quantify and monitor cognitive abilities. The application of BCI technology in cognitive function assessment provides clinicians and researchers with a new tool to more comprehensively and accurately understand a patient's cognitive status.

[0004] Augmented Reality (AR) technology combines digital information, images, or other virtual content with the real-world environment to create an enhanced perceptual experience. AR uses computer technology to overlay virtual digital information onto the real world, allowing users to see and interact with virtual content within real-world scenes.

[0005] Cognitive training is a method designed to improve an individual's thinking and perceptual abilities. It aims to enhance cognitive functions such as memory, attention, problem-solving, logical reasoning, language skills, and spatial awareness. Cognitive training can be achieved through various activities and exercises, designed to help individuals better process information, solve problems, make decisions, and improve brain function. Using video games for cognitive training is a fun and effective method. However, existing cognitive training methods are often limited by the training environment; users with mobility impairments cannot effectively participate in cognitive training. Furthermore, the evaluation of a user's cognitive abilities relies on facial expression tracking and body movement data collection, which, due to individual differences, leads to inaccurate assessments.

[0006] In the existing technology, there is a lack of an efficient and accurate method for training intelligent cognitive abilities that is easy to carry and use. Summary of the Invention

[0007] To address the technical problems of limited training space and poor training effects in existing cognitive training technologies, this invention provides an intelligent cognitive training method and system based on portable BCI-AR. The technical solution is as follows:

[0008] On the one hand, a portable BCI-AR-based intelligent cognitive training method is provided, which is implemented by an intelligent cognitive training device and includes:

[0009] Cognitive ability tests were conducted based on a pre-set cognitive scale to obtain cognitive test results;

[0010] Based on the cognitive test results and the cognitive game library, cognitive test games and cognitive training games are obtained through matching.

[0011] In an AR environment, cognitive training is conducted using the aforementioned cognitive training game; before and after training, the cognitive testing game is used for testing, and EEG signals are collected to obtain test EEG signals.

[0012] Based on the tested EEG signals, an evaluation is performed using a preset neural network to obtain training evaluation results;

[0013] The cognitive training evaluation results are obtained by analyzing the training evaluation results and the preset classification evaluation indicators.

[0014] Optionally, the step of matching the cognitive test results with a cognitive game library to obtain cognitive test games and cognitive training games includes:

[0015] Based on the cognitive test results, the cognitive domain that needs to be trained is obtained;

[0016] Based on the cognitive domain and the cognitive game library, cognitive test games and cognitive training games are obtained through matching.

[0017] Optionally, the cognitive training game is used for cognitive training; the cognitive testing game is used for testing before and after training, and EEG signals are collected to obtain test EEG signals, including:

[0018] The cognitive test game was used to conduct the test before training, and EEG signals were collected to obtain the test EEG signals before training.

[0019] Periodic cognitive training is performed using the cognitive training game; after training, the cognitive testing game is used for testing, and EEG signals are collected to obtain the post-training test EEG signals.

[0020] Test EEG signals are obtained based on the test EEG signals before training and the test EEG signals after training.

[0021] Optionally, the step of evaluating the test EEG signal through a preset neural network to obtain training evaluation results includes:

[0022] The tested EEG signals are preprocessed to obtain processed EEG signals;

[0023] Feature extraction is performed on the processed EEG signals to obtain an EEG signal feature matrix;

[0024] Based on the EEG signal feature matrix, the training evaluation results are obtained through a preset neural network.

[0025] On the other hand, a portable BCI-AR-based intelligent cognitive training system is provided. This system is applied to a portable BCI-AR-based intelligent cognitive training method. The system includes an EEG acquisition device, electronic devices, and an AR device, wherein:

[0026] The EEG acquisition device is used to acquire EEG signals before and after training to obtain test EEG signals.

[0027] The electronic device is used to match cognitive test results with a cognitive game library to obtain cognitive test games and cognitive training games; to evaluate the test EEG signals through a preset neural network to obtain training evaluation results; and to analyze the training evaluation results with preset classification evaluation indicators to obtain cognitive training evaluation.

[0028] The AR device is used to conduct cognitive ability tests based on a preset cognitive scale and obtain cognitive test results; in the AR environment, cognitive training is conducted using the cognitive training game, and the cognitive test game is used to conduct tests before and after training.

[0029] Optionally, the electronic device is further configured to:

[0030] Based on the cognitive test results, the cognitive domain that needs to be trained is obtained;

[0031] Based on the cognitive domain and the cognitive game library, cognitive test games and cognitive training games are obtained through matching.

[0032] Optionally, the EEG acquisition device is further used for:

[0033] The cognitive test game was used to conduct the test before training, and EEG signals were collected to obtain the test EEG signals before training.

[0034] Periodic cognitive training is performed using the cognitive training game; after training, the cognitive testing game is used for testing, and EEG signals are collected to obtain the post-training test EEG signals.

[0035] Test EEG signals are obtained based on the test EEG signals before training and the test EEG signals after training.

[0036] Optionally, the electronic device is further configured to:

[0037] The tested EEG signals are preprocessed to obtain processed EEG signals;

[0038] Feature extraction is performed on the processed EEG signals to obtain an EEG signal feature matrix;

[0039] Based on the EEG signal feature matrix, the training evaluation results are obtained through a preset neural network.

[0040] On the other hand, an intelligent cognitive training device is provided, comprising: a processor; and a memory storing computer-readable instructions, wherein when the computer-readable instructions are executed by the processor, any one of the methods described above for intelligent cognitive training based on portable BCI-AR is implemented.

[0041] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction is stored in the storage medium, the at least one instruction being loaded and executed by a processor to implement any of the above-described intelligent cognitive training methods based on portable BCI-AR.

[0042] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following:

[0043] This invention proposes a portable BCI-AR-based intelligent cognitive training method. It utilizes AR devices to display training scenarios, leveraging the advantage of AR devices to combine real and virtual scenes, effectively presenting the training content. AR devices are easily deployed without location restrictions, making the system lightweight and portable. This allows for effective cognitive training for users with limited mobility or those who are bedridden, and supports use in various scenarios. This method is widely applicable to cognitive function training across different cognitive domains. Using the difference in EEG signals before and after training as an evaluation indicator addresses the current shortcomings in assessing cognitive training effectiveness. This invention provides a portable, efficient, and accurate intelligent cognitive ability training method. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a flowchart of an intelligent cognitive training method based on portable BCI-AR provided by an embodiment of the present invention;

[0046] Figure 2 This is a block diagram of an intelligent cognitive training system based on portable BCI-AR provided in an embodiment of the present invention;

[0047] Figure 3 This is a schematic diagram of the structure of an intelligent cognitive training device provided in an embodiment of the present invention. Detailed Implementation

[0048] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0049] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0050] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, their intended meanings are consistent. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, their intended meanings are consistent.

[0051] In this embodiment of the invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0052] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0053] This invention provides an intelligent cognitive training method based on portable BCI-AR. This method can be implemented using an intelligent cognitive training device, which can be a terminal or a server. Figure 1 The flowchart shown is for an intelligent cognitive training method based on portable BCI-AR. The processing flow of this method may include the following steps:

[0054] S1. Conduct a cognitive ability test based on a pre-set cognitive scale to obtain the cognitive test results.

[0055] In one feasible implementation, the device used in this invention is a portable brain-computer interface-augmented reality (BCI-AR) device, and the cognitive scales employed involve multiple technical fields. The electronic scales are displayed in the AR device, and users complete these electronic scale tests to check their cognitive abilities.

[0056] Classic cognitive scale tests require the presence of researchers to explain and supervise them. Some scales even require communication and demonstration, which can sometimes increase the psychological burden on the test subjects and affect their ability to complete the cognitive test tasks normally. In addition, the tests require the participation of researchers and cannot be conducted at home.

[0057] Digitizing cognitive scales allows for testing in any setting. Electronic scales enable users to complete tests in a quiet and comfortable environment, further improving the robustness of the collected data. Data such as test time and scores are automatically saved for convenient statistical analysis.

[0058] The Mini-Mental State Examination (MMSE) is a commonly used, simplified, comprehensive cognitive function screening scale and the most frequently used cognitive function assessment tool internationally. This scale includes five dimensions: orientation, memory, attention and calculation, recall, and language. The Montreal Cognitive Assessment (MoCA) is a tool used for rapid screening of abnormal cognitive function. It includes 11 items across eight cognitive domains: visuospatial function, naming, attention, sentence repetition, fluency, abstract thinking, delayed recall, and orientation. The Revised Hasegawa Dementia Scale (HDS-R) is a modified version of the Hasegawa Dementia Scale. The HDS-R evaluates five dimensions: orientation, memory, recent memory, calculation, and general knowledge.

[0059] In the field of spatial cognition, scales such as the Guilford-Zimmerman Spatial Orientation Test (GZSOT), the Perspective Taking Spatial Orientation Test (PTSOT), and the Corsi Block-Tapping Task (CBTT) are primarily used to test spatial cognitive abilities. The GZSOT is a traditional and commonly used scale for testing spatial localization ability. It is developed using the Python graphical interface library tkinter, which is simple and easy to use. The development interface is displayed in full screen to prevent user distraction and provides example questions to help users understand the questions. The PTSOT tests a user's spatial imagination and spatial localization abilities. It contains 12 questions and must be completed within 5 minutes. The score is the percentage of the average error. This scale is also developed using the Python graphical interface library tkinter and packaged as an offline application. The Corsi Block-Tapping Task (CBTT) is used to detect spatial memory and is often used to assess short-term visual-spatial memory.

[0060] In the attention domain, the Schulte Grid Scale can be used to assess attention levels, and this scale has been digitized. The Schulte Grid Scale is a psychometric tool used to assess an individual's attention, concentration, and visual search abilities. In the executive function domain, the Stroop Color Words Test (SCWT) can be used. The SCWT involves components of executive function such as abstract generalization ability, information processing speed, and interference inhibition ability, reflecting the subject's resistance to interference and judgment. It is a commonly used, short method for assessing executive function.

[0061] The various cognitive domain corresponding scales used in this step include, but are not limited to, the above-mentioned scale examples.

[0062] S2. Match cognitive test results with a cognitive game library to obtain cognitive test games and cognitive training games.

[0063] Optionally, based on the cognitive test results and a cognitive game library, cognitive test games and cognitive training games are obtained, including:

[0064] Based on the cognitive test results, the cognitive domains that need to be trained are obtained;

[0065] Based on the cognitive domain and the cognitive game library, cognitive test games and cognitive training games are obtained through matching.

[0066] In one feasible implementation, based on the test results of the scale, the cognitive domains of the cognitive functions that the user needs to train in their current state can be analyzed. The user can then select the corresponding game and set the game difficulty according to the cognitive domain they need to train. The game visuals will be presented to the user through an AR device, allowing the user to conveniently use the system for cognitive training in various scenarios.

[0067] The cognitive game library includes cognitive testing games and cognitive training games; cognitive testing games are a type of game or task designed to assess an individual's cognitive abilities and functions. Different cognitive domains correspond to different cognitive testing games in the cognitive game library, and these games can provide objective measurements of cognitive abilities in the corresponding cognitive domains.

[0068] Cognitive training games are a type of game designed to train and improve users' cognitive functions. Different cognitive domains correspond to different cognitive training games in the cognitive game library. Cognitive training games can improve users' cognitive abilities in the corresponding cognitive domains through repeated practice and challenging tasks.

[0069] City parkour games are used to train attention, requiring users to react quickly to changes, such as sudden rewards or obstacles. Maze games are used to train spatial awareness, training basic spatial orientation and spatial memory. Hidden object search games are used to train memory, requiring users to find specific objects hidden in complex scenes, helping to improve observation and memory skills.

[0070] The various cognitive domain-corresponding training games used in this step include, but are not limited to, the training game examples mentioned above.

[0071] S3. In an AR environment, cognitive training games are used for cognitive training; cognitive test games are used for testing before and after training, and EEG signals are collected to obtain test EEG signals.

[0072] Optionally, cognitive training is conducted using the aforementioned cognitive training game; a cognitive test game is used to conduct tests before and after training, and electroencephalogram (EEG) signals are collected to obtain test EEG signals, including:

[0073] Before training, a cognitive test game was used to conduct the test and collect EEG signals to obtain the test EEG signals before training.

[0074] Cyclical cognitive training is conducted using cognitive training games; after training is completed, cognitive testing games are used to conduct tests and collect EEG signals to obtain post-training test EEG signals.

[0075] Test EEG signals are obtained based on the test EEG signals before and after training.

[0076] In one feasible implementation, this invention uses an EEG cap to collect the user's electroencephalogram (EEG) signals. The electrodes in the EEG cap are non-invasive, and their placement follows the international standard Lead 10-20 configuration. The user can place the electrodes and wear the brain-computer interface with the assistance of family members. To improve signal acquisition quality, EEG signals from different brain regions can be collected for different cognitive domains, making the collected EEG signals more targeted. The EEG cap collects EEG signals before and after training and sends them to electronic devices for further processing.

[0077] S4. Based on the tested EEG signals, the training evaluation results are obtained through a preset neural network.

[0078] Optionally, based on the tested EEG signals, an evaluation is performed through a pre-set neural network to obtain training evaluation results, including:

[0079] Preprocessing of the test EEG signals yields processed EEG signals;

[0080] Feature extraction is performed on the processed EEG signals to obtain the EEG signal feature matrix;

[0081] Based on the EEG signal feature matrix, the training evaluation results are obtained through a pre-set neural network.

[0082] In one feasible implementation, the main preprocessing methods in this invention include removing drift data, filtering, removing artifacts, and baseline correction.

[0083] Drift refers to slow fluctuations in EEG signals caused by various reasons, such as breathing, heartbeat, and electrode movement. These fluctuations are not related to the EEG activity of interest and therefore need to be removed to improve signal quality and accuracy.

[0084] Filtering includes concave filtering and bandpass filtering. Concave filtering aims to remove 50Hz mains interference. Bandpass filtering aims to select the frequency band required for the study. In EEG research in the cognitive domain, the commonly used bandpass filtering range is 1Hz to 50Hz. This frequency range is widely used in most cognitive tasks and covers most EEG activity related to cognitive function. Therefore, a 1-50Hz bandpass filter is used to filter EEG signals.

[0085] Artifacts can be caused by various factors, such as poor electrode contact, motion artifacts, power line interference, and electromyographic interference. Independent component analysis (ICA) can be used to remove interfering components from EEG signals and improve the signal-to-noise ratio.

[0086] Baseline correction aims to adjust the overall bias of EEG signals, bringing the signal mean within a suitable range. EEG signals may exhibit DC bias, meaning the signal is shifted upwards or downwards, causing the signal mean to deviate from zero. Baseline correction aims to eliminate this bias, bringing the signal mean closer to zero for subsequent analysis and interpretation.

[0087] The feature extraction method employed in this invention utilizes Mutual Information (MI) to extract coupling features from electroencephalogram (EEG) signals. MI is used to analyze the coupling direction of binary neural groups. This method is a nonlinear coupling feature analysis approach for EEG signals. Mutual Information algorithms are widely used in feature extraction to reveal the correlation and information transmission between different regions in EEG signals.

[0088] Mutual information is commonly used to measure the interdependence between different brain regions. By calculating the mutual information of EEG signals, it is possible to reveal information transmission, functional connectivity, and potential nonlinear relationships between different brain regions. The mutual information matrix (MI) method can analyze the coupling relationship between signals from two different brain regions and has strong robustness. In MI, the coupling strength between signals X and X itself is generally not considered, and after the EEG signal is divided into 7 frequency bands, each frequency band has a different MI matrix. Finally, after feature extraction, several EEG signal coupling features can be obtained. The resulting one-dimensional vector is then used as the input to a neural network classifier.

[0089] The approach to EEG signal assessment involves using data mining, deep learning, and neural networks to perform binary classification of EEG signals before and after cognitive training. If the classification is effective, it indicates a high degree of differentiation between the pre- and post-test EEG signals, suggesting a significant change in the user's cognitive abilities before and after training.

[0090] The EEG signals before and after training are classified using a neural network. The coupled features obtained from the above feature extraction are used as input to the classifier to build a classification model. The data is divided into training and test sets in a ratio of 9:1. The parameters in the model are optimized using a grid search method. The training set is trained using a method similar to K-fold cross-validation, and the test set is used to make predictions and evaluate the performance.

[0091] To prevent overfitting and improve generalization ability, a K-fold cross-validation-like approach was adopted. The training set was divided into 5 folds, and training was performed 5 times. In each training, the model learned 80% of the data and predicted 20% of the data. The final evaluation index was obtained by averaging the 20% prediction results of the 5 models and the test set results.

[0092] S5. Analyze the training evaluation results and the preset classification evaluation indicators to obtain the cognitive training evaluation results.

[0093] In one feasible implementation, the present invention uses several commonly used classification evaluation metrics to evaluate the classification effect. Common evaluation metrics for measuring the performance of classification models include accuracy, precision, recall, F1 score (F1), ROC curve (Receiver Operating Characteristic Curve, ROC), and area under the ROC curve (AUC). Among these, accuracy is used as the evaluation metric for cognitive training effect.

[0094] This invention proposes a portable BCI-AR-based intelligent cognitive training method. It utilizes AR devices to display training scenarios, leveraging the advantage of AR devices to combine real and virtual scenes, effectively presenting the training content. AR devices are easily deployed without location restrictions, making the system lightweight and portable. This allows for effective cognitive training for users with limited mobility or those who are bedridden, and supports use in various scenarios. This method is widely applicable to cognitive function training across different cognitive domains. Using the difference in EEG signals before and after training as an evaluation indicator addresses the current shortcomings in assessing cognitive training effectiveness. This invention provides a portable, efficient, and accurate intelligent cognitive ability training method.

[0095] Figure 2 This is a block diagram illustrating an intelligent cognitive training system based on a portable BCI-AR according to an exemplary embodiment. The system is used for an intelligent cognitive training method based on a portable BCI-AR. (Refer to...) Figure 2 The system includes an EEG acquisition device 210, an electronic device 220, and an AR device 230. For ease of explanation, Figure 2 Only the main components of this end-to-end visualization system 200 are shown:

[0096] EEG acquisition device 210 is used to acquire EEG signals before and after training to obtain test EEG signals;

[0097] Electronic device 220 is used to match cognitive test results with a cognitive game library to obtain cognitive test games and cognitive training games; to evaluate training results through a preset neural network based on test EEG signals; and to analyze training evaluation results and preset classification evaluation indicators to obtain cognitive training evaluation.

[0098] AR device 230 is used to conduct cognitive ability tests based on a preset cognitive scale and obtain cognitive test results; in the AR environment, cognitive training games are used for cognitive training, and cognitive test games are used for testing before and after training.

[0099] Optionally, the electronic device 220 is further used for:

[0100] Based on the cognitive test results, the cognitive domains that need to be trained are obtained;

[0101] Based on the cognitive domain and the cognitive game library, cognitive test games and cognitive training games are obtained through matching.

[0102] Optionally, the EEG acquisition device 210 is further used for:

[0103] Before training, a cognitive test game was used to conduct the test and collect EEG signals to obtain the test EEG signals before training.

[0104] Cyclical cognitive training is conducted using cognitive training games; after training is completed, cognitive testing games are used to conduct tests and collect EEG signals to obtain post-training test EEG signals.

[0105] Test EEG signals are obtained based on the test EEG signals before and after training.

[0106] Optionally, the electronic device 220 is further used for:

[0107] Preprocessing of the test EEG signals yields processed EEG signals;

[0108] Feature extraction is performed on the processed EEG signals to obtain the EEG signal feature matrix;

[0109] Based on the EEG signal feature matrix, the training evaluation results are obtained through a pre-set neural network.

[0110] This invention proposes a portable BCI-AR-based intelligent cognitive training method. It utilizes AR devices to display training scenarios, leveraging the advantage of AR devices to combine real and virtual scenes, effectively presenting the training content. AR devices are easily deployed without location restrictions, making the system lightweight and portable. This allows for effective cognitive training for users with limited mobility or those who are bedridden, and supports use in various scenarios. This method is widely applicable to cognitive function training across different cognitive domains. Using the difference in EEG signals before and after training as an evaluation indicator addresses the current shortcomings in assessing cognitive training effectiveness. This invention provides a portable, efficient, and accurate intelligent cognitive ability training method.

[0111] Figure 3 This is a schematic diagram of the structure of an intelligent cognitive training device provided in an embodiment of the present invention, as shown below. Figure 3As shown, the intelligent cognitive training device may include the above-mentioned Figure 3 The illustrated intelligent cognitive training system is based on portable BCI-AR. Optionally, the intelligent cognitive training device 310 may include a processor 2001.

[0112] Optionally, the intelligent cognitive training device 310 may also include a memory 2002 and a transceiver 2003.

[0113] The processor 2001, memory 2002, and transceiver 2003 can be connected via a communication bus.

[0114] The following is combined Figure 3 A detailed introduction to each component of the intelligent cognitive training device 310:

[0115] The processor 2001 is the control center of the intelligent cognitive training device 310. It can be a single processor or a collective term for multiple processing elements. For example, the processor 2001 can be one or more central processing units (CPUs), application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0116] Optionally, the processor 2001 can perform various functions of the intelligent cognitive training device 310 by running or executing software programs stored in the memory 2002 and calling data stored in the memory 2002.

[0117] In a specific implementation, as one example, the processor 2001 may include one or more CPUs, for example... Figure 3 CPU0 and CPU1 are shown in the diagram.

[0118] In a specific implementation, as one example, the intelligent cognitive training device 310 may also include multiple processors, for example... Figure 3 The processors 2001 and 2004 are shown. Each of these processors can be a single-core processor or a multi-core processor. Here, "processor" can refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0119] The memory 2002 is used to store the software program that executes the present invention, and is controlled by the processor 2001 to execute it. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0120] Optionally, the memory 2002 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 2002 may be integrated with the processor 2001 or exist independently, and may be connected via the interface circuit of the intelligent cognitive training device 310. Figure 3 (Not shown in the figure) is coupled to processor 2001, and the embodiments of the present invention do not specifically limit this.

[0121] The transceiver 2003 is used to communicate with network devices or with terminal devices.

[0122] Alternatively, transceiver 2003 may include a receiver and a transmitter. Figure 3 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the sending function.

[0123] Optionally, the transceiver 2003 can be integrated with the processor 2001, or it can exist independently and be connected to the interface circuit of the intelligent cognitive training device 310. Figure 3 (Not shown in the figure) is coupled to processor 2001, and the embodiments of the present invention do not specifically limit this.

[0124] It should be noted that, Figure 3 The structure of the intelligent cognitive training device 310 shown does not constitute a limitation on the router. Actual knowledge structure recognition devices may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0125] Furthermore, the technical effects of the intelligent cognitive training device 310 can be referenced from the technical effects of the intelligent cognitive training method based on portable BCI-AR described in the above method embodiments, and will not be repeated here.

[0126] It should be understood that the processor 2001 in this embodiment of the invention can be a central processing unit (CPU), or it can be 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. The general-purpose processor can be a microprocessor or any conventional processor.

[0127] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0128] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable system. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0129] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0130] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0131] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0132] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0133] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, systems, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0134] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or units may be electrical, mechanical, or other forms.

[0135] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0136] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0137] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0138] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for intelligent cognitive training based on portable BCI-AR, characterized in that, The method includes: Cognitive ability tests were conducted based on a pre-set cognitive scale to obtain cognitive test results; Based on the cognitive test results and the cognitive game library, cognitive test games and cognitive training games are obtained through matching, including: Based on the cognitive test results, the cognitive domain that needs to be trained is obtained; Based on the cognitive domain and the cognitive game library, cognitive test games and cognitive training games are obtained through matching. In an AR environment, cognitive training is conducted using the aforementioned cognitive training game; before and after training, the cognitive testing game is used for testing, and electroencephalogram (EEG) signals are collected to obtain test EEG signals, including: The cognitive test game was used to conduct the test before training, and EEG signals were collected to obtain the test EEG signals before training. Periodic cognitive training is performed using the cognitive training game; after training, the cognitive testing game is used for testing, and EEG signals are collected to obtain the post-training test EEG signals. The test EEG signal is obtained based on the test EEG signal before training and the test EEG signal after training; Based on the tested EEG signals, mutual information is used to extract the coupling features of the EEG signals, which are then evaluated through a preset neural network to obtain training evaluation results. The cognitive training evaluation results are obtained by analyzing the training evaluation results and the preset classification evaluation indicators.

2. The intelligent cognitive training method based on portable BCI-AR according to claim 1, characterized in that, The step of evaluating the test EEG signals through a preset neural network to obtain training evaluation results includes: The tested EEG signals are preprocessed to obtain processed EEG signals; Feature extraction is performed on the processed EEG signals to obtain an EEG signal feature matrix; Based on the EEG signal feature matrix, the training evaluation results are obtained through a preset neural network.

3. A portable BCI-AR-based intelligent cognitive training system, characterized in that, The system includes an EEG acquisition device, electronic devices, and an AR device, wherein: The EEG acquisition device is used to acquire EEG signals before and after training to obtain test EEG signals. The electronic device is used to match cognitive test results with a cognitive game library to obtain cognitive test games and cognitive training games; to extract coupling features of the EEG signals using mutual information based on the test EEG signals, and to evaluate them through a preset neural network to obtain training evaluation results; and to analyze the training evaluation results and preset classification evaluation indicators to obtain cognitive training evaluation. The AR device is used to perform cognitive ability tests based on a preset cognitive scale and obtain cognitive test results; in the AR environment, cognitive training is performed using the cognitive training game, and the cognitive test game is used to perform tests before and after training. The electronic device is further used for: Based on the cognitive test results, the cognitive domain that needs to be trained is obtained; Based on the cognitive domain and the cognitive game library, cognitive test games and cognitive training games are obtained through matching. The electroencephalogram (EEG) acquisition device is further used for: Before training, a cognitive test game was used to conduct the test and collect EEG signals to obtain the test EEG signals before training. Periodic cognitive training is performed using the cognitive training game; after training, the cognitive testing game is used for testing, and EEG signals are collected to obtain the post-training test EEG signals. Test EEG signals are obtained based on the test EEG signals before training and the test EEG signals after training.

4. The intelligent cognitive training system based on portable BCI-AR according to claim 3, characterized in that, The electronic device is further used for: The tested EEG signals are preprocessed to obtain processed EEG signals; Feature extraction is performed on the processed EEG signals to obtain an EEG signal feature matrix; Based on the EEG signal feature matrix, the training evaluation results are obtained through a preset neural network.

5. An intelligent cognitive training device, characterized in that, The intelligent cognitive training device includes: processor; A memory storing computer-readable instructions that, when executed by the processor, implement the method as described in any one of claims 1 to 2.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains program code that can be invoked by a processor to execute the method as described in any one of claims 1 to 2.

Images