WO2020037332A2

WO2020037332A2 - Systems and methods for personalized learning and attention evaluation through neuro-feedback training

Info

Publication number: WO2020037332A2
Application number: PCT/US2019/054057
Authority: WO
Inventors: Max NEWLON; Dongsheng SUN; Bicheng HAN; Hui Zheng; Xiang Yu; Zhoayi YANG; Tianhe Wang; Juewei DONG; Si Li; Lawrence FRANCHINI; Joshua VARELA; Disi A; Yue Sun
Original assignee: Shenzhen Xinliu Technology Co., Ltd.; BrainCo Inc.
Priority date: 2018-08-01
Filing date: 2019-10-01
Publication date: 2020-02-20
Also published as: CN109009171B; WO2020037332A3; WO2020024688A1; BR112021001717A2; CN109009171A

Abstract

A method and system for neuro-feedback training are disclosed. The method may include detecting a brainwave signal associated with an electrical activity of a brain of a learner; analyzing a characteristic of the brainwave signal; generating an attention score indicative of a level of engagement of the learner; determining a performance score of the learner; adjusting the stimulus based on a combination of the attention score and the performance score to personalize the educational experience of the learner. An attention evaluation method and system are disclosed. The method comprises obtaining answer data when a user performs a preset attention game and may acquire corresponding EEG data through a wearable device. The answer data and the EEG data may be processed, so that corresponding answer scores and EEG scores can be obtained. The answer scores and the EEG scores may be substituted into an equation to obtain attention scores.

Description

SYSTEMS AND METHODS FOR PERSONALIZED LEARNING AND ATTENTION EVALUATION THROUGH NEURO-FEEDBACK TRAINING

RELATED APPLICATION

[0001] This application claims priority to CN Application No. 201810868482.0, filed August 1, 2018, the contents of which are hereby incorporated by reference in its entirety.

TECHNICAL FIELD

[0002] The present disclosure relates generally to a brain-machine interface, and more particularly, to neuro-feedback training systems and methods for personalized learning and teaching experience using biometric data of a user.

BACKGROUND

[0003] A human brain consists of billions of neurons that are densely interconnected via synapses, which act as gateways of inhibitory or excitatory activity. When thousands of neurons fire in sync, they generate an electrical field which is strong enough to spread through tissue, bone, and skull. Eventually, it can be measured on the head surface through

Electroencephalography (EEG). The electrical signals from human brains may vary based on the activity being performed by a person. For example, in the resting state, the neurons fire much slower than compared to when the person is actively engaged in a mental activity, or a conversation, or a learning task. Traditionally, researchers and medical doctors have used EEG devices to measure and characterize the electrical signals from the brain. Current methods of evaluating engagement in the classroom rely on teacher intuition, survey data, or in research settings eye-tracking hardware.

[0004] In academic setups such as a classroom, student engagement may not be reliably determined, partly because the level of engagement is hard to quantify beyond biased surveys and teacher intuition. Although qualitative, surveys indicate that the average active student engagement may be as low as 50% in some classroom setups. Research has also shown that a small percentage increase in student engagement may result in 6-8% improvement in reading and math scores. Therefore, student engagement may be an important factor for improving the education experience.

[0005] Teachers often encounter the challenge of creating and maintaining high levels of student engagement in a classroom. Tills is because human brains react differently to learning stimuli, and people have their own style of learning such as auditory, visual, kinesthetic, linguistic, logical-mathematical, and the like. As a result, even in a classroom full of equally intelligent people, a lesson plan that works successfully for some learners may not work as well for others. Additionally, teachers may not appreciate the cognitive workload on a student because while some students in the classroom may find a learning task underwhelming, the others may find the same task overwhelming. Therefore, it may be desirable to personalize the education experience based on the student engagement and cognitive workload.

[0006] Moreover, to enhance the education experience for learners as well as educators, not only is it important to quantify student engagement, it may also be beneficial to quantify student engagement in real-time, providing teachers and students with an index that may help predict successful strategies.

[0007] The disclosed neuro-feedback training systems and methods are directed to mitigating or overcoming one or more of the problems set forth above and/or other problems in the prior art

SUMMARY

[0008] One aspect of the present disclosure is directed to a processor-implemented method of personalizing an educational experience based on neuro-feedback training. The method may comprise processor-implemented steps comprising detecting a brainwave signal of a learner generated in response to a stimulus, analyzing at least one characteristic of the brainwave signal, generating a cognitive workload index indicative of an amount of effort applied by the learner to respond to the stimulus, based on the analysis, and adjusting the stimulus based on the generated cognitive workload index to personalize the educational experience.

[0009] The method may further comprise updating in real-time, the cognitive workload index in a database associated with the processor, and adjusting the stimulus based on the updated cognitive workload index, wherein the stimulus comprises an educational task. The method may also include generating a personalized learner profile including information associated with a learner; and updating the personalized learner profile based on the updated cognitive workload index and the adjusted stimulus.

[0010] Analyzing the at least one characteristic of the brainwave signal may comprise analyzing one of a waveform, a frequency, a frequency distribution, an amplitude, and a periodicity of the brainwave signal. The method may also include transmitting by the processor via a communication network, the updated cognitive workload index to at least one of an online learning platform, an offline learning program, and an educator

[0011] Generating the cognitive workload index may comprise determining the cognitive workload index using an artificial intelligence (AI) based algorithm. Adjusting the stimulus may comprise adjusting at least one of a difficulty, a pace, and a sequence of a plurality of educational tasks presented to the learner. The brainwave signal may be indicative of an electrical activity of a brain of the learner, and may comprise an electroencephalography (EEG) signal. The processor may comprise a sensor disposed on a wearable device and configured to receive and detect the brainwave signal, and the wearable device may comprise a headband worn by the learner.

[0012] Another aspect of the present disclosure is directed to a processor-implemented method of personalizing an educational experience based on neuro-feedback training. The method may comprise processor-implemented steps comprising detecting a brainwave signal of a learner generated in response to a stimulus, analyzing at least one characteristic of the brainwave signal, generating, based on the analysis, an attention score indicative of a level of engagement of the learner, determining a performance score of the learner based on the response to the stimulus, and adjusting the stimulus based on a combination of the attention score and the performance score to personalize the educational experience of the learner.

[0013] The method may further comprise updating in real-time, the attention score and the performance score in a database associated with the processor, and adjusting the stimulus based on the updated attention score and the updated performance score, wherein the stimulus comprises an educational task. The method may further include generating a personalized learner profile including information associated with the learner; and updating the personalized learner profile based on the updated attention score, the updated performance score, and the adjusted stimulus.

[0014] Analyzing the at least one characteristic of the brainwave signal comprises analyzing one of a waveform, a frequency, a frequency distribution, an amplitude, and a periodicity of the brainwave signal. The method may further include transmitting by the processor via a communication network, the updated attention score and the updated performance score to at least one of an online learning platform, an offline learning program, and an educator.

[0015] Transmitting the updated attention score and the updated performance score may comprise wirelessly communicating with a device associated with at least one of the online learning platform, the offline learning program, and the educator. Generating the attention score comprises determining the attention score using an AI based algorithm.

[0016] Yet another aspect of the present disclosure is directed to a neuro-feedback training system. The system may comprise a sensor coupled with a processor. The processor may be configured to detect a brainwave signal of a learner generated in response to a stimulus, analyze at least one characteristic of the brainwave signal, generate, based on the analysis, an attention score indicative of a level of engagement of the learner, determine a performance score of the learner based on the response to the stimulus, and adjust the stimulus based on a combination of the attention score and the performance score to personalize the educational experience of the learner. The stimulus may comprise a plurality of educational tasks. The brainwave signal may be indicative of an electrical activity of a brain of the learner, and may comprise an

electroencephalography (EEG) signal. The processor may comprise a sensor disposed on a wearable device and configured to receive and detect the brainwave signal, and the wearable device may comprise a headband worn by the learner. The at least one characteristic of the brainwave signal comprises one of a waveform, a frequency, a frequency distribution, an amplitude, and a periodicity of the brainwave signal.

[0617] Yet another aspect of the present disclosure is directed to a non -transitory computer- readable medium storing instructions which, when executed, cause one or more processors to perfor a method for neuro-feedback training. The method may comprise detecting a brainwave signal of a learner generated in response to a stimulus, analyzing at least one characteristic of the brainwave signal, generating, based on the analysis, an attention score indicative of a level of engagement of the learner, determining a performance score of the learner based on the response to the stimulus, and adjusting the stimulus based on a combination of the attention score and the performance score to personalize the educational experience of the learner.

[0018] Another aspect of the present disclosure relates to the technical field of attention evaluation, in particular to an attention evaluation method, an attention evaluation system and a computer readable storage medium.

[0019] Attention is the ability of people to point and focus on some things, and is directed and concentrated to a certain object by psychological activities, and is a common psychological feature which is accompanied with psychological processes such as sensory perception, memory, thinking, imagination and the like. According to the attention dimension, the attention can be classified into the following five categories: a selective attention, an alternate attention, a sustained attention, a divided attention, and an attention breadth. Attention has important correlation and influence on many aspects of users, for example, attention levels of children affect their cognitive development, therefore, a lot of attention games can be used to test the attention of the user, so that the attention of the user can he developed and promoted in a targeted manner. However, because the evaluation of attention is mainly based on some related attention games, the evaluation result is only based on the scoring rule of the game, and therefore, the accuracy of the evaluation results is low.

[0020] Some embodiments of the present disclosure are directed to providing an attention evaluation method and system and a computer readable storage medium, and aims to improve the accuracy of attention evaluation results. In order to improve the accuracy of the attention evaluation results, the disclosed attention evaluation method is applied to attention evaluation system, wherein the attention evaluation system comprises an attention evaluation terminal and an intelligent wearable device

[0021] The attention evaluation method may comprise acquiring answer data when a user performs a preset attention game, and acquires corresponding brain wave EEG data through the intelligent wearable device; processing the answer data and the EEG data to obtain

corresponding answer scores and EEG scores. According to the answer score, the EEG score and the preset multivariable regression equation, an attention score value may be obtained. The general formula of the preset multi -variable regression equation is: Z = aX + bY, where Z is an attention score, x is an answer score, y is an EEG score, and a and b are corresponding optimal coefficients, respectively.

[0022] The preset attention game may include persistent attention games and other attention games, and the other attention games comprise a selective attention game, a conversion attention game, a dispersibility attention game and an attention breadth game, the attention evaluation terminal acquires answer data when an user performs a preset attention game, and acquires corresponding brain wave EEG data through the intelligent wearable device the method comprises the following steps:

[0023] The attention evaluation ter inal respectively acquires first answer data and second answer data when the user performs continuous attention games and other attention games, and respectively acquiring corresponding first EEG data and second EEG data through the intelligent wearable device; processing the answer data and the EEG data to obtain corresponding answer scores and EEG scores the method comprises the following steps: processing the first answer data, the first EEG data, the second answer data and the second EEG data respectively, and obtaining a corresponding first answer score, a first EEG score, a second answer score and a second EEG score; and the step of obtaining the attention value according to the ans wer score, the EEG score and the preset multivariable regression equation comprises the following steps: first and second answer scores according to the first answer score, the first EEG score and the second answer score, a second EEG sub-value and a preset multi-variable regression equation to obtain a fractional value of the continuous attention game and a fractional value of other attention;

[0024] Optionally, the attention evaluation method further comprises: acquiring first evaluation answer data and first self-scores when an evaluation person performs the continuous attention game, and acquiring corresponding first evaluation EEG data through the intelligent wearable device; preprocessing the first evaluation answer data and the first evaluation EEG data to obtain corresponding first scores and second scores; performing statistical estimation on the first and second scores to obtain a corresponding first distribution curve and a second distribution curve; obtaining a continuous attention evaluation answer score according to the first score and the first distribution curve, and obtaining a continuous attention evaluation EEG score according to the second score and the second distribution curve.

[0025] The first multivariable regression equation is constructed according to the continuous attention evaluation answer score, the continuous attention evaluation EEG score and the first self-score, and obtaining a first optimal coefficient of the first multi variable regression equation through a normal equation, substituting the first optimal coefficient into the first multivariable regression equation to obtain a multivariable regression equation of the continuous attention of the preset multivariable regression equation;

[0026] Optionally, the attention evaluation method further comprises: acquiring second evaluation answer data and second self-scores when the evaluation person performs the other attention games, and acquiring corresponding second evaluation EEG data through the intelligent wearable device; preprocessing the second evaluation answer data and the second evaluation EEG data to obtain corresponding third and fourth scores; performing statistical estimation on the third sub- value and the fourth sub- value to obtain a corresponding third distribution curve and a fourth distribution curve; obtaining evaluation answer scores of other attention according to the third distribution curve and the third distribution curve, and obtaining evaluation EEG scores of other attention according to the fourth distribution curve and the fourth distribution curve; establishing a second multivariable regression equation according to the evaluation answer scores of the other attention, the evaluation EEG scores of other attention and the second self-score, and obtaining a second optimal coefficient of the second multivariable regression equation through a normal equation, substituting the second optimal coefficient into the second multivariable regression equation to obtain a multivariable regression equation of other attention of the preset multivariable regression equation;

[0027] Optionally, the processing is performed on the first answer data, the first EEG data, the second answer data and the second EEG data respectively, and obtaining a corresponding first answer score, a first EEG score, a second answer score and a second EEG score the method comprises the following steps: preprocessing the first answer data, the first EEG data, the second answer data and the second EEG data respectively, and a fifth sub-value, a sixth sub-value, a seventh sub-value and an eighth sub-value of the corresponding fifth sub-value, sixth sub-value, seventh sub-value and eighth sub-valise are obtained; obtaining a first curve lower area corresponding to the fifth score and a first total area between the first distribution curve and the cross axis according to the fifth score and the first distribution curve by integrating, and recording the percentage value of the lower area of the first curve and the first total area as a first answer score; obtaining a second curve lower area corresponding to the sixth sub-value and a second total area between the second distribution curve and the horizontal axis according to the sixth sub-value and the second distribution curve, and recording the percentage value of the lower area of the second curve and the second total area as first EEG scores; obtaining a third curve lower area corresponding to the seventh sub- value and a third total area between the third distribution curve and the horizontal axis according to the seventh sub-value and the third distribution curve, and recording the percentage value of the lower area of the third curve and the third total area as a second answer score; obtaining the lower area of the fourth curve corresponding to the eighth value and the fourth total area between the fourth distribution curve and the horizontal axis according to the eighth and fourth distribution curves, and recording the percentage value of the lower area of the fourth curve and the fourth total area as second EEG scores.

[0028] Optionally, according to the first answer score, the first EEG score and the second answer score, a second EEG score and a preset multivariable regression equation to obtain the score of the follow-up attention game and the score of other attention; the method comprises the following steps; obtaining the fractional value of the follow-up attention game according to the first answer score, the first EEG score and the multivariable regression equation of the continuous attention in the preset multivariable regression equation, and obtaining the fractional values of other attention according to the second answer score, the second EEG score and the multi-variable regression equation of other attention in the preset multivariable regression equation.

[0029] Optionally, the first answer data and the first evaluation answer data comprise the maximum continuous answer correct number and the answer total number, wherein the second answer data and the second evaluation answer data comprise answer correct numbers and answer errors. In addition, in order to achieve the aim, the invention further provides an attention evaluation system. The attention evaluation system comprises an attention evaluation terminal and an intelligent wearable device, and further comprises a memory, a processor, and an attention evaluation program stored on the memory and capable of running on the processor, the attention evaluation program is executed by the processor to realize the attention evaluation method as described above.

[0030] In addition, in order to achieve the aim, the invention further provides a computer readable storage medium, the attention evaluation program is stored on the computer readable storage medium; the attention evaluation program is executed by the processor to realize the attention evaluation method as described above.

[0031] The invention provides an attention evaluation method and system and a computer readable storage technology. The attention evaluation method is applied to an attention evaluation system. The attention evaluation system comprises an attention evaluation terminal and an intelligent wearable device. The attention evaluation terminal acquires answer data when the user performs a preset attention game, and obtains corresponding EEG data through the intelligent wearable device; then, the answer data and the EEG data are processed, so that corresponding answer scores and EEG scores are obtained; finally, the answer scores and the EEG scores are substituted into a preset multi-variable regression equation, so that attention scores can be obtained; According to the method, EEG data are acquired by using a brain computer interface technology, answer data and EEG data are combined, and corresponding answer scores and EEG scores are obtained through processing, and the scores of the attention are calculated through the attention scores obtained through early -stage optimization and the multi-variable regression equation between the answer scores and the EEG scores, and compared with the prior art evaluation and scoring are carried out only in a single mode according to the scoring rule of the game, the accuracy of the attention evaluation result can be improved, and the accuracy of the attention evaluation result can be improved.

BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Fig. 1 is a schematic diagram illustrating an exemplary neuro-feedback training system 100 for personalizing an educational experience, consistent with embodiments of the present disclosure.

[0033] Fig. 2 is a block diagram of an exemplary neuro-feedback training system 200, consistent with embodiments of the present disclosure.

[0034] Fig. 3 is a schematic diagram illustrating an exemplary headband for detecting brainwave signal(s), consistent with embodiments of the present disclosure.

[0035] Fig. 4 is a schematic diagram illustrating an exemplary neuro-feedback system 400 in an academic set-up, consistent with embodiments of the present disclosure.

[0036] Fig. 5 is a schematic diagram illustrating an exemplary user-interface display of a neuro feedback system shown in Fig. 4, consistent with embodiments of the present disclosure.

[0037] Fig. 6 is a schematic diagram illustrating an exemplary user-interface of a neuro- feedback system shown in Fig. 4, consistent with embodiments of the present disclosure.

[0038] Fig. 7 is a flowchart of an exemplary method for neuro-feedback training for

personalizing an educational experience of a learner, consistent with embodiments of the present disclosure.

[0039] Fig. 8 is a flowchart of an exemplary method for neuro-feedback training for

[0040] Fig. 9 is a schematic structural diagram of an exemplary ter inal of a hardware running environment, consistent with embodiments of the present disclosure.

[0041] Fig. 10 is a flowchart of a first embodiment of an attention evaluation method, consistent with embodiments of the present disclosure.

[0042] Fig. 11 is a flowchart of a second embodiment of an attention evaluation method, consistent with embodiments of the present disclosure.

[0043] Fig. 12 is a flowchart of a third embodiment of an attention evaluation method, consistent with embodiments of the present disclosure. [0044] Fig. 13 is a schematic illustration of a first distribution curve, consistent with

embodiments of the present disclosure.

[0045] Fig. 14 is a flowchart of a fourth embodiment of an attention evaluation method, consistent with embodiments of the present disclosure.

[0046] The following detailed description refers to the accompanying drawings. Wherever possible, the same reference numbers are used in the drawings and the following description to refer to the same or similar parts. While several illustrative embodiments are described herein, modifications, adaptations and other implementations are possible. For example, substitutions, additions, or modifications may be made to the components and steps illustrated in the drawings, and the illustrative methods described herein may be modified by substituting, reordering, removing, or adding steps to the disclosed methods. Accordingly, the following detailed description is not limited to the disclosed embodiments and examples. Instead, the proper scope of the invention is defined by the appended claims.

[0647] Relative dimensions of components in drawings may be exaggerated for clarity. Within the following description of drawings, the same or like reference numbers refer to the same or like components or entities, and only the differences with respect to the individual embodiments are described. As used herein, unless specifically stated otherwise, the term“or” encompasses all possible combinations, except where infeasible. For example, if it is stated that a component may include A or B, then, unless specifically stated otherwise or infeasible, the component may include A, or B, or A and B. As a second example, if it is stated that a component may include A, B, or C, then, unless specifically stated otherwise or infeasible, the component may include A, or B, or C, or A and B, or A and C, or B and C, or A and B and C.

[0048] This disclosure is generally directed to systems and methods for neuro-feedback training. In the disclosed embodiments, the systems collect and analyze brainwave signals of a human subject (i.e., a user of the neuro -feedback training system) in some embodiments, the human subject using the neuro-feedback training system may also be referred to as a learner or a trainee. Based on the user profile and the purpose of the neuro-feedback training, the method may include detecting a brainwave signal associated with an electrical activity of a brain of a learner wherein the brainwave signal is generated in response to a stimulus. At least one characteristic of the brainwave signal may be analyzed and based on the analysis, an attention score indicative of a level of engagement of the learner may be generated. The method may include determining a performance score of the learner based on the response to the stimulus, and adjusting the stimulus based on a combination of the attention score and the performance score to personalize the educational experience of the learner. The method may further include generating, by the processor based on the analysis, a cognitive workload index indicative of an amount of effort applied by the learner to respond to the stimulus.

[0049] Reference is now made to Fig. 1, which is a schematic diagram illustrating an exemplary neuro-feedback training system 100 for personalizing an educational experience, consistent with embodiments of the present disclosure. Neuro-feedback training system 100 may include a user 105 wearing a headband 1 10, one or more terminals 120, one or more cloud servers 130. It is to be appreciated that other relevant components may be added to or omitted from neuro-feedback training system 100, as appropriate.

[0050] In some embodiments, user 105 may comprise a learner, a student, a trainee, an evaluates, a human subject, and the like. In some embodiments, user 105 may comprise a group of users, for example, a group of students in a classroom, each wearing headband 110.

[0051] In some embodiments, headband 110 may be configured to detect and/or measure at least one brainwave signal of user 105. Consistent with the disclosed embodiments, headband 1 10 may stream or otherwise transmit the measured brainwave signal(s) to terminal 120 or cloud server 130 in real-time. Both, terminal 120 and cloud server 130 may be configured to store and/or process the measured brainwave signal(s). One or more headbands 110 may he stored in a specific room or on a mobile cart. In some embodiments, one or more headbands 110 may be brought into a classroom, a school, or a test facility, and students can put them on and start learning a software or perform a task.

[0052] Terminal 120, in some embodiments, may be implemented as an electronic device with computing capabilities, such as including, but is not limited to, a desktop computer 120A, a mobile phone 12GB, or a laptop 120C. In some embodiments, terminal 120 may include one or more of a wearable devices (e.g., a smart watch), a personal digital assistant (PDA), a remote controller, exercise equipment, an e-book reader, a MPEG (Moving Picture Experts Group) player, and the like. One or more tasks or stimuli may be stored in cloud server 130, and made downloadable to terminal 120. After download, the tasks may be installed on terminal 120.

When user 105 selects a task or a stimulus and starts a neuro-feedback training session, terminal 120 may load the selected task or stimulus and generate the task-related data based on the brainwave signals of user 105 received from headband 110. A task or a stimulus may include, but is not limited to, an academic task, educational task, an evaluation task, or an instruction - based task. In some embodiments, a software, an application, an executable set of instructions, and the like, may be downloadable on terminal 120.

[0053] Terminal 120, in some embodiments, may be configured to receive user input or display information based on the user input in real-time. For example, in an academic setup such as a classroom, while user 105 may provide input related to performing the task using terminal 120 (120A, 120B, or 120C), an educator or an instructor may access the information related to user 105 on terminal 120 based on the provided input, in real-time. Terminal 120 may receive user input or display information through a user-interface. The user-interface may comprise a graphic user-interface (GUI), an audio-visual interface, and the like.

[0054] Alternatively, and additionally, in some embodiments, the task may also be stored and run on one or more cloud servers 130. Cloud server 130 may be implemented as a general- purpose computer, a mainframe computer, one or more databases, one or more networks, or any combination of these components. In some embodiments, databases may comprise, for example, Oracle™ databases, Sybase™ databases, or other relational databases or non-relational databases, such as Hadoop™ sequence files, HBase™, or Cassandra™. The databases may include computing components (e.g., database management system, database server, etc.) configured to receive and process requests for data stored in memory devices of the database and to provide data from the database.

[0055] Cloud server 130 may be implemented as a server, a server cluster consisting of a plurality of servers, or a cloud computing service center. Cloud server 130 may be operated by a third-party service provider, an administrator of the neuro-feedbac training, a manufacturer, or a supplier of headband 110. In some embodiments, cloud server 130 may receive the brainwave signal(s) from headband 110 and generate the task-related data based on the received brainwave signal(s). Cloud server 130 may stream the generated task-related data to terminal 120, so that the user can perform the task on terminal 120 in real-time.

[0056] Reference is now made to Fig. 2, which illustrates a block diagram of a neuro-feedback training system 200, consistent with embodiments of the present disclosure. Neuro-feedback training system 200 may include headband 210, one or more terminals 220, and cloud server(s) 230, connected with each other through network 240. It is appreciated that headband 210, terminal 220, and cloud server 230 may be substantially similar and perform substantially similar functions as headband 110, terminal 120, and cloud server 130 of Fig. 1, respectively.

[0057] Headband 210 may comprise components including, but are not limited to, sensors 212 and 214, a signal processing module 216, and a communication module 218. In some embodiments, headband 210 may form a wired or a wireless connection with terminal 220 and/or cloud server(s) 230 via network 240. Network 240 may comprise a wired or a wireless network that allows transmitting and receiving data. For example, network 240 may be implemented as a nationwide cellular network, a local wireless network (e.g., Bluetooth^IM or WiFi), or a wired network. In some embodiments, headband 210, terminal 220, and cloud server(s) 230 may communicate with each other directly or indirectly via network 240.

[0058] As shown in Fig. 2, terminal 220 may comprise a controller 225 and a user interface 229. Controller 225 may include, among other things, an I/O (input/output) interface 222, a processing unit 224, a memory module 226, and a storage unit 228. These units may be configured to transfer data and send or receive instructions between or among each other in some embodiments, controller 225 may also be configured to communicate with cloud server 230 via network 240.

[0059] I/O interface 222 may be configured for two-way communication between controller 225 and various devices. For example, as depicted in Fig. 2, I/O interface 222 may send and receive signals to and from communication module 218 of headband 210, cloud server 30, and user interface 229. I/O interface 222 may send and receive data between each of the components via communication cables, networks (e.g., network 240), or other communication mediums.

[0060] I/O interface 222, in some embodiments, may be configured to consolidate signals it receives from the various components and relay the data to processing unit 224. Processing unit 224 may include a general-purpose or special-purpose microprocessor, digital signal processor, or microprocessor, or the like. Processing unit 224 may be implemented as a separate processor module dedicated to performing the disclosed methods for neuro-feedback training.

Alternatively, processing unit 224 may be configured as a shared processor module for performing other functions of terminal 220 unrelated to neuro-feedback training.

[0061] In some embodiments, processing unit 224 may be configured to receive data and/or signals from components of neuro-feedback training system 200 and process the data and/or signals to provide the neuro-feedback training. For example, processing unit 224 may receive brainwave signal(s) from headband 210 via I/O interface 222. Processing unit 224 may further process the received brainwave signal(s) to generate various visual or audio-visual features presented to user 105 before, during, or after performing the task. Moreover, if the tasks are run on cloud server 230, processing unit 224 may also receive task-related data from cloud server 230 via I/O interface 222. In exemplary embodiments, processing unit 224 may execute computer instructions (program codes) stored in memory module 226 and/or storage unit 228, and may perform functions in accordance with exemplary techniques described in this disclosure. More exemplary functions of processing unit 224 will be described below in relation to the disclosed methods for neuro-feedback training.

[0062] Memory module 226 and/or storage unit 228 may include any appropriate type of mass data storage means provided to store any type of information that processing unit 224 may need for operation. Memory'· module 226 and/or storage unit 228 may be a volatile or non-volatile, magnetic, semiconductor, tape, optical, removable, non-removable, or other type of storage device or tangible (i.e., non-transitory) computer-readable medium including, but not limited to, a ROM (read only memory), a flash memory', a DRAM (dynamic random access memory), or a SRAM (static random access memory_'), and the like.

[0063] Memory module 226 and/or storage unit 228 may be configured to store one or more computer programs that may be executed by processing unit 224 to perform exemplary neuro- feedback training methods disclosed in this application. For example, memory' module 226 and/or storage unit 228 may be configured to store program(s) that may be executed by- processing unit 224 to determine the level of engagement of a student based on the brainwave signal(s), and generate visual and/or audio-visual effects showing the determined attention score or interest score.

[0664] User interface 229 may be implemented as and comprise a display panel through which the task and other features may be accessed by user 105. The display panel may include a LCD (liquid crystal display) screen, a LED (light emitting diode) screen, a plasma display, a projection, or any other type of appropriate display, and may also include microphones, speakers, and/or audio input/outputs (e.g., headphone jacks), or may be coupled to an audio system of terminal 220.

[0065] Additionally, in some embodiments, user interface 229 may also be configured to receive input or commands from user 105. For example, the display panel may be implemented as a touch screen to receive input signals from user 105. The touch screen may include one or more touch sensors to sense touches, swipes, and other gestures on the touch screen. The touch sensors may not. only sense a boundary of a touch or swipe action, but also sense a period of time and a pressure associated with the touch or swipe action. Alternatively, or in addition, user interface 229 may include other input devices such as keyboards, buttons, joysticks, keyboards, and/or tracker balls. User interface 229 may be configured to send the user input to controller 225.

[0066] In some embodiments, cloud server 230 may be connected to headband 210 and terminal 220 via network 240. Cloud server 230 may include one or more controllers (not shown), similar to the configurations of controller 225 described above.

[0067] Reference is now made to Fig. 3, which illustrates an exemplar_)? headband 310 configured to detect the brainwave signal(s) of user 105 wearing headband 310. Headband 310 may be substantially similar to and may perform substantially similar functions as headband 210 of Fig. 2 and headband 110 of Fig. 1.

[0068] Headband 310 may be worn by user 105 or secured around a user’s head. In some embodiments, headband 310 may have a U-shaped body and can wrap around a user’s head. In some embodiments, headband 310 may have an adjustable length and may be made of shape memory. For example, a portion of headband 310 may be elastic or otherwise stretchable. As another example, headband 310 may have a built-in extension portion that can be hidden, extended, or partially extended to adjust the length of headband 310. As such, headband 310 can be adapted to closely fit different head dimensions.

[0069] Headband 310 may include one or more sensors (e.g., sensors 312, 314) for detecting or measuring brainwave signal(s). For example, these sensors may be medical level hydrogel sensors capable of EEG detection. The sensors (312 and 314) may be placed at different locations in headband 310 such that they detect brainwave signals from different parts of the user’s head when secured properly. As shown in Fig. 3, sensors 312 and 314 may be mounted at different positions on the surface of headband 310, such that when headband 310 is worn by user 105, sensor 312 is in substantial and appropriate contact with the user’s forehead, and sensor 314 is in substantial and appropriate contact with one of the user’s ears. The forehead is one of the commonly used scalp locations for detecting brainwave signal(s), while little or no brainwave signal(s) can be recorded at the ears and their vicinities. As such, sensor 314 serves as a reference sensor, wherein the difference of the signals recorded by sensors 312 and 314 may be used as a measured brainwave signal. It is appreciated that sensors 312 and 314 are for illustrative purpose only. The present disclosure does not limit the number of sensors and the placements of these sensors on the headband 310 and therefore, scalp for recording the brainwave signal(s)

[0070] In some embodiments, headband 310 may include a signal processing module 316 for processing the brainwave signal(s) measured by sensors 312 and 314. For example, signal processing module 316 may include one or more application specific integrated circuits (ASICs), controllers, micro-controllers (MCUs), microprocessors, or other electronic components. For example, signal processing module 316 may include an amplifier circuit that determines the difference between the signals measured by sensors 312 and 314, and amplifies the resultant brainwave signal for further analysis. Signal processing module 316 may be implemented as an embedded signal processing module and may wirelessly communicate with a terminal (e.g., terminal 220 of Fig. 2) or a cloud server (e.g., cloud server 230 of Fig. 2)

[0071] In some embodiments, headband 310 may include an embedded communication module 318 configured to facilitate communication, wired or wirelessly, between headband 310 and other devices or components of neuro-feedback training system. In some embodiments, communication module 318 and signal processing module 316 may be integrated on the same circuit board. Communication module 318 may be configured to access a wireless network based on one or more communication standards, such as WiFi, LTE, 2G, 3G, 4G, 5G, etc. In one exemplar₎'· embodiment, communication module 318 may include a near field communication (NFC) module to facilitate short-range communications between headband 310 and other system components and devices. In some embodiments, communication module 318 may be implemented based on a radio-frequency identification (RFID) technology, an infrared data association (IrDA) technology, an ultra-wideband (UWB) technology, a Bluetooth (BT) technology, or other relevant technologies. In the exemplary embodiments, signal processing module 316 may transmit, via communication module 318, the processed brainwave signals to other devices for performing the disclosed methods for neuro-feedback training.

[0072] In some embodiments, headband 310 may further include certain components not shown in Fig. 3. For example, in some embodiments, headband 310 may include one or more light- emitting diode (LED) lights for indicating including, but is not limited to, operation status of headband 310, such as on/off of headband 310, battery/power level, whether headband 310 is connected, etc. In some embodiments, headband 310 may include a micro-universal serial bus (USB) port which serves as a charging port. In some embodiments, headband 310 may include a light at the forehead position (hereinafter referred to as“forehead light”). The forehead light may indicate the current atention level as indicated by the brainwave signal(s) detected by sensors 312 and 314 For example, the forehead light may indicate the real-time attention level of the user by emiting different colors of light. For example, a red color may indicate user 105 is highly focused, a blue color may indicate user 105 is unfocused, and a green color may indicate user 105 is in transition between different attention levels. Additionally, or alternatively, the forehead light may also indicate the user’s mental state by changing the light intensities or light paterns (e.g., blinking at different frequencies). The present disclosure does not limit the method used by the forehead light to indicate the user’s mental state.

[0073] In some embodiments, headband 310 may include a power switch (not illustrated) to manually activate or deactivate headband 310. Activating headband 310 may comprise initiating sensors, initiating communication module 318, initiating signal processing module 316, etc. to enable the functionalities of the various components. Deactivating headband 310 may disable one or more functionalities of headband 310 based on a press pattern of the power switch. For example, pressing the power switch once may only deactivate sensor 312 such that sensor 312 may not detect the brainwave signal(s), while signal processing module 316 and co munication module 318 may remain activated to enable data processing and data transfer to other system components. In some embodiments, headband 310 may be activated or deactivated remotely, for example, through the software application.

[0074] In some embodiments, headband 310 may include wear-detection capabilities to ensure proper signal reception and detection, and maximize signal-to-noise (SNR) ratio. The brainwave signals may be perturbed, modified, or totally blocked by, for example, presence of hair between sensor 312 and user’s skin, dust particles on surface of sensor 312 etc

[0075] Reference is now made to Fig. 4, which illustrates an exemplary neuro-feedback system 400 in an academic set-up, consistent with embodiments of the present disclosure. The academic set-up may comprise a classroom, a test center, an auditorium, a theater, and the like. Neuro- feedback training system 400 may include one or more users 405 wearing headband 410 and using terminal 420. User 405 may include a group of users including students and teachers. For example, in an academic setup such as a classroom, user 405 may include a teacher or an instructor as well as a number of students. Terminal 420 may include, but is not limited to, a laptop, a personal desktop computer, a mobile phone, a tablet, an e-book reader, a MPEG player, and the like, capable of displaying user-interface display 430. [0076] Human brain is made up of more than 100 billion neurons. One way in which they function is by sending small electrical signals to one another. When a threshold number of the neurons“fire” in unison the signal is large enough to detect on human scalp. The brain activity changes based on the activity being performed. For example, during sleeping or relaxing, the neurons fire slower compared to when a human is awake because less information needs to be processed. On the other side of the spectrum, when a human is deeply engaged in a conversation or thinking intensely, the neurons fire much more quickly. Traditionally, researchers and medical doctors have used electroencephalograms (EEGs) to measure the electrical signals emanating from the brain, and the technique is known as electroencephalography.

[0677] Hie electrical signals may contain information associated with the number of neurons, the frequency of firing of the neurons, the pace of firing, and the like, based on the brain activity. The electrical signals may be manifested as wavefonns comprising an amplitude, a wavelength, and a frequency. One or more sensors (e.g., sensor 312 of Fig. 3) may be implemented as a headband sensor and configured to receive and detect the electrical signal(s). An algorithm may be used to interpret the electrical signals, and based on the interpretation, the level of brain activity may be determined. The algorithm may be based on or driven by advanced machine learning techniques or artificial intelligence-based techniques.

[0078] In some embodiments, the neuro-feedback training may be implemented by analyzing one or more frequency band(s) of the brainwaves. For example, the lower frequency bands may be associated with relaxation and daydreaming, the middle frequency bands may be associated with focused thinking and problem solving, and the higher frequency bands may be indicative of anxiety, hyper vigilance, and agitation. In some embodiments, in order to improve the user’s attention ability (i.e., stay focused), the mid-frequency bands, e.g., the low beta band, the theta band, and the high beta band, for example, may be tagged or marked for further analyis. In some embodiments, the neuro- feedback training may be implemented by analyzing the characteristics of the brainwave signal(s) within one or more frequency band(s).

[0079] In some embodiments, the neuro-feedback training may be implemented by analyzing one or more outputs of EEG algorithm's) that measure different cognitive states such as focus or relaxation, such that the neurofeedback training reinforces one or more of these states. The algorithm(s) to measure these states may be developed by generating machine learning based models of EEG signals that predict the likelihood that a user is in one of these states. [0080] In an academic setup such as a classroom, as illustrated in F!g. 4, neuro-feedback training system 400 may be configured to personalize an educational experience of teaching and learning based on biometric data. One of the several ways to personalize the educational experience may include determining a cognitive workload of a learner (e.g., a student), and using the obtained cognitive workload information, by an instructor (e.g., a teacher), to personalize the educational experience of the learner. As used herein, cognitive workload may refer to the amount of effort put in by the learner towards a particular learning task or in response to a stimulus. The cognitive workload, in some embodiments, may be used to scale factors including, but not limited to, the difficulty, the pace, and the sequence of learning tasks delivered to the learner.

[0081] As an example, individuals may respond differently to different tasks or stimuli based on factors including, but are not limited to, the format of the delivered tasks, the sequence of delivery’ of the tasks, the difficulty of the tasks, the pace with which the tasks are delivered, etc. and there may be an optimal way for individuals to learn such as, for example, auditory learners, visual learners, etc. By understanding how each learner may react to different learning tasks or stimuli, a personalized learner profile may be generated for each learner. The personalized learner profile may be used to enhance the educational experiences for learners as well as educators by customization of content, workload, difficulty, and the like.

[0082] In some embodiments, headband 410 may be configured to detect brainwave signal(s). The detected signal(s) may be processed to determine a cognitive workload index as a measure of the amount of effort involved towards the learning task over a predefined time period. In some embodiments, cognitive workload index may be a quantitative assessment of the amount of effort put in by the learner towards a task or a response to stimuli. In some embodiments, cognitive workload index may be a qualitative assessment of the amount of effort put in by the learner towards a particular learning task or a response to stimuli, indicated using levels of workload such as low, medium, or high; or indicated using a color scale.

[0083] The cogniti ve workload index may be a number ranging from 0 to 100, or 0 to 10, or any predefined range. The Al-based algorithm may quantify the cognitive workload and generate a cognitive workload index based on the detected brainwave signal(s). In some embodiments, a higher cognitive workload index may indicate that the learner may be overwhelmed, and a lower cognitive workload index may indicate that the learner may be underwhelmed, too relaxed, or insufficiently challenged. The proposed method of determining cognitive workload may also include fluctuations of cognitive workload to provide a more dynamic learning experience for the learner.

[0084] in some embodiments, developing an AI-based cognitive workload algorithm may include labeling the raw EEG data based on intensity of workload and looking for commonalities between the different task intensities. The raw EEG data may be obtained from a large number of subjects (e.g., users or test-takers) completing different cognitive tasks with various workload intensities. Based on multiple variables and features in the EEG signal(s), the workload state may be determined.

[0085] in some embodiments, based on a number of factors including, but are not limited to, the dynamic cognitive workload index, historical data, learner profile information, type of task, etc., the AI-based algorithm may set a“sweetspot” of cognitive workload index to adjust the cognitive workload to an optimal level of challenge. The sweetspot of cognitive workload index may be determined in real-time based on learner profile or may be predefined based on historical data, for example. In some embodiments, a system administrator or an instructor may determine the sweetspot of cognitive workload index based on historical data, past performance, expectations, goals, and the like.

[0086] In some embodiments, in addition to cognitive workload index, the detected brainwave signa!(s) may be processed to determine a level of engagement or level of attention as a measure of interest shown by the learner towards the learning tas over a predefined time period, in real time. Based on the detected brainwave signal(s), learning experiences may be customized to maximize the engagement and focus, while maintaining the sweetspot of cognitive workload.

[0087] in some embodiments, Aί-based algorithms may determine the level of engagement or interest of a learner based on an analysis of one or more characteristics of the brainwave signal(s) in real-time. Characteristics of the brainwave signals may include, but are not limited to, amplitude, frequency, wavelength, frequency band distribution, fluctuations within the frequency band, and the like. In some embodiments, neuro-feedback training system 400 may be configured to quantify the level of engagement or the level of interest with an attention score. As used herein, attention score may be referred to as the level of interest or engagement shown by a learner towards the learning tasks or stimuli. The attention score may be a number ranging from 0 to 100, or 0 to 10, or any predefined range. Based on the attention score, the system, or a system administrator, or an instructor, may determine the educational experience that engages the learner most. In some embodiments, the attention score may be used to scale the difficulty, pace, subject, skillset, and the like, to personalize and enhance the learning experience.

[0088] In some embodiments, the attention score may be used by an instructor, or a teacher to personalize, develop, modify, or create teaching experiences to enhance student engagement or classroom involvement in real-time. For example, if the average attention score of a classroom of students is higher for a mathematics problem invol ving algebra compared to other topics, the attention score may be displayed on the teacher’s terminal 420 via a graphic user-interface display 430, as shown in Fig, 4, in real-time. Based on the information obtained and/or displayed, the teacher may decide to customize, in real-time, the rest of her teaching material to include more algebra. Additionally, the lower level of interest displayed by the students, and determined by the AI based algorithm based on detected brainwave signal(s), in other topics of mathematics may warrant introducing more creative or engaging techniques from the teacher.

[0089] Reference is now made to Fig. 5, which illustrates an exemplary graphic user-interface display 530 depicting an information display panel 540, consistent with embodiments of the present disclosure. Information display panel 540 may comprise information including, but is not limited to, learner profile, real-time performance metrics, comparative data, information related to the learning task or stimuli, system status, and the like.

[0090] In some embodiments, as shown in Fig, 5, display element 550 may be configured to display information associated with the learner such as personal details, task being performed, task status, and the like. Display element 550 may comprise an interactive user-interface configured to receive user input, display feedback, system status, and the like. In some embodiments, display element 550 may comprise an audio, a video, or an audio-visual interface. It is appreciated that other information display panels comprising relevant information may be displayed based on user input, learning task, learner profile, and the like.

[0091] In some embodiments, exemplary information display panel 540 may display the determined attention score of one or more learners over a period of time. As shown in Fig, 5, the average attention score is graphically represented and may be updated in real-time. Information display panel 540 may be displayed on one or more terminals (e.g., terminal 420 of Fig, 4) used by a student, a group of students, a teacher, a group of teachers, or any combination thereof.

[0092] In some embodiments, a neuro-feedback training system (e.g., neuro-feedback training system 400 of Fig. 4) may be configured to track, in real-time, attention score feedback of individual learners and/or a classroom of students. For example, a teacher may track the attention score of the students to determine the effectiveness of a teaching technique, introduction of new subject material, determine individual performance levels, and the like. One of the several ways to track teaching methods is to“tag” or identify patterns of attention level on information display panel 540 by analyzing the attention scores of an individual or a group of students, in real-time.

[0093] Tagging, in some embodiments, may include marking or identifying instances of a large difference in the attention score from an immediately previous reading, analyzing a pattern of increasing attention score, or a pattern of decreasing attention score, and the like. In some embodiments, AI-based algorithm or advanced machine learning algorithms may be configured to tag patterns and instances of attention scores based on a predefined set of criteria, or an instructor may monitor and manually tag the attention scores in real-time.

[0094] As illustrated in Fig. 5, information display panel 540 comprises attention score tags 542 and 544. In this example, tag 542 represents an instance of a high attention score and tag 544 represents an instance of a low attention score. In some embodiments, the teacher may analyze the information obtained from neuro-feedback training system including the tags, and determine the content or the subject matter associated with the tag 542. For example, tag 542 may be associated with the learner’s response to a task of visualizing an object in 3D (three-dimensions), the teacher may determine that the learner may be the most engaged and interested in related subject material. Based on the information and the analysis, the teacher may create or develop a more meaningful and personalized educational experience for the learner. The teachers may also the information to customize their teaching methods and strategies.

[0095] In some embodiments, the software application, or a platform that executes the software application, may be configured to generate a report including i nformation associated with a test session or an academic session. The reports may include information related to the student, attention scores, tags, timing and duration, cognitive workload, and the like. The teacher may share the report with the student or the parents. In some embodiments, the teacher may share the report with the classroom at the end of a class or a session to discuss o verall class attention levels, highlight areas of improvement, teaching methods and strategies, learning strategies, and the like.

[0096] In some embodiments, a neuro-feedback training system (e.g., neuro-feedback training system 400 of Fig. 4) may be configured to personalize the educational experience of a learner based on a combination of the attention score and a performance score. Personalizing the educational experience may comprise adjusting the difficulty of the tasks delivered to the learner based on their level of engagement and performance such that the tasks are not too difficult and discouraging or too easy and boring. The performance score may be determined in real-time by AΪ based algorithms, advanced machine learning techniques, manually by an instructor, or by other relevant means. In some embodiments, neuro-feedback training system 400 may determine the overall performance of a learner by combining the attention score and the performance score of the learner for the task.

[0097] Reference is now made to Fig. 6, which illustrates an exemplary graphic user-interface display 630 depicting an information display panel 640, consistent with embodiments of the present disclosure. Information display panel 640 may comprise information associated with the overall performance of a learner. In some embodiments, the overall performance of a learner in responding to a learning task may be categorized based on a combination of attention score and performance score for the task. Display element 650 may be substantially similar to display element 550 and may perform substantially similar functions. It is appreciated that display element 650 may be configurable to display other relevant information, as appropriate.

[0098] in an exemplary representation of a decision model to determine the next learning task, the overall performance of a learner may be depicted in quadrants 642, 644, 646, and 648, as illustrated in Fig. 6. In some embodiments, the overall performance of the learner may be represented in a matrix format, an array format, and the like. For example, if the attention score is high and the performance score for the task is low, the student’s overall performance may be represented by first quadrant 642. A low performance score and a high attention score indicate that the learning task may be too difficult for the learner because despite the student’s brain being highly focused and concentrated, the student’s performance is low. In such a case, the system may adjust the tas accordingly by, for example, making the next question on the test slightly easier.

[0099] The overall performance of a learner may be represented by second quadrant 644 if the attention score and the performance score for the task are high. High attention scores and performance scores for the task indicate that the learning tas is optimal and is a good fit for their educational growth. In such a case, the system may continue delivering tasks of similar difficulty level or slightly more difficult to encourage the student and maintain the level of interest. As illustrated in Fig. 6, a quadrant (e.g., quadrant 644) may he highlighted in the displayed information to indicate the overall performance of the learner for a particular task, or a number of tasks. In some embodiments, the overall performance score may be averaged, for example, at the end of a session, a learning task, or learning stimuli.

[00100] The overall performance of a learner may be represented by third quadrant 646 if the attention score is low and the performance score for the task is high. Exhibiting a high performance score while the attention score is low, indicates that the learning task is too easy for the learner, and the learner may get bored, if the level of engagement and difficulty are unchanged. In such a case, the system may increase the difficulty of the learning task delivered to the learner to optimize the challenge and level of engagement.

[00101] The overall performance of a learner may be represented by fourth quadrant 648 if the attention score is low and the performance score for the task is low'. Exhibiting a low performance score while the attention score is low, indicates that the student is disengaged with the task. The teacher may use this information to re-engage the student with a more exciting task, a more exciting teaching strategy, revise goals and expectations during meeting with the student or student’s representatives, and the like.

[00102] In some embodiments, the personalization of educational experiences may be implemented digitally and assisted by AI driven algorithms and programs on an online learning platform. In this scenario, the online learning platform may adapt, update, and present tasks based on the brainwave data obtained. Alternatively, a human teacher, instructor, or an educator may access the processed brainwave data and utilize the information to adapt and change the tasks or teaching methods to create a customized learning and teaching experience.

[00103] Some of the advantages of a neuro-feedback training system and methods of personalizing educational experience using the neuro-feedback training system are as follows:

i. Real-time performance monitoring - As proposed, the neuro-feedbac training system may enable real-time monitoring of a learner’s cognitive workload and level of attention. The ability to monitor real-time performance based on the brainwave signal(s) may allow' the teacher to adjust the content, the amount, and the way learning tasks may be delivered, for example, in an academic setup. ii. Real-time feedback - The detected brainwave signal(s) indicative of the electrical activity of the learner’s brain and therefore, the level of interest or engagement may provide instant feedback of the effectiveness of a teaching strategy, in real time. The ability to receive real-time feedback may allow the teacher to improve lesson plans, address attention in real-time during class, and test different methods and ideas with quantitative feedback on the effectiveness of those methods and ideas.

iii. Personalized educational experience - The proposed neuro-feedback training systems and methods may allow students to develop self-regulation an ownership over their education experience through social, emotional, academic learning. iv. System compatibility - The online learning platform may be integrated with a plethora of software applications provided by any education or learning software vendors.

[00104] Next, neuro-feedback training methods consistent with the present disclosure will be described. Without special explanation, the following description assumes the steps of the disclosed methods are performed by a terminal (e.g., terminal 420 of F!g. 4). However, it is contemplated some or all of the steps in the following described methods may also be performed by headband 410 and/or cloud server 230.

[00105] Reference is now made to Fig. 7, which illustrates a flowchart of a method 700 for personalizing an educational experience based on neuro-feedback training, consistent with embodiments of the present disclosure. For example, a terminal (e.g., terminal 420) may be installed with an application for neuro-feedback training. To start a neuro-feedback training session, a user (e.g., user 405 of Fig. 4) may wear a headband (e.g., headband 410 of Fig, 4) and activate the headband to record the brainwave signal(s) from the user’s brain. Meanwhile, the user may then initiate the application, such that the terminal may establish a wireless connection with the headband and perform method 700. Referring to Fig. 7, method 700 may include the following steps 710-740. It is appreciated that steps may be added, omitted, edited, reordered, as needed.

[00106] In step 710, a brainwave signal generated by a learner in response to a stimulus or while performing a learning task may be detected. In some embodiments, the headband may be configured to detect one or more generated brainwave signal(s). The brainwave signal(s) may be measured continuously over time, or during set time intervals. The headband may comprise one or more sensors (e.g., sensors 312 and 314 of Fig. 3) to receive, detect, and measure the brainwave signal(s). The headband may also comprise a signal processing module (e.g., signal processing module 316 of Fig. 3) for processing the brainwave signal(s) measured by the sensors. For example, the signal processing module may include one or more ASICs, controllers, micro-controllers, microprocessors, or other electronic components. The signal processing module may include an amplifier circuit that determines the difference between the signals measured by the sensors, and amplifies the resultant brainwave signal for further analysis. The signal processing module may be implemented as an embedded signal processing module and may wirelessly communicate with the terminal or the cloud server.

[00107] In some embodiments, the headband may include an embedded communication module (e.g., communication module 318 of Fig. 3) configured to facilitate communication, wired or wirelessly, between the headband and other devices or components of the neuro- feedback training system. In some embodiments, the communication module and the signal processing module may be integrated on the same circuit board.

[00108] The brainwave signal generated may be an electrical signal measured at the scalp of the user through sensors of the headband. The headband may be secured around the head such that the brain activity sensor is in contact with the skin of the forehead. The headband may be activated prior to sensing the brainwave signal(s).

[00109] In step 720, the terminal may receive the processed brainwave signal and may analyze at least one characteristic of the brainwave signal(s). For example, the terminal may be configured to analyze the amplitude, the frequency or the frequency band distribution of the processed brainwave signal(s). In some embodiments, the terminal may apply a low-pass filter to remove the signal noise and derive the power spectrum of the brainwave signal, e.g., using mathematic methods such as a Fourier transform. As described above, the amplitudes of the power spectrum may be grouped into different frequency bands. Besides the normal bands showing the brain activities, sometimes the power spectrum may also include one or more frequency bands corresponding to artifacts. For example, eye blinking, chewing, and other facial muscle movements may give rise to one or more distinct artifact bands. When the amplitude of the artifact is higher than a predefined threshold level, the whole power spectrum may be distorted and render inaccurate feedback determination. If the artifact bands are present, the terminal may further determine whether the amplitude of the artifact bands exceeds their respective artifact threshold. If at least one artifact band has an amplitude higher the respective artifact threshold, the terminal may disregard the brainwave signal received during the period of time in which the artifact is detected. Otherwise, the terminal may conclude the brainwave signal is valid.

[00110] in step 730, the terminal may be configured to generate a cognitive workload index based on the analysis of at least one of the characteristics of the brainwave signal. The cognitive workload index is a measure of the amount of effort involved towards the learning task over a predefined time period. In some embodiments, cognitive workload index may be a quantitative assessment of the amount of effort put in by the learner towards a task or a response to stimuli. In some embodiments, cognitive workload index may be a qualitative assessment of the amount of effort put in by the learner towards a particular learning task or a response to stimuli, indicated using levels of workload such as low, medium, or high; or indicated using a color scale.

[00111] The cognitive workload index may be a number ranging from 0 to 100, or 0 to 10, or any predefined range. The AI-based algorithm may quantify the cognitive workload and generate a cognitive workload index based on the detected brainwave signal(s). In some embodiments, a higher cognitive workload index may indicate that the learner may be overwhelmed, and a low'er cognitive workload index may indicate that the learner may be underwhelmed, too relaxed, or insufficiently challenged. The proposed method of determining cognitive workload may also include fluctuations of cognitive workload to provide a more dynamic learning experience for the learner.

[00112] In step 740, the learning task or the stimulus may be adjusted based on the generated cognitive workload index to personalize the educational experience for the learner. Adjusting the learning task may include determining whether the next learning task should be easier, harder, or unchanged based on the cognitive workload index, learner profile, learner goals, and the like.

[00113] In some embodiments, based on a number of factors including, but are not limited to, the dynamic cognitive workload index, historical data, learner profile information, type of task, etc., the AI-based algorithm may set a sweetspot of cognitive workload index to adjust the cognitive workload to an optimal level of challenge. The sweetspot of cognitive workload index may be determined in real-time based on learner profile or may be predefined based on historical data, for example. In some embodiments, a system administrator or an instructor may determine the sweetspot of cognitive workload index based on historical data, past performance, expectations, goals, and the like.

[00114] Reference is now' made to Fig. 8, which illustrates a flowchart of a method 800 for personalizing an educational experience based on neuro-feedback training, consistent with embodiments of the present disclosure. For example, a terminal (e.g., terminal 420) may he installed with an application for neuro-feedback training. To start a neuro-feedback training session, a user (e.g., user 405 of Fig. 4) may wear a headband (e.g., headband 410 of Fig. 4) and activate the headband to record the brainwave signal(s) from the user’s brain. Meanwhile, the user may then initiate the application, such that the terminal may establish a wireless connection with the headband and perform method 800. Referring to Fig. 8, method 800 may include the following steps 810-850. It is appreciated that steps may be added, omitted, edited, reordered, as needed.

[00115] In step 810, a brainwave signal generated by a learner in response to a stimulus or while performing a learning task may be detected. In some embodiments, the headband may be configured to detect one or more generated brainwave signal(s). The brainwave signal(s) may be measured continuously over time, or during set time intervals. The headband may comprise one or more sensors (e.g., sensors 312 and 314 of Fig, 3) to receive, detect, and measure the brainwave signal(s). The headband may also comprise a signal processing module (e.g., signal processing module 316 of Fig, 3) for processing the brainwave signal(s) measured by the sensors. For example, the signal processing module may include one or more ASICs, controllers, micro-controllers, microprocessors, or other electronic components. The signal processing module may include an amplifier circuit that determines the difference between the signals measured by the sensors, and amplifies the resultant brainwave signal for further analysis. The signal processing module may be implemented as an embedded signal processing module and may wirelessly communicate with the terminal or the cloud server.

[00116] In some embodiments, the headband may include an embedded communication module (e.g., communication module 318 of Fig, 3) configured to facilitate communication, wired or wirelessly, between the headband and other devices or components of the neuro feedback training system. In some embodiments, the communication module and the signal processing module may be integrated on the same circuit board.

[00117] The brainwave signal generated may be an electrical signal measured at the scalp of the user through sensors of the headband. The headband may be secured around the head such that the brain activity sensor is in contact with the skin of the forehead. The headband may be activated prior to sensing the brainwave signal(s).

[00118] In step 820, the terminal may receive the processed brainwave signal and may analyze at least one characteristic of the brainwave signal(s). For example, the terminal may be configured to analyze the amplitude, the frequency or the frequency band distribution of the processed brainwave signal(s). In some embodiments, the terminal may apply a low-pass filter to remove the signal noise and derive the power spectrum of the brainwave signal, e.g., using mathematic methods such as a Fourier transform. As described above, the amplitudes of the power spectrum may be grouped into different frequency bands. Besides the normal bands showing the brain activities, sometimes the power spectrum may also include one or more frequency bands corresponding to artifacts. For example, eye blinking, chewing, and other facial muscle movements may give rise to one or more distinct artifact bands. When the amplitude of the artifact is higher than a predefined threshold level, the whole power spectrum may be distorted and render inaccurate feedback determination. If the artifact bands are present, the terminal may further determine whether the amplitude of the artifact bands exceeds their respective artifact threshold. If at least one artifact band has an amplitude higher the respective artifact threshold, the terminal may disregard the brainwave signal received during the period of time in which the artifact is detected. Otherwise, the terminal may conclude the brainwave signal is valid.

[00119] In step 830, the terminal may be configured to generate an attention score of a learner based on the analysis of at least one of the characteristics of the brainwave signal(s). The detected brainwave signal(s) may be processed to determine a level of engagement or level of attention as a measure of interest shown by the learner towards the learning task over a predefined time period, in real-time. Based on the detected brainwave signal(s), learning experiences may be customized to maximize the engagement and focus, while maintaining the sweetspot of cognitive workload.

[00120] In some embodiments, AI-based algorithms may determine the level of engagement or interest of a learner based on an analysis of one or more characteristics of the brainwave signal(s) in real-time. Characteristics of the brainwave signals may include, but are not limited to, amplitude, frequency, wavelength, frequency band distribution, fluctuations within the frequency band, and the like. In some embodiments, the neuro-feedback training system may be configured to quantify the level of engagement or the level of interest with an attention score. As used herein, attention score may be referred to as the level of interest or engagement shown by a learner towards the learning tasks or stimuli. The attention score may be a number ranging from 0 to 100, or 0 to 10, or any predefined range. Based on the attention score, the system, or a system administrator, or an instructor, may determine the educational experience that engages the learner most. In some embodiments, the attention score may be used to scale the difficulty, pace, subject, skillset, and the like, to personalize and enhance the learning experience.

[00121] In some embodiments, the attention score may be used by an instructor, or a teacher to personalize, develop, modify, or create teaching experiences to enhance student engagement or classroom involvement in real -time. For example, if the average attention score of a classroom of students is higher for a mathematics problem invol ving algebra compared to other topics, the attention score may be displayed on the teacher’s terminal via a graphic user- interface display (e.g., user-interface display 430 of Fig. 4), in real-time. Based on the information obtained and/or displayed, the teacher may decide to customize, in real-time, the rest of her teaching material to include more algebra. Additionally, the lower level of interest displayed by the students, and determined by the AI based algorithm based on detected brainwave signal(s), in other topics of mathematics may warrant introducing more creative or engaging techniques from the teacher.

[00122] In step 840, a performance score of the learner for the task may be determined. The performance score may be determined in real-time by AI based algorithms, advanced machine learning techniques, manually by an instructor, or by other relevant means.

[00123] In step 850, the learning task or the stimulus may be adjusted based on a combination of the attention score and the performance score for the learning task, to personalize the educational experience for the learner. The combination of the attention score and the performance score for the task may be referred to as the overall performance score. Personalizing the educational experience for the learner may comprise adjusting the difficulty of the tasks delivered to the learner based on their level of engagement and performance, such that the tasks are not too difficult and discouraging or too easy and boring. The performance score may be determined in real-time by AI based algorithms, advanced machine learning techniques, manually by an instructor, or by other relevant means.

[00124] In general, although methods 700 and 800 are described in connection with the frequency features of the brainwave signal(s), the present disclosure is not limited to the frequency features. Rather, it is intended that the disclosed methods and systems may use any suitable features of the brainwave signal(s). For example, one phenomenon known as Event Related Potential (ERP) refers to a significant change in a brainwave signal following specific stimulus (e.g., viewing certain scenes or hearing a specific music). For example, a user’s exposure to certain stimuli may create a significant change in the brainwave signal’s amplitude approximately 300 milliseconds after the exposure (also known as“P3QQ ERP”). Such change may be used to detect the user’s response to a stimulus and generate neuro- feedback.

[00125] In exemplary embodiments, the data used and generated by the disclosed methods for neuro-feedback training may be saved in, for example, mentor_}' module 226 and/or storage unit 228 for further study and analysis. In one embodiment the data may be analyzed to optimize the neuro-feedback training for each individual user. For example, memory module 226 and/or storage unit 228 may store a user profile assisted with each user. The user profile may include but are not limited to each user’s age, gender demographic information. EEG characteristics, and past brainwave signals generated during the neuro-feedback training. Machine learning methods, such as regression algorithms or Bayesian algorithms, may be employed to analyze the user profile and optimize (or customize) the neuro-feedback training for the individual user.

[00126] Another aspect of the disclosure is directed to a non -transitory computer-readable medium storing instructions which, when executed, cause one or more processors to perform the methods, as discussed above. The computer-readable medium may include volatile or non volatile, magnetic, semiconductor, tape, optical, removable, non-removable, or other types of computer-readable medium or computer- readable storage devices. For example, the computer- readable medium may be the storage unit or the memory module having the computer instructions stored thereon, as disclosed. In some embodiments, the computer-readable medium may be a disc or a flash drive having the computer instructions stored thereon.

[00127] As discussed earlier, attention has important correlation and influence on many aspects of users, for example, the attention level of children affects their cognitive development, and therefore, a lot of attention games can be pushed out to test the attention of the user, so that the attention of the user can be cultured and promoted in a targeted manner. However, because the evaluation of attention is mainly based on some related attention games, the evaluation result is only based on the scoring rule of the game, and the accuracy of the evaluation result is low.

[00128] hi order to solve the technical problem of inaccurate attention evaluation results, this disclosure provides an attention evaluation method, a system and a computer readable storage medium. The attention evaluation method may be applied to the attention evaluation system, and the attention evaluation system may comprise an attention evaluation terminal and an intelligent wearable device. The attention evaluation terminal may obtain the answer data when the user performs the preset attention game and may acquire corresponding EEG data through the intelligent wearable device. The answer data and the EEG data may be processed, so that corresponding answer scores and EEG scores are obtained. Finally, the answer scores and the EEG scores are substituted into a preset multi-variable regression equation, so that attention scores can be obtained. According to the method, EEG data may be acquired by using a brain computer interface technology, answer data and EEG data are combined, and corresponding answer scores and EEG scores are obtained through processing, and the attention scores may be calculated based on attention scores obtained through early-stage optimization and the multi- variable regression equation between the answer scores and the EEG scores. In contrast with the prior art, evaluation and scoring are carried out only in a single mode according to the scoring rule of the game, the accuracy of the attention evaluation result can be improved, and the accuracy of the attention evaluation result can be improved

[00129] Reference is now made to Fig, 9, which illustrates a schematic structural diagram of an attention-evaluation terminal 1000 of a hardware running environment consistent with embodiments of the present disclosure. The attention-evaluation terminal 1000 provided by the embodiment of the invention can be a PC (personal computer) and can also be a smart phone and a tablet computer, a portable computer and the like with a display function. A preset attention game may be arranged in the attention evaluation ter inal.

[00130] As illustrated in Fig, 9, the attention-evaluation terminal 1000 may include a processor 1001, such as a CPU and a communication bus 1002, a user interface 1003, a network interface 1004 and a memory 1005. Communication bus 1002 may be configured to be used for realizing connection communication between the components. User interface 1003 may include a display screen (a display), an input unit such as a keyboard. An optional user interface 1003 may include a standard wired interface or a wireless interface. Network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., a Wi-fi interface). Memory 1005 may be a high-speed RAM memor ', or may be a stable non-volatile memory, such as a magnetic disk memory. In some embodiments, memory 1005 may optionally be a memory device independent of processor 1001. It will be understood by those skilled in the art that the terminal structure shown in Fig, 9 is not limited to a terminal, more or fewer components can be included or some components can be combined, or different components can be arranged, as appropriate or as needed.

[00131] As illustrated in Fig, 9, an operating system, a network communication module, a user interface module and an attention evaluation program may be included in memory' 1005 of a computer storage medium. In attention-evaluation terminal 1000 shown in Fig, 9, network interface 1004 may be configured to be used for being connected with a background server and is in data communication with the background server; user interface 1003 may be configured to be used for being connected with a client.

[00132] In some embodiments, processor 1001 may be used for calling the attention evaluation program stored in the memory 1005 and executing the following operations:

i. The attention evaluation terminal 1000 acquires answer data when a user

performs a preset attention game, and acquires corresponding brain wave EEG data through the intelligent wearable device;

ii. Processing the answer data and the EEG data to obtain corresponding answer scores and EEG scores; and

iii. Based on the answer score, the EEG score and the preset multi-variable regression equation, an attention score value is obtained.

[00133] In some embodiments, processor 1001 can call attention evaluation programs stored in the memory 1005, and execute the following operations. The general formula of the preset multi-variable regression equation is as follows: Z = aX + bY, wherein Z is an attention value, x is an answer score, y is an EEG score, and a and b are corresponding optimal coefficients, respectively. Further, the pre-set attention game includes a continuous attention game and other attention games including a selective attention game, a conversion attention game, a distributed attention game, and an attention breadth game.

[00134] In some embodiments, processor 1001 can call attention evaluation programs stored in memory_' 1005, and further execute the following operations.

i. The attention evaluation terminal respectively acquires first answer data and

second answer data when the user performs continuous attention games and other attention games, and respectively acquiring corresponding first EEG data and second EEG data through the intelligent wearable device;

ii. Processing the first answer data, the first EEG data, the second answer data and the second EEG data respectively, and obtaining a corresponding first answer score, a first EEG score, a second answer score and a second EEG score; and iii. First and second answer scores according to the first answer score, the first EEG score and the second answer score, a second EEG sub-value and a preset multi variable regression equation to obtain a fractional value of the continuous attention game and a fractional value of other attention.

[00135] In some embodiments, processor 1001 may be used for calling the attention evaluation program stored in the memory 1005 and executing the following operations:

i. Acquiring first evaluation answer data and first self-scores when an evaluation person perforins the continuous attention game, and acquiring corresponding first evaluation EEG data through the intelligent wearable device;

ii. Respectively preprocessing the first evaluation answer data and the first

evaluation EEG data to obtain corresponding first scores and second scores; iii. Respectively performing statistical estimation on the first and second scores to obtain a corresponding first distribution curve and a second distribution curve; iv. Obtaining a continuous attention evaluation answer score according to the first score and the first distribution curve, and obtaining a continuous attention evaluation EEG score according to the second score and the second distribution curve; and

v. The first multi-variable regression equation is constructed according to the

continuous attention evaluation answer score, the continuous attention evaluation

EEG score and the first self-score, and obtaining a first optimal coefficient of the first multivariable regression equation through a normal equation, substituting the first optimal coefficient into the first multivariable regression equation to obtain a multivariable regression equation of the continuous attention of the preset multi- variable regression equation.

[00136] In some embodiments, processor 1001 may be used for calling the attention evaluation program stored in the memory 1005 and executing the following operations:

i. Acquiring second evaluation answer data and second self-scores when the

evaluation person perforins the other attention games, and acquiring corresponding second evaluation EEG data through the intelligent wearable device;

ii. Respectively preprocessing the second evaluation answer data and the second evaluation EEG data to obtain corresponding third and fourth scores; iii. Respectively performing statistical estimation on the third sub- value and the fourth sub-value to obtain a corresponding third distribution curve and a fourth distribution curve;

iv. Obtaining evaluation answer scores of other attention according to the third

distribution curve and the third distribution curve, and obtaining evaluation EEG scores of other attention according to the fourth distribution curve and the fourth distribution curve; and

v. Establishing a second multivariable regression equation according to the

evaluation answer scores of the other attention, the evaluation EEG scores of other attention and the second self-score, and obtaining a second optimal coefficient of the second multivariable regression equation through a normal equation, substituting the second optimal coefficient into the second multivariable regression equation to obtain a multivariable regression equation of other attention of the preset multi- variable regression equation.

[00137] In some embodiments, processor 1001 may be used for calling the attention evaluation program stored in the memory 1005 and executing the following operations:

i. Preprocessing the first answer data, the first EEG data, the second answer data and the second EEG data respectively, and a fifth sub-value, a sixth sub-value, a seventh sub-value and an eighth sub-value of the corresponding fifth sub-value, sixth sub-value, seventh sub-value and eighth sub- value are obtained;

ii. Obtaining a first curve lower area corresponding to the fifth score and a first total area between the first distribution curve and the cross axis according to the fifth score and the first distribution curve by integrating, and recording the percentage value of the lower area of the first curve and the first total area as a first answer score;

iii. Obtaining a second curve lower area corresponding to the sixth sub-value and a second total area between the second distribution curve and the horizontal axis according to the sixth sub-value and the second distribution curve, and recording the percentage value of the lower area of the second curve and the second total area as first EEG scores;

iv. Obtaining a third curve lower area corresponding to the seventh sub-value and a third total area between the third distribution curve and the horizontal axis according to the seventh sub-value and the third distribution curve, and recording the percentage value of the lower area of the third curve and the third total area as a second ans wer score; and

v. Obtaining the lower area of the fourth curve corresponding to the eighth value and tiie fourth total area between the fourth distribution curve and the horizontal axis according to the eighth and fourth distribution curves, and recording the percentage value of the lower area of the fourth curve and the fourth total area as second EEG scores.

[00138] In some embodiments, processor 1001 may be used for calling the attention evaluation program stored in the memory 1005 and executing the following operations:

i. Obtaining the fractional value of the follow-up attention game according to the first answer score, the first EEG score and the multivariable regression equation of the continuous attention in the preset multivariable regression equation, and obtaining the fractional values of other attention according to the second answer score, the second EEG score and the multi-variable regression equation of other attention in the preset multivariable regression equation; and

ii. The first answer data and the first evaluation answer data comprise the maximum continuous answer correct number and the answer total number, wherein the second answer data and the second evaluation answer data comprise answer correct numbers and answer errors.

[00139] Reference is now made to Fig. 10, which illustrates a flowchart of an attention evaluation method according to a first embodiment of the present disclosure. In this embodiment of the invention, the attention evaluation method is applied to an attention evaluation system such as attention evaluation terminal 1000 of Fig. 9, and the attention evaluation syste comprises an attention evaluation terminal and an intelligent wearable device. The attention evaluation terminal is internally provided with a preset attention game for the user and the evaluation person to perform evaluation attention, wherein the preset attention game comprises a continuous attention game and other attention games. Other attention games may include a selective attention game, a conversion attention game, a dispersed attention game and an attention breadth game. The attention evaluation terminal may be used for acquiring answer data and EEG data sent by the intelligent wearable device when the user and the evaluation person carry out the preset attention game, and then processing the EEG data to obtain the final attention score. In some embodiments, brain-computer interface technology may be applied to intelligent wearable device and used for collecting EEG (Electroencephalogram) and brain wave of user and evaluation person) data and can be in communication connection with the attention evaluation terminal so as to transmit the EEG to the attention evaluation terminal for processing and evaluation. The attention evaluation method may comprise the following steps:

[00140] In step S10, the attention evaluation terminal may be configured to acquire answer data when a user performs a preset attention game, and acquire corresponding brain wave EEG data through the intelligent wearable device. The answer data can include, but are not limited to, answer correct numbers and answer errors, the maximum continuous answer correct number and the answer total number can be obtained according to different types of the preset attention games, and different answer data can be acquired. For example, when a preset attention game is a continuous attention game, corresponding answer data can be recorded as first answer data, and the first answer data can comprise the maximum continuous answer correct number and the answer total number. When the preset attention game is other attention games, the corresponding answer data can be recorded as the second answer data, and the second answer data can comprise the maximum continuous ans wer correct number and the ans wer total number.

[00141] In step S20, the attention evaluation terminal may be configured to process the answer data and the EEG data to obtain corresponding answer scores and EEG scores.

Specifically, due to the evaluation of different types of attention, the acquired answer data and EEG data may not be consistent, and the corresponding data processing methods are different. The specific processing method can be referred to the following embodiments, and is not described in detail herein. In the embodiments, the answer score may include a first answer score and a second score, and the EEG score may include a first EEG score and a second EEG score.

[00142] In step S30, the attention evaluation terminal may be configured to obtain an attention score value according to the answer score, the EEG score, and a preset multi- variable regression equation. The preset multi-variable regression equation may comprise a multi-variable regression equation of continuous attention and a multi-variable regression equation of other attention. The multi-variable regression equation of other attention may include a multi- variable regression equation of the selective attention, the multi-variable regression equation of the conversion attention, the multi-variable regression equation of the dispersity attention, and the multi-variable regression equation of the attention breadth. The general formula of the preset multi -variable regression equation is as described earlier, where X is an answer score, Y is an EEG score, and a and b are corresponding optimal coefficients, respectively lire answer scores and the EEG scores are substituted into a preset multi -variable regression equation, so that attention scores can be obtained.

[00143] In some embodiments, an attention evaluation method applied to an attention evaluation system may be provided. The attention evaluation system may comprise an attention evaluation terminal and an intelligent wearable device. An attention evaluation terminal may acquire answer data when a user performs a preset attention game, and may acquire

corresponding EEG data through the intelligent wearable device. The attention evaluation system may process the answer data and the EEG data to obtain corresponding answer scores and EEG scores, finally, the answer scores and the EEG scores are substituted into a preset multi-variable regression equation, so that the attention scores can be obtained. According to the method, EEG data are acquired by using a brain computer interface technology, the answer data and EEG data are combined, and corresponding answer scores and EEG scores are obtained through processing, and the scores of the attention are calculated through the attention scores obtained through early-stage optimization and the multi-variable regression equation between the answer scores and the EEG scores. In contrast with the prior art, because evaluation and scoring are carried out only in a single mode according to the scoring rule of the game, the accuracy of the attention evaluation result can be improved.

[00144] Reference is now made to Fig. 11, which illustrates a flowchart of an attention evaluation method according to a second embodiment of the present disclosure, based on the first embodiment shown in Fig. 10, in view of persistent attention and other attention (including computational selectivity attention, conversion attention, dispersity attention and attention breadth) games. In some embodiments, therefore, when the scores corresponding to the attention of each dimension are calculated, the processing method and the algorithm are different. The selective attention and the conversion attention are calculated, the algorithm of the four attention scores of the dispersity attention and the attention breadth is the same, and the algorithm for calculating the continuous attention score is different. Correspondingly, the preset attention game comprises a continuous attention game and other attention games, and the other attention games comprise a selective attention game, a conversion attention game, a dispersion attention game and an attention breadth game. In other embodiments, the preset attention game may include five checkpoints, and each checkpoint may correspond to one attention. The attention evaluation method may comprise the following steps: [00145] In step SIOO, the attention evaluation terminal may acquire first answer data and second answer data of the user for continuous attention games and other attention games respectively, and may acquire corresponding first EEG data and second EEG data through the intelligent wearable device. In this case, due to the fact that the algorithm of continuous attention scores and other attention scores is not consistent, the game data of the corresponding games need to be obtained respectively, and corresponding processing and calculation are respectively carried out. Firstly, the attention evaluation terminal obtains first answer data and second answer data when the user performs a continuous attention game and other attention games respectively, and the corresponding first EEG data and second EEG data are acquired through the intelligent wearable device. The first answer data may include, but is not limited to, the maximum continuous answer correct number and the answer total number, and the second answer data may comprise, but is not limited to, answer correct numbers and answer error numbers.

[00146] In step S200, the attention evaluation terminal may process the first answer data, the first EEG data, the second answer data and the second EEG data, and obtain a corresponding first answer score, a first EEG score, a second answer score and a second EEG score. The system may process the first answer data, the first EEG data, the second answer data and the second EEG data, and a corresponding first answer score, a first EEG score, a second answer score and a second EEG score are obtained.

[00147] In step S300, according to the first answer score, the first EEG score and the second answer score, the second EEG scores and the preset multivariable regression equation, and the fractional values of the continuous attention games and the fractional values of other attention are obtained. The preset multi- variable regression equation is optimized in the earlier stage. The preset multi- variable regression equation may comprise a multi-variable regression equation of continuous attention and a multi- variable regression equation of other attention. The multi -variable regression equation of other attention may comprise a multi-variable regression equation of selective attention, the multi-variable regression equation of the conversion attention, the multi- van able regression equation of the dispersity attention and the multi-variable regression equation of the attention breadth. The first answer score and the first EEG score are substituted into the continuous attention multi-variable regression equation to obtain the fractional value of the continuous attention game. The second answer score and the second EEG score are correspondingly substituted into a multi -variable regression equation of other attention to obtain the fractional values of other attention games. [00148] Reference is now made to Fig. 12, which is a schematic flow chart of a third embodiment of the attention evaluation method, consistent with the embodiments of the present disclosure. Based on the first embodiment and the second embodiment, an evaluation person needs to be selected before the user is evaluated, and the corresponding algorithm is optimized according to the question answering result of the evaluation person. Therefore, before step S100, the attention evaluation method may further comprise the following steps:

[00149] In step S410, the attention evaluation method comprises acquiring a first evaluation answer data and a first self-score of an evaluation person during the continuous attention game, and acquiring corresponding first evaluation EEG data through the intelligent wearable device. Here, the persistent attention refers to the concentration persistence of an important message, and the algorithm of the algorithm is inconsistent with the algorithm of other attention scores according to the embodiment of the invention, the algorithm optimization process of the continuous attention score is introduced.

[00150] In some embodiments, the attention evaluation method comprises obtaining a first evaluation answer data and a first self-score of an evaluation person in a continuous attention game, and the corresponding first evaluation EEG data is acquired through the intelligent wearable device. The first evaluation answer data comprises the maximum continuous answer correct number and the answer total number. The first self-score is the self-scoring number input by the attention evaluation ter inal and is input by the attention evaluation terminal before the evaluation person finishes the continuous attention game. The meaning represented by the continuous attention can be explained to ensure that the evaluation person performs self- evaluation after understanding, the accuracy of the algorithm is improved, and the accuracy of the final evaluation result is improved. It should be noted that, in order to ensure the accuracy of the attention algorithm, certain requirements are provided for selection and quantity of evaluation persons, the selection requirements are not specifically set forth, and the number of the evaluated persons is within a certain range, and can be selected according to actual conditions. In some embodiments, for example, 15 evaluated persons can be selected for evaluation.

[00151] In step S420, the attention evaluation method comprises preprocessing the first evaluation answer data and the first evaluation EEG data obtaining corresponding first scores and second scores. The percentage value of the maximum continuous answer correct number and the total answer number in the first evaluation answ^rer data is calculated, namely, a first score, for example, out of a total of five question of the continuous attention game (that is, the total number of answer questions is 5), a certain tester answers the third, fourth question (that is, the maximum continuous answer correct number is 2), and then the first score is 2/5 * 100 = 40. Then the average concentration force value corresponding to the first evaluation EEG data is calculated through a concentration force algorithm, the time tl corresponding to the average concentration force value is obtained according to the first evaluation EEG data and the average concentration force value, and calculating the percentage value of the time tl and the total game time, namely a second score. The concentration force algorithm is obtained through multiple iterations of experiments and optimization.

[00152] In step S430, the attention evaluation method comprises performing statistical estimation on the first score and the second score obtaining a corresponding first distribution curve and a second distribution curve, respectively. The specific implementation principle and technology can be referred to in prior art and will not be described in detail herein.

[00153] In step S440, the attention evaluation method comprises obtaining a continuous attention evaluation answer score according to the first score and the first distribution curve, and obtaining a continuous attention evaluation EEG score according to the second score and the second distribution curve. Specifically, calculating the area si 1 between the curve of the left part of the first distribution curve corresponding to the first distribution curve and the horizontal axis, and the area s 12 between the first distribution curve and the horizontal axis, and then calculating the percentage value of the area si 1 and the area sI2, namely the evaluation answer score of the continuous attention. For example, the first distribution curve is 40, the corresponding first distribution curve is shown in Fig. 13, and sll is the area corresponding to the dark/shadow part in Fig. 13. Then calculating the area s2l between the curve of the left part of the second distribution curve corresponding to the second distribution curve and the horizontal axis, and the area s22 between the second distribution curve and the horizontal axis, and then calculating the percentage value of the area s21 and the area s22, namely evaluating the EEG scores for continuous attention. For convenience of explanation, the first and second scores can be marked as fl and f2 respectively, the first distribution curve and the second distribution curve are marked as 11 (x) and f2 (x) respectively, and the specific formula is as follows:

511

continuous attention evaluation answer score x 100 100;

5Ϊ2

521

continuous attention evaluation EEG score

522

[00154] In step S450, the attention evaluation method comprises establishing a first multivariable regression equation according to the continuous attention evaluation answer score, the continuous attention evaluation EEG score and the first self-score, and obtaining a first optimal coefficient of the first multivariable regression equation through a normal equation, substituting the first optimal coefficient into the first multivariable regression equation to obtain a multivariable regression equation of the continuous attention of the preset multivariable regression equation. The first multi-variable regression equation can be as follows: Z1 = alXl + blYl, wherein the first multi-variable regression equation is shown in the specification the method comprises the following steps: Z1 represents a first self-score; XI represents the evaluation answer score of the continuous attention; Y 1 represents the evaluation EEG score of the continuous attention. The method may include obtaining a first optimal coefficient of the first multivariable regression equation through a regular equation, substituting the first optimal coefficient into the first multivariable regression equation to obtain a multivariable regression equation of the continuous attention of the preset multivariable regression equation.

[00155] For example, 15 evaluation persons are selected, 15 sets of first evaluation answer data, 15 sets of first self-scores and 15 sets of first evaluation EEG data are acquired. After being processed, corresponding evaluation and answer scores of 15 groups of continuous attention and evaluation EEG scores of 15 groups of continuous attention are obtained. Then, the answer scores are evaluated according to 15 sets of first self-scoring and 15 sets of continuous attention, 15 sets of continuous attention evaluation EEG scores and a first multivariable regression equation, and finding out the optimal coefficients al and bl through a regular equation, assuming that al = 0.6 and bl = 0.4. The segmentation calculation formula of the continuous attention is as follows: Zl = 0.6X1 +0.4 Yi.

[00156] In some embodiments, before step S 100 of Fig. 11, the attention evaluation method may further comprise the following steps illustrated in Fig. 14.

[00157] In step S510, the attention evaluation method may comprise acquiring a second evaluation answer data and a second self-score of the evaluated person during the other attention game, and acquiring corresponding second evaluation EEG data through the intelligent wearable device. The algorithm of other attention scores is inconsistent with the algorithm of the continuous attention score, so that the algorithm optimization process of other attention scores is introduced in the embodiment, namely, the algorithm optimization process of the four attention scores of the attention, the conversion attention, the dispersibility attention and the attention breadth.

[00158] In some embodiments, the attention evaluation terminal firstly obtains a second evaluation answer data and a second self-score of an evaluation person for performing other attention games, and the corresponding second evaluation EEG data is acquired through the intelligent wearable device. The second evaluation answer data comprises the answer correct number and the answer error number, and the second self-score is the evaluation person after other attention games are completed lire attention evaluation terminal inputs the self-scoring number of the attention evaluation terminal (before the evaluation of the evaluation person), the meaning corresponding to other attention can be explained so as to ensure that the evaluation person can perform self-evaluation after understanding, the accuracy of the algorithm is improved, and the accuracy of the final evaluation result is improved). It should be noted that the other attention games include selective attention games, conversion attention games, dispersed attention games and attention breadth games. Therefore, in the acquisition and calculation process of the data in the embodiment, the data corresponding to the four types of attention are also acquired. The finally obtained multi-variable regression equation of the other attention also comprises four types, namely a multi-variable regression equation of the selective attention, the multi-variable regression equation of the conversion attention, the multi-variable regression equation of the dispersity attention and the multi-variable regression equation of the attention breadth.

[00159] In step S520, the attention evaluation method may comprise preprocessing the second evaluation answer data and the second evaluation EEG data to obtain corresponding third scores and fourth scores. The difference value of the answer error number is subtracted from the answer correct number in the second evaluation answer data, and the difference value is the third score. Then, the average concentration force value corresponding to the second evaluation EEG data is calculated through a concentration force algorithm, and the average concentration force value is the fourth score. The concentration force algorithm is obtained through multiple iterations of experiments and optimization. [00166] In step S530, the attention evaluation method may comprise performing statistical estimation on the third sub- value and the fourth sub-value to obtain a corresponding third distribution curve and a fourth distribution curve, respectively. The specific implementation principle and technology can be referred to in the prior art and will not be described in detail herein.

[00161] In step S540, the atention evaluation method may comprise obtaining evaluation answer scores of other attention according to the third distribution curve and the third distribution curve, and obtaining evaluation EEG scores of other attention according to the third distribution curve and the fourth distribution curve. For example, the area s31 between the curve of the left part of the third distribution curve corresponding to the third distribution curve and the horizontal axis is calculated, and the area s32 between the third distribution curve and the horizontal axis, and then calculating the percentage value of the area s31 and the area s32, namely the evaluation answer scores of other attention. The fourth sub-value is calculated to correspond to the area s41 between the curve of the left part of the fourth distribution curve corresponding to the fourth distribution curve and the horizontal axis, and the area s42 between the third distribution curve and the horizontal axis, and then calculating the percentage value of the area s41 and the area s42 to obtain the evaluation EEG scores of other attention. For convenience of explanation, the third and fourth scores can be marked as C3 and C4

respectively, the third distribution curve and the fourth distribution curve are marked as f3 (x) and f4 (x) respectively, and the specific formula is as follows:

531

other attention evaluation answer score x 100 100;

S02

541

other attention evaluation EEG score x 100 = 100

542

[00162] In step S550, the attention evaluation method may comprise constructing a second multivariable regression equation according to the evaluation answer scores of the other attention, the evaluation EEG scores of other attention and the second self-score, and obtaining a second optimal coefficient of the second multivariable regression equation through a normal equation, substituting the second optimal coefficient into the second multivariable regression equation to obtain a multivariable regression equation of other attention of the preset multivariable regression equation.

[00163] The method may further comprise establishing a second multivariable regression equation according to evaluation answer scores of other attention, evaluation EEG scores of other attention and second self-score, and the second multi- variable regression equation can be Z2 =a2X2 +b2Y2, wherein Z2 represents a second self-score; X2 represents an evaluation answer score of other attention; Y2 represents the evaluation EEG scores of other attention, and then, and a second optimal coefficient of the second multi-variable regression equation is obtained through a normal equation, substituting the second optimal coefficient into the second multi-variable regression equation to obtain a multi-variable regression equation of other attention of the preset multi-variable regression equation.

[00164] For example, for selective attention, in the above example, 15 sets of second evaluation answer data are acquired since 15 evaluated persons are selected, 15 sets of second self-scores and 15 sets of second evaluation EEG data after being processed, 15 sets of other attention evaluation answer scores and 15 sets of other attention evaluation EEG scores are obtained. Then, according to 15 sets of second self-scoring, 15 sets of other attention evaluation answer scores, 15 sets of other attention evaluation EEG scores and a second multivariable regression equation. Finding out the optimal coefficients a2 and b2 through a regular equation, and assuming that a2 = 0.5 and b2 = 0.7, the division calculation formula of the selective attention is as follows: Z2 = 0.5 X2 + 0.7 Y2.

[00165] It should be noted that steps S410-S450 in the second embodiment and steps S510-S550 in the third embodiment may not be executed in sequence or an order. Further, based on the embodiments shown in Figs. 10-12, a fifth embodiment (no flowchart shown) of the attention evaluation method of the present invention is proposed.

[00166] In step S210, the attention evaluation method may comprise preprocessing the first answer data, the first EEG data, the second answer data and the second EEG data respectively, and a fifth sub-value, a sixth sub-value, a seventh sub-value and an eighth sub value of the corresponding fifth sub- value, sixth sub- value, seventh sub-value and eighth sub value are obtained. The attention evaluation terminal obtains first answer data and second answer data when the user performs continuous attention games and other attention games, and the corresponding first EEG data and the corresponding second EEG data are acquired through the intelligent wearable device, respectively. Preprocessing the first answ^rer data, the first EEG data, the second answer data and the second EEG data respectively, a fifth sub-value, a sixth sub- value, a seventh sub-value and an eighth sub- value corresponding to the fifth sub-value, the sixth sub- value, the seventh sub-value and the eighth sub-value are obtained. Specifically, calculating the percentage value of the maximum continuous answer correct number and the answer total number in the first answer data, namely the fifth score: and the difference value of the answer correct number in the second evaluation answer data and the answer error number is calculated, and the average concentration force value corresponding to the first EEG data is calculated through a concentration force algorithm, the time corresponding to the average concentration force value is obtained according to the first EEG data and the average concentration force value, and the percentage value of the time and the total game time is calculated, namely the seventh score; calculating the average concentration force value corresponding to the second EEG data through a concentration force algorithm, namely the eighth score.

[00167] In step S220, the attention evaluation method may comprise, according to the fifth sub- value and the first distribution curve, integrating the fifth sub-value and the first distribution curve by integrating the lov er area of the first curve corresponding to the fifth score and the first total area between the first distribution curve and the horizontal axis, and recording the percentage value of the lower area of the first curve and the first total area as a first answer score.

[00168] In step S230, the attention evaluation method may comprise, according to the sixth sub-value and the second distribution curve, integrating the sixth sub-value and the second distribution curve by integrating the lower area of the second curve corresponding to the sixth score and the second total area between the second distribution curve and the horizontal axis, and recording the percentage value of the lower area of the second curve and the second total area as first EEG scores.

[00169] In step S240, the attention evaluation method may comprise, according to the seventh sub-value and the third distribution curve, integrating the seventh sub-value and the third distribution curve by integrating the lower area of the third curve corresponding to the seventh score and the third total area between the third distribution curve and the horizontal axis, and recording the percentage value of the lower area of the third curve and the third total area as a second answer score.

[00170] In step S250, the attention evaluation method may comprise, obtaining an eighth score and a fourth distribution curve through integral according to the eighth score and the fourth distribution curve the fourth curve corresponding to the eighth score and the fourth total area between the fourth distribution curve and the horizontal axis, and recording the percentage value of the lower area of the fourth curve and the fourth total area as second EEG scores.

[00171] Then, according to the fifth score and the first distribution curve, obtaining the first curve lower area corresponding to the fifth score and the first total area between the first distribution curve and the horizontal axis through integration, and the percentage value of the lower area of the first curve and the first total area is marked as the first answer score. The first distribution curve is obtained in an algorithm optimization process, the fifth sub-value is marked as C5. For convenience of description, and according to the fifth sub- value C5 and the first distribution curve fl (x) and the lower area of the first curve corresponding to the fifth sub-value obtained through integration is recorded as s!3, wherein the first total area between the first distribution curve and the horizontal axis is sl2:

513

S13

first answer score x 100 100 ; 512

[00172] Similarly, the second curve lower area corresponding to the sixth score and the second total area between the second distribution curve and the horizontal axis are obtained through integral according to the sixth score and the second distribution curve, and the percentage value of the lower area of the second curve and the second total area is recorded as the first EEG score. Obtaining a third curve lower area corresponding to the seventh sub-value and a third total area between the third distribution curve and the horizontal axis according to the seventh sub-value and the third distribution curve, and the percentage value of the lower area of the third curve and the third total area is marked as the second answer score. Obtaining the lower area of the fourth curve corresponding to the eighth value and the fourth total area between the fourth distribution curve and the horizontal axis according to the eighth value and the fourth distribution curve the percentage value of the lower area of the fourth curve and the fourth total area is recorded as the second EEG score. The specific treatment method can be described with reference to the above-described embodiments, and is not further described herein. It should be noted that the execution of each step in steps S220 to S250 is not performed in sequence.

[00173] At this time, step S300 can further comprise the following steps. In step S310, the attention evaluation method may comprise, according to the first answer score, and the fractional value of the follow-up atention game is obtained through a multi-variable regression equation of the continuous attention in the first EEG sub-value and the preset multi- variable regression equation, and obtaining the fractional values of other attention according to the second answer score, the second EEG score and the multi- variable regression equation of other atention in the preset multivariable regression equation. Here, according to a first answer score, the first EEG scores are substituted into a multivariable regression equation of the continuous attention in a preset multivariable regression equation, and the fractional value of the continuous attention game can be obtained. Similarly, the second answer score and the second EEG score are substituted into the multi- variable regression equation of other attention in the preset multivariable regression equation, so that the fractional values of other attention games can be obtained.

[00174] It is contemplated the disclosed methods for neuro-feedback training may have various applications, both medical and non-medical. For example, as mentioned above, the disclosed methods may be used for training and improving attention related behaviors. As such, the disclosed methods may be used for effectively relieving or treating attention related medical conditions, such as ADHD (attention deficit hyperactivity disorder). The present disclosure does not limit the application areas of the disclosed methods and systems.

[00175] It will be apparent to those skilled in the art that various modifications and variations can be made to the disclosed neuro-feedback training systems and related methods. Other embodiments will be apparent to those skilled in the art from consideration of the specification and practice of the disclosed neuro-feedback training system and related methods.

It is intended that the specification and examples be considered as exemplary only, with a true scope being indicated by the following claims and their equivalents.

[00176] The invention further provides an attention evaluation system. The attention evaluation system comprises an attention evaluation terminal and an intelligent wearable device, and further comprises a memory, a processor and an attention evaluation program stored on the memory and capable of running on the processor, the attention evaluation program is executed by the processor so as to achieve the attention evaluation method as described in any one embodiment. The embodiments of the attention evaluation system of the present invention are basically the same as the embodiments of the attention evaluation method described above, and are not described in detail herein. The invention further provides a computer readable storage medium, and an attention evaluation program is stored on the computer readable storage medium, the atention evaluation program is executed by the processor so as to achieve the attention evaluation method as described in any one embodiment. The embodiments of the computer readable storage medium and the embodiments of the above attention evaluation method are basically the same, and are not described in detail herein. It should be noted that the terms "comprising," " comprising, "or any other variants thereof are intended to cover a non exclusive inclusion, such that a process comprising a series of elements is contemplated, methods, articles, or systems include not only those elements but also other elements not explicitly listed, or also elements inherent to such processes, methods, articles, or systems.. In the case of no more restrictions, the statement“includes one/’ The defined elements do not exclude other identical elements in the process, method, article, or system comprising the element.

The sequence numbers of the embodiments of the present invention are only for description and do not represent the disadvantages and disadvantages of the embodiments.

[00177] Through the description of the above embodiments, it will be apparent to those skilled in the art that the above-described embodiments can be implemented by means of a software plus necessary universal hardware platform, the invention can also be implemented by hardware, but in many cases, the former is a better implementation mode.. Based on such understanding, the technical solution of the present invention essentially or the part that makes contributions to the prior art can be embodied in the form of a software product, the computer software product is stored in a storage medium (such as a ROM/RAM, a magnetic disk and an optical disk) as described above), wherein the instructions are used for enabling one terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or network equipment and the like) to execute the method disclosed by the embodiment of the invention [00178] The above is only a preferred embodiment of the present invention, and is not intended to limit the patent scope of the present invention, and any equivalent structure or equivalent process conversion made by using the specification and the accompanying drawings of the present invention is used, are directly or indirectly applied to other related technical fields, and are all the same as those in the patent protection scope of the present invention.

Claims

What is claimed is:

1. A processor-implemented method for personalizing an educational experience based on neuro-feedback training, the method comprising:

detecting, using a processor, a brainwave signal of a learner generated in response to a stimulus;

analyzing, using the processor, at least one characteristic of the brainwave signal;

generating, by the processor based on the analysis, a cognitive workload index indicative of an amount of effort applied by the learner to respond to the stimulus;

adjusting the stimulus based on the generated cognitive workload index to personalize the educational experience.

2. The method of claim 1, further comprising updating in real-time, the cognitive workload index in a database associated with the processor.

3. The method of claim 2, further comprising adjusting the stimulus based on the updated cognitive workload index, wherein the stimulus comprises an educational task.

4. The method of claim 2, further comprising:

generating a personalized learner profile including information associated with a learner; and

updating the personalized learner profile based on the updated cognitive workload index and the adjusted stimulus.

5. The method of claim 1, wherein analyzing the at least one characteristic of the brainwave signal comprises analyzing one of a waveform, a frequency, a frequency distribution, an amplitude, and a periodicity of the brainwave signal.

6. The method of claim 3, further comprising transmitting by the processor via a communication network, the updated cognitive workload index to at least one of an online learning platform, an offline learning program, and an educator.

7. The method of claim 6, wherein transmitting the updated cognitive workload index comprises wirelessly communicating with a device associated with at least one of the online learning platform, the offline learning program, and the educator.

8. The method of claim 1 , wherein generating the cognitive workload index comprises determining the cognitive workload index using an artificial intelligence-based algorithm.

9. The method of claim 4, wherein adjusting the stimulus comprises adjusting at least one of a difficulty, a pace, and a sequence of a plurality of educational tasks presented to the learner.

10. The method of claim 4, wherein the brainwave signal is indicative of an electrical activity of a brain of the learner.

11. The method of claim 1, wherein the brainwave signal comprises an

electroencephalography (EEG) signal.

12. The method of claim 1 , wherein the processor comprises a sensor disposed on a wearable device and configured to receive and detect the brainwave signal.

13. The method of claim 12, wherein the wearable device comprises a headband worn by the learner.

14. A processor- implemented method for personalizing an educational experience based on neuro-feedback training, the method comprising: detecting, using a processor, a brainwave signal associated with an electrical activity of a brain of a learner, the brain ^rave signal generated in response to a stimulus;

analyzing, using the processor, at least one characteristic of the brainwave signal ;

generating, by the processor based on the analysis, an attention score indicative of a level of engagement of the learner;

determining, by the processor, a performance score of the learner based on the response to the stimulus;

adjusting the stimulus based on a combination of the attention score and the performance score to personalize the educational experience of the learner.

15 The method of claim 14, further comprising updating in real-time, the attention score and the performance score in a database associated with the processor.

16. The method of claim 15, further comprising adjusting the stimulus based on the updated attention score and the updated performance score, wherein the stimulus comprises an educational task.

17. The method of claim 15, further comprising:

generating a personalized learner profile including information associated with the learner; and

updating the personalized learner profile based on the updated attention score, the updated performance score, and the adjusted stimulus.

18. The method of claim 14, wherein analyzing the at least one characteristic of the brainwave signal comprises analyzing one of a wavefonn, a frequency, a frequency distribution, an amplitude, and a periodicity of the brainwave signal.

19. The method of claim 16, further comprising transmitting by the processor via a communication network, the updated attention score and the updated performance score to at least one of an online learning platform, an offline learning program, and an educator.

20. The method of claim 19, wherein transmitting the updated attention score and the updated performance score comprises wirelessly communicating with a device associated with at least one of the online learning platform, the offline learning program, and the educator.

21. Hie method of claim 14, wherein generating the attention score comprises determining the attention score using an artificial intelligence (AΪ) based algorithm.

22. The method of claim 14, wherein adjusting the stimulus comprises adjusting at least one of a difficulty, a pace, and a sequence of a plurality of educational tasks presented to the learner.

23. The method of claim 14, wherein the brainwave signal comprises an

electroencephalography (EEG) signal.

24. The method of claim 14, wherein the processor comprises a sensor disposed on a wearable device and configured to receive and detect the brainwave signal.

25. Hie method of claim 24, wherein the wearable device comprises a headband worn by the learner.

26. A neuro-feedback training system comprising:

a sensor coupled with a processor, the processor configured to:

detect a brainwave signal associated with an electrical activity of a brain of a learner, the brainwave signal generated in response to a stimulus;

analyze at least one characteristic of the brainwave signal;

generate, based on the analysis, an attention score indicative of a level of engagement of the learner;

determine a performance score of the learner based on the response to the stimulus; adjus ing the stimulus based on a combination of the attention score and the performance score to personalize the educational experience of the learner.

27 The system of claim 26, wherein the brainwave signal comprises an

electroencephalography (EEG) signal.

28. The system of claim 26, wherein the sensor is mounted on a wearable device and configured to receive and detect the brainwave signal.

29. The system of claim 28, wherein the wearable device comprises a headband worn by the learner.

30. The system of claim 26, wherein generating the attention score comprises determining the attention score using an artificial intelligence (AI) based algorithm.

31. The system of claim 26, wherein the stimulus comprises a plurality of educational tasks.

32. The system of claim 26, wherein the at least one characteristic of the brainwave signal comprises one of a waveform, a frequency, a frequency distribution, an amplitude, and a periodicity of the brainwave signal.

33. A non-transitory computer- readable medium storing instructions wiiich, when executed, cause one or more processors to perform a method for neuro-feedback training, the method comprising:

detecting a brainwave signal associated with an electrical activity of a brain of a learner, the brainwave signal generated in response to a stimulus;

analyzing at least one characteristic of the brain wave signal:

generating, based on the analysis, an attention score indicative of a level of engagement of the learner; determining a performance score of the learner based on the response to the stimulus; adjusting the stimulus based on a combination of the attention score and the performance score to personalize the educational experience of the learner.

34. An attention evaluation method is characterized by being applied to an attention evaluation system, wherein the attention evaluation system comprises an attention evaluation terminal and an intelligent wearable device; the attention evaluation method comprising:

acquiring, using the attention evaluation terminal, answer data from a user performing a preset attention game;

acquiring corresponding brain wave data through the intelligent wearable device;

processing the answer data and the brain wave data to obtain a corresponding answer score and an electroencephalogram (EEG) score; and

determining, using a preset technique, an attention score based on the answer score and the EEG score.

35. The method of claim 34, wherein the preset technique comprises using a preset multivariable regression equation, and wherein the preset multivariable regression equation is Z=aX +bY, wherein Z is the attention score, X is the answer score, Y is the EEG score, and a and b are corresponding optimal coefficients.

36. The method of claim 34, further comprising a preset attention game, wherein the preset attention game comprises a continuous attention game and other attention games, and the other attention games comprise at least one of a selective attention game and a conversion attention game, a dispersion attention game and an attention breadth game, wherein the attention evaluation terminal acquires answer data when a user performs the preset attention game, and acquiring corresponding brain wave data through the intelligent wearable device, the method comprising:

acquiring, using the attention evaluation terminal, first answer data and second answer data when the user performs continuous attention games and other attention games, and respectively acquiring corresponding first EEG data and second EEG data through the intelligent wearable device;

processing the answer data and the EEG data to obtain corresponding answer scores and EEG scores the method comprises the following steps:

processing the first answer data, the first EEG data, the second answer data and the second EEG data respectively, and obtaining a corresponding first answer score, a first EEG score, a second answer score and a second EEG score; and

obtaining the attention value according to the answer score, the EEG score and the preset multivariable regression equation comprises the following steps:

first and second answer scores according to the first answer score, the first EEG score and the second answer score, a second EEG sub-value and a preset multi-variable regression equation to obtain a fractional value of the continuous attention game and a fractional value of other attention.

37. The method of claim 36, further comprising:

acquiring first evaluation answer data and first self-scores when an evaluation person performs the continuous attention game, and acquiring corresponding first evaluation EEG data through the intelligent wearable device;

preprocessing the first evaluation answer data and the first evaluation EEG data to obtain corresponding first scores and second scores;

performing statistical estimation on the first and second scores to obtain a corresponding first distribution curve and a second distribution curve; and

obtaining a continuous attention evaluation answer score according to the first score and the first distribution curve, and obtaining a continuous attention evaluation EEG score according to the second score and the second distribution curve, wherein

the first multivariable regression equation is constructed according to the continuous attention evaluation answer score, the continuous attention evaluation EEG score and the first self-score, and obtaining a first optimal coefficient of the first multivariable regression equation through a normal equation, substituting the first optimal coefficient into the first multivariable regression equation to obtain a multivariable regression equation of the continuous attention of the preset multivariable regression equation.

38. The method of claim 37, further comprising:

acquiring second evaluation answer data and second self-scores when the evaluation person performs the other attention games, and acquiring corresponding second evaluation EEG data through the intelligent wearable device;

preprocessing the second evaluation answer data and the second evaluation EEG data to obtain corresponding third and fourth scores;

performing statistical estimation on the third sub-value and the fourth sub-value to obtain a corresponding third distribution curve and a fourth distribution curve;

obtaining evaluation answer scores of other attention according to the third distribution curve and the third distribution curve, and obtaining evaluation EEG scores of other attention according to the fourth distribution curve and the fourth distribution curve; and

establishing a second multivariable regression equation according to the evaluation answer scores of the other attention, the evaluation EEG scores of other attention and the second self-score, and obtaining a second optimal coefficient of the second multivariable regression equation through a normal equation, substituting the second optimal coefficient into the second multi variable regression equation to obtain a multivariable regression equation of other attention of the preset multivariable regression equation.

39. The method of claim 38, wherein the processing is performed on the first answer data, the first EEG data, the second answer data and the second EEG data respectively, and obtaining a corresponding first answer score, a first EEG score, a second answer score and a second EEG score the method comprises the following steps:

preprocessing the first answer data, the first EEG data, the second answer data and the second EEG data respectively, and a fifth sub-value, a sixth sub-value, a seventh sub-value and an eighth sub-value of the corresponding fifth sub-value, sixth sub-value, seventh sub-value and eighth sub-value are obtained; obtaining a first curve lower area corresponding to the fifth score and a first total area between the first distribution curve and the cross axis according to the fifth score and the first distribution curve by integrating, and recording the percentage value of the lower area of the first curve and the first total area as a first answer score;

obtaining a second curve lower area corresponding to the sixth sub-value and a second total area between the second distribution curve and the horizontal axis according to the sixth sub-value and the second distribution curve, and recording the percentage value of the lower area of the second curve and the second total area as first EEG scores:

obtaining a third curve lower area corresponding to the seventh sub- value and a third total area between the third distribution curve and the horizontal axis according to the seventh sub- value and the third distribution curve, and recording the percentage value of the lower area of the third curve and the third total area as a second answer score: and

obtaining the lower area of the fourth curve corresponding to the eighth value and the fourth total area between the fourth distribution curve and the horizontal axis according to the eighth and fourth distribution curves, and recording the percentage value of the lower area of the fourth curve and the fourth total area as second EEG scores.

40. The method of claim 38, characterized in that, according to the first answer score, the first EEC score and the second answer score, a second EEG score and a preset multivariable regression equation to obtain the score of the follow-up attention game and the score of other attention; the method comprising obtaining the fractional value of the follow-up attention game according to the first answer score, the first EEG score and the multivariable regression equation of the continuous attention in the preset multivariable regression equation, and obtaining the fractional values of other attention according to the second answer score, the second EEG score and the multi- variable regression equation of other attention in the preset multivariable regression equation.

41. The method of claim 40, wherein the first answer data and the first evaluation answer data comprise the maximum continuous answer correct number and the answer total number, wherein the second answer data and the second evaluation answer data comprise answer correct numbers and answer errors.

42 An attention evaluation system is characterized in that the attention evaluation system comprises an attention evaluation terminal and an intelligent wearable device and further comprises a memory, a processor and an attention evaluation program stored on the memory and capable of running on the processor, the attention evaluation program is executed by the processor, so that the attention evaluation method according to any one of claims 34 to 41 is realized.

43 A computer readable storage medium is characterized in that an attention evaluation program is stored on the computer readable storage medium, the attention evaluation program is executed by the processor to realize the attention evaluation method according to any one of claims 34 to 41.