CN113509189B

CN113509189B - Learning state monitoring method and related equipment thereof

Info

Publication number: CN113509189B
Application number: CN202110769337.9A
Authority: CN
Inventors: 胡铭铭; 梁华东; 李鑫
Original assignee: iFlytek Co Ltd
Current assignee: iFlytek Co Ltd
Priority date: 2021-07-07
Filing date: 2021-07-07
Publication date: 2024-07-05
Anticipated expiration: 2041-07-07
Also published as: CN113509189A

Abstract

The application discloses a learning state monitoring method and related equipment thereof, wherein the method comprises the following steps: after determining that the monitored object completes the test question to be evaluated, determining the fatigue score to be used of the monitored object according to the brain electricity data to be used of the monitored object, the eye movement data to be used of the monitored object, the answer information to be used of the monitored object and the attribute information of the test question to be evaluated; if the fatigue score to be used of the monitored object is higher than the fatigue score threshold, determining that the learning state of the monitored object is a fatigue state when the monitored object replies to the test question to be evaluated, and thus realizing real-time monitoring of the learning state of the monitored object.

Description

Learning state monitoring method and related equipment thereof

Technical Field

The application relates to the technical field of artificial intelligence, in particular to a learning state monitoring method and related equipment thereof.

Background

Learning has long been the focus of research. For students, the learning state is an important reason for influencing the learning efficiency and the performance of the students. Students learn mainly by mental activities, and high-intensity or long-time continuous mental activities bring uncomfortable states (such as fatigue states) to students, and the uncomfortable states can lead to weakening of learning ability, reduction of learning efficiency and mental 'exhaustion', and simultaneously lead the students to generate emotional reactions such as boredom to learning, and the learning effect of the students can be poorer and worse over time.

However, how to monitor learning states is still a technical problem to be solved.

Disclosure of Invention

The embodiment of the application mainly aims to provide a learning state monitoring method and related equipment thereof, which can realize monitoring on learning states.

The embodiment of the application provides a learning state monitoring method, which comprises the following steps:

After determining that a monitored object completes a test question to be evaluated, determining a fatigue score to be used of the monitored object according to brain electricity data to be used of the monitored object, eye movement data to be used of the monitored object, answer information to be used of the monitored object and attribute information of the test question to be evaluated; the electroencephalogram data to be used of the monitored object comprises electroencephalogram data of the monitored object when the monitored object replies to the test question to be evaluated; the eye movement data to be used of the monitored object comprises eye movement data of the monitored object when the monitored object replies to the test question to be evaluated; the answer information to be used of the monitored object comprises answer data of the monitored object aiming at the test question to be evaluated;

and if the fatigue score to be used of the monitored object is higher than a fatigue score threshold value, determining that the learning state of the monitored object is a fatigue state when the monitored object replies to the test question to be evaluated.

In one possible implementation manner, the determining process of the fatigue score to be used of the monitored object includes:

Determining a physical fatigue score of the monitored object according to the electroencephalogram data to be used of the monitored object and the eye movement data to be used of the monitored object;

And determining the fatigue score to be used of the monitored object according to the physical fatigue score of the monitored object, the answer information to be used of the monitored object and the attribute information of the test question to be evaluated.

In one possible embodiment, the determining of the physical fatigue score of the monitored subject includes:

extracting characteristics of the electroencephalogram data to be used of the monitored object to obtain electroencephalogram characteristics to be used of the monitored object;

performing feature analysis on the eye movement data to be used of the monitored object to obtain eye movement features to be used of the monitored object;

Factor analysis is carried out on the electroencephalogram feature to be used of the monitored object and the eye movement feature to be used of the monitored object, so that at least one common factor and a weighting weight corresponding to the at least one common factor are obtained;

And carrying out weighted summation on the at least one common factor according to the weighted weight corresponding to the at least one common factor to obtain the physical fatigue score of the monitored object.

In a possible implementation manner, if the answer information to be used includes an answer time to be used and an answer accuracy to be used, and the attribute information includes a reference time, determining the fatigue score to be used of the monitored object according to the physical fatigue score of the monitored object, the answer information to be used of the monitored object, and the attribute information of the test question to be evaluated includes:

Determining a response time score of the monitored object according to the ratio between the to-be-used response time of the monitored object and the reference time of the to-be-evaluated test question; the answer time to be used of the monitored object refers to answer time of the monitored object for the test question to be evaluated;

Determining a response accuracy score of the monitored object according to the reciprocal of the accuracy of the to-be-used answer of the monitored object; the accuracy of the answer to be used of the monitored object refers to the accuracy of the answer of the monitored object to the test question to be evaluated;

and determining the fatigue score to be used of the monitored object according to the physical fatigue score of the monitored object, the response time length score of the monitored object and the response accuracy score of the monitored object.

In one possible implementation manner, the determining the fatigue score to be used of the monitored object according to the physical fatigue score of the monitored object, the response duration score of the monitored object and the response accuracy score of the monitored object includes:

and determining the fatigue score to be used of the monitored object according to the product of the physical fatigue score of the monitored object, the response time length score of the monitored object and the response accuracy score of the monitored object.

In one possible implementation, the fatigue score threshold is generated according to sample electroencephalogram data of a sample object, sample eye movement data of the sample object, sample answer information of the sample object and attribute information of a sample test question; the sample test questions and the test questions to be evaluated meet a preset association relation; the sample electroencephalogram data of the sample object comprises electroencephalogram data of the sample object when the sample object replies to the sample test question; the sample eye movement data of the sample object comprises eye movement data of the sample object when the sample object replies to the sample test question; the sample answer information of the sample object comprises answer data of the sample object for the sample test question.

In a possible implementation manner, the sample test question and the test question to be evaluated meet a preset association relationship, and the method includes:

the test question difficulty of the sample test questions is the same as the test question difficulty of the test questions to be evaluated;

Or alternatively

The test question type of the sample test question is the same as the test question type of the test question to be evaluated;

Or alternatively

The test question type and the test question difficulty of the sample test question are respectively the same as the test question type and the test question difficulty of the test question to be evaluated;

Or alternatively

And the sample test question is the test question to be evaluated.

In one possible embodiment, the generating of the fatigue score threshold includes:

Determining a sample fatigue score of the sample object according to the sample electroencephalogram data of the sample object, the sample eye movement data of the sample object, the sample answer information of the sample object and the attribute information of the sample test question;

Obtaining at least one personality score for the sample object;

Determining the fatigue score threshold based on at least one personality score of the sample object and a sample fatigue score of the sample object.

In one possible embodiment, if the number of personality scores is N and the number of sample objects is M, determining the fatigue score threshold according to the at least one personality score of the sample object and the sample fatigue score of the sample object includes:

According to sample fatigue scores of M sample objects, a normal distribution mean value corresponding to the sample fatigue scores, a normal distribution standard deviation corresponding to the sample fatigue scores and a normal distribution map corresponding to the sample fatigue scores are obtained; wherein M is a positive integer;

According to the nth personal lattice score of the M sample objects, determining a normal distribution mean value corresponding to the nth personal lattice score, a normal distribution standard deviation corresponding to the nth personal lattice score and a normal distribution map corresponding to the nth personal lattice score; wherein N is a positive integer, N is less than or equal to N, and N is a positive integer;

And determining the fatigue score threshold according to the N personality scores of the M sample objects, the normal distribution map corresponding to the sample fatigue scores, the normal distribution average value corresponding to the sample fatigue scores, the normal distribution standard deviation corresponding to the sample fatigue scores, the normal distribution map corresponding to the N personality scores, the normal distribution average value corresponding to the N personality scores and the normal distribution standard deviation corresponding to the N personality scores.

In one possible embodiment, the determining of the fatigue score threshold includes:

Determining a test question score corresponding to the nth person lattice score according to the nth person lattice score of the M sample objects, a normal distribution mean value corresponding to the sample fatigue score, a normal distribution standard deviation corresponding to the sample fatigue score, a normal distribution mean value corresponding to the nth person lattice score, a normal distribution standard deviation corresponding to the nth person lattice score and the correlation degree between a normal distribution map corresponding to the sample fatigue score and a normal distribution map corresponding to the nth person lattice score; wherein N is a positive integer, N is less than or equal to N, and N is a positive integer;

And determining the fatigue score threshold according to the N personal scores of the M sample objects and the test question scores corresponding to the N personal scores.

In one possible embodiment, the method further comprises:

Generating reminding information after determining that the fatigue score to be used of the monitored object is higher than a fatigue score threshold value, and sending the reminding information to the monitored object; the reminding information is used for reminding the monitored object to rest.

The embodiment of the application also provides a learning state monitoring device, which comprises:

The score determining unit is used for determining a fatigue score to be used of the monitored object according to the electroencephalogram data to be used of the monitored object, the eye movement data to be used of the monitored object, answer information to be used of the monitored object and attribute information of the test question to be evaluated after determining that the monitored object completes the test question to be evaluated; the electroencephalogram data to be used of the monitored object comprises electroencephalogram data of the monitored object when the monitored object replies to the test question to be evaluated; the eye movement data to be used of the monitored object comprises eye movement data of the monitored object when the monitored object replies to the test question to be evaluated; the answer information to be used of the monitored object comprises answer data of the monitored object aiming at the test question to be evaluated;

And the fatigue determination unit is used for determining that the learning state of the monitored object is a fatigue state when the monitored object replies to the test question to be evaluated if the fatigue score to be used of the monitored object is higher than a fatigue score threshold value.

The embodiment of the application also provides a learning state monitoring system, which comprises: brain wave acquisition equipment, eye movement acquisition equipment and any implementation mode of the learning state monitoring device provided by the embodiment of the application; the brain wave acquisition equipment is used for acquiring brain wave data to be used of a monitored object and sending the brain wave data to be used of the monitored object to the learning state monitoring device; the eye movement acquisition equipment is used for acquiring eye movement data to be used of the monitored object and sending the eye movement data to be used of the monitored object to the learning state monitoring device.

The embodiment of the application also provides equipment, which comprises: a processor, memory, system bus;

The processor and the memory are connected through the system bus;

The memory is configured to store one or more programs, the one or more programs comprising instructions, which when executed by the processor, cause the processor to perform any of the learning state monitoring methods provided by the embodiments of the present application.

The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores instructions, and when the instructions run on the terminal equipment, the terminal equipment is caused to execute any implementation mode of the learning state monitoring method provided by the embodiment of the application.

The embodiment of the application also provides a computer program product, which when being run on the terminal equipment, causes the terminal equipment to execute any implementation mode of the learning state monitoring method provided by the embodiment of the application.

Based on the technical scheme, the application has the following beneficial effects:

according to the technical scheme, after the monitored object is determined to finish a test question to be evaluated, determining a fatigue score to be used of the monitored object according to brain electricity data to be used of the monitored object, eye movement data to be used of the monitored object, answer information to be used of the monitored object and attribute information of the test question to be evaluated; if the fatigue score to be used of the monitored object is higher than the fatigue score threshold, determining that the learning state of the monitored object is a fatigue state when the monitored object replies to the test question to be evaluated, and monitoring the learning state of the monitored object.

The electroencephalogram data to be used of the monitored object comprises electroencephalogram data of the monitored object when the monitored object replies to the test question to be evaluated, the eye movement data to be used of the monitored object comprises eye movement data of the monitored object when the monitored object replies to the test question to be evaluated, and the answer information to be used of the monitored object comprises answer data of the monitored object aiming at the test question to be evaluated, so that the fatigue score to be used of the monitored object determined based on the data can more accurately represent the learning state (such as whether the monitored object is in a fatigue state) of the monitored object when the monitored object replies to the test question to be evaluated, and therefore the fatigue score to be used can more accurately represent whether the monitored object is in the fatigue state when the monitored object replies to the test question to be evaluated, and the learning state monitoring process realized based on the fatigue score to be used is more accurate, and the learning effect of the monitored object is improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flowchart of a learning state monitoring method according to an embodiment of the present application;

FIG. 2 is a schematic diagram of a factor analysis according to an embodiment of the present application;

Fig. 3 is a schematic structural diagram of a learning state monitoring device according to an embodiment of the present application;

fig. 4 is a schematic structural diagram of a learning state monitoring system according to an embodiment of the present application.

Detailed Description

The inventors have found in studies on learning states that learning states can sometimes be measured from a time perspective (e.g., if a student's learning period reaches 30-40 minutes, it is determined that the student is in a tired state). However, when the same time is required for the test questions with the same difficulty (or the test questions with the same type or the same test questions), students with different character patterns are different in the situation of the same external environment change or the same burst pressure, so that the occurrence time points of the students with different character patterns reaching the fatigue state are different. At this time, if the rest time points of the students are still determined according to the above duration (for example, 30-40 minutes), it may result in that part of the students have already developed fatigue states in the learning process corresponding to the above duration. The learning under the fatigue state is further an ineffective learning (for example, the situation that the student may have errors in the mastered knowledge in the fatigue state, so that the error ineffective learning is performed), so that the "part of students" cannot continuously keep high-efficiency learning in the learning process corresponding to the duration, and the learning effect of the students is poor.

Based on the above findings, in order to solve the technical problems in the background art, an embodiment of the present application provides a learning state monitoring method, including: after determining that the monitored object completes the test question to be evaluated, determining the fatigue score to be used of the monitored object according to the brain electricity data to be used of the monitored object, the eye movement data to be used of the monitored object, the answer information to be used of the monitored object and the attribute information of the test question to be evaluated; if the fatigue score to be used of the monitored object is higher than the fatigue score threshold, determining that the learning state of the monitored object is a fatigue state when the monitored object replies to the test question to be evaluated, and monitoring the learning state of the monitored object.

In addition, the embodiment of the application is not limited to the execution subject of the learning state monitoring method, and for example, the learning state monitoring method provided by the embodiment of the application can be applied to data processing equipment such as terminal equipment or a server. The terminal device may be a smart phone, a computer, a Personal digital assistant (Personal DIGITAL ASSITANT, PDA), a tablet computer, or the like. The servers may be stand alone servers, clustered servers, or cloud servers.

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

Method embodiment

Referring to fig. 1, the figure is a flowchart of a learning state monitoring method provided in an embodiment of the present application.

The learning state monitoring method provided by the embodiment of the application comprises the following steps of S1-S2:

S1: after determining that the monitored object completes the test question to be evaluated, determining the fatigue score to be used of the monitored object according to the brain electricity data to be used of the monitored object, the eye movement data to be used of the monitored object, the answer information to be used of the monitored object and the attribute information of the test question to be evaluated.

Wherein, the monitored object refers to students needing to monitor learning state.

The test questions to be evaluated are test questions completed by the monitored object; in addition, the embodiment of the application is not limited to the test questions to be evaluated, for example, in order to improve the monitoring instantaneity of the learning state, the test questions to be evaluated can refer to the test questions which are closest to the current moment and are completed by the monitored object. That is, in order to improve the monitoring instantaneity of the learning state, the learning state of the monitored object can be determined immediately by adopting the learning state monitoring method provided by the embodiment of the application after each test of the monitored object is completed, so that the learning duration of the monitored object in the fatigue state can be reduced as much as possible, and the learning effect of the monitored object can be improved.

The brain wave data to be used of the monitored object is brain wave information which is required to be referred when the pointer monitors the learning state of the monitored object; and the brain electricity data to be used of the monitored object comprises brain electricity data of the monitored object when the monitored object replies to the test question to be evaluated.

The embodiment of the application is not limited to 'brain electrical data', for example, the brain electrical data can comprise the arrangement entropy characteristics of brain electrical alpha waves, the arrangement entropy characteristics of brain electrical theta waves, the arrangement entropy characteristics of brain electrical delta waves and the like, because research shows that the amplitude of brain electrical alpha waves (8-13 Hz), brain electrical theta waves (4-7 Hz) and brain electrical delta waves (1-3 Hz) are closely related to fatigue. In addition, the embodiment of the application is not limited to the acquisition mode of brain wave data, and for example, the application can be implemented by adopting any existing or future equipment capable of acquiring brain wave.

The eye movement data to be used of the monitored object is eye movement information which is required to be referred to when the pointer monitors the learning state of the monitored object; and the eye movement data to be used of the monitored object comprises the eye movement data of the monitored object when the monitored object replies to the test question to be evaluated.

Embodiments of the present application are not limited to "eye movement data", and may specifically include, for example: jump, eye movement track, fixation, pupil, blink, etc. In addition, the embodiment of the present application is not limited to the acquisition mode of the "eye movement data", and for example, the embodiment may be implemented by using an eye movement instrument. The eye movement instrument is a complex psychological precision instrument, and can record the change characteristics of relevant eye movement indexes such as jump, eye movement track, gazing, pupil, blink and the like of a person when the person processes visual information based on a pupil-cornea reflection principle or a gazing point recording principle.

Answer information to be used of the monitored object is test question answer data which is required to be referred when a pointer monitors the learning state of the monitored object; and the answer information to be used of the monitored object comprises answer data of the monitored object aiming at the test question to be evaluated.

Embodiments of the present application are not limited to "reply data", and may specifically include, for example: reply duration and/or reply accuracy. The reply time length is used for representing the time consumed by a student to reply to a test question. The answer accuracy is used to represent the scoring of a student for a test question. In addition, the embodiment of the application is not limited to the method for acquiring the "answer data", for example, if the monitored object replies to the test question to be evaluated on an answer system, the "answer data" may be read from a system background (e.g., a server) corresponding to the answer system.

The attribute information of the test question to be evaluated is used for describing the test question characteristics of the test question to be evaluated. In addition, the embodiment of the present application is not limited to "attribute information", and for example, it may include at least one of a question difficulty, a question type, and a reference time length.

The reference time length is used for representing the time length of reference required when a test question is replied; the reference duration is not limited to the "reference duration", for example, the reference duration may refer to a standard answer duration of the test question, or may refer to a standard answer duration of a test question set (e.g., a test paper) including the test question (e.g., if the monitored object is answering a test question set and the test question set includes the test question to be evaluated), and the "reference duration of the test question to be evaluated" may refer to a standard answer duration of the test question set.

The fatigue score to be used of the monitored object is used for indicating the fatigue degree reached by the monitored object when the monitored object replies to the test question to be evaluated, so that the fatigue score to be used of the monitored object can accurately indicate the learning state of the monitored object when the monitored object replies to the test question to be evaluated.

In addition, the embodiment of the present application is not limited to the determination process of the fatigue score to be used of the monitored object, for example, in one possible implementation manner, the method may specifically include steps 11 to 12:

Step 11: and determining the physical fatigue score of the monitored object according to the brain electricity data to be used of the monitored object and the eye movement data to be used of the monitored object.

The physical fatigue score of the monitored object is used for representing the fatigue degree of the monitored object, which is presented from the physical state when the monitored object replies to the test question to be evaluated.

In addition, the embodiment of the present application is not limited to the implementation of step 11, for example, in one possible implementation, step 11 may specifically include steps 111-114:

step 111: and extracting characteristics of the electroencephalogram data to be used of the monitored object to obtain the electroencephalogram characteristics to be used of the monitored object.

The brain wave characteristics to be used of the monitored object refer to brain wave characteristics (such as frequency spectrum, energy spectrum, power spectrum and the like) carried by the brain wave data to be used of the monitored object, so that the brain wave characteristics to be used of the monitored object can accurately represent the brain wave state characteristics of the monitored object when the monitored object replies to the test question to be evaluated.

The embodiment of the present application is not limited to the implementation of step 111, and may be implemented by any method that can extract brain wave features from brain wave data, for example, existing or future.

Step 112: and performing characteristic analysis on the eye movement data to be used of the monitored object to obtain the eye movement characteristics to be used of the monitored object.

The eye movement characteristics to be used of the monitored object refer to the eye movement characteristics (such as average speed, average fixation time, jump main sequence parameters (parameters such as amplitude, frequency, etc. of eye moving from the current fixation point to the next fixation point) carried by the eye movement data of the monitored object, so that the eye movement characteristics to be used of the monitored object can accurately represent the eye movement state characteristics of the monitored object when the monitored object replies to the test question to be evaluated.

In addition, embodiments of the present application are not limited to the implementation of step 112, and may be implemented using any method that is currently available or that appears in the future that is capable of extracting eye movement characteristics from eye movement data, for example.

Step 113: and performing factor analysis on the electroencephalogram feature to be used of the monitored object and the eye movement feature to be used of the monitored object to obtain at least one common factor and a weighting weight corresponding to the at least one common factor.

In the embodiment of the present application, after obtaining the electroencephalogram feature to be used of the monitored object and the eye movement feature to be used of the monitored object, factor analysis may be directly performed on the features (as shown in fig. 2) to obtain at least one common factor (e.g., common factor 1 to common factor H in fig. 2) and weighting weights (e.g., weighting weights 1 to weighting H in fig. 2) corresponding to the common factors, so that the body fatigue score of the monitored object can be determined based on the common factors and the weighting weights corresponding to the common factors. Wherein H is a positive integer.

Step 114: and carrying out weighted summation on at least one common factor according to the weighted weight corresponding to the at least one common factor to obtain the physical fatigue score of the monitored object.

As an example, as shown in fig. 2, if the "at least one common factor" includes common factor 1, common factor 2, … …, and common factor H, and the weighting corresponding to the common factor 1 is weight 1, the weighting corresponding to the common factor 2 is weights 2, … …, and the weighting corresponding to the common factor H is weight H, the physical fatigue score of the monitored object=common factor 1×weight 1+common factor 2×weight 2+ … … +common factor hx weight H.

Based on the above-mentioned related content of step 11, after the electroencephalogram data to be used and the eye movement data to be used of the monitored object are collected, body state features (such as brain wave features and eye movement features) can be extracted from the data; and calculating the physical fatigue score of the monitored object by referring to the physical state characteristics, so that the physical fatigue score can accurately represent the fatigue degree of the monitored object from the physical state when the monitored object replies to the test question to be evaluated, and the fatigue score to be used of the monitored object can be determined based on the physical fatigue score.

Step 12: and determining the fatigue score to be used of the monitored object according to the physical fatigue score of the monitored object, the answer information to be used of the monitored object and the attribute information of the test question to be evaluated.

The embodiment of the present application is not limited to the implementation manner of step 12, for example, if the answer information to be used includes the answer duration to be used and the answer accuracy to be used, and the attribute information includes the reference duration, step 12 may specifically include steps 121-123:

Step 121: and determining the answer time score of the monitored object according to the ratio between the answer time to be used of the monitored object and the reference time of the test question to be evaluated.

The answer time to be used of the monitored object is used for indicating the time consumed by the monitored object to answer the test question to be evaluated.

The reference time length of the test question to be evaluated is the time length required to be referred when the pointer carries out reply time length scoring on the test question to be evaluated; and the reference time period may be set in advance. It should be noted that, please refer to the above for the related content of the "reference time period".

The answer time score of the monitored object is used for representing the fatigue degree of the monitored object presented from the answer time when answering the test questions to be evaluated; and the reply time score of the monitored object is positively correlated with the reply time to be used of the monitored object.

In addition, the embodiment of the present application does not limit the determination process of the "reply duration score of the monitored object", and for example, it may specifically include: and determining the ratio of the length of the answer to be used of the monitored object to the reference length of the test question to be evaluated as the answer length score of the monitored object.

Step 122: and determining the answer accuracy score of the monitored object according to the reciprocal of the accuracy of the answer to be used of the monitored object.

The accuracy of the answer to be used of the monitored object refers to the answer accuracy of the monitored object to the test question to be evaluated.

The answer accuracy score of the monitored object is used for representing the fatigue degree of the monitored object presented on the answer score when the monitored object answers the test question to be evaluated; and the answer accuracy score of the monitored object is inversely related to the answer accuracy to be used of the monitored object.

In addition, the embodiment of the present application is not limited to the determination process of the "answer accuracy score of the monitored object", and for example, it may specifically include: and determining the reciprocal of the accuracy of the answer to be used of the monitored object as the answer accuracy score of the monitored object.

Step 123: and determining the fatigue score to be used of the monitored object according to the physical fatigue score of the monitored object, the response duration score of the monitored object and the response accuracy score of the monitored object.

Example 1, step 123 may specifically include: and determining the fatigue score to be used of the monitored object according to the product of the physical fatigue score of the monitored object, the response time length score of the monitored object and the response accuracy score of the monitored object.

It can be seen that, after the physical fatigue score of the monitored object, the response duration score of the monitored object, and the response accuracy score of the monitored object are obtained, the fatigue score to be used of the monitored object can be determined by referring to the product between the three (as shown in formula (1), the product between the three can be directly determined as the fatigue score to be used of the monitored object).

P_score＝z×(t_use/T_refer)/acc_score (1)

Wherein P _score represents the fatigue score to be used of the monitored object; z represents the physical fatigue score of the monitored subject; t _use represents the duration of the answer to be used of the monitored object; t _refer represents the reference time length of the test question to be evaluated; acc _score represents the accuracy of the answer to be used of the monitored object.

Example 2, step 123 may specifically include: and determining the fatigue score to be used of the monitored object according to the sum value among the physical fatigue score of the monitored object, the response time length score of the monitored object and the response accuracy score of the monitored object.

It can be seen that, after the physical fatigue score of the monitored object, the response duration score of the monitored object, and the response accuracy score of the monitored object are obtained, the fatigue score to be used of the monitored object may be determined with reference to the sum value between the three (for example, the sum value between the three may be directly determined as the fatigue score to be used of the monitored object).

Based on the above-mentioned related content of S1, after the monitored object completes the test question to be evaluated, the fatigue score to be used of the monitored object can be determined according to the electroencephalogram data and the eye movement data of the monitored object when the monitored object replies to the test question to be evaluated, the reply data of the monitored object for the test question to be evaluated, and the attribute information of the test question to be evaluated, so that the fatigue score to be used can accurately represent the fatigue degree reached by the monitored object when the monitored object replies to the test question to be evaluated, so that whether the monitored object is in a fatigue state can be judged based on the fatigue score to be used.

S2: and if the fatigue score to be used of the monitored object is higher than the fatigue score threshold, determining that the learning state of the monitored object is a fatigue state when the monitored object replies to the test question to be evaluated.

Wherein the fatigue score threshold is used to describe a boundary between a fatigue state and a non-fatigue state; moreover, the embodiment of the application is not limited to the determination manner of the fatigue score threshold, for example, the fatigue score threshold may be preset.

In some cases, to further improve the accuracy of the fatigue score threshold, topics with different attribute information may correspond to different fatigue score thresholds. Based on this, the embodiment of the present application further provides a possible implementation manner of the learning state monitoring method, which further includes, before S2: searching a fatigue scoring threshold corresponding to the attribute information of the test question to be evaluated from the first mapping relation. The first mapping relation comprises a corresponding relation between attribute information of the test question to be evaluated and a fatigue scoring threshold corresponding to the attribute information of the test question to be evaluated.

It can be seen that, the first mapping relationship is used for recording fatigue scoring thresholds corresponding to different attribute information (such as test question difficulty and/or test question type), so in order to further improve the accuracy of the fatigue scoring thresholds, after the attribute information of the test question to be evaluated is obtained, the fatigue scoring threshold corresponding to the attribute information of the test question to be evaluated can be searched from the first mapping relationship (for example, if the first mapping relationship is used for recording the fatigue scoring thresholds corresponding to the test question difficulty of different test questions, the fatigue scoring threshold corresponding to the test question to be evaluated can be searched from the first mapping relationship, and if the first mapping relationship is used for recording the fatigue scoring threshold corresponding to the test question type of different test questions, the fatigue scoring threshold corresponding to the test question type of the test question to be evaluated can be searched from the first mapping relationship, and if the fatigue scoring threshold corresponding to the test question type of different binary groups (test question difficulty, test question type) can be searched from the first mapping relationship, the fatigue scoring threshold corresponding to the test question type to be compared with the fatigue scoring threshold can be conveniently performed by using the fatigue scoring threshold of the object to be compared.

In some cases, to further improve the accuracy of the fatigue score threshold, different questions may correspond to different fatigue score thresholds. Based on this, the embodiment of the present application further provides a possible implementation manner of the learning state monitoring method, which further includes, before S2: and searching a fatigue scoring threshold corresponding to the test question to be evaluated from the second mapping relation. The second mapping relation comprises a corresponding relation between the test questions to be evaluated and fatigue scoring thresholds corresponding to the test questions to be evaluated.

Therefore, in order to further improve the accuracy of the fatigue scoring threshold, the fatigue scoring threshold corresponding to the test question to be evaluated can be searched from the second mapping relation after the test question to be evaluated is acquired, so that the fatigue scoring threshold can be used for comparing with the fatigue scoring to be used of the monitored object.

In addition, the embodiment of the present application is not limited to the method for acquiring the fatigue score threshold value in the first mapping relationship or the second mapping relationship, and may be preset, for example. As another example, the generation may be performed in advance based on some sample data, and for ease of understanding, a process of generating a fatigue score threshold is described below as an example.

As an example, the fatigue score threshold may be generated in advance from sample electroencephalogram data of a sample object, sample eye movement data of the sample object, sample answer information of the sample object, and attribute information of the sample test.

Wherein the sample object refers to a student to which a reference is required when generating a fatigue score threshold; furthermore, the number of sample objects is not limited in the embodiment of the present application, for example, the number of sample objects may be M, where M is a positive integer.

The sample test questions refer to test questions of which sample objects are completed; and the sample test questions and the test questions to be evaluated meet the preset association relation.

In addition, the embodiment of the present application is not limited to the above-mentioned "preset association relationship", and for example, the "preset association relationship" may include any one of the following relationships:

Relationship 1: the test question difficulty of the sample test questions is the same as the test question difficulty of the test questions to be evaluated.

Relationship 2: the test question type of the sample test question is the same as the test question type of the test question to be evaluated.

Relationship 3: the test question type and the test question difficulty of the sample test questions are respectively the same as those of the test questions to be evaluated.

Relationship 4: the sample test questions are test questions to be evaluated.

In addition, the embodiment of the present application is not limited to the above-mentioned "preset association relationship" determining process, for example, in a possible implementation manner, the above-mentioned "preset association relationship" may be determined according to the monitoring accuracy requirement in the current application scenario; it may specifically include: if the monitoring accuracy requirement in the current application scene comprises reaching the accuracy of the test question difficulty level, determining that all test questions under the same test question difficulty level share the same fatigue scoring threshold value, and determining that the test question difficulty of the sample test questions is the same as the test question difficulty of the test questions to be evaluated according to the preset association relation; if the monitoring accuracy requirement under the current application scene comprises that the accuracy of the test question type level is reached, the fact that all test questions belonging to the same test question type share the same fatigue scoring threshold value can be determined, so that the test question type of the test questions with the ' preset association relation ' comprising the sample test questions is the same as the test question type of the test questions to be evaluated ' can be determined; if the monitoring accuracy requirement in the current application scene is that the accuracy of the test question level is reached, it can be determined that each test question corresponds to different fatigue scoring thresholds, so that it can be determined that the "preset association relationship" includes "the sample test question as the test question to be evaluated.

It can be seen that the above-mentioned "relationship 1" may be used to construct a first mapping relationship in which fatigue scoring thresholds corresponding to different test question difficulties are recorded; the above-mentioned "relation 2" may be used to construct a first mapping relation in which fatigue score thresholds corresponding to different test question types are recorded; the above-mentioned "relation 3" may be used to construct a first mapping relation in which fatigue scoring thresholds corresponding to different tuples (test question difficulty, test question type) are recorded; the above-mentioned "relation 4" may be used to construct a second mapping relation in which fatigue score thresholds corresponding to different test questions are recorded.

The sample brain wave data of the sample object refers to brain wave information which needs to be referred when the sample object is subjected to learning state monitoring by using a sample test question; and the sample electroencephalogram data of the sample object may include electroencephalogram data of the sample object that appears when the sample object is replied to the sample test question. It should be noted that, please refer to the above S1 for the relevant content of the "brain electrical data".

The sample eye movement data of the sample object refers to eye movement information which needs to be referred when the sample object is used for monitoring the learning state of the sample object; and the sample eye movement data of the sample object includes eye movement data of the sample object that appears when the sample object is replied to the sample test question. Note that, please refer to the above S1 for the relevant content of the "eye movement data".

The sample answer information of the sample object refers to test question answer data which needs to be referred when the sample object is used for monitoring the learning state of the sample object; and the sample answer information of the sample object comprises answer data of the sample object aiming at the sample test question. Note that, please refer to the above S1 for the relevant content of the "reply data".

In addition, the embodiment of the present application is not limited to the process of generating the "fatigue score threshold", for example, in one possible implementation, if the number of sample objects is M, the process of generating the "fatigue score threshold" may specifically include steps 21-23:

Step 21: and determining the sample fatigue score of the mth sample object according to the sample electroencephalogram data of the mth sample object, the sample eye movement data of the mth sample object, the sample answer information of the mth sample object and the attribute information of the mth sample test question. Wherein m is a positive integer; m is less than or equal to M, and M is a positive integer.

The sample fatigue score of the mth sample object is used for indicating the fatigue degree reached by the mth sample object when the mth sample object is replied to the sample test question, so that the sample fatigue score of the mth sample object can accurately indicate the learning state of the mth sample object when the mth sample object is replied to the sample test question.

In addition, the determination of the "sample fatigue score of the mth sample object" may be performed by any embodiment of the determination of the "fatigue score to be used of the monitored object" above, and the "monitored object" is replaced by the "mth sample object" and the "fatigue score to be used" is replaced by the "sample fatigue score" in any embodiment of the determination of the "fatigue score to be used of the monitored object" above.

Step 22: obtaining at least one personality score for an mth sample object; wherein m is a positive integer; m is less than or equal to M, and M is a positive integer.

Wherein at least one personality score of an mth sample object is used to describe personality characteristics exhibited by the mth sample object in at least one personality dimension.

In addition, embodiments of the present application are not limited to "at least one personality", and may include, for example, a personality (i.e., open, responsible, camber, humanity, nervous) measured by a large five personality questionnaire, a personality (i.e., group, smart, stability, strength, excitement, chemostamina, dare, sensitivity, suspicion, fantasy, cause, anxiety, experimental, independence, autonomy, tension) measured by a catter 16 personality factor questionnaire, and a personality (i.e., inside and outside, nervous, mental) measured by an exendin.

In addition, the embodiment of the present application is not limited to the implementation of step 22, and may specifically include: at least one personality score for an mth sample object is determined based on measurements of the mth sample object on a preset personality measurement questionnaire (e.g., a large five personality questionnaire, a catter 16 personality factor questionnaire, an exendi personality questionnaire, etc.).

Step 23: a fatigue score threshold is determined based on the sample fatigue scores of the M sample objects and at least one personality score of the M sample objects.

As an example, if the number of personality scores is N, step 23 may specifically include steps 231-233:

Step 231: and obtaining a normal distribution mean value corresponding to the sample fatigue scores, a normal distribution standard deviation corresponding to the sample fatigue scores and a normal distribution map corresponding to the sample fatigue scores according to the sample fatigue scores of the M sample objects.

The embodiment of the present application is not limited to the implementation of step 231, and for ease of understanding, the following description will be made with reference to two examples.

Example 1, step 231 may specifically include steps 31-33:

step 31: and determining a normal distribution mean value corresponding to the sample fatigue scores according to the mean value among the sample fatigue scores of the M sample objects.

In the embodiment of the application, after the sample fatigue scores of the M sample objects are obtained, an average value among the sample fatigue scores of the M sample objects can be calculated; and determining a normal distribution mean value corresponding to the sample fatigue score according to the average value (for example, the average value can be directly determined as the normal distribution mean value corresponding to the sample fatigue score).

Step 32: and determining the normal distribution standard deviation corresponding to the sample fatigue scores according to the variances among the sample fatigue scores of the M sample objects.

In the embodiment of the application, after the sample fatigue scores of M sample objects are obtained, the variance among the sample fatigue scores of the M sample objects is calculated; and then determining a normal distribution standard deviation corresponding to the sample fatigue score according to the average value (for example, the variance can be directly determined as the normal distribution standard deviation corresponding to the sample fatigue score).

Step 33: and constructing a normal distribution map corresponding to the sample fatigue score according to the normal distribution mean value corresponding to the sample fatigue score and the normal distribution standard deviation corresponding to the sample fatigue score.

In the embodiment of the application, after the normal distribution mean value corresponding to the sample fatigue score and the normal distribution standard deviation corresponding to the sample fatigue score are obtained, the normal distribution map corresponding to the sample fatigue score can be constructed according to the normal distribution mean value corresponding to the sample fatigue score and the normal distribution standard deviation corresponding to the sample fatigue score, so that the normal distribution map can be subjected to data distribution according to the normal distribution mean value corresponding to the sample fatigue score and the normal distribution standard deviation corresponding to the sample fatigue score.

Based on the above-mentioned related content of step 31 to step 33, after obtaining the sample fatigue scores of the M sample objects, determining a normal distribution mean value corresponding to the sample fatigue scores and a normal distribution standard deviation corresponding to the sample fatigue scores according to the sample fatigue scores of the M sample objects; and constructing a normal distribution diagram corresponding to the sample fatigue scores by referring to the two normal distribution parameters, so that the normal distribution diagram can accurately represent the normal distribution states of the sample fatigue scores of the M sample objects.

Example 2, step 231 may specifically include steps 41-42:

Step 41: and carrying out normal distribution fitting on the sample fatigue scores of the M sample objects to obtain a normal distribution diagram corresponding to the sample fatigue scores.

It should be noted that the embodiment of the present application is not limited to the "normal distribution fitting" in step 41, and may be implemented by any method that can fit a normal distribution map from some data, existing or occurring in the future.

Step 42: and determining a normal distribution mean value corresponding to the sample fatigue score and a normal distribution standard deviation corresponding to the sample fatigue score according to the normal distribution map corresponding to the sample fatigue score.

Based on the above-mentioned related content of steps 41 to 42, after obtaining the sample fatigue scores of the M sample objects, normal distribution fitting may be performed first according to the sample fatigue scores of the M sample objects to obtain a normal distribution map corresponding to the sample fatigue scores, so that the normal distribution map may accurately represent the normal distribution states of the sample fatigue scores of the M sample objects; and extracting a normal distribution mean value corresponding to the sample fatigue score and a normal distribution standard deviation corresponding to the sample fatigue score from the normal distribution map.

Based on the above-mentioned correlation of step 232, after the sample fatigue scores of the M sample objects are obtained, a normal distribution mean value corresponding to the sample fatigue scores, a normal distribution standard deviation corresponding to the sample fatigue scores, and a normal distribution map corresponding to the sample fatigue scores may be analyzed from the sample fatigue scores of the M sample objects, so that the fatigue score threshold may be determined subsequently based on these data.

Step 232: according to the nth personal lattice score of the M sample objects, determining a normal distribution mean value corresponding to the nth personal lattice score, a normal distribution standard deviation corresponding to the nth personal lattice score and a normal distribution map corresponding to the nth personal lattice score; wherein N is a positive integer, N is less than or equal to N, and N is a positive integer.

Example 1, step 232 may specifically include steps 51-53:

step 51: and determining a normal distribution mean value corresponding to the nth personal lattice score according to the mean value among the nth personal lattice scores of the M sample objects.

In the embodiment of the application, after the nth personal gram score of the M sample objects is obtained, the average value between the nth personal gram scores of the M sample objects can be calculated; and then determining a normal distribution mean value corresponding to the nth personal lattice score according to the average value (for example, the average value can be directly determined as the normal distribution mean value corresponding to the nth personal lattice score).

Step 52: and determining a normal distribution standard deviation corresponding to the nth personal lattice score according to the variance among the nth personal lattice scores of the M sample objects.

In the embodiment of the application, after the nth personal gram score of the M sample objects is obtained, the variance between the nth personal gram scores of the M sample objects is calculated; and then determining a normal distribution standard deviation corresponding to the nth personal cell score according to the average value (for example, the variance can be directly determined as the normal distribution standard deviation corresponding to the nth personal cell score).

Step 53: and constructing a normal distribution diagram corresponding to the nth personal lattice score according to the normal distribution mean value corresponding to the nth personal lattice score and the normal distribution standard deviation corresponding to the nth personal lattice score.

In the embodiment of the application, after the normal distribution mean value corresponding to the nth personal lattice score and the normal distribution standard deviation corresponding to the nth personal lattice score are obtained, a normal distribution map corresponding to the nth personal lattice score can be constructed according to the normal distribution mean value corresponding to the nth personal lattice score and the normal distribution standard deviation corresponding to the nth personal lattice score, so that the normal distribution map carries out data distribution according to the normal distribution mean value corresponding to the nth personal lattice score and the normal distribution standard deviation corresponding to the nth personal lattice score.

Based on the above-mentioned related content in steps 51 to 53, after the nth person's score of the M sample objects is obtained, the normal distribution mean value corresponding to the nth person's score and the normal distribution standard deviation corresponding to the nth person's score may be determined according to the nth person's score of the M sample objects; and constructing a normal distribution diagram corresponding to the nth personal lattice score by referring to the two normal distribution parameters so that the normal distribution diagram can accurately represent the normal distribution state of the nth personal lattice score of the M sample objects.

Example 2, step 232 may specifically include steps 61-62:

step 61: and carrying out normal distribution fitting on the nth personal lattice score of the M sample objects to obtain a normal distribution diagram corresponding to the nth personal lattice score.

It should be noted that the embodiment of the present application is not limited to the "normal distribution fitting" in step 61, and may be implemented by any method that can fit a normal distribution map from some data, existing or occurring in the future.

Step 62: and determining a normal distribution mean value corresponding to the nth personal lattice score and a normal distribution standard deviation corresponding to the nth personal lattice score according to the normal distribution map corresponding to the nth personal lattice score.

Based on the above-mentioned related contents of steps 61 to 62, after obtaining the nth personal score of the M sample objects, normal distribution fitting may be performed on the nth personal score of the M sample objects to obtain a normal distribution map corresponding to the nth personal score, so that the normal distribution map may accurately represent the normal distribution state of the nth personal score of the M sample objects; and extracting a normal distribution mean value corresponding to the nth personal lattice score and a normal distribution standard deviation corresponding to the nth personal lattice score from the normal distribution map.

Based on the above-mentioned related content of step 232, after the nth person cell score of the M sample objects is obtained, a normal distribution mean value corresponding to the nth person cell score, a normal distribution standard deviation corresponding to the nth person cell score, and a normal distribution map corresponding to the nth person cell score may be analyzed from the nth person cell score of the M sample objects, so that the fatigue score threshold can be determined based on these data. Wherein N is a positive integer, N is less than or equal to N, and N is a positive integer.

Step 233: and determining a fatigue score threshold according to the N personality scores of the M sample objects, the normal distribution map corresponding to the sample fatigue scores, the normal distribution mean value corresponding to the sample fatigue scores, the normal distribution standard deviation corresponding to the sample fatigue scores, the normal distribution map corresponding to the N personality scores, the normal distribution mean value corresponding to the N personality scores and the normal distribution standard deviation corresponding to the N personality scores.

Embodiments of the present application are not limited to the implementation of step 233, and may specifically include steps 71-72:

Step 71: and determining the test question score corresponding to the nth person lattice score according to the nth person lattice score of the M sample objects, the normal distribution mean value corresponding to the sample fatigue score, the normal distribution standard deviation corresponding to the sample fatigue score, the normal distribution mean value corresponding to the nth person lattice score, the normal distribution standard deviation corresponding to the nth person lattice score and the correlation degree between the normal distribution map corresponding to the sample fatigue score and the normal distribution map corresponding to the nth person lattice score. Wherein N is a positive integer, N is less than or equal to N, and N is a positive integer.

The "correlation degree between the normal distribution map corresponding to the sample fatigue score and the normal distribution map corresponding to the nth person's score" is used to represent the correlation between the normal distribution map corresponding to the sample fatigue score and the normal distribution map corresponding to the nth person's score.

In addition, the embodiment of the present application is not limited to the above-mentioned determination process of the degree of correlation between the normal distribution map corresponding to the sample fatigue score and the normal distribution map corresponding to the nth person lattice score, for example, the distance between the normal distribution map corresponding to the sample fatigue score and the normal distribution map corresponding to the nth person lattice score may be calculated by using js divergence (Jensen-Shannon divergence); and determining the reciprocal of the distance between the normal distribution map corresponding to the sample fatigue score and the normal distribution map corresponding to the nth person lattice score as the correlation degree between the normal distribution map corresponding to the sample fatigue score and the normal distribution map corresponding to the nth person lattice score.

The question score corresponding to the nth personal score is used to represent the learning state (e.g., the degree of fatigue) that the above-described "M sample objects" present on the nth personal score when replying to the sample questions.

In addition, the embodiment of the present application is not limited to the implementation of step 71, and for ease of understanding, the following description will be given with reference to two examples.

For example, if the test question score corresponding to the nth personal score includes only one numerical value, step 71 may be implemented using formula (2).

In the method, in the process of the invention,The test question scores corresponding to the nth personal lattice scores are represented; u _z represents a normal distribution mean corresponding to the fatigue score of the sample; sd _z represents the normal distribution standard deviation corresponding to the sample fatigue score; an nth personality score representing an mth sample object; representing a normal distribution mean value corresponding to the nth personal lattice score; Representing the normal distribution standard deviation corresponding to the nth personal lattice score; d _n represents the degree of correlation between the normal profile corresponding to the fatigue score of the sample and the normal profile corresponding to the nth personality score.

For example, if the question score corresponding to the nth personality score includes M values, step 71 may be implemented using equation (3).

In the method, in the process of the invention,The mth numerical value in the test question score corresponding to the nth personal score is represented (that is, the test question score corresponding to the nth personal score includes) ; U _z represents a normal distribution mean corresponding to the fatigue score of the sample; sd _z represents the normal distribution standard deviation corresponding to the sample fatigue score; an nth personality score representing an mth sample object; representing a normal distribution mean value corresponding to the nth personal lattice score; Representing the normal distribution standard deviation corresponding to the nth personal lattice score; d _n represents the degree of correlation between the normal profile corresponding to the fatigue score of the sample and the normal profile corresponding to the nth personality score.

Based on the above-mentioned related content of step 71, after obtaining the normal distribution mean value corresponding to the sample fatigue score, the normal distribution standard deviation corresponding to the sample fatigue score, the normal distribution mean value corresponding to the nth person lattice score, the normal distribution standard deviation corresponding to the nth person lattice score, and the normal distribution map corresponding to the nth person lattice score, the test question score corresponding to the nth person lattice score may be determined by referring to these information and the nth person lattice score of the M sample objects, so that the test question score corresponding to the nth person lattice score may accurately represent the fatigue degree of the "M sample objects" presented on the nth person lattice score when replying to the sample test questions.

Step 72: and determining a fatigue score threshold according to the N personal scores of the M sample objects and the test question scores corresponding to the N personal scores.

The embodiment of the present application is not limited to the implementation of step 72, and for ease of understanding, the following description will be made with reference to two examples.

Example one: if the test question score corresponding to the nth personal score is the aboveStep 72 may be specifically performed using equation (4).

Wherein P _threshold represents a fatigue score threshold; ; an nth personality score representing an mth sample object; And (5) representing the test question score corresponding to the nth personal lattice score.

Example two, if the test question score corresponding to the nth personal score includesStep 72 may be specifically performed using equation (5).

Wherein P _threshold represents a fatigue score threshold; ; an nth personality score representing an mth sample object; and (5) representing the mth numerical value in the test question scores corresponding to the nth personal lattice score.

Based on the above-described content of the fatigue score threshold, the fatigue score threshold can accurately represent the learning state (e.g., the degree of fatigue) exhibited by the student in a normal state (i.e., in a state of not reaching fatigue) when replying to the test question to be evaluated, so that the learning state of one student can be monitored later with the fatigue score threshold as a reference value.

After obtaining the fatigue score to be used of the monitored object, if the fatigue score to be used of the monitored object is higher than a fatigue score threshold (for example, a fatigue score threshold corresponding to the test question difficulty of the test question to be evaluated, a fatigue score threshold corresponding to the test question type of the test question to be evaluated, a fatigue score threshold corresponding to a binary group (the test question difficulty of the test question to be evaluated, the test question type of the test question to be evaluated) or a fatigue score threshold corresponding to the test question to be evaluated), the fatigue degree of the monitored object when replying to the test question to be evaluated is higher, so that the learning state of the monitored object when replying to the test question to be evaluated can be determined to be a fatigue state; if the fatigue score to be used of the monitored object is not higher than the fatigue score threshold, the fatigue degree of the monitored object when the monitored object replies to the test question to be evaluated is lower, so that the learning state of the monitored object when the monitored object replies to the test question to be evaluated can be determined to be a normal state.

In addition, in order to further improve the learning effect of the monitored object, after determining that the fatigue score to be used of the monitored object is higher than the fatigue score threshold, the reminding information is generated and sent to the monitored object, so that the reminding information is used for reminding the monitored object to rest.

Therefore, after the fatigue score to be used of the monitored object is higher than the fatigue score threshold value, the fatigue degree reached by the monitored object when the monitored object replies to the test question to be evaluated can be determined to be higher, so that the learning ability of the monitored object can be determined to be reduced, and the monitored object can be reminded of rest by means of reminding information, so that the monitored object can rest in time, invalid learning of the monitored object in a fatigue state can be avoided as much as possible, and the learning effect of the monitored object can be improved.

The embodiment of the present application is not limited to the above-mentioned transmission method of the "reminding information", and for example, the method may specifically be to display by means of a display screen, to transmit by means of a short message, to transmit by means of a mail, and the like.

Based on the above-mentioned related content of S1 to S2, for the learning state monitoring method provided by the embodiment of the present application, after determining that the monitored object completes the test question to be evaluated, determining a fatigue score to be used of the monitored object according to the electroencephalogram data to be used of the monitored object, the eye movement data to be used of the monitored object, answer information to be used of the monitored object, and attribute information of the test question to be evaluated; if the fatigue score to be used of the monitored object is higher than the fatigue score threshold, determining that the learning state of the monitored object is a fatigue state when the monitored object replies to the test question to be evaluated, and monitoring the learning state of the monitored object.

The to-be-used electroencephalogram data of the monitored object comprises electroencephalogram data of the monitored object when the monitored object replies to the to-be-evaluated test question, the to-be-used eye data of the monitored object comprises eye data of the monitored object when the monitored object replies to the to-be-evaluated test question, and the to-be-used answer information of the monitored object comprises answer data of the monitored object aiming at the to-be-evaluated test question, so that the to-be-used fatigue score of the monitored object determined based on the data can more accurately represent the learning state of the monitored object when the monitored object replies to the to-be-evaluated test question, and further, the to-be-used fatigue score can more accurately represent whether the monitored object has fatigue state when the monitored object replies to the to-be-evaluated test question, so that the learning state monitoring process realized based on the to-be-used fatigue score is more accurate, and the learning effect of the monitored object is improved.

Based on the learning state monitoring method provided by the method embodiment, the embodiment of the application also provides a learning state monitoring device, which is explained and illustrated below with reference to the accompanying drawings.

Device embodiment

The device embodiment is described for the learning state monitoring device, and the related content is referred to the method embodiment.

Referring to fig. 3, the structure of a learning state monitoring device according to an embodiment of the present application is shown.

The learning state monitoring device 300 provided in the embodiment of the application includes:

the score determining unit 301 is configured to determine, after determining that a monitored object completes a test question to be evaluated, a fatigue score to be used of the monitored object according to electroencephalogram data to be used of the monitored object, eye movement data to be used of the monitored object, answer information to be used of the monitored object, and attribute information of the test question to be evaluated; the electroencephalogram data to be used of the monitored object comprises electroencephalogram data of the monitored object when the monitored object replies to the test question to be evaluated; the eye movement data to be used of the monitored object comprises eye movement data of the monitored object when the monitored object replies to the test question to be evaluated; the answer information to be used of the monitored object comprises answer data of the monitored object aiming at the test question to be evaluated;

And the fatigue determining unit 302 is configured to determine that the learning state of the monitored object when the monitored object replies to the test question to be evaluated is a fatigue state if the fatigue score to be used of the monitored object is higher than a fatigue score threshold.

In one possible implementation, the score determining unit 301 includes:

A first determining subunit, configured to determine a physical fatigue score of the monitored object according to electroencephalogram data to be used of the monitored object and eye movement data to be used of the monitored object;

And the second determination subunit is used for determining the fatigue score to be used of the monitored object according to the physical fatigue score of the monitored object, the answer information to be used of the monitored object and the attribute information of the test question to be evaluated.

In a possible embodiment, the first determining subunit is specifically configured to: extracting characteristics of the electroencephalogram data to be used of the monitored object to obtain electroencephalogram characteristics to be used of the monitored object; performing feature analysis on the eye movement data to be used of the monitored object to obtain eye movement features to be used of the monitored object; factor analysis is carried out on the electroencephalogram feature to be used of the monitored object and the eye movement feature to be used of the monitored object, so that at least one common factor and a weighting weight corresponding to the at least one common factor are obtained; and carrying out weighted summation on the at least one common factor according to the weighted weight corresponding to the at least one common factor to obtain the physical fatigue score of the monitored object.

In one possible embodiment, the second determining subunit includes:

A third determining subunit, configured to determine, if the answer information to be used includes an answer duration to be used and an answer accuracy to be used, and the attribute information includes a reference duration, a answer duration score of the monitored object according to a ratio between the answer duration to be used of the monitored object and the reference duration of the test question to be evaluated; the answer time to be used of the monitored object refers to answer time of the monitored object for the test question to be evaluated;

A fourth determination subunit, configured to determine a reply accuracy score of the monitored object according to an inverse of the accuracy of the answer to be used of the monitored object; the accuracy of the answer to be used of the monitored object refers to the accuracy of the answer of the monitored object to the test question to be evaluated;

And a fifth determining subunit, configured to determine a fatigue score to be used of the monitored object according to the physical fatigue score of the monitored object, the response duration score of the monitored object, and the response accuracy score of the monitored object.

In a possible embodiment, the fifth determining subunit is specifically configured to: and determining the fatigue score to be used of the monitored object according to the product of the physical fatigue score of the monitored object, the response time length score of the monitored object and the response accuracy score of the monitored object.

Or alternatively

And the sample test question is the test question to be evaluated.

Obtaining at least one personality score for the sample object;

In one possible implementation manner, if the number of personality scores is N and the number of sample objects is M, the determining the fatigue score threshold includes:

In one possible embodiment, the learning state monitoring apparatus 300 further includes:

The information reminding unit is used for generating reminding information after determining that the fatigue score to be used of the monitored object is higher than a fatigue score threshold value, and sending the reminding information to the monitored object; the reminding information is used for reminding the monitored object to rest.

Based on the related content of the learning state monitoring device 300, as shown in fig. 4, an embodiment of the present application further provides a learning state monitoring system 400, where the system 400 includes: any implementation mode of the brain wave acquisition device 401, the eye movement acquisition device 402 and the learning state monitoring apparatus 300 provided by the embodiment of the application; the brain wave acquisition device 401 is configured to acquire brain wave data to be used of a monitored object and send the brain wave data to be used of the monitored object to the learning state monitoring apparatus 300; the eye movement collection device 402 is configured to collect eye movement data to be used of the monitored object and send the eye movement data to be used of the monitored object to the learning state monitoring apparatus 300.

Further, the embodiment of the application also provides a learning state monitoring device, which comprises: a processor, memory, system bus;

The processor and the memory are connected through the system bus;

The memory is for storing one or more programs, the one or more programs comprising instructions, which when executed by the processor, cause the processor to perform any of the implementations of the learning state monitoring method described above.

Further, the embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores instructions, and when the instructions run on the terminal equipment, the terminal equipment is caused to execute any implementation method of the learning state monitoring method.

Further, the embodiment of the application also provides a computer program product, which when being run on the terminal equipment, causes the terminal equipment to execute any implementation method of the learning state monitoring method.

From the above description of embodiments, it will be apparent to those skilled in the art that all or part of the steps of the above described example methods may be implemented in software plus necessary general purpose hardware platforms. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network communication device such as a media gateway, etc.) to execute the method described in the embodiments or some parts of the embodiments of the present application.

It should be noted that, in the present description, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different manner from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.

It is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A learning state monitoring method, the method comprising:

After determining that a monitored object completes a test question to be evaluated, determining a fatigue score to be used of the monitored object according to brain electricity data to be used of the monitored object, eye movement data to be used of the monitored object, answer information to be used of the monitored object and attribute information of the test question to be evaluated; the test questions to be evaluated are the test questions which are closest to the current moment and completed by the monitored object; the electroencephalogram data to be used of the monitored object comprises electroencephalogram data of the monitored object when the monitored object replies to the test question to be evaluated; the eye movement data to be used of the monitored object comprises eye movement data of the monitored object when the monitored object replies to the test question to be evaluated; the answer information to be used of the monitored object comprises answer data of the monitored object aiming at the test question to be evaluated;

If the fatigue score to be used of the monitored object is higher than a fatigue score threshold, determining that the learning state of the monitored object is a fatigue state when the monitored object replies to the test question to be evaluated;

The fatigue scoring threshold is generated according to sample electroencephalogram data of a sample object, sample eye movement data of the sample object, sample answer information of the sample object and attribute information of a sample test question; the sample test questions and the test questions to be evaluated meet a preset association relation; the sample electroencephalogram data of the sample object comprises electroencephalogram data of the sample object when the sample object replies to the sample test question; the sample eye movement data of the sample object comprises eye movement data of the sample object when the sample object replies to the sample test question; the sample answer information of the sample object comprises answer data of the sample object aiming at the sample test question;

the generation process of the fatigue score threshold comprises the following steps: determining a sample fatigue score of the sample object according to the sample electroencephalogram data of the sample object, the sample eye movement data of the sample object, the sample answer information of the sample object and the attribute information of the sample test question; obtaining at least one personality score for the sample object; determining the fatigue score threshold based on at least one personality score of the sample object and a sample fatigue score of the sample object.

2. The method according to claim 1, wherein the determining of the fatigue score to be used of the monitored object comprises:

3. The method according to claim 2, wherein the determining of the physical fatigue score of the monitored subject comprises:

4. The method according to claim 2, wherein if the answer information to be used includes an answer time to be used and an answer accuracy to be used, and the attribute information includes a reference time, determining the fatigue score to be used of the monitored object according to the physical fatigue score of the monitored object, the answer information to be used of the monitored object, and the attribute information of the test question to be evaluated includes:

5. The method of claim 4, wherein the determining a fatigue score to be used for the monitored subject based on the physical fatigue score of the monitored subject, the response time duration score of the monitored subject, and the response accuracy score of the monitored subject comprises:

6. The method according to claim 5, wherein the sample test question and the test question to be evaluated satisfy a preset association relationship, comprising:

Or alternatively

And the sample test question is the test question to be evaluated.

7. The method of claim 1, wherein if the number of personality scores is N and the number of sample objects is M, the determining the fatigue score threshold from the at least one personality score of the sample object and the sample fatigue score of the sample object comprises:

8. The method of claim 7, wherein the determining of the fatigue score threshold comprises:

9. The method according to claim 1, wherein the method further comprises:

10. A learning state monitoring device, characterized by comprising:

The score determining unit is used for determining a fatigue score to be used of the monitored object according to the electroencephalogram data to be used of the monitored object, the eye movement data to be used of the monitored object, answer information to be used of the monitored object and attribute information of the test question to be evaluated after determining that the monitored object completes the test question to be evaluated; the test questions to be evaluated are the test questions which are closest to the current moment and completed by the monitored object; the electroencephalogram data to be used of the monitored object comprises electroencephalogram data of the monitored object when the monitored object replies to the test question to be evaluated; the eye movement data to be used of the monitored object comprises eye movement data of the monitored object when the monitored object replies to the test question to be evaluated; the answer information to be used of the monitored object comprises answer data of the monitored object aiming at the test question to be evaluated;

The fatigue determination unit is used for determining that the learning state of the monitored object is a fatigue state when the monitored object replies to the test question to be evaluated if the fatigue score to be used of the monitored object is higher than a fatigue score threshold value; the fatigue scoring threshold is generated according to sample electroencephalogram data of a sample object, sample eye movement data of the sample object, sample answer information of the sample object and attribute information of a sample test question; the sample test questions and the test questions to be evaluated meet a preset association relation; the sample electroencephalogram data of the sample object comprises electroencephalogram data of the sample object when the sample object replies to the sample test question; the sample eye movement data of the sample object comprises eye movement data of the sample object when the sample object replies to the sample test question; the sample answer information of the sample object comprises answer data of the sample object aiming at the sample test question; the generation process of the fatigue score threshold comprises the following steps: determining a sample fatigue score of the sample object according to the sample electroencephalogram data of the sample object, the sample eye movement data of the sample object, the sample answer information of the sample object and the attribute information of the sample test question; obtaining at least one personality score for the sample object; determining the fatigue score threshold based on at least one personality score of the sample object and a sample fatigue score of the sample object.

11. A learning state monitoring system, the system comprising: brain wave acquisition apparatus, eye movement acquisition apparatus, and learning state monitoring device according to claim 10; the brain wave acquisition equipment is used for acquiring brain wave data to be used of a monitored object and sending the brain wave data to be used of the monitored object to the learning state monitoring device; the eye movement acquisition equipment is used for acquiring eye movement data to be used of the monitored object and sending the eye movement data to be used of the monitored object to the learning state monitoring device.

12. An apparatus, the apparatus comprising: a processor, memory, system bus;

The processor and the memory are connected through the system bus;

The memory is for storing one or more programs, the one or more programs comprising instructions, which when executed by the processor, cause the processor to perform the method of any of claims 1-9.

13. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein instructions, which when run on a terminal device, cause the terminal device to perform the method of any of claims 1 to 9.

14. A computer program product, characterized in that the computer program product, when run on a terminal device, causes the terminal device to perform the method of any of claims 1 to 9.