WO2019201215A1 - 课堂评测方法、装置及计算机可读存储介质 - Google Patents

课堂评测方法、装置及计算机可读存储介质 Download PDF

Info

Publication number
WO2019201215A1
WO2019201215A1 PCT/CN2019/082743 CN2019082743W WO2019201215A1 WO 2019201215 A1 WO2019201215 A1 WO 2019201215A1 CN 2019082743 W CN2019082743 W CN 2019082743W WO 2019201215 A1 WO2019201215 A1 WO 2019201215A1
Authority
WO
WIPO (PCT)
Prior art keywords
attention
value
data
energy
attention value
Prior art date
Application number
PCT/CN2019/082743
Other languages
English (en)
French (fr)
Inventor
韩璧丞
阿·迪斯
杨钊祎
郑辉
孙东圣
孙越
于翔
周承邦
郭西鹏
Original Assignee
深圳市心流科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市心流科技有限公司 filed Critical 深圳市心流科技有限公司
Publication of WO2019201215A1 publication Critical patent/WO2019201215A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/20—Education
    • G06Q50/205—Education administration or guidance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/02—Preprocessing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/12—Classification; Matching

Definitions

  • the present application relates to the field of educational information technology, and in particular, to a classroom evaluation method, apparatus, and computer readable storage medium.
  • the brain frequency is in alpha waves (frequency range 8-13 Hz). At this time, the brain waves are relatively stable. The best brainwave state for people to learn and think about.
  • the brain frequency is in the beta wave (frequency range above 14Hz)
  • the brain wave frequency becomes faster and the amplitude increases, and the appropriate ⁇ wave has a positive effect on the improvement of attention and the development of cognitive behavior. , but the duration is short and fatigue.
  • the brain frequency is in the ⁇ wave (frequency range 4-8Hz). At this time, the brain wave is generally messy, and the frequency gradually becomes slower.
  • the human consciousness gradually dissipates, the body is deep and relaxed, and the trigger is deep. Memory, strengthening long-term memory, etc. are extremely helpful.
  • the classroom teaching system of the school is more and more adopting multimedia technology, but the evaluation method of the teaching method still stays in the backward mode such as subjective observation and staged test. It is difficult for teachers to input and observe the attention level of the students. Moreover, Through the after-school homework or phased test to evaluate the effect of classroom teaching, the current classroom teaching system lacks objective and effective evaluation, and it is impossible to deeply evaluate and analyze the attention level of students' classrooms, resulting in low classroom teaching efficiency.
  • the main purpose of the present application is to provide a classroom evaluation method, device and computer readable storage medium, aiming at solving the lack of objective and effective evaluation of the classroom teaching system, and failing to deeply evaluate and analyze the attention level of the student classroom, resulting in classroom teaching. Inefficient technical problems.
  • the present application provides a classroom evaluation method, the method comprising the following steps:
  • the target attention value is calculated based on the feature data, and the attention state of the student is analyzed.
  • the step of acquiring energy information of each band in the brain wave data by using a preset algorithm includes:
  • the energy information is acquired based on the frequency domain data.
  • the step of calculating a target attention value based on the feature data includes:
  • the target attention value is calculated based on the initial attention value.
  • the step of calculating the target attention value based on the initial attention value further includes:
  • the attention value is calculated as the sum of the initial attention value and the predicted attention value, and the attention value is the sum of the initial attention value and the predicted attention value as the target attention value.
  • the step of analyzing the attention state of the student includes:
  • the target attention value is compared with the attention state evaluation criterion to determine a level level corresponding to the attention value.
  • the classroom evaluation method further includes:
  • the user When detecting that the wearing state is not worn, the user is prompted to adjust the wearing device.
  • the step of detecting a wearing state of the user includes:
  • a current state of the wearing device is determined based on the probability.
  • the classroom evaluation method further includes:
  • the brain wave data, the feature data, and the analysis result at the time of attention state analysis are compression-encrypted, and an attention analysis report is generated.
  • the present application further provides a classroom evaluation apparatus, including: a memory, a processor, and a classroom evaluation program stored on the memory and operable on the processor, the classroom The steps of the above-described classroom evaluation method are implemented when the evaluation program is executed by the processor.
  • the present application further provides a computer readable storage medium, where the computer readable storage medium stores a classroom evaluation program, and the classroom evaluation program is executed by the processor to implement any of the above classroom evaluations. The steps of the method.
  • the present application obtains brain wave data of a student, and then acquires energy information of each band in the brain wave data by using a preset algorithm, and then extracts feature data of the energy information, and finally calculates a target attention value based on the feature data. Analyze the students' attention state; thus realize the calculation and analysis of the attention value, so as to objectively and effectively evaluate the user's attention level, thereby improving the classroom teaching efficiency.
  • FIG. 1 is a schematic structural diagram of a terminal to which a classroom evaluation device belongs in a hardware operating environment according to an embodiment of the present application;
  • FIG. 2 is a schematic flow chart of a first embodiment of a classroom evaluation method according to the present application.
  • FIG. 3 is a schematic flowchart of a step of acquiring energy information of each band in the brain wave data by using a preset algorithm in the second embodiment of the classroom evaluation method of the present application;
  • FIG. 4 is a schematic flowchart of a step of calculating a target attention value based on the feature data in the third embodiment of the classroom evaluation method of the present application;
  • FIG. 5 is a schematic diagram of a refinement process of the step of calculating the target attention value based on the initial attention value according to the fourth embodiment of the classroom evaluation method of the present application;
  • FIG. 6 is a schematic flowchart of the step of analyzing the attention state step in the fifth embodiment of the classroom evaluation method of the present application.
  • FIG. 7 is a schematic flow chart of a sixth embodiment of a classroom evaluation method according to the present application.
  • FIG. 8 is a schematic diagram of a refinement process for detecting a wearing state of a user in the seventh embodiment of the classroom evaluation method of the present application.
  • FIG. 9 is a schematic flow chart of the eighth embodiment of the classroom evaluation method of the present application.
  • FIG. 1 is a schematic structural diagram of a terminal to which a device belongs in a hardware operating environment according to an embodiment of the present application.
  • the terminal in this embodiment of the present application may be a PC.
  • the terminal may include a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002.
  • the communication bus 1002 is used to implement connection communication between these components.
  • the user interface 1003 can include a display, an input unit such as a keyboard, and the optional user interface 1003 can also include a standard wired interface, a wireless interface.
  • the network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a WI-FI interface).
  • the memory 1005 may be a high speed RAM memory or a stable memory (non-volatile) Memory), such as disk storage.
  • the memory 1005 can also optionally be a storage device independent of the aforementioned processor 1001.
  • the terminal may further include a camera, RF (Radio) Frequency, RF) circuits, sensors, audio circuits, WiFi modules, and more.
  • sensors such as light sensors, motion sensors, and other sensors.
  • the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display according to the brightness of the ambient light, and the proximity sensor may turn off the display and/or when the mobile terminal moves to the ear.
  • the gravity acceleration sensor can detect the magnitude of the acceleration in the direction (usually three axes). When it is stationary, it can detect the magnitude and direction of gravity.
  • the mobile terminal can be used to identify the attitude of the mobile terminal (such as horizontal and vertical screen switching, related Game, magnetometer attitude calibration), vibration recognition related functions (such as pedometer, tapping), etc.; of course, the mobile terminal can also be equipped with other sensors such as gyroscope, barometer, hygrometer, thermometer, infrared sensor, etc. Let me repeat.
  • terminal structure shown in FIG. 1 does not constitute a limitation to the terminal, and may include more or less components than those illustrated, or a combination of certain components, or different component arrangements.
  • an operation server may be included in the memory 1005 as a computer storage medium.
  • the network interface 1004 is mainly used to connect to the background server and perform data communication with the background server;
  • the user interface 1003 is mainly used to connect the client (user end), and perform data communication with the client;
  • the processor 1001 can be used to call a program stored in the memory 1005.
  • the device includes: a memory 1005, a processor 1001, and a program stored on the memory 1005 and executable on the processor 1001, wherein when the processor 1001 calls a program stored in the memory 1005, Do the following:
  • the target attention value is calculated based on the feature data, and the attention state is analyzed.
  • processor 1001 can call the classroom evaluation program stored in the memory 1005, and also perform the following operations:
  • the energy information is acquired based on the frequency domain data.
  • processor 1001 can call the classroom evaluation program stored in the memory 1005, and also perform the following operations:
  • the target attention value is calculated based on the initial attention value.
  • processor 1001 can call the classroom evaluation program stored in the memory 1005, and also perform the following operations:
  • the attention value is calculated as the sum of the initial attention value and the predicted attention value, and the attention value is the sum of the initial attention value and the predicted attention value as the target attention value.
  • processor 1001 can call the classroom evaluation program stored in the memory 1005, and also perform the following operations:
  • the target attention value is compared with the attention state evaluation criterion to determine a level level corresponding to the attention value.
  • processor 1001 can call the classroom evaluation program stored in the memory 1005, and also perform the following operations:
  • the user When detecting that the wearing state is not worn, the user is prompted to adjust the wearing device.
  • processor 1001 can call the classroom evaluation program stored in the memory 1005, and also perform the following operations:
  • a current state of the wearing device is determined based on the probability.
  • processor 1001 can call the classroom evaluation program stored in the memory 1005, and also perform the following operations:
  • the brain wave data, the feature data, and the analysis result at the time of attention state analysis are compression-encrypted, and an attention analysis report is generated.
  • FIG. 2 is a schematic flowchart of a first embodiment of a classroom evaluation method according to the present application.
  • the classroom evaluation method includes the following steps:
  • Step S10 acquiring brain wave data of the student
  • the classroom evaluation method is applied to a classroom evaluation system, which includes an EEG collection terminal, a local data collection and processing system, a local database, a cloud server, an EEG database, and an attention reporting system.
  • the brain electrical collection terminal includes an EEG (electroencephalo-graph)
  • EEG electroencephalo-graph
  • the head ring of the brain wave which can collect the brain wave data of the student in real time, and send the collected brain wave data to the local data acquisition and processing system according to the data acquisition frequency, for example, when the data acquisition frequency is set to 160HZ, each 80 raw EEG data were sent to the local data acquisition and processing system as a data packet in 0.5 seconds.
  • the local data collection and processing system includes a local data collection terminal, and the local data collection terminal can pass UDP (User Datagram Protoco User Message Protocol) Broadcast Automatic Scan identifies all intranet head rings and establishes connections via TCP/IP to enable communication and read data from EEG acquisition terminals.
  • UDP User Datagram Protoco User Message Protocol
  • the collection terminal includes an EEG collecting electrode, a microprocessor module, a WIFI module, and an attention indicator light.
  • the microprocessor module acquires brain wave data of the collected student through the brain electrical collecting electrode, and sends the data to the ground data from the wireless local area network through the WIFI module. And the processing system, it is also possible to realize communication between various devices through Bluetooth or the like.
  • Step S20 acquiring energy information of each band in the brain wave data by using a preset algorithm
  • Step S30 extracting feature data of the energy information
  • the energy information includes an energy value corresponding to alpha wave energy, beta wave energy, and theta wave energy
  • the preset algorithm includes a Fourier transform algorithm
  • the representation can represent a certain function satisfying a certain condition as a triangle.
  • a function sine and / or cosine function
  • the energy on the band, and extracting the characteristic data of the energy in different bands of the brain wave data are corresponding spectral changes, thereby being stored in the local database.
  • the characteristic data includes alpha wave energy, beta wave energy, theta wave energy, mean value of each frequency energy in the time domain, standard deviation, energy ratio of each frequency band, product, etc., and the stored data can be used to generate a student attention value report. Analyze students' attention level and analyze student hobbies.
  • Step S40 calculating a target attention value based on the feature data, and analyzing the attention state of the student.
  • the local data collection and processing system analyzes and classifies each student's attention value.
  • the local data acquisition and processing system calculates the final attention value through the calculation method of the attention value, the machine learning auxiliary attention calculation, and the intelligent matching detection algorithm, wherein the calculation method of the attention value calculates the initial attention.
  • the force value, machine learning assisted attention algorithm calculates the predicted attention value, and the target attention value is the sum of the initial attention value and the predicted attention value.
  • the smart wearing detection algorithm determines whether the user wears the device by calculating the probability of wearing the worn state and the non-wearing state of the wearing device, preventing data entering the non-wearing state or wearing but contacting the bad state, and reminding the user to adjust the wearing when the user does not wear the device. device.
  • the classroom evaluation method proposed by the embodiment obtains the brain wave data of the student, and then acquires the energy corresponding to the brain wave data by using a preset algorithm, and then extracts the feature data of the energy information, and finally calculates the target based on the feature data.
  • the attention value is used to analyze the attention state of the students; the calculation and analysis of the attention value is realized, so that the user's attention level is evaluated objectively and effectively, thereby improving the classroom teaching efficiency.
  • step S20 includes:
  • Step S21 performing data cleaning and noise reduction on the brain wave data to obtain target brain wave data
  • the data collected by the EEG collection system contains various noises, mainly including electromyographic signal interference caused by blinking, and potential change caused by friction between the head ring and the skin.
  • the main characteristics of these noises are: special peaks in the time domain signal and the frequency division signal.
  • the main function of the data preprocessing module is to detect these noises and reject them.
  • the data cleaning includes three parts, IMU motion processing, blink detection, and peak compression.
  • the IMU data is headband physical motion data collected by the head loop built-in module, and the data includes three headbands in the three-dimensional space at the time point. Acceleration on the coordinate axis. When the acceleration is greater than a certain threshold, the data of the time is judged to be untrustworthy.
  • V. V_ ⁇ 0 ⁇ + (t-t_ ⁇ 0 ⁇ ) * (V_ ⁇ 1 ⁇ -V_ ⁇ 0 ⁇ ) / (t_ ⁇ 1 ⁇ -t ⁇ 0 ⁇ ), where V is the interpolation at time t, and V_ ⁇ 0 ⁇ and V_ ⁇ 1 ⁇ are the start and end times of the discarded data segment, respectively, V_ ⁇ 0 ⁇ and V_ ⁇ 1 ⁇ is the voltage value at the corresponding time.
  • the signal may still be affected by different noises, causing the voltage to be too high, and the noise is further processed by the peak compression.
  • the band is abnormal voltage.
  • the voltage value is considered too high.
  • the collected data of the brain wave data is cleaned and the data obtained by the noise reduction is filtered again, first by bandpass filtering, then by band rejection filtering, and finally the band-block filtered data is used as the target brain wave data. .
  • Step S22 acquiring frequency domain data by using a Fourier transform algorithm based on the target brain wave data
  • Step S23 acquiring the energy information based on the frequency domain data.
  • the Fourier transform is used to obtain the frequency domain data, and the spectrum is generated.
  • the frequency spectrum is the frequency distribution curve, and the complex oscillation is decomposed into a resonant wave with different amplitudes and different frequencies. The amplitudes of these resonant waves are arranged according to frequency.
  • the graph is called the spectrum.
  • the user state change can be reflected from the change of the spectrum, and the corresponding energy information can be automatically obtained according to the frequency domain data, and the energy information includes the energy value corresponding to the alpha wave energy, the beta wave energy, and theta wave energy.
  • the frequency domain data obtained by the Fourier transform and the acquired brain wave data can extract characteristic data of energy on different bands, for example, the overall energy distribution situation, the frequency corresponding to the energy peak, and the spectral change corresponding to the user state change
  • the feature data and the brain wave data are stored in a local database, and the feature data includes feature data including delta, theta, alpha, Beta, high-beta, gamma energy values of each frequency, the mean value of each frequency energy in the time domain, the standard deviation, the ratio of the energy of each frequency band, the product, and so on.
  • step S40 includes:
  • Step S41 normalizing the maximum value and the minimum value of the energy based on the feature data to obtain a normalized energy value
  • Step S42 calculating a ratio of the energy of the Beta segment energy to the energy value of the Alpha segment energy, the average peak distance of the Beta segment, and the maximum value filtering of the Beta segment energy;
  • Step S43 calculating a weighted sum of the ratio, the average peak distance, and the maximum value filter, and using the weighted squared sum as an initial attention value;
  • Step S44 calculating the target attention value based on the initial attention value.
  • the ratio of the energy of the Beta segment energy to the energy value of the Alpha segment energy, the average peak distance of the Beta segment, and the maximum value of the Beta segment energy are calculated, wherein the Beta segment average
  • the crest distance is the distance between the crest and the crest in a time window that is forward in the current time.
  • the classroom evaluation method proposed in this embodiment normalizes the maximum value and the minimum value of the energy based on the feature data to obtain a normalized energy value, and then calculates the ratio of the energy of the Beta segment energy to the energy value of the Alpha segment energy, and the Beta segment.
  • the attention value is used to calculate the target attention value; the initial attention value is calculated according to the ratio of the energy of the Beta segment energy to the energy value of the Alpha segment energy, the average peak distance of the Beta segment, and the maximum value of the Beta segment energy, thereby being able to calculate
  • the target attention value further improves the efficiency of classroom evaluation and analysis.
  • the initial attention value can also reflect the user's current attention level.
  • step S44 includes:
  • Step S441 calculating a predicted attention value by using a machine learning training model
  • Step S442 calculating the attention value as the sum of the initial attention value and the predicted attention value, and using the attention value as the sum of the initial attention value and the predicted attention value as the target attention value.
  • the overall learning algorithm is used, and the post-pruning and ten-fold cross-validation is used to learn according to the data samples, and the trained model is used to predict the attention value.
  • the input of the machine learning training model includes the original voltage value, the respective energy at the three frequencies of alpha, beta, and theta, the two-two ratio of the energy values of the three energies, and the two-two product of the energy values of the three energies.
  • the statistical features in the time domain have a total of sixteen values. Each value is averaged over ten data points before entering the training model, and the mean is used for prediction. Through the calculation of the model, the predicted attention value can be obtained, and then the sum of the initial attention value and the predicted attention value is calculated to obtain the target attention value.
  • the classroom evaluation method proposed in this embodiment calculates a predicted attention value by using a machine learning training model, and then calculates the attention value as a sum of an initial attention value and the predicted attention value, and the attention value is The sum of the initial attention value and the predicted attention value is taken as the target attention value; the predicted attention value is calculated by the machine learning training model, thereby calculating the target attention value, thereby improving the efficiency of the classroom evaluation.
  • step S40 further includes:
  • Step S45 obtaining an attention state evaluation standard
  • Step S46 comparing the attention value with the attention state evaluation standard, and determining a level level corresponding to the attention value.
  • the attention evaluation standard includes an upper limit value and a lower limit value preset by a technician to determine a corresponding attention level level, and compare the target attention value with the attention state standard, for example, when The attention value of the collected students is less than the preset lower limit value, and it is judged that the attention is not concentrated.
  • the attention value of the collected student is greater than the set upper limit value, it is determined that the student's attention is highly concentrated, and the attention value is equal to
  • the preset lower limit value or upper limit value and the value between the upper limit value and the lower limit value are used, the attention is determined to be centered, and the detection terminal can display the attention state of the student by representing the color change of the icon of the student, and The attention level is reflected in real time by the color change of the attention indicator light. For example, red indicates concentration, blue indicates inattention, and yellow indicates attention is centered.
  • the attention state evaluation standard may set multiple levels, and the different levels correspond to the respective attention value intervals. As long as the target attention value is compared with the attention state evaluation standard, the current attention level level of the user can be determined.
  • Equal Bining's method maps the attention value to a value between 0-100, which can represent the attention level score.
  • the level corresponding to the score is found in the attention evaluation criteria, for example, the target The value obtained after the conversion of the attention value is 80, and the score is judged to be excellent by the attention state evaluation standard, which represents a high concentration.
  • the overall attention level of the whole class can also be measured in real time.
  • the average attention value of the whole class is lower than the set lower limit value, it is judged that the students as a whole are too sloppy.
  • the average attention level of the whole class is higher than the set upper limit value, it is determined that the students are highly concentrated as a whole, and the detection terminal can be
  • the overall attention state of the class is displayed by representing the real-time curve color change.
  • the classroom evaluation method proposed by the embodiment obtains the attention state evaluation standard, and then compares the target attention value with the attention state evaluation standard to determine the level corresponding to the attention value;
  • the target attention value determines the corresponding level of attention level, so that the user's attention level can be clearly understood, and the quality of classroom teaching is reflected, thereby improving classroom teaching efficiency.
  • step S10 the method further includes:
  • Step S50 detecting a wearing state of the wearing device
  • Step S60 when detecting that the wearing state is not worn, prompting the user to adjust the wearing device.
  • the evaluation system is capable of autonomously completing the detection of the wearing state, thereby preventing entry of data in a non-wearing state or wearing but a bad contact state, and prompting the user to adjust the wearing device.
  • the detected voltage is greater than the preset threshold, it is considered that the brain wave signal in the device is abnormal, and is determined to be a wearing or removing action, and the current state may be a wearing state or a non-wearing state, and the calculated wearing state corresponds to the unworn state.
  • the probability is used to determine the current state. If the wearing state of the device of the current user is not worn, the user is prompted to adjust the wearing device, and the prompting method may be a voice prompt, or send a prompt message to the terminal display interface, or by prompting The light prompts the component to prompt.
  • the classroom evaluation method provided in this embodiment detects the wearing state of the wearing device, and then prompts the user to adjust the wearing device when detecting that the wearing state is not worn; thereby avoiding avoiding entering the non-wearing state or wearing the poor contact state. data.
  • step S50 includes:
  • Step S51 detecting whether the brain wave signal in the wearing device is abnormal
  • Step S52 when it is detected that the brain wave signal is abnormal in the wearing device, calculate the probability of the worn state and the unworn state;
  • Step S53 determining a current state of the wearing device based on the probability.
  • the brain wave signal in the device when the detected voltage is greater than the preset threshold, the brain wave signal in the device is considered to be abnormal, and the time is first divided into a plurality of time periods, and it is considered that the same state (wearing or not wearing) in one time period.
  • the basis of the segmentation is that when the voltage appearing in the EEG data is greater than a predetermined value (for example, greater than 10000V), wherein the brainwave signal abnormality (the voltage value is greater than a preset threshold) is currently detected in the device, it is determined to be a wearer. Or remove the action and re-determine whether the current state is worn or not.
  • the judgment method is as follows: First, calculate a base probability (Prior), the base probability is only related to the previous state, if the previous state is judged to be worn The state, the converted non-wearing state base probability is slightly higher than the probability of wearing state, and then according to the characteristics of the energy of each frequency band, each data point votes on the current state, if the maximum energy value of a certain frequency band is greater than the energy of other frequency bands If the maximum energy value is twice, the vote is worn, otherwise it is not worn, and the votes of the two states (Vots) and the total number of votes (TotalVotes) are counted.
  • the probability of calculating the two states is:
  • the classroom evaluation method proposed in this embodiment detects the abnormality of the brain wave signal in the wearing device, and then calculates the probability of the worn state and the unworn state when detecting the abnormality of the brain wave signal in the wearing device, and finally based on the The probability determines the current state of the wearing device; it is achieved that the current state of the wearing device is correctly determined, and data that is entered in the non-wearing state or worn but in poor contact state is avoided.
  • an eighth embodiment of the classroom evaluation method of the present application is provided. Referring to FIG. 9, in this embodiment, after step S40, the method further includes:
  • Step S70 classifying and storing the brain wave data, the feature data, and the analysis result when the attention state analysis is performed;
  • step S80 the brain wave data, the feature data, and the analysis result at the time of attention state analysis are compression-encrypted, and an attention analysis report is generated.
  • the original data, the feature data, and the attention level level are sent to the cloud server, and the cloud server collects the data according to the user and the data.
  • the environment and other tags are classified and stored, and the data is compressed and encrypted and stored in the EEG database, and an attention analysis report is generated, and the generated attention value report is sent by e-mail to the terminal of the student teacher's parent and the academic office, wherein
  • the attention analysis report includes the level of attention level, the phase change curve of the attention value, and the brain wave data and the curve analysis of the characteristic data.
  • cloud services can be redesigned by API (Application Programming Interface application programming interface).
  • the teacher can personally set the seat layout according to the class situation and the student hypocrisy according to the actual situation of the class, and connect and display the connection status of the corresponding device terminal.
  • the classroom evaluation method proposed in the embodiment analyzes the brain wave data, the feature data, and the analysis result in the attention state analysis, and then analyzes the brain wave data, the feature data, and the attention state analysis.
  • the result is compressed and encrypted, and an attention analysis report is generated; the attention analysis report is generated to facilitate the user to understand the classroom evaluation results.
  • the embodiment of the present application further provides a computer readable storage medium.
  • the classroom readable program is stored on the computer readable storage medium of the present application, and the classroom evaluation program is executed by the processor to implement the following steps:
  • the target attention value is calculated based on the feature data, and the attention state of the student is analyzed.
  • the energy information is acquired based on the frequency domain data.
  • the target attention value is calculated based on the initial attention value.
  • the attention value is calculated as the sum of the initial attention value and the predicted attention value, and the attention value is the sum of the initial attention value and the predicted attention value as the target attention value.
  • the target attention value is compared with the attention state evaluation criterion to determine a level level corresponding to the attention value.
  • the user When detecting that the wearing state is not worn, the user is prompted to adjust the wearing device.
  • a current state of the wearing device is determined based on the probability.
  • the brain wave data, the feature data, and the analysis result at the time of attention state analysis are compression-encrypted, and an attention analysis report is generated.
  • the technical solution of the present application which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM as described above). , a disk, an optical disk, including a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in the various embodiments of the present application.
  • a terminal device which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.

Abstract

一种课堂评测方法、课堂评测装置及计算机可读存储介质，所述方法包括以下步骤：获取学生的脑电波数据（S10）；利用预设算法获取所述脑电波数据中各波段的能量信息（S20）；提取所述能量信息的特征数据（S30）；基于所述特征数据计算目标注意力数值，分析注意力状态（S40）。所述方法实现了对注意力数值的计算与分析，从而客观、有效的对用户注意力水平进行评测，进而提高了课堂教学效率。

Description

课堂评测方法、装置及计算机可读存储介质
本申请要求于2018年04月17日提交中国专利局、申请号为201810345765.7、申请名称为“课堂评测方法、装置及计算机可读存储介质”的中国专利申请的优先权，其全部内容通过引用结合在申请中。
技术领域
本申请涉及教育信息化技术领域，尤其涉及一种课堂评测方法、装置及计算机可读存储介质。
背景技术
人类的心理活动变化与自身的脑电波变化存在一定的关联，例如，人在专心学习、注意力集中时，大脑频率处于α波，（频率范围8-13Hz），此时脑波比较平稳，是人们学习与思考的最佳脑波状态。当学习兴奋，或精神紧张时，大脑频率处于β波（频率范围14Hz以上），此时脑波频率变快，幅度加大，适当的β波对注意力提升以及认知行为的发展有积极作用，但持续时间较短，且易疲劳。当学习疲劳、精神松弛时，大脑频率处于θ波（频率范围4-8Hz），此时脑波整体比较杂乱，且频率逐渐变慢，人的意识逐渐涣散，身体深沉放松，此时对触发深沉记忆、强化长期记忆等帮助极大。
目前，学校的课堂教学系统越来越多采用多媒体技术，但授课方式的效果测评方式仍然停留在主观观察和阶段性测试等较落后的方式，教师很难输入观察学生的注意力水平，而且，通过课后作业或者阶段性测试来评测课堂授课的效果，所以，目前的课堂教学系统缺少客观、有效的评测，无法深入对学生课堂的注意力水平进行评测分析，造成课堂教学效率低。
上述内容仅用于辅助理解本申请的技术方案，并不代表承认上述内容是现有技术。
发明内容
本申请的主要目的在于提供一种课堂评测方法、装置及计算机可读存储介质，旨在解决课堂教学系统缺少客观、有效的评测，无法深入对学生课堂的注意力水平进行评测分析，造成课堂教学效率低的技术问题。
为实现上述目的，本申请提供一种课堂评测方法，所述方法包括以下步骤：
获取学生的脑电波数据；
利用预设算法获取所述脑电波数据中各波段的能量信息；
提取所述能量信息的特征数据；
基于所述特征数据计算目标注意力数值，分析学生的注意力状态。
可选地，利用预设算法获取所述脑电波数据中各波段的能量信息的步骤包括：
对所述脑电波数据中进行数据清理及降噪，以得到目标脑电波数据；
基于所述目标脑电波数据利用傅里叶变换算法获取频域数据；
基于所述频域数据获取所述能量信息。
可选地，所述基于所述特征数据计算目标注意力数值的步骤包括：
基于所述特征数据将能量的最大值及最小值进行标准化，以得到标准化能量值；
计算Beta段能量与Alpha段能量的能量值的比值、Beta段的平均波峰距离及Beta段能量的最值滤波；
计算所述比值、所述平均波峰距离及所述最值滤波的加权总和，将所述加权平方和作为初始注意力数值；
基于所述初始注意力数值计算所述目标注意力数值。
可选地，所述基于所述初始注意力数值计算所述目标注意力数值的步骤还包括：
利用机器学习训练模型计算预测注意力数值；
计算所述注意力数值为初始注意力数值与所述预测注意力数值之和，将所述注意力数值为初始注意力数值与所述预测注意力数值之和作为目标注意力数值。
可选地，所述分析学生的注意力状态的步骤包括：
获取注意力状态评测标准；
将所述目标注意力数值与所述注意力状态评测标准进行比较，确定所述注意力数值对应的水平等级。
可选地，所述获取脑电波数据之后，所述课堂评测方法还包括：
检测佩戴设备的佩戴状态；
当检测所述佩戴状态为未佩戴时，提示用户调整佩戴设备。
可选地，所述检测用户佩戴状态的步骤包括：
检测佩戴设备中脑电波信号是否异常；
当检测到所述佩戴设备中脑电波信号异常时，计算已佩戴状态及未佩戴状态的概率；
基于所述概率确定所述佩戴设备的当前状态。
可选地，所述基于所述特征数据计算注意力数值，分析学生的注意力状态之后，所述课堂评测方法还包括：
分类存储所述脑电波数据、所述特征数据及注意力状态分析时的分析结果；
将所述脑电波数据、特征数据及注意力状态分析时的分析结果进行压缩加密，并生成注意力分析报告。
此外，为实现上述目的，本申请还提供一种课堂评测装置，课堂评测装置包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的课堂评测程序，所述课堂评测程序被所述处理器执行时实现上述任一项课堂评测方法的步骤。
此外，为实现上述目的，本申请还提供一种计算机可读存储介质，所述计算机可读存储介质上存储有课堂评测程序，所述课堂评测程序被处理器执行时实现上述任一项课堂评测方法的步骤。
本申请通过获取学生的脑电波数据，接着利用预设算法获取所述脑电波数据中各波段的能量信息，然后提取所述能量信息的特征数据，最后基于所述特征数据计算目标注意力数值，分析学生的注意力状态；由此实现了对注意力数值的计算与分析，从而客观、有效的对用户注意力水平进行评测，进而提高了课堂教学效率。
附图说明
图1是本申请实施例方案涉及的硬件运行环境中课堂评测装置所属终端的结构示意图；
图2为本申请课堂评测方法第一实施例的流程示意图；
图3为本申请课堂评测方法第二实施例中所述利用预设算法获取所述脑电波数据中各波段的能量信息步骤的细化流程示意图；
图4为本申请课堂评测方法第三实施例中所述基于所述特征数据计算目标注意力数值步骤的细化流程示意图；
图5为本申请课堂评测方法第四实施例中所述基于所述初始注意力数值计算所述目标注意力数值步骤的细化流程示意图；
图6为本申请课堂评测方法第五实施例中所述分析注意力状态步骤的细化流程示意图；
图7为本申请课堂评测方法第六实施例的流程示意图；
图8为本申请课堂评测方法第七实施例中所述检测用户佩戴状态的细化流程示意图；
图9为本申请课堂评测方法第八实施例的流程示意图。
本申请目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
具体实施方式
应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
如图1所示，图1是本申请实施例方案涉及的硬件运行环境中装置所属终端的结构示意图。
本申请实施例终端可以是PC。如图1所示，该终端可以包括：处理器1001，例如CPU，网络接口1004，用户接口1003，存储器1005，通信总线1002。其中，通信总线1002用于实现这些组件之间的连接通信。用户接口1003可以包括显示屏（Display）、输入单元比如键盘（Keyboard），可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口（如WI-FI接口）。存储器1005可以是高速RAM存储器，也可以是稳定的存储器（non-volatile memory），例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。
可选地，终端还可以包括摄像头、RF（Radio Frequency，射频）电路，传感器、音频电路、WiFi模块等等。其中，传感器比如光传感器、运动传感器以及其他传感器。具体地，光传感器可包括环境光传感器及接近传感器，其中，环境光传感器可根据环境光线的明暗来调节显示屏的亮度，接近传感器可在移动终端移动到耳边时，关闭显示屏和/或背光。作为运动传感器的一种，重力加速度传感器可检测方向上（一般为三轴）加速度的大小，静止时可检测出重力的大小及方向，可用于识别移动终端姿态的应用（比如横竖屏切换、相关游戏、磁力计姿态校准）、振动识别相关功能（比如计步器、敲击）等；当然，移动终端还可配置陀螺仪、气压计、湿度计、温度计、红外线传感器等其他传感器，在此不再赘述。
本领域技术人员可以理解，图1中示出的终端结构并不构成对终端的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
如图1所示，作为一种计算机存储介质的存储器1005中可以包括操作服务器、网络通信模块、用户接口模块以及程序。
在图1所示的终端中，网络接口1004主要用于连接后台服务器，与后台服务器进行数据通信；用户接口1003主要用于连接客户端（用户端），与客户端进行数据通信；而处理器1001可以用于调用存储器1005中存储的程序。
在本实施例中，装置包括：存储器1005、处理器1001及存储在所述存储器1005上并可在所述处理器1001上运行的程序，其中，处理器1001调用存储器1005中存储的程序时，执行以下操作：
获取脑电波数据；
利用预设算法获取所述脑电波数据中各波段的能量信息；
提取所述能量的特征数据；
基于所述特征数据计算目标注意力数值，分析注意力状态。
进一步地，处理器1001可以调用存储器1005中存储的课堂评测程序，还执行以下操作：
对所述脑电波数据中进行数据清理及降噪，以得到目标脑电波数据；
基于所述目标脑电波数据利用傅里叶变换算法获取频域数据；
基于所述频域数据获取所述能量信息。
进一步地，处理器1001可以调用存储器1005中存储的课堂评测程序，还执行以下操作：
基于所述特征数据将能量的最大值及最小值进行标准化，以得到标准化能量值；
计算Beta段能量与Alpha段能量的能量值的比值、Beta段的平均波峰距离及Beta段能量的最值滤波；
计算所述比值、所述平均波峰距离及所述最值滤波的加权总和，将所述加权平方和作为初始注意力数值；
基于所述初始注意力数值计算所述目标注意力数值。
进一步地，处理器1001可以调用存储器1005中存储的课堂评测程序，还执行以下操作：
利用机器学习训练模型计算预测注意力数值；
计算所述注意力数值为初始注意力数值与所述预测注意力数值之和，将所述注意力数值为初始注意力数值与所述预测注意力数值之和作为目标注意力数值。
进一步地，处理器1001可以调用存储器1005中存储的课堂评测程序，还执行以下操作：
获取注意力状态评测标准；
将所述目标注意力数值与所述注意力状态评测标准进行比较，确定所述注意力数值对应的水平等级。
进一步地，处理器1001可以调用存储器1005中存储的课堂评测程序，还执行以下操作：
检测佩戴设备的佩戴状态；
当检测所述佩戴状态为未佩戴时，提示用户调整佩戴设备。
进一步地，处理器1001可以调用存储器1005中存储的课堂评测程序，还执行以下操作：
检测佩戴设备中脑电波信号是否异常；
当检测到所述佩戴设备中脑电波信号异常时，计算已佩戴状态及未佩戴状态的概率；
基于所述概率确定所述佩戴设备的当前状态。
进一步地，处理器1001可以调用存储器1005中存储的课堂评测程序，还执行以下操作：
分类存储所述脑电波数据、所述特征数据及注意力状态分析时的分析结果；
将所述脑电波数据、特征数据及注意力状态分析时的分析结果进行压缩加密，并生成注意力分析报告。
本申请进一步提供一种课堂评测方法。参照图2，图2为本申请课堂评测方法第一实施例的流程示意图。
在本实施例中，该课堂评测方法包括以下步骤：
步骤S10，获取学生的脑电波数据；
在本实施例中，该课堂评测方法应用于课堂评测系统，该课堂评测系统包括脑电采集终端、本地数据采集与处理系统、本地数据库、云服务器、脑电数据库、注意力报告系统。
该脑电采集终端包括采集EEG（electroencephalo-graph 脑电波）的头环，该头环能够实时采集学生的脑电波数据，根据数据采集频率将采集到的脑电波数据发送至本地数据采集与处理系统，例如，当数据采集频率设置为160HZ，每0.5秒将80个原始脑电数据作为一个数据包发送给本地数据采集与处理系统。本地数据采集与处理系统包括本地数据采集终端，本地数据采集终端可以通过UDP（User Datagram Protoco 用户报文协议）广播自动扫描识别所有网内头环并通过TCP/IP建立连接，实现通信，从脑电采集终端读取数据。采集终端包括脑电采集电极、微处理器模块、WIFI模块、注意力指示灯，微处理器模块通过脑电采集电极获取被采集学生的脑电波数据，经WIFI模块从无线局域网送至地数据采集与处理系统，还可以通过蓝牙等实现各个设备间的通信。
步骤S20，利用预设算法获取所述脑电波数据中各波段的能量信息；
步骤S30，提取所述能量信息的特征数据；
在本实施例中，该能量信息包括alpha波能量、beta波能量、theta波能量对应的能量值，该预设算法包括傅里叶变换算法，表示能将满足一定条件的某个函数表示成三角函数（正弦和/或余弦函数），或者该三角函数的积分的线性组合。在获取到脑电采集终端采集到的脑电波数据时，对脑电波数据进行数据清理及降噪，经过多个带通或者带阻滤波，过滤多种噪声，然后采用傅里叶变换获得各个频率波段上的能量，并提取脑电波数据中不同波段上能量的特征数据，例如，整体能量分布态势、能量峰值对应的频率、用户状态变化是对应的频谱变化，从而存储进本地数据库。该特征数据包括alpha波能量、beta波能量、theta波能量、各频率能量在时域上的均值，标准差，各频段能量的比值、乘积等，储存的数据可以用于生成学生注意力数值报告、分析学生注意力提升水平及分析学生爱好特长等。
步骤S40，基于所述特征数据计算目标注意力数值，分析学生的注意力状态。
在本实施例中，本地数据采集与处理系统对每个学生的注意力数值进行分析与课堂检测。根据各个特征数据，本地数据采集与处理系统通过注意力数值的计算方法、机器学习辅助注意力计算、以及智能配到检测算法计算最终的注意力数值，其中，注意力数值的计算方法计算初始注意力数值，机器学习辅助注意力算法计算预测注意力数值，目标注意力数值为初始注意力数值及预测注意力数值之和。智能佩戴检测算法通过计算佩戴设备的已佩戴状态与未佩戴状态的概率来判断用户是否佩戴设备，防止录入非佩戴状态或佩戴但接触不良状态的数据，在用户没有佩戴设备时，提醒用户调整佩戴设备。
本实施例提出的课堂评测方法，通过获取学生的脑电波数据，接着利用预设算法获取所述脑电波数据对应的能量，然后提取所述能量信息的特征数据，最后基于所述特征数据计算目标注意力数值，分析学生的注意力状态；实现了对注意力数值的计算与分析，从而客观、有效的对用户注意力水平进行评测，进而提高了课堂教学效率。
基于第一实施例，提出本申请课堂评测方法的第二实施例，参照图3，本实施例中，步骤S20包括：
步骤S21，对所述脑电波数据中进行数据清理及降噪，以得到目标脑电波数据；
在本实施例中，脑电收集系统采集到的数据中包含多种噪音，主要包括因眨眼等造成的肌电信号干扰、因头环与皮肤摩擦造成的电势变化。这些噪音的主要特征为：在时域信号以及分频信号上的特殊峰值。数据预处理模块的主要功能是检测这些噪声并对这些噪声进行剔除。该数据清理包含三个部分，IMU动作处理，眨眼检测，波峰压缩，具体地，IMU数据是头环内置模块采集的头环物理运动数据，该数据包括头环在该时间点在三维空间三个坐标轴上的加速度，当加速度大于一定阈值，则判断该时间的数据不可信，对于不可信的数据段，直接丢弃，并在时域上进行线性插值，例如，V = V_{0} + (t-t_{0}) * (V_{1}-V_{0}) / (t_{1}-t{0})，其中，V为在时刻t进行的插值，V_{0}和V_{1}分别是丢弃数据段的起始和结束时刻，V_{0}和V_{1}是相应时刻的电压值。
在经过IMU处理和眨眼检测之后，信号中仍可能受到不同的噪声影响，从而造成电压过高，则通过波峰压缩对噪声进行进一步处理，具体地，对于任何原始电压值过高的波段，认为该波段是电压异常，电压值超过预设阈值时，则认为电压值过高，对于超过预设阈值的异常波段，按照下列公式对电压值进行压缩:V=U_avgNormal / avdyArtifact其中， 是原始电压值，avgNormal是正常波段的电压均值，avdyArtifact是异常波段的电压均值，V是异常波段压缩后的数值。
进一步地，将采集到的脑电波数据进行清理及降噪后得到的数据再次进行滤波操作，首先通过带通滤波，然后再进行带阻滤波，最后将带阻滤波后的数据作为目标脑电波数据。
步骤S22，基于所述目标脑电波数据利用傅里叶变换算法获取频域数据；
步骤S23，基于所述频域数据获取所述能量信息。
在本实施例中，采用傅里叶变换获取频域数据，生成频谱，频谱就是频率的分布曲线，复杂振荡分解为振幅不同和频率不同的谐振荡，这些谐振荡的幅值按频率排列的的图形叫做频谱。用户状态变化能够从频谱的变化中体现，根据频域数据能够自动获取到对应的能量信息，该能量信息包括alpha波能量、beta波能量、theta波能量对应的能量值。根据傅里叶变换获得的频域数据及采集到的脑电波数据能够提取不同波段上能量的特征数据，例如，整体能量分布态势、能量峰值对应的频率、用户状态变化对应的频谱变化，将这些特征数据及脑电波数据存储至本地数据库，该特征数据包括特征数据包括delta，theta，alpha， beta， high-beta， gamma各频率能量值，各频率能量在时域上的均值，标准差，各频段能量的比值、乘积等。
基于第二实施例，提出本申请课堂评测方法的第三实施例，参照图4，本实施例中，步骤S40包括：
步骤S41，基于所述特征数据将能量的最大值及最小值进行标准化，以得到标准化能量值；
步骤S42，计算Beta段能量与Alpha段能量的能量值的比值、Beta段的平均波峰距离及Beta段能量的最值滤波；
步骤S43，计算所述比值、所述平均波峰距离及所述最值滤波的加权总和，将所述加权平方和作为初始注意力数值；
步骤S44，基于所述初始注意力数值计算所述目标注意力数值。
在本实施例中，在计算注意力数值时，首先通过注意力数值计算方法计算初始注意力数值，然后通过机器学习训练模型计算预测注意力数值，其中，在计算初始注意力数值时，先对Beta段能量进行标准化，可以根据Beta段能量实时最大值和最小值进行标准化，Norm = (Beta–min) / (max - min)，其中Norm是标准化后的结果，Beta是实时的Beta段能量，min和max分别是实时的Beta能量最小值及最大值。
进一步地，对Beta段能量进行标准化得到标注化能量值时，计算Beta段能量与Alpha段能量的能量值的比值、Beta段的平均波峰距离及Beta段能量的最值滤波，其中，Beta段平均波峰距离是在以当前时间向前的一个时间窗口内波峰与波峰之间的距离。计算Beta段能量与Alpha段能量的能量值的比值、Beta段的平均波峰距离及Beta段能量的最值滤波这三个数值的加权总和。
本实施例提出的课堂评测方法，通过基于所述特征数据将能量的最大值及最小值进行标准化，以得到标准化能量值，然后计算Beta段能量与Alpha段能量的能量值的比值、Beta段的平均波峰距离及Beta段能量的最值滤波，接着计算所述比值、所述平均波峰距离及所述最值滤波的加权总和，将所述加权平方和作为初始注意力数值，最后基于所述初始注意力数值计算所述目标注意力数值；实现了根据Beta段能量与Alpha段能量的能量值的比值、Beta段的平均波峰距离及Beta段能量的最值滤波计算初始注意力数值，从而能够计算目标注意力数值，进一步提高了课堂评测及分析的效率，同时，初始注意力数值也能体现用户当前注意力水平。
基于第三实施例，提出本申请课堂评测方法的第四实施例，参照图5，本实施例中，步骤S44包括：
步骤S441，利用机器学习训练模型计算预测注意力数值；
步骤S442，计算所述注意力数值为初始注意力数值与所述预测注意力数值之和，将所述注意力数值为初始注意力数值与所述预测注意力数值之和作为目标注意力数值。
在本实施例中，采用整体学习算法，使用事后剪枝及十折交叉验证，根据数据样本进行学习，将训练出的模型用于预测注意力数值。机器学习训练模型的输入包括原始电压值、alpha、beta、theta三个频率上各自的能量，三个能量的能量值的两两比值，三个能量的能量值的两两乘积，三个能量在时域上的统计特征共十六个数值，每个数值在进入训练模型前，都在临近十个数据点上进行了平均，并用均值进行预测。通过模型的运算能够得到预测注意力数值，然后计算初始注意力数值与预测注意力数值之和得到目标注意力数值。
本实施例提出的课堂评测方法，通过利用机器学习训练模型计算预测注意力数值，然后计算所述注意力数值为初始注意力数值与所述预测注意力数值之和，将所述注意力数值为初始注意力数值与所述预测注意力数值之和作为目标注意力数值；实现了通过机器学习训练模型计算预测注意力数值，从而计算目标注意力数值，进而提高了课堂评测的效率。
基于第四实施例，提出本申请课堂评测方法的第五实施例，参照图6，本实施例中，步骤S40还包括：
步骤S45，获取注意力状态评测标准；
步骤S46，将所述注意力数值与所述注意力状态评测标准进行比较，确定所述注意力数值对应的水平等级。
在本实施例中，该注意力评测标准包括由技术人员预设的上限值及下限值来确定对应的注意力水平等级，将目标注意力数值与注意力状态标准进行比较，例如，当被采集学生的注意力数值小于预设的下限值，判定为注意力不集中，当被采集学生的注意数值大于设定上限值，判定为该学生注意力高度集中，当注意力数值等于预设的下限值或者上限值、在上限值与下限值中间的数值时，则判定注意力居中，检测终端可以通过代表学生的图标颜色变化来显示该学生注意力状态，还可以通过注意力意力指示灯的颜色变化实时反映注意力水平，例如，红色代表注意力集中，蓝色表示注意力不集中，黄色表示注意力居中。当然，注意力状态评测标准中可以设定多个等级，不同等级对应各个注意力数值区间，只要将目标注意力数值与注意力状态评测标准进行比较，则能确定用户当前注意力水平等级。或者，通过Equal Bining的方法将注意力数值映射为0-100之间的数值，则该数值可以表示注意力水平评分，然而，根据该评分在注意力评测标准中找到该评分对应的水平等级，例如，将目标注意力数值转化后得到的数值为80，通过注意力状态评测标准判定评分为优秀，代表高度集中。
进一步地，也可以实时测量全班整体注意力水平。当全班平均注意力数值低于设定的下限值时，判定学生整体过于散漫，当全班平均注意力水平高于设定上限值时，则判定为学生整体高度集中，检测终端可通过代表实时曲线颜色变化来显示全班整体注意力状态。
本实施例提出的课堂评测方法，通过获取注意力状态评测标准，然后将所述目标注意力数值与所述注意力状态评测标准进行比较，确定所述注意力数值对应的水平等级；实现了根据目标注意力数值确定对应的注意力水平等级，从而能够清楚了解用户的注意力水平，反应课堂教学质量，从而提高课堂教学效率。
基于第五实施例，提出本申请课堂评测方法的第六实施例，参照图7，本实施例中，步骤S10之后，还包括：
步骤S50，检测佩戴设备的佩戴状态；
步骤S60，当检测所述佩戴状态为未佩戴时，提示用户调整佩戴设备。
在本实施例中，该评测系统能够自主完成佩戴状态的检测，从而防止录入非佩戴状态或佩戴但接触不良状态的数据，并提示用户调整佩戴设备。当检测到电压大于预设阈值时，则认为设备中脑电波信号异常，判断为一个佩戴或者取下的动作，当前状态可以是佩戴状态或者未佩戴状态，通过计算佩戴状态与未佩戴状态对应的概率来确定当前所处的状态，若当前检测用户的设备的佩戴状态为未佩戴时，将提示用户调整佩戴设备，提示方法可以是语音提示，或者将提示消息发送至终端显示界面，或者通过提示灯灯提示元件进行提示。
本实施例提出的课堂评测方法，通过检测佩戴设备的佩戴状态，然后当检测所述佩戴状态为未佩戴时，提示用户调整佩戴设备；实现了避免在录入非佩戴状态或佩戴但接触不良状态的数据。
基于第六实施例，提出本申请课堂评测方法的第七实施例，参照图8，本实施例中，步骤S50包括：
步骤S51，检测佩戴设备中脑电波信号是否异常；
步骤S52，当检测到所述佩戴设备中脑电波信号异常时，计算已佩戴状态及未佩戴状态的概率；
步骤S53，基于所述概率确定所述佩戴设备的当前状态。
在本实施例中，当检测到电压大于预设阈值时，则认为设备中脑电波信号异常，首先将时间分成多个时段，认为一个时段内都是同一状态（已佩戴或未佩戴）。分割的依据是EEG数据中出现的电压大于某一预设值时，（例如，大于10000V），其中，当前检测到设备中脑电波信号异常（电压值大于预设阈值），则判断为一个佩戴或者取下的动作，并重新判断当前状态为已佩戴状态还是未佩戴状态，判断方法如下：首先计算一个基础概率（Prior），该基础概率只跟前一状态有关，若前一状态判断为已佩戴状态，则转换后的非佩戴状态基础概率略高于已佩戴状态的概率，然后根据各频段能量的特征，各数据点对当前状态进行投票，如果某频段的最大能量值大于其他各频段能量中最大能量值的两倍，则投票为已佩戴状态，否则为未佩戴状态，并统计两个状态分别的票数(Votes)，以及总票数(TotalVotes)，最后计算两个状态的概率为：
P=priori*Votes / TotalVotes
选择P较大的状态作为当前状态。
本实施例提出的课堂评测方法，通过检测佩戴设备中脑电波信号是否异常，然后当检测到所述佩戴设备中脑电波信号异常时，计算已佩戴状态及未佩戴状态的概率，最后基于所述概率确定所述佩戴设备的当前状态；实现了正确确定佩戴设备的当前状态，避免在录入非佩戴状态或佩戴但接触不良状态的数据。
基于第七实施例，提出本申请课堂评测方法的第八实施例，参照图9，本实施例中，步骤S40之后，还包括：
步骤S70，分类存储所述脑电波数据、所述特征数据及注意力状态分析时的分析结果；
步骤S80，将所述脑电波数据、特征数据及注意力状态分析时的分析结果进行压缩加密，并生成注意力分析报告。
在本实施例中，本地数据采集与处理系统在采集并处理原始脑电数据后，将原始数据、特征数据，以及注意力水平等级等发送至云服务器，云服务器将数据根据用户、数据采集的环境等标签进行分类与存储，将数据压缩加密后存入脑电数据库，并生成注意力分析报告，将生成的注意力数值报告通过电子邮件发至学生老师家长和教务处所在终端，其中，该注意力分析报告包括注意力水平等级、注意力数值阶段性的变化曲线及脑电波数据、特征数据的曲线图分析等。当然，云服务可通过重新设计API（Application Programming Interface 应用程序编程接口）替代。
进一步地，还支持学生成绩的录入和导入，通过对学生上课情况的历史数据与学生的学习成果的进行分析，分析数据，横向对比不同学生、不同班级、不同课程、不同老师的注意力水平，纵向对比学生或班级一段时间内的注意力波动，给出提高学生学习效率的方法与建议。教师可以根据课堂实际情况在检测终端上根据班级人数，学生虚伪情况个性化设置座位布局并连接和显示相应设备终端的连接情况，
进一步地，还可以在教室安装摄像机，对学生上课情况的多角度录像与注意力水平数据同步记录，可以通过人脸识别等技术，提供辅助的反馈，授课内容的视频录像和录音与注意力水平数据同步记录，帮助教师课后能有针对性地分析授课内容。
本实施例提出的课堂评测方法，通过分类存储所述脑电波数据、所述特征数据及注意力状态分析时的分析结果，然后将所述脑电波数据、特征数据及注意力状态分析时的分析结果进行压缩加密，并生成注意力分析报告；实现了生成注意力分析报告，方便用户了解课堂评测结果。
此外，本申请实施例还提出一种计算机可读存储介质。本申请计算机可读存储介质上存储有课堂评测程序，所述课堂评测程序被处理器执行时实现如下步骤：
获取学生的脑电波数据；
利用预设算法获取所述脑电波数据中各波段的能量信息；
提取所述能量信息的特征数据；
基于所述特征数据计算目标注意力数值，分析学生的注意力状态。
进一步地，该课堂评测程序被所述处理器执行时，还实现如下步骤：
对所述脑电波数据中进行数据清理及降噪，以得到目标脑电波数据；
基于所述目标脑电波数据利用傅里叶变换算法获取频域数据；
基于所述频域数据获取所述能量信息。
进一步地，该课堂评测程序被所述处理器执行时，还实现如下步骤：
基于所述特征数据将能量的最大值及最小值进行标准化，以得到标准化能量值；
计算Beta段能量与Alpha段能量的能量值的比值、Beta段的平均波峰距离及Beta段能量的最值滤波；
计算所述比值、所述平均波峰距离及所述最值滤波的加权总和，将所述加权平方和作为初始注意力数值；
基于所述初始注意力数值计算所述目标注意力数值。
进一步地，该课堂评测程序被所述处理器执行时，还实现如下步骤：
利用机器学习训练模型计算预测注意力数值；
计算所述注意力数值为初始注意力数值与所述预测注意力数值之和，将所述注意力数值为初始注意力数值与所述预测注意力数值之和作为目标注意力数值。
进一步地，该课堂评测程序被所述处理器执行时，还实现如下步骤：
获取注意力状态评测标准；
将所述目标注意力数值与所述注意力状态评测标准进行比较，确定所述注意力数值对应的水平等级。
进一步地，该课堂评测程序被所述处理器执行时，还实现如下步骤：
检测佩戴设备的佩戴状态；
当检测所述佩戴状态为未佩戴时，提示用户调整佩戴设备。
进一步地，该课堂评测程序被所述处理器执行时，还实现如下步骤：
检测佩戴设备中脑电波信号是否异常；
当检测到所述佩戴设备中脑电波信号异常时，计算已佩戴状态及未佩戴状态的概率；
基于所述概率确定所述佩戴设备的当前状态。
进一步地，该课堂评测程序被所述处理器执行时，还实现如下步骤：
分类存储所述脑电波数据、所述特征数据及注意力状态分析时的分析结果；
将所述脑电波数据、特征数据及注意力状态分析时的分析结果进行压缩加密，并生成注意力分析报告。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者系统不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者系统所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在如上所述的一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种课堂评测方法，其中，所述课堂评测方法包括以下步骤：
    获取学生的脑电波数据；
    利用预设算法获取所述脑电波数据中各波段的能量信息；
    提取所述能量信息的特征数据；
    基于所述特征数据计算目标注意力数值，分析学生的注意力状态。
  2. 如权利要求1所述的课堂评测方法，其中，所述利用预设算法获取所述脑电波数据中各波段的能量信息的步骤包括：
    对所述脑电波数据进行数据清理及降噪，以得到目标脑电波数据；
    基于所述目标脑电波数据利用傅里叶变换算法获取频域数据；
    基于所述频域数据获取所述能量信息。
  3. 如权利要求2所述的课堂评测方法，其中，所述基于所述特征数据计算目标注意力数值的步骤包括：
    基于所述特征数据将能量的最大值及最小值进行标准化，以得到标准化能量值；
    计算Beta段能量与Alpha段能量的能量值的比值、Beta段的平均波峰距离及Beta段能量的最值滤波；
    计算所述比值、所述平均波峰距离及所述最值滤波的加权总和，将所述加权平方和作为初始注意力数值；
    基于所述初始注意力数值计算所述目标注意力数值。
  4. 如权利要求3所述的课堂评测方法，其中，所述基于所述初始注意力数值计算所述目标注意力数值的步骤还包括：
    利用机器学习训练模型计算预测注意力数值；
    计算所述注意力数值为初始注意力数值与所述预测注意力数值之和，将所述注意力数值为初始注意力数值与所述预测注意力数值之和作为目标注意力数值。
  5. 如权利要求4所述的课堂评测方法，其中，所述分析学生的注意力状态的步骤包括：
    获取注意力状态评测标准；
    将所述目标注意力数值与所述注意力状态评测标准进行比较，确定所述注意力数值对应的水平等级。
  6. 如权利要求1所述的课堂评测方法，其中，所述获取脑电波数据之后，所述课堂评测方法还包括：
    检测佩戴设备的佩戴状态；
    当检测所述佩戴状态为未佩戴时，提示用户调整佩戴设备。
  7. 如权利要求6所述的课堂评测方法，其中，所述检测用户佩戴状态的步骤包括：
    检测佩戴设备中脑电波信号是否异常；
    当检测到所述佩戴设备中脑电波信号异常时，计算已佩戴状态及未佩戴状态的概率；
    基于所述概率确定所述佩戴设备的当前状态。
  8. 如权利要求1所述的课堂评测方法，其中，所述基于所述特征数据计算目标注意力数值，分析学生的注意力状态之后，所述课堂评测方法还包括：
    分类存储所述脑电波数据、所述特征数据及注意力状态分析时的分析结果；
    将所述脑电波数据、特征数据及注意力状态分析时的分析结果进行压缩加密，并生成注意力分析报告。
  9. 一种课堂评测装置，其中，所述课堂评测装置包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的课堂评测程序，所述课堂评测程序被所述处理器执行时实现以下步骤：
    获取学生的脑电波数据；
    利用预设算法获取所述脑电波数据中各波段的能量信息；
    提取所述能量信息的特征数据；
    基于所述特征数据计算目标注意力数值，分析学生的注意力状态。
  10. 如权利要求9所述的课堂评测装置，其中，所述课堂评测程序被所述处理器执行时实现以下步骤：
    对所述脑电波数据进行数据清理及降噪，以得到目标脑电波数据；
    基于所述目标脑电波数据利用傅里叶变换算法获取频域数据；
    基于所述频域数据获取所述能量信息。
  11. 如权利要求10所述的课堂评测装置，其中，所述课堂评测程序被所述处理器执行时实现以下步骤：
    基于所述特征数据将能量的最大值及最小值进行标准化，以得到标准化能量值；
    计算Beta段能量与Alpha段能量的能量值的比值、Beta段的平均波峰距离及Beta段能量的最值滤波；
    计算所述比值、所述平均波峰距离及所述最值滤波的加权总和，将所述加权平方和作为初始注意力数值；
    基于所述初始注意力数值计算所述目标注意力数值。
  12. 如权利要求11所述的课堂评测装置，其中，所述课堂评测程序被所述处理器执行时实现以下步骤：
    利用机器学习训练模型计算预测注意力数值；
    计算所述注意力数值为初始注意力数值与所述预测注意力数值之和，将所述注意力数值为初始注意力数值与所述预测注意力数值之和作为目标注意力数值。
  13. 如权利要求12所述的课堂评测装置，其中，所述课堂评测程序被所述处理器执行时实现以下步骤：
    获取注意力状态评测标准；
    将所述目标注意力数值与所述注意力状态评测标准进行比较，确定所述注意力数值对应的水平等级。
  14. 如权利要求9所述的课堂评测装置，其中，所述课堂评测程序被所述处理器执行时实现以下步骤：
    检测佩戴设备的佩戴状态；
    当检测所述佩戴状态为未佩戴时，提示用户调整佩戴设备。
  15. 如权利要求14所述的课堂评测装置，其中，所述课堂评测程序被所述处理器执行时实现以下步骤：
    检测佩戴设备中脑电波信号是否异常；
    当检测到所述佩戴设备中脑电波信号异常时，计算已佩戴状态及未佩戴状态的概率；
    基于所述概率确定所述佩戴设备的当前状态。
  16. 如权利要求9所述的课堂评测装置，其中，所述课堂评测程序被所述处理器执行时实现以下步骤：
    分类存储所述脑电波数据、所述特征数据及注意力状态分析时的分析结果；
    将所述脑电波数据、特征数据及注意力状态分析时的分析结果进行压缩加密，并生成注意力分析报告。
  17. 一种计算机可读存储介质，其中，所述计算机可读存储介质上存储有课堂评测程序，所述课堂评测程序被处理器执行时实现以下步骤：
    获取学生的脑电波数据；
    利用预设算法获取所述脑电波数据中各波段的能量信息；
    提取所述能量信息的特征数据；
    基于所述特征数据计算目标注意力数值，分析学生的注意力状态。
  18. 如权利要求17所述的计算机可读存储介质，其中，所述课堂评测程序被处理器执行时实现以下步骤：
    对所述脑电波数据进行数据清理及降噪，以得到目标脑电波数据；
    基于所述目标脑电波数据利用傅里叶变换算法获取频域数据；
    基于所述频域数据获取所述能量信息。
  19. 如权利要求18所述的计算机可读存储介质，其中，所述课堂评测程序被处理器执行时实现以下步骤：
    基于所述特征数据将能量的最大值及最小值进行标准化，以得到标准化能量值；
    计算Beta段能量与Alpha段能量的能量值的比值、Beta段的平均波峰距离及Beta段能量的最值滤波；
    计算所述比值、所述平均波峰距离及所述最值滤波的加权总和，将所述加权平方和作为初始注意力数值；
    基于所述初始注意力数值计算所述目标注意力数值。
  20. 如权利要求19所述的计算机可读存储介质，其中，所述课堂评测程序被处理器执行时实现以下步骤：
    利用机器学习训练模型计算预测注意力数值；
    计算所述注意力数值为初始注意力数值与所述预测注意力数值之和，将所述注意力数值为初始注意力数值与所述预测注意力数值之和作为目标注意力数值。
PCT/CN2019/082743 2018-04-17 2019-04-15 课堂评测方法、装置及计算机可读存储介质 WO2019201215A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810345765.7 2018-04-17
CN201810345765.7A CN108537704A (zh) 2018-04-17 2018-04-17 课堂评测方法、装置及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2019201215A1 true WO2019201215A1 (zh) 2019-10-24

Family

ID=63481316

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/082743 WO2019201215A1 (zh) 2018-04-17 2019-04-15 课堂评测方法、装置及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN108537704A (zh)
WO (1) WO2019201215A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111507555A (zh) * 2019-11-05 2020-08-07 浙江大华技术股份有限公司 人体状态检测方法、课堂教学质量的评价方法及相关装置
CN112086196A (zh) * 2020-09-16 2020-12-15 中国科学院自动化研究所 多选择性注意力评估与训练的方法及系统
CN113689147A (zh) * 2021-09-15 2021-11-23 武汉乐知科技有限公司 一种教学质量评估的机器学习算法
CN116138780A (zh) * 2022-12-30 2023-05-23 北京视友科技有限责任公司 一种学生注意力评价方法、终端及计算机可读存储介质

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108537704A (zh) * 2018-04-17 2018-09-14 深圳市心流科技有限公司 课堂评测方法、装置及计算机可读存储介质
CN108932511B (zh) * 2018-10-09 2022-09-13 南京邮电大学 一种基于脑机交互的购物决策方法
CN109635725B (zh) * 2018-12-11 2023-09-12 深圳先进技术研究院 检测学生专注度的方法、计算机存储介质及计算机设备
CN110084508A (zh) * 2019-04-25 2019-08-02 清华大学 一种课堂教学效果评测方法及装置
CN110991249A (zh) * 2019-11-04 2020-04-10 支付宝(杭州)信息技术有限公司 人脸检测方法、装置、电子设备及介质
CN110956407A (zh) * 2019-12-09 2020-04-03 探客柏瑞科技（北京）有限公司 应用于神经教育学领域的教学调整方法及装置
CN110916631B (zh) * 2019-12-13 2022-04-22 东南大学 基于可穿戴生理信号监测的学生课堂学习状态评测系统
CN111223566A (zh) * 2019-12-30 2020-06-02 浙江强脑科技有限公司 注意力测评和训练方法、装置、设备及可读存储介质
CN111402643A (zh) * 2020-04-07 2020-07-10 符智博 基于脑电教育系统的教学方法、教育系统、设备及介质
CN111781656B (zh) * 2020-07-30 2023-09-15 广州市南方人力资源评价中心有限公司 头戴式显示设备的佩戴状态检测方法、装置、设备和介质
CN113208632A (zh) * 2021-04-07 2021-08-06 北京脑陆科技有限公司 一种基于卷积神经网络的注意力检测方法、系统
CN113641241A (zh) * 2021-08-10 2021-11-12 西安领跑网络传媒科技股份有限公司 一种基于专注度的课堂辅助教学系统、设备及方法
CN113925509B (zh) * 2021-09-09 2024-01-23 杭州回车电子科技有限公司 基于脑电信号的注意力值计算方法、装置和电子装置
CN113974657B (zh) * 2021-12-27 2022-09-27 深圳市心流科技有限公司 基于脑电信号的训练方法、装置、设备及存储介质
CN114224364B (zh) * 2022-02-21 2022-05-17 深圳市心流科技有限公司 用于专注力训练的脑电波信号处理方法、装置及存储介质
CN116671938A (zh) * 2023-07-27 2023-09-01 之江实验室 一种任务执行方法、装置、存储介质及电子设备
CN116687411B (zh) * 2023-08-09 2023-11-17 深圳市心流科技有限公司 一种游戏综合分数获取方法、装置、智能终端和存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103815902A (zh) * 2013-11-22 2014-05-28 刘志勇 基于脑电频域特征指标化算法的课堂教学评估系统及方法
CN106175799A (zh) * 2015-04-30 2016-12-07 深圳市前海览岳科技有限公司 基于脑电波评估人体情绪和疲劳状态的方法及系统
CN107024987A (zh) * 2017-03-20 2017-08-08 南京邮电大学 一种基于eeg的实时人脑注意力测试和训练系统
WO2018004028A1 (ko) * 2016-06-28 2018-01-04 주식회사 소소 뇌파 기반 주의력 결핍 과잉 행동 장애 진단 시스템
CN107657868A (zh) * 2017-10-19 2018-02-02 重庆邮电大学 一种基于脑电波的教学跟踪辅助系统
CN108537704A (zh) * 2018-04-17 2018-09-14 深圳市心流科技有限公司 课堂评测方法、装置及计算机可读存储介质

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4285012B2 (ja) * 2003-01-31 2009-06-24 株式会社日立製作所 学習状況判断プログラム及びユーザ状況判断システム
US10198958B2 (en) * 2007-05-04 2019-02-05 Freer Logic Method and apparatus for training a team by employing brainwave monitoring and synchronized attention levels of team trainees
CN105139695A (zh) * 2015-09-28 2015-12-09 南通大学 一种基于脑电波采集的课堂教学监测方法及系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103815902A (zh) * 2013-11-22 2014-05-28 刘志勇 基于脑电频域特征指标化算法的课堂教学评估系统及方法
CN106175799A (zh) * 2015-04-30 2016-12-07 深圳市前海览岳科技有限公司 基于脑电波评估人体情绪和疲劳状态的方法及系统
WO2018004028A1 (ko) * 2016-06-28 2018-01-04 주식회사 소소 뇌파 기반 주의력 결핍 과잉 행동 장애 진단 시스템
CN107024987A (zh) * 2017-03-20 2017-08-08 南京邮电大学 一种基于eeg的实时人脑注意力测试和训练系统
CN107657868A (zh) * 2017-10-19 2018-02-02 重庆邮电大学 一种基于脑电波的教学跟踪辅助系统
CN108537704A (zh) * 2018-04-17 2018-09-14 深圳市心流科技有限公司 课堂评测方法、装置及计算机可读存储介质

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111507555A (zh) * 2019-11-05 2020-08-07 浙江大华技术股份有限公司 人体状态检测方法、课堂教学质量的评价方法及相关装置
CN111507555B (zh) * 2019-11-05 2023-11-14 浙江大华技术股份有限公司 人体状态检测方法、课堂教学质量的评价方法及相关装置
CN112086196A (zh) * 2020-09-16 2020-12-15 中国科学院自动化研究所 多选择性注意力评估与训练的方法及系统
CN112086196B (zh) * 2020-09-16 2023-11-28 中国科学院自动化研究所 多选择性注意力评估与训练的方法及系统
CN113689147A (zh) * 2021-09-15 2021-11-23 武汉乐知科技有限公司 一种教学质量评估的机器学习算法
CN116138780A (zh) * 2022-12-30 2023-05-23 北京视友科技有限责任公司 一种学生注意力评价方法、终端及计算机可读存储介质
CN116138780B (zh) * 2022-12-30 2023-08-08 北京视友科技有限责任公司 一种学生注意力评价方法、终端及计算机可读存储介质

Also Published As

Publication number Publication date
CN108537704A (zh) 2018-09-14

Similar Documents

Publication Publication Date Title
WO2019201215A1 (zh) 课堂评测方法、装置及计算机可读存储介质
WO2019214445A1 (zh) 提高注意力的教学方法、装置及计算机可读存储介质
WO2019103187A1 (ko) 뇌파를 통한 뇌 인지기능 평가 플랫폼 및 방법
WO2016105135A1 (en) Wearable apparatus, management server, management system having the same, and method for controlling thereof
WO2018205424A1 (zh) 基于肌电的生物识别方法、终端及计算机可读存储介质
WO2016024752A1 (en) Wearable device and method of operating the same
WO2018194243A1 (en) Video communication device, video communication method, and video communication mediating method
WO2019013517A1 (en) APPARATUS AND METHOD FOR VOICE CONTROL CONTEXT
WO2016129917A1 (ko) 사용자 단말 및 이의 제공 방법
WO2016200204A1 (en) Electronic device and control method thereof
WO2020122485A2 (ko) 의료 보조서비스를 제공하는 로봇 시스템 및 그 방법
WO2018135693A1 (ko) 스트레스 측정을 위한 이어 헤드셋 장치 및 이를 이용한 스트레스 측정 방법
WO2019182269A1 (ko) 전자 장치, 전자 장치의 이미지 처리 방법 및 컴퓨터 판독 가능 매체
WO2017099314A1 (ko) 사용자 정보를 제공하는 전자 장치 및 방법
WO2019124963A1 (ko) 음성 인식 장치 및 방법
WO2020253115A1 (zh) 基于语音识别的产品推荐方法、装置、设备和存储介质
WO2018124584A1 (ko) 개인 안전 장치 및 그 동작방법
WO2020098013A1 (zh) 电视节目推荐方法、终端、系统及存储介质
WO2020233055A1 (zh) 基于活体检测的产品推广方法、装置、设备及存储介质
WO2021261944A1 (ko) Adhd 아동을 위한 일상 과업 수행 지원 장치 및 그 방법
WO2019045385A1 (ko) 영상 얼라인먼트 방법 및 그 장치
WO2020184746A1 (ko) 주행 정보에 기반한 오토 스탑 시스템을 제어하는 인공 지능 장치 및 그 방법
WO2019223547A1 (zh) 教学分析方法、服务器及计算机可读存储介质
WO2016074284A1 (zh) 基于o2o健康管理的健康报告智能提示系统和方法
WO2021033827A1 (ko) 딥러닝 모듈을 이용한 발달장애 개선 시스템 및 방법

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19788375

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 16/02/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19788375

Country of ref document: EP

Kind code of ref document: A1