CN117608411A - Signal transmission processing method and system based on brain-computer interface - Google Patents
Signal transmission processing method and system based on brain-computer interface Download PDFInfo
- Publication number
- CN117608411A CN117608411A CN202410089103.3A CN202410089103A CN117608411A CN 117608411 A CN117608411 A CN 117608411A CN 202410089103 A CN202410089103 A CN 202410089103A CN 117608411 A CN117608411 A CN 117608411A
- Authority
- CN
- China
- Prior art keywords
- interestingness
- learning
- electroencephalogram
- correction
- contents
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
- 230000008054 signal transmission Effects 0.000 title claims abstract description 40
- 238000003672 processing method Methods 0.000 title claims abstract description 13
- 230000013016 learning Effects 0.000 claims abstract description 186
- 108010076504 Protein Sorting Signals Proteins 0.000 claims abstract description 107
- 238000012937 correction Methods 0.000 claims abstract description 95
- 238000004458 analytical method Methods 0.000 claims abstract description 85
- 238000000034 method Methods 0.000 claims abstract description 57
- 238000012545 processing Methods 0.000 claims abstract description 56
- 239000011159 matrix material Substances 0.000 claims abstract description 52
- 238000004364 calculation method Methods 0.000 claims description 43
- 230000008569 process Effects 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 22
- 210000004556 brain Anatomy 0.000 claims description 16
- 238000012544 monitoring process Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 abstract description 16
- 238000005457 optimization Methods 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004873 anchoring Methods 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/015—Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- 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
- G06F2218/04—Denoising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Neurology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Neurosurgery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Dermatology (AREA)
- Biomedical Technology (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The disclosure provides a signal transmission processing method and system based on brain-computer interface, and relates to the technical field of brain-electrical signal processing, wherein the method comprises the following steps: based on the plurality of sub-electroencephalogram signal sequence sets, performing interest degree analysis and challenge degree analysis on a plurality of appointed contents by a user; correcting the interestingness according to the number of noise point sets in the electroencephalogram signal sequence sets; acquiring relevance coefficients of every two appointed contents, and correcting a plurality of correction interestingness and a plurality of challenged degrees; and acquiring a plurality of learning scores, combining the plurality of correction interestingness and the plurality of correction challenges, constructing a learning characteristic information matrix, and calculating to acquire a plurality of learning state information as a signal processing result. The method can solve the problem of inaccurate learning state evaluation caused by lower accuracy of electroencephalogram signal identification due to incapability of carrying out targeted accurate analysis on the electroencephalogram signal, and can improve the accuracy of electroencephalogram signal identification, thereby improving the accuracy of learning state evaluation.
Description
Technical Field
The present disclosure relates to the technical field of electroencephalogram signal processing, and more particularly, to a signal transmission processing method and system based on a brain-computer interface.
Background
The brain-computer interface technology is a technology for realizing information transmission, interaction and function integration between a brain sleeve system and a computer by establishing an information channel for direct communication between the brain of a learner and external equipment and encoding and decoding brain physiological data.
By combining brain-computer interface technology to perform feature analysis on the brain-computer signal in the user learning process, the real learning state of the user can be known, and the real and accurate learning state evaluation of the user is realized. However, the electroencephalogram signals are interfered by other factors, and meanwhile, the existing electroencephalogram signal processing method cannot conduct targeted denoising processing and data verification on the electroencephalogram signals, so that the recognition accuracy of the electroencephalogram signals of the user is low, and the accuracy of learning state evaluation of the user is affected.
The existing method for evaluating the learning state of the user through the electroencephalogram signal has the following defects: because the electroencephalogram signals cannot be accurately analyzed in a targeted mode, the electroencephalogram signal identification accuracy is low, and the learning state evaluation of the user is inaccurate.
Disclosure of Invention
Therefore, in order to solve the above technical problems, the technical solution adopted in the embodiments of the present disclosure is as follows:
The signal transmission processing method based on the brain-computer interface is applied to a signal transmission processing device based on the brain-computer interface, and the device comprises noninvasive wearable electroencephalogram equipment, a signal transmission acquisition unit and a signal processing unit, and comprises the following steps: acquiring electroencephalogram signals through a signal transmission acquisition unit in the process of learning target contents by a target user wearing electroencephalogram equipment, and obtaining a plurality of electroencephalogram signal sequences, wherein the target contents comprise a plurality of appointed contents and correspond to the plurality of electroencephalogram signal sequences; dividing the plurality of electroencephalogram signal sequences according to a preset time period to obtain a plurality of sub-electroencephalogram signal sequence sets; the signal processing unit is used for carrying out interest analysis and challenge analysis and calculation on the plurality of specified contents by a target user based on the plurality of sub-electroencephalogram signal sequence sets to obtain a plurality of interests and a plurality of challenges; extracting noise points in the plurality of sub-electroencephalogram signal sequence sets to obtain a plurality of noise point sets, and performing correction calculation on the plurality of interestingness according to the number and the size of the plurality of noise point sets to obtain a plurality of correction interestingness; obtaining relevance coefficients of every two specified contents in the specified contents, and performing correction calculation on the corrected interestingness and the challenged interestingness to obtain corrected interestingness and corrected challenged interestingness; acquiring a plurality of learning scores of the target user on the plurality of specified contents, and constructing a learning feature information matrix of the target user on the plurality of specified contents by combining the plurality of correction interestingness and the plurality of correction challenges; and according to the learning characteristic information matrix, analyzing and calculating to obtain a plurality of pieces of learning state information of the target user on the plurality of specified contents as a signal processing result.
The utility model provides a signal transmission processing system based on brain-computer interface, the system includes a signal transmission processing apparatus based on brain-computer interface, the device includes noninvasive wearing formula brain electricity equipment, signal transmission collection unit, signal processing unit, includes: the electroencephalogram signal sequence acquisition module is used for acquiring electroencephalogram signals through the signal transmission acquisition unit in the learning process of target contents of target users wearing electroencephalogram equipment to acquire a plurality of electroencephalogram signal sequences, wherein the target contents comprise a plurality of appointed contents and correspond to the plurality of electroencephalogram signal sequences; the electroencephalogram signal sequence dividing module is used for dividing the plurality of electroencephalogram signal sequences according to a preset time period to obtain a plurality of sub-electroencephalogram signal sequence sets; the analysis and calculation module is used for analyzing and calculating the interestingness and the challenged degrees of the target user on the specified contents based on the electroencephalogram signal sequence sets through the signal processing unit to obtain interestingness and challenged degrees; the noise point extraction module is used for extracting noise points in the plurality of sub-electroencephalogram signal sequence sets to obtain a plurality of noise point sets, and correcting and calculating the plurality of interestingness according to the number of the plurality of noise point sets to obtain a plurality of corrected interestingness; the information correction module is used for obtaining the relevance coefficient of each two appointed contents in the plurality of appointed contents, correcting and calculating the plurality of corrected interestingness and the plurality of challenged interestingness, and obtaining a plurality of corrected interestingness and a plurality of corrected challenged interestingness; the learning characteristic information matrix construction module is used for acquiring a plurality of learning scores of the target user on the plurality of specified contents and constructing a learning characteristic information matrix of the target user on the plurality of specified contents by combining the plurality of correction interestingness and the plurality of correction challenged degrees; and the signal processing result obtaining module is used for obtaining a plurality of pieces of learning state information of the target user on the plurality of specified contents as a signal processing result according to the learning characteristic information matrix through analysis and calculation.
By adopting the technical method, compared with the prior art, the technical progress of the present disclosure has the following points:
the method can solve the technical problems that the existing method for evaluating the learning state of the user through the electroencephalogram cannot conduct targeted accurate analysis on the electroencephalogram, so that the electroencephalogram identification accuracy is low, and the learning state evaluation of the user is inaccurate. Firstly, acquiring electroencephalogram signals through a signal transmission acquisition unit in the learning process of target contents of a target user wearing electroencephalogram equipment, and obtaining a plurality of electroencephalogram signal sequences, wherein the target contents comprise a plurality of appointed contents and correspond to the plurality of electroencephalogram signal sequences; then dividing the plurality of electroencephalogram signal sequences according to a preset time period to obtain a plurality of sub-electroencephalogram signal sequence sets; based on the plurality of sub-electroencephalogram signal sequence sets, performing interest degree analysis and challenge degree analysis and calculation on the plurality of specified contents by a target user through a signal processing unit to obtain a plurality of interest degrees and a plurality of challenges; further extracting noise points in the plurality of sub-electroencephalogram signal sequence sets to obtain a plurality of noise point sets, and carrying out correction calculation on the plurality of interestingness according to the number of the plurality of noise point sets to obtain a plurality of corrected interestingness; acquiring relevance coefficients of every two appointed contents in the appointed contents, and correcting and calculating the corrected interestingness and the challenge challenged according to the relevance coefficients to obtain corrected interestingness and corrected challenge challenged; acquiring a plurality of learning scores of the target user on the plurality of specified contents, and constructing a learning feature information matrix of the target user on the plurality of specified contents by combining the plurality of correction interestingness and the plurality of correction challenges; and finally, according to the learning characteristic information matrix, analyzing and calculating to obtain a plurality of pieces of learning state information of the target user on the plurality of specified contents, and taking the plurality of pieces of learning state information as a signal processing result. By the method, the accuracy of electroencephalogram signal identification and analysis in the user learning process can be improved, so that the accuracy of user learning state evaluation is improved, and a basis is provided for the optimization management of learning content of subsequent users.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings that are used in the description of the embodiments will be briefly described below.
Fig. 1 is a schematic flow chart of a signal transmission processing method based on a brain-computer interface;
fig. 2 is a schematic flow chart of obtaining a plurality of corrected interestingness in a signal transmission processing method based on a brain-computer interface;
fig. 3 is a schematic structural diagram of a signal transmission processing method system based on a brain-computer interface.
Reference numerals illustrate: an electroencephalogram signal sequence obtaining module 01, an electroencephalogram signal sequence dividing module 02, an analysis and calculation module 03, a noise point extracting module 04, an information correcting module 05, a learning characteristic information matrix constructing module 06 and a signal processing result obtaining module 07.
Detailed Description
The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure. All other embodiments, which can be made by one of ordinary skill in the art without inventive effort, based on the embodiments in this disclosure are intended to be within the scope of this disclosure.
Based on the above description, as shown in fig. 1, the present disclosure provides a signal transmission processing method based on a brain-computer interface, where the method is applied to a signal transmission processing device based on the brain-computer interface, where the device includes a wearable electroencephalogram device, a signal transmission acquisition unit, and a signal processing unit, and includes:
when the brain performs different activities, different brain waves are generated, and the brain waves are called brain signals, and the information such as frequency, amplitude, phase and the like of the brain waves can reflect the state and the function of the brain, so that data support is provided for user state analysis.
The method provided by the application is used for optimizing the electroencephalogram signal processing method so as to achieve the aim of improving the accuracy of electroencephalogram signal identification and analysis in the learning process of a user, so that the accuracy of the learning state evaluation of the user is further improved, a basis is provided for the optimization and management of learning contents of subsequent users, the method is concretely implemented in a brain-computer interface-based signal transmission processing device, the device comprises noninvasive wearable electroencephalogram equipment, a signal transmission acquisition unit and a signal processing unit, the noninvasive wearable electroencephalogram equipment is equipment for acquiring electroencephalogram signals, the electroencephalogram waves of the brain can be measured in a noninvasive mode, the electroencephalogram signals are acquired by placing electrodes on the head, invasive surgery or puncture is not needed, and the method has the advantages of noninvasive performance, convenience, practicability and the like, for example: equipment such as an electroencephalogram cap, a near infrared helmet and the like; the signal transmission acquisition unit is used for acquiring the electroencephalogram signals of the user, wherein the wearable electroencephalogram equipment performs data interaction with the signal transmission acquisition unit in a signal transmission mode and transmits the acquired electroencephalogram signals to the signal transmission acquisition unit; the signal processing unit is used for analyzing and identifying the acquired brain electrical signals.
Acquiring electroencephalogram signals through a signal transmission acquisition unit in the process of learning target contents by a target user wearing electroencephalogram equipment, and obtaining a plurality of electroencephalogram signal sequences, wherein the target contents comprise a plurality of appointed contents and correspond to the plurality of electroencephalogram signal sequences;
in this embodiment of the present application, first, in a learning process of a target user wearing an electroencephalogram device to perform target content, electroencephalogram signal acquisition is performed on the target user through a signal transmission acquisition unit, where the target user is any learner participating in learning state evaluation, the acquired electroencephalogram signals are divided according to the target content and arranged according to a sequence of acquisition times, so as to obtain a plurality of electroencephalogram signal sequences, where the target content includes a plurality of specified contents, and the specified contents correspond to the electroencephalogram signal sequences one to one, and a person skilled in the art of specified contents can perform setting according to the target learning content, for example: when a target user learns a high-second physical course, designating the content as a plurality of sections of a first chapter in the high-second physical course.
A plurality of electroencephalogram signal sequences are acquired through electroencephalogram signal acquisition, and data support is provided for learning state analysis in the next step of user learning process.
Dividing the plurality of electroencephalogram signal sequences according to a preset time period to obtain a plurality of sub-electroencephalogram signal sequence sets;
in this embodiment of the present application, a preset time period is obtained, where the preset time period can be set by a person skilled in the art according to actual situations, for example: the preset time period is set to one minute. And then dividing the plurality of electroencephalogram signal sequences according to the preset time period, and obtaining a plurality of sub-electroencephalogram signal sequence sets according to a dividing result.
In one embodiment, the method further comprises:
acquiring time stamp information corresponding to each electroencephalogram signal in the plurality of electroencephalogram signal sequences;
based on the time stamp information, dividing the electroencephalogram signals in a preset time period in the plurality of electroencephalogram signal sequences according to the preset time period, and obtaining a plurality of sets of the electroencephalogram signal sequences as the electroencephalogram signal sequences.
In this embodiment of the present application, first, timestamp information corresponding to each electroencephalogram signal in the plurality of electroencephalogram signal sequences is obtained, where the timestamp information refers to a timestamp when the electroencephalogram signal is acquired, and is usually in units of seconds or milliseconds.
Dividing the plurality of electroencephalogram signal sequences according to the preset time period according to the timestamp information, namely taking the electroencephalogram signal in a preset time period as a sub-electroencephalogram signal sequence to obtain a plurality of sub-electroencephalogram signal sequence sets.
By dividing the individual electroencephalogram signal sequences, a sub electroencephalogram signal sequence set is obtained, and the accuracy and fineness of electroencephalogram signal analysis can be improved, so that the accuracy of electroencephalogram signal analysis and recognition is improved.
The signal processing unit is used for carrying out interest analysis and challenge analysis and calculation on the plurality of specified contents by a target user based on the plurality of sub-electroencephalogram signal sequence sets to obtain a plurality of interests and a plurality of challenges;
in the embodiment of the application, signal analysis is performed on the plurality of sub-electroencephalogram signal sequence sets through a signal processing unit, and analysis and calculation of interest degree and challenge degree of a target user on the plurality of specified contents are performed according to an electroencephalogram signal analysis result, wherein the interest degree is used for representing the authentication degree of the target user during learning, wherein the higher the interest degree of the user is, the more serious the user learning is represented, and the interest degree is percentage data between 0 and 1; the challenge is used for representing the difficulty of the user in learning, wherein the greater the challenge is, the greater the difficulty of the user in learning is represented by percentage data between 0 and 1; and obtaining a plurality of interestingness and a plurality of challenges according to the analysis and calculation result.
In one embodiment, the method further comprises:
acquiring a plurality of sample sub-brain electrical signal sequence sets based on brain electrical monitoring analysis data records in a user learning process, and acquiring a sample interest level set and a sample challenge level set;
respectively constructing an interestingness analysis branch and a challenged degree analysis branch by adopting the plurality of sample sub-electroencephalogram signal sequence sets, the sample interestingness set and the sample challenged degree set, and performing supervision training until convergence to obtain an electroencephalogram signal analyzer;
analyzing the plurality of sub-electroencephalogram signal sequence sets by adopting the electroencephalogram signal analyzer to obtain a plurality of interestingness sets and a plurality of challenge sets;
and calculating to obtain a plurality of interestingness and a plurality of challenges according to the plurality of interestingness sets and the plurality of challenges.
In the embodiment of the present application, the analysis and calculation process of the interestingness and the challenge is as follows, and firstly, an electroencephalogram monitoring and analysis data record in the user learning process is called, where the electroencephalogram monitoring and analysis data record includes a plurality of historical electroencephalogram monitoring and analysis data of the target user. And acquiring a plurality of sample sub-electroencephalogram signal sequence sets based on the electroencephalogram monitoring analysis data record, and a sample interest degree set and a sample challenge degree set corresponding to the plurality of sample sub-electroencephalogram signal sequence sets, wherein the sample interest degree and the sample challenge degree can be acquired through questionnaires of target users and dictating by the target users, and a person skilled in the art can also select an adaptive method to acquire the sample interest degree and the sample challenge degree according to actual conditions.
And constructing an interestingness analysis branch and a challenge analysis branch based on the machine learning and the BP neural network, wherein the interestingness analysis branch and the challenge analysis branch are neural network models which can be subjected to iterative optimization in the machine learning. The input data of the interestingness analysis branch and the challenge analysis branch are sub-electroencephalogram signal sequences, and the output data is interestingness; and the input signals of the challenge analysis branches are sub-brain electrical signal sequences, and the output data are challenges.
Constructing a first training data set by adopting the plurality of sample sub-electroencephalogram signal sequence sets and the sample interest degree set, and performing supervision training on the interest degree analysis branch through the first training data set; and taking the plurality of sample sub-electroencephalogram signal sequence sets and the sample challenge degree set as a second training data set, and performing supervision training on the challenge degree analysis branch through the second training data set.
Firstly, randomly selecting first training data in the first training data set, wherein the first training data comprises a first sample electroencephalogram signal sequence and a first sample interest level; then, performing supervision training on the interestingness analysis branch through the first training data, and outputting a first interestingness; comparing the first sample interestingness with the first interestingness, and selecting second training data to supervise and train the interestingness analysis branch when the first sample interestingness and the first interestingness are consistent; when the two are inconsistent, obtaining the first sample interestingness and the interestingness deviation of the first interestingness, optimizing and adjusting the weight parameters of the interestingness analysis branch according to the interestingness deviation, and then selecting second training data to supervise and train the interestingness analysis branch; and carrying out iterative training on the interestingness analysis branch by using the training data set, and obtaining the interestingness analysis branch after training when the output result of the interestingness analysis branch tends to be in a convergence state.
The training method of the challenge analysis branch is the same as the training method of the interest analysis branch, and development and explanation are not performed here, so that the challenge analysis branch with the training completed is obtained. And then constructing an electroencephalogram analyzer according to the trained interestingness analysis branch and the trained challenge analysis branch to obtain the electroencephalogram analyzer.
By constructing the electroencephalogram signal analyzer based on the machine learning and BP neural network, a specific method and steps are provided for obtaining the interestingness and the challenge based on the electroencephalogram signal analysis, and meanwhile, the accuracy and the efficiency of the interestingness and the challenge analysis and calculation can be improved.
And performing electroencephalogram signal analysis on the plurality of sub-electroencephalogram signal sequence sets through the electroencephalogram signal analyzer to obtain a plurality of interestingness sets and a plurality of challenged sets. Respectively carrying out average value calculation on the plurality of interest degree sets, and taking the interest degree average value as the interest degree of the corresponding interest degree set to obtain a plurality of interest degrees; and carrying out average value calculation on the plurality of challenge degree sets to obtain a plurality of challenge degrees. By obtaining a plurality of interestingness and a plurality of challenges, a basis is provided for learning state analysis of the user.
Extracting noise points in the plurality of sub-electroencephalogram signal sequence sets to obtain a plurality of noise point sets, and performing correction calculation on the plurality of interestingness according to the number and the size of the plurality of noise point sets to obtain a plurality of correction interestingness;
in the embodiment of the application, firstly, extracting noise points in the plurality of sub-electroencephalogram signal sequence sets, wherein the noise points are abnormal electroencephalogram signals generated in a user learning process, and are related to interestingness in the user learning process due to the reasons of distraction, thought anchoring, concentration lack and the like in the user learning process; a plurality of noise point sets is obtained. And then carrying out correction calculation on the plurality of interestingness according to the number of the plurality of noise point sets, wherein the larger the number of the noise point sets is, the smaller the interestingness corresponding to the corrected noise point sets is, and a plurality of corrected interestingness is obtained.
As shown in fig. 2, in one embodiment, the method further comprises:
extracting peak noise points from the plurality of sub-electroencephalogram signal sequence sets to obtain a plurality of peak noise point sets;
extracting valley noise points from the plurality of sub-electroencephalogram signal sequence sets to obtain a plurality of valley noise point sets, combining the plurality of peak noise point sets, and counting to obtain a plurality of noise point sets;
And carrying out correction calculation on the plurality of interestingness according to the reciprocal of the ratio of the number of noise points in each noise point set to the number of historical average noise points, so as to obtain the plurality of corrected interestingness.
In this embodiment of the present application, first, a peak noise threshold, a Gu Zaosheng threshold, and a noise fluctuation threshold are set, where the peak noise threshold, the Gu Zaosheng threshold, and the noise fluctuation threshold can be set by a person skilled in the art according to practical situations, and the peak noise threshold is far greater than the Gu Zaosheng threshold, and the noise fluctuation threshold is a standard fluctuation range of two adjacent electroencephalogram signals.
Sequentially extracting peak noise points from the sub-computer signal sequences in the plurality of sub-brain signal sequence sets according to the peak noise threshold and the noise fluctuation threshold, wherein the peak noise points refer to noise points in the sub-computer signal sequences, wherein noise in the sub-computer signal sequences is larger than the peak noise threshold, and noise difference values of two adjacent brain signals are larger than the noise fluctuation threshold, so that a plurality of peak noise point sets are obtained, and the peak noise point sets and the sub-brain signal sequence sets have a corresponding relation. And extracting valley noise points in the plurality of sub-brain signal sequence sets based on the Gu Zaosheng threshold and the noise fluctuation threshold, wherein the valley noise points are noise points in the sub-computer signal sequence, the noise in which the noise is smaller than the Gu Zaosheng threshold, and the noise difference value of two adjacent brain signals is larger than the noise fluctuation threshold, so as to obtain a plurality of valley noise point sets, and according to the plurality of valley noise point sets and the plurality of peak noise point sets, obtaining a plurality of noise point sets.
Sequentially counting the number of the noise points in the noise point sets to obtain the number of the noise points, wherein the number of the noise points is the sum of the number of peak noise points and the number of valley noise points in the noise point sets. And obtaining the number of the historical average noise points, wherein the number of the historical average noise points can be obtained through calculation of a plurality of sample historical data, and then taking the reciprocal of the ratio of the number of the noise points in each noise point set to the number of the historical average noise points as a correction coefficient to obtain a plurality of correction coefficients, wherein the correction coefficient corresponds to one noise point set.
And carrying out correction calculation on the plurality of interestingness according to the plurality of correction coefficients to obtain a plurality of corrected interestingness, wherein the corrected interestingness is the product of the correction coefficient and the corresponding interestingness.
The noise point collection is obtained by extracting the noise points, and the interestingness is corrected according to the noise point collection, so that the accuracy of obtaining the corrected interestingness can be improved, and the accuracy of the user learning state evaluation is improved.
Obtaining relevance coefficients of every two specified contents in the specified contents, and performing correction calculation on the corrected interestingness and the challenged interestingness to obtain corrected interestingness and corrected challenged interestingness;
In the embodiment of the application, first, relevance analysis is performed on every two specified contents in the plurality of specified contents, wherein every two specified contents are any two specified contents in the plurality of specified contents, and relevance coefficients are obtained according to relevance analysis results, so that a plurality of relevance coefficients are obtained. And then, correcting and calculating the plurality of corrected interestingness and the plurality of challenged degrees according to the plurality of relevance coefficients to obtain a plurality of corrected interestingness and a plurality of corrected challenged degrees.
In one embodiment, the method further comprises:
acquiring relevance coefficients of each two specified contents according to the learning contents in the specified contents to acquire a plurality of relevance coefficients;
acquiring a plurality of groups of designated contents with relevance coefficients larger than relevance coefficient threshold values, acquiring two corrected interestingness and two challenged degrees corresponding to each group of designated contents, carrying out negative correction on the large corrected interestingness and challenged degrees according to the relevance coefficients, and carrying out positive correction on the small corrected interestingness and challenged degrees to acquire a plurality of corrected interestingness and a plurality of corrected challenged degrees.
In this embodiment of the present application, first, association analysis is performed on each two specified contents based on learning contents in the plurality of specified contents, and an association coefficient of each two specified contents is obtained, where the greater the association between two specified contents is, the greater the association coefficient between the two specified contents is, for example: the association coefficient of the electric first section and the electric second section in the physical textbook is larger than that of the electric first section and the mechanical first section; a plurality of relevance coefficients are obtained.
Setting a relevance coefficient threshold, which can be set by a person skilled in the art according to the actual situation, for example: the relevance coefficient threshold is set to 80% relevance. And then judging a plurality of relevance coefficients according to the relevance coefficient threshold value to obtain a plurality of groups of appointed contents with relevance coefficients larger than the relevance coefficient threshold value, and obtaining two corrected interestingness and two challenged interestingness corresponding to each group of appointed contents. And then setting correction force according to the relevance coefficient, wherein the correction force is larger as the relevance coefficient is larger, and the correction force can be set according to actual conditions, for example: when the correlation coefficient is 85%, the correction strength is 2%; when the correlation coefficient is 90%, the correction strength is 4%. And then carrying out negative correction on the large correction interest and challenge according to the correction strength, and carrying out positive correction on the small correction interest and challenge, for example: the large correction interestingness is 85%, the small correction interestingness is 65%, the correction strength is 5%, the corrected large correction interestingness is 80%, and the corrected small correction interestingness is 70%; a plurality of correction interestingness and a plurality of correction challenges are obtained.
By carrying out fusion correction on the corrected interestingness and the corrected challenge corresponding to the two appointed contents with large relevance, the rationality and the accuracy of obtaining the corrected interestingness and the corrected challenge can be improved, and the accuracy of the user learning state evaluation is improved.
Acquiring a plurality of learning scores of the target user on the plurality of specified contents, and constructing a learning feature information matrix of the target user on the plurality of specified contents by combining the plurality of correction interestingness and the plurality of correction challenges;
in the embodiment of the present application, first, a plurality of learning scores of the target user on the plurality of specified contents are obtained, where the learning scores refer to assessment scores of the target user after learning the specified contents, for example: and designating examination scores and job scores corresponding to the contents. And then constructing a learning characteristic information matrix of the target user for the specified contents according to the learning scores, the correction interestingness and the correction challenge.
In one embodiment, the method further comprises:
acquiring a plurality of learning scores of the target user on the plurality of specified contents;
normalizing the learning scores to obtain a plurality of learning degrees;
Carrying out forward processing on the plurality of correction challenged degrees to obtain a plurality of forward challenged degrees;
based on the learning degrees, the correction interestingness degrees and the forward challenges, a learning characteristic information matrix of the target user for the specified contents is constructed, wherein the learning characteristic information matrix comprises the following formula:
；
wherein A is a learning characteristic information matrix, M is the number of a plurality of specified contents,andthe learning level of the 1 st specified content and the Mth specified content for the target user,andthe corrected interestingness of the target user for the 1 st specified content and the mth specified content,andthe forward challenges for the target user to the 1 st specified content and the Mth specified content.
In this embodiment of the present application, first, a plurality of learning scores of the target user for the plurality of specified contents are obtained, and then normalization processing is performed on the plurality of learning scores, where normalization processing refers to converting the plurality of learning scores into a range of intervals between 0 and 1, so as to obtain a plurality of learning degrees. Forward processing is carried out on the correction challenges according to the learning degrees, wherein the forward processing refers to optimization adjustment of the correction challenges according to the learning degrees, and the higher the learning degree is, the lower the difficulty of representing the appointed content is, and the correction challenges are properly reduced; the smaller the learning degree is, the higher the difficulty of representing the appointed content is, and the correction challenge degree is properly increased; resulting in multiple forward challenges. The accuracy of the forward challenge can be further improved by forward processing the correction challenge according to the learning level.
According to the learning degrees, the correction interestingness degrees and the forward challenges, a learning characteristic information matrix of the target user for the specified contents is constructed, wherein the learning characteristic information matrix is as follows:the method comprises the steps of carrying out a first treatment on the surface of the In the learning characteristic information matrix, A is a learning characteristic information matrix, M is the number of a plurality of specified contents,andthe learning level of the 1 st specified content and the Mth specified content for the target user,andthe corrected interestingness of the target user for the 1 st specified content and the mth specified content,andthe forward challenges for the target user to the 1 st specified content and the Mth specified content.
By constructing the learning characteristic information matrix, support is provided for the next learning state analysis of the target user.
And according to the learning characteristic information matrix, analyzing and calculating to obtain a plurality of pieces of learning state information of the target user on the plurality of specified contents as a signal processing result.
According to the learning characteristic information matrix, the learning states of the target user on the specified contents are analyzed and calculated in sequence to obtain a plurality of pieces of learning state information, wherein the learning state information is used for representing the learning quality of the user on a certain specified content and can serve as a basis of subsequent learning planning of the target user, and the plurality of pieces of learning state information serve as signal processing results.
In one embodiment, the method further comprises:
according to the learning characteristic information matrix, a plurality of pieces of learning state information of the target user on the plurality of specified contents are obtained through analysis and calculation, and the following formula is obtained:
；
；
；
wherein,the ith learning state information for the target user for the ith designated content,、、、、、to learn the maximum and minimum of M learnings, M corrected interests and M forward challenges within the feature information matrix,、、for learning the ith learning level, correction interest level and forward challenge level of the ith designated content in the characteristic information matrix,、andis a learning level weight, an interest level weight and a challenge level weight.
In this embodiment of the present application, according to the learning feature information matrix, a plurality of pieces of learning state information of the target user on the plurality of specified contents are sequentially calculated, where a calculation formula of the learning state information is as follows:
；
；
；
wherein,ith learning state information for an ith specified content for a target user, wherein the ith specified content is any one of the plurality of specified contents,、、、、、to learn the maximum and minimum of M learnings, M corrected interests and M forward challenges within the feature information matrix, 、、For learning the ith learning level, correction interest level and forward challenge level of the ith designated content in the characteristic information matrix,、andis a learning level weight, an interest level weight and a challenge level weight, wherein、Andthe influence degree of the learning state information can be set by the skilled person according to the learning degree, the interest degree and the challenge degree, wherein the larger the influence degree of which index is, the larger the corresponding weight is, the more the learning state information isThe weight setting is performed by a coefficient of variation method, which is a weighting method commonly used by those skilled in the art, and will not be described herein.
The method can solve the technical problems of inaccurate learning state evaluation of the user caused by lower accuracy of the identification of the electroencephalogram due to incapability of carrying out targeted accurate analysis on the electroencephalogram in the traditional method for carrying out learning state evaluation of the user through the electroencephalogram, and can improve the accuracy of the identification and analysis of the electroencephalogram in the learning process of the user, thereby improving the accuracy of learning state evaluation of the user and providing basis for optimizing and managing learning contents of subsequent users.
In one embodiment, as shown in fig. 3, there is provided a brain-computer interface-based signal transmission processing system, the system including a brain-computer interface-based signal transmission processing device, the device including a noninvasive wearable electroencephalogram apparatus, a signal transmission acquisition unit, a signal processing unit, including: an electroencephalogram signal sequence obtaining module 01, an electroencephalogram signal sequence dividing module 02, an analysis and calculation module 03, a noise point extracting module 04, an information correcting module 05, a learning characteristic information matrix constructing module 06 and a signal processing result obtaining module 07, wherein:
The electroencephalogram signal sequence obtaining module 01 is used for obtaining a plurality of electroencephalogram signal sequences by a signal transmission and collection unit in the process of learning target contents by a target user wearing electroencephalogram equipment, wherein the target contents comprise a plurality of appointed contents and correspond to the plurality of electroencephalogram signal sequences;
the electroencephalogram signal sequence dividing module 02 is used for dividing the plurality of electroencephalogram signal sequences according to a preset time period to obtain a plurality of sub-electroencephalogram signal sequence sets;
the analysis and calculation module 03 is configured to perform, by using a signal processing unit, interest analysis and challenge analysis and calculation of the target user on the multiple specified contents based on the multiple sets of sub-electroencephalogram signal sequences, so as to obtain multiple interests and multiple challenges;
the noise point extraction module 04 is used for extracting noise points in the plurality of sub-electroencephalogram signal sequence sets to obtain a plurality of noise point sets, and correcting and calculating the plurality of interestingness according to the number of the plurality of noise point sets to obtain a plurality of corrected interestingness;
The information correction module 05 is configured to obtain relevance coefficients of each two specified contents in the plurality of specified contents, and perform correction calculation on the plurality of corrected interestingness and the plurality of challenged interestingness to obtain a plurality of corrected interestingness and a plurality of corrected challenged interestingness;
the learning feature information matrix construction module 06, where the learning feature information matrix construction module 06 is configured to obtain a plurality of learning scores of the target user on the plurality of specified contents, and combine the plurality of correction interestingness and the plurality of correction challenged degrees to construct a learning feature information matrix of the target user on the plurality of specified contents;
and the signal processing result obtaining module 07 is used for obtaining a plurality of pieces of learning state information of the target user on the plurality of specified contents as a signal processing result according to the learning characteristic information matrix through analysis and calculation.
In one embodiment, the system further comprises:
the time stamp information acquisition module is used for acquiring time stamp information corresponding to each electroencephalogram signal in the plurality of electroencephalogram signal sequences;
the electroencephalogram sequence setting module is used for dividing the electroencephalogram signals in the electroencephalogram sequences within a preset time period according to the preset time period based on the time stamp information and used as the electroencephalogram sequence to obtain a plurality of electroencephalogram sequence sets.
In one embodiment, the system further comprises:
the sample information acquisition module is used for acquiring a plurality of sample sub-electroencephalogram signal sequence sets based on electroencephalogram monitoring analysis data records in a user learning process and acquiring a sample interest level set and a sample challenge level set;
the electroencephalogram signal analyzer obtaining module is used for respectively constructing an interestingness analysis branch and a challenged degree analysis branch by adopting the plurality of sample sub-electroencephalogram signal sequence sets, the sample interestingness set and the sample challenged degree set, and performing supervision training until convergence to obtain an electroencephalogram signal analyzer;
the electroencephalogram sequence set analysis module is used for analyzing the plurality of electroencephalogram sequence sets by adopting the electroencephalogram analyzer to obtain a plurality of interestingness sets and a plurality of challenged sets;
the information calculation module is used for calculating and obtaining a plurality of interestingness and a plurality of challenged degrees according to the plurality of interestingness sets and the plurality of challenged degrees.
In one embodiment, the system further comprises:
the peak noise point extraction module is used for extracting peak noise points in the plurality of sub-electroencephalogram signal sequence sets to obtain a plurality of peak noise point sets;
The valley noise point extraction module is used for extracting valley noise points in the plurality of sub-electroencephalogram signal sequence sets to obtain a plurality of valley noise point sets, and counting to obtain a plurality of noise point sets by combining the plurality of peak noise point sets;
the interest degree correction module is used for carrying out correction calculation on the plurality of interest degrees according to the reciprocal of the ratio of the number of noise points in each noise point set to the number of historical average noise points to obtain the plurality of corrected interest degrees.
In one embodiment, the system further comprises:
the relevance coefficient acquisition module is used for acquiring relevance coefficients of every two specified contents according to the learning contents in the specified contents to acquire a plurality of relevance coefficients;
the correction information obtaining module is used for obtaining multiple groups of specified contents with the relevance coefficient larger than the relevance coefficient threshold, obtaining two correction interestingness and two challenges corresponding to each group of specified contents, carrying out negative correction on the large correction interestingness and challenges according to the relevance coefficient, and carrying out positive correction on the small correction interestingness and challenges to obtain multiple correction interestingness and multiple correction challenges.
In one embodiment, the system further comprises:
a learning score acquisition module for acquiring a plurality of learning scores of the target user for the plurality of specified contents;
the normalization processing module is used for carrying out normalization processing on the learning scores to obtain a plurality of learning degrees;
the forward processing module is used for carrying out forward processing on the plurality of correction challenged degrees to obtain a plurality of forward challenged degrees;
the learning characteristic information matrix construction module is used for constructing a learning characteristic information matrix of the target user on the plurality of specified contents based on the plurality of learning degrees, the plurality of correction interestingness degrees and the plurality of forward challenges, and the formula is as follows:
；
a matrix parameter module, wherein A is a learning characteristic information matrix, M is the number of a plurality of appointed contents,andthe learning level of the 1 st specified content and the Mth specified content for the target user,andthe corrected interestingness of the target user for the 1 st specified content and the mth specified content,andthe forward challenges for the target user to the 1 st specified content and the Mth specified content.
In one embodiment, the system further comprises:
the learning state information calculation module is used for analyzing and calculating to obtain a plurality of pieces of learning state information of the target user on the plurality of specified contents according to the learning characteristic information matrix, and the learning state information calculation module is represented by the following formula:
；
；
；
a parameter module, wherein the parameter module refers to a parameter module,the ith learning state information for the target user for the ith designated content,、、、、、to learn the maximum and minimum of M learnings, M corrected interests and M forward challenges within the feature information matrix,、、for learning the ith learning level, correction interest level and forward challenge level of the ith designated content in the characteristic information matrix,、andis a learning level weight, an interest level weight and a challenge level weight.
In summary, compared with the prior art, the embodiments of the present disclosure have the following technical effects:
(1) The accuracy of electroencephalogram signal identification and analysis in the user learning process can be improved, so that the accuracy of user learning state evaluation is improved, and basis is provided for the optimization management of learning content of subsequent users.
(2) By constructing the electroencephalogram signal analyzer based on the machine learning and BP neural network, a specific method and steps are provided for obtaining the interestingness and the challenge based on the electroencephalogram signal analysis, and meanwhile, the accuracy and the efficiency of the interestingness and the challenge analysis and calculation can be improved.
(3) The noise point collection is obtained by extracting the noise points, and the interestingness is corrected according to the noise point collection, so that the accuracy of obtaining the corrected interestingness can be improved; by carrying out fusion correction on the corrected interestingness and the corrected challenge corresponding to the two appointed contents with large relevance, the rationality and the accuracy of obtaining the corrected interestingness and the corrected challenge can be improved, and the accuracy of the user learning state evaluation is improved.
The above examples merely represent a few embodiments of the present disclosure and are not to be construed as limiting the scope of the invention. Accordingly, various alterations, modifications and variations may be made by those having ordinary skill in the art without departing from the scope of the disclosed concept as defined by the following claims and all such alterations, modifications and variations are intended to be included within the scope of the present disclosure.
Claims (8)
1. The signal transmission processing method based on the brain-computer interface is characterized in that the method is applied to a signal transmission processing device based on the brain-computer interface, the device comprises noninvasive wearable electroencephalogram equipment, a signal transmission acquisition unit and a signal processing unit, and the method comprises the following steps:
acquiring electroencephalogram signals through a signal transmission acquisition unit in the process of learning target contents by a target user wearing electroencephalogram equipment, and obtaining a plurality of electroencephalogram signal sequences, wherein the target contents comprise a plurality of appointed contents and correspond to the plurality of electroencephalogram signal sequences;
Dividing the plurality of electroencephalogram signal sequences according to a preset time period to obtain a plurality of sub-electroencephalogram signal sequence sets;
the signal processing unit is used for carrying out interest analysis and challenge analysis and calculation on the plurality of specified contents by a target user based on the plurality of sub-electroencephalogram signal sequence sets to obtain a plurality of interests and a plurality of challenges;
extracting noise points in the plurality of sub-electroencephalogram signal sequence sets to obtain a plurality of noise point sets, and performing correction calculation on the plurality of interestingness according to the number and the size of the plurality of noise point sets to obtain a plurality of correction interestingness;
obtaining relevance coefficients of every two specified contents in the specified contents, and performing correction calculation on the corrected interestingness and the challenged interestingness to obtain corrected interestingness and corrected challenged interestingness;
acquiring a plurality of learning scores of the target user on the plurality of specified contents, and constructing a learning feature information matrix of the target user on the plurality of specified contents by combining the plurality of correction interestingness and the plurality of correction challenges;
and according to the learning characteristic information matrix, analyzing and calculating to obtain a plurality of pieces of learning state information of the target user on the plurality of specified contents as a signal processing result.
2. The method of claim 1, wherein dividing the plurality of electroencephalogram sequences according to a preset time period to obtain a plurality of sets of sub-electroencephalogram sequences comprises:
acquiring time stamp information corresponding to each electroencephalogram signal in the plurality of electroencephalogram signal sequences;
based on the time stamp information, dividing the electroencephalogram signals in a preset time period in the plurality of electroencephalogram signal sequences according to the preset time period, and obtaining a plurality of sets of the electroencephalogram signal sequences as the electroencephalogram signal sequences.
3. The method of claim 1, wherein performing, by the signal processing unit, interest level analysis and challenge level analysis and calculation of the target user on the plurality of specified contents based on the plurality of sets of sub-electroencephalogram signal sequences, comprises:
acquiring a plurality of sample sub-brain electrical signal sequence sets based on brain electrical monitoring analysis data records in a user learning process, and acquiring a sample interest level set and a sample challenge level set;
respectively constructing an interestingness analysis branch and a challenged degree analysis branch by adopting the plurality of sample sub-electroencephalogram signal sequence sets, the sample interestingness set and the sample challenged degree set, and performing supervision training until convergence to obtain an electroencephalogram signal analyzer;
Analyzing the plurality of sub-electroencephalogram signal sequence sets by adopting the electroencephalogram signal analyzer to obtain a plurality of interestingness sets and a plurality of challenge sets;
and calculating to obtain a plurality of interestingness and a plurality of challenges according to the plurality of interestingness sets and the plurality of challenges.
4. The method of claim 1, wherein extracting noise points in the plurality of sets of sub-electroencephalogram signal sequences to obtain a plurality of sets of noise points, performing correction calculation on the plurality of interestingness according to a number of the plurality of sets of noise points to obtain a plurality of corrected interestingness, comprising:
extracting peak noise points from the plurality of sub-electroencephalogram signal sequence sets to obtain a plurality of peak noise point sets;
extracting valley noise points from the plurality of sub-electroencephalogram signal sequence sets to obtain a plurality of valley noise point sets, combining the plurality of peak noise point sets, and counting to obtain a plurality of noise point sets;
and carrying out correction calculation on the plurality of interestingness according to the reciprocal of the ratio of the number of noise points in each noise point set to the number of historical average noise points, so as to obtain the plurality of corrected interestingness.
5. The method of claim 1, wherein obtaining the relevance coefficients for each two specified contents of the plurality of specified contents, performing a correction calculation on the plurality of corrected interestingness levels and the plurality of challenged levels, and obtaining a plurality of corrected interestingness levels and a plurality of corrected challenged levels, comprises:
Acquiring relevance coefficients of each two specified contents according to the learning contents in the specified contents to acquire a plurality of relevance coefficients;
acquiring a plurality of groups of designated contents with relevance coefficients larger than relevance coefficient threshold values, acquiring two corrected interestingness and two challenged degrees corresponding to each group of designated contents, carrying out negative correction on the large corrected interestingness and challenged degrees according to the relevance coefficients, and carrying out positive correction on the small corrected interestingness and challenged degrees to acquire a plurality of corrected interestingness and a plurality of corrected challenged degrees.
6. The method of claim 1, wherein obtaining a plurality of learning scores of the target user for the plurality of specified content, and combining the plurality of corrected interestingness and the plurality of corrected challenged degrees, constructing a learning feature information matrix of the target user for the plurality of specified content, comprises:
acquiring a plurality of learning scores of the target user on the plurality of specified contents;
normalizing the learning scores to obtain a plurality of learning degrees;
carrying out forward processing on the plurality of correction challenged degrees to obtain a plurality of forward challenged degrees;
based on the learning degrees, the correction interestingness degrees and the forward challenges, a learning characteristic information matrix of the target user for the specified contents is constructed, wherein the learning characteristic information matrix comprises the following formula:
；
Wherein A is a learning characteristic information matrix, M is the number of a plurality of specified contents,and->Learning degree of 1 st specified content and M th specified content for target user, ++>And->Correction interest level for target user for 1 st specified content and Mth specified content, ++>And->The forward challenges for the target user to the 1 st specified content and the Mth specified content.
7. The method according to claim 6, wherein analyzing and calculating to obtain a plurality of pieces of learning state information of the target user for the plurality of specified contents as a result of signal processing based on the learning characteristic information matrix includes:
according to the learning characteristic information matrix, a plurality of pieces of learning state information of the target user on the plurality of specified contents are obtained through analysis and calculation, and the following formula is obtained:
；
；
；
wherein,ith learning status information for the target user for the ith designated content, +.>、/>、/>、、/>、/>For learning maximum and minimum values in M learning degrees, M correction interest degrees and M forward challenge degrees in the characteristic information matrix, +.>、/>、/>The ith learning level, the correction interest level and the forward challenge level for the ith appointed content in the learning characteristic information matrix, ++>、/>And->Is a learning level weight, an interest level weight and a challenge level weight.
8. A brain-computer interface based signal transmission processing system, characterized by steps for performing any one of the brain-computer interface based signal transmission processing methods of claims 1-7, the system comprising a brain-computer interface based signal transmission processing device, the device comprising a noninvasive wearable electroencephalogram device, a signal transmission acquisition unit, a signal processing unit, comprising:
the electroencephalogram signal sequence acquisition module is used for acquiring electroencephalogram signals through the signal transmission acquisition unit in the learning process of target contents of target users wearing electroencephalogram equipment to acquire a plurality of electroencephalogram signal sequences, wherein the target contents comprise a plurality of appointed contents and correspond to the plurality of electroencephalogram signal sequences;
the electroencephalogram signal sequence dividing module is used for dividing the plurality of electroencephalogram signal sequences according to a preset time period to obtain a plurality of sub-electroencephalogram signal sequence sets;
the analysis and calculation module is used for analyzing and calculating the interestingness and the challenged degrees of the target user on the specified contents based on the electroencephalogram signal sequence sets through the signal processing unit to obtain interestingness and challenged degrees;
The noise point extraction module is used for extracting noise points in the plurality of sub-electroencephalogram signal sequence sets to obtain a plurality of noise point sets, and correcting and calculating the plurality of interestingness according to the number of the plurality of noise point sets to obtain a plurality of corrected interestingness;
the information correction module is used for obtaining the relevance coefficient of each two appointed contents in the plurality of appointed contents, correcting and calculating the plurality of corrected interestingness and the plurality of challenged interestingness, and obtaining a plurality of corrected interestingness and a plurality of corrected challenged interestingness;
the learning characteristic information matrix construction module is used for acquiring a plurality of learning scores of the target user on the plurality of specified contents and constructing a learning characteristic information matrix of the target user on the plurality of specified contents by combining the plurality of correction interestingness and the plurality of correction challenged degrees;
and the signal processing result obtaining module is used for obtaining a plurality of pieces of learning state information of the target user on the plurality of specified contents as a signal processing result according to the learning characteristic information matrix through analysis and calculation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410089103.3A CN117608411B (en) | 2024-01-23 | 2024-01-23 | Signal transmission processing method and system based on brain-computer interface |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410089103.3A CN117608411B (en) | 2024-01-23 | 2024-01-23 | Signal transmission processing method and system based on brain-computer interface |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117608411A true CN117608411A (en) | 2024-02-27 |
| CN117608411B CN117608411B (en) | 2024-03-22 |
Family
ID=89950258
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410089103.3A Active CN117608411B (en) | 2024-01-23 | 2024-01-23 | Signal transmission processing method and system based on brain-computer interface |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117608411B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090228318A1 (en) * | 2008-03-06 | 2009-09-10 | Hitachi, Ltd. | Server and sensor net system for measuring quality of activity |
| CN107123019A (en) * | 2017-03-28 | 2017-09-01 | 华南理工大学 | A kind of VR shopping commending systems and method based on physiological data and Emotion identification |
| US20200060603A1 (en) * | 2016-10-24 | 2020-02-27 | Akili Interactive Labs, Inc. | Cognitive platform configured as a biomarker or other type of marker |
| CN116823408A (en) * | 2023-08-29 | 2023-09-29 | 小舟科技有限公司 | Commodity recommendation method, device, terminal and storage medium based on virtual reality |
| CN117063075A (en) * | 2021-01-26 | 2023-11-14 | 皇家飞利浦有限公司 | Monitoring of FMRI checks |
-
2024
- 2024-01-23 CN CN202410089103.3A patent/CN117608411B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090228318A1 (en) * | 2008-03-06 | 2009-09-10 | Hitachi, Ltd. | Server and sensor net system for measuring quality of activity |
| US20200060603A1 (en) * | 2016-10-24 | 2020-02-27 | Akili Interactive Labs, Inc. | Cognitive platform configured as a biomarker or other type of marker |
| CN107123019A (en) * | 2017-03-28 | 2017-09-01 | 华南理工大学 | A kind of VR shopping commending systems and method based on physiological data and Emotion identification |
| CN117063075A (en) * | 2021-01-26 | 2023-11-14 | 皇家飞利浦有限公司 | Monitoring of FMRI checks |
| CN116823408A (en) * | 2023-08-29 | 2023-09-29 | 小舟科技有限公司 | Commodity recommendation method, device, terminal and storage medium based on virtual reality |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117608411B (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200367800A1 (en) | Method for identifying driving fatigue based on cnn-lstm deep learning model | |
| CN108959895B (en) | Electroencephalogram EEG (electroencephalogram) identity recognition method based on convolutional neural network | |
| CN108836323B (en) | Learning state monitoring system based on electroencephalogram analysis and using method thereof | |
| CN103955270B (en) | Character high-speed input method of brain-computer interface system based on P300 | |
| CN111544015B (en) | Cognitive power-based control work efficiency analysis method, device and system | |
| CN110598676B (en) | Deep learning gesture electromyographic signal identification method based on confidence score model | |
| CN111598451B (en) | Control work efficiency analysis method, device and system based on task execution capacity | |
| CN105595990A (en) | Intelligent terminal device for evaluating and distinguishing quality of electrocardiosignal | |
| CN111598453B (en) | Control work efficiency analysis method, device and system based on execution force in virtual scene | |
| CN111000555B (en) | Training data generation method, automatic recognition model modeling method and automatic recognition method for epileptic electroencephalogram signals | |
| Yudhana et al. | Human emotion recognition based on EEG signal using fast fourier transform and K-Nearest neighbor | |
| CN114129129A (en) | Epilepsy detection system based on CNN and Transformer | |
| CN115590529A (en) | Epilepsia electroencephalogram signal monitoring method and system based on space-time attention mechanism | |
| CN113288157A (en) | Arrhythmia classification method based on depth separable convolution and improved loss function | |
| CN111067513A (en) | Sleep quality detection key brain area judgment method based on characteristic weight self-learning | |
| CN113128585B (en) | Deep neural network based multi-size convolution kernel method for realizing electrocardiographic abnormality detection and classification | |
| CN110811548A (en) | Memory state evaluation method, system, device and storage medium | |
| CN112698720B (en) | Movement imagery identification method based on mutual information feature extraction and multi-person fusion | |
| CN117608411B (en) | Signal transmission processing method and system based on brain-computer interface | |
| CN117883082A (en) | Abnormal emotion recognition method, system, equipment and medium | |
| CN111643076A (en) | BECT spike intelligent detection method based on multi-channel electroencephalogram signals | |
| CN113171111B (en) | Upper limb movement direction nerve decoding method and device | |
| CN112149724B (en) | Electroencephalogram data feature extraction method based on intra-class compactness | |
| CN117643475B (en) | Feature extraction method based on KL divergence | |
| CN117137426B (en) | Visual field damage evaluation training method and system based on micro-glance feature monitoring |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |