CN110008874A - Data processing method and its device, computer system and readable medium - Google Patents
Data processing method and its device, computer system and readable medium Download PDFInfo
- Publication number
- CN110008874A CN110008874A CN201910231389.3A CN201910231389A CN110008874A CN 110008874 A CN110008874 A CN 110008874A CN 201910231389 A CN201910231389 A CN 201910231389A CN 110008874 A CN110008874 A CN 110008874A
- Authority
- CN
- China
- Prior art keywords
- data
- measurand
- marked
- eeg signals
- cognitive state
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
Present disclose provides a kind of data processing methods, comprising: acquires the data to be marked of measurand, wherein data to be marked are used to record behavior state of the measurand in acquisition timing；Acquire the EEG signals data of measurand, wherein EEG signals data are used to characterize cognitive state of the measurand in acquisition timing；And EEG signals data and data to be marked are based on, generate the labeled data of measurand.The disclosure additionally provides a kind of data processing equipment, computer system and computer readable medium.
Description
Technical field
This disclosure relates to a kind of data processing method and its device, computer system and readable medium.
Background technique
In the intelligent algorithm of perception identification measurand cognitive state (mood, attention etc.), training is based on number
A large amount of labeled data is needed according to the machine learning model of driving, the confidence level of labeled data is most important, to a certain extent
The accuracy for determining training pattern directly affects the recognition result to measurand cognitive state.
During realizing disclosure design, inventor's discovery at least has the following deficiencies: current industry in the related technology
Data set (video, audio, eye movement, myoelectricity etc.) data volume used in the machine learning research on boundary is huge, it is most of be all by
Mark personnel mark by hand.However the psychology such as the emotion of the mankind, attention, cognitive state data are that mark personnel are difficult by making
Data set (video, audio, eye movement, myoelectricity etc.) carries out accurate calibration, usually can be because of the individual of different labeled personnel
Deviation causes the labeled data consistency of multidigit mark personnel poor, and annotation results are with a low credibility, eventually lead to machine learning model
Can not Accurate Prediction measurand cognitive state consequence.
Summary of the invention
An aspect of this disclosure provides a kind of data processing method, comprising: the data to be marked of measurand are acquired,
Wherein, above-mentioned data to be marked are used to record behavior state of the above-mentioned measurand in acquisition timing, acquire above-mentioned tested pair
The EEG signals data of elephant, wherein above-mentioned EEG signals data are for characterizing above-mentioned measurand in above-mentioned acquisition timing
Cognitive state, and above-mentioned EEG signals data and above-mentioned data to be marked are based on, generate the labeled data of above-mentioned measurand.
Optionally, above-mentioned to be based on above-mentioned EEG signals data and above-mentioned data to be marked, generate the mark of above-mentioned measurand
Note data include: in the above-mentioned data to be marked of detection with the presence or absence of the data slot for meeting preset condition, in above-mentioned number to be marked
In the case where according to the middle data slot for existing and meeting above-mentioned preset condition, it is right in above-mentioned acquisition timing to obtain above-mentioned data slot
The EEG signals fragment data answered, and above-mentioned EEG signals fragment data and above-mentioned data to be marked are based on, generate above-mentioned quilt
Survey the labeled data of object.
Optionally, above-mentioned to be based on above-mentioned EEG signals fragment data and above-mentioned data to be marked, generate above-mentioned measurand
Labeled data include: that correction is filtered to above-mentioned EEG signals fragment data, with the EEG signals segment after being corrected
Data, the EEG signals fragment data after identifying above-mentioned correction are recognized with obtaining above-mentioned measurand in above-mentioned acquisition timing
The recognition result of state, and the recognition result based on above-mentioned cognitive state and above-mentioned data to be marked generate above-mentioned tested pair
The labeled data of elephant.
Optionally, the above-mentioned recognition result based on above-mentioned cognitive state and above-mentioned data to be marked generate above-mentioned tested pair
The labeled data of elephant includes: to cluster to the recognition result of above-mentioned cognitive state, to obtain the cluster knot of above-mentioned cognitive state
Fruit, and the cluster result based on above-mentioned cognitive state divide above-mentioned data to be marked, to generate the mark of above-mentioned measurand
Data.
Another aspect of the disclosure provides a kind of data processing equipment, comprising: the first acquisition module is configured as adopting
Collect the data to be marked of measurand, wherein above-mentioned data to be marked are for recording above-mentioned measurand in acquisition timing
Behavior state, the second acquisition module are configured as acquiring the EEG signals data of above-mentioned measurand, wherein above-mentioned brain telecommunications
Number is configured as base for characterizing cognitive state and processing module of the above-mentioned measurand in above-mentioned acquisition timing
In above-mentioned EEG signals data and above-mentioned data to be marked, the labeled data of above-mentioned measurand is generated.
Optionally, whether above-mentioned processing module includes: detection sub-module, be configured as detecting and deposit in above-mentioned data to be marked
In the data slot for meeting preset condition, acquisition submodule is configured as in above-mentioned data to be marked above-mentioned pre- in the presence of meeting
If in the case where the data slot of condition, obtaining above-mentioned data slot corresponding EEG signals segments in above-mentioned acquisition timing
According to, and processing submodule, it is configured as generating above-mentioned quilt based on above-mentioned EEG signals fragment data and above-mentioned data to be marked
Survey the labeled data of object.
Optionally, above-mentioned processing submodule includes: correction unit, is configured as carrying out above-mentioned EEG signals fragment data
Filtering and calibration, with the EEG signals fragment data after being corrected, recognition unit is configured as identifying the brain electricity after above-mentioned correction
Signal segment data, to obtain the recognition result of above-mentioned measurand cognitive state in above-mentioned acquisition timing, and processing list
Member is configured as recognition result and above-mentioned data to be marked based on above-mentioned cognitive state, generates the mark of above-mentioned measurand
Data.
Optionally, above-mentioned processing unit includes: cluster subelement, be configured as to the recognition result of above-mentioned cognitive state into
Row cluster is configured as with obtaining the cluster result of above-mentioned cognitive state, and processing subelement based on above-mentioned cognitive state
Cluster result divides above-mentioned data to be marked, to generate the labeled data of above-mentioned measurand.
Another aspect of the disclosure provides a kind of computer system, comprising: one or more processors；Storage dress
It sets, for storing one or more programs, wherein when one or more programs are executed by one or more processors, so that
The method of one or more processors realization any of the above-described.
Another aspect of the disclosure provides a kind of computer-readable medium, is stored thereon with executable instruction, this refers to
Enable the method for making processor realize any of the above-described when being executed by processor.
Detailed description of the invention
In order to which the disclosure and its advantage is more fully understood, referring now to being described below in conjunction with attached drawing, in which:
Fig. 1 diagrammatically illustrates the applied field of data processing method and data processing equipment according to the embodiment of the present disclosure
Scape；
Fig. 2 diagrammatically illustrates the flow chart of the data processing method according to the embodiment of the present disclosure；
Fig. 3 A is diagrammatically illustrated according to the embodiment of the present disclosure based on EEG signals data and data to be marked, generates quilt
Survey the flow chart of the labeled data of object；
Fig. 3 B is diagrammatically illustrated according to the embodiment of the present disclosure based on EEG signals fragment data and data to be marked, raw
At the flow chart of the labeled data of measurand；
Fig. 3 C diagrammatically illustrates recognition result and data to be marked according to the embodiment of the present disclosure based on cognitive state,
Generate the flow chart of the labeled data of measurand；
Fig. 4 diagrammatically illustrates the block diagram of the data processing equipment according to the embodiment of the present disclosure；
Fig. 5 A diagrammatically illustrates the block diagram of the processing module according to the embodiment of the present disclosure；
Fig. 5 B diagrammatically illustrates the block diagram of the processing submodule according to the embodiment of the present disclosure；
Fig. 5 C diagrammatically illustrates the block diagram of the processing unit according to the embodiment of the present disclosure；And
Fig. 6 diagrammatically illustrates the block diagram of the computer system according to the embodiment of the present disclosure.
Specific embodiment
Hereinafter, will be described with reference to the accompanying drawings embodiment of the disclosure.However, it should be understood that these descriptions are only exemplary
, and it is not intended to limit the scope of the present disclosure.In the following detailed description, to elaborate many specific thin convenient for explaining
Section is to provide the comprehensive understanding to the embodiment of the present disclosure.It may be evident, however, that one or more embodiments are not having these specific thin
It can also be carried out in the case where section.In addition, in the following description, descriptions of well-known structures and technologies are omitted, to avoid
Unnecessarily obscure the concept of the disclosure.
Term as used herein is not intended to limit the disclosure just for the sake of description specific embodiment.It uses herein
The terms "include", "comprise" etc. show the presence of the feature, step, operation and/or component, but it is not excluded that in the presence of
Or add other one or more features, step, operation or component.
There are all terms (including technical and scientific term) as used herein those skilled in the art to be generally understood
Meaning, unless otherwise defined.It should be noted that term used herein should be interpreted that with consistent with the context of this specification
Meaning, without that should be explained with idealization or excessively mechanical mode.
It, in general should be according to this using statement as " at least one in A, B and C etc. " is similar to
Field technical staff is generally understood the meaning of the statement to make an explanation (for example, " system at least one in A, B and C "
Should include but is not limited to individually with A, individually with B, individually with C, with A and B, with A and C, have B and C, and/or
System etc. with A, B, C).Using statement as " at least one in A, B or C etc. " is similar to, generally come
Saying be generally understood the meaning of the statement according to those skilled in the art to make an explanation (for example, " having in A, B or C at least
One system " should include but is not limited to individually with A, individually with B, individually with C, with A and B, have A and C, have
B and C, and/or the system with A, B, C etc.).
Shown in the drawings of some block diagrams and/or flow chart.It should be understood that some sides in block diagram and/or flow chart
Frame or combinations thereof can be realized by computer program instructions.These computer program instructions can be supplied to general purpose computer,
The processor of special purpose computer or other programmable data processing units, so that these instructions are when executed by this processor can be with
Creation is for realizing function/operation device illustrated in these block diagrams and/or flow chart.The technology of the disclosure can be hard
The form of part and/or software (including firmware, microcode etc.) is realized.In addition, the technology of the disclosure, which can be taken, is stored with finger
The form of computer program product on the computer readable storage medium of order, the computer program product is for instruction execution system
System uses or instruction execution system is combined to use.
Present disclose provides a kind of data processing methods, comprising: acquires the data to be marked of measurand, wherein described
Data to be marked are used to record behavior state of the measurand in acquisition timing；Acquire the brain telecommunications of the measurand
Number, wherein the EEG signals data are used to characterize cognitive state of the measurand in the acquisition timing；With
And the EEG signals data and the data to be marked are based on, generate the labeled data of the measurand.
Fig. 1 diagrammatically illustrates the application scenarios of data processing method and data processing equipment according to the embodiment of the present disclosure
100.It should be noted that being only the example that can apply the application scenarios of the embodiment of the present disclosure shown in Fig. 1, to help this field
Technical staff understands the technology contents of the disclosure, but be not meant to the embodiment of the present disclosure may not be usable for other equipment, system,
Environment or scene.
Due to the psychology such as emotion, attention, cognitive state may be subjected in measurand itself physiologic factor and by
The joint effect of the external factor such as object local environment is surveyed, therefore, cognitive state data are that mark personnel are difficult accurately to be marked
Fixed.
Cerebral cortex is the maincenter of brain processing information, by neuron (basic function unit of nervous system) groups of cells
At EEG signals are mainly formed by by the synchronous summation of current potential after neuronal synapses a large amount of in cortex, are that many neurons are total
With movable result.Although EEG signals are faint electricity physiological signals, wherein comprising a large amount of physiology and disease information,
It is played a very important role in clinical medicine, human brain cognitive science research.
With the continuous progress of technology and development, people have investigated various ways also to obtain EEG signals, wherein logical
The mode of the electrode record electroencephalogram spectrum (Electroencephalogram, EEG) of scalp surface is crossed due to the letter of its recording technique
It is single, easy to operate, it is still most important eeg signal acquisition mode employed in current EEG research, uses Electrophysiology
Method detection obtained from the spontaneity of brain cell group, rhythmicity electrical activity.
As shown in Figure 1, the data processing method and data processing equipment of the embodiment of the present disclosure can be applied to perception identification
In the intelligent algorithm of measurand cognitive state (mood, attention etc.), such as monitoring wisdom education student scene.Brain machine
Interface (Brain Computer Interface, BCI) is a kind of in such a way that human brain signal is passed to computer by equipment,
To reach the target that human brain can directly control machine.Psychology, the cognition of measurand can be monitored in real time using passive type BCI
State, such as alertness, attention, pressure, cognitive load, mood etc..
In formally acquisition initial data, while acquiring data to be marked 102 (video, audio, the eye of measurand 101
Dynamic, myoelectricity etc.) and EEG signals data 103, data 102 to be marked and EEG signals data 103 are based on, measurand is generated
101 labeled data 104 generates data set based on labeled data, is trained to data set to obtain for predicting tested pair
The machine training pattern of the cognitive state of elephant can perceive identification measurand cognitive state (mood, attention etc.).
It should be noted that being not the specific limit to the adaptable scene of the disclosure to the foregoing description of application scenarios
It is fixed.
Fig. 2 diagrammatically illustrates the flow chart of the data processing method according to the embodiment of the present disclosure.
As shown in Fig. 2, this method includes operation S210~operation S230.Wherein:
In operation S210, the data to be marked of measurand are acquired.
In operation S220, the EEG signals data of measurand are acquired.
In operation S230, EEG signals data and data to be marked are based on, the labeled data of measurand is generated.
In accordance with an embodiment of the present disclosure, EEG signals data and data to be marked can be acquired by sensor, wherein to
Labeled data is used to record behavior state of the measurand in acquisition timing, and EEG signals data exist for characterizing measurand
Acquire the cognitive state in timing.
Data to be marked and EEG signals data never can reflect measurand cognitive state by ipsilateral.Specifically,
Data to be marked can characterize the cognitive state of measurand more presentation, for example, it may be limb activity, speaking shows
Voice, intonation and word speed etc..And EEG signals data, the more inherent cognitive state of characterization measurand, for example, mood,
Attention etc..
Data to be marked and EEG signals data influence each other between the two, mutually constrain.For example, the mood of measurand
When comparing exciting, the limb action amplitude that may be shown is larger, and the tone, intonation and the word speed spoken may be very fast, on the contrary, by
When the mood of survey object is more gentle, the limb action amplitude that may be shown is smaller, and the tone, intonation and the word speed spoken may
It is relatively slow.
In accordance with an embodiment of the present disclosure, in formal acquisition, data to be marked (video, audio, the eye of measurand are acquired
Dynamic, myoelectricity etc.) while acquire EEG signals data.
It should be noted that can be by inducing material collection, in order to obtain more accurate EEG signals data, just
Before formula acquires data to be marked, the brain activity data baseline (Baseline) of measurand can be calculated, in this way in follow-up data
When processing, it can use the baseline and baseline drift carried out to EEG signals data, give acquisition data band to eliminate acquisition equipment
Systematic error.
By embodiment of the disclosure, in the number to be marked of behavior state of the acquisition characterization measurand in acquisition timing
According to while, also acquire the EEG signals data that can accurately more characterize measurand psychological cognition status data, be based on two kinds
Data are acquired, the labeled data of measurand is automatically generated, not only can be low to avoid service efficiency, the manual mark of higher cost
Injecting method, realizes automatic marking, mass mark, and lower-cost technical effect can also overcome artificial mark accuracy rate not
High technical problem reaches the technical effect for improving the accuracy of data mark.
Fig. 3 A is diagrammatically illustrated according to the embodiment of the present disclosure based on EEG signals data and data to be marked, generates quilt
Survey the flow chart of the labeled data of object.
As shown in Figure 3A, aforementioned operation S230 (is based on EEG signals data and data to be marked, generates the mark of measurand
Infuse data) it include operation S311~operation S313.Wherein:
In operation S311, detect in data to be marked with the presence or absence of the data slot for meeting preset condition.
In operation S312, in the case where there is the data slot for meeting preset condition in data to be marked, data are obtained
Segment corresponding EEG signals fragment data in acquisition timing.
In operation S313, EEG signals fragment data and data to be marked are based on, the labeled data of measurand is generated.
It should be noted that data to be marked can include but is not limited to audio, audio data, relative to EEG signals number
According to data to be marked more can intuitively reflect the mood of measurand, be that the macroscopic view of measurand cognitive state embodies.To
Labeled data reflects the language performance and/or action behavior of measurand, is the microcosmic embodiment of measurand cognitive state.And by
It surveys object and shows the above-mentioned behavior in data to be marked, also will reflect in and obtained with data sampling time sequence synchronous acquisition to be marked
EEG signals data in, i.e., the language performance of measurand and/or action behavior can also reflect tested on certain procedures
The physiological datas such as emotion, attention, the cognitive state of object.
Based on this, in accordance with an embodiment of the present disclosure, the identification that labeled data carries out language and/or movement can be treated, inspection
Survey in data to be marked can include but is not limited to detect in data to be marked with the presence or absence of the data slot for meeting preset condition
With the presence or absence of apparent language and/or the data slot of movement.If so, it is corresponding in acquisition timing then to obtain the data slot
EEG signals fragment data is based on EEG signals fragment data and data to be marked, generates the labeled data of measurand.
For example, the identification to one section of acquisition time data to be marked progress language for being 10 seconds and/or movement, if identifying
Within 3~7 second this period, there are an obvious movements, and in 0~3 second and 7~10 seconds the two periods, it has no bright
Aobvious movement, then EEG signals fragment data is collected EEG signals data in 3~7 second this period；If identifying 0~3
In second and 7~10 seconds the two periods, there are obvious movements, and in 3~7 second this period, without obvious movement, then brain is electric
Signal segment data are collected EEG signals data in 0~3 second and 7~10 seconds the two periods.
In accordance with an embodiment of the present disclosure, the identification of language and/or movement is carried out by treating labeled data, acquisition has language
And/or the data slot of movement corresponding EEG signals fragment data in acquisition timing, it can be selectively based on brain electricity
Signal segment data and data to be marked generate the labeled data of measurand, reduce the data volume of mark traversal, improve data
The efficiency and accuracy of mark.
Fig. 3 B is diagrammatically illustrated according to the embodiment of the present disclosure based on EEG signals fragment data and data to be marked, raw
At the flow chart of the labeled data of measurand.
As shown in Figure 3B, aforementioned operation S313 (is based on EEG signals fragment data and data to be marked, generates measurand
Labeled data) include operation S321~operation S323.Wherein:
In operation S321, correction is filtered to EEG signals fragment data, with the EEG signals segment after being corrected
Data.
EEG signals fragment data after operation S322, identification correction is recognized with obtaining measurand in acquisition timing
Know the recognition result of state.
In operation S323, recognition result and data to be marked based on cognitive state generate the labeled data of measurand.
It should be noted that since EEG signals are a kind of extremely faint physiological signals, amplitude in microvolt rank, because
This EEG signals is extremely easy to be influenced even to fall into oblivion by noise.In addition to the electromagnetic interference in environment, human body itself it is some because
Element can also have an impact brain electricity, eye electricity (Electrooculography, EOG) and myoelectricity (Electromyography, EMG)
Artefact is the interference component that most important two kinds be present in signal result from human body itself.And the ingredient of EMG artefact than
The complicated component of EOG artefact much, is caused by the movement of human muscle group, and source is more, with the muscle institute of neck and face
The influence of generation is the most significant.EMG has an impact 20 hertz or more of EEG frequency content, the muscular movement institute of different location
Influence of the caused EMG to channel EEG each on scalp is also different.Artefact can encounter very big difficulty in processing, due to its signal
Frequency range have with the frequency range of brain electricity it is overlapping, therefore simple filtering method may let us lose a part effectively
Information.And these interference are difficult to realize automatic detection by hardware.
It in accordance with an embodiment of the present disclosure, can be to there is obvious language, dynamic before carrying out complicated brain electricity analytical pretreatment
The EEG signals data for making segment carry out the filtering and calibration of Muscle artifacts, with the EEG signals fragment data after being corrected.Example
Baseline drift is such as removed, Hz noise is removed, bandpass filtering is carried out according to required range of signal, screens the quality of signal,
Exist in observation signal with the presence or absence of apparent eye electricity artefact and Muscle artifacts.It is above two that the relevant technologies provide some removals
Method of artefact, such as adaptive-filtering, space filtering, blind source separating etc., details are not described herein again, and those skilled in the art can be with
The filtering and calibration method suitable with the business experience of oneself selection according to actual needs, the disclosure is without limitation.
By embodiment of the disclosure, pretreatment is corrected etc. to EEG signals fragment data, to obtain measurand
The recognition result of cognitive state, recognition result and data to be marked based on cognitive state in acquisition timing, generate tested pair
The quality of data of EEG signals data can be improved in the labeled data of elephant, improves the accuracy of data annotation results.
Fig. 3 C diagrammatically illustrates recognition result and data to be marked according to the embodiment of the present disclosure based on cognitive state,
Generate the flow chart of the labeled data of measurand.
As shown in Figure 3 C, (recognition result and data to be marked based on cognitive state generate tested pair to aforementioned operation S323
The labeled data of elephant) it include operation S331 and operation S332.Wherein:
In operation S331, the recognition result of cognitive state is clustered, to obtain the cluster result of cognitive state.
In operation S332, the cluster result based on cognitive state divides data to be marked, to generate the mark of measurand
Data.
In accordance with an embodiment of the present disclosure, the EEG signals data after correction are calculated to current psychology, the cognition of tested object
State, and the cluster based on timing is carried out, and treat labeled data using the cluster result of EEG signals data and be split, most
Cognitive state can be labeled in the segment eventually, to generate the labeled data of measurand.
For example, the cluster result of measurand EEG signals data is distinguished in one section of 0~10 second EEG signals data
Are as follows: 0~3 second (thinking), 3~7 seconds (excitement), 7~10 seconds (losing).Above-mentioned three kinds of cluster results are labeled in data to be marked
In corresponding timing.The labeled data of measurand in one section of 0~10 second data to be marked are as follows: 0~3 second (thinking), 3
~7 seconds (excitement), 7~10 seconds (losing).
It should be noted that the recognition result of cognitive state can be clustered using any known technological means,
To obtain the cluster result of cognitive state, the disclosure is not specifically limited.
By embodiment of the disclosure, EEG signals fragment data is determined in EEG signals based on data to be marked, then
The cluster result of the cognitive state obtained is identified based on brain electricity fragment data, removes back annotation number to be marked in corresponding timing
According to being mutually authenticated and correcting for EEG signals data and data to be marked may be implemented, annotation results are more accurate, and efficiency is more
It is high.
Fig. 4 diagrammatically illustrates the block diagram of the data processing equipment according to the embodiment of the present disclosure.
As shown in figure 4, the data processing equipment 400 includes the first acquisition module 410, the second acquisition module 420 and place
Manage module 430.The information processing system 400 can execute the data processing method being described above, to be based on EEG signals data
With data to be marked, the labeled data of measurand is generated.Wherein:
First acquisition module 410 is configured as the data to be marked of acquisition measurand.
Second acquisition module 420 is configured as the EEG signals data of acquisition measurand.
Processing module 430 is configured as generating the mark number of measurand based on EEG signals data and data to be marked
According to.
By embodiment of the disclosure, in the number to be marked of behavior state of the acquisition characterization measurand in acquisition timing
According to while, also acquire the EEG signals data that can accurately more characterize measurand psychological cognition status data, be based on two kinds
Data are acquired, the labeled data of measurand is automatically generated, not only can be low to avoid service efficiency, the manual mark of higher cost
Injecting method, realizes automatic marking, mass mark, and lower-cost technical effect can also overcome artificial mark accuracy rate not
High technical problem reaches the technical effect for improving the accuracy of data mark.
Fig. 5 A diagrammatically illustrates the block diagram of the processing module according to the embodiment of the present disclosure.
As shown in Figure 5A, aforementioned processing module 430 includes detection sub-module 511, acquisition submodule 512 and processing submodule
Block 513.Wherein:
Detection sub-module 511 is configured as detecting in data to be marked with the presence or absence of the data slot for meeting preset condition.
Acquisition submodule 512 is configured as the presence of the case where data slot for meeting preset condition in data to be marked
Under, obtain data slot corresponding EEG signals fragment data in acquisition timing.
Submodule 513 is handled, is configured as generating measurand based on EEG signals fragment data and data to be marked
Labeled data.
By embodiment of the disclosure, the identification of language and/or movement is carried out by treating labeled data, acquisition has language
And/or the data slot of movement corresponding EEG signals fragment data in acquisition timing, it can be selectively based on brain electricity
Signal segment data and data to be marked generate the labeled data of measurand, improve the efficiency and accuracy of data mark.
Fig. 5 B diagrammatically illustrates the block diagram of the processing submodule according to the embodiment of the present disclosure.
As shown in Figure 5 B, aforementioned processing submodule 513 includes correction unit 521, recognition unit 522 and processing unit
523.Wherein:
Unit 521 is corrected, is configured as being filtered correction to EEG signals fragment data, it is electric with the brain after being corrected
Signal segment data.
Recognition unit 522, the EEG signals fragment data after being configured as identification correction, is being acquired with obtaining measurand
The recognition result of cognitive state in timing.
Processing unit 523 is configured as recognition result and data to be marked based on cognitive state, generates measurand
Labeled data.
By embodiment of the disclosure, pretreatment is corrected etc. to EEG signals fragment data, to obtain measurand
The recognition result of cognitive state, recognition result and data to be marked based on cognitive state in acquisition timing, generate tested pair
The quality of data of EEG signals data can be improved in the labeled data of elephant, improves the accuracy of data annotation results.
Fig. 5 C diagrammatically illustrates the block diagram of the processing unit according to the embodiment of the present disclosure.
As shown in Figure 5 C, aforementioned processing unit 523 includes cluster subelement 531 and processing subelement 532.Wherein:
Subelement 531 is clustered, is configured as clustering the recognition result of cognitive state, to obtain the poly- of cognitive state
Class result.
Subelement 532 is handled, the cluster result based on cognitive state is configured as and divides data to be marked, it is tested to generate
The labeled data of object.
By embodiment of the disclosure, EEG signals fragment data is determined in EEG signals based on data to be marked, then
The cluster result of the cognitive state obtained is identified based on brain electricity fragment data, removes back annotation number to be marked in corresponding timing
According to being mutually authenticated and correcting for EEG signals data and data to be marked may be implemented, annotation results are more accurate, and efficiency is more
It is high.
It is module according to an embodiment of the present disclosure, submodule, unit, any number of or in which any more in subelement
A at least partly function can be realized in a module.It is single according to the module of the embodiment of the present disclosure, submodule, unit, son
Any one or more in member can be split into multiple modules to realize.According to the module of the embodiment of the present disclosure, submodule,
Any one or more in unit, subelement can at least be implemented partly as hardware circuit, such as field programmable gate
Array (FPGA), programmable logic array (PLA), system on chip, the system on substrate, the system in encapsulation, dedicated integrated electricity
Road (ASIC), or can be by the hardware or firmware for any other rational method for integrate or encapsulate to circuit come real
Show, or with any one in three kinds of software, hardware and firmware implementations or with wherein any several appropriately combined next reality
It is existing.Alternatively, can be at least by part according to one or more of the module of the embodiment of the present disclosure, submodule, unit, subelement
Ground is embodied as computer program module, when the computer program module is run, can execute corresponding function.
For example, any number of in the first acquisition module 410, the second acquisition module 420 and processing module 430 can close
And it is realized in a module or any one module therein can be split into multiple modules.Alternatively, in these modules
At least partly functions of one or more modules can be combined at least partly function of other modules, and in a module
Middle realization.In accordance with an embodiment of the present disclosure, in the first acquisition module 410, the second acquisition module 420 and processing module 430
At least one can at least be implemented partly as hardware circuit, such as field programmable gate array (FPGA), programmable logic
Array (PLA), system on chip, the system on substrate, the system in encapsulation, specific integrated circuit (ASIC), or can be by right
Circuit carries out the hardware such as any other rational method that is integrated or encapsulating or firmware to realize, or with software, hardware and consolidates
Any one in three kinds of implementations of part several appropriately combined is realized with wherein any.Alternatively, the first acquisition module
410, at least one of the second acquisition module 420 and processing module 430 can at least be implemented partly as computer journey
Sequence module can execute corresponding function when the computer program module is run.
Fig. 6 diagrammatically illustrates the block diagram of the computer system according to the embodiment of the present disclosure.Computer system shown in Fig. 6
An only example, should not function to the embodiment of the present disclosure and use scope bring any restrictions.
As shown in fig. 6, computer system 600 includes processor 610, computer readable storage medium 620.The department of computer science
System 600 can execute the method according to the embodiment of the present disclosure.
Specifically, processor 610 for example may include general purpose microprocessor, instruction set processor and/or related chip group
And/or special microprocessor (for example, specific integrated circuit (ASIC)), etc..Processor 610 can also include using for caching
The onboard storage device on way.Processor 610 can be the different movements for executing the method flow according to the embodiment of the present disclosure
Single treatment unit either multiple processing units.
Computer readable storage medium 620, such as can be non-volatile computer readable storage medium, specific example
Including but not limited to: magnetic memory apparatus, such as tape or hard disk (HDD)；Light storage device, such as CD (CD-ROM)；Memory, such as
Random access memory (RAM) or flash memory；Etc..
Computer readable storage medium 620 may include computer program 621, which may include generation
Code/computer executable instructions execute processor 610 according to the embodiment of the present disclosure
Method or its any deformation.
Computer program 621 can be configured to have the computer program code for example including computer program module.Example
Such as, in the exemplary embodiment, the code in computer program 621 may include one or more program modules, for example including
621A, module 621B ....It should be noted that the division mode and number of module are not fixation, those skilled in the art can
To be combined according to the actual situation using suitable program module or program module, when these program modules are combined by processor 610
When execution, processor 610 is executed according to the method for the embodiment of the present disclosure or its any deformation.
According to an embodiment of the invention, in the first acquisition module 410, the second acquisition module 420 and processing module 430
At least one can be implemented as the computer program module with reference to Fig. 6 description may be implemented when being executed by processor 610
Corresponding operating described above.
The disclosure additionally provides a kind of computer readable storage medium, which can be above-mentioned reality
It applies included in equipment/device/system described in example；Be also possible to individualism, and without be incorporated the equipment/device/
In system.Above-mentioned computer readable storage medium carries one or more program, when said one or multiple program quilts
When execution, the method according to the embodiment of the present disclosure is realized.
In accordance with an embodiment of the present disclosure, computer readable storage medium can be non-volatile computer-readable storage medium
Matter, such as can include but is not limited to: portable computer diskette, hard disk, random access storage device (RAM), read-only memory
(ROM), erasable programmable read only memory (EPROM or flash memory), portable compact disc read-only memory (CD-ROM), light
Memory device, magnetic memory device or above-mentioned any appropriate combination.In the disclosure, computer readable storage medium can
With to be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
Person is in connection.
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the disclosure, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of above-mentioned module, program segment or code include one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it wants
It is noted that the combination of each box in block diagram or flow chart and the box in block diagram or flow chart, can use and execute rule
The dedicated hardware based systems of fixed functions or operations is realized, or can use the group of specialized hardware and computer instruction
It closes to realize.
It will be understood by those skilled in the art that the feature recorded in each embodiment and/or claim of the disclosure can
To carry out multiple combinations and/or combination, even if such combination or combination are not expressly recited in the disclosure.Particularly, exist
In the case where not departing from disclosure spirit or teaching, the feature recorded in each embodiment and/or claim of the disclosure can
To carry out multiple combinations and/or combination.All these combinations and/or combination each fall within the scope of the present disclosure.
Although the disclosure, art technology has shown and described referring to the certain exemplary embodiments of the disclosure
Personnel it should be understood that in the case where the spirit and scope of the present disclosure limited without departing substantially from the following claims and their equivalents,
A variety of changes in form and details can be carried out to the disclosure.Therefore, the scope of the present disclosure should not necessarily be limited by above-described embodiment,
But should be not only determined by appended claims, also it is defined by the equivalent of appended claims.
Claims (10)
1. a kind of data processing method, comprising:
Acquire the data to be marked of measurand, wherein the data to be marked are for recording the measurand in acquisition
Behavior state in sequence；
Acquire the EEG signals data of the measurand, wherein the EEG signals data are for characterizing the measurand
Cognitive state in the acquisition timing；And
Based on the EEG signals data and the data to be marked, the labeled data of the measurand is generated.
2. generating institute according to the method described in claim 1, described be based on the EEG signals data and the data to be marked
The labeled data for stating measurand includes:
It detects in the data to be marked with the presence or absence of the data slot for meeting preset condition；
In the case where there is the data slot for meeting the preset condition in the data to be marked, the data slot is obtained
The corresponding EEG signals fragment data in the acquisition timing；And
Based on the EEG signals fragment data and the data to be marked, the labeled data of the measurand is generated.
3. described to be based on the EEG signals fragment data and the number to be marked according to the method described in claim 2, wherein
According to the labeled data for generating the measurand includes:
Correction is filtered to the EEG signals fragment data, with the EEG signals fragment data after being corrected；
EEG signals fragment data after identifying the correction recognizes shape to obtain the measurand in the acquisition timing
The recognition result of state；And
Recognition result and the data to be marked based on the cognitive state, generate the labeled data of the measurand.
4. according to the method described in claim 3, wherein, the recognition result based on the cognitive state and described to be marked
Data, the labeled data for generating the measurand include:
The recognition result of the cognitive state is clustered, to obtain the cluster result of the cognitive state；And
Cluster result based on the cognitive state divides the data to be marked, to generate the mark number of the measurand
According to.
5. a kind of data processing equipment, comprising:
First acquisition module is configured as the data to be marked of acquisition measurand, wherein the data to be marked are for recording
Behavior state of the measurand in acquisition timing；
Second acquisition module is configured as acquiring the EEG signals data of the measurand, wherein the EEG signals data
For characterizing cognitive state of the measurand in the acquisition timing；And
Processing module is configured as generating the measurand based on the EEG signals data and the data to be marked
Labeled data.
6. device according to claim 5, the processing module include:
Detection sub-module is configured as detecting in the data to be marked with the presence or absence of the data slot for meeting preset condition；
Acquisition submodule is configured as the presence of the case where data slot for meeting the preset condition in the data to be marked
Under, obtain the data slot corresponding EEG signals fragment data in the acquisition timing；And
Submodule is handled, is configured as generating described tested based on the EEG signals fragment data and the data to be marked
The labeled data of object.
7. device according to claim 6, wherein the processing submodule includes:
Unit is corrected, is configured as being filtered correction to the EEG signals fragment data, with the brain telecommunications after being corrected
Number fragment data；
Recognition unit is configured as identifying the EEG signals fragment data after the correction, to obtain the measurand in institute
State the recognition result of cognitive state in acquisition timing；And
Processing unit is configured as recognition result and the data to be marked based on the cognitive state, generates described tested
The labeled data of object.
8. device according to claim 7, wherein the processing unit includes:
Subelement is clustered, is configured as clustering the recognition result of the cognitive state, to obtain the cognitive state
Cluster result；And
Subelement is handled, the cluster result based on the cognitive state is configured as and divides the data to be marked, to generate
State the labeled data of measurand.
9. a kind of computer system, comprising:
One or more processors；
Storage device, for storing one or more programs,
Wherein, when one or more programs are executed by one or more processors, so that one or more processors realize power
The method that benefit requires any one of 1 to 4.
10. a kind of computer-readable medium, is stored thereon with executable instruction, which makes processor real when being executed by processor
The method of existing any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910231389.3A CN110008874B (en) | 2019-03-25 | 2019-03-25 | Data processing method and device, computer system and readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910231389.3A CN110008874B (en) | 2019-03-25 | 2019-03-25 | Data processing method and device, computer system and readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110008874A true CN110008874A (en) | 2019-07-12 |
| CN110008874B CN110008874B (en) | 2021-05-18 |
Family
ID=67168185
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910231389.3A Active CN110008874B (en) | 2019-03-25 | 2019-03-25 | Data processing method and device, computer system and readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110008874B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112383829A (en) * | 2019-11-06 | 2021-02-19 | 致讯科技(天津)有限公司 | Experience quality evaluation method and device |
| CN116671942A (en) * | 2023-07-08 | 2023-09-01 | 中国科学院心理研究所 | Remote facial myoelectricity-based data labeling system and method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105105774A (en) * | 2015-10-09 | 2015-12-02 | 吉林大学 | Driver alertness monitoring method and system based on electroencephalogram information |
| CN105852831A (en) * | 2016-05-10 | 2016-08-17 | 华南理工大学 | Equipment based on virtual reality interaction technology and brain function real-time monitoring technology |
| CN106560765A (en) * | 2016-06-14 | 2017-04-12 | 深圳创达云睿智能科技有限公司 | Method and device for content interaction in virtual reality |
| CN107374652A (en) * | 2017-07-20 | 2017-11-24 | 京东方科技集团股份有限公司 | Quality monitoring method, device and system based on electronic product study |
| CN108201435A (en) * | 2017-12-06 | 2018-06-26 | 深圳和而泰数据资源与云技术有限公司 | Sleep stage determines method, relevant device and computer-readable medium |
| CN108205686A (en) * | 2017-12-06 | 2018-06-26 | 中国电子科技集团公司电子科学研究院 | Video feeling sorting technique and device |
| CN108492224A (en) * | 2018-03-09 | 2018-09-04 | 上海开放大学 | Based on deep learning online education Students ' Comprehensive portrait tag control system |
| CN108966013A (en) * | 2018-07-26 | 2018-12-07 | 北京理工大学 | A kind of viewer response appraisal procedure and system based on panoramic video |
| CN109035960A (en) * | 2018-06-15 | 2018-12-18 | 吉林大学 | Driver's driving mode analysis system and analysis method based on simulation driving platform |
-
2019
- 2019-03-25 CN CN201910231389.3A patent/CN110008874B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105105774A (en) * | 2015-10-09 | 2015-12-02 | 吉林大学 | Driver alertness monitoring method and system based on electroencephalogram information |
| CN105852831A (en) * | 2016-05-10 | 2016-08-17 | 华南理工大学 | Equipment based on virtual reality interaction technology and brain function real-time monitoring technology |
| CN106560765A (en) * | 2016-06-14 | 2017-04-12 | 深圳创达云睿智能科技有限公司 | Method and device for content interaction in virtual reality |
| CN107374652A (en) * | 2017-07-20 | 2017-11-24 | 京东方科技集团股份有限公司 | Quality monitoring method, device and system based on electronic product study |
| CN108201435A (en) * | 2017-12-06 | 2018-06-26 | 深圳和而泰数据资源与云技术有限公司 | Sleep stage determines method, relevant device and computer-readable medium |
| CN108205686A (en) * | 2017-12-06 | 2018-06-26 | 中国电子科技集团公司电子科学研究院 | Video feeling sorting technique and device |
| CN108492224A (en) * | 2018-03-09 | 2018-09-04 | 上海开放大学 | Based on deep learning online education Students ' Comprehensive portrait tag control system |
| CN109035960A (en) * | 2018-06-15 | 2018-12-18 | 吉林大学 | Driver's driving mode analysis system and analysis method based on simulation driving platform |
| CN108966013A (en) * | 2018-07-26 | 2018-12-07 | 北京理工大学 | A kind of viewer response appraisal procedure and system based on panoramic video |
Non-Patent Citations (2)
| Title |
|---|
| MOHAMMAD SOLEYMANI 等: ""Analysis of EEG Signals and Facial Expressions for Continuous Emotion Detection"", 《IEEE TRANSACTIONS ON AFFECTIVE COMPUTING》 * |
| SHANGFEIWANG 等: ""Hybrid video emotional tagging using users’ EEG and video content"", 《SPRINGER》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112383829A (en) * | 2019-11-06 | 2021-02-19 | 致讯科技(天津)有限公司 | Experience quality evaluation method and device |
| CN116671942A (en) * | 2023-07-08 | 2023-09-01 | 中国科学院心理研究所 | Remote facial myoelectricity-based data labeling system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110008874B (en) | 2021-05-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11911171B2 (en) | Systems and methods for brain activity interpretation | |
| Rubin et al. | Learned motor patterns are replayed in human motor cortex during sleep | |
| Belal et al. | Identification of memory reactivation during sleep by EEG classification | |
| Atienza et al. | Semantic congruence enhances memory of episodic associations: role of theta oscillations | |
| Wang et al. | LGNet: Learning local–global EEG representations for cognitive workload classification in simulated flights | |
| Lam et al. | Robust neuronal oscillatory entrainment to speech displays individual variation in lateralisation | |
| CN110008874A (en) | Data processing method and its device, computer system and readable medium | |
| Yadawad et al. | Predicting anxiety among young adults using machine learning algorithms | |
| EP3646784B1 (en) | Electroencephalographic method and apparatus for measuring sensory stimulation salience | |
| KR102060863B1 (en) | Apparatus and method of cognitive load measurement for using physiological psychological reaction data and recall stimulus reaction data | |
| Dharia et al. | Fractal dimension of resting-State EEG as a biomarker for autonomous sensory meridian response (ASMR) | |
| LU505476B1 (en) | Multi-modal and multi-parameter neural feedback training system based on virtual reality | |
| Hasan et al. | Emotion prediction through EEG recordings using computational intelligence | |
| Loock | Learning from the Unexpected: How Prediction Errors Shape Episodic Memory Formation | |
| Sallard et al. | Topographical differences during motion processing in autistic and dyslexic children | |
| Wang et al. | Unified pipeline for generalized mental state detection using EEG signals | |
| Dapit et al. | A Computational Model for Stress Intervention using Affective Brain-Computer Interfaces | |
| Strzelczyk et al. | Impact of Aging on Theta-Gamma Phase-Amplitude Coupling During Learning: A Multivariate Analysis | |
| Sushko | EEG analysis for Emotional Burnout detection | |
| Hu et al. | TDD: Auxiliary framework for recognizing people with depression based on physiological and emotional characteristics of EEG signals | |
| Osuagwu et al. | Artificial neural network based automatic detection of motor evoked potentials | |
| Gopi | CM-II meditation as an intervention to reduce stress and improve attention: A study of ML detection, Spectral Analysis, and HRV metrics | |
| Romaniuk et al. | EEG Headband-Based Emotion Valence Prediction Approach: CNN Model and Evaluation | |
| Mura et al. | Emotional Blunting and Time Estimation in Depression | |
| Ahmadi et al. | Physiological Sensing and Machine Learning Approaches Toward Anxiety Detection: A Systematic Review |
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 |