CN109961018A - Electroencephalogramsignal signal analysis method, system and terminal device - Google Patents
Electroencephalogramsignal signal analysis method, system and terminal device Download PDFInfo
- Publication number
- CN109961018A CN109961018A CN201910146934.9A CN201910146934A CN109961018A CN 109961018 A CN109961018 A CN 109961018A CN 201910146934 A CN201910146934 A CN 201910146934A CN 109961018 A CN109961018 A CN 109961018A
- Authority
- CN
- China
- Prior art keywords
- eeg signals
- stimulus
- signal
- scene
- user
- 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; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The present invention is suitable for bioelectrical signals analysis technical field, disclose a kind of electroencephalogramsignal signal analysis method, system and terminal device, it include: physiologic information and the first user corresponding EEG signals under multiple stimulus groups for obtaining the first user, stimulus group includes at least one corresponding stimulus of the first scene, and the first scene is any one scene in multiple default scenes；According to EEG signals, the markup information of corresponding stimulus group is obtained；Based on physiologic information, the first scene, EEG signals, stimulus group and stimulus group markup information, carry out machine learning, obtain stimulus group recommended models and electroencephalogramsignal signal analyzing model.The present invention can determine different stimulus groups to the effect of stimulation of different people by electroencephalogramsignal signal analyzing model, it is to want to enter into the different people of Same Scene to recommend different stimulus groups by stimulus group recommended models, it can be realized personalized recommendation, make different to rapidly enter corresponding scene per capita.
Description
Technical field
The invention belongs to bioelectrical signals analysis technical field more particularly to a kind of electroencephalogramsignal signal analysis method, system and
Terminal device.
Background technique
E.E.G, also referred to as brain wave refer to that generated electrical resistance is swung when the nerve cell activity in human brain, because this
Swing is presented on scientific instrument, it appears that just as fluctuation, therefore referred to as E.E.G.When people is by outside stimulus, brain electricity
Wave signal can be varied, and this variation is that people is uncontrollable.
Currently, having the product much made one by giving outside stimulus into certain scene, such as light by playing
Music, make one enter relaxing scene.But these products are directed to different people, the outside stimulus given is identical, nothing
Method accomplishes to make different to rapidly enter corresponding scene per capita.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of electroencephalogramsignal signal analysis method, system and terminal device, to solve
In the prior art, for different people, the outside stimulus given be it is identical, can not accomplish to make different to rapidly enter per capita
The problem of corresponding scene.
The first aspect of the embodiment of the present invention provides a kind of electroencephalogramsignal signal analysis method, comprising:
Physiologic information and the first user corresponding EEG signals under multiple stimulus groups of the first user are obtained, are pierced
Stimulus group includes at least one corresponding stimulus of the first scene, and the first scene is any one field in multiple default scenes
Scape, the first user are any one user；
According to EEG signals, the markup information of corresponding stimulus group is obtained；
Based on physiologic information, the first scene, EEG signals, stimulus group and stimulus group markup information, carry out machine
Study, obtains stimulus group recommended models and electroencephalogramsignal signal analyzing model.
The second aspect of the embodiment of the present invention provides a kind of electroencephalogramsignal signal analyzing system, comprising:
Module is obtained, physiologic information and the first user for obtaining the first user respectively correspond under multiple stimulus groups
EEG signals, stimulus group include at least one corresponding stimulus of the first scene, the first scene be multiple default scenes in
Any one, the first user be any one user；
Electroencephalogramsignal signal analyzing module, for obtaining the markup information of corresponding stimulus group according to EEG signals；
Machine learning module, for based on physiologic information, the first scene, EEG signals and stimulus group markup information,
Machine learning is carried out, stimulus group recommended models and brain electric information analysis model are obtained.
The third aspect of the embodiment of the present invention provides a kind of terminal device, including memory, processor and is stored in
In memory and the computer program that can run on a processor, processor are realized when executing computer program such as first aspect institute
The step of stating electroencephalogramsignal signal analysis method.
The fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, computer readable storage medium
It is stored with computer program, EEG signals as described in relation to the first aspect are realized when computer program is executed by one or more processors
The step of analysis method.
Existing beneficial effect is the embodiment of the present invention compared with prior art: the embodiment of the present invention obtains the first use first
The physiologic information at family and the first user corresponding EEG signals under multiple stimulus groups obtain then according to EEG signals
The markup information of corresponding stimulus group is obtained, physiologic information, the first scene, EEG signals, stimulus group and stimulation are finally based on
The markup information of source group carries out machine learning, obtains stimulus group recommended models and electroencephalogramsignal signal analyzing model, can pass through brain
Electric signal analysis model determines that different stimulus groups is to think by stimulus group recommended models to the effect of stimulation of different people
The different people that enter Same Scene recommend different stimulus groups, can be realized personalized recommendation, make different per capita
Rapidly enter corresponding scene.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is the implementation process schematic diagram for the electroencephalogramsignal signal analysis method that one embodiment of the invention provides；
Fig. 2 be another embodiment of the present invention provides electroencephalogramsignal signal analysis method implementation process schematic diagram；
Fig. 3 is the schematic block diagram for the electroencephalogramsignal signal analyzing system that one embodiment of the invention provides；
Fig. 4 is the schematic block diagram for the terminal device that one embodiment of the invention provides.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, so as to provide a thorough understanding of the present application embodiment.However, it will be clear to one skilled in the art that there is no these specific
The application also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, so as not to obscure the description of the present application with unnecessary details.
In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.
Fig. 1 is the implementation process schematic diagram for the electroencephalogramsignal signal analysis method that one embodiment of the invention provides, for the ease of saying
Bright, only parts related to embodiments of the present invention are shown.The executing subject of the embodiment of the present invention can be terminal device.
As shown in Figure 1, this method may comprise steps of:
Step S101: physiologic information and the first user corresponding brain under multiple stimulus groups of the first user is obtained
Electric signal, stimulus group include at least one corresponding stimulus of the first scene, and the first scene is appointing in multiple default scenes
It anticipates a scene, the first user is any one user.
Wherein, physiologic information may include one of information such as gender, age, height and weight or much information, when
So, according to the actual situation, physiologic information also may include other information, such as heart rate, blood pressure, sick information etc..
Stimulus group includes at least one corresponding stimulus of the first scene.Stimulus is used to give people's outside stimulus, from
And EEG signals is made to change, it may include any stimulation of vision, the sense of hearing, tactile, taste and smell etc..For example,
Visual stimulus can be picture material, video content etc., can be different to generate by switching picture material or video content
Visual stimulus；Auditory stimulation can be sound, can generate different auditory stimulation by adjusting size and the frequency of sound；
Haptic stimulus can be soft object, can generate different haptic stimulus by adjusting the softness of object；The sense of taste
Stimulation can be different taste, such as acid, sweet tea, hardship, peppery, salty etc., can pass through the degree of the different taste of adjusting, such as sweet tea
Degree, to generate different taste stimulations；Olfactory stimulation can be different smell, can pass through the strong journey of adjusting smell
Degree is to generate different olfactory stimulations.
First scene can be any one scene in multiple default scenes.Default scene may include loosen, fall asleep,
Excitement, attention collection are medium, it is of course also possible to include other any scenes with demand.The corresponding stimulus of first scene
For the stimulus for meeting the first scene requirement as far as possible, for example, if the first scene is to loosen, then the corresponding stimulus of the first scene
It can be the music, etc. that people can be allowed to loosen.The corresponding stimulus of first scene can be determined according to common sense or expertise.
First user can be any one user, or any type user, for example, it may be any type has
There is the user of the same or similar physiologic information, is not used to refer in particular to certain class user or some user.
In embodiments of the present invention, in one experiment, the first user available brain electricity under a stimulation group
Signal.Many experiments can be taken to obtain by carrying out many experiments EEG signals of the same user under same stimulation group
EEG signals EEG signals of the average value as the user under the stimulation of the stimulation group；Primary experiment can also be obtained
EEG signals of the EEG signals as the user under the stimulation of the stimulation group.Wherein, EEG signals are referred to as E.E.G
Signal or eeg signal can use brain wave acquisition equipment and collect.
In each experiment, the information for the stimulus that stimulus group includes can be directly by being manually entered acquisition, can also
To acquire the information of stimulus group by sensor, and it is based on the second machine recognition model, identifies and wrapped in the information of stimulus group
The information of each stimulus contained.Wherein, the second machine recognition model can be used to identify the information of different stimulus.
The embodiment of the present invention by many experiments, can obtain multiple users physiologic information and multiple users it is multiple not
Under the stimulation of same stimulus group, corresponding EEG signals.Wherein, the physiologic information of multiple users realizes multiplicity as far as possible
Change, multiple and different stimulus groups also realizes diversification as far as possible.
Step S102: according to EEG signals, the markup information of corresponding stimulus group is obtained.
Wherein, the markup information of stimulus group can indicate the first user under the stimulation of the stimulus group, if meet
The requirement of first scene, and meet the degree of the requirement of the first scene.
The embodiment of the present invention is by analyzing EEG signals, the mark of the corresponding stimulus group of available EEG signals
Infuse information.
Step S103: based on physiologic information, the first scene, EEG signals, stimulus group and stimulus group markup information,
Machine learning is carried out, stimulus group recommended models and electroencephalogramsignal signal analyzing model are obtained.
Wherein, stimulus group recommended models can recommend to meet scene requirement to user according to the physiologic information of user
Stimulus group.Electroencephalogramsignal signal analyzing model can determine the user under the stimulation of stimulus group according to the physiologic information of user
Meet the degree of the requirement of the scene.
Specifically, by the physiologic information of user and scene input stimulus source group recommended models, can export accords with the user
Close the stimulus group of the requirement of the scene.For example, inputting the physiologic information of user under the scene loosened, stimulus group is recommended
Model can export the music categories for loosening the user, smell type etc..
The physiologic information of user, stimulus group and scene are inputted in electroencephalogramsignal signal analyzing model, can be exported in the thorn
Under the stimulation of stimulus group, which meets the degree of the requirement of the scene.For example, input one is first easily under the scene loosened
Music and user physiologic information, the degree that electroencephalogramsignal signal analyzing model can export the music and the user can be allowed to loosen is
How much.
In embodiments of the present invention, based on physiologic information, the first scene, EEG signals, stimulus group and stimulus group
Markup information carries out machine learning, during obtaining stimulus group recommended models and electroencephalogramsignal signal analyzing model, the instruction of use
Practice method can for k nearest neighbour method, perceptron, naive Bayesian method, decision tree, Logic Regression Models, support vector machines,
Any one in the methods of Adaboost, Bayesian network and neural network.
Seen from the above description, the embodiment of the present invention is by being based on physiologic information, the first scene, EEG signals, stimulus
The markup information of group and stimulus group carries out machine learning, obtains stimulus group recommended models and electroencephalogramsignal signal analyzing model, can
To determine that different stimulus groups to the effect of stimulation of different people, is recommended by stimulus group by electroencephalogramsignal signal analyzing model
Model is to want to enter into the different people of Same Scene to recommend different stimulus groups, can be realized personalized recommendation, makes difference
Can rapidly enter corresponding scene per capita.
Fig. 2 be another embodiment of the present invention provides electroencephalogramsignal signal analysis method implementation process schematic diagram, for the ease of
Illustrate, only parts related to embodiments of the present invention are shown.As shown in Fig. 2, on the basis of the above embodiments, step S102
It may comprise steps of:
Step S201: the characteristic signal of each EEG signals is extracted.
In embodiments of the present invention, existing method can be used, the characteristic signal of each EEG signals is extracted.Wherein, brain
The characteristic signal of electric signal can be the power spectrum signal for one or more E.E.Gs that EEG signals include, or brain telecommunications
Number Evoked ptential signal power spectrum signal, can also for EEG signals Evoked ptential signal power spectrum signal and benchmark
The difference signal of power spectrum signal；Reference power spectrum signal is the brain electricity of the first user of acquisition when stimulus group is not added
The mean power spectrum signal of the Evoked ptential signal of signal.
Power spectrum signal is the abbreviation of power spectral density function, is the signal power in unit frequency band.Power spectrum signal is used
In expression signal power with the situation of change of frequency, i.e. distribution situation of the signal power in frequency domain.Reference power spectrum signal is
Under not by environmental stimuli, the power spectrum signal of the Evoked ptential signal of the EEG signals of multi collect is averaged first user
Value.The power spectrum signal of the Evoked ptential signal of EEG signals subtracts reference power signal and obtains difference signal.Wherein, brain telecommunications
Number Evoked ptential signal can be collected by brain wave acquisition equipment.
E.E.G can be divided into four major class: β wave (aobvious consciousness), α wave when frequency variation range is between 1 to 30 time per second
(bridge consciousness), θ wave (subconsciousness) and δ wave (unconscious), these consciousness combination, form a people it is inside and outside row
Performance for, mood and in study.In addition to this, when awakening and being absorbed in a certain part thing, a kind of frequency of Chang Kejian is more compared with β wave
High γ wave, wave amplitude range are indefinite.
Evoked ptential signal is referred to as event related potential, and after people is stimulated by certain events, brain can be spontaneous
Ground generates reaction pattern, reflects approach and the time of brain processing thing.Such as subject will quickly judge occur on screen
Pattern when being target (as red) or non-targeted (such as green), there is target compared to non-targeted object, the electrode of top is piercing
It will record positive (positivity) current potential, referred to as P300 current potential for 300~500 milliseconds after excitation is raw.P300 is considered and people
Evaluation process (decision evaluation) reaction to make a decision is related, can be used to the selection of interpretation people.
Step S202: clustering is carried out to the characteristic signal of each EEG signals, the feature of each EEG signals is believed
Number it is divided into two classifications.
In embodiments of the present invention, existing clustering algorithm, such as K-MEANS algorithm can be used, by each brain telecommunications
Number characteristic signal be divided into two classifications.
Step S203: in two classifications, the few classification of the quantity of selected characteristic signal is as not preferred classification.
Count the quantity for the characteristic signal for including in two classifications after dividing, the classification more than the quantity of selected characteristic signal
As preferred classes, the few classification of the quantity of selected characteristic signal is as not preferred classification.
Since stimulus group is at least one corresponding stimulus of the first scene, as meet the first scene requirement as far as possible
At least one stimulus, so most of stimulus group meets the first scene requirement, so by the quantity of characteristic signal
More classification is as priority categories, using the classification of characteristic signal negligible amounts as not preferred classification.Spy in preferred classes
The corresponding stimulus group of reference number is to meet the stimulus group of the first scene requirement, only meets the degree of the first scene requirement not
Together, the corresponding stimulus group of characteristic signal in not preferred classification is not meet the stimulus group of the first scene requirement, is not met
The degree of first scene requirement is not also identical.
Step S204: calculate between the preset signals in the characteristic signal and not preferred classification of each EEG signals away from
From, and according to apart from the markup information for determining the corresponding stimulus group of each EEG signals.
Wherein, the preset signals in not preferred classification can be some specified characteristic signal in not preferred classification,
It is also possible to the center signal of all characteristic signals in not preferred classification.Wherein, all characteristic signals in not preferred classification
Center signal can be the average signals of all characteristic signals in not preferred classification, be also possible to after the completion of cluster, it is non-
The mass center of preferred classes.
In embodiments of the present invention, calculate each EEG signals characteristic signal and not preferred classification in preset signals it
Between distance, wherein the distance of calculating can be Euclidean distance, and Euclidean distance is bigger, indicate the first user in the EEG signals
Under the stimulation of corresponding stimulus group, the degree for meeting the first scene requirement is higher.
The markup information that the corresponding stimulus group of each EEG signals is determined according to the distance, is specifically as follows: by this
Markup information of the distance as the corresponding stimulus group of each EEG signals, can also by distance with meet the first scene requirement
A mapping is done between degree (0%~100%), using the numerical value after distance mapping as the corresponding stimulus of each EEG signals
The markup information of group.
In one embodiment of the invention, the characteristic signal of EEG signals includes: one kind or more that EEG signals include
The Evoked ptential letter of the power spectrum signal of kind E.E.G, the power spectrum signal of the Evoked ptential signal of EEG signals and EEG signals
Number power spectrum signal and reference power spectrum signal at least one of difference signal signal；Wherein, reference power spectrum signal
For when stimulus group is not added to first user, the average power spectra of the Evoked ptential signal of the EEG signals of acquisition is believed
Number.
In one embodiment of the invention, step S102 may comprise steps of:
According to preset rules, the power spectrum signal for one or more E.E.Gs that EEG signals include is calculated, is obtained
The calculated result of power spectrum signal；
The mark of the corresponding stimulus group of each EEG signals is determined according to the calculated result of power spectrum signal and preset rules
Infuse information.
In embodiments of the present invention, according to preset rules, β wave, α wave, θ wave, δ wave and γ wave that EEG signals include are chosen
One of or the power spectrum signals of a variety of E.E.Gs calculated, obtain the calculated result of power spectrum signal, believed according to power spectrum
Number calculated result and preset rules in the qualifications of calculated result, determine the corresponding stimulus group of each EEG signals
Markup information.
Illustratively, under relaxing scene, whether the α wave/β wave numerical value for calculating each EEG signals is greater than default ratio
Value, the numerical value are more greater than default ratio, indicate that user more loosens, corresponding stimulus group is more effective.
In one embodiment of the invention, after step s 102, above-mentioned electroencephalogramsignal signal analysis method can also include:
The first scene and the corresponding optimal stimulus source group of physiologic information are determined according to the markup information of multiple stimulus groups.
In embodiments of the present invention, the maximum markup information pair of numerical value in the markup information of multiple stimulus groups can be chosen
The stimulus group answered, the corresponding optimal stimulus source group of physiologic information as the first scene and the first user.
In one embodiment of the invention, the physiologic information of the first user " obtain " in step S101 may include:
Obtain the physiologic information for the first user being manually entered；Or,
The image information or video information of the first user are obtained, and is based on the first machine recognition model, according to the first user
Image information or video information, identification obtain the physiologic information of the first user.
In embodiments of the present invention, the acquisition modes of the physiologic information of the first user can be divided into two kinds: one is direct
Obtain the physiologic information for the first user being manually entered；Another kind is the image information or view that the first user is obtained using camera
Frequency information is based on the first machine recognition model, according to described image information or video information, identifies the physiology letter of the first user
Breath.It is of course also possible to use the mode that two methods combine, part physiologic information is obtained by being manually entered, part physiologic information
It identifies to obtain by the first machine recognition model.Wherein, the first machine recognition model is used to be known according to image information or video information
The physiologic information of user is not obtained.
Fig. 3 is that the schematic block diagram for the electroencephalogramsignal signal analyzing system that one embodiment of the invention provides only shows for ease of description
Part related to the embodiment of the present invention out.
In embodiments of the present invention, electroencephalogramsignal signal analyzing system 3 includes:
Module 31 is obtained, the physiologic information and the first user for obtaining the first user are right respectively under multiple stimulus groups
The EEG signals answered, stimulus group include at least one corresponding stimulus of the first scene, and the first scene is multiple default scenes
In any one, the first user be any one user；
Electroencephalogramsignal signal analyzing module 32, for obtaining the markup information of corresponding stimulus group according to EEG signals；
Machine learning module 33, for the mark letter based on physiologic information, the first scene, EEG signals and stimulus group
Breath carries out machine learning, obtains stimulus group recommended models and brain electric information analysis model.
Optionally, electroencephalogramsignal signal analyzing module 32 includes:
Feature signal extraction unit, for extracting the characteristic signal of each EEG signals；
Cluster analysis unit carries out clustering for the characteristic signal to each EEG signals, by each EEG signals
Characteristic signal be divided into two classifications；
Not preferred classification determination unit, in two classifications, the few classification of the quantity of selected characteristic signal to be as non-
Preferred classes；
First markup information determination unit, for calculate the characteristic signals of each EEG signals with it is pre- in not preferred classification
If the distance between signal, and according to apart from the markup information for determining the corresponding stimulus group of each EEG signals.
Optionally, the characteristic signal of EEG signals includes: the power spectrum letter for one or more E.E.Gs that EEG signals include
Number, the power spectrum signal of the Evoked ptential signals of the power spectrum signal of the Evoked ptential signals of EEG signals and EEG signals with
At least one of the difference signal of reference power spectrum signal signal；Wherein, reference power spectrum signal be to the first user not
When stimulus group is added, the mean power spectrum signal of the Evoked ptential signal of the EEG signals of acquisition.
Optionally, electroencephalogramsignal signal analyzing module 32 includes:
Computing unit is used for according to preset rules, to the power spectrum signal for one or more E.E.Gs that EEG signals include
It is calculated, obtains the calculated result of power spectrum signal；
Second markup information determination unit, for determining each brain according to the calculated result and preset rules of power spectrum signal
The markup information of the corresponding stimulus group of electric signal.
Optionally, electroencephalogramsignal signal analyzing system 3 further include:
Optimal stimulus source group determining module, for determining the first scene and physiology according to the markup information of multiple stimulus groups
The corresponding optimal stimulus source group of information.
Optionally, module 31 is obtained further include:
Physiologic information acquiring unit, for obtaining the physiologic information for the first user being manually entered；Or, obtaining the first user
Image information or video information, and be based on the first machine recognition model, according to the image information or video information of the first user,
Identification obtains the physiologic information of the first user.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of the electroencephalogramsignal signal analyzing system is divided into different functional unit or mould
Block, to complete all or part of the functions described above.Each functional unit in embodiment, module can integrate at one
It manages in unit, is also possible to each unit and physically exists alone, can also be integrated in one unit with two or more units
In, above-mentioned integrated unit both can take the form of hardware realization, can also realize in the form of software functional units.Separately
Outside, each functional unit, module specific name be also only for convenience of distinguishing each other, the protection model being not intended to limit this application
It encloses.The specific work process of unit in above-mentioned apparatus, module, can refer to corresponding processes in the foregoing method embodiment, herein
It repeats no more.
Fig. 4 is the schematic block diagram for the terminal device that one embodiment of the invention provides.As shown in figure 4, the terminal of the embodiment
Equipment 4 includes: one or more processors 40, memory 41 and is stored in the memory 41 and can be in the processor
The computer program 42 run on 40.The processor 40 realizes above-mentioned each EEG signals when executing the computer program 42
Step in analysis method embodiment, such as step S101 to S103 shown in FIG. 1.Alternatively, the processor 40 execute it is described
The function of each module/unit in above-mentioned electroencephalogramsignal signal analyzing system embodiment, such as mould shown in Fig. 3 are realized when computer program 42
The function of block 31 to 33.
Illustratively, the computer program 42 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 41, and are executed by the processor 40, to complete the application.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, which is used for
Implementation procedure of the computer program 42 in the terminal device 4 is described.For example, the computer program 42 can be divided
It is as follows to be cut into acquisition module, electroencephalogramsignal signal analyzing module and machine learning module, the concrete function of modules:
Module is obtained, physiologic information and the first user for obtaining the first user respectively correspond under multiple stimulus groups
EEG signals, stimulus group include at least one corresponding stimulus of the first scene, the first scene be multiple default scenes in
Any one, the first user be any one user；
Electroencephalogramsignal signal analyzing module, for obtaining the markup information of corresponding stimulus group according to EEG signals；
Machine learning module, for based on physiologic information, the first scene, EEG signals and stimulus group markup information,
Machine learning is carried out, stimulus group recommended models and brain electric information analysis model are obtained.
Other modules or unit can refer to the description in embodiment shown in Fig. 3, and details are not described herein.
The terminal device 4 can be mobile phone, tablet computer, notebook etc. and calculate equipment, be also possible to wearable device.
The terminal device 4 includes but are not limited to processor 40, memory 41.It will be understood by those skilled in the art that Fig. 4 is only
One example of terminal device, does not constitute the restriction to terminal device 4, may include components more more or fewer than diagram,
Perhaps combine certain components or different components, for example, the terminal device 4 can also include input equipment, output equipment,
Network access equipment, bus etc..
Optionally, the terminal device 4 is the head hoop for acquiring EEG signals, or for acquiring EEG signals and heartbeat
The head hoop of signal.
Wherein it is possible to heartbeat signal be acquired using existing method, for example, can obtain by detecting the shadow variation of blood vessel
Obtain heartbeat signal.
The processor 40 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
The memory 41 can be the internal storage unit of the terminal device, such as the hard disk or interior of terminal device
It deposits.What the memory 41 was also possible to be equipped on the External memory equipment of the terminal device, such as the terminal device inserts
Connect formula hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash memory
Block (Flash Card) etc..Further, the memory 41 can also both include the internal storage unit of terminal device or wrap
Include External memory equipment.The memory 41 is for storing needed for the computer program 42 and the terminal device other
Program and data.The memory 41 can be also used for temporarily storing the data that has exported or will export.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
Scope of the present application.
In embodiment provided herein, it should be understood that disclosed electroencephalogramsignal signal analyzing system and method, it can
To realize by another way.For example, electroencephalogramsignal signal analyzing system embodiment described above is only schematical, example
Such as, the division of the module or unit, only a kind of logical function partition, can there is other division side in actual implementation
Formula, such as multiple units or components can be combined or can be integrated into another system, or some features can be ignored, or not
It executes.Another point, shown or discussed mutual coupling or direct-coupling or communication connection can be to be connect by some
Mouthful, the INDIRECT COUPLING or communication connection of device or unit can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the application realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program generation
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..The computer-readable medium
It may include: any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic that can carry the computer program code
Dish, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that described
The content that computer-readable medium includes can carry out increasing appropriate according to the requirement made laws in jurisdiction with patent practice
Subtract, such as in certain jurisdictions, according to legislation and patent practice, computer-readable medium do not include be electric carrier signal and
Telecommunication signal.
Embodiment described above is only to illustrate the technical solution of the application, rather than its limitations；Although referring to aforementioned reality
Example is applied the application is described in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope of each embodiment technical solution of the application that it does not separate the essence of the corresponding technical solution should all
Comprising within the scope of protection of this application.
Claims (10)
1. a kind of electroencephalogramsignal signal analysis method characterized by comprising
Obtain physiologic information and first user corresponding EEG signals, the institute under multiple stimulus groups of the first user
Stating stimulus group includes at least one corresponding stimulus of the first scene, and first scene is any in multiple default scenes
One scene, first user are any one user；
According to the EEG signals, the markup information of corresponding stimulus group is obtained；
Based on the physiologic information, first scene, the EEG signals, the stimulus group and the stimulus group mark
Information is infused, machine learning is carried out, obtains stimulus group recommended models and electroencephalogramsignal signal analyzing model.
2. electroencephalogramsignal signal analysis method according to claim 1, which is characterized in that it is described according to the EEG signals, it obtains
Obtain the markup information of corresponding stimulus group, comprising:
Extract the characteristic signal of each EEG signals；
Clustering is carried out to the characteristic signal of each EEG signals, the characteristic signal of each EEG signals is divided
For two classifications；
In described two classifications, the few classification of the quantity of selected characteristic signal is as not preferred classification；
The distance between the characteristic signal for calculating each EEG signals and the preset signals in the not preferred classification, and root
The markup information of the corresponding stimulus group of each EEG signals is determined according to the distance.
3. electroencephalogramsignal signal analysis method according to claim 2, which is characterized in that the characteristic signal packet of the EEG signals
It includes: the Evoked ptential signal of the power spectrum signals of one or more E.E.Gs that the EEG signals include, the EEG signals
The power spectrum signal of the Evoked ptential signal of power spectrum signal and the EEG signals and the difference of reference power spectrum signal are believed
Number at least one of signal；
Wherein, the reference power spectrum signal is the EEG signals of acquisition when stimulus group is not added to first user
Evoked ptential signal mean power spectrum signal.
4. electroencephalogramsignal signal analysis method according to claim 1, which is characterized in that it is described according to the EEG signals, it obtains
Obtain the markup information of corresponding stimulus group, comprising:
According to preset rules, the power spectrum signal for one or more E.E.Gs that the EEG signals include is calculated, is obtained
The calculated result of power spectrum signal；
The corresponding stimulus group of each EEG signals is determined according to the calculated result of the power spectrum signal and the preset rules
Markup information.
5. electroencephalogramsignal signal analysis method according to any one of claims 1 to 4, which is characterized in that described according to
EEG signals, after the markup information for obtaining corresponding stimulus group, further includes:
First scene and the corresponding optimal stimulus source of the physiologic information are determined according to the markup information of multiple stimulus groups
Group.
6. electroencephalogramsignal signal analysis method according to any one of claims 1 to 4, which is characterized in that described to obtain the first use
The physiologic information at family, comprising:
Obtain the physiologic information for first user being manually entered；Or,
The image information or video information of first user are obtained, and is based on the first machine recognition model, according to described first
The image information or video information of user, identification obtain the physiologic information of first user.
7. a kind of electroencephalogramsignal signal analyzing system characterized by comprising
Module is obtained, physiologic information and first user for obtaining the first user respectively correspond under multiple stimulus groups
EEG signals, the stimulus group include at least one corresponding stimulus of the first scene, first scene be it is multiple pre-
If any one in scene, first user is any one user；
Electroencephalogramsignal signal analyzing module, for obtaining the markup information of corresponding stimulus group according to the EEG signals；
Machine learning module, for being based on the physiologic information, first scene, the EEG signals and the stimulus group
Markup information, carry out machine learning, obtain stimulus group recommended models and brain electric information analysis model.
8. a kind of terminal device, including memory, processor and storage are in the memory and can be on the processor
The computer program of operation, which is characterized in that the processor realizes such as claim 1 to 6 when executing the computer program
The step of any one electroencephalogramsignal signal analysis method.
9. terminal device according to claim 8, which is characterized in that the terminal device is for acquiring EEG signals
Head hoop, or the head hoop for acquiring EEG signals and heartbeat signal.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer journey
Sequence realizes the EEG signals as described in any one of claim 1 to 6 when the computer program is executed by one or more processors
The step of analysis method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910146934.9A CN109961018B (en) | 2019-02-27 | 2019-02-27 | Electroencephalogram signal analysis method and system and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910146934.9A CN109961018B (en) | 2019-02-27 | 2019-02-27 | Electroencephalogram signal analysis method and system and terminal equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109961018A true CN109961018A (en) | 2019-07-02 |
| CN109961018B CN109961018B (en) | 2021-03-05 |
Family
ID=67023895
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910146934.9A Active CN109961018B (en) | 2019-02-27 | 2019-02-27 | Electroencephalogram signal analysis method and system and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109961018B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110908505A (en) * | 2019-10-29 | 2020-03-24 | 易念科技（深圳）有限公司 | Interest identification method and device, terminal equipment and storage medium |
| CN112450949A (en) * | 2020-12-07 | 2021-03-09 | 东北大学 | Electroencephalogram signal processing method and system for cognitive rehabilitation training |
| CN112687373A (en) * | 2020-12-28 | 2021-04-20 | 易念科技（深圳）有限公司 | System and method for quantifying psychological craving degree |
| CN112906783A (en) * | 2021-02-06 | 2021-06-04 | 西北大学 | Electroencephalogram emotion recognition method and device suitable for cross-test |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010220151A (en) * | 2009-03-19 | 2010-09-30 | Nomura Research Institute Ltd | Content distribution system, content distribution method, and computer program |
| CN103412646A (en) * | 2013-08-07 | 2013-11-27 | 南京师范大学 | Emotional music recommendation method based on brain-computer interaction |
| US20140277649A1 (en) * | 2013-03-15 | 2014-09-18 | Futurewei Technologies, Inc. | Music Recommendation Based on Biometric and Motion Sensors on Mobile Device |
| CN105868382A (en) * | 2016-04-08 | 2016-08-17 | 惠州Tcl移动通信有限公司 | Music recommendation method and system |
| CN105893518A (en) * | 2016-03-30 | 2016-08-24 | 惠州Tcl移动通信有限公司 | Intelligent music recommendation method and system thereof |
| CN106620990A (en) * | 2016-11-24 | 2017-05-10 | 深圳创达云睿智能科技有限公司 | Method and device for monitoring mood |
| CN107438398A (en) * | 2015-01-06 | 2017-12-05 | 大卫·伯顿 | Portable wearable monitoring system |
| CN108932511A (en) * | 2018-10-09 | 2018-12-04 | 南京邮电大学 | A kind of shopping decision-making technique based on brain-machine interaction |
| CN109086726A (en) * | 2018-08-10 | 2018-12-25 | 陈涛 | A kind of topography's recognition methods and system based on AR intelligent glasses |
| CN109276243A (en) * | 2018-08-31 | 2019-01-29 | 易念科技（深圳）有限公司 | Brain electricity psychological test method and terminal device |
-
2019
- 2019-02-27 CN CN201910146934.9A patent/CN109961018B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010220151A (en) * | 2009-03-19 | 2010-09-30 | Nomura Research Institute Ltd | Content distribution system, content distribution method, and computer program |
| US20140277649A1 (en) * | 2013-03-15 | 2014-09-18 | Futurewei Technologies, Inc. | Music Recommendation Based on Biometric and Motion Sensors on Mobile Device |
| CN103412646A (en) * | 2013-08-07 | 2013-11-27 | 南京师范大学 | Emotional music recommendation method based on brain-computer interaction |
| CN107438398A (en) * | 2015-01-06 | 2017-12-05 | 大卫·伯顿 | Portable wearable monitoring system |
| CN105893518A (en) * | 2016-03-30 | 2016-08-24 | 惠州Tcl移动通信有限公司 | Intelligent music recommendation method and system thereof |
| CN105868382A (en) * | 2016-04-08 | 2016-08-17 | 惠州Tcl移动通信有限公司 | Music recommendation method and system |
| CN106620990A (en) * | 2016-11-24 | 2017-05-10 | 深圳创达云睿智能科技有限公司 | Method and device for monitoring mood |
| CN109086726A (en) * | 2018-08-10 | 2018-12-25 | 陈涛 | A kind of topography's recognition methods and system based on AR intelligent glasses |
| CN109276243A (en) * | 2018-08-31 | 2019-01-29 | 易念科技（深圳）有限公司 | Brain electricity psychological test method and terminal device |
| CN108932511A (en) * | 2018-10-09 | 2018-12-04 | 南京邮电大学 | A kind of shopping decision-making technique based on brain-machine interaction |
Non-Patent Citations (3)
| Title |
|---|
| HIROKI ITOGA ET.AL: "EEG based automatic music recommendation system using ranking deep artificial neural network", 《PATHOPHYSIOLOGY》 * |
| SAIM SHIN ET.AL: "MyMusicShuffler: Mood-Based Music Recommendation with the Practical Usage of Brainwave Signals", 《2014 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS (ICCE)》 * |
| 马勇 等: "脑电信号驱动的个性化情绪音乐播放系统算法研究及初步实现", 《生物医学工程学杂志》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110908505A (en) * | 2019-10-29 | 2020-03-24 | 易念科技（深圳）有限公司 | Interest identification method and device, terminal equipment and storage medium |
| CN110908505B (en) * | 2019-10-29 | 2023-06-30 | 易念科技（深圳）有限公司 | Interest identification method, device, terminal equipment and storage medium |
| CN112450949A (en) * | 2020-12-07 | 2021-03-09 | 东北大学 | Electroencephalogram signal processing method and system for cognitive rehabilitation training |
| CN112687373A (en) * | 2020-12-28 | 2021-04-20 | 易念科技（深圳）有限公司 | System and method for quantifying psychological craving degree |
| CN112906783A (en) * | 2021-02-06 | 2021-06-04 | 西北大学 | Electroencephalogram emotion recognition method and device suitable for cross-test |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109961018B (en) | 2021-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109961018A (en) | Electroencephalogramsignal signal analysis method, system and terminal device | |
| CN110522983B (en) | Brain stimulation system, method, device and storage medium based on artificial intelligence | |
| CN104902806B (en) | The assessment system and method for europathology | |
| CN104871160B (en) | System and method for feeling and recognizing anatomy | |
| CN107123019A (en) | A kind of VR shopping commending systems and method based on physiological data and Emotion identification | |
| Li et al. | Multi-modal bioelectrical signal fusion analysis based on different acquisition devices and scene settings: Overview, challenges, and novel orientation | |
| CN109843163A (en) | For marking dormant method and system | |
| Wu et al. | Modeling perceived stress via HRV and accelerometer sensor streams | |
| CN103038772A (en) | Method of predicting the survivability of a patient | |
| CN106236027B (en) | Depressed crowd's decision method that a kind of brain electricity is combined with temperature | |
| CN108201435A (en) | Sleep stage determines method, relevant device and computer-readable medium | |
| CN109859570A (en) | A kind of brain training method and system | |
| CN108549276B (en) | Method and system for intelligently and interactively controlling water production equipment | |
| CN106510702B (en) | The extraction of sense of hearing attention characteristics, identifying system and method based on Middle latency auditory evoked potential | |
| CN108310759A (en) | Information processing method and related product | |
| CN109394188A (en) | A kind of adnormal respiration detection method, device and equipment based on heart rate variability | |
| CN110141258A (en) | A kind of emotional state detection method, equipment and terminal | |
| CN109276243A (en) | Brain electricity psychological test method and terminal device | |
| CN110367976A (en) | Eeg signal detection method, relevant device and storage medium | |
| CN107957780A (en) | A kind of brain machine interface system based on Steady State Visual Evoked Potential physiological property | |
| Zhang et al. | An improved EEGNet for single-trial EEG classification in rapid serial visual presentation task | |
| CN106137207A (en) | Feeding action information determines method and apparatus | |
| CN114145745A (en) | Multi-task self-supervision emotion recognition method based on graph | |
| CN113812933A (en) | Acute myocardial infarction real-time early warning system based on wearable equipment | |
| CN113749656A (en) | Emotion identification method and device based on multi-dimensional physiological signals |
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 |