CN109920498A - Interpersonal relationships prediction technique based on mood brain electroresponse similitude - Google Patents
Interpersonal relationships prediction technique based on mood brain electroresponse similitude Download PDFInfo
- Publication number
- CN109920498A CN109920498A CN201811622000.XA CN201811622000A CN109920498A CN 109920498 A CN109920498 A CN 109920498A CN 201811622000 A CN201811622000 A CN 201811622000A CN 109920498 A CN109920498 A CN 109920498A
- Authority
- CN
- China
- Prior art keywords
- mood
- interpersonal relationships
- video
- similitude
- brain
- 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.)
- Pending
Links
Abstract
The present invention relates to human-computer interaction and biomechanics technical field is related to, a kind of interpersonal relationships prediction technique based on mood brain electroresponse similitude is disclosed, comprising steps of S1: establishing mood video database；S2: interpersonal relationships prediction model is constructed to the EEG signals that video-see in the mood video database generates according to the experimenter of different society group；S3: the real-time EEG signals that tester watches video in the mood video database are obtained；S4: the real-time EEG signals are applied to the interpersonal relationships prediction model, to predict the interpersonal relationships state of development of tester.The present invention can obtain more objective mood evaluating result, and sharper tracking can be carried out to the dynamic changing process of emotional state.
Description
Technical field
The present invention relates to human-computer interaction and biomechanics technical fields, in particular to a kind of to be based on mood brain electroresponse phase
Like the interpersonal relationships prediction technique of property.
Background technique
People establishes extensive social relationships as social animal, by human communication.On the one hand, each individual has it
Unique thought, emotion and behavior pattern.On the other hand, individual between on upper angle there is also certain similitude,
Homogeney.And homogeney is one of the fundamental characteristics that social relationships are established, i.e., more similar people is more intimate as friend, development
A possibility that interpersonal relationships, is bigger.
At present, it has been found that similitude/homogeney of some psychic traits can be used to predict the quality of interpersonal relationships, for example,
The similitude of the personal traits (such as: extropism) of participant's Subjective Reports, can predict friendship situation to a certain extent.But these
Cognitive process, the characteristic of predictive variable one side concern are relatively simple, and variable dimension itself is less, and selection speciality is more single,
It is not fine enough, the Subjective Reports of testee are on the other hand also depended on mostly, it is difficult to avoid the influence of the factors such as social desirability.
Mood is most important mental mechanism in Social Interaction and interpersonal communication as a kind of cognitive process of complexity.Previous research
It was found that the emotional reactions similitude on close relationship both sides' behavior level can predict the development of interpersonal relationships.And mood
Similitude both included emotional experience classification and intensity similitude, also include mood dynamic fluctuation mode similitude.And it passes
The emotional measurement method of system obtains the Subjective Reports of testee by modes such as questionnaire or interviews mostly, with psychic trait measurement one
Sample is difficult to exclude the interference of social desirability completely, and is difficult to carry out fine tracking to the dynamic fluctuation mode of mood.
Summary of the invention
The present invention proposes a kind of interpersonal relationships prediction technique based on mood brain electroresponse similitude, solves prior art feelings
Thread measurement method is difficult to exclude the interference of social desirability completely, and is difficult to carry out finely the dynamic fluctuation mode of mood
The problem of tracking.
The present invention provides a kind of interpersonal relationships prediction techniques based on mood brain electroresponse similitude, comprising steps of
S1: mood video database is established；
S2: the brain telecommunications that video-see in the mood video database is generated according to the experimenter of different society group
Number building interpersonal relationships prediction model；
S3: the real-time EEG signals that tester watches video in the mood video database are obtained；
S4: the real-time EEG signals are applied to the interpersonal relationships prediction model, to predict the interpersonal pass of tester
It is state of development.
Wherein, the step S1 includes:
Mood classification actively, neutral and passive is determined according to psychology mood category theory；
The video that target emotion is effectively aroused in primary election carries out editing and adds subtitle；
The mood attribute of selected audio-visual-materials is carried out to carry out 7 point scale scorings in each emotional dimension, selection is predetermined to divide
Video more than number is added to mood video database.
Wherein, the step S2 includes:
For the experimenter of different society group, the brain telecommunications in different channels is distributed in the overall process record of viewing video
Number；
Under the stimulation of different type of emotion, extract EEG signals in include time domain, frequency domain and the brain in airspace electrical feature,
By the different brain electrical feature similitude composition characteristic vectors for inducing video；
The social distance of all experimenters between any two in public organization is collected mutually to comment；
The whole community network of multidimensional in group is portrayed by nominating method of formation, obtains multidimensional interpersonal relationships number
According to.
By the feature vector of brain electrical feature similitude composition, social distance mutually comments and multidimensional interpersonal relationships data,
Interpersonal relationships prediction model is respectively trained in multiple dimensions.
Wherein, using self-other people are overlapped scale social distance are mutually commented between any two to testee.
Wherein, the brain electrical feature be certain type of emotion under video induce brain electroresponse in special time period gained
The mean value of EEG signals.
It wherein, is that a unit is presented to the experimenter with the video of four sections of same type moods in step S2 and S3
And tester, the video for often finishing watching a unit allow experimenter and tester to carry out judgement task for mathematical problem is presented.
Wherein, the EEG signals include: the theta signal of the delta signal of 1-3Hz, 4-8Hz, the alpha of 8-13Hz
The gamma signal of signal, the beta signal of 14-30Hz and 30-50Hz.
Method of the invention is on the one hand available more objective compared to traditional prediction technique for interpersonal relationships
On the other hand mood evaluating result can also carry out sharper tracking, for interpersonal to the dynamic changing process of emotional state
The automatic Prediction of relationship has important application value to setting-up and development, the team building of interpersonal relationships.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention without any creative labor, may be used also for those of ordinary skill in the art
To obtain other drawings based on these drawings.
Fig. 1 is a kind of interpersonal relationships prediction technique flow chart based on mood brain electroresponse similitude of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The interpersonal relationships prediction technique based on mood brain electroresponse similitude of the present embodiment is as shown in Figure 1, comprising:
Step S1, establishes mood video database, and video material therein is used to induce the mood of measured.
Step S2, the brain that video-see in the mood video database is generated according to the experimenter of different society group
Electric signal constructs interpersonal relationships prediction model.
Step S3 obtains the real-time EEG signals that tester watches video in the mood video database.
The real-time EEG signals are applied to the interpersonal relationships prediction model, to predict the people of tester by step S4
Border relationship state of development.
The method of the present embodiment is on the one hand available more objective compared to traditional prediction technique for interpersonal relationships
Mood evaluating result, on the other hand sharper tracking can also be carried out to the dynamic changing process of emotional state, for people
The automatic Prediction of border relationship has important application value to setting-up and development, the team building of interpersonal relationships.
In the present embodiment, step S1 is specifically included:
Determine that actively (happiness, excitation, humour and tender feeling etc.), neutral and passiveness are (sad according to psychology mood category theory
Wound, it is frightened, detest and indignation etc.) mood classification.Primary election mood arouses the preferable video of effect and carries out editing and add subtitle,
To enhance the understandability of video material.It invites expert to score the mood attribute of selected audio-visual-materials, selects predetermined score
Above video is added to mood video database.
Wherein step S2 includes:
For the experimenter of different society group, the brain telecommunications in different channels is distributed in the overall process record of viewing video
Number；Under the stimulation of different type of emotion, extract EEG signals in include time domain, frequency domain and the brain in airspace electrical feature, will not
With the brain electrical feature similitude composition characteristic vector for inducing video；Collect the society of all experimenters between any two in public organization
Distance is mutually commented；The whole community network of multidimensional in group is portrayed by nominating method of formation, obtains multidimensional interpersonal relationships number
According to.By the feature vector of brain electrical feature similitude composition, social distance mutually comments and multidimensional interpersonal relationships data, in multiple dimensions
Interpersonal relationships prediction model is respectively trained in degree.The interpersonal Relationship Prediction model prototype is multivariate regression models, with society when training
Mutual comment with multidimensional interpersonal relationships data of distance is dependent variable, and the feature vector of the brain electrical feature similitude composition of experimenter is from change
Training multivariate regression models is measured, to obtain interpersonal relationships prediction model.
Corresponding mood is presented respectively to more than 100 testees from multiple and different public organizations first and induces element
Material is distributed in each testee record the EEG signals in the Different electrodes channel of Different brain region, then in different moods
Under the stimulation of type, extracting in EEG signals includes but is not limited to that time domain, frequency domain and spatial feature are interpersonal similar for calculating
Property.Delta (1-3Hz) in EEG signals, theta (4-8Hz), alpha (8-13Hz), beta (14-30Hz), gamma (30-
50Hz) etc. frequency band energies and brain electricity amplitude, phase etc. are characterized in that plan in the present invention is extracted but not limited to this feature.
Secondly, current embodiment require that collecting interpersonal relation data.On the one hand, collect public organization in all participants two-by-two
Between social distance mutually comment, using self-other people are overlapped scale social distance are mutually commented between any two to testee；It is another
Aspect, by nominating method of formation, to the whole community network (emotion network, trust network, consultation network) of multidimensional in group into
Row is portrayed, and multidimensional interpersonal relationships data are obtained.
Finally, by collect it is total be more than the EEG signals of 100 experimenters, social distance mutually comment and it is multiple it is social in
The prediction model of interpersonal relationships is respectively trained in above-mentioned multiple dimensions in the interpersonal relationships data in portion.
Specifically, feature extraction is carried out to collected different channel EEG signals, obtains every experimenter for inducing
The brain electrical feature of material.EEG signals, which go out current moment by material, be aligned and time domain superposed average, such superposed average needle
Video material under different type of emotion attributes is carried out respectively.The brain electrical feature being extracted is material under certain type of emotion
In the brain electroresponse of induction in certain special time period gained EEG signals mean value.By experimenter to the different brains for inducing material
Input of the electrical feature similitude composition characteristic vector as interpersonal relationships prediction model, the training model parameter is to establish interpersonal pass
It is prediction model.In a particular embodiment, according to the following formula 1 calculate every group of testee interpersonal relationships index:
Wherein, SiFor the Scoring Guidelines (i.e. multidimensional interpersonal relationships data) of i-th interpersonal relationships dimension of experimenter, aikTo add
Weigh combination coefficient (N is brain electrical feature number), fikFor the element in interpersonal relationships related brain electrical feature similarity feature vector.Its
In, multiple regression equation is established by dependent variable of the interpersonal relationships assessment indicator for scene of specifically testing and assessing to obtain institute by study
State weighted array coefficient.
It is that a unit is presented to the experimenter and test with the video of four sections of same type moods in step S2 and S3
Person, often finish watching a unit video will present mathematical problem (can be 8~12 mathematical problems being simply easy to do) allow experimenter and
Tester carries out judgement task and it is helped to calm down mood, so that prediction result is more acurrate.And every for constructing the experiment of model
Person and the tester for establishing model acquire 32 channel EEG signals, and sample rate is not less than 250Hz.Wherein, acquisition channel quantity
Increase can be promoted mood detection with identification accuracy rate.
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (7)
1. a kind of interpersonal relationships prediction technique based on mood brain electroresponse similitude, which is characterized in that comprising steps of
S1: mood video database is established；
S2: the EEG signals structure that video-see in the mood video database is generated according to the experimenter of different society group
Build interpersonal relationships prediction model；
S3: the real-time EEG signals that tester watches video in the mood video database are obtained；
S4: being applied to the interpersonal relationships prediction model for the real-time EEG signals, to predict the interpersonal relationships hair of tester
Exhibition situation.
2. the interpersonal relationships prediction technique as described in claim 1 based on mood brain electroresponse similitude, which is characterized in that institute
Stating step S1 includes:
Mood classification actively, neutral and passive is determined according to psychology mood category theory；
The video that target emotion is effectively aroused in primary election carries out editing and adds subtitle；
The mood attributes of selected audio-visual-materials is carried out to carry out 7 point scale scorings in each emotional dimension, select predetermined score with
On video be added to mood video database.
3. the interpersonal relationships prediction technique as described in claim 1 based on mood brain electroresponse similitude, which is characterized in that institute
Stating step S2 includes:
For the experimenter of different society group, the EEG signals in different channels are distributed in the overall process record of viewing video；
Under the stimulation of different type of emotion, extract EEG signals in include time domain, frequency domain and the brain in airspace electrical feature, will not
With the brain electrical feature similitude composition characteristic vector for inducing video；
The social distance of all experimenters between any two in public organization is collected mutually to comment；
The whole community network of multidimensional in group is portrayed by nominating method of formation, obtains multidimensional interpersonal relationships data；
By the feature vector of brain electrical feature similitude composition, social distance mutually comments and multidimensional interpersonal relationships data, multiple
Interpersonal relationships prediction model is respectively trained in dimension.
4. the interpersonal relationships prediction technique as claimed in claim 3 based on mood brain electroresponse similitude, which is characterized in that adopt
With self-other people are overlapped scale social distance are mutually commented between any two to testee.
5. the interpersonal relationships prediction technique as claimed in claim 3 based on mood brain electroresponse similitude, which is characterized in that institute
State the mean value of the gained EEG signals in special time period in the brain electroresponse that brain electrical feature induces for video under certain type of emotion.
6. the interpersonal relationships prediction technique as described in claim 1 based on mood brain electroresponse similitude, which is characterized in that
In step S2 and S3, it is that a unit is presented to the experimenter and tester with the video of four sections of same type moods, often finishes watching
The video of one unit allows experimenter and tester to carry out judgement task for mathematical problem is presented.
7. such as the interpersonal relationships prediction technique according to any one of claims 1 to 6 based on mood brain electroresponse similitude,
It is characterized in that, the EEG signals include: the theta signal of the delta signal of 1-3Hz, 4-8Hz, the alpha letter of 8-13Hz
Number, the gamma signal of the beta signal of 14-30Hz and 30-50Hz.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811622000.XA CN109920498A (en) | 2018-12-28 | 2018-12-28 | Interpersonal relationships prediction technique based on mood brain electroresponse similitude |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811622000.XA CN109920498A (en) | 2018-12-28 | 2018-12-28 | Interpersonal relationships prediction technique based on mood brain electroresponse similitude |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109920498A true CN109920498A (en) | 2019-06-21 |
Family
ID=66960113
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811622000.XA Pending CN109920498A (en) | 2018-12-28 | 2018-12-28 | Interpersonal relationships prediction technique based on mood brain electroresponse similitude |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109920498A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112203083A (en) * | 2020-09-30 | 2021-01-08 | 清华大学 | Method and device for determining quality grade of video data |
| CN112288462A (en) * | 2020-10-12 | 2021-01-29 | 中国食品发酵工业研究院有限公司 | Method for quantitatively evaluating food sensory quality and consumer preference by applying facial expression emotion recognition software and application |
| CN113205885A (en) * | 2021-02-08 | 2021-08-03 | 中国科学院心理研究所 | Interpersonal relationship quality assessment and intervention method and system for group based on go/no-go test task |
| CN113327019A (en) * | 2021-02-08 | 2021-08-31 | 中国科学院心理研究所 | Group relation quality evaluation and intervention method and system based on graph pairing task |
| CN114356095A (en) * | 2022-01-08 | 2022-04-15 | 吉林大学 | Method for objectively evaluating experience quality of touch representation device based on electroencephalogram signals |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105205317A (en) * | 2015-09-10 | 2015-12-30 | 清华大学 | Method and device for reflecting collaboration degree of at least two participants |
| CN106407733A (en) * | 2016-12-12 | 2017-02-15 | 兰州大学 | Depression risk screening system and method based on virtual reality scene electroencephalogram signal |
| CN106618561A (en) * | 2016-12-27 | 2017-05-10 | 深圳职业技术学院 | High-robustness analysis method for electroencephalogram (ECG) signal of disabled people in motion state |
| CN107348962A (en) * | 2017-06-01 | 2017-11-17 | 清华大学 | A kind of personal traits measuring method and equipment based on brain-computer interface technology |
| CN107411738A (en) * | 2017-04-18 | 2017-12-01 | 天津大学 | A kind of mood based on resting electroencephalogramidentification similitude is across individual discrimination method |
| CN108881985A (en) * | 2018-07-18 | 2018-11-23 | 南京邮电大学 | Program points-scoring system based on brain electricity Emotion identification |
-
2018
- 2018-12-28 CN CN201811622000.XA patent/CN109920498A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105205317A (en) * | 2015-09-10 | 2015-12-30 | 清华大学 | Method and device for reflecting collaboration degree of at least two participants |
| CN106407733A (en) * | 2016-12-12 | 2017-02-15 | 兰州大学 | Depression risk screening system and method based on virtual reality scene electroencephalogram signal |
| CN106618561A (en) * | 2016-12-27 | 2017-05-10 | 深圳职业技术学院 | High-robustness analysis method for electroencephalogram (ECG) signal of disabled people in motion state |
| CN107411738A (en) * | 2017-04-18 | 2017-12-01 | 天津大学 | A kind of mood based on resting electroencephalogramidentification similitude is across individual discrimination method |
| CN107348962A (en) * | 2017-06-01 | 2017-11-17 | 清华大学 | A kind of personal traits measuring method and equipment based on brain-computer interface technology |
| CN108881985A (en) * | 2018-07-18 | 2018-11-23 | 南京邮电大学 | Program points-scoring system based on brain electricity Emotion identification |
Non-Patent Citations (3)
| Title |
|---|
| YUE DING ET AL: "《inter-brain EEG feature extraction and analysis for continuous implicit emotion tagging during video watching》", 《IEEE TRANSACTION ON AFFECTIVE COMPUTING》 * |
| 刘爽等: "《脑电时间效应对情绪识别模型的影响及解决措施研究》", 《中国生物医学工程学报》 * |
| 白芷嫣等: "《基于脑电信号的抑郁情绪倾向研究》", 《北京生物医学工程》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112203083A (en) * | 2020-09-30 | 2021-01-08 | 清华大学 | Method and device for determining quality grade of video data |
| CN112288462A (en) * | 2020-10-12 | 2021-01-29 | 中国食品发酵工业研究院有限公司 | Method for quantitatively evaluating food sensory quality and consumer preference by applying facial expression emotion recognition software and application |
| CN113205885A (en) * | 2021-02-08 | 2021-08-03 | 中国科学院心理研究所 | Interpersonal relationship quality assessment and intervention method and system for group based on go/no-go test task |
| CN113327019A (en) * | 2021-02-08 | 2021-08-31 | 中国科学院心理研究所 | Group relation quality evaluation and intervention method and system based on graph pairing task |
| CN113327019B (en) * | 2021-02-08 | 2023-06-09 | 中国科学院心理研究所 | Group relation quality evaluation and intervention method and system based on graph pairing task |
| CN113205885B (en) * | 2021-02-08 | 2023-06-16 | 中国科学院心理研究所 | Inter-group interpersonal relationship quality assessment and intervention method and system based on go/no-go test task |
| CN114356095A (en) * | 2022-01-08 | 2022-04-15 | 吉林大学 | Method for objectively evaluating experience quality of touch representation device based on electroencephalogram signals |
| CN114356095B (en) * | 2022-01-08 | 2023-07-21 | 吉林大学 | Objective evaluation method for experience quality of touch reproduction device based on electroencephalogram signals |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109920498A (en) | Interpersonal relationships prediction technique based on mood brain electroresponse similitude | |
| Shoval et al. | Real-time measurement of tourists’ objective and subjective emotions in time and space | |
| CN104361356B (en) | A kind of film audient experience evaluation method based on man-machine interaction | |
| CN109567830B (en) | Personality measuring method and system based on neural response | |
| CN108056774A (en) | Experimental paradigm mood analysis implementation method and its device based on visual transmission material | |
| CN108052973B (en) | Map symbol user interest analysis method based on multiple items of eye movement data | |
| CN107348962B (en) | A kind of personal traits measurement method and equipment based on brain-computer interface technology | |
| Hargreaves et al. | The neural correlates of the body-object interaction effect in semantic processing | |
| CN104983435A (en) | Stimulus information establishing method for interest orientation value test | |
| EP3474743B1 (en) | Method and system for detection and analysis of cognitive flow | |
| Yu et al. | A hybrid user experience evaluation method for mobile games | |
| Manjrekar et al. | Exploring the utility of emotional awareness and negative affect in predicting body satisfaction and body distortion | |
| CN108324292A (en) | Visual Environment Analysis of Satisfaction method based on EEG signals | |
| Chew et al. | A neurocomputational model for intrinsic reward | |
| Kim | Real-time bio-signal-processing of students based on an intelligent algorithm for Internet of Things to assess engagement levels in a classroom | |
| CN110432915A (en) | A kind of method and device for assessing information flow intention | |
| Niu et al. | User experience evaluation in virtual reality based on subjective feelings and physiological signals | |
| de León et al. | Modeling active aging and explicit memory: An empirical study | |
| Masui et al. | Measurement of advertisement effect based on multimodal emotional responses considering personality | |
| Kapsetaki et al. | Type of encoded material and age modulate the relationship between episodic recall of visual perspective and autobiographical memory | |
| Holman et al. | Taking the Subjectivity out of UX Evaluation with Emotiv EPOC+ | |
| Lee et al. | From knowing the game to enjoying the game: EEG/ERP assessment of emotional processing | |
| Vom Brocke et al. | Neuroscience in design-oriented research: exploring new potentials | |
| Kopton et al. | Users' trust building processes during their initial connecting behavior in social networks: Behavioral and neural evidence | |
| Güngör | The Relationship between Attitudes towards Learning and Success Orientation in Undergraduate Students. |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190621 |