CN108921199A - Eye based on object table symptom state pays close attention to preference prediction technique - Google Patents
Eye based on object table symptom state pays close attention to preference prediction technique Download PDFInfo
- Publication number
- CN108921199A CN108921199A CN201810597488.9A CN201810597488A CN108921199A CN 108921199 A CN108921199 A CN 108921199A CN 201810597488 A CN201810597488 A CN 201810597488A CN 108921199 A CN108921199 A CN 108921199A
- Authority
- CN
- China
- Prior art keywords
- eye
- state
- user
- preference
- close attention
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/013—Eye tracking input arrangements
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Computer Interaction (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention is based on the eyes of object table symptom state to pay close attention to preference prediction technique, it is propagated by using label, tri- kinds of machine learning classification algorithms of decision tree and SVM learn the relevance of eye movement state characterization state different from two-dimensional screen, building pays close attention to preference prediction model for eye of the different people to different characterization state objects, after obtaining the object table sign status data that eye of the user on two-dimensional screen is absorbed in point coordinate data and two-dimensional screen, preference prediction model is paid close attention to using eye to predict the concern preference of user, and combine real time environment information locating for user, the behavior trend of user is predicted and analyzed with preference trend.
Description
Technical field
The present invention relates to a kind of, and the eye based on object table symptom state pays close attention to preference prediction technique.
Background technique
Currently, it is latent to possess very big development also in the stage of an opposing primary with the research of eye movement intercorrelation
Power.Existing application method relevant to eye movement has the following defects：
1, acquisition and the statistical analysis of data are confined to；
2, the situation not systematically by the eye movement behavior of people locating for it combines；
3, lack the analysis and description to user context cognitive state；
4, the model analysis for well not abstracting the eye movement mode of people.
Therefore, the information that eye motion state is contained also needs more in depth to be analyzed and excavated.
Summary of the invention
The purpose of the present invention is to provide a kind of, and the eye based on object table symptom state pays close attention to preference prediction technique, and analysis is not
Preference is paid close attention to for the eye of different characterization state objects with people, is closed by acquiring and demarcating training data, generate eye
Preference prediction model is infused, and context information is combined to predict user behavior trend, it is final to analyze user cognition state.
The present invention is based on the eyes of object table symptom state to pay close attention to preference prediction technique, is propagated by using label, decision tree
And tri- kinds of machine learning classification algorithms of SVM learn the relevance of eye movement state characterization state different from two-dimensional screen,
Building pays close attention to preference prediction model for eye of the different people to different characterization state objects, is obtaining user on two-dimensional screen
Eye be absorbed in point coordinate data and two-dimensional screen on object table sign status data after, utilize eye pay close attention to preference prediction model
It predicts the concern preference of user, and combines real time environment information locating for user, to the behavior trend and preference of user
Trend is predicted and is analyzed.
Specifically comprise the following steps：
The eye movement state of step 1, acquisition different people in the object of characterization states different on observing two-dimensional screen, to eye movement
Status data is demarcated according to the different characterization states of above-mentioned object；The object table symptom state includes shape, color, movement class
Type, the eye movement status data include blinkpunkt coordinate of the user on two-dimensional screen, object coordinates and use on two-dimensional screen
The concern state at family；
Step 2 is propagated, decision tree and tri- kinds of SVM using the characterization state of the object shown on two-dimensional screen as label
The input feature vector of machine learning classification algorithm, by the concern state of user and the characterization state for being concerned object collectively as instruction
Experienced prediction label is put into machine learning classification algorithm, trains different people and the eye of different characterization state objects is closed
Preference prediction model is infused, for predicting that different people pays close attention to preference to the eye of different characterization state objects；
Step 3 acquires user in the eye movement data for the object for observing different characterization states, in conjunction with the characterization for being concerned object
State pays close attention to preference prediction model, concern preference of the prediction user for the observed object by eye；
Step 4, the eye pay close attention to preference prediction model combination real time environment information, carry out to the behavior trend of user pre-
It surveys, thus the preference trend based on eye movement interaction prediction user.
The present invention is using machine learning classification algorithm training and constructs different people for the object of different characterization states
Eye pays close attention to preference prediction model, pays close attention to preference prediction model by the eye, to predict different people to possessing different characterization shapes
The eye of the object of state pays close attention to preference state, and is combined according to prediction result contextual information locating for people to predict people's
Behavior trend, thus the preference trend based on eye movement interaction prediction user.
Detailed description of the invention
Fig. 1 is the working principle of the invention schematic diagram.
The present invention is further described below in conjunction with the drawings and specific embodiments.
Specific embodiment
The present invention is based on the eyes of object table symptom state to pay close attention to preference prediction technique, by obtaining user on two-dimensional screen
Eye concern state in conjunction with the object table symptom state (shape, color, motion state) on two-dimensional screen utilize machine learning
Classification algorithm training characteristic relevant to user's eye concern state, constructs different people to different characterization state objects
Eye pays close attention to preference prediction model, and combines contextual information locating for user, and the behavior trend and preference trend to user carry out
Prediction and analysis, as shown in Figure 1, including the following steps：
The eye movement state of step 1, acquisition different people in the object of characterization states different on observing two-dimensional screen, to eye movement
Status data is demarcated according to the different characterization states of above-mentioned object；The object table symptom state includes shape, color, movement class
Type, the eye movement status data include blinkpunkt coordinate of the user on two-dimensional screen, object coordinates and use on two-dimensional screen
The concern state at family；
Step 2 is propagated, decision tree and tri- kinds of SVM using the characterization state of the object shown on two-dimensional screen as label
The input feature vector of machine learning classification algorithm, by the concern state of user and the characterization state for being concerned object collectively as instruction
Experienced prediction label is put into machine learning classification algorithm, trains different people and the eye of different characterization state objects is closed
Preference prediction model is infused, for predicting that different people pays close attention to preference to the eye of different characterization state objects；
Step 3 acquires user in the eye movement data for the object for observing different characterization states, in conjunction with the characterization for being concerned object
State pays close attention to preference prediction model, concern preference of the prediction user for the observed object by eye；
Step 4, the eye pay close attention to preference prediction model combination real time environment information, carry out to the behavior trend of user pre-
It surveys, thus the preference trend based on eye movement interaction prediction user, the prediction result of above-mentioned user behavior trend be can be applied to respectively
In the different interactive media of kind.
The above is only present pre-ferred embodiments, is not intended to limit the scope of the present invention, therefore
Any subtle modifications, equivalent variations and modifications to the above embodiments according to the technical essence of the invention, still belong to
In the range of technical solution of the present invention.
Claims (2)
1. the eye based on object table symptom state pays close attention to preference prediction technique, it is characterised in that：It is propagated by using label, decision
Tree and tri- kinds of machine learning classification algorithms of SVM learn the association of eye movement state characterization state different from two-dimensional screen
Property, building is paid close attention to preference prediction model for eye of the different people to different characterization state objects, is shielded obtaining user in two dimension
After eye on curtain is absorbed in the object table sign status data in point coordinate data and two-dimensional screen, predicted using eye concern preference
Model predicts the concern preference of user, and combines real time environment information locating for user, to the behavior trend of user with
Preference trend is predicted and is analyzed.
2. the eye according to claim 1 based on object table symptom state pays close attention to preference prediction technique, it is characterised in that packet
Include following steps：
The eye movement state of step 1, acquisition different people in the object of characterization states different on observing two-dimensional screen, to eye movement state
Data are demarcated according to the different characterization states of above-mentioned object；The object table symptom state includes shape, color, type of sports,
The eye movement status data includes blinkpunkt coordinate of the user on two-dimensional screen, the object coordinates on two-dimensional screen and user
Concern state；
Step 2 is propagated, tri- kinds of machines of decision tree and SVM using the characterization state of the object shown on two-dimensional screen as label
The input feature vector of learning classification algorithm, by the concern state of user and the characterization state for being concerned object collectively as trained
Prediction label is put into machine learning classification algorithm, trains different people and the eye of different characterization state objects is paid close attention to partially
Good prediction model, for predicting that different people pays close attention to preference to the eye of different characterization state objects；
Step 3 acquires user in the eye movement data for the object for observing different characterization states, in conjunction with the characterization shape for being concerned object
State pays close attention to preference prediction model, concern preference of the prediction user for the observed object by eye；
Step 4, the eye pay close attention to preference prediction model combination real time environment information, predict the behavior trend of user, from
And the preference trend based on eye movement interaction prediction user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810597488.9A CN108921199A (en) | 2018-06-11 | 2018-06-11 | Eye based on object table symptom state pays close attention to preference prediction technique |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810597488.9A CN108921199A (en) | 2018-06-11 | 2018-06-11 | Eye based on object table symptom state pays close attention to preference prediction technique |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108921199A true CN108921199A (en) | 2018-11-30 |
Family
ID=64409814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810597488.9A Pending CN108921199A (en) | 2018-06-11 | 2018-06-11 | Eye based on object table symptom state pays close attention to preference prediction technique |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108921199A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109960892A (en) * | 2019-04-04 | 2019-07-02 | 北京理工大学 | A kind of CAD instruction generation method and system based on eye movement signal |
| US20220236794A1 (en) * | 2016-11-10 | 2022-07-28 | Neurotrack Technologies, Inc. | Method and system for correlating an image capturing device to a human user for analyzing gaze information associated with cognitive performance |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130097011A1 (en) * | 2011-10-14 | 2013-04-18 | Microsoft Corporation | Online Advertisement Perception Prediction |
| CN103324287A (en) * | 2013-06-09 | 2013-09-25 | 浙江大学 | Computer-assisted sketch drawing method and system based on eye movement and brush stroke data |
| CN104504390A (en) * | 2015-01-14 | 2015-04-08 | 北京工业大学 | On-line user state recognition method and device based on eye movement data |
| CN106920129A (en) * | 2017-03-09 | 2017-07-04 | 山东师范大学 | A kind of network advertisement effect evaluation system and its method that tracking is moved based on eye |
| CN107562202A (en) * | 2017-09-14 | 2018-01-09 | 中国石油大学(北京) | The recognition methods of process operator's human error and device based on Eye-controlling focus |
-
2018
- 2018-06-11 CN CN201810597488.9A patent/CN108921199A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130097011A1 (en) * | 2011-10-14 | 2013-04-18 | Microsoft Corporation | Online Advertisement Perception Prediction |
| CN103324287A (en) * | 2013-06-09 | 2013-09-25 | 浙江大学 | Computer-assisted sketch drawing method and system based on eye movement and brush stroke data |
| CN104504390A (en) * | 2015-01-14 | 2015-04-08 | 北京工业大学 | On-line user state recognition method and device based on eye movement data |
| CN106920129A (en) * | 2017-03-09 | 2017-07-04 | 山东师范大学 | A kind of network advertisement effect evaluation system and its method that tracking is moved based on eye |
| CN107562202A (en) * | 2017-09-14 | 2018-01-09 | 中国石油大学(北京) | The recognition methods of process operator's human error and device based on Eye-controlling focus |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220236794A1 (en) * | 2016-11-10 | 2022-07-28 | Neurotrack Technologies, Inc. | Method and system for correlating an image capturing device to a human user for analyzing gaze information associated with cognitive performance |
| CN109960892A (en) * | 2019-04-04 | 2019-07-02 | 北京理工大学 | A kind of CAD instruction generation method and system based on eye movement signal |
| CN109960892B (en) * | 2019-04-04 | 2020-09-01 | 北京理工大学 | CAD instruction generation method and system based on eye movement signal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang et al. | Evaluating explanation without ground truth in interpretable machine learning | |
| Bearman et al. | What’s the point: Semantic segmentation with point supervision | |
| Guzdial et al. | An interaction framework for studying co-creative ai | |
| CN105264528A (en) | Client intent in integrated search environment | |
| US20180101391A1 (en) | System for co-adaptive human-computer interaction | |
| Wall et al. | A formative study of interactive bias metrics in visual analytics using anchoring bias | |
| Gu et al. | Seer: Language instructed video prediction with latent diffusion models | |
| CN108921199A (en) | Eye based on object table symptom state pays close attention to preference prediction technique | |
| McNeese et al. | Stepping out of the shadow of human-human teaming: Crafting a unique identity for human-autonomy teams | |
| Zhou et al. | 2D transparency space—bring domain users and machine learning experts together | |
| Coccoli et al. | Adopting cognitive computing solutions in healthcare | |
| Oliveira et al. | Progress in Artificial Intelligence: 19th EPIA Conference on Artificial Intelligence, EPIA 2019, Vila Real, Portugal, September 3–6, 2019, Proceedings, Part II | |
| CN116740238A (en) | Personalized configuration method, device, electronic equipment and storage medium | |
| Boschetti et al. | Interactive modelling for natural resource management | |
| Morera | Foundation Models in shaping the future of ecology | |
| Alevizos et al. | Evaluating the Inclusiveness of Artificial Intelligence Software in Enhancing Project Management Efficiency--A Review | |
| Sokol et al. | LIMEtree: Consistent and faithful surrogate explanations of multiple classes | |
| CN108985164A (en) | Eye based on object moving state pays close attention to prediction technique | |
| Moran et al. | Bridging the analytical gap between distributed cognition and actor network theory using a tool for information trajectory analysis | |
| Rodrigues | Interactive intelligent tools for creative processes using multimodal information | |
| Bird et al. | Past, present, and future of analyzing software data | |
| CN103778642B (en) | Object tracking method and apparatus | |
| Rowson et al. | Knowledge capture and reuse through expert’s activity monitoring in engineering design | |
| Raschke et al. | Cognitive ergonomics in visualization | |
| Wang | Applications of Machine Learning to Form-giving in Industrial Design |
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: 20181130 |