Eye tracking system, eye tracking method, and eye tracking program

Patent metadata

Field	Value
Publication number	US-12554324-B2
Application number	US-202419001237-A
Country	US
Kind code	B2
Filing date	Dec 24, 2024
Priority date	Sep 30, 2020
Publication date	Feb 17, 2026
Grant date	Feb 17, 2026

Abstract

An eye tracking system according to one embodiment includes at least one processor. The at least one processor is configured to: dynamically set a partial area of first content displayed on a screen as a guidance area to have a user gaze at the partial area; identify first viewpoint coordinates on the screen based on an eye movement of the user gazing at the guidance area; calculate a difference between the first viewpoint coordinates identified and area coordinates of the guidance area on the screen; and calibrate second viewpoint coordinates of the user viewing second content displayed on the screen by using the difference.

First claim

The invention claimed is:

1 . A system, comprising at least one processor configured to:
dynamically set a partial area of a first content displayed on a screen as a guidance area to have a user gaze at the partial area; identify first viewpoint coordinates on the screen based on an eye movement of the user gazing at the guidance area; calculate a difference between the first viewpoint coordinates and area coordinates of the guidance area on the screen; identify second viewpoint coordinates of the user viewing a second content displayed on the screen; calibrate the second viewpoint coordinates by using the difference; obtain the calibrated second viewpoint coordinates at each given time interval and generate viewpoint data that indicate movement of a user viewpoint; estimate a user understanding level based on the viewpoint data and correlation data, wherein the correlation data indicate correlation between the user viewpoint movement and the user understanding level, the correlation data is generated based on sample data in advance, and the sample data indicates a pair of a movement of a sample user viewpoint on a sample content and an understating level of the sample user for the sample content; and output assist information corresponding to the estimated user understanding level.

2 . The system according to claim 1 , wherein the assist information includes information for promoting the user understanding of the content.

3 . The system according to claim 1 , wherein the correlation data is generated by statistical processing on the sample data acquired in advance.

4 . The system according to claim 1 , wherein the at least one processor is configured to cluster a plurality of sets of sample data based on the viewpoint movement of the sample user and the user understanding level for the sample content to generate the correlation data.

5 . The system according to claim 4 , wherein the at least one processor is configured to estimate the user understanding level indicated by a cluster to which the user understanding level belongs.

6 . The system according to claim 1 , wherein the at least one processor is further configured to determine similarity of understanding level of content based on at least one of an understanding level of a meaning of a word or an understanding level of a grammar of a sentence.

7 . The system according to claim 1 , wherein the at least one processor is further configured to derive the correlation between the user viewpoint movement and the user understanding level from clustering results.

8 . The system according to claim 7 , wherein the correlation indicates a pair of a user viewpoint movement tendency and the user understanding level corresponding to the user viewpoint movement tendency.

9 . The system according to claim 1 , wherein the at least one processor is further configured to:
generalize the correlation data; and estimate the user understanding level based on the generalized correlation data.

10 . The system according to claim 1 , wherein the at least one processor is configured to select the sample data for statistical processing to generate the correlation data of a plurality of types.

11 . The system according to claim 1 , wherein the at least one processor is configured to, for each sample content of a plurality of sample contents, generate the correlation data as content-specific correlation data by using the sample data obtained from a plurality of sample users viewing the plurality of sample contents.

12 . The system according to claim 1 , wherein the at least one processor is configured to generate the correlation data as generalized correlation data by using the sample data from a plurality of sample contents, the generalized correlation data common to a plurality of contents.

13 . The system according to claim 1 , wherein the assist information include information that can compensate for a part of the content that lacks the user understanding.

14 . The system according to claim 1 , wherein the at least one processor causes a user terminal to display the assist information along with the content.

15 . The system according to claim 1 , wherein the correlation data includes the user understanding level indicating at least one of lack of vocabulary, lack of grammatical competence, or lack of background of a scene of the content, associated with the corresponding user viewpoint movement, and
the at least one processor estimates the user understating level based on the correlation data, and outputs the assist information related to the at least one of lack of vocabulary, lack of grammatical competence, or lack of background of a scene of the content.

16 . The system according to claim 1 , wherein
the correlation data includes the user understanding level indicating lack of vocabulary associated with the corresponding user viewpoint movement, and the at least one processor estimates the user understating level indicating the lack of vocabulary based on the correlation data, and outputs the assist information related to vocabulary.

17 . The system according to claim 1 , wherein
the correlation data include the user understanding level indicating lack of grammatical competence associated with the corresponding user viewpoint movement, and the at least one processor estimates the user understating level indicating the lack of grammatical competence based on the correlation data, and outputs the assist information related to the grammar.

18 . The system according to claim 1 , wherein
the correlation data include the user understanding level indicating lack of background of a scene of the content associated with the corresponding user viewpoint movement, and the at least one processor estimates the user understating level indicating the lack of background of the scene of the content based on the correlation data, and outputs the assist information related to the background of the scene.

19 . A non-transitory computer-readable medium storing thereon a program that, when executed, causes a computer to:
dynamically set a partial area of a first content displayed on a screen as a guidance area to have a user gaze at the partial area; identify first viewpoint coordinates on the screen based on an eye movement of the user gazing at the guidance area; calculate a difference between the first viewpoint coordinates and area coordinates of the guidance area on the screen; identify second viewpoint coordinates of the user viewing a second content displayed on the screen; calibrate the second viewpoint coordinates by using the difference; obtain the calibrated second viewpoint coordinates at each given time interval and generate viewpoint data that indicate movement of a user viewpoint; estimate a user understanding level based on the viewpoint data and correlation data, wherein the correlation data indicate correlation between the user viewpoint movement and the user understanding level, the correlation data is generated based on sample data in advance, and the sample data indicates a pair of a movement of a sample user viewpoint on a sample content and an understating level of the sample user for the sample content; and output assist information corresponding to the estimated user understanding level.

20 . An assist method executable by an assist system comprising at least one processor, the method comprising:
dynamically setting a partial area of a first content displayed on a screen as a guidance area to have a user gaze at t

Assignees

• Dwango Co Ltd

Inventors

• Kawakami Nobuo
• Odagiri Yuri

Classifications

• A61B3/113

  for determining or recording eye movement · CPC title

• G06F3/01

  Input arrangements or combined input and output arrangements for interaction between user and computer (G06F3/16 takes precedence) · CPC title

• G06F3/013 Primary

  Eye tracking input arrangements (G06F3/015 takes precedence) · CPC title