Evaluation device, evaluation system, evaluation method, and program

Abstract

To provide an evaluation device, an evaluation system, an evaluation method, and a program allowing for appropriately evaluating the quality of a review of an outcome of system development.SOLUTION: An evaluation device 10 comprises: an acquiring section 11 that acquires eye-tracking data indicative of a result of tracking a gazing point of a user who reviews a review object; a stay-time calculating section 12 that calculates a time period in which the gazing point has stayed in each of a plurality of evaluation segments included in the review object; and a determining section 13 that determines whether the time period is equal to or longer than a reference time set for each evaluation segment.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an evaluation device, an evaluation system, an evaluation method, and a program, and more particularly to a technique for evaluating review quality. [Background technology]

[0002] Patent Document 1 describes a review evaluation system that evaluates the quality of reviews in projects to develop software, etc. The technology described in Patent Document 1 makes it possible to evaluate review quality by taking into account the skills of the reviewer and the reviewers.

[0003] Furthermore, Patent Document 2 describes a close reading determination device that can determine whether a user has carefully read an electronic document. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2013-033391

[0005] [Patent Document 2] Japanese Patent Application Laid-Open No. 2015-032274 Summary of the Invention [Problem to be solved by the invention]

[0006] The complexity of each part of a system development deliverable varies, and it is not necessarily read line by line in order. Therefore, it is difficult to properly evaluate the quality of a system development deliverable review. [Means for solving the problem]

[0007] In view of the above-mentioned problems, an object of the present disclosure is to provide an evaluation device, an evaluation system, an evaluation method, and a program that can appropriately evaluate the quality of reviews of system development deliverables.

[0008] The evaluation device according to the present disclosure includes: an acquisition unit that acquires eye tracking data indicating the results of tracking the gaze points of users reviewing a review target; a dwell time calculation unit that calculates a time period during which the gaze point stays on each of a plurality of evaluation segments included in the review target; and a determination unit that determines whether the time period is equal to or greater than a reference time set for each evaluation segment.

[0009] The evaluation system according to the present disclosure includes: an eye tracking device that tracks the gaze point of a user reviewing a review object; an evaluation device; Equipped with The evaluation device acquiring eye tracking data indicating the results of tracking the gaze point; calculating a time period during which the gaze point stayed on each of a plurality of evaluation segments included in the review object; It is determined whether the time period is equal to or greater than a reference time set for each evaluation segment.

[0010] The evaluation method according to the present disclosure includes: The computer Obtaining eye tracking data showing the results of tracking the gaze points of users reviewing the review subject; calculating a time period during which the gaze point stayed on each of a plurality of evaluation segments included in the review object; It is determined whether the time period is equal to or greater than a reference time set for each evaluation segment.

[0011] The program according to the present disclosure is On the computer, acquiring eye tracking data indicating the results of tracking the gaze points of users reviewing the review object; A process of calculating a time period during which the gaze point stayed on each of a plurality of evaluation segments included in the review object; A process of determining whether the time period is equal to or greater than a reference time set for each evaluation segment; This is what causes the following to be executed. [Effects of the Invention]

[0012] The evaluation device, evaluation system, evaluation method, and program according to the present disclosure can appropriately evaluate the quality of reviews of system development deliverables. [Brief explanation of the drawings]

[0013] [Figure 1] FIG. 1 is a block diagram showing the configuration of an evaluation device according to a first embodiment. [Figure 2] FIG. 10 is a block diagram showing the configuration of an evaluation system according to a second embodiment. [Figure 3] FIG. 10 is a block diagram showing the configuration of a review evaluation device according to a second embodiment. [Figure 4] Schematic showing eye tracking data. [Figure 5] FIG. 1 is a schematic diagram showing evaluation segment data. [Figure 6] FIG. 10 is a schematic diagram showing evaluation criteria data. [Figure 7] FIG. 10 is a schematic diagram showing evaluation result data. [Figure 8] Schematic diagram illustrating review objects and evaluation segments. [Figure 9] Schematic diagram illustrating review objects and evaluation segments. [Figure 10] Schematic diagram illustrating review objects and evaluation segments. DETAILED DESCRIPTION OF THE INVENTION

[0014] Embodiment 1 Hereinafter, embodiments of the present invention will be described with reference to the drawings. Fig. 1 is a block diagram showing the configuration of an evaluation device 10 according to the first embodiment. The evaluation device 10 includes an acquisition unit 11, a dwell time calculation unit 12, and a determination unit 13. The evaluation device 10 may be connected to a display device that displays the review target or an eye-tracking device that collects eye-tracking data of users.

[0015] The acquisition unit 11 acquires eye tracking data indicating the results of tracking the gaze point of a user reviewing a review object. The gaze point is the intersection point between a person's line of sight and the object being viewed. The eye tracking data may be data that associates the user's gaze point coordinates with the time period during which the gaze point coordinates remain at the same coordinates (hereinafter also referred to as "dwell time"). The review object may be, for example, a design document, a program, a GUI (Graphical User Interface) screen, etc.

[0016] The dwell time calculation unit 12 calculates the time period (hereinafter also referred to as dwell time) during which the user's gaze point stays on each of the multiple evaluation segments included in the review target. The multiple evaluation segments may be generated by dividing the review target. A reference time, which will be described later, is set for each evaluation segment.

[0017] The determination unit 13 determines whether the time period calculated by the retention time calculation unit 12 is equal to or greater than a reference time set for each evaluation segment. For example, the reference time is set according to the complexity of the function included in each evaluation segment.

[0018] The evaluation device 10 determines whether the time period during which the gaze point stays in each evaluation segment is equal to or longer than a reference time, thereby making it possible to appropriately evaluate the quality of reviews of deliverables whose parts differ in complexity.

[0019] The rating device 10 may include an rating unit (not shown) that evaluates review quality based on the judgment results of the judgment unit 13. The rating unit may evaluate the review quality as high if the judgment results of all rating segments are positive, and may evaluate the review quality as low if not. The rating unit may also evaluate the review quality according to the number of positive judgment results.

[0020] The evaluation device 10 includes a processor, a memory, and a storage device (not shown). The storage device stores a computer program that implements the processing of the evaluation method according to the first embodiment. The processor then loads the computer program from the storage device into the memory and executes the computer program. As a result, the processor realizes the functions of an acquisition unit 11, a residence time calculation unit 12, and a determination unit 13.

[0021] Alternatively, the acquisition unit 11, the residence time calculation unit 12, and the determination unit 13 may each be realized by dedicated hardware. Furthermore, some or all of the components of each device may be realized by general-purpose or dedicated circuits, processors, etc., or a combination of these. These may be configured by a single chip, or by multiple chips connected via a bus. Some or all of the components of each device may be realized by a combination of the above-mentioned circuits, etc., and programs. Furthermore, a CPU (Central Processing Unit), GPU (Graphics Processing Unit), FPGA (Field-Programmable Gate Array), quantum processor (quantum computer control chip), etc., may be used as the processor.

[0022] Furthermore, when some or all of the components of the evaluation device 10 are realized by multiple information processing devices, circuits, etc., the multiple information processing devices, circuits, etc. may be centrally or distributed. For example, the information processing devices, circuits, etc. may be realized as a client-server system, a cloud computing system, etc., in which each device is connected via a communication network. Furthermore, the functions of the evaluation device 10 may be provided in a SaaS (Software as a Service) format.

[0023] Embodiment 2 FIG. 2 is a block diagram showing the configuration of an evaluation system 1000 according to a second embodiment. The evaluation system 1000 is a system that evaluates the quality of a review of a system development deliverable. The review target refers to a deliverable of software development and similar system development. Specifically, the review target includes an external design document, an internal design document, source code of software or IaC (Infrastructure as Code), a GUI screen, etc.

[0024] The rating system 1000 includes an eye tracking device 100, a review rating result display device 200, and a review rating apparatus 300.

[0025] The eye tracking device 100 tracks the user's gaze point for each frame and outputs the tracking result to the review evaluation device 300. A user refers to a person who reviews a review subject. A user is also called a reviewer. The eye tracking device 100 may be a wearable device such as glasses or a headset, or may be a device integrated with a display.

[0026] The eye tracking device 100 may generate eye tracking data in which the user's gaze point coordinates are associated with the time period during which the gaze point coordinates remain at the same coordinates (also referred to as dwell time), and output the data to the review evaluation device 300. The gaze point coordinates are also referred to as line of sight coordinates. The review evaluation device 300, which will be described later, may also generate eye tracking data in which the gaze point coordinates are associated with the dwell time. Specific examples of eye tracking data will be described later.

[0027] The review evaluation result display device 200 displays the judgment result (also referred to as evaluation result data) by the review evaluation device 300, which will be described later. The review evaluation result display device 200 is a display device such as a display. The judgment result means whether the review quality for each evaluation segment is good or bad.

[0028] The rating system 1000 may also include a display device (not shown) that displays the review subject. In this case, the user reviews the review subject displayed on the display device. The display device may be a normal display or a head-mounted display.

[0029] 3 is a block diagram showing the configuration of the review evaluation device 300. The review evaluation device 300 is a specific example of the above-mentioned evaluation device 10. The review evaluation device 300 includes a management unit 310 and a review evaluation unit 320.

[0030] The management unit 310 includes a memory for storing eye-tracking data, the display position range of each evaluation segment (also referred to as evaluation segment data), and the time period during which the gaze point should remain on each evaluation segment (also referred to as evaluation criterion data). The management unit 310 may further manage evaluation result data. The data managed by the management unit 310 (e.g., eye-tracking data) may be acquired from the eye-tracking device 100. The data managed by the management unit 310 (e.g., evaluation criterion data) may also be acquired from an external system or an input device (not shown). The management unit 310 includes an eye-tracking data management unit 311, an evaluation segment data management unit 312, and an evaluation criterion data management unit 313.

[0031] The eye-tracking data management unit 311 is a specific example of the above-mentioned acquisition unit 11. The eye-tracking data management unit 311 manages eye-tracking data. The eye-tracking data is data that associates the user's gaze point coordinates with the time period during which the gaze point coordinates remain at the same coordinates (also referred to as a dwell time).

[0032] 4 is a schematic diagram showing an example of eye tracking data. The eye tracking data 20 includes a gaze point x coordinate 21, a gaze point y coordinate 22, and a dwell time 23 (unit: milliseconds). The gaze point x coordinate 21 and the gaze point y coordinate 22 are gaze point coordinates on the user's field of view image displayed on the eye tracking device 100.

[0033] Returning to FIG. 3, the explanation will be continued. The evaluation segment data management unit 312 manages the display position range (also referred to as evaluation segment data) for each evaluation segment. Multiple evaluation segments are generated by dividing the review subject. The division method is set appropriately depending on the review subject. A specific method for setting evaluation segments will be described later.

[0034] 5 is a schematic diagram illustrating an example of rating segment data. The rating segment data 30 includes a rating segment identifier 31 (e.g., A, B, C), a rating segment x coordinate 32, and a rating segment y coordinate 33. The rating segment x coordinate 32 indicates the range of the x coordinate of each rating segment, and the rating segment y coordinate 33 indicates the range of the y coordinate of each rating segment. The review rating unit 320, which will be described later, calculates the time period during which the user's gaze point stays on each rating segment based on the display position range of each rating segment. The sum of the time periods during which the gaze point stays on the range of each rating segment is also referred to as the rating segment stay time.

[0035] Note that FIG. 5 shows evaluation segments when the review object (for example, a display screen on a web browser) fits on one screen. On the other hand, when the review object is a design document, source code, user manual, or the like, the review object is made up of multiple pages. In such cases, the second embodiment can be applied by appropriately dividing the eye tracking data and setting the evaluation segments. As will be described later, in the second embodiment, the review evaluation is performed based on how long the gaze point remains on the evaluation segment of the object. Therefore, when the object has multiple pages, the evaluation segments are set and the gaze point coordinates and dwell time are collected for each page. Then, by processing a single page multiple times, the review of the review object made up of multiple pages can be evaluated.

[0036] Furthermore, the evaluation segment x coordinate 32 and the evaluation segment y coordinate 33 may be updated in response to scrolling of the screen. In such a case, the review evaluation device 300 may include a tracking unit (not shown) that tracks the position of a characteristic part included in the review object using a camera or the like. Japanese Patent Application Laid-Open Publication No. 2017-102708, for example, is known as a technology that enables tracking of object coordinates by video analysis. This makes it possible to track the coordinates of the evaluation segment based on image features even when the review object is switched by scrolling the screen, i.e., even when the coordinates of the evaluation segment change. This makes it possible to determine whether the gaze point coordinates are present in the evaluation segment.

[0037] When the tracking unit tracks a feature portion, for example, a part of a program is highlighted as the feature portion. The tracking unit tracks the feature portion using color features. Note that tracking may be performed using shape features of objects or symbols, or may be performed using both shape features and color features. The evaluation segment data management unit 312 then updates the display position range of each evaluation segment based on its relative position with respect to the feature portion. This allows the review evaluation unit 320, described later, to calculate the period of time the gaze point stays on each evaluation segment based on the tracking results of the tracking unit, even when the user scrolls the screen.

[0038] Continuing the explanation, returning to Fig. 3, the evaluation criterion data management unit 313 manages the time period (also referred to as evaluation criterion data) during which the gaze point should stay in each evaluation segment.

[0039] FIG. 6 is a schematic diagram illustrating evaluation criterion data. The evaluation criterion data 40 includes an evaluation segment identifier 41 (e.g., A, B, C) and an evaluation criterion 42 (unit: milliseconds). The evaluation criterion 42 corresponds to the reference time described above and indicates the time period during which the gaze point should dwell on each evaluation segment. The evaluation segment identifier 41 corresponds to the evaluation segment identifier 31. The evaluation criterion 42 serves as a criterion for evaluating the dwell time of each evaluation segment. For example, if the gaze point dwells on evaluation segment A for 240,000 milliseconds or more, evaluation segment A is determined to have been sufficiently reviewed.

[0040] The evaluation criteria data must be defined in advance and are set appropriately, taking into account, for example, the programming language characteristics of the source code, the complexity of the functions included in the evaluation segments, the skills of the source code creator, and the skills of the reviewer. As an example, let's consider the case where evaluation criteria data is set based on the size of the evaluation segments. Assume that one screen to be reviewed contains three evaluation segments, A, B, and C, with an area ratio of A:B:C = 1:2:3. If the review time is 30 minutes, a simple calculation shows that the review time spent on evaluation segments A, B, and C is 5, 10, and 15 minutes, respectively. However, it is unlikely that the entire review time is spent on the review. Therefore, taking into account time spent looking away, we define 80% of the review time as effective. In this case, the evaluation criteria for ratings A, B, and C are 4, 8, and 12 minutes, respectively.

[0041] Continuing the explanation, returning to Fig. 3, the review evaluation unit 320 includes a stay time calculation unit 321 and a determination unit 322.

[0042] The dwell time calculation unit 321 is a specific example of the above-mentioned dwell time calculation unit 12. The dwell time calculation unit 321 calculates the time period during which the gaze point dwells on each evaluation segment (evaluation segment dwell time) based on the eye tracking data and the evaluation segment data.

[0043] The specific processing steps are as follows. First, the evaluation segment data is referenced to determine which evaluation segment the gaze point coordinates contained in the eye tracking data belong to. Gaze point coordinates that do not belong to any evaluation segment are not used in subsequent processing. Next, the sum of the dwell times for each evaluation segment (evaluation segment dwell time) is calculated.

[0044] The determination unit 322 is a specific example of the determination unit 13 described below. The determination unit 322 determines whether the calculated time period (rating segment dwell time) is equal to or greater than the evaluation standard set for each rating segment. The determination unit 322 may display the determination result on the review rating result display device 200. After evaluating whether the rating segment dwell time for each segment satisfies the evaluation standard, the determination unit 322 may register the evaluation result data in the management unit 310.

[0045] FIG. 7 is a schematic diagram showing an example of evaluation result data. The evaluation result data 50 includes an evaluation segment identifier 51 (e.g., A, B, C) and an evaluation result 52. The evaluation segment identifier 51 corresponds to the evaluation segment identifier 31, etc. The evaluation result 52 indicates whether or not each evaluation segment has been sufficiently reviewed. If the time period during which the gaze point stayed on the evaluation segment is equal to or longer than the evaluation standard, it is judged as "OK." On the other hand, if the time period during which the gaze point stayed on the evaluation segment is less than the evaluation standard, it is judged as "NG." FIG. 7 shows that evaluation segments A and C were sufficiently reviewed, and evaluation segment B was not sufficiently reviewed.

[0046] The review evaluation unit 320 may include an evaluation unit (not shown) that evaluates the review quality based on the evaluation result of the evaluation unit 322. For example, if the evaluation results of all evaluation segments are positive, the evaluation unit may evaluate the review quality as being sufficiently high. The evaluation unit may, for example, display a table in which the overall evaluation results are added to FIG. 7 on the review evaluation result display device 200. The evaluation result is "OK" if the evaluation results of all evaluation segments are positive, and "NG" otherwise.

[0047] Setting the evaluation segments and evaluation criteria is important in embodiment 2. By setting these appropriately, more rigorous review evaluation becomes possible.

[0048] Dividing the review target area into smaller evaluation segments allows for efficient evaluation of review quality. Figures 8 and 9 show examples of setting different numbers of evaluation segments in the same area. The review target is a web page and includes a logo L. In Figure 8, the area 61 included in the review target is divided into one evaluation segment D. In Figure 9, the area 61 is divided into three evaluation segments E, F, and G.

[0049] Assume that the time period during which the gaze point stayed on evaluation segment D is equal to or exceeds the evaluation criterion. Even in such a case, if there is a bias in the coordinates of the gaze point, it is possible that the user is not able to review area 61 in detail. As an extreme example, even if the user looks at logo L in the upper left corner for the entire review time, in the case of Figure 8, the dwell time will be equal to or exceeds the evaluation criterion. If the evaluation segments are divided into three as in Figure 9, the dwell time in any of the three evaluation segments E, F, and G will be less than the evaluation criterion in the above case.

[0050] In addition to the area ratio between evaluation segments, by taking into account the complexity of the functions included in the evaluation segment and the skill of the reviewer, it is possible to set evaluation criteria more appropriately and improve evaluation accuracy. Highly complex source code requires more review effort depending on the complexity. Therefore, if two source code fragments are of the same size (area), the evaluation criteria for the more complex source code should be set higher than the evaluation criteria for the less complex source code. Furthermore, if two source code fragments are of the same complexity, the evaluation criteria for a reviewer with higher skills should be set lower than the evaluation criteria for a reviewer with lower skills.

[0051] Next, a case where the complexity within an evaluation segment is taken into consideration will be specifically described with reference to Figures 8 and 10. One evaluation segment D is set in an area 61 shown in Figure 8. One evaluation segment H is set in an area 62 shown in Figure 10.

[0052] The configuration of area 61 is simple. However, it is necessary to review the behavior of a specific component (e.g., a button) when the mouse is hovered over it. The complexity of evaluation segment D is higher than that of an evaluation segment of the same area as evaluation segment D, which contains only plain text. Therefore, when the review target is a GUI screen, the evaluation criteria for an evaluation segment that contains a specific GUI component (e.g., a button) that takes time to review may be set higher than the evaluation criteria for other evaluation segments.

[0053] The number of characters in the evaluation segment H shown in Figure 10 is large. However, if the review does not include character strings and only reviews the color scheme, the complexity of the evaluation segment H is low. Therefore, the evaluation criteria for the evaluation segment H should be set low.

[0054] Next, a modified example of the second embodiment will be described. A review screen may be output on a head-mounted display, and reviews may be evaluated based on eye-tracking data collected in real time. Evaluation result data may be output on a separate screen, or may be generated on a separate layer on the review screen. By using this to check the completion of the review, it is possible to perform a thorough review and optimize the review time.

[0055] As described above, the review evaluation device 300 uses data on gaze points and dwell times. Furthermore, by correlating the period from the start to the end of collection of eye-tracking data with review man-hours, it is possible to make man-hour input more efficient. In such cases, the review evaluation device 300 is equipped with a man-hour calculation unit (not shown) that calculates the man-hours required to review the review target based on the eye-tracking data. The man-hour calculation unit extracts the review man-hours, for example, by extracting the start and end points of the review using a frame counter of the eye-tracking data, calculating the total sum of dwell times, or by cutting out the video at the actual start and end points of the review.

[0056] Finally, the effects of the evaluation system 1000 according to the second embodiment will be described. In software quality analysis and evaluation, it is common to analyze process metrics and product metrics from a statistical or empirical perspective during the development process. In the evaluation of reviews, it is determined whether the quality and quantity are sufficient. In other words, it is confirmed whether reviewers with appropriate skills are conducting the reviews over a sufficient amount of time.

[0057] A technology has been disclosed that quantifies developer skills and enables quality analysis and evaluation. Patent Document 1 makes it possible to evaluate review quality by taking into account the skills of the reviewer and reviewers. However, Patent Document 1 and other documents do not strictly discuss the effectiveness of review time. For example, even highly skilled reviewers are uncertain whether they can comprehensively check all targets within the review time, and there is a risk that some checks will be insufficient due to disturbances or distractions.

[0058] Additionally, there is a growing demand for the use of eye tracking data in engineering from the perspective of usability analysis. There are a variety of eye tracking devices available, ranging from wearable glasses and headsets to devices with integrated displays.

[0059] By utilizing the evaluation method and evaluation system according to the second embodiment, reviews can be rigorously evaluated using eye tracking data.

[0060] The present invention is not limited to the above-described embodiment, and can be modified as appropriate within the scope of the invention. [Explanation of symbols]

[0061] 10 Evaluation equipment 11 Acquisition Department 12 Residence time calculation section 13 Judgment section 1000 rating system 100 Eye Tracking Devices 200 review evaluation result display device 300 Review Rating Device 310 Management Department 311 Eye Tracking Data Management Department 312 Evaluation Segment Data Management Department 313 Evaluation Criteria Data Management Department 320 Review Evaluation Department 321 Residence time calculation unit 322 Judgment section 20 Eye Tracking Data 21 x-coordinate of gaze point 22 y-coordinate of gaze point 23 Residence time 30 Evaluation Segment Data 31 Evaluation Segment Identifier 32 Evaluation segment x coordinate 33 Evaluation segment y coordinate 40 Evaluation Criteria Data 41 Evaluation Segment Identifier 42 Evaluation Criteria 50 Evaluation result data 51 Evaluation Segment Identifier 52 Evaluation Results 61, 62 area A, B, C, D, E, F, G, H rating segments

Claims

1. an acquisition unit that acquires eye tracking data indicating the results of tracking the gaze points of users reviewing a review target; a dwell time calculation unit that calculates a time period during which the gaze point stays on each of a plurality of evaluation segments included in the review target; a determination unit that determines whether the time period is equal to or greater than a reference time set for each evaluation segment; Equipped with The coordinates of each evaluation segment are updated as the screen scrolls. a tracking unit that tracks the position of a feature included in the review object; a segment data management unit that manages the coordinates of each evaluation segment based on the tracking result of the tracking unit; Equipped with Evaluation equipment.

2. an evaluation unit that evaluates the review quality as high if the judgment results of all evaluation segments are positive; The evaluation device according to claim 1 .

3. The reference time is set according to the complexity of the functions included in each evaluation segment. The evaluation device according to claim 1 or 2.

4. the review target is a GUI (Graphical User Interface) screen, the reference time of an evaluation segment including a predetermined GUI component is set higher than the reference time of other evaluation segments; The evaluation device according to claim 1 .

5. a man-hour calculation unit that calculates the man-hours required to review the review object based on the eye tracking data; The evaluation device according to claim 1 , comprising:

6. A part of the program to be reviewed is highlighted as the characteristic part. The evaluation device according to claim 1 .

7. an eye tracking device that tracks the gaze point of a user reviewing a review object; an evaluation device; Equipped with The evaluation device an acquisition unit that acquires eye tracking data indicating a result of tracking the gaze point; a dwell time calculation unit that calculates a time period during which the gaze point stays on each of a plurality of evaluation segments included in the review target; a determination unit that determines whether the time period is equal to or greater than a reference time set for each evaluation segment; Equipped with The coordinates of each evaluation segment are updated as the screen scrolls. The evaluation device a tracking unit that tracks the position of a feature included in the review object; a segment data management unit that manages the coordinates of each evaluation segment based on the tracking result of the tracking unit; Equipped with Rating system.

8. If the results of all evaluation segments are positive, the review quality is rated high. The evaluation system according to claim 7 .

9. The computer acquiring eye tracking data indicating the results of tracking the gaze points of users reviewing the review subject; Calculating a time period during which the gaze point stayed on each of a plurality of evaluation segments included in the review object; determining whether the time period is equal to or greater than a reference time set for each evaluation segment; Including, The coordinates of each evaluation segment are updated as the screen scrolls. tracking the location of features within the review object; managing the coordinates of each evaluation segment based on the tracking results; Contains Evaluation method.

10. On the computer, acquiring eye tracking data indicating the results of tracking the gaze points of users reviewing the review object; A process of calculating a time period during which the user's gaze point stayed on each of a plurality of evaluation segments included in the review object; A process of determining whether the time period is equal to or greater than a reference time set for each evaluation segment; Execute The coordinates of each evaluation segment are updated as the screen scrolls. The computer, tracking the location of features in the review object; a process of managing the coordinates of each evaluation segment based on the tracking result; Run program.

Images