Method, device and equipment for collecting eye movement tracking data and medium

Abstract

Embodiments of the present disclosure relate to a method and apparatus for collecting eye tracking data, and a medium, wherein the method comprises: displaying a first gaze area on a target interface; the first gaze area is filled with a target color; in response to the display area of the first gaze area being not greater than a preset area threshold, statically displaying a second gaze area within a preset time length; the second gaze area is divided into a plurality of gaze sub-areas, the plurality of gaze sub-areas include a gaze sub-area filled with the target color, and the colors of the remaining gaze sub-areas in the plurality of gaze sub-areas except the gaze sub-area filled with the target color are all different from the target color; obtaining gaze feedback information of a target user, and obtaining a target eye image of the target user during the display of the first gaze area; and collecting eye tracking data of the target user based on the gaze feedback information and the target eye image. Embodiments of the present disclosure help to better guarantee the accuracy of the collected eye tracking data.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a method, apparatus, device and medium for acquiring eye-tracking data. Background Technology

[0002] In many fields such as gaming, healthcare, and intelligent control, it is necessary to identify the direction of human eye gaze in order to implement appropriate strategies based on the estimated gaze direction. The accuracy of the collected eye-tracking data is crucial; for example, a gaze direction estimation model trained on inaccurate eye-tracking data will have correspondingly low accuracy. The inventors' research revealed that existing methods for collecting eye-tracking data are inadequate, making it difficult to guarantee the accuracy of the final eye-tracking data. Summary of the Invention

[0003] To solve the above-mentioned technical problems, or at least partially solve them, this disclosure provides a method, apparatus, device, and medium for acquiring eye-tracking data.

[0004] This disclosure provides a method for collecting eye-tracking data. The method includes: displaying a first gaze area on a target interface; wherein the first gaze area is filled with a target color; statically displaying a second gaze area for a preset duration in response to the display area of ​​the first gaze area not exceeding a preset area threshold; wherein the second gaze area is divided into multiple gaze sub-areas, including a gaze sub-area filled with the target color, and the colors of the other gaze sub-areas besides the gaze sub-area filled with the target color are different from the target color; acquiring gaze feedback information of a target user, and acquiring a target eye image of the target user during the display of the first gaze area; wherein the gaze feedback information is information about a target gaze sub-area with the same target color among the multiple gaze sub-areas reported by the target user; and collecting eye-tracking data of the target user based on the gaze feedback information and the target eye image.

[0005] Optionally, displaying the first gaze area on the target interface includes: displaying the first gaze area on the target interface in response to the fulfillment of preset display conditions; the preset display conditions include one or more of the following: receiving a display instruction for the first gaze area, satisfying the position switching conditions of the first gaze area, and satisfying the color switching conditions of the first gaze area.

[0006] Optionally, the position switching conditions include one or more of the following: the first gaze area reaches the same position on the target interface a specified number of display cycles, the gaze feedback information corresponding to the previous display cycle of the first gaze area is incorrect, or the gaze feedback information corresponding to the previous display cycle of the first gaze area is not obtained within a specified time; the color switching conditions include: the gaze feedback information corresponding to the previous display cycle of the first gaze area is correct; wherein, the first gaze area is filled with one color in one display cycle, the first gaze area is filled with different colors in different display cycles, and there is a preset color disappearance time interval between adjacent display cycles of the first gaze area.

[0007] Optionally, displaying the first gaze area on the target interface includes: determining a first display position of the first gaze area on the target interface; wherein, when the position switching condition of the first gaze area is met, the first display position is a position different from the previous display position of the first gaze area; determining a target color to be filled in the first gaze area; wherein, when the color switching condition is met, the target color is a color different from the color filled in the previous display cycle of the first gaze area; and displaying the first gaze area on the target interface based on the first display position and the target color.

[0008] Optionally, displaying the first gaze area on the target interface includes: displaying the first gaze area on the target interface based on a preset size gradient strategy; wherein the size gradient strategy is used to instruct the first gaze area to gradually change from a first size to a second size within a display cycle, the first size being larger than the second size; and / or, obtaining a depth value corresponding to the first gaze area; and displaying the first gaze area on the target interface based on the depth value; wherein the depth value is a randomly generated value or a preset value.

[0009] Optionally, statically displaying the second gaze area within a preset duration includes: determining a second display position of the second gaze area on the target interface based on a first display position of the first gaze area on the target interface and a preset relative positional relationship between the first gaze area and the second gaze area; and statically displaying the second gaze area within a preset duration based on the second display position on the target interface.

[0010] Optionally, the step of statically displaying the second gaze area within a preset duration includes: randomly setting the orientation of multiple gaze sub-areas within the second gaze area; and statically displaying the second gaze area within a preset duration based on the orientation of the multiple gaze sub-areas.

[0011] Optionally, the second gaze area is a hollow ring-shaped region, and the first gaze area is located within the hollow ring of the second gaze area.

[0012] Optionally, the method further includes: continuously rotating the second gaze area during a display period when the display area of ​​the first gaze area is greater than a preset area threshold; the step of displaying the second gaze area on the target interface in response to the display area of ​​the first gaze area not being greater than the preset area threshold includes: stopping the rotation of the second gaze area in response to the display area of ​​the first gaze area not being greater than the preset area threshold, and statically displaying the second gaze area for a preset duration based on the orientation of multiple gaze sub-areas in the second gaze area when the rotation stops.

[0013] Optionally, the method further includes: after reaching the preset time, continuing to rotate the second gaze area; or, after reaching the preset time, changing the display position of the second gaze area, and continuously rotating the second gaze area during the position change; wherein the changed display position of the second gaze area is related to the next display position of the first gaze area.

[0014] Optionally, the size of the second gaze area is related to the size of the first gaze area, and the size of the second gaze area changes as the size of the first gaze area changes.

[0015] Optionally, the method further includes: switching the background color of the target interface based on a preset background switching timing.

[0016] Optionally, different gaze sub-regions among the plurality of gaze sub-regions may have different colors.

[0017] Optionally, the step of collecting eye-tracking data of the target user based on the gaze feedback information and the target eye image includes: filtering valid eye images from the target eye image based on the gaze feedback information; wherein the gaze feedback information corresponding to the valid eye image is correct; and performing gaze annotation operation on the valid eye image based on the position of the first gaze area corresponding to the valid eye image to obtain the eye-tracking data of the target user.

[0018] Optionally, the step of filtering valid eye images from the target eye images based on the gaze feedback information includes: obtaining the pixel differences between target eye images corresponding to different display cycles at the same position of the first gaze area on the target interface; and filtering valid eye images from the target eye images based on the pixel differences between the target eye images corresponding to different display cycles at the same position, and the gaze feedback information corresponding to each display cycle at each position of the first gaze area on the target interface.

[0019] Optionally, the step of filtering valid eye images from the target eye images includes: obtaining a first confidence score for the target eye images at the same location corresponding to different display periods based on a comparison result of the pixel differences between the target eye images at different display periods corresponding to the same location and a preset difference threshold; obtaining a second confidence score for the target eye images at each display period based on the correctness judgment result of the gaze feedback information at each location of the first gaze area on the target interface corresponding to each display period; and filtering valid eye images from the target eye images based on the first confidence score and the second confidence score corresponding to the target eye images.

[0020] This disclosure also provides an eye-tracking data acquisition device, comprising: a first display module for displaying a first gaze area on a target interface; wherein the first gaze area is filled with a target color; a second display module for statically displaying a second gaze area for a preset duration in response to the display area of ​​the first gaze area not exceeding a preset area threshold; wherein the second gaze area is divided into multiple gaze sub-areas, the multiple gaze sub-areas including a gaze sub-area filled with the target color, and the colors of the other gaze sub-areas besides the gaze sub-area filled with the target color are different from the target color; an acquisition module for acquiring gaze feedback information of a target user and acquiring a target eye image of the target user during the display of the first gaze area; wherein the gaze feedback information is information of a target gaze sub-area that matches the target color among the multiple gaze sub-areas reported by the target user; and a data acquisition module for acquiring eye-tracking data of the target user based on the gaze feedback information and the target eye image.

[0021] This disclosure also provides an electronic device, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the eye-tracking data acquisition method provided in this disclosure.

[0022] This disclosure also provides a computer-readable storage medium storing a computer program for executing the eye-tracking data acquisition method provided in this disclosure.

[0023] This disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the eye-tracking data acquisition method provided in this disclosure.

[0024] The technical solution provided in this disclosure first displays a first gaze area filled with a target color on the target interface, and then statically displays a second gaze area (divided into multiple gaze sub-areas, including a gaze sub-area filled with the target color, and the colors of the other gaze sub-areas besides the gaze sub-area filled with the target color are different from the target color) when the display area of ​​the first gaze area is not greater than a preset area threshold. Then, gaze feedback information from the target user (i.e., information about the target gaze sub-area with the same target color among the multiple gaze sub-areas reported by the target user) and a target eye image of the target user during the display of the first gaze area can be obtained. Based on the gaze feedback information and the target eye image, eye-tracking data of the target user can be collected. Through this method, the gaze feedback information helps to effectively identify whether the target user is gazing at the first gaze area during its display, and collecting eye-tracking data based on the gaze feedback information helps to better ensure the accuracy of the collected eye-tracking data.

[0025] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0026] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0027] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 A flowchart illustrating a method for acquiring eye-tracking data according to an embodiment of this disclosure;

[0029] Figure 2 A schematic diagram of the gaze region provided in an embodiment of this disclosure;

[0030] Figure 3 A schematic diagram of interface changes provided in an embodiment of this disclosure;

[0031] Figure 4 A schematic diagram of interface changes provided in an embodiment of this disclosure;

[0032] Figure 5 A schematic diagram of interface changes provided in an embodiment of this disclosure;

[0033] Figure 6 This is a schematic diagram of the structure of an eye-tracking data acquisition device provided in an embodiment of the present disclosure;

[0034] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0035] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0036] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0037] In practical applications, gaze estimation models are often required for gaze estimation. The accuracy of gaze estimation is directly related to the accuracy of the eye-tracking data used to train the model. This eye-tracking data includes captured eye images and corresponding gaze direction labels. Related technologies acquire eye images by providing the user with a gaze point and having the user look at that point. Since the gaze point position is fixed, a theoretical gaze direction can be obtained, which is then used as the gaze direction label for the captured eye images. However, the inventors discovered through research that the accuracy of eye-tracking data obtained by related technologies is low. The main reason is that in many cases, users may not actually be looking at the designated gaze point, but rather at other locations or experiencing gaze drift. Therefore, the eye image captured at the gaze point does not match the theoretical gaze direction corresponding to that gaze point. The resulting eye-tracking data is essentially unusable dirty data. Furthermore, it is difficult to identify whether the user is actually looking at the designated gaze point in related technologies, which means it is difficult to determine whether the eye-tracking data is accurate. Consequently, the gaze estimation accuracy of the gaze estimation model trained using eye-tracking data with low accuracy is also correspondingly poor.

[0038] To address the aforementioned issues, this disclosure provides a method, apparatus, device, and medium for acquiring eye-tracking data, which helps improve the accuracy of the acquired eye-tracking data. These are described in detail below.

[0039] Figure 1This is a flowchart illustrating a method for acquiring eye-tracking data according to an embodiment of the present disclosure. This method can be executed by an eye-tracking data acquisition device, which can be implemented using software and / or hardware, and is generally integrated into an electronic device. Figure 1 As shown, the method mainly includes the following steps S102 to S108:

[0040] Step S102: Display the first gaze area on the target interface; wherein the first gaze area is filled with the target color. This embodiment of the present disclosure does not limit the shape of the first gaze area, such as a circular area, a star-shaped area, etc. In order to better focus the user's gaze, the area of ​​the first gaze area does not exceed a preset area threshold, that is, the overall size of the first gaze area is relatively small, thus presenting a point-like visual effect to the user.

[0041] Step S104: In response to the first gaze area not exceeding a preset area threshold, the second gaze area is statically displayed for a preset duration. The second gaze area is divided into multiple gaze sub-areas, each filled with a color. Among these sub-areas is a gaze sub-area filled with a target color. The colors of the remaining gaze sub-areas, excluding the target color, are different from the target color. The number of gaze sub-areas filled with the target color can be one or more, but it must be ensured that in addition to the target color, there are gaze sub-areas filled with other colors for the user to choose from. In some specific examples, to increase the difficulty of user selection, the colors of different gaze sub-areas are different. Here, "multiple" means at least two, meaning the second gaze area can be divided into at least two gaze sub-areas. For example, the second gaze area can be divided into 4, 6, or 8 gaze sub-areas, etc., and can be flexibly set according to the shape of the second gaze area and actual needs. Furthermore, the aforementioned "static" refers to the second gaze area being displayed in a static state, without any dynamic changes such as rotation. By setting the second gaze area to be statically displayed for a preset duration, users can provide gaze information based on the statically presented second gaze area, such as which gaze sub-area in the second gaze area has a color that matches the target color of the first gaze area. In practical applications, the preset duration can be flexibly set according to needs and is not limited here. In this embodiment, the second gaze area can be statically displayed for a preset duration. For example, under normal circumstances, the static display duration of the second gaze area is at most the preset duration. After the preset duration is reached, the second gaze area can disappear or switch to dynamic display. In addition, a termination condition for the static display of the second gaze area can be set. For example, if gaze feedback information from the target user is received within the preset duration, the static display of the second gaze area can be directly terminated, in which case the static display duration of the second gaze area is less than the preset duration. Furthermore, this embodiment does not limit the display method of the second gaze area after the preset duration is reached, and it can be flexibly set.

[0042] It should also be noted that the preset area threshold can be flexibly set in practical applications. For example, the area threshold can be set to a small value that is not easily visible to the human eye, or the preset area threshold can be directly set to zero. If the preset area threshold is zero, the case where the displayed area of ​​the first gaze area is not greater than the preset area threshold is also the case where the first gaze area disappears. In some implementation examples, the case where the displayed area of ​​the first gaze area is not greater than the preset area threshold may include the case where the first gaze area shrinks to a dot, or the case where the first gaze area disappears. In order to fully ensure the reliability of the gaze feedback information of the target user finally obtained, in some specific implementation examples, in response to the case where the displayed area of ​​the first gaze area is not greater than the preset area threshold, the second gaze area is statically displayed for a preset time period, including: in response to the case where the first gaze area disappears, the second gaze area is statically displayed for a preset time period.

[0043] This disclosure allows for the static display of a second gaze area when the display area of ​​the first gaze area is no larger than a preset area threshold. The second gaze area can be used to determine whether the user is looking at the first gaze area during its display. It should be noted that in some embodiments, the second gaze area is only displayed when the display area of ​​the first gaze area is no larger than the preset area threshold. In other embodiments, even when the display area of ​​the first gaze area is larger than the preset area threshold, the second gaze area is dynamically displayed on the target interface. A preset relative positional relationship exists between the first display position corresponding to the first gaze area and the second display position corresponding to the second gaze area. Optionally, the first and second display positions are within a preset distance range, meaning the first and second gaze areas are relatively close. The user's attention can be attracted by dynamically displaying (e.g., rotating) the second gaze area, preventing the user from becoming distracted. This disclosure does not limit the shape of the second gaze area. In some specific examples, the second gaze area is a hollow ring-shaped region, with the first gaze area located within the hollow ring of the second gaze area, meaning the second gaze area surrounds the first gaze area. The center point of the second gaze area may coincide with the center point of the first gaze area. In this way, when the first and second gaze areas are displayed simultaneously, the second gaze area will not only not affect the user's gaze on the first gaze area, but will also attract the user's attention to focus on the first gaze area.

[0044] For easier understanding, please refer to Figure 2 The diagram shown illustrates a fixation area, simultaneously showing the first and second fixation areas. Figure 2 In the example, the second fixation area is divided into four sub-fixation areas, each with a different color. This illustrates that the four sub-fixation areas are filled with red, yellow, blue, and green, respectively, and that the first fixation area is filled with green. It should be noted that... Figure 2This is intended to illustrate the shape of the first and second gaze areas, as well as their relative positional relationship. It should not be assumed that the first and second gaze areas must be simultaneously located on the target interface. In practical applications, the first gaze area can be displayed first, and the second gaze area can be displayed after the first gaze area disappears. Alternatively, the second gaze area can be dynamically displayed by rotation during the display of the first gaze area. No restrictions are imposed here.

[0045] Step S106: Obtain the gaze feedback information of the target user, and obtain the target eye image of the target user during the display in the first gaze area; wherein, the gaze feedback information is the information of the target gaze sub-region that matches the target color among the multiple gaze sub-regions reported by the target user. This information may be any information that can uniquely identify the target gaze sub-region, such as the identification information of the target gaze sub-region, the orientation information of the target gaze sub-region, etc., and is not limited here.

[0046] In practical applications, the user whose eye-tracking data is to be collected is the target user. The target user can wear devices such as VR glasses, smart glasses, eye trackers, or other electronic devices capable of collecting eye-tracking data. This electronic device can present the target interface to the user and capture images of the target user's eyes during the first gaze zone. Alternatively, the user can directly view the electronic screen displaying the target interface without wearing a device, and the target user's eyes during the first gaze zone can be captured directly by a camera at a preset position. There are no restrictions on the method of capturing the target eye images. It should be noted that before capturing the target eye images (specifically, before displaying the first gaze zone), a prompt message can be sent to the user informing them of the purpose of the capture. The user's eye images are then captured only after obtaining their authorization. For example, the prompt message can be sent to the user in the form of a pop-up window, which can present the prompt message in text form. Furthermore, the pop-up window can also include a selection control for the user to choose "agree" or "disagree" to allow the electronic device to capture their eye images. It is understood that the above notification and user authorization process is merely illustrative and does not constitute a limitation on the implementation of this disclosure.

[0047] Feedback can be provided to the target user, such as providing feedback controls on the interface to indicate the location of the target's gaze area. Figure 2For example, four directional controls (up, down, left, and right) can be provided on the interface. The user can trigger the target directional control from among these four controls based on the location of the target gaze area within the second gaze area. The backend can then determine the target gaze area based on the location of the triggered target directional control. Alternatively, the user can directly operate a controller with up, down, left, and right directional controls, or in a VR scene, the user can directly select the target gaze area using a controller, laser, or other means. This embodiment does not limit the method of obtaining the target user's gaze feedback information.

[0048] Step S108: Based on gaze feedback information and target eye image, collect eye-tracking data of the target user.

[0049] For example, based on the correctness determination result of the gaze feedback information, valid eye images (i.e., eye images with correct gaze feedback information) can be selected from the target eye images. Then, gaze annotation is performed on the valid eye images based on the display position of the first gaze region corresponding to each valid eye image, thus obtaining the target user's eye-tracking data. Furthermore, based on the correctness determination result of the gaze feedback information, other valid eye image determination information can be combined. For example, the difference between target eye images acquired at the same location in the first gaze region can be used to measure whether the target user's eye position has changed. By comprehensively selecting target eye images with correct gaze feedback information and unchanged target user eye position as valid eye images, the reliability of the eye-tracking data can be fully guaranteed.

[0050] In summary, the above methods, based on gaze feedback information, help to effectively identify whether the target user is gazing at the first gaze area during the display of the first gaze area. Collecting eye-tracking data based on gaze feedback information helps to better ensure the accuracy of the collected eye-tracking data.

[0051] In some implementation examples, the step of displaying the first gaze area on the target interface described above can be performed as follows: In response to the fulfillment of preset display conditions, the first gaze area is displayed on the target interface. That is, the first gaze area is displayed only after certain conditions are met. For example, the preset display conditions include one or more of the following display conditions one through three:

[0052] Display Condition 1: A display instruction is received from the first gaze area. This instruction can be triggered directly by the user or sent by the server; no restrictions are imposed here.

[0053] Display Condition Two: The position switching condition of the first gaze area is met. For example, the position switching condition includes one or more of the following: the first gaze area reaches a specified number of display cycles at the same location on the target interface; the gaze feedback information corresponding to the previous display cycle of the first gaze area is incorrect; or the gaze feedback information corresponding to the previous display cycle of the first gaze area is not obtained within a specified duration. The first gaze area is filled with one color within one display cycle, and the color filled with the first gaze area is different in different display cycles. Furthermore, there is a preset color disappearance time interval between adjacent display cycles of the first gaze area. It is understood that the first gaze area can be displayed at different locations on the target interface, and the specific settings can be flexible. For example, when collecting eye-tracking data from the target user, it can be set to display the first gaze area sequentially at M locations on the target interface (which can be specified locations or random locations). The first gaze area can be displayed for up to N cycles at each display location. For each cycle, the first gaze area appears at the beginning of the cycle and disappears at the end of the cycle, and the color of the first gaze area remains unchanged within that cycle. After the current cycle ends, if the user's gaze feedback for that cycle is correct, the next cycle can begin after a certain interval, and the color of the first gaze area will change. If the user's gaze feedback for that cycle is incorrect, or if the cycle has reached its Nth cycle, the cycle ends, and the display of the first gaze area will switch to the next position. Both M and N can be flexibly set and are not restricted here.

[0054] The method for determining whether the gaze feedback information is correct can be combined with Figure 2 To clarify, the first gaze area is green, and this green area is located below the second gaze area. Assuming the user's gaze feedback is represented by the location of the gaze sub-area, if the user triggers a control indicating the lower direction, it means the user believes the color of the lower gaze sub-area (green) matches the previously displayed color of the first gaze area, and the gaze feedback is correct. However, if the user triggers a control indicating the upper direction, it means the user believes the color of the upper gaze sub-area (red) matches the previously displayed color of the first gaze area, and the gaze feedback is incorrect, indicating that the user was not looking at the first gaze area when it was displayed (green). In practical applications, after the user provides gaze feedback, indicators such as checkmarks or crosses can be used to show the user whether the gaze feedback is correct; this is not restricted here.

[0055] Display Condition 3: The color switching condition for the first gaze area is met. For example, the color switching condition includes: the gaze feedback information corresponding to the previous display cycle of the first gaze area is correct. As mentioned earlier, at the same location, the color of the first gaze area can only be switched if the gaze feedback information corresponding to the previous display cycle of the first gaze area is correct. Furthermore, the above color switching condition can be used to restrict the color of the first gaze area at the same location. When the first gaze area switches from one location to another, the last displayed color at the earlier location and the first displayed color at the later location can be the same or different; this is not restricted here.

[0056] The first gaze area can be displayed if any of the display conditions one through three above are met. In some embodiments, the aforementioned step of displaying the first gaze area on the target interface can be performed with reference to the following steps (1) through (3):

[0057] Step (1) determines the first display position of the first gaze area on the target interface; wherein, if the position switching condition of the first gaze area is met, the first display position is a position different from the previous display position of the first gaze area; if the position switching condition of the first gaze area is not met, the first display position is the same as the previous display position of the first gaze area. Each display position of the first gaze area on the target interface can be randomly determined so as to be able to acquire eye images from multiple gaze directions.

[0058] Step (2) Determine the target color to be filled in the first gaze area; wherein, under the condition of satisfying the color switching, the target color is a color different from the color filled in the previous display cycle of the first gaze area; the colors of the N display cycles corresponding to each position of the first gaze area can be specified in advance, such as specifying that the first gaze area is displayed in the order of color 1, color 2, ... color N, or can be randomly selected from the N specified colors, without any restrictions here.

[0059] Step (3): Based on the first display position and target color, display the first gaze area on the target interface.

[0060] In some implementations, the aforementioned display of the first gaze area on the target interface can be performed with reference to the following steps 1 and / or 2:

[0061] Step 1: Based on a preset size gradient strategy, display a first gaze area on the target interface; wherein, the size gradient strategy is used to indicate that the first gaze area gradually changes from a first size to a second size within a display cycle, and the first size is larger than the second size; for example, the first gaze area is a circular area, and the first gaze area can dynamically change from large to small within each display cycle, which can not only attract the user's attention, but also help the user focus their gaze.

[0062] And / or,

[0063] Step 2: Obtain the depth value corresponding to the first gaze region; based on the depth value, display the first gaze region on the target interface; wherein, the depth value is a randomly generated value or a preset value. This method also allows for effective adjustment of the focal length, enabling the acquisition of richer and more diverse eye images.

[0064] In practical applications, the above methods can be flexibly selected according to the needs. For example, in some specific implementation examples, the first gaze area can be displayed on the target interface based on the first display position, target color, size gradient strategy and depth value.

[0065] In some implementations, the aforementioned static display of the second gaze area within a preset duration can be performed with reference to the following steps a and b:

[0066] Step a: Based on the first display position of the first gaze area on the target interface and the preset relative positional relationship between the first and second gaze areas, determine the second display position of the second gaze area on the target interface. For example, the second gaze area is a ring-shaped region that surrounds the first gaze area, and the center points of the first and second gaze areas coincide.

[0067] Step b: Based on the second display position on the target interface, statically display the second gaze area for a preset duration.

[0068] In some specific implementations, the second gaze region is statically displayed within a preset duration, including: randomly setting the orientations of multiple gaze sub-regions within the second gaze region; and statically displaying the second gaze region within the preset duration based on the orientations of the multiple gaze sub-regions. For ease of understanding, please refer to... Figure 3 The diagram illustrates an interface change. First, a first gaze area is displayed alone. Then, in response to the disappearance of the first gaze area, a second gaze area is displayed. The orientation of each gaze sub-area within the second gaze area is random; for example, the gaze sub-area corresponding to the red area can be located in any direction (up, down, left, right), without restriction.

[0069] In some implementations, the second gaze area is a hollow ring-shaped region, and the first gaze area is located within the hollow ring of the second gaze area. Furthermore, the method further includes continuously rotating the second gaze area during the display period when the display area of ​​the first gaze area is greater than a preset area threshold. This effectively prevents users from becoming distracted or spacing out, helps focus the user's gaze, and avoids users relying on peripheral vision for feedback. Further, the aforementioned step of displaying the second gaze area on the target interface in response to the display area of ​​the first gaze area not exceeding the preset area threshold includes: stopping the rotation of the second gaze area in response to the display area of ​​the first gaze area not exceeding the preset area threshold, and statically displaying the second gaze area for a preset duration based on the orientation of multiple gaze sub-areas within the second gaze area when rotation stops. For ease of understanding, please refer to... Figure 4 The diagram illustrates an interface change where a first gaze area and a second gaze area can be displayed simultaneously. During the display of the first gaze area, the second gaze area rotates dynamically; in response to the disappearance of the first gaze area, the second gaze area becomes static. This helps users carefully observe the second gaze area and pinpoint the location of the target gaze sub-area. Building upon this, the method further includes: continuing to rotate the second gaze area after a preset time period; or, changing the display position of the second gaze area after a preset time period, and continuously rotating the second gaze area during the position change; wherein the changed display position of the second gaze area is related to the next display position of the first gaze area, and their relative positional relationship remains unchanged. In the above implementation example, the second gaze area can always be displayed on the target interface and can be displayed dynamically or statically depending on the actual situation. For example, it can only be statically displayed for a preset time period after the first gaze area disappears, stably presented to the user, so that the user can provide feedback based on the color of the static gaze sub-area of ​​the second gaze area. Otherwise, it can be dynamically displayed to attract user attention and prevent users from remembering the location of each gaze sub-area and thus ceasing to gaze. For example, refer to... Figure 5 The diagram illustrates an interface change where the first gaze area disappears at a first position, and a second gaze area is statically displayed. Afterward, the second gaze area can dynamically rotate to another position, where the first gaze area begins to be displayed. During the display of the first gaze area, the second gaze area can continue to rotate. Of course, Figure 5 This is just an example. In actual applications, when switching positions, the first gaze area can appear first, and the second gaze area can appear after the first gaze area disappears. The specific settings can be flexibly configured and are not restricted here.

[0070] In some specific implementation examples, if the second gaze area is a hollow ring-shaped area and the first gaze area is located inside the hollow ring of the second gaze area, then the size of the second gaze area is related to the size of the first gaze area, and the size of the second gaze area changes with the size of the first gaze area. For example, if the first gaze area shrinks during the display, the second gaze area that dynamically rotates around the first gaze area will also shrink accordingly, thus presenting a dynamic visual effect.

[0071] Furthermore, the method provided in this disclosure also includes: switching the background color of the target interface based on a preset background switching timing. This disclosure does not limit the background switching timing; for example, it can be the timing when the position and / or color of the first gaze area changes, or the timing when the first gaze area disappears, or the background switching can be performed at preset time intervals. This disclosure can preset multiple background colors for switching, such as black and white backgrounds, etc., without limitation. In this way, user visual fatigue can also be effectively avoided, and user attention can be improved.

[0072] In some implementations, the steps described above for collecting eye-tracking data of the target user based on gaze feedback information and the target eye image can be performed with reference to steps A and B as follows:

[0073] Step A involves selecting valid eye images from the target eye images based on gaze feedback information; where valid eye images correspond to correct gaze feedback information. In some specific implementation examples, Step A can be performed as follows: Steps A1 to A2

[0074] Step A1: Obtain the pixel difference between target eye images corresponding to different display cycles at the same location on the target interface for the first gaze area. This pixel difference can be characterized by the average pixel difference between target eye images corresponding to different display cycles. The first gaze area has at most N display cycles at each location. If N=2, the pixel difference between the target eye image corresponding to display cycle 1 and the target eye image corresponding to display cycle 2 at the same location for the first gaze area can be obtained. If N is greater than 2, assuming N=3, the pixel difference between any two target eye images corresponding to different display cycles can be randomly obtained, or the pixel difference between target eye images corresponding to two adjacent display cycles can be obtained, or the pixel difference between target eye images corresponding to two specified different display cycles (such as the first display cycle and the last display cycle) can be obtained. The specific settings are flexible and not limited here. It is understood that if the user always gazes at the same location, the theoretical pixel difference between the collected target eye images will be small, unless the user's eyes move or the gaze shifts, in which case the pixel difference between target eye images collected at the same location in different display cycles will be larger. By obtaining the aforementioned pixel differences, this embodiment of the disclosure can further determine whether the user is always looking at the display position of the first gaze area, which helps in the subsequent screening of valid eye images.

[0075] Step A2 involves filtering out valid eye images from the target eye images based on the pixel differences between target eye images at different display cycles at the same location, and the gaze feedback information corresponding to each display cycle at each location of the first gaze area on the target interface. For example, the selected valid eye images correspond to correct gaze feedback information, and the pixel differences are below a preset difference threshold. Specifically, steps A2.1 to A2.3 can be performed as follows:

[0076] Step A2.1: Based on the comparison result of the pixel difference between the target eye images corresponding to different display periods at the same location and the preset difference threshold, a first confidence score of the target eye images corresponding to different display periods at the same location is obtained; for example, for two target eye images corresponding to different display periods, if the pixel difference between the two is lower than the preset difference threshold, then the first confidence score of the two target eye images is a first value; if the pixel difference between the two is not lower than the preset difference threshold, then the first confidence score of the two target eye images is a second value, wherein the first value is greater than the second value. For example, the first value can be a positive number and the second value can be a negative number.

[0077] Step A2.2: Based on the correctness judgment results of the gaze feedback information corresponding to each display cycle at each position of the first gaze area on the target interface, a second confidence score of the target eye image corresponding to each display cycle is obtained. For each display cycle, if the gaze feedback information corresponding to that display cycle is correct, the second confidence score of the target eye image corresponding to that display cycle is a third value; if the gaze feedback information corresponding to that display cycle is incorrect, the second confidence score of the target eye image corresponding to that display cycle is a fourth value. The third value is greater than the fourth value. For example, the third value can be a positive number, and the fourth value can be a negative number.

[0078] Step A2.3: Based on the first and second confidence scores corresponding to the target eye images, select valid eye images from the target eye images. For example, the sum of the first and second confidence scores corresponding to each target eye image can be obtained to get the comprehensive score of each target eye image. In some implementation examples, eye images with scores higher than a preset score threshold can be selected as target eye images from the comprehensive scores of multiple target eye images. In other implementation examples, target eye images with scores higher than a preset first threshold can be selected as valid eye images from the comprehensive scores of multiple target eye images. The average of the comprehensive scores of multiple target eye images can be calculated. Only when the average value is higher than a preset second threshold is it confirmed that the target user has a high degree of cooperation during the entire eye tracking data collection process, and the overall confidence of this batch of target eye images is high. Furthermore, the target eye image with the highest score is selected from this batch of target eye images as a valid eye image, thereby fully ensuring the accuracy of the valid eye images.

[0079] Step B involves performing gaze labeling on the effective eye images based on the location of the first gaze region corresponding to each effective eye image, thereby obtaining the target user's eye-tracking data. Based on the location of the first gaze region corresponding to each effective eye image, the theoretical gaze label can be determined. This allows for the association of the effective eye images with the theoretical gaze labels, thus obtaining the target user's eye-tracking data. This method ensures a match between the effective eye images and the theoretical gaze labels, guaranteeing the accuracy of the eye-tracking data.

[0080] By utilizing the methods provided in this embodiment, and with the help of user gaze feedback information based on the color of the first gaze area and the colors of multiple gaze sub-areas within the second gaze area, it is possible to effectively identify whether the user is actually gazing at the designated gaze area and whether the captured eye image is accurate. Furthermore, it should be noted that the methods provided in this embodiment can effectively reduce the occurrence of users guessing the gaze feedback information instead of directly gazing at the designated gaze area. Specifically, taking the gaze feedback information as the location information of the target gaze sub-area with the same color as the target among multiple gaze sub-areas provided by the user as an example, assuming the first gaze area needs to be displayed sequentially at multiple locations on the target interface, and the first gaze area can be displayed for up to N cycles at each display location (i.e., the first gaze area can change to N colors at that location), and the second gaze area is divided into X gaze sub-areas, if N = 2 and X = 4, the probability that the user correctly guesses the gaze feedback information provided twice consecutively for a display location is 1 / 16; if N = 2 and X = 8, the probability that the user correctly guesses the gaze feedback information provided twice consecutively for a display location is 1 / 64. If N=3 and X=4, for a given display location, the probability that a user correctly guesses the gaze feedback information provided three times consecutively for that location is 1 / 64. In other words, for a given display location, the probability that a user correctly guesses the gaze feedback information provided N times consecutively for that location is 1 / X raised to the power of N. Based on the above analysis, it can be seen that the probability of a user correctly guessing the gaze feedback information without actually looking at the first gaze area is very low. In other words, the accurate gaze feedback information obtained in this embodiment is real and effective, and the eye images obtained based on the accurate gaze feedback information are also reliable. In addition, to ensure the richness and reliability of the eye images, for the same target user, eye images can be collected when the user wears different devices, or eye images can be collected after the user wears the same device multiple times. The specific settings can be flexibly configured.

[0081] In summary, the embodiments disclosed herein help to better ensure the accuracy of the collected eye-tracking data.

[0082] Corresponding to the aforementioned method for acquiring eye-tracking data, this disclosure further provides an eye-tracking data acquisition device. Figure 6 This is a schematic diagram of the structure of an eye-tracking data acquisition device provided in an embodiment of this disclosure. The device can be implemented by software and / or hardware, and is generally integrated into an electronic device, such as... Figure 6 As shown, the eye-tracking data acquisition device includes:

[0083] The first display module 602 is used to display a first gaze area on the target interface; wherein the first gaze area is filled with the target color;

[0084] The second display module 604 is used to statically display the second gaze area on the target interface for a preset time period in response to the display area of ​​the first gaze area not being greater than a preset area threshold; wherein the second gaze area is divided into multiple gaze sub-areas, the multiple gaze sub-areas including a gaze sub-area filled with the target color, and the colors of the other gaze sub-areas besides the gaze sub-area filled with the target color are different from the target color.

[0085] The acquisition module 606 is used to acquire the gaze feedback information of the target user and to acquire the target eye image of the target user during the display in the first gaze area; wherein, the gaze feedback information is the information of the target gaze sub-area with the same color as the target among the multiple gaze sub-areas fed back by the target user.

[0086] The data acquisition module 608 is used to acquire eye-tracking data of the target user based on gaze feedback information and target eye images.

[0087] The aforementioned device helps to effectively identify whether the target user is gazing at the first gaze area during the display of the first gaze area based on gaze feedback information. The collection of eye-tracking data based on gaze feedback information helps to better ensure the accuracy of the collected eye-tracking data.

[0088] In some implementations, the first display module 602 is specifically used to: display a first gaze area on a target interface in response to the achievement of preset display conditions; the preset display conditions include one or more of the following: receiving a display instruction for the first gaze area, satisfying the position switching conditions of the first gaze area, and satisfying the color switching conditions of the first gaze area.

[0089] In some implementations, the position switching conditions include one or more of the following: the first gaze area reaches the same position on the target interface a specified number of display cycles, the gaze feedback information corresponding to the previous display cycle of the first gaze area is incorrect, or the gaze feedback information corresponding to the previous display cycle of the first gaze area is not obtained within a specified time.

[0090] The color switching condition includes: the gaze feedback information corresponding to the previous display cycle of the first gaze area is correct;

[0091] The first gaze area is filled with one color in one display cycle, and the color filled with the first gaze area is different in different display cycles. There is a preset color disappearance time interval between adjacent display cycles of the first gaze area.

[0092] In some implementations, the first display module 602 is specifically used to: determine a first display position of the first gaze area on the target interface; wherein, when the position switching condition of the first gaze area is met, the first display position is a position different from the previous display position of the first gaze area; determine a target color to be filled in the first gaze area; wherein, when the color switching condition is met, the target color is a color different from the color filled in the previous display cycle of the first gaze area; and display the first gaze area on the target interface based on the first display position and the target color.

[0093] In some implementations, the first display module 602 is specifically used to: display a first gaze area on a target interface based on a preset size gradient strategy; wherein the size gradient strategy is used to instruct the first gaze area to gradually change from a first size to a second size within a display cycle, the first size being larger than the second size; and / or, obtain a depth value corresponding to the first gaze area; and display the first gaze area on the target interface based on the depth value; wherein the depth value is a randomly generated value or a preset value.

[0094] In some implementations, the second display module 604 is specifically used to: determine the second display position of the second gaze area on the target interface based on the first display position of the first gaze area on the target interface and the preset relative positional relationship between the first gaze area and the second gaze area; and statically display the second gaze area for a preset duration based on the second display position on the target interface.

[0095] In some embodiments, the second display module 604 is specifically used to: randomly set the orientation of multiple gaze sub-regions in the second gaze area; and statically display the second gaze area within a preset time period based on the orientation of the multiple gaze sub-regions.

[0096] In some embodiments, the second gaze area is a hollow annular region, and the first gaze area is located within the hollow annular region of the second gaze area.

[0097] In some embodiments, the device further includes a first rotation module for continuously rotating the second gaze area during a display period when the display area of ​​the first gaze area is greater than a preset area threshold; the second display module 604 is specifically used to: stop rotating the second gaze area in response to the display area of ​​the first gaze area not being greater than the preset area threshold, and statically display the second gaze area for a preset duration based on the orientation of multiple gaze sub-areas in the second gaze area when the rotation stops.

[0098] In some embodiments, the device further includes a second rotation module for continuing to rotate the second gaze area after the preset time period has been reached; or, after the preset time period has been reached, changing the display position of the second gaze area and continuously rotating the second gaze area during the position change; wherein the changed display position of the second gaze area is related to the next display position of the first gaze area.

[0099] In some implementations, the size of the second gaze region is related to the size of the first gaze region, and the size of the second gaze region varies with the size of the first gaze region.

[0100] In some embodiments, the device further includes a background switching module for switching the background color of the target interface based on a preset background switching timing.

[0101] In some implementations, different gaze sub-regions among the plurality of gaze sub-regions have different colors.

[0102] In some embodiments, the data acquisition module 608 is specifically used to: filter out valid eye images from the target eye images based on the gaze feedback information; wherein the gaze feedback information corresponding to the valid eye images is correct; and perform gaze annotation operation on the valid eye images based on the position of the first gaze area corresponding to the valid eye images to obtain the eye tracking data of the target user.

[0103] In some embodiments, the data acquisition module 608 is specifically used to: acquire the pixel differences between target eye images corresponding to different display cycles at the same position of the first gaze area on the target interface; and filter out valid eye images from the target eye images based on the pixel differences between the target eye images corresponding to different display cycles at the same position, and the gaze feedback information corresponding to each display cycle at each position of the first gaze area on the target interface.

[0104] In some embodiments, the data acquisition module 608 is specifically used to: obtain a first confidence score for the target eye images corresponding to different display cycles at the same location based on the comparison result of the pixel difference between the target eye images corresponding to different display cycles at the same location and a preset difference threshold; obtain a second confidence score for the target eye images corresponding to each display cycle based on the correctness judgment result of the gaze feedback information corresponding to each display cycle at each location of the first gaze area on the target interface; and filter out valid eye images from the target eye images based on the first confidence score and the second confidence score corresponding to the target eye images.

[0105] The eye-tracking data acquisition device provided in this disclosure can execute the eye-tracking data acquisition method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects of executing the method.

[0106] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described device embodiments can be referred to the corresponding process in the method embodiments, and will not be repeated here.

[0107] This disclosure provides an electronic device, which includes: a storage device storing a computer program thereon; and a processing device for executing the computer program in the storage device to implement the steps of any method of this disclosure.

[0108] The following is for reference. Figure 7 The diagram illustrates a structural schematic of an electronic device 700 suitable for implementing embodiments of the present disclosure. Terminal devices in embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0109] like Figure 7 As shown, the electronic device 700 may include a processing unit (e.g., a central processing unit, a graphics processor, etc.) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage device 708 into a random access memory (RAM) 703. The RAM 703 also stores various programs and data required for the operation of the electronic device 700. The processing unit 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0110] Typically, the following devices can be connected to I / O interface 705: input devices 706 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 707 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 708 including, for example, magnetic tapes, hard disks, etc.; and communication devices 709. Communication device 709 allows electronic device 700 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 7An electronic device 700 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0111] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 709, or installed from storage device 708, or installed from ROM 702. When the computer program is executed by processing device 701, it performs the functions defined in the methods of embodiments of this disclosure.

[0112] In addition to the methods and devices described above, embodiments of this disclosure can also be computer program products, comprising computer program instructions that, when executed by a processor, cause the processor to perform the methods provided in the embodiments of this disclosure. The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this disclosure. These programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on a user computing device, partially on a user device, as a standalone software package, partially on a user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0113] Furthermore, embodiments of this disclosure may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the eye-tracking data acquisition method provided in embodiments of this disclosure.

[0114] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0115] This disclosure also provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the eye-tracking data acquisition method of this disclosure.

[0116] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0117] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0118] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0119] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0120] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0121] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for acquiring eye-tracking data, characterized in that, include: A first gaze area is displayed on the target interface; wherein the first gaze area is filled with the target color; In response to the fact that the display area of ​​the first gaze area is not greater than a preset area threshold, the second gaze area is statically displayed for a preset duration; wherein, the second gaze area is divided into multiple gaze sub-areas, the multiple gaze sub-areas include a gaze sub-area filled with the target color, and the colors of the other gaze sub-areas besides the gaze sub-area filled with the target color are different from the target color; Acquire gaze feedback information of the target user, and acquire the target eye image of the target user during the display in the first gaze area; wherein, the gaze feedback information is the information of the target gaze sub-region that matches the target color among the plurality of gaze sub-regions reported by the target user; Based on the gaze feedback information and the target eye image, eye-tracking data of the target user is collected.

2. The method according to claim 1, characterized in that, Displaying the first gaze area on the target interface includes: In response to the fulfillment of preset display conditions, a first gaze area is displayed on the target interface; the preset display conditions include one or more of the following: receiving a display instruction for the first gaze area, satisfying the position switching conditions of the first gaze area, and satisfying the color switching conditions of the first gaze area.

3. The method according to claim 2, characterized in that, The position switching conditions include one or more of the following: the first gaze area reaches the same position on the target interface a specified number of display cycles, the gaze feedback information corresponding to the previous display cycle of the first gaze area is incorrect, or the gaze feedback information corresponding to the previous display cycle of the first gaze area is not obtained within a specified time. The color switching condition includes: the gaze feedback information corresponding to the previous display cycle of the first gaze area is correct; The first gaze area is filled with one color in one display cycle, and the color filled with the first gaze area is different in different display cycles. There is a preset color disappearance time interval between adjacent display cycles of the first gaze area.

4. The method according to claim 2, characterized in that, Displaying the first gaze area on the target interface includes: Determine the first display position of the first gaze area on the target interface; wherein, under the condition of the position switching of the first gaze area, the first display position is a position different from the previous display position of the first gaze area; Determine the target color to be filled in the first gaze area; wherein, under the condition of satisfying the color switching, the target color is a color different from the color filled in the first gaze area in the previous display cycle; Based on the first display position and the target color, a first gaze area is displayed on the target interface.

5. The method according to claim 1 or 4, characterized in that, Displaying the first gaze area on the target interface includes: Based on a preset size gradient strategy, a first gaze area is displayed on the target interface; wherein, the size gradient strategy is used to instruct the first gaze area to gradually change from a first size to a second size within a display cycle, the first size being larger than the second size; and / or, Obtain the depth value corresponding to the first gaze region; based on the depth value, display the first gaze region on the target interface; wherein the depth value is a randomly generated value or a preset value.

6. The method according to claim 1, characterized in that, The second gaze area is statically displayed for a preset duration, including: Based on the first display position of the first gaze area on the target interface and the preset relative positional relationship between the first gaze area and the second gaze area, the second display position of the second gaze area on the target interface is determined. Based on the second display position on the target interface, the second gaze area is statically displayed for a preset duration.

7. The method according to claim 1 or 6, characterized in that, The static display of the second gaze area within a preset duration includes: Randomly assign the orientation of multiple gaze sub-regions within the second gaze region; Based on the orientation of the multiple gaze sub-regions, the second gaze region is statically displayed for a preset duration.

8. The method according to claim 1, characterized in that, The second gaze area is a hollow ring-shaped region, and the first gaze area is located within the hollow ring of the second gaze area.

9. The method according to claim 8, characterized in that, The method further includes: During the display period when the display area of ​​the first gaze area is greater than a preset area threshold, the second gaze area is continuously rotated; The step of displaying a second gaze area on the target interface in response to the first gaze area not exceeding a preset area threshold includes: In response to the fact that the display area of ​​the first gaze area is not greater than a preset area threshold, the rotation of the second gaze area is stopped, and the second gaze area is statically displayed for a preset time period based on the orientation of the multiple gaze sub-areas in the second gaze area when the rotation is stopped.

10. The method according to claim 9, characterized in that, The method further includes: After the preset duration is reached, continue rotating the second gaze area; or, After the preset duration is reached, the display position of the second gaze area is changed, and the second gaze area is continuously rotated during the position change; wherein the changed display position of the second gaze area is related to the next display position of the first gaze area.

11. The method according to claim 8, characterized in that, The size of the second gaze area is related to the size of the first gaze area, and the size of the second gaze area changes as the size of the first gaze area changes.

12. The method according to claim 1, characterized in that, The method further includes: The background color of the target interface is switched based on a preset background switching timing.

13. The method according to claim 1, characterized in that, The different gaze sub-regions among the multiple gaze sub-regions have different colors.

14. The method according to claim 1, characterized in that, The step of collecting eye-tracking data of the target user based on the gaze feedback information and the target eye image includes: Based on the gaze feedback information, valid eye images are selected from the target eye images; wherein the gaze feedback information corresponding to the valid eye images is correct. Based on the position of the first gaze region corresponding to the effective eye image, gaze annotation is performed on the effective eye image to obtain the eye-tracking data of the target user.

15. The method according to claim 14, characterized in that, The step of filtering valid eye images from the target eye images based on the gaze feedback information includes: Acquire the pixel differences between target eye images corresponding to different display cycles at the same location of the first gaze area on the target interface; Based on the pixel differences between the target eye images corresponding to different display cycles at the same location, and the gaze feedback information corresponding to each display cycle at each location of the first gaze area on the target interface, valid eye images are selected from the target eye images.

16. The method according to claim 15, characterized in that, The step of filtering valid eye images from the target eye images includes: Based on the comparison results of the pixel differences between the target eye images corresponding to different display cycles at the same location and the preset difference threshold, the first confidence score of the target eye images corresponding to different display cycles at the same location is obtained. Based on the correctness judgment result of the gaze feedback information corresponding to each display cycle at each position of the first gaze area on the target interface, a second confidence score of the target eye image corresponding to each display cycle is obtained. Based on the first confidence score and the second confidence score corresponding to the target eye image, valid eye images are selected from the target eye images.

17. A device for acquiring eye-tracking data, characterized in that, include: The first display module is used to display a first gaze area on the target interface; wherein the first gaze area is filled with the target color; The second display module is used to statically display the second gaze area for a preset duration in response to the display area of ​​the first gaze area not being greater than a preset area threshold; wherein the second gaze area is divided into multiple gaze sub-areas, the multiple gaze sub-areas including a gaze sub-area filled with the target color, and the colors of the other gaze sub-areas besides the gaze sub-area filled with the target color are different from the target color. The acquisition module is used to acquire gaze feedback information of the target user and to acquire the target eye image of the target user during the display in the first gaze area; wherein, the gaze feedback information is the information of the target gaze sub-region that matches the target color among the plurality of gaze sub-regions fed back by the target user; The data acquisition module is used to acquire eye-tracking data of the target user based on the gaze feedback information and the target eye image.

18. An electronic device, characterized in that, The electronic device includes: A storage device on which computer programs are stored; A processing device for executing the computer program in the storage device to implement the steps of the eye-tracking data acquisition method according to any one of claims 1-17.

19. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for executing the eye-tracking data acquisition method according to any one of claims 1-16.

20. A computer program product, characterized in that, The method includes a computer program that, when executed by a processor, implements the method for acquiring eye-tracking data according to any one of claims 1-16.

Images