Eye movement tracking test method and test system based on virtual reality technology
By building an associated score structure tree in eye movement tracking test and filtering test tasks and eye movement indicators suitable for users, the problem of eye movement indicator deviation and cognitive information unreliable caused by test tasks in the prior art is solved. , achieving higher accuracy and reliability.
Patent Information
- Application Number
- CN202411099959.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-12
- Publication Date
- 2024-11-08
AI Technical Summary
In the existing eye movement tracking test methods, when the test task is not suitable for users, it leads to eye movement indicator deviation and cognitive information results unreliable.
Using the eye tracking test method based on virtual reality technology, by calculating the correlation scores between multiple test tasks, building a structure tree, and performing eye tracking tests on users in the order of correlation scores from high to low, filtering out Test tasks and eye movement indicators suitable for users, improving the accuracy of eye movement indicators.
It improves the accuracy of eye movement indicators and the reliability of cognitive information results, provides more effective user matching testing tasks, and reduces the impact of invalid eye movement indicators.
Smart Images

Figure CN118902377A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of eye tracking, and in particular to a test method and a test system for eye tracking based on virtual reality technology. Background Art
[0002] Eye tracking technology mainly uses infrared to record the user's eye movement to generate a variety of eye movement indicators, such as area of interest, fixation point, eye saccade frequency, fixation duration, etc., and then uses a computer to analyze the eye movement indicators to obtain cognitive information related to the user, which is then used to assess the user's health status. Therefore, eye tracking technology is often used in the field of clinical research.
[0003] During the test, the user's eyes respond to the test tasks displayed on the display interface, and then the user's response behaviors are recorded by infrared to obtain a variety of eye movement indicators. However, different test tasks have different degrees of stimulation to the user, which makes the user's response behaviors different. When the selected test task is not suitable for the user, not only will the eye movement indicators obtained be biased, but the cognitive information results obtained in the subsequent analysis will also be unreliable. Therefore, there is an urgent need for a test method for improving the accuracy of the user's eye movement indicators. Summary of the invention
[0004] In order to solve the problem that the cognitive information results obtained based on eye movement indicator analysis are unreliable, the present application provides an eye movement tracking test method and test system based on virtual reality technology.
[0005] In a first aspect of the present application, a test method for eye tracking based on virtual reality technology is provided. The method comprises: Acquire multiple test tasks, where the test tasks are used to perform an eye tracking test on a user; Calculate the correlation scores between the multiple test tasks, and arrange the multiple test tasks in descending order of the correlation scores to obtain a structure tree, wherein the structure tree consists of a trunk and branches, the test task at the bottom of the trunk has the largest correlation score and is determined as the root node, the test tasks on the trunk except the root node are determined as leaf nodes, and the test tasks on the branches are determined as leaf nodes; Performing an eye tracking test on the user in a test direction from the root node of the structure tree toward the leaf node, and obtaining the eye movement index of the user; The next test task is determined according to the test progress of the structure tree and the eye movement index.
[0006] By adopting the above technical solution, based on the obtained multiple test tasks, the correlation scores between the multiple test tasks are first calculated, and the multiple test tasks are arranged in order of correlation scores from high to low to obtain a structure tree. Since the structure tree is obtained by arranging the multiple test tasks in order of correlation scores from high to low, the classification of the test tasks is more obvious from the root node to the leaf node. Therefore, in the process of performing eye tracking tests on users in sequence in the test direction from the root node to the leaf node of the structure tree, the eye movement indicators are used as the basis for selecting one or more types of test tasks adapted to the user, the effective eye movement indicators are retained, and the invalid eye movement indicators are filtered out, which can improve the accuracy of the obtained eye movement indicators, thereby providing data support for improving the reliability of the obtained cognitive information results.
[0007] In a possible implementation manner: the branch includes at least one level, and at least one test task is set on each level; The determining the next test task according to the test progress of the structure tree and the eye movement index comprises: Determine whether the current test task is located on a trigger node according to the test progress of the structure tree, wherein the trigger node is the last leaf node of each level on each branch; If so, the level where the current test task is located is determined as the target level, the eye movement indicators corresponding to all the test tasks on the target level are retrieved, and the test task on the target level corresponding to the eye movement indicator that exceeds the threshold range is used as the parent node, and the test task on the child node under the parent node is determined as the next test task; If not, traverse the target level and retrieve the test tasks that are in order after the current test task until the current test task is on the trigger node, then retrieve the eye movement indicators corresponding to all the test tasks on the target level, and take the test task on the target level corresponding to the eye movement indicators that exceed the threshold range as the parent node, and the test task on the child node under the parent node is determined as the next test task.
[0008] By adopting the above technical solution, when the test progress reaches the trigger node of the branch, the eye movement indicators corresponding to all test tasks on the target level are retrieved, and the next test task is determined based on the eye movement indicators, thereby ensuring that the test task matching the user can be further determined from the branch.
[0009] In a possible implementation, the method further includes retaining eye movement indicators corresponding to the test tasks on the trunk and eye movement indicators on each level of the branches that exceed a threshold range.
[0010] In a possible implementation, the method further includes retaining the eye movement index corresponding to the test task on the trunk and the eye movement index at each level of the branch as an extreme value, wherein the extreme value is a maximum value or a minimum value.
[0011] By adopting the above technical solution, in the two methods of selecting the eye movement indicators to be retained provided above, the eye movement indicators corresponding to the test tasks on the trunk are retained, so the accuracy of the obtained eye movement indicators can be guaranteed. When the eye movement indicators that exceed the threshold range are retained at each level of the branch, the accuracy of the obtained eye movement indicators is further improved because the richness of the eye movement indicator data is increased and the effective eye movement indicators are increased. In addition, when the eye movement indicators as extreme values are retained at each level of the branch, not only the effective eye movement indicators are retained, further improving the accuracy of the obtained eye movement indicators, but also because the amount of added eye movement indicator data is small, the efficiency of obtaining accurate eye movement indicators can be improved.
[0012] In a possible implementation: the test task includes test items and test requirements; The calculating the correlation scores between the plurality of test tasks comprises: Calculate a first score according to the test item; Calculate a second score according to the test requirements; The correlation score is obtained by calculating the sum of the first score and the second score.
[0013] In a possible implementation manner, the step of calculating the first score according to the test item includes: Obtaining a basic score according to the type of the test item; Determining the number of unit scores according to the number of identical and similar data items between the test items; The first score is obtained by adding the basic score and the determined unit score.
[0014] By adopting the above technical solution, the accuracy of the obtained correlation score can be guaranteed based on the type of test item, the number of identical and similar data items of the test item, and the test requirements as influencing factors for calculating the correlation score, thereby providing data support for obtaining accurate eye movement indicators.
[0015] In a possible implementation, the obtaining of multiple test tasks includes: A plurality of the test tasks are obtained by matching the basic information of the user, wherein the basic information includes gender, age, occupation and health status, and the health status is used to record whether the user has health problems such as color blindness, color weakness and hearing impairment; By adopting the above technical solution, the test tasks corresponding to the user are preliminarily matched according to the user's basic information, and then a structure tree is established according to the matched test tasks, so as to facilitate the subsequent matching of test tasks that are more suitable for the user from the structure tree.
[0016] In a second aspect of the present application, a test system for eye tracking based on virtual reality technology is provided. The system includes a test module and a control module for implementing any of the above-mentioned eye tracking test methods based on virtual reality technology; The test module includes VR glasses and earphones, wherein the earphones are hinged to the inner side walls of the temples of the VR glasses; The control module is communicatively connected to the VR glasses and the earphones respectively.
[0017] In a possible implementation manner: the earphone is a circumaural earphone.
[0018] In a possible implementation, closed silicone is provided on the inner side of the frame of the VR glasses.
[0019] By adopting the above technical solution, on the one hand, VR glasses and headphones are connected as one through the temples, with a simple appearance, light and comfortable to wear, reducing the burden on users, making the collected eye movement indicators more real and accurate; on the other hand, the headphones are hinged on the inner wall of the temples of the VR glasses, which can flexibly adjust the position of the headphones, and the headphones can shield external sound interference, and are used to perform audio playback test tasks, increasing the diversity of test tasks. In addition, VR glasses can not only present clear graphics, videos, virtual scenes, etc., but also make VR glasses fit the user's eyes more closely by setting up closed silicone, isolating external visual interference, and providing hardware support for obtaining accurate eye movement indicators.
[0020] In summary, the present application includes at least one of the following beneficial technical effects: 1. From the data level: This application first preliminarily selects multiple test tasks that match the user based on the user's basic information, then calculates the correlation scores between the multiple test tasks, and arranges the multiple test tasks in order of correlation scores from high to low to obtain a structure tree. Since the structure tree is obtained by arranging multiple test tasks in order of correlation scores from high to low, the classification of test tasks becomes more obvious from the root node to the leaf node. Therefore, in the process of performing eye tracking tests on users in sequence from the root node to the leaf node of the structure tree, the eye movement indicators are used as the basis for selecting one or more types of test tasks that are adapted to the user, the valid eye movement indicators are retained, and the invalid eye movement indicators are filtered out, which can improve the accuracy of the obtained eye movement indicators, thereby providing data support for improving the reliability of the obtained cognitive information results; 2. From the hardware level: VR glasses and headphones are designed as an integrated whole, and the inside of the frame of VR glasses is provided with closed silicone. The test module has a simple appearance, is light and comfortable to wear, reduces the user's usage burden, and makes the collected eye movement indicators more real and accurate. At the same time, the headphones can block external sound interference, and VR glasses can isolate external visual interference. While increasing the diversity of test tasks, it can also ensure that users are provided with an interference-free test environment, providing hardware support for obtaining accurate eye movement indicators. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] Figure 1 It is a structural diagram of an eye tracking test system based on virtual reality technology in an embodiment of the present application.
[0022] Figure 2 It is a flow chart of the eye tracking testing method based on virtual reality technology in an embodiment of the present application.
[0023] Figure 3 This is an example diagram of a structure tree obtained by arranging multiple test tasks in descending order of correlation scores in an embodiment of the method of the present application.
[0024] Explanation of the accompanying drawings: 1. test module; 11. VR glasses; 12. headphones; 2. control module; 21. server; 22. display screen. DETAILED DESCRIPTION
[0025] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0026] Figure 1 The structure diagram of the eye tracking test system based on virtual reality technology according to the embodiment of the present application is shown. The test system includes a test module 1 and a control module 2. The test module 1 is used to perform an eye tracking test on the user and collect the user's response behavior during the test. It also generates eye movement indicators based on the user's response behavior and transmits them to the control module 2. The eye movement indicators include indicators such as the area of interest, fixation point, eye saccade frequency, and fixation duration. The control module 2 can not only analyze the user's cognitive information based on the eye movement indicators, but also automatically adjust the test parameters of the test module 1 based on the eye movement indicators.
[0027] The test module 1 includes VR glasses 11 and earphones 12. The VR glasses 11 and earphones 12 are of an integrated design. Specifically, the earphones 12 are arranged on the temples of the VR glasses 11. In this example, the earphones 12 are circumaural earphones, which are hinged on the inner side walls of the temples so that the position of the earphones 12 can be flexibly adjusted. Among the two temples of the VR glasses 11, a hook is arranged on the movable end (the end away from the frame) of one of the temples, and an elastic band is connected to the movable end of the other temple. A loop matching the hook is arranged on the elastic band. The VR glasses 11 are fixed by the cooperation of the hook and the loop to prevent the VR glasses 11 from slipping. The inner side of the frame of the VR glasses 11 is provided with closed silicone, which can fit around the user's eyes to isolate them from external visual interference. An infrared camera is arranged between the two frames or on the inner side of the two frames. The infrared camera captures the user's eye movement at close range when the virtual screen of the VR glasses 11 plays videos, pictures, web pages or the headphones 12 play audio, and transmits it to the control module 2 through wired or wireless transmission. That is, the test module 1 supports both wired and wireless transmission modes. Wired transmission is through cable transmission, and wireless transmission is Bluetooth technology transmission, WIFI technology transmission or 4G / 5G network transmission.
[0028] The control module 2 includes a server 21 and a display screen 22 connected to the server 21. The server 21 is provided with a big data model. The eye movement index of a normal user is obtained through training of the big data model. After obtaining the eye movement index input by the test module 1, the input eye movement index is compared with the eye movement index of the normal user to analyze the user's cognitive information. The display screen 22 is used to display the cognitive information analyzed by the server 21. In addition, the server 21 can also automatically adjust the test parameters of the test module 1 according to the eye movement index, thereby optimizing the accuracy of the eye movement index obtained by the test module 1.
[0029] It should be noted that Figure 1 The test system shown is only illustrative and is not intended to limit the application or use of the embodiments of the present application. For example, the test system may include multiple test modules 1, and one control module 2 may control multiple test modules 1 simultaneously.
[0030] Figure 2 A flow chart of a test method for eye tracking based on virtual reality technology according to an embodiment of the present application is shown. The method is applied in the control module 2, specifically in the server 21. The main process of the test method is described as follows.
[0031] Step S1: obtaining a plurality of test tasks, where the test tasks are used to perform an eye tracking test on a user.
[0032] The test task includes test items and test requirements. The test items include images, videos, web pages, audio, text and other items that can stimulate users, while the test requirements include free observation, visual search, reading, picture viewing, video viewing and other requirements for users to respond to the test items. It should be noted that a test task only includes one test item and one test requirement, so that it is convenient to select the test task adapted to the user from multiple test tasks, that is, to know the combination of test items and test requirements adapted to the user, so as to improve the accuracy of the obtained eye movement indicators.
[0033] Multiple test tasks are stored in a database. The database can be set in the control module 2 or in an external memory. The memory is connected to the control module 2, and the control module 2 can call the data in the external memory.
[0034] The control module 2 selects a test task that matches the user from the database based on the user's basic information, that is, the control module 2 obtains multiple test tasks. Specifically, the user's basic information includes information such as gender, age, occupation, and health status. The health status mainly records whether the user has health problems such as color blindness, color weakness, and hearing impairment. Then, multiple test tasks are retrieved from the database based on the user's basic information. For example, if the user is old, a test task with a low audio volume and high image clarity is selected. If the user has a hearing impairment, all test tasks except the audio test tasks will be exported.
[0035] Step S2, calculate the correlation scores between multiple test tasks, and arrange the multiple test tasks in order of correlation scores from high to low to obtain a structure tree, the structure tree consists of a trunk and branches, the test task located at the bottom of the trunk has the largest correlation score and is determined as the root node, the test tasks on the trunk except the root node are determined as leaf nodes and the test tasks located on the branches are also determined as leaf nodes.
[0036] The server 21 is provided with a calculation model, which is used to calculate the correlation scores between multiple test tasks. The calculation model is a model trained in advance using a large number of test tasks. In order to facilitate the explanation of the specific calculation process, the calculation of the correlation score between any two test tasks is taken as an example: First, the first score is calculated based on the test items. The first score is calculated based on the type of the test items and the similarity value of the test items. Specifically, if the test items belong to the same type, a preset basic score is obtained by matching, such as a fixed score of 10 points, 20 points, etc. Otherwise, when the types of the test items are different, the basic score obtained by matching is 0 points. For example, if both test items are images, the basic score is 10 points, and if the two test items are images and videos respectively, the basic score of the matching is 0 points due to the different types. Then, the similarity value between the test items is calculated, specifically to determine the same and similar data items between the test items, such as color, display size, font, text, audio volume, audio content, audio accent, etc. If one of them is the same or similar, a unit score is added to the basic score. The unit score here is 1 point. In other examples, the unit score can also be customized. The number of added unit scores is equal to the number of identical data items, that is, if there are several identical data items, several unit scores are added on the basis of the basic score to obtain the first score.
[0037] At the same time, the second score is calculated according to the test requirements. Similar to the basic score obtained by matching the types of test items, if the test requirements of the two test tasks are the same, a preset second score is obtained by matching, and the preset second score is greater than the preset basic score, but less than twice the preset basic score. Otherwise, when the test requirements of the two test tasks are different, the second score obtained by matching is 0 points.
[0038] Then, based on the first score and the second score between any two test tasks, the sum of the first score and the second score is calculated to obtain the correlation score between the two test tasks.
[0039] Therefore, the correlation scores between all test tasks can be calculated through the above calculation process.
[0040] After calculating the correlation scores between all test tasks, multiple test tasks are arranged in descending order of correlation scores to obtain a structure tree. Specifically, the structure tree is mainly divided into a trunk and branches. The test tasks at the bottom of the trunk have the largest correlation score, and the test tasks at the bottom of the trunk are used as root nodes. The test tasks on the trunk except the root node are determined as leaf nodes, and the test tasks on the branches are all determined as leaf nodes.
[0041] Since the test tasks on the same leaf node have different correlation scores, and some test tasks do not even have a correlation relationship, the structure tree is presented in a hierarchical manner as a whole. The higher the correlation score between test tasks, the higher the level of the test task on the leaf node, and the closer it is to the root node; and when the correlation score between test tasks is smaller, the lower the level of the test task on the leaf node, and the farther away from the root node. At the same time, multiple test tasks with a correlation relationship also form a branch, and the test tasks located at the branch point serve as branch nodes. In addition to the branch nodes, the remaining leaf nodes on the same branch are also presented in a hierarchical manner. For the sake of convenience of display and explanation, for example Figure 3 As shown in the figure, assuming that there are test tasks a, b, c, d, e, f, g, h, i, j, k, l, m, n, a is located at the root node, a, c, g form the trunk, represented by a dotted line. b and e form a branch, b is a branch node; c, f, j, k form a branch, c is a branch node; g and k form a branch, g is a branch node; c and h form a branch, c is also a branch node; d and h form a branch, d is a branch node; d, i, l, m, n also form a branch, d is also a branch node.
[0042] Step S3: perform an eye tracking test on the user in a test direction from the root node of the structure tree toward the leaf node, and obtain the user's eye movement index.
[0043] Since the structure tree is obtained by sorting multiple test tasks from high to low according to the associated scores, the classification of test tasks is more obvious from the root node to the leaf node. Therefore, performing eye tracking tests on users in the direction from the root node of the structure tree toward the leaf node can gradually match more suitable test tasks for users.
[0044] During the test, in addition to performing eye tracking tests on users in the test direction from the root node to the leaf node, when there are multiple test tasks at the same level on the same branch, each test task is called in sequence from left to right or from right to left for testing, such as Figure 3 In the example, l, m, and n are on the same level. If they are called from left to right, the order is l, m, and n; if they are called from right to left, the order is n, m, and l. At the same time, after each test task is completed, the user's corresponding eye movement indicators need to be recorded.
[0045] Step S4: determine the next test task according to the test progress and eye movement index of the structure tree.
[0046] Step S41: Determine whether the current test task is located on a trigger node according to the test progress of the structure tree. The trigger node is the last leaf node of each level on each branch. Figure 3 In the example, when the calling order is from left to right, in the branch consisting of b and e, e is the trigger node; in the branch consisting of c, f, j, k, at the level where j and k are located, k is the trigger node; and so on, in the branch consisting of d, i, l, m, n, at the level where l, m, n are located, n is the trigger node. In other words, the trigger node may be different depending on the calling order, except when there is only one leaf node at the level of the branch.
[0047] Step S42, if yes, then the level where the current test task is located is determined as the target level, the eye movement indicators corresponding to all the test tasks on the target level are retrieved, and the test task on the target level corresponding to the eye movement indicators that exceed the threshold range is used as the parent node, and the test task on the child node under the parent node is determined as the next test task. It should be noted that the threshold range is calculated in advance, specifically a numerical range calculated by the server 21 based on the eye movement indicators of normal users. When the user's eye movement indicators exceed the threshold range, it means that the user has health problems in this aspect, and it is necessary to further match the corresponding test tasks to obtain more accurate eye movement indicators. In addition, the correspondence between the parent node and the child node is as shown in the figure. Figure 3 In the example, i is the parent node, and l, m, and n are all child nodes of i.
[0048] Step S43, otherwise, continue to traverse the target level and call the test tasks that are located after the current test task in order until the current test task is located on the trigger node, call the eye movement indicators corresponding to all the test tasks on the target level respectively, and use the test task on the target level corresponding to the eye movement indicators that exceed the threshold range as the parent node, and the test task on the child node under the parent node is determined as the next test task.
[0049] It can be seen that in order to select test tasks that match the user from multiple levels of multiple branches, the last leaf node on each level of each branch is used as a trigger node. When the current test task is determined to be on the trigger node based on the test progress, the test task on the target level whose eye movement indicators exceed the threshold range is locked, and the test task on the next level that is associated with the test task is used as the next test task.
[0050] In this example, after traversing each branch, the eye movement indicators corresponding to the test tasks on the output trunk and the eye movement indicators on each level of the branches that exceed the threshold range, or the eye movement indicators corresponding to the test tasks on the output trunk and the eye movement indicators on each level of the branches are used as extreme values, and the extreme values are maximum values or minimum values. That is, the present application retains the eye movement indicators that exceed the threshold range, and other eye movement indicators that are no different from normal users are considered invalid eye movement indicators, and the invalid eye movement indicators are filtered out to prevent the invalid eye movement indicators from affecting the cognitive information results obtained based on the eye movement indicators, thereby achieving the purpose of improving the accuracy of the obtained eye movement indicators, and further providing data support for improving the reliability of the cognitive information results obtained based on the eye movement indicator analysis.
[0051] In summary, the implementation principle of the eye tracking test method based on virtual reality technology in the embodiment of the present application is: first, preliminarily select multiple test tasks that match the user according to the basic information of the user, then calculate the correlation scores between the multiple test tasks, and arrange the multiple test tasks in order from high to low according to the correlation scores to obtain a structure tree. Since the structure tree is obtained by arranging multiple test tasks in order from high to low according to the correlation scores, the classification of the test tasks is more obvious from the test direction from the root node to the leaf node. Therefore, the eye tracking test of the user is performed in sequence from the root node of the structure tree to the leaf node. During the test, the test tasks that can cause the user's eye movement index fluctuations in each level are retained, and other invalid eye movement indicators will be filtered out, thereby improving the accuracy of the obtained eye movement indicators, and then providing data support for improving the reliability of the obtained cognitive information results.
[0052] In order to better execute the program of the above method, the present application also provides an eye tracking test device based on virtual reality technology, which includes a memory and a processor.
[0053] The memory may be used to store instructions, programs, codes, code sets or instruction sets. The memory may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing the above-mentioned eye tracking test method based on virtual reality technology, etc.; the data storage area may store data involved in the above-mentioned eye tracking test method based on virtual reality technology, etc.
[0054] The processor may include one or more processing cores. The processor calls the data stored in the memory by running or executing the instructions, programs, code sets or instruction sets stored in the memory, performs various functions of the present application and processes data. The processor may be at least one of a special purpose integrated circuit, a digital signal processor, a digital signal processing device, a programmable logic device, a field programmable gate array, a central processing unit, a controller, a microcontroller and a microprocessor. It is understandable that for different devices, the electronic device used to implement the above-mentioned processor function can also be other, and the embodiments of the present application are not specifically limited.
[0055] The present application also provides a computer-readable storage medium, for example, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes. The computer-readable storage medium stores a computer program that can be loaded by a processor and execute the above-mentioned eye tracking test method based on virtual reality technology.
[0056] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present application (but not limited to) by each other to form a technical solution.
Claims
1. A test method for eye tracking based on virtual reality technology, It is characterized in that include: Acquire multiple test tasks, where the test tasks are used to perform an eye tracking test on a user; Calculate the correlation scores between the multiple test tasks, and arrange the multiple test tasks in descending order of the correlation scores to obtain a structure tree, wherein the structure tree consists of a trunk and branches, the test task at the bottom of the trunk has the largest correlation score and is determined as the root node, the test tasks on the trunk except the root node are determined as leaf nodes, and the test tasks on the branches are determined as leaf nodes; Performing an eye tracking test on the user in a test direction from the root node of the structure tree toward the leaf node, and obtaining the eye movement index of the user; The next test task is determined according to the test progress of the structure tree and the eye movement index.
2. The eye tracking testing method based on virtual reality technology according to claim 1, It is characterized in that The branch includes at least one level, and at least one test task is set on each level; The determining the next test task according to the test progress of the structure tree and the eye movement index comprises: Determine whether the current test task is located on a trigger node according to the test progress of the structure tree, wherein the trigger node is the last leaf node of each level on each branch; If so, the level where the current test task is located is determined as the target level, the eye movement indicators corresponding to all the test tasks on the target level are retrieved, and the test task on the target level corresponding to the eye movement indicator that exceeds the threshold range is used as the parent node, and the test task on the child node under the parent node is determined as the next test task; If not, traverse the target level and retrieve the test tasks that are in order after the current test task until the current test task is on the trigger node, then retrieve the eye movement indicators corresponding to all the test tasks on the target level, and take the test task on the target level corresponding to the eye movement indicators that exceed the threshold range as the parent node, and the test task on the child node under the parent node is determined as the next test task.
3. The eye tracking testing method based on virtual reality technology according to claim 2, It is characterized in that The method further includes: retaining the eye movement indicators corresponding to the test tasks on the trunk and the eye movement indicators exceeding the threshold range at each level of the branches.
4. The eye tracking testing method based on virtual reality technology according to claim 2, It is characterized in that The method further includes: retaining the eye movement index corresponding to the test task on the trunk and the eye movement index at each level of the branch as an extreme value, wherein the extreme value is a maximum value or a minimum value.
5. The eye tracking testing method based on virtual reality technology according to claim 1, It is characterized in that The test tasks include test items and test requirements; The calculating the correlation scores between the plurality of test tasks comprises: Calculate a first score according to the test item; Calculate a second score according to the test requirements; The correlation score is obtained by calculating the sum of the first score and the second score.
6. The eye tracking testing method based on virtual reality technology according to claim 5, It is characterized in that The step of calculating a first score according to the test item includes: Obtaining a basic score according to the type of the test item; Determining the number of unit scores according to the number of identical and similar data items between the test items; The first score is obtained by adding the basic score and the determined unit score.
7. The eye tracking testing method based on virtual reality technology according to claim 1, It is characterized in that The obtaining of multiple test tasks includes: A plurality of the test tasks are obtained by matching the basic information of the user, wherein the basic information includes gender, age, occupation and health status, and the health status is used to record whether the user has health problems such as color blindness, color weakness and hearing impairment.
8. An eye tracking test system based on virtual reality technology, It is characterized in that comprising a test module (1) and a control module (2) for executing the method according to any one of claims 1 to 7; The test module (1) comprises a VR pair of glasses (11) and an earphone (12), wherein the earphone (12) is hingedly connected to the inner wall of the temple of the VR pair of glasses (11); The control module (2) is communicatively connected to the VR glasses (11) and the earphone (12) respectively.
9. The eye tracking test system based on virtual reality technology according to claim 8, It is characterized in that The earphone (12) is a circumaural earphone.
10. The eye tracking test system based on virtual reality technology according to claim 8, It is characterized in that The inside of the frame of the VR glasses (11) is provided with closed silica gel.
