Visual function training system and method based on glasses type eye movement tracking multi-compliance

Abstract

The invention relates to the technical field of visual training, in particular to a visual function training system and method based on glasses type eye movement tracking multi-compliance, and the system comprises a single-chip microcomputer which is used for controlling the operation of training glasses and providing the multi-compliance training of the eyes of a user; the capturing module is used for capturing the eye movement path of the user in the eye multi-compliance training process; the matching degree evaluation module is used for acquiring the user eye movement path captured in the capturing module and evaluating the matching degree of the user eye movement path and a theoretical eye movement path; according to the method, good eye movement training service is provided for the user through self-adaptive pushing of the multi-compliance training video, meanwhile, the training effect of the user can be intelligently evaluated based on matching degree evaluation of the eye movement path, it is ensured that the eye movement training process of the user is more scientific and reasonable, and the eye movement training effect of the user is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of vision training, and in particular to a vision function training system and method based on glasses-type eye tracking multi-compliance. Background Art

[0002] Eye movement compliance training is a rehabilitation training method that uses specific equipment to guide the eyeballs to move along a specified trajectory. During training, patients need to perform scanning, tracking and other movements according to visual cues. It can effectively exercise eye muscles and improve eye movement control ability. It is often used to treat eye diseases such as strabismus and amblyopia, and also helps to improve attention and visual cognition.

[0003] The invention patent application with application number 201710474942.7 discloses a vision training system based on eye movement, including: an imaging module, configured to display electronic images; a virtual coordinate module, configured to establish a rectangular coordinate system in the plane where the virtual image is located, and the position of the virtual image in the plane is fixed; a normal view orientation module, configured to determine the normal view direction Q0 of the eye, the normal view direction Q0 is perpendicular to the plane where the virtual image is located and the line of sight of the eye along the normal view direction Q0 is concentrated on the center point 0 of the virtual image; a calling module, configured to obtain the standard refractive power D0 of the user's eye, and obtain the straight-line distance between the eye and the center point 0 of the virtual image as L0; a gaze orientation module, configured to detect the eye shape of the user, and obtain to the user's real-time gaze direction Q1; an optimal refractive power generating module is configured to obtain the straight-line distance L1 between the eye's gaze point 01 on the virtual image and the eye according to the distance L0, the gaze direction Q1 and the embrasure direction Q0, and obtain the real-time optimal refractive power D1 according to the distance L1 and the standard refractive power D0: an adjusting module is configured to adjust the zoom lens so that the refractive power of the area of ​​the zoom lens in front of the eye's lens is D1. This application aims to solve the problem that although the head-mounted display device can give people an immersive feeling, the virtual image of the electronic image is relatively close to the eyeball, which is equivalent to watching the electronic screen at a close distance. The ciliary muscle will remain in a tense state for a long time as mentioned above, causing myopia.

[0004] However, the current level of intelligence of this type of training equipment is low and it can only provide user training services. The control in aspects such as user training effect evaluation and intelligent provision of training videos to users still needs to be developed.

[0005] Therefore, a visual function training system and method based on glasses-type eye tracking multi-compliance is proposed. Summary of the invention

[0006] In view of the above-mentioned shortcomings of the prior art, the present invention provides a visual function training system and method based on glasses-type eye tracking multi-compliance, which solves the technical problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention is realized through the following technical solutions:

[0008] In a first aspect, a visual function training system based on glasses-type eye movement tracking and multiple compliance includes:

[0009] A single-chip microcomputer for controlling the operation of the training glasses and providing multiple compliance training for the user's eyes; a capture module for capturing the eye movement path of the user during the multiple compliance training of the eyes; a matching degree evaluation module for obtaining the eye movement path of the user captured by the capture module and evaluating the matching degree between the user's eye movement path and the theoretical eye movement path; a decision-making module for setting a matching determination threshold, obtaining the matching degree evaluation result in the matching degree evaluation module, comparing the evaluation result with the matching determination threshold, and making a decision based on the comparison result whether to continue the current eye compliance training of the user; a selection module for triggering the reset operation of the training glasses, controlling the training glasses to re-select the multiple compliance training videos stored internally, and providing multiple compliance training for the user's eyes again; an identification module for obtaining the matching degree evaluation results of each eye compliance training of the user and identifying the health status of the user's eye training based on the evaluation results.

[0010] Furthermore, the training glasses are AR glasses. When the user wears the AR glasses, the AR glasses play multiple compliance training videos to guide the user's eyeballs to make corresponding movements for training;

[0011] The training glasses are connected to the network to download a number of training videos, and each downloaded training video is bound with a theoretical eye movement path;

[0012] Among them, the eye movement paths bound to each training video are the paths formed by the corresponding theoretical guidance for the user's eyeballs to make corresponding movements in advance. The training glasses store the downloaded training videos, and the training video first provided to the user by the training glasses is the training video with the largest product of the complexity of the eye movement path and the size of the corresponding area among all the stored training videos.

[0013] Furthermore, the product of the complexity of the eye movement path and the size of the corresponding area is expressed as:

[0014] ;

[0015] In the formula: is the total number of intersection points and nodes in the eye movement path; is the distance between the i-th intersection point or node and the (i + 1)-th intersection point or node; is the size of the area defined by the connection of the outermost intersection points or nodes of the eye movement path;

[0016] Among them, represents the average value of for Indicates the complexity of the eye movement path.

[0017] Furthermore, the eye movement paths in both the capture module and the training glasses are composed of points and lines. During the eye movement path formation stage, the line type is set synchronously. The line type includes: maximum line width, minimum line width, and line width scaling ratio. During the eye movement path formation process, the actions of the user's eye pupil dilation or constriction are captured in real time, so that the eye movement path adjusts the line type in real time based on the actions of the user's eye pupil dilation or constriction. The unit of the line width scaling ratio is: mm / d, where mm is the line width of the eye movement path and d is the diameter of the eye pupil. The line type adjustment period of the eye movement path is 0.1 s.

[0018] Furthermore, the theoretical eye movement path applied in the matching degree evaluation module is the eye movement path bound to the training video used by the user during the multi-compliance training of the eyes. The matching degree between the user's eye movement path and the theoretical eye movement path is evaluated based on the similarity of the two eye movement paths;

[0019] ;

[0020] In the formula: is the matching degree between the user's eye movement path and the theoretical eye movement path; is the graph edit distance between the user's eye movement path and the theoretical eye movement path; is the maximum edit distance from the user's eye movement path and the theoretical eye movement path to the complete graph; is the maximum value within the parentheses; , are the total number of sampling points in the user's eye movement path and the theoretical eye movement path; is the line width at the position of the jth sampling point in the user's eye movement path and the theoretical eye movement path;

[0021] Among them, the complete graph is a path graph in which all nodes are connected to each other. The sampling points in the user's eye movement path and the theoretical eye movement path are manually edited by the user at the system end, and the distances between adjacent sampling points are equal.

[0022] Furthermore, the matching determination threshold in the decision module is user-defined by the user at the system end. When the evaluation result is greater than or equal to the determination threshold, the current eye compliance training of the user ends. Otherwise, the jump selection module further executes.

[0023] Furthermore, when the selection module controls the training glasses to select the multi-compliance training video, it follows:

[0024] Set the total duration of the user's eye training, and control the number of times that the total duration of the multi-compliance training videos continuously configured for the user exceeds the total duration of the user's eye training, which does not exceed two times;

[0025] Select the multi-compliance training video corresponding to the theoretical eye movement path with the highest difference from the previous user's eye movement path in the training glasses as the training video for the next application;

[0026] Among them, the theoretical eye movement path with the highest difference from the previous user's eye movement path is determined based on the calculation logic.

[0027] Furthermore, during the operation stage of the recognition module, obtain the evaluation results of each time of the matching degree evaluation module when the user conducts multi-compliance training through the training glasses each time. Select the maximum value and the minimum value from the evaluation results each time, and then calculate the average value of the maximum value and the minimum value, denoted as corresponding to each multi-compliance training, denoted as based on the time sequence;

[0028] Among them, when obtain the latest calculation results of no less than three times, and when the calculation results of no less than three times show a continuous upward trend based on the time sequence, it indicates that the user's eye training effect tends to be healthy, otherwise, it indicates that the user's eye training effect tends to deteriorate.

[0029] Furthermore, the single-chip microcomputer is interconnected with the training glasses through a medium electrically, the capture module is interconnected with the matching degree evaluation module through a local area network, the matching degree evaluation module is interconnected with the determination module and the selection module through a local area network, and the matching degree evaluation module and the selection module are interconnected with the recognition module through a local area network.

[0030] In the second aspect, a visual function training method based on glasses-type eye movement tracking multi-compliance includes the following steps:

[0031] Calculate the product of the complexity corresponding to the eye movement path of the eye multi-compliance training video stored in the training glasses and the size of the corresponding area;

[0032] Select the eye multi-compliance training video with the largest product and provide it to the user for training for the first time;

[0033] Evaluate the eye movement path of the user during the eye multi-compliance training process, and perform a matching degree evaluation with the theoretical eye movement path bound to the eye multi-compliance training video provided to the user;

[0034] Set the re-push logic of the eye multi-compliance training video, decide whether to provide the eye multi-compliance training video to the user again according to the evaluation result, and control the stop of the push operation based on the re-push logic of the eye multi-compliance training video;

[0035] Identify the health trend of the user's eye training according to the historical training results.

[0036] Adopting the technical solution provided by the present invention, compared with the known public technology, it has the following beneficial effects:

[0037] The present invention provides a visual function training system and method based on multi-compliance of glasses-type eye movement tracking. During the execution of the system and method, through the adaptive push of multi-compliance training videos, it provides users with good eye movement training services. At the same time, based on the matching degree evaluation of the eye movement path, it can intelligently evaluate the training effect of users, ensure that the user's eye movement training process is more scientific and reasonable, and guarantee the user's eye movement training effect.

[0038] In addition, during the execution process, it can also take into account the user's training fatigue degree, so that each eye movement training of the user can be carried out just right, promoting the user's rehabilitation and improvement process. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0040] Figure 1 It is a schematic structural diagram of a visual function training system based on multi-compliance of glasses-type eye movement tracking;

[0041] Figure 2 It is a schematic flowchart of a visual function training method based on multi-compliance of glasses-type eye movement tracking. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0043] The following further describes the present invention with reference to the embodiments.

[0044] Embodiment 1:

[0045] A visual function training system based on multi-compliance of glasses-type eye movement tracking in this embodiment, as Figure 1 shown, includes:

[0046] The training glasses are AR glasses. When the user wears the AR glasses, the AR glasses play multi-compliance training videos to guide the user's eyes to make corresponding movements for training;

[0047] The training glasses are connected to the network to download several training videos, and each downloaded training video is bound with a theoretical eye movement path;

[0048] Among them, the eye movement paths bound to each training video are all the paths formed by the corresponding theoretical guidance for the user's eyes to make corresponding movements preset. The training glasses store the downloaded training videos, and the training video provided to the user for the first time by the training glasses is the training video with the largest product of the complexity of the eye movement path and the size of the corresponding area among all the stored training videos;

[0049] The product of the complexity of the eye movement path and the size of the corresponding area is expressed as:

[0050] ;

[0051] In the formula: is the total amount of intersections and nodes in the eye movement path; is the distance between the i-th intersection or node and the i + 1-th intersection or node; is the size of the area defined by the connection of the outermost intersections or nodes of the eye movement path;

[0052] Among them, represents the average value of , represents the complexity of the eye movement path;

[0053] Through the above formula, the specific calculation logic of the product of the complexity of the eye movement path and the size of the corresponding area is defined;

[0054] A single-chip microcomputer is used to control the operation of the training glasses and provide multi-compliance training for the user's eyes;

[0055] A capture module is used to capture the eye movement path of the user during the multi-compliance training of the eyes;

[0056] The eye movement paths in both the capture module and the training glasses are composed of points and lines. During the formation stage of the eye movement path, the line type is set synchronously. The line type includes: the maximum line width, the minimum line width, and the line width scaling ratio. During the formation process of the eye movement path, the actions of the user's eye pupil dilation or constriction are captured in real time, so that the eye movement path adjusts the line type in real time based on the actions of the user's eye pupil dilation or constriction. The unit of the line width scaling ratio is: mm / d, where mm is the line width of the eye movement path and d is the diameter of the eye pupil. The line type adjustment period of the eye movement path is 0.1 s;

[0057] A matching degree evaluation module, which is used to obtain the user's eye movement path captured by the capture module and evaluate the matching degree between the user's eye movement path and the theoretical eye movement path;

[0058] The theoretical eye movement path applied in the matching degree evaluation module is the eye movement path bound to the training video used by the user during the multi-compliance training of the eyes. The matching degree between the user's eye movement path and the theoretical eye movement path is evaluated based on the similarity of the two eye movement paths;

[0059] ;

[0060] In the formula: is the matching degree between the user's eye movement path and the theoretical eye movement path; is the graph edit distance between the user's eye movement path and the theoretical eye movement path; is the maximum edit distance from the user's eye movement path and the theoretical eye movement path to the complete graph; is the maximum value within the parentheses; , are the total number of sampling points in the user's eye movement path and the theoretical eye movement path; is the line width at the position of the j-th sampling point in the user's eye movement path and the theoretical eye movement path;

[0061] Through the above logical formula, the matching degree between the user's eye movement path and the theoretical eye movement path is calculated, providing support for the operation of the decision-making module in this implementation;

[0062] Among them, the complete graph is a path graph in which all nodes are connected to each other. The sampling points in the user's eye movement path and the theoretical eye movement path are manually edited by the user at the system end, and the distances between adjacent sampling points are equal;

[0063] A decision-making module, which is used to set a matching determination threshold, obtain the matching degree evaluation result in the matching degree evaluation module, compare the evaluation result with the matching determination threshold, and make a decision on whether to continue the user's current eye compliance training based on the comparison result;

[0064] The matching determination threshold in the decision-making module is customized by the user at the system end. When the evaluation result is greater than or equal to the determination threshold, the user's current eye compliance training ends. Otherwise, it jumps to the selection module for further execution;

[0065] A selection module, which is used to trigger the reset operation of the training glasses, control the training glasses to re-select the multi-compliance training video stored internally, and provide the user with multi-compliance training for the eyes again;

[0066] When the selection module controls the training glasses to select the multi-compliance training video, it follows:

[0067] Set the total duration of the user's eye training, and control the number of times that the total duration of the multi-compliance training videos continuously configured for the user's eyes exceeds the total duration of the user's eye training to no more than two times;

[0068] Select the multi-compliance training video corresponding to the theoretical eye movement path with the highest difference from the user's previous eye movement path in the training glasses as the training video for the next application;

[0069] Among them, the theoretical eye movement path with the highest difference from the user's previous eye movement path is based on the calculation logic for determination;

[0070] An identification module, used to obtain the matching degree evaluation results of each time of the user's eye multi-compliance training, and identify the user's eye training health situation based on the evaluation results;

[0071] During the operation stage of the identification module, when obtaining each evaluation result of the matching degree evaluation module each time the user conducts multi-compliance training through the training glasses, select the maximum value and the minimum value from each evaluation result, and then calculate the average value of the maximum value and the minimum value, denoted as , corresponding to each multi-compliance training, denoted as based on the time sequence;

[0072] Among them, when obtain the latest calculation results of no less than three times, and when the calculation results of no less than three times show a continuous upward trend based on the time sequence, it indicates that the user's eye training effect tends to be healthy, otherwise, it indicates that the user's eye training effect tends to deteriorate;

[0073] The single-chip microcomputer is connected to the training glasses through medium electricity, the capture module is connected to the matching degree evaluation module through a local area network, the matching degree evaluation module is connected to the determination module and the selection module through a local area network, and the matching degree evaluation module and the selection module are connected to the identification module through a local area network.

[0074] In this embodiment, the single-chip microcomputer runs to control the operation of the training glasses, provides multi-compliance training for the user's eyes, the capture module runs later to capture the user's eye movement path during the multi-compliance training of the eyes, the matching degree evaluation module further obtains the user's eye movement path captured in the capture module, evaluates the matching degree between the user's eye movement path and the theoretical eye movement path, and then the decision module sets the matching determination threshold, obtains the matching degree evaluation result in the matching degree evaluation module, compares the evaluation result with the matching determination threshold, makes a decision on whether to continue the current eye compliance training of the user based on the comparison result, the selection module further triggers the training glasses to reset and run, controls the training glasses to re-select the multi-compliance training videos stored internally, provides multi-compliance training for the user's eyes again, and finally the identification module obtains the matching degree evaluation results of each time of the user's eye multi-compliance training, and identifies the user's eye training health situation based on the evaluation results.

[0075] Through the operation of the system in the above embodiments, when the user wears the training glasses for eye movement training, a more intelligent training service is provided, effectively controlling the training duration, synchronously maintaining the monitoring of the training health status, and ensuring that the user can continuously obtain stable eye movement training effects.

[0076] Embodiment 2:

[0077] At the specific implementation level, on the basis of Embodiment 1, this embodiment refers to Figure 2 to further specifically describe a visual function training system based on glasses-type eye movement tracking with multiple compliance in Embodiment 1:

[0078] A visual function training method based on glasses-type eye movement tracking with multiple compliance includes the following steps:

[0079] Calculate the product of the complexity corresponding to the eye movement path of the eye movement multiple compliance training video stored in the training glasses and the size of the corresponding area;

[0080] Select the eye movement multiple compliance training video with the largest product and provide it to the user for training for the first time;

[0081] Evaluate the eye movement path during the user's eye movement multiple compliance training process, and perform a matching degree evaluation with the theoretical eye movement path bound to the eye movement multiple compliance training video provided to the user;

[0082] Set the re-push logic of the eye movement multiple compliance training video, decide whether to provide the eye movement multiple compliance training video to the user again according to the evaluation result, and control the stop of the push operation based on the re-push logic of the eye movement multiple compliance training video;

[0083] Identify the user's eye training health status according to the historical training results.

[0084] In summary, during the execution of the system and method in the above embodiments, through the adaptive push of the multiple compliance training video, a good eye movement training service is provided to the user. At the same time, based on the matching degree evaluation of the eye movement path, the training effect of the user can be intelligently evaluated, ensuring that the user's eye movement training process is more scientific and reasonable, guaranteeing the user's eye movement training effect. At the same time, the training fatigue degree of the user can also be considered during the execution process, so that each eye movement training of the user can be carried out just right, promoting the user's rehabilitation and improvement process.

[0085] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A visual function training system based on glasses-type eye tracking multi-compliance, characterized in that: include: A single chip microcomputer is used to control the operation of the training glasses and provide users with multi-compliance eye training; A capture module, used to capture the eye movement path of the user during the eye multi-compliance training; A matching evaluation module is used to obtain the user's eye movement path captured in the capture module and evaluate the matching degree between the user's eye movement path and the theoretical eye movement path; A decision module is used to set a matching determination threshold, obtain a matching evaluation result from a matching evaluation module, compare the evaluation result with the matching determination threshold, and decide whether to continue the user's current eye compliance training based on the comparison result; A selection module is used to trigger the training glasses to reset and control the training glasses to reselect the multi-compliance training video stored internally, and provide the user with eye multi-compliance training again; The identification module is used to obtain the matching evaluation results of each user's eye multi-compliance training and identify the user's eye training health status based on the evaluation results.

2. The visual function training system based on glasses-type eye tracking multi-compliance according to claim 1, characterized in that: The training glasses are AR glasses. When the user wears the AR glasses, the AR glasses play a multi-compliance training video to guide the user's eyeballs to make corresponding movements for training; The training glasses download a number of training videos via the Internet, and each downloaded training video is bound to a theoretical eye movement path; Among them, the eye movement paths bound to each training video are all paths formed by the preset corresponding theories of each training video to guide the user's eyeballs to make corresponding movements. The training glasses store the downloaded training videos, and the training video that the training glasses provide to the user for the first time is the training video with the largest product of the complexity of the eye movement path and the size of the corresponding area among all stored training videos.

3. The visual function training system based on glasses-type eye tracking multi-compliance according to claim 1, characterized in that: The product of the complexity of the eye movement path and the size of the corresponding area is expressed as: ； Where: is the total number of intersections and nodes in the eye movement path; is the distance between the i-th intersection or node and the i+1-th intersection or node; The size of the area bounded by the outermost intersections or nodes of the eye movement paths; in, Express The average, Indicates the complexity of the eye movement path.

4. The visual function training system based on glasses-type eye tracking multi-compliance according to claim 1, characterized in that: The eye movement paths in the capture module and the training glasses are composed of points and lines. In the eye movement path forming stage, the line type is set synchronously, and the line type includes: maximum line width, minimum line width and line width scaling ratio. During the eye movement path forming process, the user's eye pupil dilation or contraction movement is captured in real time, so that the eye movement path adjusts the line type in real time based on the user's eye pupil dilation or contraction movement. The unit of the line width scaling ratio is: mm / d, mm is the eye movement path line width, d is the eye pupil diameter, and the line type adjustment period of the eye movement path is 0.1s.

5. The visual function training system based on glasses-type eye tracking multi-compliance according to claim 1, characterized in that: The theoretical eye movement path used in the matching evaluation module is the eye movement path bound to the training video used by the user when performing eye multi-compliance training, and the matching degree between the user's eye movement path and the theoretical eye movement path is evaluated based on the similarity of the two eye movement paths; ； Where: The matching degree between the user's eye movement path and the theoretical eye movement path; The edit distance between the user's eye movement path and the theoretical eye movement path; The maximum edit distance from the user's eye movement path, the theoretical eye movement path to the complete graph; The maximum value in brackets; , The total number of sampling points in the user's eye movement path and the theoretical eye movement path; is the line width of the jth sampling point in the user's eye movement path and theoretical eye movement path; Among them, the complete graph is a path graph in which all nodes are interconnected. The sampling points in the user's eye movement path and theoretical eye movement path are manually edited by the system user, and the distance between each adjacent sampling point is equal.

6. The visual function training system based on glasses-type eye tracking multi-compliance according to claim 1, characterized in that: The matching judgment threshold in the decision module is customized by the system end user. When the evaluation result is greater than or equal to the judgment threshold, the user's current eye compliance training ends. Otherwise, the jump selection module is further executed.

7. The visual function training system based on glasses-type eye tracking multi-compliance according to claim 1, characterized in that: When the selection module controls the training glasses to select multiple compliance training videos, it complies with: Set the total duration of the user's eye training, and control the number of times that the total duration of the eye multi-compliance training videos configured continuously for the user exceeds the total duration of the user's eye training, which shall not exceed twice; In the training glasses, select the multi-compliance training video corresponding to the theoretical eye movement path that is most different from the user's eye movement path of the previous time as the training video for the next application; Among them, the theoretical eye movement path with the highest difference from the previous user's eye movement path is based on The calculation logic is determined.

8. The visual function training system based on glasses-type eye tracking multi-compliance according to claim 1, characterized in that: During the operation phase of the recognition module, each evaluation result of the matching evaluation module is obtained when the user performs multi-compliance training through the training glasses, and the maximum and minimum values ​​are selected from each evaluation result, and then the maximum and minimum values ​​are averaged, which is recorded as , corresponding to each multi-compliance training based on time series ; Among them, The latest calculation results of no less than three times are obtained. When the calculation results of no less than three times show a continuous upward trend based on the time series, it means that the user's eye training effect is tending to be healthy. Otherwise, it means that the user's eye training effect is tending to be worse.

9. The visual function training system based on glasses-type eye tracking multi-compliance according to claim 1, characterized in that: The single chip microcomputer is interactively connected with the training glasses through dielectric electrical properties, the capture module is interactively connected with the matching evaluation module through a local area network, the matching evaluation module is interactively connected with the determination module and the selection module through the local area network, and the matching evaluation module and the selection module are interactively connected with the recognition module through the local area network.

10. A method for visual function training based on glasses-type eye tracking with multiple dependencies, the method being an implementation method of a visual function training system based on glasses-type eye tracking with multiple dependencies as claimed in any one of claims 1 to 9, characterized in that: The following steps are involved: The eye multi-compliance training video stored in the training glasses is used to calculate the product of the corresponding complexity of the eye movement path of the eye multi-compliance training video and the size of the corresponding area; The ocular multi-compliance training video with the largest product is selected and provided to the user for training for the first time; Evaluate the eye movement path of the user during the eye multi-compliance training process, and evaluate the matching degree with the theoretical eye movement path bound to the eye multi-compliance training video provided to the user; Setting the re-push logic of the eye multi-compliance training video, deciding whether to provide the eye multi-compliance training video to the user again according to the evaluation results, and controlling the stopping of the push operation based on the re-push logic of the eye multi-compliance training video; Identify the user's eye training health status based on historical training results.

Images