Eye movement information processing device

Abstract

The embodiment of the invention provides an eye movement information processing device, and the device comprises an installation mechanism which comprises a mechanism body detachably disposed in an installation region, and an extension part which extends from the mechanism body to an eye region of a user; the image collector is arranged on the extension piece of the mounting mechanism, so that the collection range of the image collector covers the eye region to obtain an eye image of the user; and the control unit is in communication connection with the image collector and is used for extracting eye movement information according to the eye image and obtaining a predicted risk value of at least one disease associated with eye movement based on the eye movement information and the physical sign and / or case information of the user. According to the eye movement information processing device, through the design of the detachable mounting mechanism and the extension piece, the image collector is accurately positioned in the eye area of the user, and eye movement data collection is achieved. The device has the advantages of being comfortable to wear and convenient to install, and is suitable for home health monitoring and early disease screening.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of disease risk prediction, and in particular to a processing device for eye movement information. BACKGROUND

[0002] Eye movement information, as an important physiological indicator reflecting the activity of the human nervous system and cognitive state, has wide application value in many fields such as medical diagnosis, human-computer interaction, psychology research, and fatigue driving monitoring. The movement of human eyeballs is precisely controlled by multiple brain nerves, and abnormal changes in parameters such as movement mode, trajectory, speed, and frequency are often closely related to specific nervous system diseases, mental diseases, or systemic diseases. For example, nystagmus, saccadic smoothness abnormalities, and decreased pursuit movement ability may be early clinical manifestations of diseases such as Alzheimer's disease, Parkinson's disease, multiple sclerosis, and thyroid-related eye disease.

[0003] Currently, eye movement information collection and analysis technology is developing from laboratory environment to daily and scenario-based applications. Some wearable eye tracking devices have appeared on the market, such as eye trackers integrated in virtual reality (VR) or augmented reality (AR) head-mounted devices, and some head-mounted eye trackers designed for scientific research or specific applications (such as assistive interaction for the disabled). These devices usually continuously or intermittently capture user eye images through a miniature camera (i.e., an image collector) mounted on a glasses frame or a headgear, and then extract features such as pupil center and corneal reflection points through algorithm analysis, and finally calculate various eye movement parameters such as gaze point, saccade, and blink.

[0004] However, the existing eye movement information processing devices and technologies have obvious limitations in clinical applications for disease risk prediction. First, most consumer-level eye tracking devices focus on human-computer interaction and behavior analysis, and the accuracy and medical reliability of the eye movement data collected are insufficient, and there is a lack of deep integration with clinical medical knowledge. Second, the existing analysis methods mostly stop at the description and simple analysis of eye movement trajectories themselves, and fail to fuse and analyze eye movement information with comprehensive health information of individual users. Single and isolated eye movement data lack individual specificity background, and their sensitivity and specificity as disease biomarkers are limited. For example, the same eye movement retardation phenomenon may have completely different clinical significance in a healthy elderly person and an elderly person with a history of cerebrovascular disease. SUMMARY

[0005] In view of the above-mentioned shortcomings of the prior art, the purpose of the present disclosure is to provide a processing device for eye movement information to solve the problems in the related art.

[0006] The first aspect of the present disclosure provides a processing device for eye movement information, comprising: an installation area for installation on a wearable object worn on the head of a user; and

[0007] The mounting mechanism comprises a mechanism body detachably arranged on the mounting area, and an extension member extending from the mechanism body to the eye area of the user;

[0008] The image collector is arranged on the extension member of the mounting mechanism, so that the collection range of the image collector covers the eye area, and the eye image of the user is acquired;

[0009] The control unit is communicatively connected to the image collector, configured to extract eye movement information according to the eye image, and obtain a predicted risk value of at least one disease associated with eye movement based on the eye movement information and the physical sign and / or case information of the user.

[0010] In an embodiment of the first aspect, the wearable object comprises a hanging part arranged at one end of the wearable object facing the head; the mounting area is arranged on the hanging part for connection with the mounting mechanism; wherein the hanging part is away from the face of the user.

[0011] In an embodiment of the first aspect, the wearable object is in the form of glasses, comprising:

[0012] The frame comprises a pair of rims for mounting lenses, and a crossbeam connecting the pair of rims; the crossbeam forms a mounting area for mounting the mounting mechanism.

[0013] In an embodiment of the first aspect, the mounting mechanism comprises at least one of the following:

[0014] 1) an elastic jaw assembly having at least two elastic arms; the elastic arms are provided with a hanging hook at the end; the mounting area is provided with a clamping groove matched with the hanging hook;

[0015] 2) a first insertion part provided with a first magnet; wherein the mounting area is provided with a second insertion part matched with the first insertion part; the second insertion part is inserted with a second magnet magnetically matched with the first magnet on the first insertion part; wherein the arrangement direction between the first magnet and the second magnet is consistent with or perpendicular to the insertion direction.

[0016] In an embodiment of the first aspect, the extension member is located on the inner side of the lens facing the user, and the extension member extends in a ring shape to form a closed or non-closed curved structure; the hollow part in the middle of the curved structure corresponds to the eyeball of the user for perspective.

[0017] In an embodiment of the first aspect, at least one light emitter is arranged on the extension member and configured to face the eye area in the working state so that the light emitting range covers the eye area.

[0018] In an embodiment of the first aspect, the plurality of light emitters and the plurality of image collectors are arranged at intervals along the extension member or are arranged at intervals alternately;

[0019] And / or, the light emitters and / or image collectors are integrally / detachably arranged on the extension member, and the extension member is formed with conductive lines connecting the light emitters and / or image collectors to a control unit and a power supply arranged in the mechanism body; in the case that the light emitters and / or image collectors are detachable, the extension member and the light emitters and / or image collectors are respectively provided with electrically connected contact parts;

[0020] And / or, the extension member is detachably connected to the mechanism body.

[0021] In an embodiment of the first aspect, the head movement image collector is fixed to the wearing object or the mounting mechanism and is used to collect movement information of the user's head; wherein, the movement information includes a rotation track and a swing rate.

[0022] The control unit is further configured to correct the predicted risk value according to the movement information and the eye information.

[0023] In an embodiment of the first aspect, the obtaining of the predicted risk value of at least one disease matched with the eye information according to the eye information and the basic information of the user includes:

[0024] Extracting a feature parameter in the eye information and obtaining the basic information associated with the feature parameter; wherein, the feature parameter includes pupil diameter response information, eye color information and spontaneous nystagmus information.

[0025] Obtaining a preliminary risk value of different diseases in the target disease type through a trained disease matching model according to the feature parameter and the basic information.

[0026] In an embodiment of the first aspect, the head movement image collector is fixed to the wearing object or the mounting mechanism and is used to collect movement information of the user's head; wherein, the movement information includes a rotation track and a swing rate.

[0027] The control unit is further configured to correct the predicted risk value according to the movement information and the eye information.

[0028] The eye movement information processing device provided by the present application can accurately position the image collector in the eye area of the user through the detachable mounting mechanism and the extension piece design, realize eye movement data collection, and output the prediction risk value of various nervous system or mental diseases by combining the eye movement information and the user's physical signs and case information through the control unit. The device has the advantages of comfortable wearing and convenient installation, and is suitable for home health monitoring and early disease screening. BRIEF DESCRIPTION OF DRAWINGS

[0029] Figure 1 The structure schematic diagram of the processing device when worn in an embodiment of the present application is shown.

[0030] Figure 2 The communication connection schematic diagram of the processing device in an embodiment of the present application is shown.

[0031] Figure 3 The flow chart of predicting the prediction risk value of the disease in an embodiment of the present application is shown.

[0032] Figure 4 The structure schematic diagram of the joint action of the disease matching model and the collaborative analysis model in an embodiment of the present application is shown.

[0033] Figure 5 The schematic diagram of the association analysis of the preliminary risk value and the head information in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0034] The embodiments of the present application are described below through specific and concrete examples, and those skilled in the art can easily understand other advantages and effects of the present application from the disclosed messages. The present application can also be implemented or applied in different specific embodiments, and the details in the present application can be modified or changed according to different views and applications without departing from the spirit of the present application. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0035] The embodiments of the present application are described in detail below with reference to the accompanying drawings, so that those skilled in the art can easily implement the present application. The present application can be embodied in various different forms, and is not limited to the embodiments described herein.

[0036] In the description of the present disclosure, the expressions "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" etc. mean that the particular feature, structure, material or characteristic following the expressions are included in at least one embodiment or example of the present disclosure. Also, the expressions can include a particular feature, structure, material or characteristic in combination with one or more of the other features, structures, materials or characteristics in any one or more embodiments or examples. In addition, the different embodiments or examples of the present disclosure and the features of the different embodiments or examples can be combined and combined with each other, if not mutually exclusive.

[0037] In addition, the terms "first", "second", etc. are used only to indicate a purpose, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the present disclosure, the meaning of "a group" is two or more, unless specifically limited.

[0038] In order to clearly illustrate the present disclosure, devices irrelevant to the description are omitted, and the same reference numerals are given to the same or similar constituent elements throughout the description.

[0039] Throughout the description, when it is said that a device is "connected" to another device, it includes not only the case of "direct connection", but also the case of "indirect connection" in which other elements are placed therebetween. In addition, when it is said that a device "includes" a certain constituent element, unless specifically stated to the contrary, it does not exclude other constituent elements, but means that other constituent elements can also be included.

[0040] Although the terms first, second, etc. are used herein to refer to various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first interface and a second interface, etc. are indicated. Furthermore, as used herein, the singular forms "a", "an" and "the" are intended to include plural forms, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises", "comprising", "includes" and / or "including", mean the presence of the stated features, steps, operations, elements, modules, items, kinds and / or groups, but do not exclude the presence or addition of one or more other features, steps, operations, elements, modules, items, kinds and / or groups. The terms "or" and "and / or" as used herein are to be interpreted as inclusive, or meaning either or any combination. Therefore, "A, B or C" or "A, B and / or C" means "any of the following: A; B; C; A and B; A and C; B and C; A, B and C". This definition applies only when a combination of elements, functions, steps or operations are in some way specifically called out in a claim.

[0041] The professional terms used herein are used only to refer to specific embodiments and are not intended to limit the present disclosure. The singular form used herein, unless the context clearly indicates the opposite, also includes the plural form. In the specification, the meaning of "include" is to specify a certain feature, region, integer, step, operation, element, and / or component, and is not to exclude the presence or addition of other features, regions, integers, steps, operations, elements, and / or components.

[0042] Although not differently defined, the technical terms and scientific terms used herein include the meanings commonly understood by those skilled in the art to which the present disclosure belongs. The terms defined in the commonly used dictionary are additionally explained to have the meanings consistent with the related technical documents and the currently prompted messages, unless defined, and should not be over-interpreted as ideal or very formal meanings.

[0043] Eye movement data is mainly used in the medical field for neurological diseases, mental diseases, ophthalmic diseases, and cognitive function evaluation. In neurological diseases such as Alzheimer's disease and Parkinson's disease, early screening and disease monitoring can be achieved through abnormal indicators such as saccade speed and fixation stability. In mental and psychological diseases such as depression and ADHD, data such as fixation time and eye movement exploration range can be used to assist diagnosis and reduce subjective assessment errors. In ophthalmic diseases such as glaucoma and amblyopia, traditional detection methods can be supplemented to evaluate optic nerve damage or binocular movement coordination. Further, it can also be used for rehabilitation evaluation of brain injury patients and cognitive aging research of different age groups.

[0044] In the related art, the processing device of eye movement information has poor installation adaptability and is difficult to flexibly adapt to different types of headwear. In addition, most devices can only extract eye movement information and cannot combine personalized health data such as user signs and cases, making it difficult to realize risk prediction of eye movement-related diseases, and the function is relatively single.

[0045] To solve the above problems, an embodiment of the present disclosure provides an eye movement information processing device. The installation mechanism is provided with a detachable mechanism body and an extension piece, so that the processing device can be flexibly and stably installed in the installation area of different headwear, solving the problem of poor adaptability. At the same time, the control unit further combines user signs and / or case information to calculate the prediction risk value of at least one eye movement-related disease after extracting eye movement information, which makes up for the problem of single function and inability to realize disease risk prediction in the related art.

[0046] Among them, Figure 1 The embodiment only takes glasses as an example, and in actual use, different wearables can be used according to the user's use habit.

[0047] The processing device is provided on a mounting area of a wearable 100 worn on the head of a user. Figure 1 In an embodiment, the processing device comprises a mounting mechanism 200, an image collector 300.

[0048] Specifically, the wearable 100 comprises a hat such as a baseball cap, a cap, a safety helmet, etc. or glasses such as myopia glasses, sunglasses, reading glasses, etc. The wearable 100 is provided with a pre-set mounting area such as the inner side of the forehead of the cap, the middle of the frame of the glasses, or the position of the temple close to the lens.

[0049] The mounting mechanism 200 comprises a mechanism body 210 detachably provided on the mounting area. The mechanism body 210 is adapted to different wearables 100.

[0050] Optionally, the mounting mechanism can be adapted to be mounted on different types of wearables 100, wherein the wearable 100 comprises a hanging part provided at one end of the wearable 100 towards the head; the mounting area is provided on the hanging part for connection with the mounting mechanism 200; wherein the hanging part is away from the face of the user.

[0051] Specifically, the hanging part is provided at a position away from the face of the user, for example, distributed on the top beam of the head-mounted device, the rear headband, etc. Since this area is not close to the eye or the nose face, it avoids interference with breathing, vision and skin contact, while having high structural stability and space expandability.

[0052] The hanging part is provided with a mounting area for detachable or fixed connection with the mounting mechanism 200 of the processing device. The mounting area can be a plane, a groove, a through hole, a magnetic surface or a sliding rail structure, and the mechanism body 210 of the mounting mechanism 200 is adapted to be quickly mounted and positioned by buckling, magnetic attraction, threading or plug-in mode. The user can directly plug or attract the processing device on the mounting area of the hanging part without taking off the wearable 100, realizing the "plug and play" of the functional module. Different functional modules (such as eye movement monitoring and head movement detection) can share the same mounting area, supporting on-demand switching.

[0053] Optionally, in Figure 1 In an embodiment, the wearable 100 is in the form of glasses, comprising a frame; the frame comprises a pair of rims for mounting lenses, and a crossbeam connecting the pair of rims; the crossbeam forms a mounting area for suspending the mounting mechanism 200.

[0054] The mirror ring is annular or half-frame structure, which is suitable for standard optical lenses, sunglasses or functional lenses (such as anti-blue light, color-changing, polarized lenses), and can be personalized according to the vision needs of users. Two mirror rings are connected by a crossbeam above the bridge, which not only plays a structural connection role, but also serves as a key component for facial force bearing and positioning, ensuring that the glasses remain stable and symmetrical when worn.

[0055] The mounting area is arranged on the outer surface, top or inner side of the crossbeam, preferably at the central axis position directly above the bridge, with good structural rigidity and spatial accessibility. The mounting area is configured to be detachably connected with the mounting mechanism 200 of the processing device, such as fixedly combined with the mechanism body 210 through buckle, magnetic attraction, sliding groove or threaded structure.

[0056] Optionally, the mounting mechanism 200 includes at least one of the following:

[0057] Embodiment 1: elastic jaw assembly, having at least two elastic arms; the elastic arms are provided with hanging hooks at the ends; the mounting area is provided with a clamping groove matched with the hanging hooks.

[0058] Specifically, the elastic arms are made of materials with good elasticity and fatigue resistance, ensuring stable rebound performance and structural strength under repeated opening and closing operations. One end of the two elastic arms is connected to the mechanism body 210 of the mounting mechanism 200, forming an integrated clamping structure; the other end extends outward and is provided with a hanging hook, which is designed in an L shape, a hook shape or a reverse type, with the end bent towards the inside of the jaw, facilitating hooking on the mounting area of the wearable 100 during installation.

[0059] In some embodiments, as shown in Figure 1 The wearable 100 is in the form of glasses, and the crossbeam of the frame serves as the main bearing structure, provided with a clamping groove matched with the hanging hook, which is formed on the top, side or end face of the crossbeam, and the inner wall profile is accurately matched with the outer shape of the hanging hook to realize mechanical engagement and anti-disengagement limiting. The clamping groove can be rectangular or U-shaped structure, provided with a guide slope or a rounded corner inside, facilitating automatic guiding and positioning of the hanging hook when inserted, reducing installation difficulty. When the user aligns the elastic jaw of the processing device with the clamping groove on the crossbeam and applies light pressure, the elastic arms are elastically deformed and opened under the action of external force, and then rapidly rebound under the action of elastic restoring force after the hanging hook passes the entrance of the clamping groove, so that the hanging hook is firmly embedded in the inside of the clamping groove, completing self-locking and achieving "plug and play" assembly without tools.

[0060] Further, the inner surface of the suspension part can be provided with anti-slip texture, micro-bumps or covered with flexible material (such as silica gel) to increase the friction between the card slot and prevent the device from loosening due to head shaking, running, cycling and other dynamic scenarios. At the same time, the bottom of the card slot can also be provided with a limiting step or a recess, which cooperates with the protruding structure at the end of the suspension hook to form a double locking mechanism.

[0061] In addition, in some preferred embodiments, the elastic clamping jaw assembly can also be fine-tuned in multiple degrees of freedom. For example, a ball hinge or flexible shaft structure is provided between the mechanism body 210 and the elastic arm, allowing the clamping jaw to be adjusted at a small angle after installation to adapt to the surface of the beam with different curvatures, ensuring that the overall posture of the device is horizontal and the extension member 220 accurately points to the eye area.

[0062] This design is not only suitable for standard optical glasses, sunglasses or goggles, but also can be extended to head-mounted display devices, industrial safety hats or sports helmets. The structure is simple, easy to operate, firmly connected, highly reusable, and does not rely on glue or screw fixation, avoiding permanent modification of the original wearing object 100.

[0063] Embodiment 2: The plug-in structure can include a first plug-in part and a second plug-in part. The first plug-in part is fixedly provided with a first magnet. The second plug-in part is provided on the mounting area and is in plug-in cooperation with the first plug-in part. The second plug-in part is plugged with a second magnet that is in magnetic attraction cooperation with the first magnet on the first plug-in part. The arrangement direction between the first magnet and the second magnet is consistent with or perpendicular to the plug-in direction.

[0064] Specifically, the first plug-in part is a first magnet accommodating groove provided at one end of the processing device, and a first magnet is fixedly arranged inside the first magnet accommodating groove.

[0065] The second plug-in part is a second magnet accommodating groove provided on the wearing object 100, and a second magnet is fixedly arranged inside the second magnet accommodating groove.

[0066] When the processing device is docked with the wearing object 100, the first plug-in part and the second plug-in part are aligned with each other, and the plug-in action realizes the nesting cooperation of the two in space, and the magnetic attraction force is generated between the first magnet and the second magnet.

[0067] According to the actual structure design requirements, the arrangement of the second magnet in the second plug-in part has multiple optional schemes:

[0068] Embodiment 2-1: The second magnet does not protrude out of the second plug-in part.

[0069] The second magnet is completely embedded and fixed inside the second plug-in part, and the front end face is flush with the slot or slightly recessed;

[0070] At this time, the length of the first magnet is designed to be greater than the depth of the first insertion part, i.e., the first magnet extends a distance forward from the first insertion part;

[0071] During the insertion process, the first magnet is inserted into the second insertion part, close to or directly against the second magnet, and the two form end face abutting magnetic attraction in the axial direction;

[0072] Embodiment 2-2: The second magnet partially or entirely extends out of the second insertion part.

[0073] One end of the second magnet extends out of the second insertion part, forming a movable end that can be inserted or abutted;

[0074] During insertion, there can be two implementation modes:

[0075] Reverse insertion mode: the extended second magnet is inserted into the first insertion part to form a close magnetic attraction with the internal first magnet, enhancing the attraction area and the bonding strength;

[0076] Face-to-face magnetic attraction mode: the second magnet does not completely enter the first insertion part after extending out, but is magnetically attracted to the first magnet extending out of the first insertion part.

[0077] In addition, the slot type structure of the first insertion part and the second insertion part can be designed as a rectangle, a U shape, etc.

[0078] Optionally, the magnetic pole arrangement direction between the first magnet and the second magnet can be flexibly configured according to the design requirements of the structure:

[0079] The arrangement direction is consistent with the insertion direction (i.e., axial attraction): the magnetization directions of the two magnets are arranged opposite along the insertion axis, for example, the N pole of the first magnet faces the S pole of the second magnet, forming end face to end face positive magnetic attraction. This mode generates a gradual attraction force during the insertion process, acting as a "self-guiding" function to prevent the device from accidentally falling off during use.

[0080] The arrangement direction is perpendicular to the insertion direction (i.e., lateral attraction): the magnetization direction of the magnet is perpendicular to the insertion axis, and the magnetic force direction is transverse, forming lateral attraction. This mode can provide additional resistance to prevent the device from loosening due to lateral sliding after the insertion is completed.

[0081] The mounting mechanism further includes an extension member 220 extending from the mechanism body 210 to the eye area of the user.

[0082] In some embodiments, the extension 220 is an arm extending from the mechanism body 210 towards the user's eye region, the length of which can be adjusted by the telescopic joint to adapt to different head shapes or wearing positions. In some preferred embodiments, the end of the extension 220 is provided with a universal joint that can rotate 360°, used to fix the image collector 300, ensuring that the lens is always aligned with the eye region.

[0083] The image collector 300 is arranged on the extension 220 of the mounting mechanism 200, so that the collection range of the image collector 300 covers the eye region to obtain the eye image of the user.

[0084] Specifically, the image collector 300 is arranged at the end or side of the extension 220, with its optical axis facing one or both eyes of the user, and the collection range completely covering the eye region, including the pupil, iris, eyelid and periorbital tissue. In some embodiments, the image collector 300 can be a miniature camera that supports working in low light or near-infrared conditions. In some embodiments, the image collector 300 is equipped with a filter to enhance the sensitivity to specific wavelengths of light (such as 850nm infrared light), to improve the accuracy of pupil recognition, while avoiding visible light interference with the user's visual experience. When the wearable 100 is a hat, the image collector 300 extends forward from the inside of the hat brim, with a certain distance between the lens and the eye region; when the wearable 100 is a pair of glasses, the image collector 300 can extend obliquely forward from the frame, with a certain distance between the lens and the eye region, ensuring that the collection angle is not blocked.

[0085] Optionally, in Figure 1 In embodiments, the extension 220 is located on the inner side of the lens facing the user, and the extension 220 extends circumferentially to form a closed or non-closed curved structure, and the hollow part in the middle of the curved structure corresponds to the user's eyeball for perspective.

[0086] Specifically, the extension 220 extends from the mechanism body 210 towards the user's eye region, and extends circumferentially along the inner edge of the frame or the nose bridge region to form a curved structure. The curved structure can be a partial arc, a C-shaped, U-shaped or approximately ring-shaped non-closed structure, or a closed ring structure surrounding one or both eyes, which is adapted to the contour of the wearer's eye socket, ensuring comfortable wearing and no compression on the face.

[0087] Further, a hollow part is formed in the middle of the curved structure, which is opposite to the user's eyeball in the wearing state, and its size and position are configured to correspond to the user's eye region, ensuring that the user's line of sight is not blocked. The hollow part allows the user to see normally, so that the image collector 300 can completely capture key information such as pupil movement, eyelid opening and closing, and periorbital muscle activity.

[0088] Furthermore, the image acquisition device 300 is disposed on the inner wall or end of the curved structure, with its lens facing the center of the hollowed-out portion, i.e., the area where the user's eyeball is located. Due to the surrounding arrangement of the curved structure, the image acquisition device 300 can be arranged in multiple positions (such as the nasal side, temporal side, and above) to achieve multi-angle synchronous acquisition, thereby improving the accuracy and robustness of eye tracking.

[0089] Optionally, the extension 220 can also be positioned on the outer side of the lens facing the user (i.e., the side of the lens furthest from the eyes, facing the external environment). With the extension 220 located on the outer side of the lens, it does not directly contact the user's face, bridge of the nose, or skin around the eyes, avoiding pressure, friction discomfort, or skin allergies caused by prolonged wear. Furthermore, it can reduce contamination of the device by sweat, oil, dander, and other pollutants, reducing cleaning frequency and improving hygiene; moreover, its outer placement does not encroach on the inner space.

[0090] In some embodiments, the processing apparatus further includes at least one light emitter 400 disposed on the extension 220 and configured to face the eye region in an operational state so that the light emission range covers the eye region.

[0091] Specifically, the emitter 400 can use low-power, small-size light source devices such as LEDs and OLEDs, supporting multiple operating modes such as continuous emission, pulse modulation, or on-demand triggering. Its installation angle is adjustable or preset to tilt downwards to avoid direct light hitting the cornea and causing strong reflection or user discomfort, while ensuring that light effectively enters the surface of the eyeball and is absorbed by the pupil or reflected from a specific angle, so that the image acquisition device 300 can capture clear pupil contour and light spot information.

[0092] In some embodiments, to adapt to detecting different types of eye diseases in users, the emitter 400 can be configured to emit light waves of multiple wavelengths. The emitter 400 can be an integrated emitter capable of emitting multiple wavelengths, or it can be multiple emitters 400 capable of emitting light waves of different wavelengths. As an example, the light waves emitted by the emitter 400 may include one or more of the following types:

[0093] Near-infrared light (such as 850nm or 940nm): used for eye tracking in low-light or nighttime environments, enabling high signal-to-noise ratio imaging without being visible to the human eye, thus avoiding interference with the user's visual experience;

[0094] White light: Used for color image acquisition in normal environments, supporting the recognition of visible features such as eyelid condition and conjunctival color;

[0095] Blue light (e.g., 450nm–470nm): used to stimulate the physiological contraction response of the pupil, to assist in the assessment of autonomic nervous system function, or to screen for specific ophthalmic diseases (e.g., optic neuropathy).

[0096] Multispectral combined light source: Integrates multiple emitters of different wavelengths (such as blue light 450nm, near-infrared 850nm, white light, etc.) and supports dynamic selection and activation of specific light sources according to the detection task. Specifically, the control unit can intelligently switch or sequentially poll the illumination modes according to the physiological characteristics of the target disease. For example, when it is necessary to assess the pupillary light reflex function to screen for autonomic neuropathy or brainstem injury, the system automatically activates blue LEDs, as they can effectively stimulate retinal ganglion cells and induce obvious pupillary contraction responses, making it easy to capture dynamic change curves. When performing routine eye tracking in low-light scenarios, the system switches to a near-infrared light source (such as 850nm or 940nm) to achieve illumination invisible to the human eye, avoiding interference with the user's vision while ensuring image acquisition quality. If it is necessary to detect signs that can only be identified under visible light, such as scleral icterus, conjunctival congestion, or abnormal iris pigmentation, to assist in the diagnosis of liver and gallbladder diseases or eye inflammation, the system activates white light illumination to acquire true-color eye images. For preliminary screening of unknown diseases or comprehensive health assessment, the system can cycle through different wavelengths of light (such as blue light → white light → infrared light) in a preset order to collect multispectral eye images in sequence, and comprehensively extract multidimensional data such as pupil response, color features and movement behavior to improve the breadth and accuracy of disease identification.

[0097] In addition, the light source switching logic can be triggered by the user selecting the detection item, or it can be automatically initiated by the control unit based on the preliminary analysis results. For example, if unstable gaze is detected under infrared light, the system can actively start blue light to perform pupillary function depth testing, forming a progressive detection process of "initial screening → directional excitation → fine evaluation".

[0098] In some preferred embodiments, such as Figure 1 In this embodiment, the processing device includes a plurality of light emitters 400 and a plurality of image collectors 300, which are arranged at intervals or alternately along the extension 220.

[0099] Specifically, multiple light emitters 400 (such as infrared LEDs, white LEDs, or blue LEDs) and multiple image acquisition devices 300 are integrated on the inner side or bottom surface of the extension 220, arranged linearly, arc-shaped, or in a surrounding pattern along its length. For example, on the curved extension 220 surrounding the outer side of the lens, the light emitters 400 and image acquisition devices 300 are distributed sequentially along the nasal side → upper side → temporal side. Alternatively, on the beam extension structure, the two are arranged in an alternating pattern of "light emitter 400-acquirrator-light emitter 400" or "acquirrator-light emitter 400-acquirrator," forming a symmetrical or asymmetrical array.

[0100] The interval setting method can be equidistant or non-equidistant distribution. The spacing is optimized according to the human eye anatomy and optical imaging requirements to ensure that each image acquisition device 300 can obtain effective illumination provided by at least one light source 400, while avoiding light spot overlap interference between adjacent light sources.

[0101] One or more emitters 400 are configured near each image acquisition unit 300 to form a "one-to-one" or "one-to-many" local illumination unit to achieve precise supplemental lighting; acquisition units at different positions can capture the reflected light spots on the surface of the eyeball and the outline of the pupil from different angles.

[0102] Furthermore, the multiple light emitters 400 can be lit in a time-sharing manner or activated on demand, and automatic lighting control can be achieved by combining the feedback signal from the image acquisition unit 300.

[0103] Example 1: The light emitter 400 and the image acquisition unit 300 are integrated into the extension 220.

[0104] The light emitter 400 and the image acquisition unit 300 are fixed to the extension 220, forming an inseparable integral assembly relationship.

[0105] Specifically, the lamp holder of the emitter 400 (e.g., a ring-shaped LED light) and the housing of the image acquisition unit 300 are integrally molded using an injection molding process and fixed to the extension 220 by welding or bolt fastening (the bolt heads are embedded inside the module housing and cannot be disassembled). The advantages of the integrated design are: high structural stability, which can avoid the relative positional shift of the emitter 400 and the image acquisition unit 300 due to vibration or external forces, ensuring that the illumination area and the image acquisition area are always matched.

[0106] Example 2: Both the light emitter 400 and the image acquisition unit 300 are detachably mounted on the extension 220.

[0107] In this embodiment, both the light emitter 400 and the image acquisition unit 300 are connected to the extension 220 with a detachable structure, which facilitates individual replacement or maintenance.

[0108] The back of the emitter 400 is provided with an elastic buckle that matches the buckle slot on the extension 220, and the image acquisition device 300 is similarly provided. In some embodiments, a buckle can be provided on the extension 220, and corresponding buckle slots can be provided on the emitter 400 and the image acquisition device 300.

[0109] When the LED 400 ages or the image acquisition unit 300 fails, it can be disassembled and replaced separately without replacing the entire extension part 220, thus reducing maintenance costs.

[0110] Example 3: The light emitter 400 or the image acquisition device 300 is detachably mounted on the extension 220.

[0111] In this embodiment, only one of the light emitter 400 and the image collector 300 adopts a detachable structure, while the other is fixedly connected to the extension 220, thus balancing stability and local flexibility.

[0112] Optionally, a conductive line is formed in the extension member 220. This conductive line is arranged along the extension direction of the extension member 220 and is used to electrically connect the light emitter 400 and image acquisition device 300 mounted thereon to the control unit 500 and power supply located in the mechanism body 210, so as to transmit working power, control signals and image data. One end of the conductive line is connected to the control unit 500 and the power supply, and the other end leads out an electrical connection node at the device mounting position of the extension member 220, which is connected to the electrode terminals of the light emitter 400 and the image acquisition device 300 respectively. When the emitter 400 and / or image acquisition unit 300 are detachable, to achieve automatic electrical connection during installation, the extension 220 is provided with a first electrical contact (such as an elastic probe, metal contact, or magnetic electrode), while the detachable emitter 400 and / or image acquisition unit 300 (or its module housing) are provided with a corresponding second electrical contact (such as a conductive pad, plug-in terminal, or complementary magnetic pole contact). After the devices are installed, the two contacts or couples to form a reliable electrical connection. This electrical contact can achieve rapid conduction using methods such as elastic crimping, sliding plugging, or magnetic alignment. The control unit 500 can automatically determine the type of the installed module and load corresponding drive parameters by recognizing the electrical characteristics of the contacts, achieving intelligent identification and adaptation. Furthermore, the electrical connection is only established after the devices are fully installed and locked, ensuring a stable connection and avoiding the risk of loose connections or short circuits.

[0113] Optionally, the extension 220 is detachably connected to the mechanism body 210.

[0114] Specifically, the detachable connection allows users to freely replace the extension piece 220 with different lengths, angles, shapes, or functional configurations according to usage needs, wearing habits, or monitoring scenarios, thereby adapting to different face shapes, frame structures, or application modes (such as monocular / dual-eye monitoring, near / far-range tracking). The extension piece 220 and the main body 210 are stably connected via a mechanical quick-release structure, including but not limited to elastic buckles, magnetic components, threaded engagement, and sliding rail insertion. In terms of electrical connection, the extension piece 220 has internal conductive lines, one end of which connects to the emitter 400 and the image acquisition unit 300, while the other end connects to the control unit 500 and power supply within the main body 210 via electrical contacts (such as spring probes and metal contacts) at the connection interface, achieving synchronous establishment of power supply and data transmission. When the extension piece 220 is removed, the circuit automatically disconnects, and the system enters a low-power or standby state to ensure safety.

[0115] exist Figure 2In this embodiment, the control unit 500 is communicatively connected to the image acquisition unit 300 and is used to extract eye movement information based on the eye image, and obtain a predicted risk value of at least one disease associated with eye movement based on the eye movement information and the user's physical signs and / or medical information.

[0116] Specifically, the control unit 500 includes a processor, a memory, and a communication interface, which are integrated inside the main body 210 or work in conjunction with an external computing device via wired / wireless means. In operation, the control unit 500 receives in real time user eye images acquired by the image acquisition unit 300 located on the extension 220. The eye images include pupil shape, iris texture, eyelid movement, and dynamic changes in the periocular region.

[0117] Based on a pre-set model, the control unit 500 extracts key eye movement information from the eye images, specifically including: fixation point coordinates and gaze trajectory, saccade speed and acceleration, fixation stability, microsaccade characteristics, pupil diameter and its dynamic response (such as light response rate and resting fluctuation), blink frequency and duration, binocular coordination, and other physiological parameters. These parameters serve as sensitive biomarkers of the functional state of the central nervous system and have the ability to reflect early neurodegenerative, mental, or ophthalmology-related diseases.

[0118] Furthermore, the control unit 500 also acquires the user's basic information and medical records. The basic information can be obtained through built-in sensors or external devices (such as smartwatches or mobile apps), including age, gender, heart rate, blood pressure, sleep quality, and activity level; the medical records include previous diagnostic records (such as Alzheimer's disease, Parkinson's disease, depression, attention deficit hyperactivity disorder (ADHD), history of concussion, glaucoma, etc.), medication history, family history, or mental health assessment results, which can be entered by the user or retrieved from the electronic health record (EHR) system with authorization.

[0119] Based on this, the control unit 500 calls a pre-trained disease risk prediction model to output a predicted risk value for at least one type of disease associated with eye movement behavior abnormalities. The predicted risk value can be expressed as: numerical probability (e.g., "early risk of Parkinson's disease: 76%)); risk level (low, medium, high); trend curve (risk value changes over multiple days); and parallel assessment results for multiple diseases (simultaneously outputting risk indices for neurodegenerative, psychiatric, and ophthalmic functional abnormalities). Finally, the control unit 500 can push the analysis results to user terminal devices (such as smartphones and tablets) via Bluetooth, Wi-Fi, or other communication methods, displaying them in the form of visual charts.

[0120] Optionally, in Figure 3In this embodiment, obtaining a predicted risk value for at least one disease matching the eye information based on the eye information and the user's basic information includes:

[0121] Step S100: Extract the feature parameters from the eye information and obtain the basic information associated with the feature parameters; wherein, the feature parameters include pupil diameter response information, eye color information and spontaneous nystagmus information.

[0122] Step S200: Using a trained disease matching model, obtain preliminary risk values ​​for different diseases in the target disease type based on the feature parameters and the basic information.

[0123] Specifically, pupil diameter information, such as resting pupil size, latency of the light reflex, amplitude and speed of constriction and recovery, and frequency of fluctuations under dark adaptation, reflects the functional state of the autonomic nervous system (especially the sympathetic and parasympathetic pathways). Eye color information, including iris pigment distribution, scleral yellowing, conjunctival congestion, or abnormal vascular dilation, helps in diagnosing hepatobiliary metabolic diseases (such as jaundice), inflammatory states, or hereditary eye diseases. Spontaneous nystagmus information: Detecting the presence of involuntary rhythmic nystagmus in the absence of visual stimulation or with the head at rest, recording its direction (horizontal, vertical, rotational), frequency, slow-phase velocity, and triggering conditions, serves as an important indicator of vestibular, cerebellar, or brainstem dysfunction.

[0124] Basic information: such as age, gender, blood pressure, heart rate variability (HRV), sleep quality, and medication use (e.g., antidepressants, sedatives). Case information: such as past diagnoses (multiple sclerosis, Meniere's disease, myasthenia gravis), family history of genetic diseases, records of head trauma, and ophthalmological examination results.

[0125] The control unit 500 inputs the extracted feature parameters and corresponding basic information into a pre-trained disease matching model. This model is a classification and regression system built based on machine learning or deep learning, such as using XGBoost, random forest, support vector machine (SVM), or multi-layer neural network (such as Transformer or LSTM) architectures. It is trained using large-scale clinical data to learn the complex nonlinear relationship between different types of diseases and specific eye movement / ocular phenotypes. By collecting ocular feature parameters, basic information, and clinical diagnosis labels from a large number of subjects, a multimodal training dataset is constructed, and supervised training is performed using machine learning or deep learning methods to establish a disease matching model that can output preliminary disease risk values.

[0126] The disease matching model outputs preliminary risk values ​​for multiple potential disease categories. Each risk value represents the degree of similarity between the user's current physiological state and the typical manifestations of a certain disease category. An example is shown below:

[0127] If spontaneous horizontal nystagmus is detected, along with changes in nystagmus direction after gazing in different directions, and a history of hypertension or diabetes, the model may output: "Brainstem ischemia risk: 95%".

[0128] If spontaneous horizontal nystagmus is detected, the nystagmus direction does not change after gazing in different directions, and head shaking is positive, the model may output: "Vestibular neuritis risk: 95%";

[0129] If a record of constricted pupils, mild scleral icterus, and abnormal liver function is found, it indicates: "Early risk of hepatic encephalopathy: 70%";

[0130] The presence of ptosis accompanied by fatigue-related blinking abnormalities, a young female physiology, and a history of autoimmune diseases increases the risk of myasthenia gravis.

[0131] This preliminary risk value is presented in the form of a probability score, risk level, or relative hazard, and can be visualized on the user's terminal device for personal health management or further evaluation by a doctor.

[0132] Optionally, the processing device further includes a head motion image acquisition device 600, fixed to the wearable device 100 or the mounting mechanism 200, for acquiring motion information of the user's head; wherein, the motion information includes rotation trajectory and swing rate.

[0133] The control unit 500 is also used to correct the predicted risk value based on the motion information and the eye information.

[0134] Optionally, the processing device further includes a head motion image acquisition unit 600, which is fixed to the wearable object 100 (such as an eyeglass frame or a head-mounted device housing) or the mounting mechanism 200 (such as the mechanism body 210 or the extension 220), preferably positioned near the geometric center of the head or an inertial stable region to ensure the representativeness and accuracy of the acquired data. The head motion image acquisition unit 600 is a miniature camera or visual sensor with a certain wide field of view, used to continuously acquire image sequences of the user's surrounding environment or facial reference points, thereby resolving the three-dimensional motion state of the head.

[0135] Specifically, the head motion image acquisition device 600 is configured to acquire the user's head motion information, including but not limited to: the head rotation trajectory (such as the curves of pitch, yaw, and roll angle changes over time) and the swing rate (i.e., a comprehensive representation of angular velocity and linear acceleration). It can also further calculate the dynamic characteristics of head motion, such as frequency, amplitude, stability, and sudden shaking.

[0136] The control unit 500 is communicatively connected to the head motion image acquisition unit 600 and synchronously analyzes the motion information acquired by it with the eye information acquired by the main image acquisition unit 300. Since users may make slight or large head movements in a natural state (such as walking, turning their heads, or nodding), these actions may interfere with the extraction of eye movement signals (for example, misinterpreting head rotation as eye saccades). Therefore, the control unit 500 uses head motion information to perform motion compensation and noise reduction correction on the raw eye movement data, separating the gaze behavior that is truly generated by the autonomous movement of the eyeballs, and improving the accuracy of eye movement parameters.

[0137] Some neurological disorders are characterized not only by abnormal eye movements but also by changes in head movement patterns. For example, Parkinson's disease patients often experience head tremors, bradykinesia, or postural instability; those with concussions or vestibular dysfunction may exhibit frequent head shaking and decreased control; and individuals with anxiety or attention deficit often display involuntary head swaying or over-adjustment during task performance.

[0138] Alternatively, please refer to Figure 4 In this embodiment, the control unit 500 is further configured to correct the preliminary risk value of the disease in the target disease type based on the preliminary risk value and the motion information using a preset collaborative analysis model, so as to obtain a corrected final risk value for ranking and determining the target disease.

[0139] The collaborative analysis model integrates preliminary risk values ​​with head-eye movement information. Using a multimodal dataset labeled with final clinical diagnostic results, it is trained using supervised learning to learn how to dynamically adjust preliminary risk values ​​and output more accurate final risk values. The training data for the collaborative analysis model includes:

[0140] (1) Preliminary risk value (output by the disease matching model);

[0141] (2) Synchronously acquired head-eye movement information (such as head movement trajectory, angular velocity, temporal relationship between nystagmus and head movements, etc.);

[0142] (3) The corresponding final clinical diagnosis label (i.e. the actual disease category).

[0143] These data come from multimodal records of the same subject during the same assessment period, and are labeled by clinical experts. They are used to train the model to learn "under what motion characteristics the initial risk of a disease should be up- or down-adjusted", thereby achieving intelligent correction of the initial risk value.

[0144] Specifically, after completing the initial risk assessment, the control unit 500 performs a correlation analysis between the initial risk value and the synchronously acquired head-eye movement coordinated behavior characteristics. Please refer to [link / reference needed]. Figure 5The specific implementation example is as follows:

[0145] If the system detects spontaneous nystagmus in a user and initially determines it to be vestibular nystagmus, but at the same time finds that the user's head still frequently and involuntarily shakes or exhibits rhythmic swaying in a resting state, the collaborative analysis model will increase the risk value of "central lesions" (such as cerebellar degeneration or multiple system atrophy) and decrease the risk value of peripheral vestibular diseases.

[0146] While both central nervous system disorders and vestibular disorders can cause vertigo and abnormal eye movements, they differ fundamentally in etiology, anatomical location, and clinical manifestations. Vestibular disorders are mostly peripheral lesions originating from the vestibular organs or vestibular nerves of the inner ear. They are commonly seen in benign paroxysmal positional vertigo (BPPV), vestibular neuritis, or Meniere's disease. Typical manifestations include sudden, severe rotational vertigo, often accompanied by nausea, vomiting, tinnitus, or hearing loss. Nystagmus is mostly horizontal-rotational and fixed in direction, and can be induced by changes in head position. The vestibulo-ocular reflex (VOR) function is decreased, but visual compensation is still possible. Central nervous system lesions involve the brainstem, cerebellum, or central nervous pathways, commonly seen in stroke, multiple sclerosis, or cerebellar degeneration. Vertigo in these lesions often manifests as persistent imbalance, a floating sensation, or unsteady gait, frequently accompanied by neurological signs such as ataxia, dysarthria, or diplopia. Eye movement characteristics are particularly significant for differentiation: spontaneous vertical or rotational nystagmus and gaze-induced nystagmus may occur, with key features including "fixation unable to suppress nystagmus" and abnormal corrective saccades, indicating impaired central integration function. This device simultaneously acquires eye images and head movement information, combining multi-dimensional parameters such as pupillary response, nystagmus direction, VOR gain, and saccade patterns. Using a collaborative analysis model, it can effectively distinguish between the two: peripheral vestibular disorders are mostly localized functional impairments, with risk warnings emphasizing lifestyle interventions and specialist repositioning treatment; while central nervous system lesion signals often indicate higher health risks. The system can output medium- to high-risk warnings based on this, guiding users to seek timely neurological consultation and avoiding delays in the early diagnosis and treatment of serious diseases.

[0147] If the initial risk indicates an "increased likelihood of Parkinson's disease" (based on eye movement characteristics such as reduced blinking and slow saccadic movements), and the motion information further indicates typical 4–6 Hz resting tremor of the head, difficulty initiating movement, or postural instability, then the model significantly increases the final risk value for the disease.

[0148] Conversely, if a preliminary assessment indicates a decline in VOR function, but the head-shaking motion is insufficient in amplitude or speed, resulting in inadequate stimulation intensity, the co-analysis model can identify this as an "invalid test" and downweight or mark the relevant risk values ​​as "to be retested" to avoid misjudgment.

[0149] This collaborative analysis model can be implemented using weighted regression, Bayesian networks, or deep attention mechanisms.

[0150] Furthermore, the head-shaking test is an important neuro-otological examination method used to detect whether the vestibular-ocular reflex function is normal. It is widely used in the auxiliary diagnosis of diseases such as vestibular vertigo, benign paroxysmal positional vertigo (BPPV), vestibular neuritis, and brainstem lesions. Traditional head-shaking tests rely on doctors manually and rapidly rotating the patient's head and observing whether the patient's eyes can stably track the target. This method is highly subjective, and the force and angle are difficult to standardize. This embodiment, by integrating a head motion image acquisition device 600, achieves automation, quantification, and visualization of the head-shaking test.

[0151] During the head-shaking experiment, the system can guide the user to perform standardized actions through voice or visual cues: for example, "Please keep your gaze fixed on the point in front of you, and after hearing the prompt, quickly turn your head to the right by about 20°, pause, and then return to the center." During this process: the head motion image acquisition device 600 records the rapid passive or active head-shaking process in real time; simultaneously, the image acquisition device 300, located on the extension 220, captures eye movements, particularly detecting whether compensatory reverse pupillary movement (i.e., VOR response) occurs during rapid head rotation, and whether saccades are present—an important indicator of vestibular dysfunction.

[0152] The control unit 500 synchronously analyzes head movement information and eye images to determine whether there are abnormal backscan eye movements.

[0153] Using this model, the control unit 500 outputs a corrected final risk value, with each disease corresponding to an updated quantified risk value. Subsequently, the system sorts all candidate diseases based on the final risk values, determines the most probable target disease, and generates a tiered early warning alert.

[0154] High risk (>75%): This indicates that the user's current physiological characteristics are highly consistent with the typical manifestations of a certain disease, and there is a high possibility of contracting the disease. It is recommended to seek medical attention as soon as possible and undergo professional clinical examination for early diagnosis and intervention.

[0155] Medium risk (50%–75%): This indicates the presence of some abnormal signals, but not enough to make a definitive diagnosis. It suggests the need for continuous monitoring of changes in relevant indicators and intervention in conjunction with lifestyle adjustments, cognitive training, or medical follow-up.

[0156] Low risk (<50%): This indicates that no significant abnormalities have been found at present, and routine health monitoring and periodic screening can be maintained.

[0157] For example, when the system determines that the final risk value for "central lesions" (such as cerebellar degeneration, brainstem ischemia, etc.) is 68%, falling into the 50% to 75% range, it is considered a medium risk. At this time, the control unit generates corresponding health alert information, such as: mild nystagmus and abnormal head movement coordination detected, the central vestibular function may be slightly impaired, it is recommended to have regular weekly retests, avoid excessive fatigue, control blood pressure and blood sugar, and have a follow-up neurological examination within one month.

[0158] The above embodiments are merely illustrative of the principles and effects of this disclosure and are not intended to limit this disclosure. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this disclosure. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this disclosure should still be covered by the protection scope of this disclosure.

Claims

1. An eye-tracking information processing device, characterized in that, An installation area for mounting on a device worn on a user's head; including: The installation mechanism includes: a mechanism body detachably disposed in the installation area, and an extension extending from the mechanism body to the user's eye area; An image acquisition device is provided on an extension of the mounting mechanism so that the acquisition range of the image acquisition device covers the eye area to obtain an image of the user's eyes; The control unit is communicatively connected to the image acquisition unit and is used to extract eye movement information from the eye images and obtain a predicted risk value for at least one disease associated with eye movement based on the eye movement information and the user's physical signs and / or medical information.

2. The processing apparatus according to claim 1, characterized in that, The wearable device includes a suspension portion located at one end of the wearable device facing the head; the mounting area is located on the suspension portion for connection with the mounting mechanism; wherein the suspension portion is located away from the user's face.

3. The processing apparatus according to claim 1, characterized in that, The wearable device is in the form of eyeglasses, including: The frame includes: a pair of lens rings for mounting lenses, and a crossbeam connecting the pair of lens rings; the crossbeam forms a mounting area for a mounting mechanism to suspend the lens.

4. The processing apparatus according to claim 1, characterized in that, The installation mechanism includes at least one of the following: 1) An elastic gripper assembly having at least two elastic arms; the end of each elastic arm is provided with a hanging hook, and the mounting area is provided with a slot adapted to the hanging hook; 2) A first insertion part of a first magnet is fixedly provided; wherein, the installation area is provided with a second insertion part that is inserted and engaged with the first insertion part; a second magnet is inserted into the second insertion part and magnetically engaged with the first magnet on the first insertion part; wherein, the arrangement direction between the first magnet and the second magnet is consistent with or perpendicular to the insertion direction.

5. The processing apparatus according to claim 3, characterized in that, The extension is located on the inside of the lens facing the user. The extension extends circumferentially to form a closed or open curved structure. The hollow part in the middle of the curved structure corresponds to the user's eyeball to allow for vision.

6. The processing apparatus according to claim 1, characterized in that, It also includes at least one light emitter disposed on the extension and configured to face the eye region when in operation, so that the light emission range covers the eye region.

7. The processing apparatus according to claim 1 or 5, characterized in that, It includes multiple light emitters and multiple image collectors, which are spaced apart or alternately arranged along the extension; And / or, the light emitter and / or image acquisition device are integrally / detachably disposed on the extension member, and the extension member has conductive lines connecting the light emitter and image acquisition device to a control unit and a power supply located in the main body of the mechanism; wherein, when the light emitter and / or image acquisition device are detachable, the extension member and the light emitter and / or image acquisition device are respectively provided with electrically connected and engaged electrical contacts. And / or, the extension is detachably connected to the mechanism body.

8. The processing apparatus according to claim 1, characterized in that, It also includes a head motion image acquisition device, fixed to the wearable device or the mounting mechanism, for acquiring motion information of the user's head; wherein, the motion information includes rotation trajectory and swing rate; The control unit is also used to correct the predicted risk value based on the motion information and the eye information.

9. The processing apparatus according to claim 1, characterized in that, The step of obtaining a predicted risk value for at least one disease matching the eye information based on the eye information and the user's basic information includes: Extract the feature parameters from the eye information and obtain the basic information associated with the feature parameters; wherein, the feature parameters include pupil diameter response information, eye color information and spontaneous nystagmus information; Based on the feature parameters and the basic information, a trained disease matching model is used to obtain preliminary risk values ​​for different diseases within the target disease type.

10. The processing apparatus according to claim 9, characterized in that, It also includes a motion capture device for collecting user head movement information; The control unit is further configured to correct the preliminary risk value of the disease in the target disease type based on the preliminary risk value and the motion information using a preset collaborative analysis model, so as to obtain the corrected final risk value for sorting and determining the target disease.

Images