Intervention system for xerophthalmia related to video syndrome

Abstract

The invention relates to an intervention system for xerophthalmia related to video syndrome, the system comprises a personal computer with a front camera and a humidifier, the personal computer uses the front camera to collect eye dynamic state changes of a current user, and the humidifier is used for humidifying the eye dynamic state changes of the current user. An analysis unit of the personal computer determines the total number of instant eyes of the current user according to the eye dynamic state change, and the analysis unit determines a composite index representing the bad eye using behavior related to the xerophthalmia according to the incomplete number of instant eyes and the instant eye frequency in the total number of instant eyes in a preset time period. And the analysis unit determines intervention reminding information according to the change of the composite index relative to the baseline data, generates an intervention scheme for driving the humidifier according to the intervention reminding information and sends the intervention scheme to the humidifier, and the humidifier executes humidification operation according to the intervention scheme. The invention solves the problem that the symptoms related to the xerophthalmia related to the video syndrome cannot be relieved due to neglecting the influence of individual differences and environmental factors.

Description

Technical Field

[0001] The present invention relates to the technical field of health data processing, and particularly to a technology for processing eye health data, and specifically to an intervention system for dry eye related to video syndrome. Background Art

[0002] Many epidemiological reports on dry eye have been published worldwide, and the results show that the incidence rate in different regions is about 5% - 50%. For example, see "Research Progress of Artificial Intelligence in Dry Eye Diagnosis" published by Han Xue, Ding Jingjuan, Lu Shuting, Jiang Qin, Yang Weihua, and Xue Jinsong in 2022 (see International Eye Science Journal (12), 2063 - 2067); and "Research on the Impact of Video Display Terminals on the Visual System" published by She Xijin, Huang Zhongning, Huang Duru, Yin Dongming, Wen Xianzhong, Qiu Chuangyi, and Huang Li in 2007 (see China Occupational Medicine (05), 392 - 394). Mufti M., Sayeed S.I., Jaan I., Nazir S. pointed out in "Does Digital Screen Exposure Cause Dry Eye?" published in 2019 (see Indian Journal of Clinical Anatomy and Physiology, doi:10.18231 / 2394 - 2126.2019.0017) that among medical graduates, long - term exposure to digital screens (especially smartphones and tablets) is significantly associated with the occurrence of dry eye symptoms, and the incidence rate of dry eye reaches 55.6%.

[0003] The research article "Blink Rate, Incomplete Blinks and Computer Vision Syndrome" published by Portello, J., Rosenfield, M., & Chu, C. et al. in 2013 (see Optometry and Vision Science, 90, 482–487) explored the relationship between Computer Vision Syndrome (CVS), blink rate, and incomplete blinks. The article found a significant positive correlation between the percentage of incomplete blinks and the total symptom score (p = 0.002), which means that the more incomplete blinks, the more severe the symptoms related to dry eye. In particular, increasing the average blink rate to 23.5 blinks per minute by external prompts did not significantly change the symptom score, that is, the method of increasing the blink rate by external prompts to improve dry eye symptoms is ineffective.

[0004] The article "The Relationship Between Dry Eye Disease and Digital Screen Use" published by Al-Mohtaseb, Z., Schachter, S., Lee, B., Garlich, J., & Trattler, W. et al. in 2021 (see Clinical Ophthalmology (Auckland, N.Z.), 15, 3811–3820) pointed out that the time of using smartphones per day (odds ratio [OR]=1.86) and the total time of using digital screens per day (OR = 1.82) were associated with an increased risk of dry eye disease; in contrast, the time of using a computer or TV per day was not found to be related to dry eye disease, based on a large-scale Korean study with N = 916; the age range was 7–12 years old, and the prevalence of smartphone use among children with dry eye disease was 96.7%, while it was 55.4% among children without dry eye disease. In addition, the article provided suggestions on behavioral and environmental adjustment measures to prevent or relieve dry eye symptoms in digital screen users, including blink exercises, the "Blind Working" strategy, the 20-20-20 rule, and arranging a desktop humidifier, etc. The humidifier can relieve dry eye symptoms by reducing tear evaporation and help prevent dry eye disease. Similarly, Mehra D., Galor A. pointed out in "Digital Screen Use and Dry Eye: A Review" published in 2020 (see Asia-Pacific Journal of Ophthalmology, 9:491-497, doi:10.1097 / APO.0000000000000328) that blue light radiation from digital screens and abnormal blink rates were the main mechanisms of evaporative dry eye of the tear film, and it was recommended to relieve symptoms through blink training and blue light filtering screens. However, for staff, during their normal working state, frequent reminder sounds will interfere with their work, and usually these staff will choose to ignore the reminder sounds or even turn off the reminder function. And the aforementioned research also showed that simply increasing the blink frequency actually did not improve dry eye symptoms.

[0005] CN116864105A discloses an artificial intelligence-based dry eye risk prediction method, which includes: obtaining a target facial video of a target object; inputting each image frame in the target facial video into a preset segmentation model for eye region segmentation to obtain an eye mask combination; calculating the blink frequency and incomplete blink data corresponding to each eye according to the target facial video and each eye mask combination; and determining the dry eye risk prediction result of each eye corresponding to the target object according to the blink frequency and incomplete blink data corresponding to each eye respectively. This patent application discloses in detail the use of the maximum eye opening amplitude (i.e., the maximum distance between the upper eyelid and the lower eyelid) to determine the existence of incomplete blinks. For example, when the maximum eye opening amplitude is not 0, this is because part of the eyeball is exposed outside the eyelids at this time. This patent application also discloses the conditions for judging dry eye: frequency condition and / or incomplete blink condition, and further gives an example that the dry eye condition is less than 15 times per minute (i.e., the frequency condition), or the incomplete blink frequency is not 0 times per second (i.e., the incomplete blink condition). However, this simple condition setting is not supported by any literature and does not conform to the objective situation. In addition, this technical solution only evaluates the dry eye risk through the blink frequency and incomplete blink data, not only ignoring the objective situation that there are great differences in blink frequencies among the subjects themselves, but also ignoring the influence of test conditions (such as the content viewed and the content carrier), and also ignoring the influence of subjective consciousness on the blink frequency and incomplete blink. Moreover, it does not mention the significance of the relationship between incomplete blinks and blink frequency for the development of dry eye conditions.

[0006] On the other hand, there are obvious contradictions between the technical solution disclosed in the patent application of CN116864105A and the existing research articles. For example, "Marked reduction and distinct patterns of eye blinking in patients with moderately dry eyes during video display terminal use" published by Schlote, T., Kadner, G., & Freudenthaler, N. in 2004 (see Graefe's Archive for Clinical and Experimental Ophthalmology, 242, 306 - 312). This article investigated the Spontaneous Eye Blink Rate (SEBR). During the conversation, the average value of SEBR was 16.8 blinks per minute; during the initial use of the video display terminal (VDT), SEBR significantly decreased to 6.6 ± 4.8 blinks per minute (P < 0.001); after re - measurement after 30 minutes of work, SEBR was 5.9 ± 4.6 blinks per minute (P < 0.001), showing no significant difference compared with the initial VDT use period (P = 0.65); in addition, during the conversation and VDT use, SEBR showed significant inter - individual differences. Thus, this article concluded that during the use of the video display terminal, the reduction of SEBR is mainly determined by obvious visual attention rather than dry eye. Cardona G, Garcia C, Seres C, Vilaseca M, Gispets J. pointed out in "Blink rate, blink amplitude, and tear film integrity during dynamic visual display terminal tasks" published in 2011 (see Curr Eye Res. 2011; 36(3): 190–197, doi: 10.3109 / 02713683.2010.544442) that the influence of the presented content on the blink frequency, amplitude, and incomplete blinks cannot be ignored. For example, the blink rate during fast - paced and slow - paced games decreased to nearly 1 / 3 and 1 / 2 of the baseline level respectively, and the proportion of incomplete blinks was larger during dynamic tasks. The research content of the above two articles shows that there is currently no unified standard for evaluating dry eye based on the blink frequency and incomplete blink frequency, and no relevant research shows that a fixed condition can be used to evaluate the dry eye risk of most people.In different studies, the differences in the blink pattern and its impact on the stability of the tear film are complex and diverse, making it difficult to generally apply to the diagnosis of dry eye in most people under a single fixed condition.

[0007] In addition, on the one hand, there are differences in the understanding of those skilled in the art; on the other hand, when the applicant made this invention, a large number of documents and patents were studied, but due to space limitations, not all details and contents were listed in detail. However, this does not mean that this invention does not possess the features of these prior arts. On the contrary, this invention already has all the features of the prior arts, and the applicant reserves the right to add relevant prior arts in the background art. Summary of the Invention

[0008] Simply relying on the blink frequency or the incomplete blink frequency as the criterion for judging dry eye does not have sufficient reliability and universality. The blink action is a complex reflex activity jointly participated by the central nervous system and the peripheral nervous system, involving multiple levels of the autonomic and somatic nervous systems. The autonomic nervous system plays an important role in tear secretion and the ocular surface protection mechanism. The autonomic nervous system consists of the sympathetic nerve and the parasympathetic nerve, and these two parts complement each other in regulating the function of the lacrimal gland. The parasympathetic nerve plays a promoting role in the blink action. It can increase tear secretion and help lubricate the eyes. The sympathetic nerve, on the other hand, reduces tear secretion and the blink frequency under stress conditions to maintain alertness. The blink action is also controlled by the somatic nervous system, especially the neural circuits in the cerebral cortex and the brainstem. The cerebral cortex can consciously control the blink frequency and intensity. Specifically, the cerebral cortex can regulate the intentional control of blinking, such as reducing the blink frequency when concentrating on the line of sight is required. The cerebral cortex (especially the primary motor cortex) controls the movement of blinking through neuronal connections. These neurons send signals that are transmitted to the brainstem through the corticobulbar tract, thereby affecting the blink action. The prefrontal cortex (especially the dorsal prefrontal cortex) is involved in planning and executing complex motor sequences, including conscious blink actions. It can regulate the timing and frequency of blinking. In addition, the cerebral cortex has neural plasticity and can adjust the control of blinking through learning and experience. For example, through practice, the coordination and accuracy of blinking can be improved. For the blink parameters, in order to better complete the task, the subject will subjectively control the closing of the eyes, that is, the number of blinks is subjectively allocated by the subject (see the master's thesis of Beijing University of Posts and Telecommunications, "Research on Visual Fatigue of Naked-eye 3D Dynamic Display Based on Human Eye Visual Characteristics" published by Li Yifan in 2023).

[0009] The prior art usually directly determines whether a user has dry eye based on parameters such as the blink frequency, and proposes a solution based on the judgment result. For example, CN118155803A proposes a solution for correcting eye use habits for dry eye. However, it has problems such as overly complex data sources and being unfeasible. In particular, its technical implementation is very difficult. For example, the data collection method mainly obtains blink frequency and amplitude data by monitoring the eyelash overlap situation from the side through a monitoring glasses frame. This method may be affected by various factors in actual application, such as the head movement of the wearer, changes in ambient light, etc., which may affect the accuracy and reliability of the data; moreover, in order to ensure the accuracy of the data, a specially designed glasses frame and a supporting sensor system are required, which increases the cost and technical threshold of the product, making it difficult for ordinary users to accept or afford; in addition, the complexity of its data processing is extremely high. It integrates and analyzes data from different sources (such as blink frequency, near eye use distance, air humidity), which not only requires powerful computing power but also complex algorithms to ensure that the correlation between data is correctly interpreted. In addition, the reminder mechanism of the technical solution of this patent application is too complex, with a large number of meaningless reminders, resulting in low patient compliance; this will also cause users to have "reminder fatigue" and ignore truly important reminder and intervention information; moreover, there is also a lack of a personalized adjustment mechanism. Not only does it not mention how to perform customized reminder settings according to the specific conditions of different individuals, which means that all users will receive the same reminder strategy, ignoring individual differences and reducing the user experience; and it will also increase the psychological burden of patients, which is instead not conducive to their maintaining good eye use habits. Even worse, in terms of eye use behavior monitoring data, this patent application does not adjust according to a personalized baseline, resulting in too many false alarm data; this is because the symptoms of dry eye vary from person to person, and a general standard cannot be applied to everyone. Without establishing a personalized baseline based on individual characteristics (such as occupation), it is difficult to distinguish normal and abnormal eye use behaviors and easy to cause misjudgment. This also leads to the problem of insufficient dynamic adaptation, ignoring the dynamic changes in the health status of patients, such as also ignoring the dynamic changes brought about by environmental factors. This is because in addition to physiological factors, the external environment (such as working environment, climate conditions, etc.) will also greatly affect eye use behavior.

[0010] In view of the deficiencies of the prior art, the present invention provides an intervention system for dry eye related to video syndrome. The system includes: a personal computer with a front camera; and a humidifier that communicates with the personal computer.

[0011] Among them, the personal computer uses its front camera to collect the changes in the dynamic state of the eyes of the current user, and the analysis unit of the personal computer determines the total number of blinks of the current user according to the changes in the dynamic state of the eyes. The analysis unit determines a composite index representing poor eye - using behaviors related to dry eye according to the incomplete blink count and blink frequency in the total number of blinks within a predetermined time period.

[0012] Among them, the analysis unit determines the intervention reminder information according to the change of the composite index relative to the baseline data, generates an intervention plan for driving the humidifier according to the intervention reminder information, and sends the intervention plan to the humidifier.

[0013] Among them, the humidifier performs a humidifying operation for intervening in poor eye - using behaviors according to the intervention plan.

[0014] According to a preferred embodiment, the baseline data of the intervention system is a standardized reference value determined based on the eye dynamic conditions of users with the same application scenarios.

[0015] According to a preferred embodiment, the baseline data of the intervention system is a user - customized standardized reference value generated by combining the symptom scores of the user after professional examinations in the hospital.

[0016] According to a preferred embodiment, the composite index of the intervention system can change dynamically through different application scenarios displayed on the screen of the user's personal computer. Among them, different application scenarios include scenarios where the content displayed on the screen changes dynamically at a relatively fast speed, scenarios where the content displayed on the screen is static, and scenarios where the content displayed on the screen changes slowly.

[0017] Preferably, the scenario where the content displayed on the screen changes dynamically at a relatively fast speed refers to the image or video content presented on the screen having a high frame rate, rapid visual element changes, and frequent scene - switching content.

[0018] Preferably, the scenario where the content displayed on the screen is static refers to the scenario where the images, texts, or other visual elements displayed on the screen remain unchanged or have only very few changes within a period of time. For example, static content includes document reading, programming code editing, spreadsheet operation, static web page browsing, etc.

[0019] Preferably, the scenario where the content displayed on the screen changes slowly refers to the scenario where the image or video content displayed on the screen has changes, but the speed of these changes is slow, the frame rate is usually between 24 FPS and 30 FPS, and the user does not need to frequently adjust the line of sight or focal length, and the change frequency of visual elements is low. Common slow - changing content includes video conferencing, movie watching, slide presentation, online courses, etc.

[0020] According to a preferred embodiment, the analysis unit is configured to adjust the humidification level of the humidifier and / or change the spraying pattern of the humidifier according to different application scenarios displayed on the screen of the user's personal computer.

[0021] According to a preferred embodiment, the analysis unit is configured to, in a scenario where the content displayed on the screen changes dynamically and rapidly,

[0022] when the user's composite index is lower than the threshold of the baseline data, control the humidifier to the low humidification level;

[0023] when the user's composite index is within the normal range of the baseline data, control the humidifier to the medium humidification level;

[0024] when the user's composite index is higher than the threshold of the baseline data, control the humidifier to the high humidification level, and at the same time control the humidification rate of the humidifier to be adjusted according to the user's breathing rhythm,

[0025] wherein, the humidification frequency of the high humidification level is higher than that of the medium humidification level, and the humidification frequency of the medium humidification level is higher than that of the low humidification level.

[0026] According to a preferred embodiment, the analysis unit is configured to, in a scenario where the content displayed on the screen is static,

[0027] when the user's composite index is lower than the threshold of the baseline data, control to turn off the humidifier;

[0028] when the user's composite index is within the normal range of the baseline data, control the humidifier to the low humidification level;

[0029] when the user's composite index is higher than the threshold of the baseline data, control the humidifier to the medium humidification level.

[0030] According to a preferred embodiment, the analysis unit is configured to, in a scenario where the content displayed on the screen is static,

[0031] when the user's composite index is lower than the threshold of the baseline data, control to turn off the humidifier;

[0032] when the user's composite index is within the normal range of the baseline data, control the humidifier to the low humidification level;

[0033] when the user's composite index is higher than the threshold of the baseline data, control the humidifier to the medium humidification level, and at the same time, control the spraying pattern of the humidifier to be the wave-shaped spraying mode.

[0034] According to a preferred embodiment, the analysis unit is configured to, in a scenario where the content displayed on the screen changes slowly,

[0035] When the user's composite index is lower than the threshold of the baseline data, the gear of the humidifier is controlled to be adjusted to the medium humidification gear;

[0036] When the user's composite index is within the normal range of the baseline data, the gear of the humidifier is controlled to be the low humidification gear;

[0037] When the user's composite index is higher than the threshold of the baseline data, the gear of the humidifier is controlled to be adjusted to the high humidification gear. At the same time, the spray pattern of the humidifier is controlled to be the circular or cloud-shaped spray mode.

[0038] According to a preferred embodiment, the personal computer determines the user's current application scenario by the collaborative work of its integrated display driver unit and processor.

[0039] Technical effects of the present invention: The present invention provides an intervention system for dry eye related to video display terminal (VDT) syndrome. Instead of directly judging whether suffering from dry eye based on the blink frequency or incomplete blink frequency, the system monitors the user's blink behavior and dynamically intervenes in the user's eye-using habits, thereby preventing and alleviating the dry eye symptoms caused by VDT syndrome. The intervention system provided by the present invention collects the user's eye-using behavior data (such as blink frequency, proportion of incomplete blinks, etc.) and establishes personalized baseline data in combination with the user's working scenario. The determined baseline data is dynamically adjusted according to the changes in the daily eye-using behavior of the corresponding patient, and the adjustment of the baseline data can be determined according to the concentration degree of the change trend of the composite index. This adjustment mechanism of the personalized baseline data ensures the accurate and reliable evaluation results of the intervention system, and the patient can receive truly important intervention information at the appropriate time. This design not only improves the user's comfort but also avoids the psychological pressure caused by excessive reminders, helping the user better maintain good eye-using habits. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is the working block diagram of the intervention system provided by the present invention;

[0041] Figure 2 is the working flowchart of the intervention system provided by the present invention;

[0042] Figure 3 is the intervention plan generated by the intervention system when the screen shows content with fast dynamic changes provided by the present invention;

[0043] Figure 4 is the intervention plan generated by the intervention system when the screen shows static content provided by the present invention;

[0044] Figure 5 is the intervention plan generated by the intervention system when the screen shows a scene with slow changes provided by the present invention;

[0045] Figure 6 It is an application scenario diagram of the intervention system provided by the present invention;

[0046] Figure 7 It is a graph showing the change trend of the composite index corresponding to the scenario where the content displayed on the screen changes dynamically relatively quickly over time;

[0047] Figure 8 It is a graph showing the change trend of the composite index corresponding to the scenario where the content displayed on the screen is static over time;

[0048] Figure 9 It is a graph showing the change trend of the composite index corresponding to the scenario where the content displayed on the screen changes slowly over time;

[0049] Figure 10 It is a schematic diagram of collecting the blinking behavior by the front camera of a personal computer;

[0050] Figure 11 It is a scenario diagram of a patient obtaining an eye score through a professional eye examination in a hospital.

[0051] List of reference numerals

[0052] 100: Personal computer; 110: Front camera; 120: Screen; 130: Analysis unit; 140: Display driving unit; 200: Humidifier. Detailed implementation manners

[0053] The following is a detailed description with reference to the accompanying drawings.

[0054] In the present invention, the monitoring behavior during the continuous working period of the user is taken as an example to illustrate the intervention system.

[0055] The personal computer 100 in the present invention is an independent computer system with computing power, data processing ability and multi-tasking function. Among them, the front camera 110 integrated in the personal computer 100 can capture the dynamic state of the user's eyes, and is used to monitor the user's blinking behavior, eye health status and other biometric information. For example, the personal computer 100 can be a device such as a desktop PC, a laptop computer, a smart phone, etc.

[0056] In the present invention, the bad eye-using behaviors related to dry eye refer to the behavior habits that may cause or exacerbate phenomena such as tear film instability, ocular surface dryness, abnormal blinking frequency, etc. These behaviors usually interfere with the normal secretion and distribution of tears, resulting in insufficient lubrication on the corneal and conjunctival surfaces, and thus triggering or exacerbating dry eye symptoms. Examples of the bad eye-using behaviors related to dry eye include the behavior of staring at the screen 120 for a long time (using electronic devices such as computers, mobile phones, tablets, etc. for a long time).

[0057] Example 1

[0058] This embodiment provides an intervention system specifically for dry eye related to video syndrome, as Figures 1 to 6 shown. The intervention system of this embodiment is completely different from the passive diagnosis system in the prior art that evaluates and diagnoses dry eye through various parameters. The systems in the prior art usually rely on several physiological indicators to determine whether a user has dry eye, ignoring the influence of individual differences and environmental factors, resulting in the judgment result being unable to accurately reflect the user's eye health status, and also ignoring the intervention of bad eye-using behaviors. The occurrence of many cases of dry eye is closely related to the user's behavior habits. The intervention system provided in this embodiment forms an active intervention strategy through dynamic monitoring and real-time feedback, thereby effectively alleviating the symptoms related to dry eye associated with video syndrome.

[0059] The intervention system of this embodiment includes: a personal computer 100 with a front camera 110; and a humidifier 200 that communicates with the personal computer 100, as Figure 6 shown. The communication between the humidifier 200 and the personal computer 100 is achieved, for example, by connecting the humidifier 200 to the USB port of the personal computer 100 through a USB cable. The USB interface not only provides power supply but also can be used for data transmission. Preferably, the humidifier 200 is built with a Wi-Fi module and communicates with the personal computer 100 through the wireless network at home or in the office. The personal computer 100 can send control instructions to the humidifier 200 through a local area network (LAN) or the Internet. Preferably, the personal computer 100 and the humidifier 200 can also be paired through the Bluetooth protocol to achieve wireless communication within a short distance. In this embodiment, the communication connection methods established between the personal computer 100 with the front camera 110 and the humidifier 200 are not listed one by one.

[0060] According to this embodiment, the personal computer 100 uses its front camera 110 to collect the dynamic state changes of the current user's eyes, and the analysis unit 130 of the personal computer 100 determines the total number of blinks of the current user according to the dynamic state changes of the eyes. The analysis unit 130 determines a composite index representing bad eye-using behaviors related to dry eye according to the incomplete blink times and blink frequency in the total number of blinks within a predetermined time period. The analysis unit 130 determines the intervention reminder information according to the change of the composite index relative to the baseline data, generates an intervention plan for driving the humidifier 200 according to the intervention reminder information, and sends the intervention plan to the humidifier 200, wherein the humidifier 200 performs a humidifying operation for intervening bad eye-using behaviors according to the intervention plan.

[0061] Preferably, the front camera 110 of the personal computer 100 collects the eye dynamic state information of the user at specific intervals. For example, the front camera 110 collects the eye dynamic state information of the user every 20 minutes, 30 minutes, or 40 minutes.

[0062] According to this embodiment, the eye dynamic state information includes the total number of blinks, the number of incomplete blinks, etc.

[0063] The steps for the personal computer 100 to process information are as follows:

[0064] S1: Data acquisition

[0065] When the user is using the computer, the front camera 110 is activated to start capturing the user's facial and eye images, as Figure 10 shown. The camera continuously collects video streams at a frequency of, for example, 30 frames per second and transmits them to the analysis unit 130 (the processor of the personal computer 100 in this embodiment).

[0066] S2: Video preprocessing

[0067] Preprocess the collected video frames, including operations such as denoising, contrast enhancement, and edge detection, to ensure that the image quality meets the analysis requirements, especially in low-light or complex background environments; use computer vision algorithms (such as Haar cascade classifiers or deep learning models) to detect and locate the user's binocular regions. Ensure that the dynamic changes of the eyes can be accurately captured each time for analysis; identify blink behaviors by analyzing the motion characteristics of the eye regions. Specifically, the methods for identifying blink behaviors include the detection of the position changes of the upper and lower eyelids, the calculation of the blink amplitude, and the calculation of the blink duration. The methods for identifying blink behaviors belong to mature existing technologies and will not be elaborated in this embodiment.

[0068] S3: Data analysis

[0069] Blink count statistics. Within a predetermined time period (such as every minute or every 10 minutes), count the total number of blinks of the user. This includes the number of complete blinks and incomplete blinks;

[0070] Blink frequency calculation. According to the total number of blinks and the time period, calculate the blink frequency (times per minute). Changes in the blink frequency can help determine whether the user has excessive eye use or abnormal blinking conditions;

[0071] Incomplete blink ratio calculation. Calculate the ratio of the number of incomplete blinks to the total number of blinks. A high ratio of incomplete blinks indicates that the user's eyes are in a tense state and the tear film stability is poor;

[0072] Composite index generation. Based on the blink frequency and the incomplete blink ratio, generate a composite index representing the adverse eye use behaviors related to dry eye.

[0073] S4: Feedback and Intervention

[0074] When the composite index exceeds the baseline data, the analysis unit 130 of the personal computer 100 determines an intervention reminder message based on the change of the composite index relative to the baseline data, generates an intervention plan for driving the humidifier 200 according to the intervention reminder message, and sends the intervention plan to the humidifier 200 connected to the personal computer 100 to control the humidifier 200 to perform a humidifying operation for intervening in the bad eye-using behavior according to the intervention plan.

[0075] The baseline data in this embodiment refers to the standard reference value for evaluating the user's blinking behavior and eye health status. The system determines whether to send an intervention reminder message and generate a corresponding intervention plan by comparing the change of the user's real-time composite index with the baseline data.

[0076] Preferably, the baseline data in this embodiment is a standardized reference value determined by big data analysis and machine learning models based on the eye movement conditions of a large number of users with the same application scenarios. This mode is applicable to a wide range of user groups, provides a general benchmark, and helps the system identify the prevalent bad eye-using behaviors. Specifically, when the user uses the personal computer 100, the front camera 110 collects the user's eye movement data (such as the number of blinks, the number of incomplete blinks, the blink frequency, the proportion of incomplete blinks, etc.) and anonymously uploads these data to the cloud server regularly. After receiving the uploaded data from multiple users, the cloud server processes these data using big data analysis models (such as machine learning models like random forest, support vector machine, neural network, etc.). By methods such as cluster analysis and regression analysis, the typical eye movement characteristics in different application scenarios are identified, and the corresponding baseline data is generated for each scenario.

[0077] According to this embodiment, the intervention reminder message is a signal generated by the analysis unit 130 (processor) of the personal computer 100 in the intervention system based on the change information of the user's eye movement state, and is used to control the humidifier 200 to perform a humidifying operation. The core purpose of these reminder messages is to intervene in the user's bad eye-using behaviors related to dry eye by adjusting the humidifying rhythm and spray pattern (spray pattern) of the humidifier 200 to relieve the bad symptoms.

[0078] According to this embodiment, the personal computer 100 determines that the current application scenario of the user is carried out by the collaborative work of a display driving unit 140 such as a graphics processing unit (GPU) and the CPU. In this embodiment, the GPU is not only responsible for processing display content (such as videos, games, web pages, etc.), but also works in cooperation with the CPU to help determine the current usage scenario. By monitoring the working state of the GPU (such as load, frame rate, rendering mode, etc.), the CPU can infer the type of content that the user is currently viewing (such as office documents, videos, games, etc.), and load corresponding calculation schemes for the blink frequency and the number of incomplete blinks according to different content types.

[0079] Specifically, the recognition steps of the application scenario of the personal computer 100 and the loading method of the calculation scheme are as follows:

[0080] S1: GPU Working State Monitoring

[0081] The CPU monitors the working state of the GPU in real time through a communication interface with the GPU (such as a PCIe bus), including load, frame rate, rendering mode, etc. Based on this information, the CPU can infer the type of content that the user is currently viewing.

[0082] S2: Calculation Scheme Loading

[0083] According to the recognized content type, the CPU loads corresponding calculation schemes for the blink frequency and the number of incomplete blinks. Each content type corresponds to different baseline data and intervention thresholds.

[0084] S3: Blink Behavior Analysis

[0085] Video acquisition and preprocessing, eye region localization, blink detection and statistics, blink frequency change and ratio change. This step is prior art and will not be elaborated in this embodiment.

[0086] S4: Composite Index Generation

[0087] Baseline data comparison. The analysis unit 130 compares data such as the user's blink frequency and incomplete blink ratio with the corresponding baseline data to generate a composite index representing bad eye-using behaviors related to dry eye;

[0088] Scene adaptability adjustment. According to different content types, the analysis unit 130 dynamically adjusts the threshold of the composite index.

[0089] In this embodiment, the test value of the corresponding composite index is generated by simulating the eye - using condition of a patient working for 8 hours. Since the content viewed by the subject is different, for example, the screen 120 displays content with fast dynamic changes, static content, or content with slow changes, etc., the same patient can be tested for three consecutive days. For example, on the first day, let the patient view content with fast dynamic changes, simulating the state of normal work for one day (8 hours). Within a continuous hour, calculate the test value of the composite index every 10 minutes. This test method is carried out in the mode of the patient's normal working hours, so the data obtained is more in line with the actual situation.

[0090] S5: Feedback and Intervention

[0091] When the composite index exceeds the baseline data, the analysis unit 130 of the personal computer 100 determines the intervention reminder information according to the change of the composite index relative to the baseline data, generates an intervention plan for driving the humidifier 200 according to the intervention reminder information, and sends the intervention plan to the humidifier 200 connected to the personal computer 100 to control the humidifier 200 to perform the humidifying operation for intervening in bad eye - using behaviors according to the intervention plan.

[0092] According to this embodiment, the intervention plan includes the adjustment of the humidifying gear of the humidifier 200 and the humidifying mode of the reminder function.

[0093] Preferably, the adjustment of the humidifying gear of the humidifier 200 includes a high - humidifying gear, a medium - humidifying gear, and a low - humidifying gear. Among them, the humidifying frequency of the high - humidifying gear is higher than that of the medium - humidifying gear, and the humidifying frequency of the medium - humidifying gear is higher than that of the low - humidifying gear.

[0094] Preferably, the humidifying mode of the reminder function includes accelerating the humidifying rate, decelerating the humidifying rate, changing the spray form of the humidifier 200, or turning off the humidifier 200 according to the user's breathing rhythm.

[0095] Embodiment 2

[0096] This embodiment is a further improvement of Embodiment 1, and the repeated content will not be elaborated.

[0097] This embodiment provides an intervention system for bad eye - using behaviors related to dry eye in the scenario where the screen 120 displays content with fast dynamic changes (such as games or sports movies).

[0098] The analysis unit 130 of the personal computer 100 is configured to calculate the corresponding composite index C, and the calculation formula of the composite index C is:

[0099] C = w1·F ratio + w2·I change ,

[0100] Among them, F ratio is the blink frequency ratio, which represents the change in blink frequency when using a video display terminal (VDT) relative to the initial blink frequency, that is, it reflects the relative change of blink frequency over time; I change is the change amount of incomplete blinks, which represents the degree of change in the proportion of incomplete blinks from the start to the current sampling time point or the end time point, that is, it directly measures the change in the proportion of incomplete blinks; w1 and w2 are weight coefficients used to adjust F ratio and I change 's importance, and satisfy w1 + w2 = 1.

[0101] Herein, Among them, F initial is the initial blink frequency, and F final is the current or final blink frequency after an interval of a specific time period (such as 30 minutes).

[0102] Herein, I change = I final - I initial Among them, I initial is the initial proportion of incomplete blinks, and I final is the current or final proportion of incomplete blinks after an interval of a specific time period (such as 30 minutes).

[0103] According to this embodiment, the weight coefficients w1 and w2 are determined based on expert knowledge and clinical experience or historical data.

[0104] In this scenario, due to highly concentrated attention, the blink frequency will decrease, while the proportion of incomplete blinks will increase significantly. The calculation scheme of the composite index in this embodiment can well capture the changes of these two variables. In particular, it reflects the change of blink frequency relative to the initial state through the blink frequency ratio F ratio and quantifies the increase in the proportion of incomplete blinks through the change amount of incomplete blinks I chage . Therefore, this scheme can effectively identify this type of bad eye - using behavior and provide a comprehensive evaluation index.

[0105] The test data for determining the risk threshold of the composite index in this embodiment is for one subject. Specifically, in this embodiment, the same subject is tested continuously for 8 hours (the content watched is content with fast - changing dynamics, such as a sports movie) to obtain a trend graph of the change of the composite index over time, specifically as Figure 7 shown.

[0106] Figure 7In it, the abscissa is time and the ordinate is the test value of the composite index. Each curve represents the test value of the composite index within one hour. Among them, the slopes of the curves in this figure are relatively scattered, and the test values of the composite index at the same time point fluctuate greatly. When the system makes a judgment (compared with the risk threshold of the composite index), due to the relatively scattered change trend, the composite index is judged to exceed the risk threshold. Therefore, when the system controls the intervention plan of the humidifier 200, it cannot intervene in this patient more accurately or appropriately, but will affect this patient due to frequent false alarms.

[0107] Embodiment 3

[0108] This embodiment is a further improvement of Embodiment 1, and the repeated content will not be elaborated.

[0109] This embodiment provides an intervention system for adverse eye use behaviors related to dry eye based on the scenario of the screen 120 displaying static content.

[0110] The analysis unit 130 of the personal computer 100 is configured to calculate the corresponding composite index C, and the calculation formula of the composite index C is:

[0111] C = w1·F + w2·(1 - I),

[0112] where w1 and w2 are weight coefficients, satisfying w1 + w2 = 1; F is the blink / eye blink frequency (times / minute); I is the proportion of incomplete blinks in the total number of blinks (incomplete blink proportion, expressed as a percentage), ranging from 0 to 1; 1 - I represents the proportion of complete blinks. When I is close to 0, it indicates that most blinks are complete; when I is close to 1, it indicates that most blinks are incomplete.

[0113] According to this embodiment, the weight coefficients w1 and w2 are determined based on expert knowledge and clinical experience or historical data.

[0114] For static content, the eye blink behavior of the user is more stable, and the change in the proportion of incomplete eye blinks is relatively small. In this case, the calculation scheme of the composite index provided by this embodiment takes into account the eye blink frequency F and the proportion of complete eye blinks 1 - I, and can balance the importance of the two by adjusting the weights w1 and w2. For example, w1 = 0.6 and w2 = 0.4. That is, this scheme can sensitively capture the small changes in the eye blink frequency, and can reflect potential adverse eye use behaviors even if the proportion of incomplete eye blinks remains relatively constant.

[0115] The test data for determining the risk threshold of the composite index in this embodiment is for one subject. Specifically, in this embodiment, the same subject is tested continuously for 8 hours (the content viewed is static content, such as Word text content) to obtain a trend chart of the change of the composite index over time, specifically asFigure 8 as shown

[0116] Figure 8 In the figure, the abscissa is time and the ordinate is the test value of the composite index. Each curve represents the test value of the composite index within one hour. Although the trend changes of the curves in this figure are relatively consistent, the test values of the composite index at the same time point fluctuate greatly. When the system makes a judgment (compared with the risk threshold of the composite index), the changes in the test values of the composite index are relatively scattered, reducing the uncertainty of the judgment. Deviations may also occur in the setting of the threshold. Therefore, when the system controls the intervention plan of the humidifier 200, false alarms or adjustment plans are more likely to occur frequently, affecting the work of this patient.

[0117] Example 4

[0118] The baseline data of this example is a user-customized standardized reference value generated by combining the unified mode and the symptom score after the user's professional examination in the hospital. This way of determining the baseline data can more accurately reflect the individual differences of users and provide a more personalized intervention plan. Specifically, the user can go to the hospital for a professional eye examination. As Figure 11 shown, the doctor will give a score for dry eye according to the actual situation of the user, and this score is uploaded to the personal computer 100 or the cloud server as an important part of the personalized baseline data.

[0119] This example is a further improvement of Example 1, and the repeated content will not be elaborated.

[0120] This example provides an intervention system for bad eye-using behaviors related to dry eye in the scenario where the content displayed on the screen 120 changes slowly.

[0121] The analysis unit 130 of the personal computer 100 is configured to calculate the corresponding composite index C, and the calculation formula of the composite index C is:

[0122] C = F × (1 - I) and / or

[0123] C = w1·F reduced + w2·I score ,

[0124] For C = F × (1 - I), where F is the number of complete blinks per minute, that is, the blink / eye blink frequency; I is the proportion of incomplete blinks in the total number of blinks (incomplete blink ratio), ranging from 0 to 1; 1 - I represents the proportion of complete blinks.

[0125] For C = w1·F reduced + w2·I score , where w1 and w2 are weight coefficients used to adjust F ratio and Ichange The importance, satisfying w1 + w2 = 1; F reduced is the degree of reduction in the blink frequency relative to the normal situation; I score is the weighted value between the proportion of incomplete blinks and the symptom score.

[0126] According to this embodiment,

[0127] wherein, F VDT is the blink frequency during the use of the video display terminal; F normal is the blink frequency under normal circumstances.

[0128] According to this embodiment, I score = I × S,

[0129] wherein, I is the proportion of incomplete blinks, and S is the symptom score of the user's professional examination in the hospital.

[0130] According to this embodiment, C = F × (1 - I) captures the combined effect between the blink frequency and the quality of complete blinks. Specifically, when F is large and I is small, that is, when the blink frequency is high and most blinks are complete blinks, the value of C will be high, which represents a good ocular surface moist state; on the contrary, if F is small or I is large, even if the blink frequency is not high or many blinks are incomplete, then the value of C will be low, which indicates insufficient ocular surface moisture and a higher risk of dry eye.

[0131] When the blink behavior shows a large degree of uncertainty or randomness, the intervention system requires a composite index that can both capture the blink frequency and reflect the impact of incomplete blinks. The calculation scheme of C = F × (1 - I) multiplies the blink frequency F by the proportion of complete blinks 1 - I to form a single product term. This method may have more advantages when dealing with data with large fluctuations because it emphasizes the simultaneous effect of both. On the other hand, to retain more flexibility and allow for an independent assessment of the degree of reduction in the blink frequency, this embodiment also utilizes C = w1·F reduced + w2·I score The calculation scheme, which separately considers the reduction in the blink frequency F reduced and the score of incomplete blinks I score , and is adjusted by the weights w1 and w2.

[0132] The test data for determining the risk threshold of the composite index in this embodiment is for one patient. Specifically, in this embodiment, the same subject is tested continuously for 8 hours (slowly changing content) to obtain a trend graph of the change of the composite index over time, specifically as Figure 9 shown. Figure 9Shows the changing trends of the first composite index (C1) and the second composite index (C2) over time. The first hour to the eighth hour in the figure represent 8 trials in 8 hours respectively.

[0133] Since the blinking behavior, eye movement state of each individual, and the reaction to the content being watched are all unique. In this embodiment, the variable of individual differences is controlled by conducting tests on the same patient for three consecutive days, avoiding the interference caused by differences such as physiological characteristics, eye - using habits, and environmental adaptability. When the same patient is tested within the same time period, their behavior patterns (such as work intensity, rest frequency, etc.) are more stable, reducing the result deviation caused by the behavior differences of different patients. On the other hand, by using the data of the same patient, baseline data suitable for this patient can be determined according to the different scenarios the patient is in and the individual's eye state. This baseline data can more accurately evaluate the impact of different screen 120 contents on the blinking behavior and composite index, without the situation that the baseline differences between different patients are too large, resulting in an intervention plan for system adjustment that is not suitable for the patient.

[0134] Figure 9 It shows that the test values of the composite index of the first composite index are more discrete at the same time point, while the test values of the composite index of the second composite index fluctuate less (more convergent) at the same time point, indicating that the changing trend of the second composite index is more concentrated. That is, using the test values of the second composite index can better reflect the overall changing trend of the eye state of this patient, with fewer individual abnormal situations. The setting of the baseline data (risk threshold) needs to be based on the situation where the overall data distribution and trend are more consistent. In this embodiment, by collecting the changing trends of the first composite index and the second composite index, it is determined that the second composite index C2 can be used to adjust the parameters of C1. The concentration of the slope of the second composite index means that the changing trend of the data is more consistent, thereby improving the prediction accuracy. This means that at future time points, the value of the second composite index of the patient can be predicted more accurately, so as to better evaluate the eye state of the patient. Further, since the slope and threshold of the second composite index can more accurately reflect and predict the eye state of the patient, the second composite index can be used to adjust the parameters of the first composite index. In addition, the baseline data or risk threshold determined based on the second composite index can prevent the system from frequently sending false alarms to interfere with the patient.

[0135] According to this embodiment, two indicators, namely the slope and the threshold of the trend graph with a more consistent or convergent trend, are used to judge the eye - using situation of the patient, effectively improving the system's judgment and prediction of the user's bad eye - using behaviors related to dry eye, so as to generate an eye intervention plan that better suits the corresponding patient.

[0136] Example 5

[0137] This embodiment is a further improvement of Embodiment 4, and the repeated content will not be elaborated.

[0138] This embodiment provides another intervention system for adverse eye-using behaviors related to dry eye in a scenario where the screen 120 displays slowly changing content.

[0139] The screen 120 displays slowly changing content, and the changes in the user's blink frequency and the proportion of incomplete blinking are random. This means that further analysis is needed to determine whether there are adverse eye-using behaviors related to dry eye. To improve the accuracy of prediction, the present invention first uses the calculation scheme of C = F×(1 - I) for preliminary evaluation, and then uses C = w1·F reduced + w2·I score for review. This method combines the advantages of two different strategies and can provide more comprehensive and detailed results.

[0140] This embodiment first uses the calculation scheme of C = F×(1 - I) for preliminary evaluation to screen out possible risk situations; then uses C = w1·F reduced + w2·I score for review. Introducing the doctor's diagnosis symptom score means that medical expertise can be used to supplement the objectively measured data. At this time, in addition to continuing to monitor the blinking behavior, professional symptom scores can be provided based on the diagnosis of an ophthalmologist, clinical experience, and the patient's self-report to confirm whether humidification intervention needs to be carried out. Therefore, combining the two calculation schemes can obtain a more accurate risk assessment conclusion to scientifically judge whether humidification intervention needs to be carried out.

[0141] Through such a combined use method, not only can the advantages of automated monitoring be fully utilized, but also important decisions can be supported by professional diagnosis, thereby improving the reliability and effectiveness of the entire intervention system. In addition, this method also provides experience for the subsequent dry eye research of current users, helps to continuously optimize the personalized evaluation algorithm to make it more in line with the actual needs of corresponding users.

[0142] It should be noted that the above specific embodiments are exemplary. Those skilled in the art can come up with various solutions inspired by the disclosed content of the present invention, and these solutions also belong to the disclosure scope of the present invention and fall within the protection scope of the present invention. Those skilled in the art should understand that the specification and drawings of the present invention are illustrative and do not constitute a limitation on the claims. The protection scope of the present invention is defined by the claims and their equivalents. The specification of the present invention contains multiple inventive concepts. For example, "preferably" and "according to a preferred embodiment" both indicate that the corresponding paragraphs disclose an independent concept. The applicant reserves the right to file divisional applications according to each inventive concept.

Claims

1. An intervention system for dry eye associated with screen syndrome, the intervention system comprising: A personal computer (100) with a front camera (110); and a humidifier (200) communicating with the personal computer (100), The invention is characterized in that the personal computer (100) uses its front camera (110) to collect the changes in the dynamic state of the eyes of the current user, and the analysis unit (130) of the personal computer (100) determines the total number of blinks of the current user according to the changes in the dynamic state of the eyes, and the analysis unit (130) determines the composite index representing the adverse eye behavior related to dry eye syndrome according to the number of incomplete blinks and the blink frequency in the total number of blinks within a predetermined time period, The analysis unit (130) determines intervention reminder information according to the change of the composite index relative to the baseline data, generates an intervention plan for driving the humidifier (200) according to the intervention reminder information, and sends the intervention plan to the humidifier (200). Wherein, the humidifier (200) performs a humidification operation for intervening in adverse eye behavior according to the intervention plan.

2. The intervention system for dry eye associated with screen syndrome according to claim 1, characterized in that: The baseline data of the intervention system is a standardized reference value determined based on the eye dynamics of users with the same application scenario.

3. The intervention system for dry eye associated with screen syndrome according to claim 1, characterized in that: The baseline data of the intervention system is a user-customized standardized reference value generated by combining the symptom score of the user after a professional examination in the hospital.

4. The intervention system for dry eye associated with screen syndrome according to claim 1, characterized in that: The composite index of the intervention system can change dynamically through different application scenarios displayed on the screen (120) of the user's personal computer (100), wherein the different application scenarios include a scenario in which the screen (120) displays content that changes rapidly, a scenario in which the screen (120) displays static content, and a scenario in which the screen (120) displays content that changes slowly.

5. The intervention system for dry eye associated with screen syndrome according to claim 4, characterized in that: The analysis unit (130) is configured to adjust the humidification level of the humidifier (200) and / or change the spray form of the humidifier (200) according to different application scenarios displayed on the screen (120) of the user's personal computer (100).

6. The intervention system for dry eye associated with screen syndrome according to claim 5, characterized in that: The analysis unit (130) is configured to: in a scenario where the screen (120) displays content that changes rapidly dynamically, When the user's composite index is lower than the threshold of the baseline data, the gear of the humidifier (200) is controlled to be a low humidification gear; When the user's composite index is within the normal range of the baseline data, the gear of the humidifier (200) is controlled to be the medium humidification gear; When the composite index of the user is higher than the threshold value of the baseline data, the gear of the humidifier (200) is controlled to be a high humidification gear, and the humidification rate of the humidifier (200) is controlled to be adjusted according to the breathing rhythm of the user. Among them, the humidification frequency of the high humidification gear is higher than that of the medium humidification gear, and the humidification frequency of the medium humidification gear is higher than that of the low humidification gear.

7. The intervention system for dry eye associated with screen syndrome according to claim 5, characterized in that: The analysis unit (130) is configured to: in a scenario where the screen (120) displays static content, When the user's composite index is lower than the threshold of the baseline data, controlling to turn off the humidifier (200); When the user's composite index is within the normal range of the baseline data, the gear of the humidifier (200) is controlled to be a low humidification gear; When the user's composite index is higher than the threshold of the baseline data, the gear of the humidifier (200) is controlled to be the medium humidification gear.

8. The intervention system for dry eye associated with screen syndrome according to claim 5, characterized in that: The analysis unit (130) is configured to: in a scenario where the screen (120) displays static content, When the user's composite index is lower than the threshold of the baseline data, controlling to turn off the humidifier (200); When the user's composite index is within the normal range of the baseline data, the gear of the humidifier (200) is controlled to be a low humidification gear; When the user's composite index is higher than the threshold value of the baseline data, the gear of the humidifier (200) is controlled to be the medium humidification gear, and at the same time, the spray pattern of the humidifier (200) is controlled to be a wave-shaped spray pattern.

9. The intervention system for dry eye associated with screen syndrome according to claim 5, characterized in that: The analysis unit (130) is configured to: in a scenario where the screen (120) displays slowly changing content, When the user's composite index is lower than the threshold of the baseline data, the gear of the humidifier (200) is controlled to be adjusted to the medium humidification gear; When the user's composite index is within the normal range of the baseline data, the gear of the humidifier (200) is controlled to be a low humidification gear; When the user's composite index is higher than the threshold of the baseline data, the gear of the humidifier (200) is controlled to be adjusted to a high humidification gear, and at the same time, the spray pattern of the humidifier (200) is controlled to be a circular or cloud-shaped spray pattern.

10. The intervention system for dry eye associated with screen syndrome according to claim 1, characterized in that: The personal computer (100) determines the user's current application scenario by utilizing the coordinated work of its integrated display drive unit (140) and processor.

Images