Self-service vision detector capable of reading human body actions by AI (Artificial Intelligence)

Abstract

The invention discloses a self-service vision detector for AI human body action reading, which comprises an action capture module, an eye movement tracking module, a self-adaptive test module, a feedback and suggestion module, an intelligent diagnosis module and a user interaction interface module, and is characterized in that the action capture module captures and analyzes human body actions in real time by using a camera or a sensor; the eye movement tracking module detects visual response of a user by analyzing movement tracks of eyeballs in real time, the self-adaptive testing module automatically adjusts difficulty of testing content according to eye movement data of the user, and the feedback and suggestion module analyzes results according to response time of the user and focusing precision data of the eyes. According to the method, the vision level of the user is automatically judged, a detailed diagnosis report is generated, and compared with the prior art, a feedback mechanism can reduce man-made interference and improve the accuracy and reliability of testing.

Description

Technical Field

[0001] This invention relates to the field of self-service vision testing technology, specifically to a self-service vision testing device that uses AI to read human movements. Background Technology

[0002] With the advancement of technology, vision testing has gradually shifted from traditional manual operation and single testing methods to intelligent and automated systems. Traditional vision testing usually relies on manual operation, and the testing process is relatively cumbersome and easily affected by human factors. The test results may be affected by factors such as user cooperation and ambient light, and the accuracy is somewhat uncertain. In addition, traditional vision testing equipment often requires professional ophthalmologists to operate, which cannot fully meet the needs of daily self-testing.

[0003] In recent years, self-service vision testing systems that combine advanced technologies such as artificial intelligence, computer vision, and eye tracking have gradually emerged. These intelligent testing systems can make vision testing more convenient, accurate, and personalized through high-precision sensors, AI algorithms, and interactive interfaces, and can automatically complete testing and analysis without an ophthalmologist.

[0004] However, current intelligent vision detection systems still face challenges such as accuracy, user experience, and adaptability, especially in areas like gesture recognition and dynamic adjustment, which still require optimization. Summary of the Invention

[0005] This invention provides a self-service vision tester that uses AI to read human movements, which can effectively solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an AI-powered self-service vision tester for reading human movements, comprising a motion capture module, an eye tracking module, an adaptive testing module, a feedback and suggestion module, an intelligent diagnosis module, and a user interface module;

[0007] The motion capture module uses cameras or sensors to capture and analyze human movements in real time.

[0008] The eye-tracking module detects the user's visual response by analyzing the movement trajectory of the eyeball in real time;

[0009] The adaptive testing module automatically adjusts the difficulty of the test content based on the user's eye movement data;

[0010] The feedback and suggestion module automatically determines the user's vision level based on the analysis results of the user's reaction time and eye focusing accuracy data, and provides corresponding feedback.

[0011] The intelligent diagnostic module of the user AI system provides diagnostic results by comprehensively analyzing the user's test results based on a series of preset visual test schemes.

[0012] The user interface module allows users to interact with the device via touchscreen, voice, or gesture commands to complete vision testing tasks.

[0013] Furthermore, in order to comprehensively and quantitatively assess the user's visual acuity, the following fusion scoring formula is adopted:

[0014]

[0015] in:

[0016] V represents the final visual acuity assessment score;

[0017] E represents the eye-tracking performance score, which includes indicators such as fixation time and tracking accuracy.

[0018] F represents the user focus and responsiveness rating;

[0019] D is the score output by the intelligent diagnostic module, which is based on the comprehensive analysis of the visual test results by AI;

[0020] M represents the motion interference factors obtained by the motion capture module, such as head movement amplitude or posture deviation;

[0021] U represents the user interaction efficiency score, such as the success rate of voice or gesture operations;

[0022] A represents the adaptive test adjustment range, reflecting the user's ability to cope with different changes in visual difficulty;

[0023] α, β, γ, and θ are weights and adjustment coefficients set internally by the system or optimized through machine learning.

[0024] Through the above fusion formula, the system can perform quantitative analysis and dynamic judgment of the user's vision status based on multi-dimensional input.

[0025] According to the above technical solution, the motion capture module is designed with a red light under each character on the vision chart, and then the subject responds by waving his hand according to the direction of the character;

[0026] The camera captures gesture signals, calculates whether they are correct, records the results as needed, and provides a prompt for the next detection character.

[0027] According to the above technical solution, the gesture data captured by the camera is analyzed by image recognition technology to determine whether it conforms to the preset response method. Real-time feedback is given based on the accuracy of gesture recognition. If the subject responds correctly, the system displays the next character for testing.

[0028] If the response is incorrect, the system will prompt you to try again and record the result. Each response result will be recorded, and the system will adjust the prompting method for the next detection character based on the user's performance.

[0029] According to the above technical solution, the eye-tracking module uses a high-precision camera or infrared sensor to monitor the movement trajectory of the subject's eyeballs in real time. By analyzing the subtle movements of the eyeballs, it can detect whether the user has made a corresponding focusing and tracking response to the targets such as letters, numbers or graphics presented on the screen.

[0030] The accuracy and stability of eye tracking enable the system to quickly assess a user's visual abilities. Furthermore, eye tracking data can provide crucial information for personalized vision assessments.

[0031] According to the above technical solution, the eye-tracking module can not only monitor the movement trajectory of the eyeball in real time, but also calculate the eyeball's fixation time, focusing stability and eyeball movement speed through AI analysis algorithms;

[0032] In addition, the subsequent visual testing plan is adjusted based on real-time eye-tracking data.

[0033] According to the above technical solution, the intelligent diagnostic module uses an AI system and a preset visual testing scheme to comprehensively analyze the user's test data. The AI ​​system can not only evaluate the accuracy of each test result, but also establish connections between tests and identify potential visual problems.

[0034] According to the above technical solution, after completing a series of vision tests, the intelligent diagnostic module will automatically generate a personalized diagnostic report. The report not only includes the specific results of each test, but also provides users with further vision health management suggestions through data analysis.

[0035] According to the above technical solution, the feedback and suggestion module uses the user's reaction time and eye focusing accuracy data to analyze and automatically determine the user's vision level in real time, and provides personalized feedback and suggestions based on the analysis results;

[0036] Based on this feedback, the system will not only alert users to specific problems, but also provide them with targeted solutions.

[0037] According to the above technical solution, the user interface module provides users with a variety of interaction methods. The touch screen function allows users to select vision test content, adjust test settings, or view test results through intuitive clicks and swipes.

[0038] The voice command function uses voice recognition technology to allow users to operate the device without a touchscreen by using simple voice commands. Users can respond to characters or make selections by waving or gesturing.

[0039] According to the above technical solution, the self-service vision tester also includes either a vision test device or a projection device, depending on the situation.

[0040] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention has a scientifically sound and reasonable structure, is safe and convenient to use, and integrates eye-tracking, gesture recognition, and AI analysis technologies to achieve automated, intelligent, and personalized vision testing. It can capture users' eye-tracking data and gesture signals in real time, and through precise algorithm analysis of users' reaction time, focusing accuracy, and the correctness of gesture responses, it automatically judges users' vision levels and generates detailed diagnostic reports. Compared with existing technologies, the feedback mechanism can reduce human interference and improve the accuracy and reliability of the test. At the same time, the diverse interaction methods provided by the device greatly enhance the user experience, making it suitable for different age groups and user needs. Furthermore, it can adjust the test difficulty in real time based on the user's test results, ensuring that the testing process is both challenging and not overly cumbersome, helping users better understand their own vision status, effectively reducing the pressure on professional medical resources, and promoting the popularization and application of intelligent medical devices. Attached Figure Description

[0041] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof.

[0042] In the attached diagram:

[0043] Figure 1 This is a schematic diagram of the system structure of the present invention. Detailed Implementation

[0044] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0045] Example: Figure 1 As shown, the present invention provides a technical solution: an AI-powered self-service vision tester for reading human movements, comprising a motion capture module, an eye tracking module, an adaptive testing module, a feedback and suggestion module, an intelligent diagnosis module, and a user interface module.

[0046] The motion capture module uses cameras or sensors to capture and analyze human movements in real time. These sensors can accurately record eye movements, eye focus, and the eye tracking process.

[0047] The motion capture module has a red light under each character on the eye chart. The light can light up in a certain pattern to prompt the subject to look at a specific character. Then the subject responds by waving his hand according to the direction of the character.

[0048] The camera captures gesture signals, calculates whether they are correct, records the results as needed, and provides a prompt for the next detection character.

[0049] The gesture data captured by the camera is analyzed using image recognition technology to determine whether it conforms to the preset response method. The system provides real-time feedback based on the accuracy of gesture recognition. If the subject responds correctly, the system displays the next character for testing; if the response is incorrect, the system prompts for a retry and records the result. Each response result is recorded. The system adjusts the prompting method for the next detection character based on the user's performance, such as changing the size of the character or the interval between appearances. In this way, personalized and intelligent vision testing is achieved, which can automatically adjust the test difficulty and provide feedback on the user's performance, ensuring the accuracy and reliability of the test.

[0050] The eye-tracking module analyzes the movement trajectory of the eyes in real time to detect the user's visual response, such as whether the eyes focus on and track the letters, numbers, and graphics displayed on the screen.

[0051] The eye-tracking module uses a high-precision camera or infrared sensor to monitor the movement trajectory of the subject's eyes in real time. By analyzing the subtle movements of the eyes, it detects whether the user focuses and tracks targets such as letters, numbers, or graphics displayed on the screen. This technology can accurately determine whether the user's eyes maintain a clear focus on specific characters during visual testing, thereby assessing their visual acuity. The accuracy and stability of eye tracking allow the system to quickly determine the user's visual abilities, such as whether there are visual problems like myopia, hyperopia, or astigmatism. In addition, eye-tracking data can provide key evidence for personalized vision assessment and provide strong support for further visual health management and diagnosis.

[0052] The eye-tracking module not only monitors the movement trajectory of the eyeball in real time, but also uses AI analysis algorithms to calculate the eye's fixation time, focus stability, and eye movement speed for specific characters. This data helps the system identify the user's visual fatigue, focus stability, and reaction speed. For example, if the user focuses on a character for too long or the eyeball does not move smoothly between characters, it can prompt the user whether there is a visual problem or whether the viewing distance needs to be adjusted. In addition, the system will adjust the subsequent visual test plan based on real-time eye-tracking data, such as adjusting the display time, position, or size of the characters, to ensure the scientific nature and accuracy of the test process and help users obtain more accurate vision assessment results.

[0053] The adaptive testing module automatically adjusts the difficulty of the test content based on the user's eye movement data, for example by changing the size, contrast, and position of the letters;

[0054] The feedback and suggestion module automatically determines the user's vision level based on the analysis results of the user's reaction time and eye focusing accuracy data, and provides corresponding feedback.

[0055] The feedback and suggestion module utilizes user reaction time and eye focusing accuracy data to analyze and automatically determine the user's vision level in real time. Based on the analysis results, it provides personalized feedback and suggestions. For example, if a user reacts slowly or has unstable eye focus during a vision chart test, the system will automatically assess potential visual problems based on eye movement data, such as blurred vision, myopia, or hyperopia. Based on this feedback, it will not only alert the user to specific problems but also provide targeted solutions, such as recommending appropriate glasses prescriptions or suggesting regular eye health checkups. Simultaneously, the system will remind users to protect their vision, such as reducing prolonged close-up work and performing eye exercises. This intelligent analysis based on reaction time and eye focusing accuracy ensures the accuracy and personalization of feedback and suggestions, helping users take effective measures in daily life to maintain and improve their vision health.

[0056] The intelligent diagnostic module uses the user's AI system to perform a series of preset visual testing schemes;

[0057] Tests such as visual acuity charts, color blindness tests, and intraocular pressure measurements are used to comprehensively analyze users' test results and provide detailed diagnostic results.

[0058] The intelligent diagnostic module uses an AI system combined with a series of preset visual testing schemes, such as visual acuity charts, color blindness tests, and intraocular pressure measurements, to comprehensively analyze the user's test data. The AI ​​system can not only evaluate the accuracy of each test result, but also establish connections between tests to identify potential visual problems. The AI ​​can analyze the correlation between visual acuity deviations in visual acuity chart tests and color blindness test results, or combine intraocular pressure measurement results to assess the risk of glaucoma. This multi-dimensional comprehensive diagnostic capability provides users with a more comprehensive visual health assessment, avoiding misdiagnosis or missed diagnosis that may result from relying on a single testing method. The system provides personalized suggestions based on the user's test data to help users discover and resolve potential visual health problems early.

[0059] The eye-tracking module is mainly used to monitor and analyze parameters such as the user's eye movement trajectory, fixation time, and focus stability for the assessment of visual acuity and visual response. For intraocular pressure measurement, the system can acquire intraocular pressure data as needed through external or integrated non-contact tonometers, traditional intraocular pressure measurement devices, or other compatible medical sensors. The intelligent diagnostic module can summarize and analyze multi-source information, including eye movement data, gesture data, and external intraocular pressure measurement data, to generate a unified diagnostic report and personalized health management recommendations. Therefore, the technical solution of this invention does not limit the implementation of intraocular pressure measurement to the eye-tracking module itself, but achieves a comprehensive assessment of the user's visual health status through the integration and expansion capabilities of the system architecture.

[0060] After completing a series of vision tests, the intelligent diagnostic module automatically generates a personalized diagnostic report. This report not only includes the specific results of each test but also provides further visual health management suggestions through data analysis. For example, for detected myopia, hyperopia, or color blindness, the system offers corresponding correction plans, recommending the wearing of appropriate glasses or corresponding vision training. If high intraocular pressure is detected, the system prompts the user to consult an ophthalmologist as soon as possible for further examination and treatment. In addition, the intelligent diagnostic module can customize recommendations for suitable eye care measures based on the subject's age, occupation, and other factors, such as the frequency of eye exercises or regular vision checks. This personalized diagnosis and advice not only improves the accuracy of the tests but also helps users maintain good visual health in daily life.

[0061] The user interface module allows users to interact with the device via touchscreen, voice, or gesture commands to complete vision testing tasks.

[0062] The user interface module provides users with multiple interaction methods, such as touchscreen, voice commands, and motion control, to improve the convenience and applicability of operation. The touchscreen function allows users to select vision test content, adjust test settings, or view test results through intuitive clicks and swipes. The voice command function uses voice recognition technology to allow users to operate without a touchscreen by using simple voice commands, such as "Start Test," "Skip Current Test," or "View Report." Motion commands use a camera to capture user gestures for interaction; users can respond to characters or complete selections by waving or gesturing. The combination of these interaction methods not only allows users of different ages and skill levels to easily use the device but also improves the smoothness of the testing process while maintaining ease of operation. The system adjusts the test content in a timely manner based on user selections or feedback to ensure the personalization and efficiency of the testing process. This diversified interactive design makes vision testing tasks more intuitive and easy to use, greatly enhancing the user experience.

[0063] Self-service vision testing devices also include either vision testing equipment or projection equipment, depending on the situation.

[0064] This paper presents an AI-powered self-service vision testing method suitable for children. It utilizes multimodal sensing technology and fractional fusion scoring formula to achieve accurate assessment of children's vision without the assistance of professional personnel.

[0065] The steps are as follows:

[0066] Child-friendly interface activation: When the system recognizes a user as a child (e.g., through height or facial recognition age estimation), a cartoon-style interface is automatically activated, using voice animations to guide the child through the detection process, improving cooperation.

[0067] Motion capture module (M) optimization: High-sensitivity sensors are used to monitor the child's head movements and sitting posture during the detection process. Considering that children are naturally active and have difficulty remaining still for long periods, the system increases the tolerance for movement, and minor movements are not penalized.

[0068] Eye-tracking module (E) data acquisition: The system presents children with visual targets featuring patterns (such as animal shapes instead of the letter "E") and records their gaze trajectory using an infrared camera. Children can complete tasks simply by looking at the target, avoiding complex instructions.

[0069] The reaction and feedback module (F) is set up as follows: the detection content is integrated with gamified interaction (such as "find where the kitten went"). The system records the child's eye focus time and reaction time to form a focus response score FFF.

[0070] The adaptive testing module (A) simplifies control: the initial graphic is large and clear, and the system gradually reduces the size of the graphic or adds distracting patterns based on the child's eye-tracking accuracy. If the child can still fixate correctly, the system records a higher AAA score.

[0071] Intelligent Diagnostic Module (D) Assessment: The system compares and analyzes a child's performance against age-appropriate visual development standards. If the performance is below the average level for the same age, the system indicates a risk of visual developmental abnormalities.

[0072] User interaction module (U) humanized settings: Children interact by touching graphics, clicking colors or responding with voice. The system recognizes the fluency and comprehension of their operations and forms an interaction score U.

[0073] Finally, all module data is input into the following fusion scoring formula:

[0074]

[0075] The parameters are set as follows in children's mode:

[0076] α=0.3, β=0.25, γ=0.45, θ=0.4;

[0077] data:

[0078] E=82, F=75, D=60, M=20, U=50, A=45;

[0079] Substituting into the calculation, we get:

[0080] V = ≈64.9;

[0081] Based on a score of V=64.9 and combined with the child's age and developmental standards, the system determined that the child has moderate vision problems, recommended going to the hospital for further examination, and generated a parent guidance and advice report.

[0082] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A self-service vision tester that uses AI to read human movements, characterized in that: It includes a motion capture module, an eye tracking module, an adaptive testing module, a feedback and suggestion module, an intelligent diagnostic module, and a user interface module; The motion capture module uses cameras or sensors to capture and analyze human movements in real time. The eye-tracking module detects the user's visual response by analyzing the movement trajectory of the eyeball in real time. The eye-tracking module uses a high-precision camera or infrared sensor to monitor the movement trajectory of the subject's eyeball in real time. By analyzing the subtle movements of the eyeball, it detects whether the user makes a corresponding focusing and tracking response to the letters, numbers or graphic targets presented on the screen. The eye-tracking module can not only monitor the movement trajectory of the eye in real time, but also use AI analysis algorithms to calculate the eye's fixation time, focusing stability and eye movement speed for specific characters; The adaptive testing module automatically adjusts the difficulty of the test content based on the user's eye movement data; The feedback and suggestion module automatically determines the user's vision level based on the analysis results of the user's reaction time and eye focusing accuracy data, and provides corresponding feedback. The intelligent diagnostic module of the user AI system provides diagnostic results by comprehensively analyzing the user's test results based on a series of preset visual test schemes. The user interface module allows users to interact with the device via touchscreen, voice, or gesture commands to complete vision testing tasks. Furthermore, in order to comprehensively and quantitatively assess the user's visual acuity, the following fusion scoring formula is adopted: in: V represents the final visual acuity assessment score; E represents the eye-tracking performance score, which includes indicators such as fixation time and tracking accuracy. F represents the user focus and responsiveness rating; D is the score output by the intelligent diagnostic module, which is based on the comprehensive analysis of the visual test results by AI; M represents the motion interference factor obtained by the motion capture module; U represents the user interaction efficiency score; A represents the adaptive test adjustment range, reflecting the user's ability to cope with different changes in visual difficulty; α, β, γ, and θ are weights and adjustment coefficients set internally by the system or optimized through machine learning. Through the above fusion formula, the system can perform quantitative analysis and dynamic judgment of the user's vision status based on multi-dimensional input.

2. The AI-powered self-service vision testing device for reading human movements according to claim 1, characterized in that, The motion capture module has a red light below each character on the vision chart, and the subject responds by waving their hand according to the direction of the character. The camera captures gesture signals, calculates whether they are correct, records the results as needed, and provides a prompt for the next detection character.

3. The AI-powered self-service vision testing device for reading human movements according to claim 2, characterized in that, The eye-tracking module analyzes the gesture data captured by the camera using image recognition technology and determines whether it conforms to the preset response method. It provides real-time feedback based on the accuracy of the gesture recognition. If the subject responds correctly, the system displays the next character for testing. If the response is incorrect, the system will prompt you to try again and record the result. Each response result will be recorded, and the system will adjust the prompting method for the next detection character based on the user's performance.

4. The AI-powered self-service vision testing device for reading human movements according to claim 1, characterized in that, ； The accuracy and stability of eye tracking enable the system to quickly assess a user's visual abilities. Furthermore, eye tracking data can provide crucial information for personalized vision assessments.

5. The AI-powered self-service vision testing device for reading human movements according to claim 1, characterized in that, The eye-tracking module adjusts the subsequent visual testing plan based on real-time eye-tracking data.

6. The AI-powered self-service vision testing device for reading human movements according to claim 1, characterized in that, The intelligent diagnostic module uses an AI system, combined with a preset visual testing scheme, to comprehensively analyze the user's test data. The AI ​​system can evaluate the accuracy of each test result, establish connections between tests, and identify potential visual problems.

7. A self-service vision testing device for reading human movements using AI, as described in claim 6, is characterized in that... After completing a series of vision tests, the intelligent diagnostic module automatically generates a personalized diagnostic report. The report not only includes the specific results of each test, but also provides users with further vision health management suggestions through data analysis.

8. The AI-powered self-service vision testing device for reading human movements according to claim 1, characterized in that, The feedback and suggestion module uses the user's reaction time and eye focusing accuracy data to analyze and automatically determine the user's vision level in real time, and provides personalized feedback and suggestions based on the analysis results. Based on this feedback, the system will alert users to specific problems and provide them with targeted solutions.

9. A self-service vision testing device for reading human movements using AI, as described in claim 1, characterized in that, The user interface module provides users with multiple interaction methods. The touch screen function allows users to select vision test content, adjust test settings, or view test results through intuitive clicks and swipes. The voice command function uses voice recognition technology to allow users to operate the device without a touchscreen by using simple voice commands. Users can respond to characters or make selections by waving or gesturing.

10. A self-service vision testing device for reading human movements using AI, as described in claim 1, characterized in that, The self-service vision tester also includes either a vision test device or a projection device, depending on the situation.

Images