Vision examination system and method based on human body posture recognition and somatosensory air control technology

Abstract

The invention relates to the technical field of vision examination, in particular to a vision examination system and method based on human body posture recognition and a somatosensory air control technology. The human body position is visually detected, the human body trunk should be in a reasonable examination area, a user is reminded to lift the shoulders with hands through voice, and graphic guidance is carried out through pictures; the distance of the user is checked through the laser radar, and the user is guided through voice and picture representation, so that the position of the user meets the requirement; checking whether the user wears glasses or not; checking the eye state; generating a vision examination icon on the display screen; when vision examination is carried out on a patient, up-down and left-right directions are randomly generated, and the system receives distance feedback of a user; after the vision examination is finished, the examination video is stored for later-stage backtracking, and the examination result is printed according to the specified requirement, so that the vision examination does not need to be manually guided, the investment of hospital nurse resources is reduced, and the labor cost of a hospital is greatly reduced.

Description

Technical Field

[0001] This invention relates to the field of vision testing technology, and in particular to a vision testing system and method based on human posture recognition and body-sensing remote control technology. Background Technology

[0002] In the current medical and health field, vision testing is a basic means of diagnosing and preventing eye diseases. Its accuracy and efficiency directly affect the patient's treatment experience and the rational allocation of medical resources. Existing vision testing methods rely on on-site guidance and operation by nurses or professionals, and use standard vision charts (such as the Snellen vision chart) to conduct line-by-line or letter-by-letter recognition tests.

[0003] However, current vision tests rely on manual guidance and require nursing services, which exacerbates the pressure on the allocation of nursing resources and results in high labor costs for hospitals. Summary of the Invention

[0004] The purpose of this invention is to provide a vision examination system and method based on human posture recognition and body-sensing remote control technology, aiming to solve the technical problems of existing vision examinations relying on manual guidance, requiring nurse services, exacerbating the pressure on nurse resource allocation, and high labor costs in hospitals.

[0005] To achieve the above objectives, the present invention employs a vision examination method based on human posture recognition and body-sensing remote control technology, comprising the following steps:

[0006] The system guides users to scan codes and swipe cards to check in, obtains the user's unique identifier, connects to the hospital's registration system to read the user's information, and uses text-to-speech technology to generate voice prompts.

[0007] The system uses visual detection to determine the position of the human body. The torso should be within the appropriate inspection area. The system provides voice prompts to remind users to raise their hands above their shoulders and uses visual guidance.

[0008] The distance to the user is checked by lidar, and the user is guided by voice and visual icons to ensure that the user's position meets the requirements.

[0009] Check if the user is wearing glasses. If so, remind the user to wear glasses via voice and visual prompts, and confirm whether the user chooses to check their uncorrected or corrected visual acuity.

[0010] When checking the eyes, check if the right eye is obstructed while checking the left eye's vision, and vice versa.

[0011] Generate vision test icons on the display screen;

[0012] When conducting vision tests on patients, the system defaults to a visual acuity of 1.0 and randomly generates directions (up, down, left, and right). The system also accepts user feedback remotely.

[0013] During the vision test, provide friendly voice prompts to the user, and give a voice farewell when the user finishes the test or leaves midway.

[0014] After the vision test is completed, the test video is stored for later review, and the test results are printed according to the specified requirements.

[0015] In the process of visually detecting the human body's position, ensuring the torso is within a reasonable inspection area, providing a voice prompt to the user to raise their hand (left or right hand) above shoulder level, and using visual guidance:

[0016] If there are multiple people in the designated area, an audio prompt will be made for unrelated individuals to leave the designated area, and the person with the largest torso area in the designated area will be selected as the person to be inspected.

[0017] Among these steps, the system uses visual detection to determine the human body's position, ensuring the torso is within a reasonable inspection area. It also provides voice prompts to guide the user to raise their hands above shoulder level, and uses visual aids for visual guidance.

[0018] If the user's position is too far to the left or right, the system will prompt the user to adjust it via voice. If the position is too high or too low, the system will automatically adjust the screen position. If the screen size is insufficient to adjust the position, the system will adjust the position by adjusting the screen's lifting mechanism.

[0019] In the step of visually detecting the human body's position, ensuring the torso is within a reasonable inspection area, providing a voice prompt to the user to raise their hands above shoulder level, and using visual guidance:

[0020] If a chair is provided for users to check their posture, the chair should be fixed in place, and the user's position and posture should be checked.

[0021] In the process of conducting vision tests on patients, starting with a visual acuity of 1.0 by default, the system randomly generates directions (up, down, left, and right) and accepts user feedback remotely.

[0022] Air feedback includes buttons, swipes, pointing, and voice. It records the number of correct and incorrect responses and generates a random direction that is not the same as the previous pointing.

[0023] In the process of conducting vision tests on patients, starting with a visual acuity of 1.0 by default, the system randomly generates directions (up, down, left, and right) and accepts user feedback remotely.

[0024] If the required number of correct answers is reached, the visual acuity level should be increased by one level and the test should continue. If the required number of incorrect answers is reached, the visual acuity level should be decreased by one level and the test should continue until the highest or lowest level is reached.

[0025] Among the steps involved in the vision test, including providing friendly voice prompts to users during the test and giving them a voice farewell upon completion or if they leave midway through the test:

[0026] Friendly voice prompts include a welcome message upon entering the screen, important notes, and a farewell message upon completion of the check or leaving midway.

[0027] This invention also provides a vision inspection system based on human posture recognition and body-sensing air control technology, including a display module, a camera, a lidar, a data acquisition module, a printing module, a microphone, a speaker module, an intelligent lifting module, an AI host, and a vision inspection algorithm; wherein:

[0028] The display module is used to generate vision test icons, display a video image of the person being tested, display the buttons required for the test and the number of times and status related to the current level, and display user information;

[0029] The camera is used to capture the state of a person;

[0030] The lidar is used to scan objects in the foreground of the lens to detect the distance to a person;

[0031] The acquisition module is used to obtain user information;

[0032] The printing module is used to print the user's vision test results;

[0033] The microphone is used for voice acquisition;

[0034] The audio module is used to provide voice broadcasts to users;

[0035] The intelligent lifting module is used to control the lifting of the display module using a height adjustment algorithm;

[0036] The AI ​​host is used to provide vision checks for users;

[0037] The posture recognition algorithm is used to detect human posture.

[0038] The vision testing algorithm includes a human distance algorithm, a voice algorithm, an eye occlusion algorithm, a limb recognition algorithm, a gesture recognition algorithm, and a glasses-wearing detection algorithm; wherein:

[0039] The human distance algorithm is used to determine whether the user's distance is within a reasonable inspection area;

[0040] The speech algorithm is used to analyze the collected user speech;

[0041] The eye occlusion algorithm is used to determine whether a user's undetected eye is properly occluded.

[0042] The limb recognition algorithm is used to identify the movement trajectory of a user's limbs;

[0043] The gesture recognition algorithm is used to record hand movement trajectories and identify the sliding and pointing directions of the user's hand.

[0044] The glasses detection algorithm is used to check whether the user is wearing glasses. If the user is wearing glasses, the algorithm will remind the user to wear glasses via voice and images, and confirm whether the user chooses to check their uncorrected or corrected visual acuity.

[0045] This invention discloses a vision examination system and method based on human posture recognition and gesture-based remote control technology. First, it guides the user to scan a code and swipe a card to register, obtaining the user's unique identifier. Then, it connects to the hospital's registration system to read the user's information and performs text-to-speech (TextTo...) The system utilizes speech technology to generate voice prompts. It visually detects the user's position, ensuring the torso is within the appropriate examination area. The system prompts the user to raise their hands above shoulder level and provides visual guidance. Next, it uses LiDAR to check the user's distance and guides them with both voice and visual cues to ensure proper positioning. It then checks if the user is wearing glasses; if so, it reminds them to wear them and confirms whether they want to have their uncorrected or corrected visual acuity checked. The system also checks the eyes' condition, detecting right-eye obstruction when checking left-eye vision and vice versa. A vision test icon is generated on the display screen. The system starts with a default visual acuity of 1.0 and randomly generates up, down, left, and right directions. The system accepts user feedback remotely. Friendly voice prompts are provided during the vision test, and a voice farewell is given if the user leaves at the end of the test. Finally, the system stores the test video for later review and prints the results according to specified requirements. This method eliminates the need for manual guidance during vision tests, reducing the need for hospital nurses and significantly lowering hospital labor costs. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1This is a flowchart of the vision examination method based on human posture recognition and body-sensing remote control technology of the present invention.

[0048] Figure 2 This is a schematic diagram of the vision examination system based on human posture recognition and body-sensing remote control technology of the present invention.

[0049] Figure 3 This is a schematic diagram illustrating the principle of the vision testing algorithm of this invention.

[0050] Figure 4 This is a schematic diagram illustrating the principle of the height adjustment algorithm in the intelligent lifting module of the present invention.

[0051] Figure 5 This is a schematic diagram illustrating the principle of the eye occlusion algorithm of this invention.

[0052] Figure 6 This is a schematic diagram of the virtual button for hands-free operation according to the present invention.

[0053] Figure 7 This is a schematic diagram illustrating the recognition of hand gestures pointing in the up, down, left, and right directions in the gesture recognition algorithm of this invention.

[0054] Figure 8 It is in this invention Figure 7 A diagram illustrating hand pointing to the left for recognition.

[0055] Figure 9 This is a schematic diagram of a finger pointing directly downwards in the gesture recognition algorithm of this invention.

[0056] 201-Display module, 202-Camera, 203-LiDAR, 204-Acquisition module, 205-Printing module, 206-Microphone, 207-Speaker module, 208-Intelligent lifting module, 209-AI host, 210-Vision test algorithm, 2101-Human distance algorithm, 2102-Voice algorithm, 2103-Eye occlusion algorithm, 2104-Body recognition algorithm, 2105-Gesture recognition algorithm, 2106-Glasses detection algorithm. Detailed Implementation

[0057] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0058] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0059] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0060] Please see Figures 1-9 This invention provides a vision examination method based on human posture recognition and body-sensing remote control technology, comprising the following steps:

[0061] S101: Guides users to scan codes and swipe cards to check in, obtains the user's unique identifier, connects to the hospital's registration system to read the user's information, and generates voice prompts through text-to-speech technology;

[0062] S102: By visually detecting the position of the human body, the torso should be in a reasonable inspection area. The voice prompt reminds the user to raise their hands above the shoulders, and the screen provides visual guidance.

[0063] S103: Uses lidar to check the user's distance and guides the user with voice and visual cues to ensure the user's position meets requirements;

[0064] S104: Check if the user is wearing glasses. If so, remind the user to wear glasses via voice and icon, and confirm whether the user chooses to check uncorrected or corrected visual acuity.

[0065] S105: Check the condition of the eyes. When checking the vision of the left eye, check whether the right eye is obstructed. When checking the vision of the right eye, check whether the left eye is obstructed.

[0066] S106: Generate vision test icons on the display screen;

[0067] S107: When conducting vision tests on patients, the system defaults to starting with visual acuity of 1.0 and randomly generates directions (up, down, left, and right). The system accepts user feedback remotely.

[0068] S108: Provide friendly voice prompts to users during the vision test, and give a voice farewell when users finish the test or leave midway.

[0069] S109: After the vision test is completed, store the test video for later review, and print the test results according to the specified requirements.

[0070] In this implementation, the user is first guided to scan a code and swipe a card to register, obtaining a unique user identifier. This information is then retrieved from the hospital's registration system. Text-to-speech technology is used to generate voice prompts. The system uses a camera to detect the user's position, ensuring the torso is within a reasonable examination area. The system then prompts the user to raise their hand (left or right) above shoulder level, with visual guidance provided on screen. If multiple people are in the designated area, unrelated individuals are prompted to leave, and the person with the largest torso area within the designated area is selected for examination. If the user's position is too far to the left or right, the system prompts the user to adjust. If the position is too high or too low, the system automatically adjusts the screen position. If the screen size is insufficient for adjustment, the system adjusts the screen's height by adjusting its lifting mechanism. Positioning; if a chair is provided for user posture testing, its position should be fixed. User position and posture should be detected, followed by distance checks using LiDAR. Voice and visual cues should be used to guide the user to the correct position. Next, check if the user is wearing glasses. If so, remind the user to wear them via voice and visual cues, and confirm whether the user chooses to test uncorrected or corrected visual acuity. Check eye condition; when testing left eye vision, check for right eye obstruction, and vice versa. A vision test icon should be generated on the display screen. Depending on the configuration, the visual acuity test target can be E-Vision. The visual acuity chart uses the symbol E, or the symbol C, or other customized text, numbers, and graphics. The direction of the visual acuity test can be the standard up, down, left, and right, or a combination of up, down, left, right, and oblique directions, or other customized directions. A standard visual acuity test typically requires 5 meters or other standard testing distances. When space is limited in a testing environment, the visual acuity target can be reduced in size to achieve the same visual angle at the standard testing distance, thus obtaining equivalent test results. When conducting a visual acuity test on a patient, the system defaults to a visual acuity of 1.0 and randomly generates up, down, left, and right directions. The system accepts user feedback via gestures, including button gestures. The system uses swiping, pointing, and voice commands to record the number of correct and incorrect answers, and generates random directions that are not the same as the previous directions, according to standards. If the number of correct answers reaches the requirement (e.g., three), the visual acuity level is increased by one level to continue testing. If the number of incorrect answers reaches the requirement (e.g., three), the visual acuity level is decreased by one level to continue testing, until the highest or lowest level is reached. During the visual acuity test, friendly voice prompts are given to the user (including a voice welcome message and precautions upon entering the screen, and a voice farewell message upon completion of the test or leaving midway). Finally, after the visual acuity test is completed, the test video is stored for later review, and the test results are printed according to specified requirements.

[0071] In addition, during remote manipulation of the patient's hands, see Figure 6The page layout includes five commonly used buttons: up, down, left, and right (if unclear). Button positions are determined by two options: Option 1 allows for fixed positions, while Option 2 uses intelligent positioning based on the user. The intelligent positioning method involves the system recognizing the user's hand and shoulder positions after they stand in the designated location (due to variations in height and left / right positioning). Taking right-handed users as an example, the system uses a slightly higher position (around the nose) as the center point (Y-coordinate) and the natural X-axis position of the raised hand as the midline point (X-coordinate). This natural layout of the five buttons facilitates user operation. Each button has its own edge on the video screen. After randomly generating a vision test image, moving the hand (using the index fingertip as a reference point) to different buttons triggers a "click" action, completing the "up, down, left, and right" interaction. If the user cannot see clearly, they click the "cannot see" button. This method eliminates the need for manual guidance during vision tests, reducing the need for hospital nurses and significantly lowering hospital labor costs.

[0072] This invention also provides a vision testing system based on human posture recognition and body-sensing air-control technology, including a display module 201, a camera 202, a lidar 203, a data acquisition module 204, a printing module 205, a microphone 206, an audio module 207, an intelligent lifting module 208, an AI host 209, and a vision testing algorithm 210; wherein:

[0073] The display module 201 is used to generate a vision test icon, display a video image of the person being tested, display the buttons required for the test and the number of times and status related to the current level, and display user information;

[0074] The camera 202 is used to capture the state of a person;

[0075] The lidar 203 is used to scan objects in the foreground of the lens to detect the distance to a person;

[0076] The acquisition module 204 is used to acquire user information;

[0077] The printing module 205 is used to print the user's vision test results;

[0078] The microphone 206 is used for voice acquisition;

[0079] The audio module 207 is used to provide voice broadcasts to users;

[0080] The intelligent lifting module 208 is used to control the lifting of the display module 201 using a height adjustment algorithm;

[0081] The AI ​​host 209 is used to run software and algorithms for checking the user's vision;

[0082] The posture recognition algorithm is used to detect human posture.

[0083] In this embodiment, the display module 201 generates vision test icons (such as E, C, or other optotypes), displays a video image of the person being examined, displays the buttons required for the examination and the current level, related number of times, and status, and displays user information (patient number, name, etc.); the camera 202 captures the person's state, and AI computing power analyzes the person's posture and operation; the lidar 203 scans objects in front of the lens using an M*N laser beam to detect whether the person's distance meets the examination requirements (such as a standard examination distance of 5 meters), and should not be too close or too far; the acquisition module 204 acquires user information, reads information that can uniquely identify the user, commonly including QR codes, barcodes, or other codes on registration slips, physical examination slips, or can directly read cards (such as ID cards, work cards, etc.), and after reading the unique identifier, it interfaces with the hospital's registration system (or other similar systems) to query the user's detailed information, such as name, for display and voice broadcast; the printing module 205 is used to print the user's vision test results; the microphone 206 is used for voice acquisition, and during voice acquisition, the microphone 206 is used to collect the patient's voice. Since the inspection distance is usually considerable and there is noise from other people and the environment, a high-sensitivity noise-canceling microphone 206 is typically selected based on the situation. The audio module 207 provides voice broadcasts to the user. The intelligent lifting module 208 uses a height adjustment algorithm to control the lifting of the display module 201. Since people have different heights, and there are standing and sitting tests, the intelligent algorithm can dynamically adjust the height of the patient's head and the eye chart to match. Based on a facial recognition algorithm, the eye position is identified, i.e., its coordinates in the camera 202's view. The icon display position has a default reasonable range, i.e., a rectangular range from (x1, y1) to (x2, y2). Figure 4 If the eyes are positioned too high or too low, or too far to the left or right, the system can automatically adjust the image display position via software. If the position exceeds the screen area, a stepper motor on the back of the display can adjust the display position up and down, ensuring that people of different heights, including adults and children, can complete the vision test in a comfortable posture. The AI ​​host 209 runs the software and algorithms for the user's vision test; the posture recognition algorithm identifies and detects human posture.

[0084] Furthermore, the vision testing algorithm 210 includes a human distance algorithm 2101, a voice algorithm 2102, an eye occlusion algorithm 2103, a limb recognition algorithm 2104, a gesture recognition algorithm 2105, and a glasses-wearing detection algorithm 2106; wherein:

[0085] The human distance algorithm 2101 is used to determine whether the user's distance is within a reasonable inspection area;

[0086] The voice algorithm 2102 is used to analyze the collected user voice.

[0087] The eye occlusion algorithm 2103 is used to determine whether the user's undetected eye is properly occluded;

[0088] The limb recognition algorithm 2104 is used to identify the movement trajectory of a user's limbs;

[0089] The gesture recognition algorithm 2105 is used to record hand movement trajectories and identify the sliding direction and pointing direction of the user's hand;

[0090] The glasses detection algorithm 2106 is used to check whether the user is wearing glasses. If the user is wearing glasses, the algorithm will remind the user to wear glasses via voice and images, and confirm whether the user chooses to check uncorrected or corrected visual acuity.

[0091] In this embodiment, the human body distance algorithm 2101 determines whether the user's distance is within a reasonable inspection area. During vision testing, because the patient's eyes and the icons need to maintain a certain angle, according to standards, the patient must maintain a certain distance from the vision chart (i.e., the display screen), such as 5 meters (or another distance). The voice algorithm 2102 analyzes the collected user voice. The eye occlusion algorithm 2103 determines whether the user's undetected eyes are properly occluded. Figure 5 In this algorithm, each eye point has a confidence level. When a small partition obstructs the view, the confidence level predicted by the point-position algorithm drops significantly, while the confidence level is very high for unobstructed views. Normal obstruction is determined based on the confidence level of the point position. The limb recognition algorithm 2104 identifies the user's limb movement trajectory. The gesture recognition algorithm 2105 records the hand movement trajectory (including the direction of hand swiping and the direction of hand pointing up, down, left, and right), identifying the user's hand swiping direction and pointing direction. In the hand swiping direction recognition, the middle fingertip represents the hand, and the hand movement trajectory is recorded based on... In this scenario, the hand initially remains still (waiting for the check icon). After the icon appears, the hand slides, with different characteristics for up, down, left, and right. Taking a rightward swipe as an example, based on the historical trajectory, the leftmost and rightmost extreme points are found. These two points are usually at a relatively horizontal angle (e.g., ±10°), and the horizontal movement distance is several times (e.g., more than twice) of the vertical distance. If the angle is too large (e.g., 45°), it is considered an "upper right" direction. It's impossible to distinguish between "right" and "up," so the action is deemed unacceptable. Secondly, see... Figure 7In hand pointing recognition (up, down, left, right), different patients have different hand pointing habits. Taking the right hand as an example, most patients habitually use their index or middle finger (or both) to point, while others use their thumb or other fingers. The algorithm's approach is to use the five fingertips as the primary coordinates, ensuring that one fingertip is at an extreme value in the up, down, left, or right directions. For example, if the index finger (or middle finger, or other) is further to the left than the other 20 points, then the index finger is selected as the reference. Several points on the index finger are then checked; if they are at a roughly horizontal position (e.g., ±10°), then the pointing is determined to be to the left. The glasses detection algorithm 2106 checks whether the user is wearing glasses. If so, the algorithm prompts the user with voice and visual cues to wear glasses and confirms whether the user chooses to check their uncorrected or corrected visual acuity.

[0092] In this implementation scheme, the camera 202 and lidar 203 can be replaced by binocular cameras, structured light cameras, depth cameras, etc., to complete the shooting of people and distance measurement.

[0093] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0094] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A vision examination method based on human posture recognition and body-sensing remote control technology, characterized in that, The steps include: The system guides users to scan codes and swipe cards to check in, obtains the user's unique identifier, connects to the hospital's registration system to read the user's information, and uses text-to-speech technology to generate voice prompts. The system uses visual detection to determine the position of the human body. The torso should be within the appropriate inspection area. The system provides voice prompts to remind users to raise their hands above their shoulders and uses visual guidance. The distance to the user is checked by lidar, and the user is guided by voice and visual icons to ensure that the user's position meets the requirements. Check if the user is wearing glasses. If so, remind the user to wear glasses via voice and visual prompts, and confirm whether the user chooses to check their uncorrected or corrected visual acuity. When checking the eyes, check if the right eye is obstructed while checking the left eye's vision, and vice versa. Generate vision test icons on the display screen; When conducting vision tests on patients, the system defaults to a visual acuity of 1.0 and randomly generates directions (up, down, left, and right). The system also accepts user feedback remotely. During the vision test, provide friendly voice prompts to the user, and give a voice farewell when the user finishes the test or leaves midway. After the vision test is completed, the test video is stored for later review, and the test results are printed according to the specified requirements.

2. The vision examination method based on human posture recognition and body-sensing remote control technology as described in claim 1, characterized in that, In the process of visually detecting the human body's position, ensuring the torso is within a reasonable inspection area, providing a voice prompt to the user to raise their hands above shoulder level, and using visual guidance: If there are multiple people in the designated area, an audio prompt will be made for unrelated individuals to leave the designated area, and the person with the largest torso area in the designated area will be selected as the person to be inspected.

3. The vision examination method based on human posture recognition and body-sensing remote control technology as described in claim 1, characterized in that, In the process of visually detecting the human body's position, ensuring the torso is within a reasonable inspection area, providing a voice prompt to the user to raise their hands above shoulder level, and using visual guidance: If the user's position is too far to the left or right, the system will prompt the user to adjust via voice. If the position is too high or too low, the system will automatically adjust the screen position. If the screen size is insufficient to adjust the position, the system will automatically adjust the position by adjusting the screen's lifting mechanism.

4. The vision examination method based on human posture recognition and body-sensing remote control technology as described in claim 1, characterized in that, In the process of visually detecting the human body's position, ensuring the torso is within a reasonable inspection area, providing a voice prompt to the user to raise their hands above shoulder level, and using visual guidance: If a chair is provided for users to check their posture, the chair should be fixed in place, and the user's position and posture should be checked.

5. The vision examination method based on human posture recognition and body-sensing remote control technology as described in claim 1, characterized in that, In the steps of generating vision test icons on the display screen: Depending on the configuration, the optotypes for vision testing can be the E on the E chart, the C on the circular chart, or other customized text, numbers, and graphics. The direction of vision testing can be the conventional up, down, left, and right, or up, down, left, right, and oblique, or other customized directions. The standard vision test generally requires 5 meters or other standard testing distances. When the actual vision testing space is limited, the optotypes can be reduced in size according to the configuration to achieve the same viewing angle at the standard testing distance, thereby obtaining equivalent test results.

6. The vision examination method based on human posture recognition and body-sensing remote control technology as described in claim 1, characterized in that, When conducting vision tests on patients, the system defaults to a visual acuity of 1.0 and randomly generates directions (up, down, left, right). The system also accepts user feedback remotely during the following steps: Air feedback includes one or a combination of buttons, swipes, pointing, and voice. It records the number of correct and incorrect responses and generates a random direction that is not the same as the previous pointing.

7. The vision examination method based on human posture recognition and body-sensing remote control technology as described in claim 6, characterized in that, When conducting vision tests on patients, the system defaults to a visual acuity of 1.0 and randomly generates directions (up, down, left, right). The system also accepts user feedback remotely during the following steps: If the required number of correct answers is reached, the visual acuity level should be increased by one level and the test should continue. If the required number of incorrect answers is reached, the visual acuity level should be decreased by one level and the test should continue until the highest or lowest level is reached. If there is a historical examination record for the user, the examination should start from the corresponding level to improve efficiency.

8. The vision examination method based on human posture recognition and body-sensing remote control technology as described in claim 1, characterized in that, The steps for providing friendly voice prompts to users during the vision test, and giving a voice farewell when users finish the test or leave midway: Friendly voice prompts include a welcome message upon entering the screen, important notes, and a farewell message upon completion of the check or leaving midway.

9. A vision examination system based on human posture recognition and body-sensing remote control technology, applied to the vision examination method based on human posture recognition and body-sensing remote control technology as described in claim 1, characterized in that, This includes a display module, camera, LiDAR, data acquisition module, printing module, microphone, speaker module, intelligent lifting module, AI host, and vision testing algorithm; among which: The display module is used to generate vision test icons, display a video image of the person being tested, display the buttons required for the test and the number of times and status related to the current level, and display user information; The camera is used to capture the state of a person; The lidar is used to scan objects in the foreground of the lens to detect the distance to a person; The acquisition module is used to obtain user information; The printing module is used to print the user's vision test results; The microphone is used for voice acquisition; The audio module is used to provide voice broadcasts to users; The intelligent lifting module is used to control the lifting of the display module using a height adjustment algorithm; The AI ​​host is used to provide vision checks for users; The posture recognition algorithm is used to detect human posture.

10. The vision inspection system based on human posture recognition and body-sensing remote control technology as described in claim 9, characterized in that, The vision testing algorithm includes a human distance algorithm, a voice algorithm, an eye occlusion algorithm, a limb recognition algorithm, a gesture recognition algorithm, and a glasses-wearing detection algorithm; wherein: The human distance algorithm is used to determine whether the user's distance is within a reasonable inspection area; The speech algorithm is used to analyze the collected user speech; The eye occlusion algorithm is used to determine whether a user's undetected eye is properly occluded. The limb recognition algorithm is used to identify the position and movement trajectory of a user's limbs; The gesture recognition algorithm is used to record hand movement trajectories and identify the sliding and pointing directions of the user's hand. The glasses detection algorithm is used to check whether the user is wearing glasses. If the user is wearing glasses, the algorithm will remind the user to wear glasses via voice and images, and confirm whether the user chooses to check their uncorrected or corrected visual acuity.

Images