Novel reading disorder assessment and intelligent correction method based on EOG

Abstract

The invention relates to a novel reading disorder assessment and intelligent correction method based on EOG. The novel reading disorder assessment and intelligent correction method comprises the following steps: S1, respectively collecting eye movement signal data of a reading disorder child and a normal reading child in a reading process by adopting eye movement collection equipment; s2, filtering the original signal to generate an eye movement diagram, and analyzing transverse and longitudinal movement tracks and directions of eyes; s3, comparing the eye movement images of the reading disorder children and the normal children, and extracting key eye movement characteristic parameters of the reading disorder children and the normal children; s4, analyzing eye movement abnormal characteristics of frequent review of the individual; and S5, assessing the reading disorder through the reading behavior, and assessing the understanding degree of the text segment by using the text-related picture. The intelligent correction module is started to improve the reading effect. According to the method, the motion state of eyeballs, individual attention, visual processing speed, cognitive load and the like are reflected through the change of the electro-oculogram potential, a non-intrusive, real-time and quantitative evaluation and correction scheme is provided, and the evaluation and correction effect of the reading disorder can be remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of cognitive assessment, and specifically relates to a new method for reading disorder assessment and intelligent correction based on EOG. Background Art

[0002] Reading disorder is a common learning disorder among school-age children, accounting for about 80% of all learning disorders. Among them, developmental reading disorder is particularly prominent, referring to children with normal intelligence who, during the development process, although there is no obvious neurological or organic damage, their reading ability is significantly lower than their intelligence level or chronological age. The main characteristics of this type of disorder are the impairment of the accuracy and speed of word recognition, which in turn affects reading comprehension, spelling ability, and hinders the accumulation of vocabulary and background knowledge.

[0003] In recent years, the application of eye movement tracking technology (EOG) in reading disorder assessment has gradually received attention. This technology records eye movements by attaching electrodes to the skin next to the eyes, and can accurately measure the eye movement patterns during reading, thus providing objective data support for assessment.

[0004] Traditional eye movement assessment methods mainly rely on questionnaires and teachers' subjective judgments. This method is easily affected by subjectivity and one-sidedness, resulting in a decline in accuracy, and cannot be monitored in real time, nor can it dynamically reflect eye movement behavior. The eye movement tracking method based on computer vision captures the user's eye movement data through a camera. Although it can provide relatively objective assessment results, its accuracy is still limited when the lighting conditions change or the user's head moves.

[0005] Currently, the correction methods mainly rely on paper text materials for training. For example, by increasing the letter spacing or word spacing, adjusting the text font size or picture color, etc. to improve reading efficiency. However, these methods are usually time-consuming and laborious, lack intelligent support, and do not fully solve the problem of how to improve the individualized correction effect and reading efficiency.

[0006] Therefore, aiming at the deficiencies of the existing methods, the present invention proposes a new method for reading disorder assessment and intelligent correction based on EOG, aiming to improve reading efficiency and correction effect through accurate eye movement tracking and personalized intelligent adjustment. Summary of the Invention

[0007] (1) Technical Problems to be Solved

[0008] Aiming at the deficiencies of the existing technology, the present invention provides a new method for reading disorder assessment and intelligent correction based on EOG to solve the problems raised in the background art.

[0009] (2) Technical Solutions

[0010] To achieve the above object, the present invention provides the following technical solutions: a novel dyslexia assessment and intelligent correction method based on EOG, comprising the following steps:

[0011] S1. Use an eye movement acquisition device to collect the eye movement signal data of children with dyslexia and children with normal reading during the reading process respectively;

[0012] S2. After filtering the original signal, generate an eye movement map through visualization processing to analyze the movement trajectory and direction of the eyes in the horizontal and vertical directions. Determine the basic direction of eye movement when an individual reads through the basic characteristics of eye movement behavior. Use a peak detection algorithm to identify peaks and valleys and intercept the effective reading signal;

[0013] S3. Compare the eye movement maps of children with dyslexia and children with normal reading, and extract the key eye movement characteristic parameters of children with dyslexia;

[0014] S4. Based on the abnormal points determined in S3, analyze the abnormal eye movement characteristics of frequent saccades of an individual, and combine factors such as curve slope, duration, and change rate to determine whether there is dyslexia;

[0015] S5. If the evaluation result shows that there is dyslexia, start the intelligent correction module, and achieve focused reading by tracking the red fonts sequentially displayed on the screen by the eyes, so as to help improve the visual focusing ability and improve the reading effect; then evaluate the user's understanding of the text by asking the user to select pictures that match the text content.

[0016] Preferably, the device required for collecting eye movement signals in S1 includes electrodes, lead wires, a digital electrooculogram acquisition module, a serial communication interface, and an output feedback device. The electrodes include an active electrode R, an active electrode L, and a reference electrode D. The input ends of the digital electrooculogram acquisition module are respectively connected to the active electrode R, the active electrode L, the reference electrode D, and the lead wires. The output end of the digital electrooculogram acquisition module is connected to the input end of the serial communication interface, and the output end of the serial communication interface is connected to the output feedback device; the output feedback device includes a tablet computer or a smart phone.

[0017] Preferably, in S1, 3 biological electrodes are worn to collect the eye movement signals of an individual during reading.

[0018] Preferably, in S2, preprocess the eye movement map, draw an envelope line, calculate the median value, and remove high-frequency noise through Butterworth low-pass filtering. The formula is:

[0019]

[0020] where w c is the cut-off frequency of filtering, and n is the order of filtering.

[0021] Preferably, in S2, a peak detection algorithm is used to identify peaks and valleys, and the specific steps are as follows:

[0022] a), Input the eye movement waveform data, ensuring that the data is in the form of a one-dimensional array, representing a time series signal;

[0023] b), Find all local maximum points (peaks) or local minimum points (valleys), including noise and insignificant extrema;

[0024] c), For each candidate extremum point, calculate its significance height (the height difference from the lowest points on both sides). When the significance height of a certain point is less than the set significance screening threshold, it is excluded, and only the points whose significance height meets the conditions are retained;

[0025] d), Check the index distance between the remaining extremum points. When the distance between two adjacent extremum points is less than the set minimum spacing, retain the point with higher significance;

[0026] e), After screening, the obtained list of peaks and valleys is the valid extremum points that meet the conditions.

[0027] Preferably, in S2, the effective reading signal is intercepted according to the peaks and valleys, and the specific steps are as follows:

[0028] a), Combine the index positions and types ("peak" or "valley") of the detected peaks and valleys into a list, and sort them in ascending order of the index position. The sorted list ensures that all peak and valley points are arranged in chronological order.

[0029] b), Check each pair of adjacent points in the sorted peak and valley point list in turn. When the types of adjacent two points are different (that is, one is a peak and the other is a valley), it is considered that a valid waveform segment is formed between these two points.

[0030] c), For each pair of adjacent peak and valley points that meet the conditions, determine the start index and end index of the waveform segment, and extract the waveform segment data.

[0031] Preferably, the significance screening threshold and the minimum spacing are set to the best values observed manually, and according to the observation results, the significance screening threshold for peak and valley detection is set to 30, and the minimum spacing between adjacent peaks and valleys is set to 10.

[0032] Preferably, in S4, by detecting whether the waveform continuously drops, calculate the slopes of all descending segments, sort them from small to large, and select the steepest about 10 - 15% segment as an anomaly, and accordingly judge the user's eye movement anomaly and evaluate reading disorders.

[0033] Preferably, in S5, the intelligent correction module is activated, and the system takes pictures to identify the text material to be read, and red characters will be displayed one by one on the screen. After each red character is displayed, it will immediately turn black, forming a dynamic window paradigm in which the red characters move left and right. In this way, the user can use their eyes to track the red characters displayed on the system screen in sequence to achieve focused reading.

[0034] Preferably, in S5, after the intelligent correction module is activated and the system finishes recognizing the text, four pictures will be attached to the interface. Only one of them matches the text description, and the other three have nothing to do with the text description. After the user reads the text, they need to select the picture that best matches the text description from the four pictures. If the user selects correctly, it can be considered that they understand the content of this text.

[0035] Preferably, in S5, the intelligent correction module further includes functions for setting font size, character spacing, line spacing, font color, and background color.

[0036] (III) Beneficial Effects

[0037] Compared with the prior art, the present invention provides a new method for evaluating reading disorders and intelligent correction based on EOG, which has the following beneficial effects:

[0038] 1. The present invention proposes a method for evaluating reading disorders by collecting EOG signals. Without using computer- and video-based eye trackers, it can directly collect electrooculogram signals and perform differential amplification processing, and can objectively and quickly reflect the eye movement state. By detecting peaks and valleys, effective reading segments are intercepted, and through this non-invasive detection technology, the subjectivity and low efficiency problems of traditional evaluation methods are effectively solved.

[0039] 2. The present invention proposes to achieve intelligent correction by having the eyes track the red characters that appear sequentially on the reading system screen. The eye-catching color can improve the visual focusing ability. When the red characters move from left to right, the eyes also move accordingly. By increasing the font size, character and line spacing, and changing the font and background colors, the reading experience can also be improved to a certain extent; then, by having the patient select the picture that matches the reading content to determine whether they understand the text content. If the selection is correct, it is considered that they understand the content of this text. For users who make incorrect selections multiple times, the system can provide more detailed text explanations or adjust the way of text description to improve the understanding degree. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings described herein are used to provide a further understanding of the present invention and form a part of this application. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0041] Figure 1It is a schematic diagram of the APP function composition of the present invention;

[0042] Figure 2 It is a schematic diagram of the working process of the system of the present invention;

[0043] Figure 3 It is a schematic diagram of the structural composition of the eye acquisition device of the present invention;

[0044] Figure 4 It is a schematic diagram of the pins of the digital electro-oculogram acquisition module of the present invention;

[0045] Figure 5 It is a distribution diagram of the EOG signal acquisition electrodes of the present invention;

[0046] Figure 6 It is the original signal electro-oculogram in the horizontal direction in the present invention.

[0047] Figure 7 It is the original signal electro-oculogram in the vertical direction in the present invention

[0048] Figure 8 It is the filtered electro-oculogram of the original signal in the horizontal direction in the present invention.

[0049] Figure 9 It is the envelope diagram of the electro-oculogram signal in the present invention.

[0050] Figure 10 It is the electro-oculogram of intercepting the effective reading signal in the present invention.

[0051] Figure 11 It is the reading comprehension test diagram in the present invention. Detailed implementation manners

[0052] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0053] The following gives specific embodiments.

[0054] Embodiment 1:

[0055] Such as Figure 1As shown, it is a system function diagram. The system displays the eye movement waveform diagram and evaluation results in real time. When a patient with dyslexia is evaluated, the intelligent correction function can be used in the system to help the patient understand the text. The patient takes a photo of the text and uploads it to the APP. The APP recognizes and converts it into an electronic text, which is displayed in the form of a moving window paradigm. By setting the text display speed, font size, character spacing, line spacing, text and background colors, the patient can understand the text and focus on reading.

[0056] Example 2:

[0057] The system working process is shown in Figure 2 , and the main steps are as follows:

[0058] Step 1: Stick electrode patches on both sides of the eyes to collect data;

[0059] Step 2: The APP receives through the serial communication interface;

[0060] Step 3: Eye movement diagram display: The APP continuously receives data, preprocesses it and adjusts the eye movement diagram baseline, removes interference through Butterworth band-pass filtering, establishes a machine learning algorithm model for judgment, and displays the real-time dynamic eye movement diagram personalized;

[0061] Step 4: Result evaluation: The system identifies and judges whether the eye movement is abnormal. If abnormal eye movement occurs, it is considered dyslexia and reading intervention and correction are required. If not, it is considered non-dyslexia.

[0062] Example 3:

[0063] Please refer to Figure 3 and Figure 4 , the present invention provides a new method for dyslexia evaluation and intelligent correction based on EOG, including electrodes, lead wires, a digital electrooculogram acquisition module, a serial communication interface, and an output feedback device. When in use, the electrodes need to be attached to fixed positions around the eyes, such as Figure 5 shown;

[0064] The electrodes include an active electrode R, an active electrode L, and a reference electrode D;

[0065] The input ends of the digital electrooculogram acquisition module are respectively connected to the active electrode R, the active electrode L, the reference electrode D, and the lead wire. The output end of the digital electrooculogram acquisition module is connected to the input end of the serial communication interface, and the output end of the serial communication interface is connected to the output feedback device;

[0066] The output feedback device includes a tablet computer or a smart phone.

[0067] The above solution: By using a portable eye movement acquisition device to detect the eye movement behavior of users during the reading process in real time, a rapid assessment of reading disorders is achieved, especially capturing key features in eye movement behavior, such as looking left, looking right, blinking, etc. An innovative intelligent correction function is also designed and developed, allowing the display mode of the text to be adjusted according to the specific needs of children to improve the reading experience and comprehension ability.

[0068] Example 4:

[0069] A new method for reading disorder assessment and intelligent correction based on EOG includes the following steps:

[0070] S1. Use an eye movement acquisition device to collect the eye movement signal data of children with reading disorders and children with normal reading during the reading process respectively;

[0071] S2. After filtering the original signal, generate an eye movement map through visualization processing to analyze the movement trajectory and direction of the eyes in the horizontal and vertical directions. Determine the basic direction of eye movement during individual reading through the basic features of eye movement behavior. Use the peak detection algorithm to identify peaks and valleys and intercept the effective reading signal;

[0072] S3. Compare the eye movement maps of children with reading disorders and children with normal reading, and extract the key eye movement feature parameters of children with reading disorders;

[0073] S4. Based on the abnormal points determined in S3, analyze the abnormal eye movement features of individual frequent regressions, and combine factors such as curve slope, duration, and change rate to determine whether there is a reading disorder;

[0074] S5. If the evaluation result shows that there is a reading disorder, start the intelligent correction module, and achieve focused reading by tracking the red fonts displayed on the screen in sequence with the eyes, thereby helping to improve the visual focusing ability and improve the reading effect.

[0075] Example 5:

[0076] As Figure 6 shown, it is the eye movement map of the original signal in the horizontal direction. The X-axis is time and the Y-axis is the potential difference. From the figure, the eye movement behaviors of looking left and looking right can be analyzed. When the eyes look left, the potential difference decreases and the curve shows a downward trend; when looking right, the potential difference increases and the curve shows an upward trend. As Figure 7 shown, it is the eye movement map of the original signal in the vertical direction. When the eyes look up, the potential difference increases and the curve shows an upward trend; when the eyes look down, the potential difference decreases and the curve shows a downward trend. Due to the inability of reading disorder patients to focus on understanding the text, when reading from left to right, there will be frequent regressions and skipping lines in the eyes. Based on this, a preliminary assessment of reading disorders can be carried out.

[0077] Example 6:

[0078] As shown Figure 8 in the figure, it is the original signal filtered eye movement diagram in the horizontal direction. After collecting the eye movement signals of the user during reading, the eye movement diagram is preprocessed and Butterworth low-pass filtered to remove high-frequency noise. The formula is:

[0079]

[0080] where w c is the cut-off frequency of the filter, and n is the order of the filter, which can obtain a smoother waveform diagram.

[0081] Example 7:

[0082] As shown Figure 9 in the figure, it is the envelope diagram of the eye movement signal. The upper envelope, lower envelope and median value are plotted in the figure. The upper envelope generates an analytic signal by performing a Hilbert transform on the input signal, calculates the modulus (i.e., amplitude) of the analytic signal, and the amplitude envelope represents the local amplitude of the signal at each time point. The lower envelope is obtained by inverting the original signal, converting the wave troughs into wave peaks, and detecting the wave peaks in the inverted signal. The median value can be calculated by finding the average value of the difference between the upper and lower envelopes, which can be used to measure the overall offset or reference level of the signal.

[0083] Example 8:

[0084] As shown Figure 10 in the figure, it is the eye movement diagram of the intercepted effective reading signal. The red descending segment in the figure represents the eye ball turning to the left, and the green ascending segment represents the eye ball turning to the right. Among them, the continuous red ascending segment indicates that the user has frequent saccade eye movement behavior, which is preliminarily evaluated as reading disorder. The specific method is to identify all local maxima (peaks) and minima (troughs), calculate the significance height of each candidate point, and remove the points with significance height lower than the set threshold to ensure that only the points with sufficient significance are retained. Check the distance between adjacent extreme points. If the distance between two points is less than the set minimum distance, retain the more significant one to further screen the extreme points. Finally, sort the remaining peaks and troughs according to the order in which they appear in the data to form an ordered list. Find two adjacent points with different types (i.e., a peak and a trough) from it. The two points form a valid waveform segment. Finally, determine the start and end indices of the waveform segment based on these two points and extract the corresponding waveform segment data.

[0085] As shown Figure 11As shown, it is a reading comprehension test diagram. The system first recognizes the text and generates pictures that match the text content according to the recognition results. After the patient reads the text, they need to select the picture that best matches the text description from the four pictures provided below. If the patient makes the correct choice, it indicates that they have understood the content they read; if the choice is incorrect, it means that they have not accurately understood the text information. This test method can not only effectively evaluate the reading comprehension ability of children with reading disorders, but also provide valuable data support for subsequent personalized corrective training, thereby further optimizing the intervention plan.

[0086] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art of this industry should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification only illustrates the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed.

Claims

1. A novel dyslexia assessment and intelligent correction method based on EOG, characterized in that, It includes the following steps: S1. Use an eye movement acquisition device to collect the eye movement signal data of children with reading disorders and normal reading children during the reading process respectively; S2. After filtering the original signal, generate an eye movement map through visualization processing to analyze the movement trajectory and direction of the eyes in the horizontal and vertical directions. Determine the basic direction of eye movement during individual reading through the basic characteristics of eye movement behavior. Use the peak detection algorithm to identify peaks and valleys and intercept the effective reading signal; S3. Compare the eye movement maps of children with reading disorders and normal reading children, and extract the key eye movement characteristic parameters of children with reading disorders; S4. Based on the abnormal points determined in S3, analyze the abnormal eye movement characteristics of frequent regressions of individuals, and combine factors such as curve slope, duration, and change rate to judge whether there is a reading disorder; S5. If the evaluation result is that there is a reading disorder, start the intelligent correction module. Achieve focused reading by tracking the red fonts sequentially displayed on the screen by the eyes, so as to help improve the visual focusing ability and improve the reading effect; then evaluate the patient's understanding of the text by asking the patient to select pictures that match the text content.

2. A novel reading disorder assessment and intelligent correction method based on EOG according to claim 1, characterized in that, The device required for collecting eye movement signals in S1 includes electrodes, lead wires, a digital electrooculogram acquisition module, a serial communication interface, and an output feedback device. The electrodes include the active electrode R, the active electrode L, and the reference electrode D. The input ends of the digital electrooculogram acquisition module are respectively connected to the active electrode R, the active electrode L, the reference electrode D, and the lead wires. The output end of the digital electrooculogram acquisition module is connected to the input end of the serial communication interface, and the output end of the serial communication interface is connected to the output feedback device; the output feedback device includes a tablet computer or a smart phone.

3. A novel dyslexia assessment and intelligent correction method based on EOG according to claim 2, characterized in that, In S1, 3 biological electrodes are worn to collect the eye movement signals of individuals during reading.

4. A novel reading disorder assessment and intelligent correction method based on EOG according to claim 1, characterized in that In S2, preprocess the eye movement map, draw the envelope line, calculate the median value, and remove high-frequency noise through Butterworth low-pass filtering. The formula is: where w c is the cut-off frequency of the filter and n is the order of the filter.

5. A novel dyslexia assessment and intelligent correction method based on EOG according to claim 1, characterized in that, In S2, use the peak detection algorithm to identify peaks and valleys. The specific steps are as follows: a). Input the eye movement waveform data, ensuring that the data is in the form of a one-dimensional array, representing a time series signal; b). Find all local maximum points (peaks) or local minimum points (valleys), including noise and insignificant extreme values; c). For each candidate extreme point, calculate its significance height (the height difference from the lowest points on both sides). When the significance height of a certain point is less than the set significance screening threshold, it is excluded, and only the points whose significance height meets the conditions are retained; d). Check the index distance between the remaining extreme points. When the distance between two adjacent extreme points is less than the set minimum distance, retain the one with higher significance; e). After screening, the obtained list of peaks and valleys is the valid extreme points that meet the conditions.

6. A novel dyslexia assessment and intelligent correction method based on EOG according to claim 1, characterized in that, In S2, intercept the effective reading signal according to the peaks and valleys. The specific steps are as follows: a). Combine the index positions and types ("peak" or "valley") of the detected peaks and valleys into a list, and sort them in ascending order according to the index positions. The sorted list ensures that all peak-valley points are arranged in chronological order. b), Check each pair of adjacent points in the sorted peak-valley point list in sequence. When the types of two adjacent points are different (i.e., one is a peak and the other is a valley), it is considered that a valid waveform segment is formed between these two points. c), For each pair of adjacent peak-valley points that meet the conditions, determine the start index and end index of the waveform segment, and extract the waveform segment data.

7. A novel reading disorder assessment and intelligent correction method based on EOG according to claim 5, characterized in that , The significance screening threshold and the minimum spacing are set to the optimal values observed manually, and according to the observation results, the significance screening threshold for peak-valley detection is set to 30, and the minimum spacing between adjacent peaks and valleys is set to 10.

8. A novel reading disorder assessment and intelligent correction method based on EOG according to claim 1, characterized in that , In S4, by detecting whether the waveform continuously decreases, calculate the slopes of all descending segments, sort them from small to large, and select the steepest about 10 - 15% segment as an anomaly, and thus judge the user's eye movement anomaly and evaluate dyslexia.

9. A novel dyslexia assessment and intelligent correction method based on EOG according to claim 1, characterized in that , In S5, start the intelligent correction module. The system uses the camera to recognize the text material to be read, and will display red characters one by one on the screen. After each red character is displayed, it immediately turns black, forming a dynamic window paradigm where the red characters move left and right. In this way, the user can use their eyes to track the red characters displayed on the system screen in sequence to achieve focused reading.

10. A novel dyslexia assessment and intelligent correction method based on EOG according to claim 1, characterized in that , In S5, after the system finishes recognizing the text, start the intelligent correction module. The system will attach four pictures to the interface, and only one of them matches the text description, while the other three have nothing to do with the text description. After the user finishes reading the text, they need to select the picture that best matches the text description from the four pictures. If the user selects correctly, it can be considered that they understand the content of this text; In S5, the intelligent correction module also includes functions for setting font size, character spacing, line spacing, font color, and background color.

Images