Eye-brain collaborative reading ability improving equipment

Abstract

The invention relates to the technical field of reading equipment, in particular to eye-brain collaborative reading ability improving equipment, which comprises a data acquisition module used for acquiring key index data in a user training process in multiple dimensions; the module combination unit comprises an eye movement speed training module, a visual capture training module, an attention training module, a visual field width training module and a reading speed testing module which cooperate with one another; the dynamic parameter adjusting module is used for dynamically adjusting training parameters of each module through a specific algorithm based on the key index data and a preset threshold value; the ability growth model module is used for constructing a user ability improvement curve based on historical training data and adjusting the training difficulty in a personalized manner; the feedback module is used for generating training effect feedback, and the eye and brain coordination of the user can be improved, so that the reading efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of reading device technology, and in particular to a device for improving reading ability through eye-brain coordination. Background Technology

[0002] Reading is a core means of acquiring knowledge and transmitting information. Reading ability, including reading speed, breadth of vision, concentration, and information retrieval efficiency, directly affects learning efficiency and the quality of knowledge absorption. For students in particular, efficient reading ability is a key foundation for academic improvement. With the development of intelligent education, various reading ability training products have emerged. The training modules of existing products, such as speed training, focus training, and vision training, are mostly independent functions stacked together, with no data exchange or collaborative linkage between modules, resulting in fragmented training effects. Moreover, most products only collect basic data such as training duration and accuracy, lacking refined collection of key indicators such as gaze trajectory coordinates, trajectory deviation, memory reaction time, and interference ignore rate. The low data collection frequency and large accuracy error make it impossible to accurately reflect the user's true training status. The product's training parameters, such as text movement speed, presentation duration, and number of characters, are mostly preset fixed values ​​or only divided into a few levels. They are not dynamically adjusted based on the user's real-time training data and historical ability curves, making it impossible to adapt to different users' ability levels, improvement pace, and weaknesses. Existing vision training often uses methods such as text stretching and fixed spacing expansion, simply increasing the text display width without considering human reading habits and visual adaptation patterns. This can easily lead to blurred text, reading breaks, and limited training effects. Furthermore, it does not gradually expand the field of vision coverage through character copying expansion, failing to improve the width of the field of vision. The product's text disappearance mechanism is mostly instantaneous or forced to disappear in a fixed order, without gradual adjustment based on the user's reading pace. This can easily interfere with the user's reading attention, leading to an increase in rereading. Summary of the Invention

[0003] In order to improve users' eye-brain coordination and thus improve reading efficiency, this application provides a reading ability enhancement device that improves eye-brain coordination.

[0004] This application provides a reading ability enhancement device based on eye-brain coordination, which adopts the following technical solution: including: The data acquisition module is used to collect key indicator data of users during the training process from multiple dimensions. The key indicator data includes training time, accuracy, gaze trajectory coordinates, trajectory deviation, average movement speed, number of dwell points, memory reaction time, and interference ignore rate. The collection frequency is once every 100ms for gaze coordinates, with an accuracy error of ≤2 pixels. The key indicator data is associated with user ID and training timestamp and stored in the cloud in JSON format. The modular unit includes eye movement speed training module, visual grasp training module, attention training module, visual field width training module and reading speed testing module that work together. Each module is not an independent function that is superimposed, and the training effect is maximized through their synergistic relationship. The dynamic parameter adjustment module is used to dynamically adjust the training parameters of each module based on the key indicator data and preset thresholds through a specific algorithm. The training parameters include the trajectory speed and trajectory complexity of eye movement speed training, the presentation duration and number of characters of visual grasping training, and the extension rate and character spacing step size of visual field width training. The capability growth model module is used to build a user capability improvement curve based on historical training data and adjust the training difficulty in a personalized way. The feedback module is used to generate feedback on training effectiveness, including level assessment and improvement suggestions.

[0005] Optionally, the eye movement speed training module employs a trajectory control algorithm to precisely control the movement trajectory and frequency of text or images. The trajectory control algorithm is a cubic Bézier curve algorithm, and its core execution steps include: S1: Set the trajectory start point, end point, and two control points; S2: Adjust the curve curvature according to the user level; S3: Update the text position according to the set frequency; The adjustment logic of the dynamic parameter adjustment module is as follows: if the trajectory deviation after the user completes the training for a set number of consecutive times is less than or equal to the set value, the trajectory speed is increased; if the trajectory deviation is greater than the set value, the current speed is maintained and the number of trajectory repetitions is increased.

[0006] Optionally, the dynamic adjustment logic of the visual grasping training module includes: The training texts are categorized by difficulty: beginner level consists of 3-5 numbers, intermediate level consists of 4-6 English words, and advanced level consists of 5-8 mixed characters. The texts are presented in a random 9-grid layout on the screen. The duration of short presentations ranges from 0.4-0.6 seconds for beginners, 0.1-0.4 seconds for intermediates, and 0.05-0.1 seconds for advanceds. When the training accuracy is ≥85%, the presentation time is reduced by 10%; when the accuracy is ≤60%, the presentation time is increased by 15%. Unremembered character combinations will have their priority increased by 30% and their presentation time extended by 20% in the next training session.

[0007] Optionally, the field-of-view width training module includes a text layout engine and a dynamic character spacing adjustment algorithm, the core implementation logic of which is: Initially, it displays two lines of text with a set width in the middle of the screen, supporting screen adaptation and custom settings for font size and length; The text layout engine parses the input text and splits the characters. Based on the user's reading progress, it expands towards both ends by combining character copying and dynamic spacing allocation. That is, it gradually copies the same character content along the lines where the initial two lines of text are located, so that each line of text expands from the initial set width to multiple groups of characters arranged from beginning to end, until it occupies the entire screen length.

[0008] Optionally, the reading speed testing module employs a multimodal triggering and gradual disappearance mechanism, specifically including: The text disappearance is triggered by a fixed time interval, which is set according to the test level. The intervals for level 1, level 2 and level 3 are different. The interval can be fine-tuned ± the set time through the core algorithm. The disappearance order follows the user's reading order from left to right or top to bottom, disappearing word by word or sentence by sentence. A fade-in effect is used during disappearance, with the transparency decreasing from 100% to 0%. The reading speed metric is the number of words read per minute. The calculation logic is: total number of correctly identified characters ÷ test duration × 60. Correct identification is defined as: characters that are not read back and match the original text.

[0009] Optionally, the dynamic parameter adjustment module adopts a PID control algorithm or a proportional-integral adjustment model, and the adjustment logic of the attention training module is to dynamically adjust the number and presentation frequency of interference items based on the interference item ignoring rate and the fluctuation value of task completion time.

[0010] Optionally, the data acquisition module also includes an abnormal data processing unit, used to remove short-stay data caused by accidental touches and to standardize the dwell time of texts of different lengths.

[0011] Optionally, the output of the feedback module includes: current reading speed, percentage exceeding that of users at the same level, difference from the historical highest speed, and weakness analysis, wherein the weakness analysis includes: optimal trajectory comparison, areas for improvement, and targeted training suggestions for the module.

[0012] Optionally, the text layout engine also has a text clarity preservation mechanism, which avoids reading difficulties caused by the extension of the ends of characters by rendering characters in real time.

[0013] In summary, this application includes the following beneficial technical effects: The modular unit organically coordinates five modules: eye movement speed, visual grasp, attention, visual field width, and reading speed testing. Through data exchange and parameter linkage, it forms an inseparable training system. The training objectives of each module support each other. Improving visual field width lays the foundation for improving reading speed, while attention training ensures the efficiency of information grasping when the visual field expands, thus achieving the overall training goal of eye-brain coordination. The data acquisition module covers metrics throughout the entire training process. Combined with a high acquisition frequency of 100ms and a high precision of ≤2 pixels, it can accurately capture the user's real-time training status, such as deviation of gaze trajectory and memory reaction delay. JSON format and cloud storage ensure data security and traceability. The abnormal data processing unit removes invalid data such as accidental touches and standardizes the dwell time of texts of different lengths, providing data support for dynamic parameter adjustment and capability growth model construction. The dynamic parameter adjustment module uses a PID control algorithm or a proportional-integral adjustment model to precisely adjust the training parameters of each module based on real-time key indicator data and preset thresholds. Combined with the historical data curves of the ability growth model module, it can adapt to the ability level and improvement pace of users of different ages and basic levels. Users with weak foundations can obtain lower difficulty and slower pace training, while users with strong abilities can obtain higher difficulty and faster pace training. The visual field width training module adopts an expansion method of character copying and dynamic spacing allocation. It gradually copies characters along the initial line to form multiple groups of characters arranged end to end. Compared with the existing stretching and fixed expansion methods, it is more in line with the physiological law of the gradual expansion of human visual field and reduces the difficulty of visual adaptation. The multimodal triggering of the reading speed test module ensures that the timing of text disappearance matches the user's reading pace. The gradual fading effect avoids the interference of sudden disappearance on attention, and the disappearance in the reading order reduces the phenomenon of rereading. Furthermore, it eliminates the influence of invalid data such as rereading and misreading on the test results, so that the calculation result of the number of words read per minute can truly reflect the user's actual reading speed and information grasping efficiency, providing a reliable basis for ability assessment and training adjustment. Detailed Implementation

[0014] This application discloses a device for improving reading ability through eye-brain coordination. The specific technical solution is as follows: It includes a data acquisition module, a module combination unit, a dynamic parameter adjustment module, a capability growth model module, and a feedback module. These modules work together to form a complete eye-brain coordination training system. Data acquisition module This system is used to collect key performance indicator (KPI) data from multiple dimensions during the user training process. The KPI data includes training time, accuracy, gaze trajectory coordinates, trajectory deviation, average movement speed, number of dwell points, memory reaction time, and interference ignore rate. The data collection frequency is gaze coordinates every 100ms, with an accuracy error of ≤2 pixels, ensuring fine granularity and accuracy of the data. The collected data is associated with the user ID and training timestamp and stored in the cloud in JSON format to ensure data traceability and security. The data acquisition module also includes an abnormal data processing unit, which is used to remove short-stay data caused by accidental touches and to standardize the dwell time of text of different lengths to avoid invalid data affecting the accuracy of subsequent parameter adjustments and model construction.

[0015] Modular combination unit It includes modules for training eye movement speed, visual grasping, attention, visual field width, and reading speed, which work together. These modules are not independent functions that are simply added together. Instead, they work together in an inseparable way through data exchange and parameter linkage, ensuring the overall effectiveness of the training and maximizing its benefits, thus achieving the goal of eye-brain coordination training.

[0016] Dynamic parameter adjustment module Using a PID control algorithm or a proportional-integral adjustment model, the training parameters of each module are dynamically adjusted based on key indicator data collected by the data acquisition module and preset thresholds. The training parameters include the trajectory speed and trajectory complexity for eye movement speed training, the presentation duration and number of characters for visual grasping training, and the extension rate and character spacing step size for visual field width training. Through real-time parameter adjustment, the system adapts to the user's real-time training status and ability level.

[0017] Capability Growth Model Module Using historical training data stored in the cloud, a user-specific ability improvement curve is constructed. By analyzing the curve, the user's ability weaknesses, improvement pace, and potential space are identified, and the training difficulty is adjusted in a personalized manner to ensure that the training difficulty always matches the user's ability and achieves a step-by-step improvement.

[0018] Feedback module It is used to generate comprehensive training effect feedback. The output includes the current reading speed, the percentage of users who are ahead of the same level, the difference from the historical highest speed, and the analysis of weaknesses. The analysis of weaknesses includes the comparison of the optimal trajectory, the areas to be improved, and the module-specific training suggestions, providing users with clear directions for improvement.

[0019] The eye movement speed training module uses a trajectory control algorithm to precisely control the movement trajectory and frequency of text or images. The trajectory control algorithm is a cubic Bézier curve algorithm, and the core execution steps include: S1: Set the trajectory start point, end point, and two control points; S2: Adjust the curve curvature according to the user level; S3: Update the text position according to the set frequency; The dynamic parameter adjustment module adjusts the following logic: if the trajectory deviation after the user completes the training for a set number of consecutive times is less than or equal to the set value, the trajectory speed is increased; if the trajectory deviation is greater than the set value, the current speed is maintained and the number of trajectory repetitions is increased.

[0020] The dynamic adjustment logic of the visual grasping training module includes: The training texts are categorized by difficulty: beginner level consists of 3-5 numbers, intermediate level consists of 4-6 English words, and advanced level consists of 5-8 mixed characters. The texts are presented randomly within a 9-grid layout on the screen to avoid training bias caused by repetitive areas. The short presentation duration ranges from 0.4-0.6 seconds for beginner, 0.1-0.4 seconds for intermediate, and 0.05-0.1 seconds for advanced, adapting to the memory thresholds of users with different abilities. When the training accuracy is ≥85%, the presentation duration is shortened by 10% to increase the training difficulty; when the accuracy is ≤60%, the presentation duration is extended by 15% to reduce the training difficulty and avoid user frustration. Unremembered character combinations receive a 30% priority increase and a 20% extension in presentation duration during the next training session, enabling targeted reinforcement training for weak points.

[0021] The visual field width training module includes a text layout engine and a dynamic character spacing adjustment algorithm. The core logic is as follows: Initially, two lines of text with a set width are displayed in the middle of the screen, supporting screen adaptation and user-defined font size and length settings to suit different devices and user reading habits. The text layout engine parses the input text and breaks down the characters. Based on the user's reading progress (determined by pausing for ≥1 second on a single sentence or by screen swiping), it expands towards both ends through a combination of character copying and dynamic spacing allocation. Specifically, it gradually copies the same character content along the lines containing the initial two lines of text, expanding each line from its initial set width into multiple sets of characters arranged sequentially until it occupies the entire screen length, conforming to the physiological laws of human visual field expansion. The text layout engine also has a text clarity preservation mechanism, rendering characters in real-time to avoid reading difficulties caused by expansion at both ends, ensuring the comfort and effectiveness of the training process.

[0022] The reading speed test module employs a multimodal triggering and gradual disappearance mechanism. Specifically, the text disappearance trigger is a fixed time interval, set according to test levels (Level 1, 2, and 3 have different intervals). This interval can be fine-tuned ± the set time through the core algorithm to match the user's reading pace. The disappearance order follows the user's reading sequence from left to right or top to bottom, disappearing word by word or sentence by sentence. A fading effect is used during disappearance, with transparency decreasing from 100% to 0% to avoid sudden disappearance interfering with reading attention. The reading speed metric is the number of words read per minute, calculated as: total number of correctly identified characters ÷ test duration × 60. Correct identification is defined as "characters that are not reread and match the original text," ensuring the test results accurately reflect the user's actual reading speed and information retrieval efficiency. The attention training module's adjustment logic dynamically adjusts the number and frequency of distractors based on the distractor ignore rate and task completion time fluctuations, achieving targeted reinforcement training for focus.

Claims

1. A device for improving reading ability through eye-brain coordination, characterized in that, include: The data acquisition module is used to collect key indicator data of users during the training process from multiple dimensions. The key indicator data includes training time, accuracy, gaze trajectory coordinates, trajectory deviation, average movement speed, number of dwell points, memory reaction time, and interference ignore rate. The collection frequency is once every 100ms for gaze coordinates, with an accuracy error of ≤2 pixels. The key indicator data is associated with user ID and training timestamp and stored in the cloud in JSON format. The modular unit includes eye movement speed training module, visual grasp training module, attention training module, visual field width training module and reading speed testing module that work together. Each module is not an independent function that is superimposed, and the training effect is maximized through their synergistic relationship. The dynamic parameter adjustment module is used to dynamically adjust the training parameters of each module based on the key indicator data and preset thresholds through a specific algorithm. The training parameters include the trajectory speed and trajectory complexity of eye movement speed training, the presentation duration and number of characters of visual grasping training, and the extension rate and character spacing step size of visual field width training. The capability growth model module is used to build a user capability improvement curve based on historical training data and adjust the training difficulty in a personalized way. The feedback module is used to generate feedback on training effectiveness, including level assessment and improvement suggestions.

2. The eye-brain coordination reading ability enhancement device according to claim 1, characterized in that, The eye movement speed training module uses a trajectory control algorithm to precisely control the movement trajectory and frequency of text or images. The trajectory control algorithm is a cubic Bézier curve algorithm, and its core execution steps include: S1: Set the trajectory start point, end point, and two control points; S2: Adjust the curve curvature according to the user level; S3: Update the text position according to the set frequency; The adjustment logic of the dynamic parameter adjustment module is as follows: if the trajectory deviation after the user completes the training for a set number of consecutive times is less than or equal to the set value, the trajectory speed is increased; if the trajectory deviation is greater than the set value, the current speed is maintained and the number of trajectory repetitions is increased.

3. The eye-brain coordination reading ability enhancement device according to claim 1, characterized in that, The dynamic adjustment logic of the visual grasping training module includes: The training texts are categorized by difficulty: beginner level consists of 3-5 numbers, intermediate level consists of 4-6 English words, and advanced level consists of 5-8 mixed characters. The texts are presented in a random 9-grid layout on the screen. The duration of short presentations ranges from 0.4-0.6 seconds for beginners, 0.1-0.4 seconds for intermediates, and 0.05-0.1 seconds for advanceds. When the training accuracy is ≥85%, the presentation time is reduced by 10%; when the accuracy is ≤60%, the presentation time is increased by 15%. Unremembered character combinations will have their priority increased by 30% and their presentation time extended by 20% in the next training session.

4. The eye-brain coordination reading ability enhancement device according to claim 1, characterized in that, The field-of-view width training module includes a text layout engine and a dynamic character spacing adjustment algorithm. The core implementation logic is as follows: Initially, it displays two lines of text with a set width in the middle of the screen, supporting screen adaptation and custom settings for font size and length; The text layout engine parses the input text and splits the characters. Based on the user's reading progress, it expands towards both ends by combining character copying and dynamic spacing allocation. That is, it gradually copies the same character content along the lines where the initial two lines of text are located, so that each line of text expands from the initial set width to multiple groups of characters arranged from beginning to end, until it occupies the entire screen length.

5. The eye-brain coordination reading ability enhancement device according to claim 1, characterized in that, The reading speed testing module employs a multimodal triggering and gradual disappearance mechanism, specifically including: The text disappearance is triggered by a fixed time interval, which is set according to the test level. The intervals for level 1, level 2 and level 3 are different. The interval can be fine-tuned ± the set time through the core algorithm. The disappearance order follows the user's reading order from left to right or top to bottom, disappearing word by word or sentence by sentence. A fade-in effect is used during disappearance, with the transparency decreasing from 100% to 0%. The reading speed metric is the number of words read per minute. The calculation logic is: total number of correctly identified characters ÷ test duration × 60. Correct identification is defined as: characters that are not read back and match the original text.

6. The eye-brain coordination reading ability enhancement device according to claim 1, characterized in that, The dynamic parameter adjustment module adopts a PID control algorithm or a proportional-integral adjustment model. The adjustment logic of the attention training module is to dynamically adjust the number and presentation frequency of interference items based on the interference item ignore rate and the fluctuation value of task completion time.

7. The eye-brain coordination reading ability enhancement device according to claim 1, characterized in that, The data acquisition module also includes an abnormal data processing unit, which is used to remove short-stay data caused by accidental touches and to standardize the dwell time of texts of different lengths.

8. The eye-brain coordination reading ability enhancement device according to claim 1, characterized in that, The feedback module outputs the following: current reading speed, percentage of users exceeding the same level, difference from the historical highest speed, and weakness analysis. The weakness analysis includes: comparison of the optimal trajectory, areas for improvement, and targeted training suggestions for the module.

9. The eye-brain coordination reading ability enhancement device according to claim 4, characterized in that, The text layout engine also has a text clarity preservation mechanism, which avoids reading difficulties caused by the extension of the ends of characters by rendering characters in real time.