Method for monitoring compliance for myopia prevention and related device

Abstract

This application discloses a method and related equipment for monitoring adherence to myopia prevention, belonging to the field of data processing technology. The method includes: acquiring usage detection data of a photobiologically regulated photomicrophone (PBM) terminal device during use, the usage detection data including at least one of the following: eye alignment status, blinking status, device posture, and usage duration; calculating adherence index data based on the usage detection data, the adherence index including at least one of the following: usage frequency, on-time rate, completion rate, and consecutive usage days; grouping and aggregating the adherence index data according to preset time windows, calculating the statistical value of the adherence index within each time window, establishing a mapping relationship between the adherence index and timestamps, and generating an adherence index dataset containing a time series structure; and generating an adherence report based on the adherence index dataset.

Description

Technical Field

[0001] This application belongs to the field of data processing technology, specifically relating to a method and related equipment for monitoring compliance in myopia prevention. Background Technology

[0002] In recent years, the prevalence of myopia among children and adolescents has continued to rise, showing a trend of high incidence and younger age of onset, and has become a major public health problem affecting the visual health of the nation. Among many intervention methods, photobiomodulation (PBM) technology plays a role by improving choroidal blood flow and influencing retinal dopamine release through physiological mechanisms.

[0003] However, the effectiveness of such interventions is highly dependent on a long-term, stable implementation process. Children have weaker self-management abilities, and parents often struggle to balance busy work schedules with their supervisory responsibilities, making it difficult to ensure the continuity and regularity of intervention implementation, thus affecting the overall effectiveness of prevention and control.

[0004] Therefore, there are still significant shortcomings in monitoring compliance during the intervention process for myopia in children. Summary of the Invention

[0005] The purpose of this application is to provide a method and related equipment for monitoring compliance in myopia prevention, which can solve the problem that there are still significant deficiencies in the current process of monitoring compliance in the intervention of photobiological regulation in children's myopia.

[0006] In a first aspect, embodiments of this application provide a method for monitoring adherence to myopia prevention, the method comprising: Acquire usage data of the photobiologically regulated PBM terminal device during use. The usage data includes at least one of the following: eye alignment status, blinking status, device posture, and usage duration. The compliance indicators are calculated based on the test data. The compliance indicators include at least one of the following: frequency of use, on-time rate, completion rate, and number of consecutive days of use. The compliance indicator data are grouped and aggregated according to a preset time window, the statistical value of compliance indicator within each time window is calculated, and the mapping relationship between compliance indicator and timestamp is established to generate a compliance indicator dataset containing a time series structure. A compliance report is generated based on the compliance indicator dataset. The compliance report includes a numerical display area for the compliance indicators, a trend curve of the compliance indicators over time, and compliance fluctuation nodes identified and labeled based on the trend curve.

[0007] Secondly, embodiments of this application provide a compliance monitoring device for myopia prevention, the device comprising: The acquisition module is used to acquire usage detection data of the photobiologically regulated PBM terminal device during use. The usage detection data includes at least one of the following: eye alignment status, blinking status, device posture, and usage duration. The calculation module is used to calculate compliance indicators based on the usage detection data. The compliance indicators include at least one of the following: usage frequency, on-time rate, completion rate, and consecutive days of use. The generation module is used to group and aggregate the compliance indicator data according to a preset time window, calculate the compliance indicator statistics within each time window, establish the mapping relationship between compliance indicators and timestamps, and generate a compliance indicator dataset containing a time series structure. The generation module is also used to generate a compliance report based on the compliance indicator dataset. The compliance report includes a numerical display area of ​​the compliance indicators, a trend curve of the compliance indicators over time, and compliance fluctuation nodes identified and labeled based on the trend curve.

[0008] Thirdly, embodiments of this application provide an electronic device including a processor and a memory, wherein the memory stores programs or instructions executable on the processor, and the programs or instructions, when executed by the processor, implement the steps of the method described in the first aspect.

[0009] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect.

[0010] Fifthly, embodiments of this application provide a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the method as described in the first aspect.

[0011] In a sixth aspect, embodiments of this application provide a computer program product stored in a storage medium, which is executed by at least one processor to implement the method described in the first aspect.

[0012] In the embodiments of this application, by acquiring usage detection data of the photobiological modulation PBM terminal device during use, the usage detection data includes at least one of the following: eye alignment state, blinking state, device posture, and usage duration; an objective record of the user's photobiological modulation operation process is achieved, providing a real and reliable data foundation for subsequent analysis. The compliance metrics are calculated based on the detection data. These compliance metrics include at least one of the following: usage frequency, on-time rate, completion rate, and consecutive days of use. The original usage behavior data is transformed into quantifiable and comparable numerical metrics, enabling standardized evaluation of user performance and facilitating horizontal and vertical comparative analysis across different time points and among different users. The compliance metric data is grouped and aggregated according to preset time windows, calculating the statistical values ​​of compliance metrics within each time window, establishing a mapping relationship between compliance metrics and timestamps, and generating a compliance metric dataset with a time-series structure. Discrete usage records are converted into structured data with a time dimension. A compliance report is generated based on the compliance metric dataset, presenting the specific values ​​of compliance metrics through a numerical display area, showing the changing patterns of compliance metrics over time through trend graphs, and highlighting time points of significant compliance changes by identifying and labeling compliance fluctuation nodes. This allows for a direct understanding of the current state of compliance, historical trends, and key change nodes. Attached Figure Description

[0013] Figure 1 This is a flowchart of a compliance monitoring method provided in an embodiment of this application; Figure 2 This is a schematic diagram of a compliance monitoring system provided in an embodiment of this application; Figure 3 This is a structural diagram of a compliance monitoring device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0014] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0015] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0016] In response to the problems in related technologies, this application provides a method and related equipment for monitoring compliance in myopia prevention, which can solve the problem that there are still obvious deficiencies in the current compliance monitoring in the process of myopia photobiological regulation intervention in children.

[0017] The compliance monitoring method provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0018] Figure 1 A flowchart illustrating a compliance monitoring method for myopia prevention provided in an embodiment of this application.

[0019] like Figure 1 As shown, the adherence monitoring method for myopia prevention may include steps 110-130. This method is applied to an adherence monitoring device for myopia prevention, as detailed below: Step 110: Obtain usage detection data of the photobiological regulation PBM terminal device during use. The usage detection data includes at least one of the following: eye alignment status, blinking status, device posture, and usage duration. Photobiological modulation (PBM) refers to a technology that uses low-intensity light of a specific wavelength to irradiate biological tissues, thereby regulating cell function through photobiological effects. A PBM terminal device is a hardware unit used to perform photobiological modulation operations, typically including a light source module, a detection module, and a communication module. Usage detection data refers to the raw data related to user behavior collected by various sensors during use of the PBM terminal device. Eye alignment status refers to whether the relative positional relationship between the user's eyes and the device's light output port meets preset requirements; specifically, whether both eyes are within the effective irradiation area and whether the center of the pupil is aligned with the center of the light path.

[0020] Blinking status refers to the real-time state of the user's eyelids opening and closing during use, used to determine whether the user keeps their eyes open during irradiation. Device posture refers to the angle and orientation of the PBM terminal device in space, used to determine whether the device is in the preset correct usage posture. Usage duration refers to the effective length of time the user actually receives photobiological modulation irradiation, excluding interruptions caused by eye closure or device posture deviation.

[0021] When acquiring eye alignment status, the PBM terminal device uses an eye proximity sensor to detect whether the distance between the user's eyes and the device's light output port is within a preset valid range. For example, the eye proximity sensor can be an infrared distance sensor. When it detects that the distance between the user's eyes and the device's light output port is within 30 mm to 50 mm, it determines that the distance meets the requirements. Simultaneously, an image sensor acquires eye images, and a pupil detection algorithm is used to identify the pupil area in the image to confirm whether the center of both pupils is aligned with the center of the light path. If both eyes are correctly aligned, the eye alignment status is recorded as valid.

[0022] When acquiring blink status, the PBM terminal device monitors eyelid opening and closing in real time using a blink detection sensor. This sensor can be based on the principle of infrared reflection, determining eyelid status by detecting changes in the intensity of infrared light reflected from the eyeball surface. If the closed eye state persists for more than a preset duration, such as 2 seconds, it is considered an abnormal blink status. When acquiring device posture, the PBM terminal device detects the device's angle data in three-dimensional space using a built-in tilt sensor. The tilt sensor can be an accelerometer or a gyroscope. If the device's pitch or roll angle deviates from the preset standard posture, for example, by more than 15 degrees, it is considered that the device posture does not meet the usage requirements. When acquiring usage duration, the PBM terminal device records the cumulative time from when the user correctly aligns and keeps their eyes open until the end of use using a time recorder. It also records the number of interruptions caused by eye alignment failure, blinking, or abnormal device posture, and the duration of each interruption, ultimately obtaining the effective illumination duration.

[0023] By using multi-dimensional sensors to collaboratively collect key behavioral data during use, the system can objectively and accurately record the user's actual performance, providing a reliable data foundation for subsequent compliance analysis and avoiding data bias and incompleteness caused by relying on subjective reports from users or manual records from parents.

[0024] Step 120: Calculate compliance index data based on the usage detection data. The compliance index includes at least one of the following: usage frequency, on-time rate, completion rate, and consecutive usage days. Among them, compliance indicators refer to numerical parameters used to quantitatively evaluate the degree to which users perform photobiological regulation operations according to preset requirements. Usage frequency refers to the ratio of actual usage times to planned usage times. On-time rate refers to the ratio of the number of times a user completes the usage near the preset planned time to the total number of usages. Completion rate refers to the ratio of the number of times a single, prescribed usage session is fully completed to the total number of usages. Continuous usage days refer to the number of days a user continuously performs the usage operation without interruption.

[0025] When calculating usage frequency, usage monitoring data uploaded by PBM terminal devices can be obtained through a cloud server. The actual number of uses within a preset period, such as a week, can be counted, and this actual number of uses can be compared with the planned number of uses set for the user to calculate the usage frequency. For example, if the planned number of uses set for the user is twice a day and fourteen times a week, and the actual number of uses is ten, then the usage frequency is calculated to be 71.4%.

[0026] When calculating the on-time rate, the cloud server obtains the start time of each use, compares it with the preset planned usage time, and determines whether the start time is within a preset tolerance range before or after the planned usage time, such as within 30 minutes. The on-time completion rate is then counted as a percentage of the total number of uses. For example, if a user uses the service ten times in a week, and eight of those times start within 30 minutes before or after the planned usage time, the on-time rate is calculated as 80%.

[0027] When calculating the completion rate, the cloud server obtains the effective exposure time for each use and compares it with the specified single usage time, such as three minutes, to determine whether the full duration requirement has been met. The percentage of complete usages is then calculated. For example, if a user uses the service ten times in a week, and nine of those times have an effective exposure time of three minutes, the completion rate is calculated as 90%. When calculating consecutive usage days, the cloud server counts the number of consecutive calendar days the user has used the service, starting from the most recent use and counting backwards. If there is no usage record on a particular day, the count is interrupted. For example, if a user has usage records for five consecutive days from Monday to Friday, the consecutive usage days are five days. If there is no usage on Saturday, the consecutive usage days are interrupted and the count restarts.

[0028] By transforming raw usage data into quantifiable and comparable compliance indicators, users' performance can be objectively evaluated and continuously tracked, providing clear numerical basis for subsequent compliance judgment and intervention.

[0029] Step 130: Group and aggregate the compliance index data according to a preset time window, calculate the compliance index statistics within each time window, establish the mapping relationship between compliance index and timestamp, and generate a compliance index dataset containing a time series structure. The preset time window refers to a fixed time interval divided along a continuous time axis, used to group discrete usage records into a unified time unit for analysis. Grouping and aggregation refers to the process of classifying and aggregating the original compliance indicator data according to the preset time window, and then summarizing and calculating the aggregated data. The compliance indicator statistical value refers to the summarized value obtained by mathematical calculation of the grouped and aggregated data, used to characterize the overall compliance level of users within that time window. A timestamp is a marker information that identifies the time position of a data point, usually in the form of a date or date and time. Mapping relationship refers to establishing a correlation between compliance indicator values ​​and their corresponding timestamps, so that each data point can be located to a specific time position. The time series structure refers to an ordered sequence structure formed by arranging data in chronological order, where each data point contains two elements: a timestamp and a corresponding compliance indicator value.

[0030] When grouping and aggregating compliance indicator data according to a preset time window, the system retrieves the original compliance indicator data calculated in step 120. This data is stored on a per-use basis, with each record containing information such as the usage date, usage frequency contribution, on-time rate contribution, completion rate contribution, and the number of consecutive days of use on that day. The system reorganizes this discrete raw data according to the preset time window division rules. The preset time window can be a daily window, that is, aggregating by calendar day, grouping multiple usage records within the same date into the compliance indicator for that day.

[0031] For example, if a user completes two uses on a certain day, with the first use completed on time and the second use delayed by 40 minutes, and both uses involving a full 3-minute irradiation, the system records the usage frequency for that day as 100%, the on-time rate as 50%, the completion rate as 100%, and the consecutive usage days as the number of consecutive usage days up to that day. The preset time window can also use a weekly window, aggregating usage records from Monday to Sunday (7 days total) into the weekly compliance metric. For example, if a user plans to use the service 14 times in a week and actually uses it 11 times, with 9 completed on time and 11 completed, and the consecutive usage days peaking at 5 days within that week, the system calculates the usage frequency for that week as 78.6%, the on-time rate as 81.8%, the completion rate as 100%, and the consecutive usage days as the maximum value of 5 days achieved within that week.

[0032] When calculating adherence statistics within each time window, the system performs various statistical calculations on the grouped and aggregated data. For percentage indicators such as usage frequency, on-time rate, and completion rate, the system calculates the average value within each time window to reflect the overall adherence level within that time window. For example, when aggregating by weekly windows, the system calculates the average daily usage frequency within that week as the weekly usage frequency statistic, the average daily on-time rate within that week as the weekly on-time rate statistic, and the average daily completion rate within that week as the weekly completion rate statistic. For cumulative indicators such as consecutive days of use, the system calculates the maximum value within each time window to reflect the user's optimal adherence level within that time window. For example, when aggregating by weekly windows, the system takes the maximum number of consecutive days of use per day within that week as the weekly consecutive days of use statistic. The system also calculates the standard deviation within each time window to characterize the degree of fluctuation in adherence indicators within that time window. For example, a larger standard deviation in usage frequency indicates greater variation in users' daily performance and a poorer regularity.

[0033] When establishing the mapping between compliance metrics and timestamps, the system associates a specific timestamp identifier with each aggregated statistical value. For data aggregated by daily windows, the timestamp uses the date of that day, in the format of year-month-day. For example, the usage frequency statistics for March 26, 2026, are mapped to that date. For data aggregated by weekly windows, the timestamp can use the date of the first day of that week or the week number, such as using the date of Monday of that week, in the format of year-month-day. The system binds the compliance metric statistics within each time window to the corresponding timestamp for that window, forming a key-value pair data record, where the timestamp is the key and the set of compliance metric statistics is the value.

[0034] When generating a compliance indicator dataset with a time-series structure, the system sorts the compliance indicator statistics with established mapping relationships according to the order of timestamps, forming a time-series structured dataset. In this dataset, data points are arranged sequentially from earliest to latest time, and each data point contains a timestamp field along with the corresponding usage frequency statistics, on-time rate statistics, completion rate statistics, and consecutive usage days statistics.

[0035] For example, a time series dataset containing four weeks of data can be represented as follows: Week 1 corresponds to March 1, 2026, with a usage frequency of 85%, on-time performance of 78%, completion rate of 95%, and consecutive usage days of 5 days; Week 2 corresponds to March 8, 2026, with a usage frequency of 92%, on-time performance of 88%, completion rate of 98%, and consecutive usage days of 7 days; Week 3 corresponds to March 15, 2026, with a usage frequency of 70%, on-time performance of 65%, completion rate of 90%, and consecutive usage days of 3 days; Week 4 corresponds to March 22, 2026, with a usage frequency of 80%, on-time performance of 75%, completion rate of 92%, and consecutive usage days of 4 days. This time series dataset maintains the chronological order of the original data, providing a foundation for subsequent trend analysis.

[0036] Step 140: Generate a compliance report based on the compliance indicator dataset. The compliance report includes a numerical display area for compliance indicators, a trend curve of compliance indicators over time, and compliance fluctuation nodes identified and labeled based on the trend curve.

[0037] The compliance report is a comprehensive data display medium presented in document or interface format, used to communicate user compliance status to parents and doctors. The numerical display area is a dedicated interface area in the report for displaying specific values ​​of compliance indicators, typically presented as numbers, dashboards, or progress bars. The trend graph is a line or curve chart plotted with time on the horizontal axis and compliance indicator values ​​on the vertical axis, used to visually demonstrate the changes in compliance indicators over time. Identification and annotation refers to the system automatically analyzing data points in the trend graph, detecting nodes that meet preset fluctuation conditions, and visually marking these nodes in the chart. Compliance fluctuation nodes are inflection points in the trend graph where compliance indicator values ​​change significantly, including sharp drops, sharp rises, or critical time points where values ​​remain consistently below the threshold.

[0038] When generating a compliance report based on the compliance indicator dataset, the report generation engine is invoked, using the time-series structured dataset generated in step 130 as input, and performing data population and visualization rendering according to a preset report template. Report generation first constructs a numerical display area. The system extracts the compliance indicator statistics for the most recent time window from the time-series structured dataset and presents them in a highlighted manner at the top of the report. For example, the numerical display area displays a progress bar showing the usage frequency of the most recent week as 80%, the on-time rate as 75%, and the completion rate as 92%; it also displays the longest consecutive usage days reached recently as 7 days in large font. The numerical display area can also adopt a dashboard format, with pointers pointing to corresponding percentage scales, and color coding indicating excellent, good, or needing improvement levels.

[0039] When generating trend charts of compliance indicators over time, the system extracts the timestamps of all time windows and the corresponding compliance indicator statistics from the time series structure dataset, and plots them as line graphs on a coordinate system. The trend chart can display four curves separately: usage frequency, on-time rate, completion rate, and consecutive days of use. Alternatively, the overall compliance score can be displayed as a single curve. Taking the usage frequency curve as an example, the horizontal axis represents the timestamp sequence, and the vertical axis represents the percentage value. Each time window corresponds to a data point, which are connected sequentially to form a line. For instance, based on the aforementioned four weeks of data, the trend chart shows that the usage frequency was 85% in week 1, rose to 92% in week 2, fell to 70% in week 3, and rebounded to 80% in week 4, forming a fluctuating curve that first rises, then falls, and then rises again.

[0040] When identifying and labeling compliance fluctuation nodes based on trend curves, the system runs a fluctuation detection algorithm to analyze the data points in the trend curve. The fluctuation detection algorithm first calculates the change in the compliance index value between adjacent time windows. When the absolute value of the change exceeds a preset change threshold, it is identified as a fluctuation node. For example, the preset change threshold is 15%. If the increase in week 2 compared to week 1 is 7%, it does not exceed the threshold and is not labeled; if the decrease in week 3 compared to week 2 is 22%, it exceeds the threshold and is identified as a significant decrease node.

[0041] The fluctuation detection algorithm also identifies nodes that consistently fall below a preset threshold. For example, the preset threshold for good compliance is 70%. When the usage frequency is below 70% for two or more consecutive time windows, these nodes are identified as persistently low nodes. The system visually annotates the identified fluctuation nodes on a trend curve: nodes with significant declines are marked with red downward arrows, nodes with significant increases are marked with green upward arrows, and nodes with persistently low levels are marked with yellow shaded areas. Simultaneously, the system generates text descriptions for the marked nodes, such as "Compliance has significantly decreased, with a decrease of 22%" next to the red downward arrow, and "Usage frequency below 70% for two consecutive weeks" next to the yellow shaded area.

[0042] By grouping and aggregating compliance indicator data according to preset time windows, the system transforms discrete usage records into structured time-series data, making the previously fragmented usage behavior data comparable and analyzable over time. Calculating the statistical values ​​of compliance indicators within each time window eliminates the interference of random fluctuations in single uses on the overall assessment, reflecting the stable compliance level of users over a longer time scale. Establishing a mapping relationship between compliance indicators and timestamps ensures the time positioning accuracy of each data point, providing a data foundation for subsequent time-series analysis.

[0043] A dataset of adherence indicators with a time-series structure is generated, ensuring the data possesses temporal order, equal intervals, and structural consistency, meeting the data format requirements for trend analysis. The latest adherence indicators are presented through a numerical display area, allowing parents and doctors to quickly gain an intuitive understanding of the current adherence status. Trend graphs illustrate the changing patterns of adherence indicators over time, visualizing the dynamic evolution of adherence and revealing its changing trends and development direction more effectively than single numerical values.

[0044] By identifying and annotating adherence fluctuation nodes based on trend curves, this system enables automatic detection and highlighting of abnormal adherence changes. This allows parents and doctors to quickly pinpoint the time points of significant adherence changes without manual data comparison, facilitating timely tracing of causes and intervention. This implementation transforms raw adherence data into a comprehensive report with temporal structure, visualization, and intelligent annotation features, significantly improving the readability and understandability of adherence information.

[0045] When generating adherence reports, the calculated adherence indicator data can be integrated and visualized via a cloud server to form structured report content. For example, the adherence report can include usage frequency displayed as a percentage, on-time performance rate displayed as a percentage, completion rate displayed as a percentage, and consecutive days of use displayed as an integer. The adherence report can also compare this week's adherence indicators with last week's, displaying the changes in adherence indicators over time in the form of trend charts. For example, the report can show a curve of the user's usage frequency changes over the past four weeks, intuitively reflecting the fluctuation trend of adherence. The cloud server pushes the generated adherence report to the monitoring application and the doctor's platform. The monitoring application can display the child's adherence status to parents using a combination of charts and text, while the doctor's platform displays an overview of the adherence of the users under their management in the form of a list or detail page. The usage monitoring data can be uploaded to the cloud server via a wireless network, and the cloud server includes an independent usage record database for each user.

[0046] By integrating scattered adherence indicator data into a clearly structured and easy-to-understand report format, parents and doctors can intuitively understand the user's performance, making it easier to identify adherence problems and evaluate the effectiveness of interventions in a timely manner.

[0047] This method automatically collects multi-dimensional usage data during use, including eye alignment, blinking, device posture, and usage duration, using PBM terminal devices. Based on this data, it calculates compliance indicators such as usage frequency, on-time rate, completion rate, and consecutive days of use, ultimately generating a structured compliance report. This approach achieves objective recording and quantitative evaluation of photobiological regulation, solving the data inaccuracies caused by traditional reliance on manual recording and subjective judgment. It provides authentic, continuous, and traceable data support for parental supervision and physician evaluation.

[0048] In one possible embodiment, step 110 includes: The distance between the user's eyes and the device is detected by an eye proximity sensor to determine whether it is within an effective range, and the correct alignment of the eyes is confirmed by a pupil detection algorithm to obtain the eye alignment status. The blinking state is confirmed by a blink detection sensor, and the timing is paused when the eyes are closed for more than a preset time, so as to obtain the blinking state. The device posture is detected by a tilt sensor. When the posture deviates from the correct posture, the device pauses and issues a voice prompt to obtain the device posture. Record the effective irradiation duration, number of interruptions, interruption duration, and location of use to obtain the usage duration.

[0049] Among them, the eye proximity sensor refers to a photoelectric sensing element used to detect the proximity of an object. It typically uses the principle of infrared emission and reception, determining distance by measuring changes in the intensity of reflected light. The effective range refers to the distance interval between the user's eyes and the device's light output port that ensures both illumination effectiveness and safety. The pupil detection algorithm refers to a computer vision algorithm that uses image processing technology to identify the pupil region in an eye image and calculate its center position. The blink detection sensor refers to a sensing element used to monitor the opening and closing of the eyelids, which can be based on the principle of infrared reflection or image recognition. The preset duration refers to the upper limit of the allowed duration of eye closure; exceeding this limit is considered abnormal eye closure.

[0050] A tilt sensor is a sensing element used to detect the angle and orientation of an object in space, including accelerometers, gyroscopes, or a combination of both. Correct posture refers to the preset orientation and angle range of the device in space, in which the emitted light direction matches the user's line of sight. Effective illumination duration refers to the cumulative time the user actually receives photobiological modulation illumination, excluding periods of interruption due to closed eyes or device posture deviation. Number of interruptions refers to the number of times illumination is interrupted during use due to eye alignment failure, closed eyes, or abnormal device posture. Interruption duration refers to the duration of each interruption. Usage location refers to the geographical location of the user when performing photobiological modulation.

[0051] When the distance between the user's eyes and the device is detected by an eye proximity sensor to ensure it is within an effective range, and the pupil detection algorithm confirms correct eye alignment, the PBM terminal device's built-in infrared distance sensor continuously measures the distance between the user's eyes and the device's light output port. If both eyes are within an effective distance of 30mm to 50mm, the distance condition is considered met. Based on this, the device acquires images of the user's eyes using an image sensor, identifies the iris region in the image using a deep learning-based object detection network, and then determines the pupil region and calculates the pupil center coordinates using contour extraction and ellipse fitting methods. The centers of the left and right pupils are matched with preset optical path center points. If the offset between the centers of both pupils and the corresponding optical path centers is within a preset tolerance range (e.g., less than 2mm), the eyes are considered correctly aligned, and the eye alignment status is recorded as valid. If the distance exceeds the effective range or the offset of either pupil center exceeds the tolerance, the eye alignment status is recorded as failed, the device pauses illumination, and a warning is issued.

[0052] When confirming the open-eye state using a blink detection sensor and pausing the timer if the eyes are closed for more than a preset duration to obtain blink status, the PBM terminal device uses an infrared reflective blink detection sensor. This sensor emits infrared light towards the eyeball and receives the reflected signal. When the eyelids are open, the infrared light undergoes specular reflection on the surface of the eyeball, resulting in a high reflected signal intensity. When the eyelids are closed, the infrared light is blocked by the eyelids, and the reflected signal intensity is significantly reduced. The device monitors the reflected signal intensity in real time. When the signal intensity is below the eye-closing threshold, it determines that the eyes are closed and starts the eye-closing timer. When the eye-closing duration exceeds a preset duration, such as 2 seconds, it is determined to be an abnormal eye-closing, the device pauses the illumination timer and records an interruption event. When the reflected signal intensity recovers to above the eye-opening threshold, it is determined that the eye-opening state has been restored, and the device resumes the illumination timer.

[0053] When the device's attitude is detected by a tilt sensor and deviates from the correct posture, the system pauses and issues a voice prompt. To obtain the device's attitude, the PBM terminal device's built-in accelerometer and gyroscope collect real-time acceleration and angular velocity data in three-dimensional space. An attitude calculation algorithm then calculates the device's pitch, roll, and yaw angles. The device compares the current pitch and roll angles with preset correct attitude angle ranges. The preset correct attitude requires the device's light output plane to be approximately parallel to the user's face plane, with the pitch angle within -10 to +10 degrees and the roll angle within -15 to +15 degrees. When the pitch or roll angle exceeds the preset range, the device is deemed to have deviated from the correct posture. The device immediately pauses the illumination timing and triggers a voice prompt unit to play a voice command such as "Please keep the device level," while simultaneously recording an interruption event. When the device's attitude returns to the preset range, the illumination timing resumes.

[0054] When recording effective illumination duration, number of interruptions, interruption duration, and usage location to obtain usage time, the PBM terminal device maintains a timing state machine using a time recorder. Effective illumination duration is accumulated starting from the moment when three conditions are simultaneously met: the user's eyes are aligned, their eyes are open normally, and the device is in the correct orientation. Accumulation is paused when any condition is not met, and the number of interruptions and the duration of each interruption are recorded. The usage time recorder also obtains usage location information through the device's built-in positioning module. The positioning module can use GPS or network positioning to record the latitude and longitude coordinates of the usage location at the start of each use.

[0055] For example, during a complete usage session, the time recorder recorded an effective irradiation duration of 2 minutes and 45 seconds, with two interruptions. The first interruption lasted 8 seconds, and the second lasted 7 seconds. The device also recorded the latitude and longitude coordinates of the usage location as a street in a specific city. The device integrates this data into structured usage duration data, including effective irradiation duration, number of interruptions, a list of interruption durations, and usage location, and uploads this data to the cloud server as part of the usage monitoring data.

[0056] Through the collaborative work of multiple sensors and refined data acquisition, the system can accurately distinguish between actual effective illumination time and invalid time caused by various interferences, ensuring that the detection data truly reflects the user's actual performance quality. The combination of an eye proximity sensor and a pupil detection algorithm ensures that effective usage time is only counted when both eyes are correctly aligned with the light path, preventing idle operation or incorrect illumination. A blink detection sensor can identify illumination interruptions caused by blinking or eye closure, ensuring that illumination only occurs when the user's eyes are open. The coordination of a tilt sensor and voice prompts can promptly correct the user when the device's posture is incorrect, ensuring that the illumination direction always meets preset requirements. Detailed recording of effective illumination time, number of interruptions, interruption duration, and usage location provides rich, granular data for subsequent compliance analysis, enabling compliance evaluation to go beyond simple usage counts and reflect the completeness and standardization of the usage process.

[0057] In one possible embodiment, a reminder notification is sent to the monitoring terminal before the planned usage time, and if no effective usage is detected after the planned usage time, a tiered reminder mechanism is activated. The tiered reminder mechanism includes at least one of the following: After the scheduled time has elapsed for a first preset period, a first reminder message will be sent to the monitoring device. Delay for a second preset time and send a second reminder message to the monitoring terminal; Delay for a third preset time, mark the current session as incomplete, and update the compliance indicator data; If the compliance indicator data fails to reach the preset compliance threshold for N consecutive days, a notification message will be sent to the doctor.

[0058] The planned usage time refers to the preset time or period for daily photobiological conditioning operations based on the user's individual circumstances. The monitoring terminal refers to the application client running on the mobile terminal device used by the parent or guardian to receive various notifications and information related to the user. Effective use refers to the user completing a single photobiological conditioning operation according to preset requirements, specifically including correct eye alignment, keeping eyes open, correct device posture, and achieving the prescribed effective irradiation duration. The tiered reminder mechanism refers to the use of different intensities and methods of reminders based on the duration of non-use or the degree of non-compliance.

[0059] The first, second, and third preset durations are three progressively increasing time intervals used to differentiate the severity of non-use. The first and second reminder messages refer to different forms of notification content, differing in reminder method, urgency of wording, or delivery channel. "N consecutive days" refers to N uninterrupted calendar days, where N is a preset positive integer. The preset compliance threshold refers to the minimum acceptable standard for compliance indicators. Attention alert messages are notifications sent to the doctor's end to alert the user to a compliance risk.

[0060] When sending a reminder notification to the monitoring device before the planned usage time, the cloud server calculates the lead time based on the user's daily planned usage time, generates a reminder notification, and sends it to the monitoring device application via push service. For example, if the user's daily planned usage time is 8:00 AM and 8:00 PM, the cloud server will send reminder notifications to the monitoring device application at 7:55 AM and 7:55 PM respectively. The notification content includes the upcoming planned usage time and a prompt encouraging the user to use the device on time. After receiving the reminder notification, the monitoring device application displays the reminder information in the mobile device's notification bar and can use vibration or a notification sound to enhance the reminder effect.

[0061] If no valid usage is detected after the planned usage time, a tiered reminder mechanism is activated. The cloud server continuously receives usage detection data uploaded by the PBM terminal device. After the planned usage time arrives, a timer is started to monitor whether the plan has been executed. If, after a first preset time period (e.g., 30 minutes) has elapsed since the planned usage time, the cloud server still has not received a corresponding valid usage record, a first-level reminder is triggered, sending a first reminder message to the monitoring device. The first reminder message can be sent via in-app push notification, with a message such as "30 minutes of planned usage time have passed, and no usage record has been detected. Please remind your child to complete the task as soon as possible." If, after a second preset time period (e.g., 60 minutes) has elapsed since the planned usage time, the cloud server still has not received a valid usage record, a second-level reminder is triggered, sending a second reminder message to the monitoring device.

[0062] The second reminder message differs from the first in its notification method. It can be sent via SMS push notification to ensure that parents still receive the reminder even with poor network connectivity or when the application is not running. The notification content could be something like, "60 minutes of the planned usage time has passed, and today's usage has not yet been completed. Please urge the user to finish using the app." If, after a third preset time period (e.g., 120 minutes) has elapsed and the cloud server still has not received a valid usage record, the third level of processing is triggered. The plan is marked as incomplete, and the user's compliance indicator data is updated based on this status. Specifically, the planned usage count for the day is included in the denominator calculation, but the actual usage count does not increase, resulting in a corresponding decrease in the usage frequency indicator. Simultaneously, the consecutive usage days are interrupted and the count restarts.

[0063] If a user's compliance metrics fail to reach a preset compliance threshold for N consecutive days, a notification is sent to the doctor's end. The cloud server calculates a user's comprehensive compliance score daily, which can be a weighted average of usage frequency, on-time performance, and completion rate. The preset compliance threshold is set at 80%. The cloud server maintains a counter for consecutive non-compliance scores; the counter increments when the daily compliance score falls below 80% and resets when it reaches or exceeds 80%. When the counter reaches a preset value of N (e.g., 3 consecutive days), the cloud server determines that the user has a continued compliance risk, generates a notification, and pushes it to the doctor's platform. The notification may include the user's identifier, the number of consecutive non-compliance days, recent compliance metrics data, and an explanation of the reason for the notification. Upon receiving the notification, the doctor's platform marks the user as a high-priority case in the doctor's management interface, allowing doctors to intervene promptly, understand the situation, and provide guidance.

[0064] The tiered reminder mechanism implements a progressive response strategy, ranging from gentle reminders to strong interventions. This avoids excessive disruption to parents while allowing for timely escalation of reminders when compliance risks increase. Reminders before planned usage times help cultivate users' time regularity and reduce the probability of forgetting. The first reminder is sent via app push notifications, and the second via SMS, ensuring reliable delivery. The third mechanism, marking incomplete tasks and updating indicators after a preset time, guarantees the authenticity and continuity of compliance metrics, preventing data distortion. When compliance is not met for several consecutive days, a notification is sent to the doctor, enabling timely professional guidance and preventing a further decline in compliance. This implementation dynamically links the reminder mechanism with compliance indicators, forming a complete closed loop from monitoring and reminders to intervention, effectively improving the timeliness of parental supervision and the targeted nature of doctor intervention.

[0065] In one possible embodiment, the user's periodic ophthalmological examination data for the PBM terminal device is acquired, and the ophthalmological examination data includes axial length and refractive error. The ophthalmological examination data and the compliance indicators are correlated to generate correlation analysis information between compliance and efficacy; the compliance report also includes the correlation analysis information.

[0066] Regular eye exam data refers to the objective measurement results obtained from eye exams conducted by users at professional institutions at preset time intervals. Axial length, the linear distance between the anteroposterior diameter of the eyeball, is usually measured in millimeters and is one of the core objective indicators for assessing myopia progression. Refractive power is a measure of the eye's optical system's ability to refract light, usually expressed in diopters, reflecting the degree of myopia, hyperopia, or astigmatism. Correlation analysis refers to the process of establishing a correspondence between compliance index data and eye exam data and performing statistical analysis. Correlation analysis information refers to the analytical results obtained through correlation analysis that reflect the relationship between compliance indicators and myopia progression indicators, used to illustrate the degree of correlation between compliance level and intervention effect.

[0067] When acquiring users' regular eye examination data from PBM terminal devices, the cloud server establishes a connection with the information system of the ophthalmology examination institution through a data interface, and automatically synchronizes the user's examination records after authorization. The cloud server also supports manual data entry, allowing parents to upload images of the user's recent eye examination reports or manually fill in the examination results through the monitoring application. Axial length data specifically includes the left and right axial lengths, for example, the left axial length is 24.15 mm and the right axial length is 24.22 mm. Refractive error data specifically includes spherical power, cylindrical power, and axis information, for example, the left spherical power is -2.25 diopters and the cylindrical power is -0.50 diopters, and the right spherical power is -2.00 diopters and the cylindrical power is -0.25 diopters. The cloud server creates a time series of eye examination data for each user, recording the date of each examination and various measurement values.

[0068] When performing correlation analysis between ophthalmological examination data and adherence indicators to generate correlation analysis information between adherence and treatment efficacy, the cloud server aligns the user's adherence indicator data with the ophthalmological examination data along the time dimension, constructing a data sequence with time as the axis. Specifically, the cloud server extracts the average adherence indicator within a time window before and after each ophthalmological examination date, and pairs this adherence indicator with the axial length and refractive error data on that examination date.

[0069] The cloud server calculates the rate of axial length growth between two consecutive eye exams, measured in millimeters per year, and also calculates the average compliance score during this period. For example, if a user's axial length was 24.10 mm at their first exam and 24.22 mm three months later at their second exam, the axial length increased by 0.12 mm in three months, which translates to an annual growth rate of 0.48 mm per year. The user's average compliance score during this period is 92%. The cloud server then aggregates all paired data from all users, groups them according to their compliance scores, and generates correlation analysis information.

[0070] Correlation analysis information can include a scatter plot showing the relationship between adherence scores and annual axial length growth rate, visually illustrating the trend of the correlation between the two. Correlation analysis information can also include statistical results of axial length growth rate grouped by adherence scores; for example, users with adherence scores greater than 90% have an average annual axial length growth rate of 0.35 mm per year; users with adherence scores between 70% and 90% have an average annual axial length growth rate of 0.52 mm per year; and users with adherence scores less than 70% have an average annual axial length growth rate of 0.68 mm per year.

[0071] Correlation analysis information can also include longitudinal comparisons at the individual level, such as comparing fluctuations in user compliance with changes in axial length growth rate. For example, when a user's compliance score in a given quarter increases by 15% compared to the previous quarter, it corresponds to the extent that the axial length growth rate slows down compared to the previous quarter. Correlation analysis information can also include correlation coefficient calculation results, such as using the Pearson correlation coefficient to calculate the strength and direction of the correlation between compliance score and axial length growth rate.

[0072] When incorporating correlation analysis information into adherence reports, the cloud server, in generating the reports, integrates the aforementioned correlation analysis information in addition to basic adherence indicators such as usage frequency, on-time rate, completion rate, and consecutive days of use. The adherence report displays the relationship between adherence scores and axial length growth rate in the form of visual charts, allowing parents and doctors to intuitively observe the correlation between adherence levels and the rate of myopia progression. The adherence report can also include individualized interpretations for each user, such as indicating the expected range of axial length growth rate corresponding to the user's current adherence score, and the expected axial length control effect if the adherence score is increased to a higher target value, based on the user's correlation analysis results.

[0073] By correlating adherence indicators with ophthalmological examination data, a leap from simple process monitoring to a combined process and outcome analysis was achieved. Axial length and refractive error are core objective indicators for assessing myopia progression. Linking these with adherence indicators allows adherence reports to reflect the intrinsic connection between adhered behavior and actual intervention effectiveness. Correlation analysis information, presented in a data-driven manner, demonstrates the quantitative relationship between adherence levels and myopia control effectiveness to parents and doctors, providing strong evidence-based support for adherence management. Parents can intuitively understand the importance of consistent use through correlation analysis information, thereby enhancing their initiative and persistence in monitoring. Doctors can use correlation analysis information to stratify users with different adherence levels and provide more targeted guidance to users with poor adherence.

[0074] In the embodiments of this application, by acquiring usage detection data of the photobiological modulation PBM terminal device during use, the usage detection data includes at least one of the following: eye alignment state, blinking state, device posture, and usage duration; an objective record of the user's photobiological modulation operation process is achieved, providing a real and reliable data foundation for subsequent analysis. The compliance metrics are calculated based on the detection data. These compliance metrics include at least one of the following: usage frequency, on-time rate, completion rate, and consecutive days of use. The original usage behavior data is transformed into quantifiable and comparable numerical metrics, enabling standardized evaluation of user performance and facilitating horizontal and vertical comparative analysis across different time points and among different users. The compliance metric data is grouped and aggregated according to preset time windows, calculating the statistical values ​​of compliance metrics within each time window, establishing a mapping relationship between compliance metrics and timestamps, and generating a compliance metric dataset with a time-series structure. Discrete usage records are converted into structured data with a time dimension. A compliance report is generated based on the compliance metric dataset, presenting the specific values ​​of compliance metrics through a numerical display area, showing the changing patterns of compliance metrics over time through trend graphs, and highlighting time points of significant compliance changes by identifying and labeling compliance fluctuation nodes. This allows for a direct understanding of the current state of compliance, historical trends, and key change nodes.

[0075] Figure 2 This is a schematic diagram of a compliance monitoring system provided in an embodiment of this application.

[0076] like Figure 2 As shown, the compliance monitoring system is specifically as follows: PBM terminal device 210 includes a light source module, a usage detection module, a data communication module and a user interaction module. The usage detection module is used to collect eye alignment status, blinking status and device posture during use. The data communication module is used to upload the usage detection data to a cloud server. The cloud server 220 is configured to receive and store the usage detection data, establish a usage record database for each user, and calculate compliance indicators. The monitoring application 230 is configured to view the user's usage records and compliance reports in real time, receive reminder notifications, set reminder methods, and communicate online with the doctor. The doctor-side platform 240 is configured to view the compliance scores of the users it manages.

[0077] Among them, PBM terminal device 210 refers to the hardware device used to perform photobiological regulation operations, serving as the source and execution terminal for data acquisition. The light source module refers to the component unit that generates light radiation of a specific wavelength, providing the light energy required for photobiological regulation. The usage detection module refers to the functional unit integrating multiple sensors, used to collect behavioral data during use in real time. The data communication module refers to the component unit responsible for data transmission and network connection, enabling data interaction between the device and the cloud. The user interaction module refers to the component unit that provides a human-machine interface, used to display information to the user and receive operation commands. The cloud server 220 refers to the computing resources and service platform deployed in the cloud, used for centralized storage, processing, and analysis of data.

[0078] Usage record database refers to a structured collection of data independently established for each user to store historical usage data. Compliance risk refers to the probability or trend that a user may fail to perform operations as preset requirements, as determined based on usage monitoring data. Monitoring application 230 refers to a software program running on the mobile terminal of a parent or guardian, providing various functions related to user management. Reminder methods refer to the technical means used by the monitoring application to deliver notification information to parents, including push notifications, SMS, and in-app messages. Online communication refers to two-way real-time or asynchronous information exchange via the internet. Doctor platform 240 refers to a software system running on the terminal of a medical institution or professional, used to centrally manage compliance data of multiple users. Compliance score refers to a single numerical comprehensive evaluation result calculated based on compliance indicators.

[0079] In the PBM terminal device 210, the light source module includes an LED light source array and a light power control circuit. The LED light source array consists of multiple light-emitting diodes that emit red light with wavelengths ranging from 630 nanometers to 680 nanometers. The light power control circuit stabilizes the output power density within the range of 8 milliwatts per square centimeter to 50 milliwatts per square centimeter through a closed-loop feedback mechanism, ensuring the safety and consistency of the light output. The detection module includes an eye proximity sensor, a blink detection sensor, a device tilt sensor, and a usage time recorder. The eye proximity sensor combines an infrared distance sensor with an image sensor. The infrared distance sensor detects the distance between the eye and the device's light output port, while the image sensor acquires an image of the eye and uses a pupil detection algorithm to confirm whether the eyes are correctly aligned. The blink detection sensor uses an infrared reflective sensor to determine the eyelid opening and closing state by monitoring changes in the intensity of the reflected signal. The device tilt sensor uses a combination of an accelerometer and a gyroscope to collect the device's angle data in three-dimensional space in real time. A time recorder is used to record the effective illumination duration, number of interruptions, interruption duration, and usage location. The data communication module includes a wireless communication unit and a local data buffer. The wireless communication unit supports both WiFi and Bluetooth wireless communication protocols. When the device is within network coverage, it automatically uploads the detection data to the cloud server 220 via the wireless communication unit. When the network is unavailable, the local data buffer temporarily stores the detection data in the device's local memory. Once the network is restored, a retransmission mechanism is automatically triggered to ensure that the data is not lost. The data communication module also includes a device authentication unit. Through a unique device identifier and digital certificate stored in a security chip, it performs two-way authentication with the cloud server 220 during each communication to prevent unauthorized device access and data tampering.

[0080] The user interaction module includes a display screen and a voice prompt unit. The display screen uses a color LCD screen to show the usage status, remaining time, and incentive information when the device is working. The voice prompt unit plays voice guidance prompts when the device is in the wrong position and plays encouraging sound effects after use.

[0081] In the cloud server 220, a data receiving interface is deployed to continuously receive usage monitoring data uploaded from multiple PBM terminal devices 210. The cloud server 220 establishes an independent usage record database for each user, storing raw monitoring data for each use in chronological order, including eye alignment status, blinking status, device posture, effective irradiation duration, number of interruptions, interruption duration, usage location, and start and end times. Based on the stored usage monitoring data, the cloud server 220 calculates compliance indicators, specifically including usage frequency, on-time rate, completion rate, and consecutive usage days. While calculating compliance indicators, the cloud server 220 identifies compliance risks by analyzing users' historical usage patterns. For example, if a user repeatedly fails to complete the planned usage within the allotted time, the usage frequency shows a continuous downward trend, or the completion rate falls below a preset threshold, the cloud server 220 marks the user as having compliance risks and triggers subsequent intervention procedures.

[0082] In the monitoring application 230, which runs on the parent's smartphone or tablet, data is exchanged with the cloud server 220 via the network. The main interface of the monitoring application 230 displays the user's usage status for the day, including whether the planned usage has been completed, the last usage time, and the cumulative number of consecutive usage days. Parents can view the user's usage record list in real time through the monitoring application 230. The list displays the start time, effective exposure duration, and completion status of each usage session by date. Clicking on a single record allows viewing detailed data, including the number of interruptions, the duration of the interruption, and the usage location.

[0083] The compliance report module of the monitoring app 230 displays trends in user compliance indicators in chart form, including a weekly trend chart of usage frequency, a distribution chart of on-time usage rate, and a calendar view of consecutive days of use. In the reminder settings interface, parents can customize daily planned usage times, choosing two different times such as 8:00 AM and 8:00 PM. They can also set reminder methods, including enabling push notifications, enabling SMS reminders, and specifying the mobile phone number to receive reminders. The monitoring app 230 also integrates online communication functionality, allowing parents to communicate with doctors in real-time via text, images, or voice messages. After regular eye exams, parents can also send images of the exam reports to the doctor's platform 240 with a single click through the monitoring app 230, enabling doctors to promptly understand the user's myopia progression.

[0084] In the doctor-side platform 240, which runs on workstations in medical institutions or doctors' mobile devices, a centralized multi-user management function is provided. The main interface of the doctor-side platform 240 displays a list of all users managed by the doctor. Each user entry in the list displays the user's basic information, the comprehensive adherence score for the most recent week, and the adherence risk level. Doctors can quickly locate users whose adherence scores are below a preset threshold using the filtering function. For example, after clicking the filter button, the system will only display users whose comprehensive adherence scores are below 70%.

[0085] After clicking on a single user entry, the doctor is taken to a details page displaying the user's comprehensive adherence data, including usage frequency, on-time performance, completion rate, consecutive days of use, and weekly trend charts for each indicator. The 240 doctor-side platform also provides time-series graphs of adherence scores, allowing doctors to view the curve of a user's adherence score changes from their first use to the present, identifying key time points of adherence fluctuations. For users with consistently low or significantly declining adherence scores, doctors can record notes and concerns through the 240 doctor-side platform, or use the adherence data to communicate specifically with parents during follow-up visits.

[0086] By collaborating across four components—PBM terminal devices, cloud servers, monitoring applications, and doctor-side platforms—a complete technology chain has been constructed, encompassing data collection, storage, visualization, and application. The PBM terminal devices, as the data source, utilize multi-sensor fusion to achieve refined collection of user behavior, ensuring data objectivity and accuracy. The cloud server, as the data hub, establishes an independent database for each user, enabling centralized data storage and automated calculation of adherence indicators, while also providing triggers for subsequent interventions through adherence risk identification. The monitoring application, serving as an information window for parents, transforms professional data into easily understandable visual reports, providing flexible reminder settings and convenient doctor-patient communication channels, reducing the monitoring burden on parents. The doctor-side platform, as a management tool for professionals, supports centralized viewing and screening of adherence data from multiple users, improving doctors' management efficiency. This embodiment achieves full-process coverage of adherence monitoring from data collection to terminal application, with clearly defined functions and reasonable division of labor among each component, forming a complete technical solution.

[0087] In one possible embodiment, the detection module includes: An eye proximity sensor is configured to detect whether the distance between the user's eyes and the device is within an effective range; A blink detection sensor is configured to detect blinking during the treatment process; The device tilt sensor is configured to detect whether the device is in the correct operating position; Using a time recorder, it is configured to record the start time, end time, effective usage duration, number of interruptions, and interruption duration for each use.

[0088] Among them, the eye proximity sensor refers to a combination of sensing elements that detect the proximity of objects through physical principles, used to determine the spatial distance between the user's eyes and the device's light output port. The effective range refers to a preset distance interval that ensures both illumination effect and safety; this interval is determined comprehensively based on the light spot size, illumination intensity, and eye safety standards. The blink detection sensor refers to a sensing element used to monitor the opening and closing of the eyelids in real time, determining whether the eyes are open or closed by detecting changes in the eyelids' obstruction or reflection of light signals. The usage process refers to the complete time period from when the user begins performing photobiological modulation operations to when the operations end. The device tilt sensor refers to a sensing element used to detect the angle and orientation of the device relative to the direction of gravity or a preset reference plane in space, typically composed of an accelerometer and a gyroscope.

[0089] Correct usage posture refers to the preset orientation and angle range of the device in space. In this posture, the light emission direction matches the user's line of sight, ensuring that the light energy accurately reaches the target area. A time recorder is an electronic module or software unit used for timing and recording time-related data, responsible for maintaining the time state machine during use. Start time refers to the moment the user starts the device and begins performing photobiological modulation. End time refers to the moment the user completes the photobiological modulation operation. Effective usage duration refers to the cumulative time the user actually receives photobiological modulation irradiation, excluding interruptions. Number of interruptions refers to the number of times irradiation is interrupted during use due to factors such as eye alignment failure, eye closure, or device posture deviation. Interruption duration refers to the length of time from the occurrence of each interruption event to its resumption.

[0090] The eye proximity sensor employs a dual-mode detection architecture combining an infrared distance sensor and an image sensor. The infrared distance sensor consists of an infrared emitter and an infrared receiver. The emitter emits modulated infrared light signals towards the user's eyes, while the receiver receives the infrared light reflected back from the eye tissue. The distance between the eye and the device's light output port is calculated by measuring the time difference between emission and reception or the change in reflected light intensity. The image sensor uses a miniature camera module to acquire image data of the user's eye area under infrared illumination. Image processing algorithms identify the position of both eyes in the image. The infrared distance sensor and image sensor work together. When the distance detected by the infrared distance sensor is within a preset effective range, such as 30 mm to 50 mm, the image sensor initiates eye image acquisition and executes a pupil detection algorithm to confirm whether the center of both pupils is aligned with the center of the device's optical path. If the distance exceeds the effective range or the pupil detection fails, the eye proximity sensor outputs an alignment failure signal, the device pauses illumination, and an interruption event is recorded.

[0091] For example, when the user brings the device close to a distance of 25 mm, the infrared distance sensor detects that the distance is too close, and the eye proximity sensor outputs a distance abnormality signal; when the user moves the device away to a distance of 55 mm, the infrared distance sensor detects that the distance is too far, and the eye proximity sensor also outputs a distance abnormality signal; when the user keeps both eyes at a distance of 40 mm and the center of the pupil is aligned with the center of the light path, the eye proximity sensor outputs an alignment valid signal, and the device begins to accumulate effective irradiation time.

[0092] The blink detection sensor employs an infrared reflection detection principle, consisting of an infrared emitting diode and an infrared receiving diode. The emitting diode emits infrared light of a specific frequency towards the user's eyeball, while the receiving diode receives the infrared light signal reflected from the eye's surface. When the user's eyes are open, the infrared light undergoes specular reflection on the moist cornea and sclera, resulting in a high and stable reflected signal intensity. When the user's eyes are closed, the infrared light is absorbed and scattered by the eyelid skin, significantly reducing the reflected signal intensity. The blink detection sensor integrates a signal conditioning circuit that converts the reflected signal intensity into a digital value and compares it with preset open and closed eye thresholds.

[0093] When the intensity of the reflected signal is higher than the eye-opening threshold, it is determined to be in an open-eye state; when it is lower than the eye-closing threshold, it is determined to be in a closed-eye state. The blink detection sensor outputs a status signal in real time. When it detects that the closed-eye state lasts for more than a preset duration, such as 2 seconds, it is determined to be an abnormal eye closure, and an abnormal blink status signal is output. The device pauses the irradiation timer and records an interruption event. When the intensity of the reflected signal recovers to above the eye-opening threshold, a normal blink status signal is output, and the device resumes the irradiation timer. For example, if a user closes their eyes to rest due to fatigue during irradiation, and the closed eyes last for 3 seconds, the blink detection sensor will trigger an abnormal signal when the closed eyes last for 2 seconds. The device will pause the timer. After the user reopens their eyes and the signal is detected to have recovered, the device will continue to accumulate the effective irradiation time and record the interruption duration as 3 seconds.

[0094] The device tilt sensor employs a six-axis inertial measurement unit (IMU), which integrates a three-axis accelerometer and a three-axis gyroscope. The three-axis accelerometer measures the linear acceleration components of the device along the X, Y, and Z axes, and calculates the device's pitch and roll angles by decomposing the gravitational acceleration onto the three axes. The three-axis gyroscope measures the device's angular velocity around the three axes, compensating for accelerometer angle measurement errors under dynamic conditions through integration calculations, thus improving the accuracy and response speed of attitude detection. The tilt sensor internally runs an attitude calculation algorithm, fusing the accelerometer and gyroscope data to output the device's current pitch and roll angles. The preset correct operating posture requires a pitch angle within the range of -10 to +10 degrees and a roll angle within the range of -15 to +15 degrees.

[0095] The device's tilt sensor monitors angle data in real time. When the pitch or roll angle exceeds the preset range, it determines that the device's posture has deviated from the correct usage position, outputs a posture abnormality signal, pauses the illumination timer, and simultaneously plays a posture correction prompt via the voice prompt unit, recording an interruption event. When the angle data recovers to the preset range and remains stable for more than a preset stable time (e.g., 1 second), it outputs a posture normality signal, and the device resumes the illumination timer. For example, if the user tilts the device downwards during illumination, causing the pitch angle to reach -18 degrees, the device's tilt sensor will detect the angle exceeding the limit and immediately trigger a posture abnormality signal. The device will pause the timer and play a voice prompt saying "Please lift the device upwards." After the user adjusts the device's posture to a pitch angle of -5 degrees, the device will resume the timer and record the interruption duration as 4 seconds.

[0096] In the time recorder, a timing state machine is built based on the microcontroller's internal hardware timer. This state machine includes a running state, a paused state, and a stopped state. When three conditions are simultaneously met—the eye proximity sensor outputs a valid alignment signal, the blink detection sensor outputs a normal eye-opening signal, and the device tilt sensor outputs a normal posture signal—the timing state machine enters the running state, and the hardware timer begins to accumulate and count, recording the effective usage time. When any condition is not met, the timing state machine switches to the paused state, the hardware timer stops accumulating, and this pause is recorded as an interrupt event. An interrupt duration timer is then started to record the duration of this interrupt.

[0097] When all conditions are met simultaneously again, the timing state machine resumes operation, the hardware timer continues to increment, the interrupt duration timer stops recording, and the interrupt duration is stored in the interrupt duration list. When the user manually shuts down the device or the device stops automatically, the timing state machine enters a stopped state. A time recorder combines the start time, end time, effective usage duration, number of interrupts, and the interrupt duration list into a structured usage time record. The start time is recorded as the timestamp when the device detects the first fulfillment of the three conditions, and the end time is recorded as the timestamp when the device stops running or when consecutive interruptions exceed a preset termination duration after the last fulfillment of the three conditions.

[0098] By combining an eye proximity sensor, a blink detection sensor, a device tilt sensor, and a usage time recorder, comprehensive data collection of key behavioral parameters during photobiological modulation is achieved. The eye proximity sensor ensures that the user's eyes are within a range where they can effectively receive illumination, avoiding reduced illumination effectiveness or safety hazards caused by improper distance. The blink detection sensor can detect brief periods of eye closure during use, ensuring that illumination only occurs when the user's eyes are open, avoiding ineffective illumination caused by eyelid obstruction.

[0099] The device's tilt sensor ensures it maintains the correct posture throughout use, guaranteeing accurate projection of light energy onto the target area, and provides real-time correction via voice prompts. A time recorder, through sophisticated state machine management, accurately distinguishes between effective illumination duration and various interruption durations, ensuring that the usage data truly reflects the user's actual performance quality, rather than simply recording device uptime. Four sensors work collaboratively to form a mutually verifying detection network; any failure to meet any condition triggers an interruption and recording, ensuring the authenticity and completeness of the usage data and providing a reliable data foundation for the accurate calculation of subsequent compliance indicators.

[0100] In one possible embodiment, the monitoring application further includes: The incentive module is configured to issue virtual points after each use and output a virtual badge when the user uses the service for a target number of consecutive days. The adherence prediction module is configured to analyze users' historical usage patterns, predict adherence risk data within a preset time period, and push preventive intervention information based on the adherence risk data.

[0101] The incentive module refers to the software functional unit in the monitoring application responsible for implementing positive reinforcement mechanisms, using gamification to enhance users' initiative and participation. Virtual points are reward points represented in numerical form, accumulated by users after completing specified actions; the number of points reflects the user's activity level and persistence. Target days refer to a preset threshold for consecutive usage days; special rewards are triggered when the user reaches this threshold. Virtual badges are honorary symbols presented graphically, used to mark specific achievements; different achievements correspond to different styles of virtual badges.

[0102] The adherence prediction module refers to the software functional unit in the monitoring application responsible for performing risk prediction and preventive intervention. It models and analyzes future adherence change trends based on historical data. Historical usage patterns refer to the set of user behavior characteristics over a past period, including the temporal distribution of usage frequency, fluctuations in on-time performance, and stability of completion rates. The future preset timeframe refers to a specific time window from the current moment forward, such as the next week or the next month. Adherence risk data refers to the quantitative assessment results of the probability or severity of a decline in adherence that may occur within the predicted future preset timeframe. Preventive intervention information refers to reminders, suggestions, or incentives generated in advance based on risk prediction results, aiming to reduce the likelihood of actual adherence risks occurring.

[0103] In the incentive module, a virtual points account is maintained, which is bound to the user's identity. Points change records are stored on a cloud server and can be synchronized to the monitoring application interface. The incentive module obtains the user's usage completion status through a data synchronization mechanism between the monitoring application and the cloud server. When the cloud server receives the usage detection data uploaded by the PBM terminal device and confirms a valid usage completion, the cloud server sends a points issuance instruction to the incentive module. The incentive module then adds the corresponding number of virtual points to the user's virtual points account according to preset points rules.

[0104] For example, the preset points system allows users to earn ten virtual points for each successful single use. If a user uses the service twice a day, morning and evening, they will earn twenty virtual points for that day. The incentive module displays the point accumulation process with animations and sound effects on the monitoring application's interface, and the total points are updated in real-time and displayed prominently on the screen. Virtual points can be redeemed for virtual items or physical rewards. The incentive module includes a built-in points redemption shop, which displays available items and their required points, allowing users or their parents to choose which items to redeem.

[0105] The incentive module also maintains a continuous usage counter, which records the number of consecutive days a user has used the service without interruption. The cloud server updates the continuous usage days daily based on usage monitoring data. When a user completes at least one valid use session on a given day, the continuous usage days are incremented by one day; if there are no valid usage records for a day, the continuous usage days are reset to zero and the counting restarts. The incentive module allows setting multiple target continuous usage days, such as three days, seven days, fourteen days, and thirty days, with each target number corresponding to a uniquely designed virtual badge.

[0106] When a user's consecutive usage days reach any target number for the first time, the incentive module triggers a virtual badge issuance event, unlocking the corresponding badge in the user's badge collection and displaying the badge image and achievement name in a pop-up animation on the monitoring application interface. For example, when a user achieves seven consecutive days of use for the first time, the incentive module issues a gold star-shaped badge with the achievement name "Star of the Week" displayed below it; when a user achieves thirty consecutive days of use for the first time, the incentive module issues a diamond-shaped badge with the achievement name "Full Moon Master" displayed below it. All obtained virtual badges are permanently displayed on the badge wall interface, while unobtained badges are displayed with a gray outline and the unlocking conditions indicated, providing users with clear goal guidance.

[0107] In the adherence prediction module, historical usage data sequences of users are retrieved from the cloud server. These sequences contain daily adherence-related parameters for the past ninety days, specifically including whether usage was completed that day, the deviation between the completion time and the planned time, the completion rate of a single use, and the number of consecutive days of use. The adherence prediction module uses time series analysis to analyze the historical data, identifying patterns in user behavior and abnormal fluctuations. For example, the module may find that users' completion rates are significantly higher on weekdays than on weekends, or that there are consecutive periods of non-use during illness, or that usage time shifts occur around exam weeks.

[0108] The compliance prediction module constructs a predictive model based on analyzed historical usage patterns. This model uses periodic characteristics, trend characteristics, and the impact of abnormal events in historical usage data as input variables, and outputs compliance risk data for a predetermined period, such as the next seven days. Compliance risk data can include daily predicted non-use probability values, predicted compliance scores, and risk level classifications. For example, the compliance prediction module predicts that the probability of non-use on Saturdays and Sundays will be 65% and 70% respectively, with predicted compliance scores of 55 and 50 points respectively, thus marking Saturdays and Sundays as medium-to-high risk days; the predicted non-use probability values ​​for weekdays will all be below 30%, with predicted compliance scores above 75 points, marking them as low-risk days.

[0109] The adherence prediction module automatically matches preventative intervention information with the predicted adherence risk data and pushes it to parents through the monitoring application at appropriate times. The content and timing of the preventative intervention information are matched with the predicted risk type and risk level. For example, for a predicted high-risk situation on weekends, the adherence prediction module pushes preventative intervention information to the monitoring application on Friday evening, with the message: "Based on recent usage patterns, weekend adherence may decrease. It is recommended to agree on usage times with your child in advance and set reminders."

[0110] In response to a predicted continuous decline in adherence over several days, the adherence prediction module pushes intervention information as soon as the decline is detected. The information reads, "Recent usage frequency has shown a downward trend. It is recommended to check for device problems or the child's resistance and adjust the usage schedule accordingly." For predicted high-risk situations during specific time periods, such as holidays, the adherence prediction module pushes preventative intervention information before the holiday begins. The information reads, "The holiday is about to begin. It is recommended to maintain regular usage habits and set a fixed daily alarm reminder."

[0111] By leveraging the synergy between the incentive module and the adherence prediction module, comprehensive management of user adherence is achieved from two dimensions: positive incentives and risk prevention. The incentive module, through gamification mechanisms using virtual points and virtual badges, transforms what would otherwise be monotonous, repetitive usage behaviors into engaging activities with immediate feedback and achievement accumulation. Virtual points provide short-term incentives, while virtual badges offer long-term goals; the combination effectively enhances users' intrinsic motivation and willingness to persist. The adherence prediction module, through intelligent analysis of historical usage patterns, can proactively identify trends of declining adherence, rather than passively responding only after adherence deteriorates. Predicting adherence risk data within a preset timeframe allows for precise delivery of preventative intervention information to parents. The timing and content of intervention messages are matched to the type of risk, avoiding the fatigue effect of uniform reminders. By upgrading adherence management from passive monitoring to proactive intervention, and expanding from single-minded supervision to a comprehensive strategy emphasizing both incentives and prevention, the effectiveness and foresight of adherence management are significantly improved.

[0112] In the embodiments of this application, the PBM terminal device uses a detection module to collect eye alignment, blinking status, and device posture, and a data communication module uploads the usage detection data to a cloud server, realizing automated collection and remote transmission of usage data. The cloud server receives and stores the usage detection data, establishes an independent usage record database for each user, and calculates compliance indicators, realizing centralized management of multi-user data and automated calculation of compliance indicators, providing a unified data foundation for subsequent data query and analysis. The monitoring application can view the user's usage records and compliance reports in real time, receive reminder notifications, and set reminder methods, enabling parents to keep track of the user's performance at any time and flexibly configure reminder strategies according to their own needs, solving the problems of delayed parental understanding of usage and limited reminder methods. The monitoring application communicates online with the doctor's end, providing a convenient information exchange channel between parents and professionals, solving the problem of low efficiency in traditional communication methods. The doctor's platform can view the compliance scores of the managed users, enabling doctors to quickly screen and locate users with poor compliance, improving the efficiency of centralized management of multiple users.

[0113] The compliance monitoring method provided in this application can be implemented by a compliance monitoring device. This application uses a compliance monitoring device to implement the compliance monitoring method as an example to illustrate the compliance monitoring device provided in this application.

[0114] Figure 3 This is a block diagram of a compliance monitoring device provided in an embodiment of this application. The device 300 includes: The acquisition module 310 is used to acquire usage detection data of the photobiological regulation PBM terminal device during use. The usage detection data includes at least one of the following: eye alignment status, blinking status, device posture, and usage duration. The calculation module 320 is used to calculate compliance index data based on the usage detection data, wherein the compliance index includes at least one of the following: usage frequency, on-time rate, completion rate, and consecutive usage days; The generation module 330 is used to group and aggregate the compliance index data according to a preset time window, calculate the compliance index statistics within each time window, establish the mapping relationship between compliance index and timestamp, and generate a compliance index dataset containing a time series structure. The generation module 330 is also used to generate a compliance report based on the compliance indicator dataset. The compliance report includes a numerical display area of ​​the compliance indicators, a trend curve of the compliance indicators over time, and compliance fluctuation nodes identified and labeled based on the trend curve.

[0115] In one possible embodiment, the acquisition module 310 is specifically used for: The distance between the user's eyes and the device is detected by an eye proximity sensor to determine whether it is within an effective range, and the correct alignment of the eyes is confirmed by a pupil detection algorithm to obtain the eye alignment status. The blinking state is confirmed by a blink detection sensor, and the timing is paused when the eyes are closed for more than a preset time, so as to obtain the blinking state. The device posture is detected by a tilt sensor. When the posture deviates from the correct posture, the device pauses and issues a voice prompt to obtain the device posture. Record the effective irradiation duration, number of interruptions, interruption duration, and location of use to obtain the usage duration.

[0116] In one possible embodiment, the device 300 includes: The reminder module is specifically used for: A reminder notification is sent to the monitoring device before the planned usage time. If no effective usage is detected after the planned usage time, a tiered reminder mechanism is activated. The tiered reminder mechanism includes at least one of the following: After the scheduled time has elapsed for a first preset period, a first reminder message will be sent to the monitoring device. Delay for a second preset time and send a second reminder message to the monitoring terminal; Delay for a third preset time, mark the current session as incomplete, and update the compliance indicator data; If the compliance indicator data fails to reach the preset compliance threshold for N consecutive days, a notification message will be sent to the doctor.

[0117] In one possible embodiment, the acquisition module 310 is further configured to acquire periodic ophthalmological examination data of the user of the PBM terminal device, the ophthalmological examination data including axial length and refractive power; The device 300 may also include: The analysis module is used to perform correlation analysis between the ophthalmological examination data and the compliance indicators to generate correlation analysis information between compliance and efficacy; the compliance report also includes the correlation analysis information.

[0118] In the embodiments of this application, by acquiring usage detection data of the photobiological modulation PBM terminal device during use, the usage detection data includes at least one of the following: eye alignment state, blinking state, device posture, and usage duration; an objective record of the user's photobiological modulation operation process is achieved, providing a real and reliable data foundation for subsequent analysis. The compliance metrics are calculated based on the detection data. These compliance metrics include at least one of the following: usage frequency, on-time rate, completion rate, and consecutive days of use. The original usage behavior data is transformed into quantifiable and comparable numerical metrics, enabling standardized evaluation of user performance and facilitating horizontal and vertical comparative analysis across different time points and among different users. The compliance metric data is grouped and aggregated according to preset time windows, calculating the statistical values ​​of compliance metrics within each time window, establishing a mapping relationship between compliance metrics and timestamps, and generating a compliance metric dataset with a time-series structure. Discrete usage records are converted into structured data with a time dimension. A compliance report is generated based on the compliance metric dataset, presenting the specific values ​​of compliance metrics through a numerical display area, showing the changing patterns of compliance metrics over time through trend graphs, and highlighting time points of significant compliance changes by identifying and labeling compliance fluctuation nodes. This allows for a direct understanding of the current state of compliance, historical trends, and key change nodes.

[0119] The compliance monitoring device provided in this application embodiment can realize the various processes implemented in the above method embodiment, and will not be described again here to avoid repetition.

[0120] Optionally, Figure 4 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application is shown.

[0121] An electronic device may include a processor 401 and a memory 402 storing computer program instructions.

[0122] Specifically, the processor 401 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0123] Memory 402 may include a large-capacity memory for data or instructions. For example, and not limitingly, memory 402 may include a hard disk drive (HDD), a floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 402 may include removable or non-removable (or fixed) media. Where appropriate, memory 402 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 402 is a non-volatile solid-state memory. In a particular embodiment, memory 402 includes read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0124] The processor 401 implements any of the compliance monitoring methods in the embodiments shown in the figure by reading and executing computer program instructions stored in the memory 402.

[0125] In one example, the electronic device may also include a communication interface 404 and a bus 410. For example, Figure 4 As shown, the processor 401, memory 402, and communication interface 404 are connected through bus 410 and complete communication with each other.

[0126] Communication interface 404 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0127] Bus 410 includes hardware, software, or both, that couples components of an electronic device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 410 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, this application contemplates any suitable bus or interconnect.

[0128] The electronic device can execute the compliance monitoring method in the embodiments of this application, thereby achieving a combination Figure 2 The described compliance monitoring method.

[0129] Furthermore, in conjunction with the compliance monitoring method in the above embodiments, this application embodiment can provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; these computer program instructions are implemented when executed by a processor. Figure 1 Compliance monitoring methods.

[0130] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0131] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0132] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0133] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for monitoring adherence to myopia prevention, characterized in that, include: Acquire usage detection data of the photobiologically regulated PBM terminal device during use, wherein the usage detection data includes at least one of the following: eye alignment status, blinking status, device posture, and usage duration; The compliance indicators are calculated based on the aforementioned usage detection data, and the compliance indicators include at least one of the following: usage frequency, on-time rate, completion rate, and consecutive days of use; The compliance indicator data are grouped and aggregated according to a preset time window, the statistical value of compliance indicator within each time window is calculated, and a mapping relationship between compliance indicator and timestamp is established to generate a compliance indicator dataset containing a time series structure. A compliance report is generated based on the compliance indicator dataset. The compliance report includes a numerical display area for the compliance indicators, a trend curve of the compliance indicators over time, and compliance fluctuation nodes identified and labeled based on the trend curve.

2. The method according to claim 1, characterized in that, The acquisition of usage detection data of the PBM terminal device during use includes: The distance between the user's eyes and the device is detected by an eye proximity sensor to determine whether it is within an effective range, and the correct alignment of the eyes is confirmed by a pupil detection algorithm to obtain the eye alignment status. The blinking state is confirmed by a blink detection sensor, and the timing is paused when the eyes are closed for more than a preset time, so as to obtain the blinking state. The device posture is detected by a tilt sensor. When the posture deviates from the correct posture, the device pauses and issues a voice prompt to obtain the device posture. Record the effective irradiation duration, number of interruptions, interruption duration, and location of use to obtain the usage duration.

3. The method according to claim 1, characterized in that, The method further includes: A reminder notification is sent to the monitoring device before the planned usage time. If no effective usage is detected after the planned usage time, a tiered reminder mechanism is activated. The tiered reminder mechanism includes at least one of the following: After the scheduled time has elapsed for a first preset period, a first reminder message will be sent to the monitoring device. Delay for a second preset time and send a second reminder message to the monitoring terminal; Delay for a third preset time, mark the current session as incomplete, and update the compliance indicator data; If the compliance indicator data fails to reach the preset compliance threshold for N consecutive days, a notification message will be sent to the doctor.

4. The method according to claim 1, characterized in that, The method further includes: Acquire periodic ophthalmological examination data of the user of the PBM terminal device, the ophthalmological examination data including axial length and refractive error; The ophthalmological examination data and the compliance indicators are correlated to generate correlation analysis information between compliance and efficacy; the compliance report also includes the correlation analysis information.

5. A compliance monitoring system for myopia prevention, characterized in that, include: The PBM terminal device includes a light source module, a usage detection module, a data communication module, and a user interaction module. The usage detection module is used to collect eye alignment status, blinking status, and device posture during use. The data communication module is used to upload the usage detection data to a cloud server. The cloud server is configured to receive and store the usage detection data, establish a usage record database for each user, and calculate compliance indicators. The monitoring application is configured to view the user's usage records and compliance reports in real time, receive reminder notifications, set reminder methods, and communicate online with the doctor. The doctor-side platform is configured to view the compliance scores of the users they manage.

6. The system according to claim 5, characterized in that, The usage detection module includes: An eye proximity sensor is configured to detect whether the distance between the user's eyes and the device is within an effective range; A blink detection sensor is configured to detect blinking during the treatment process; The device tilt sensor is configured to detect whether the device is in the correct operating position; Using a time recorder, it is configured to record the start time, end time, effective usage duration, number of interruptions, and interruption duration for each use.

7. The system according to claim 5, characterized in that, The monitoring terminal application also includes: The incentive module is configured to issue virtual points after each use and output a virtual badge when the user uses the service for a target number of consecutive days. The adherence prediction module is configured to analyze users' historical usage patterns, predict adherence risk data within a preset time period, and push preventive intervention information based on the adherence risk data.

8. A compliance monitoring device for myopia prevention, characterized in that, The device includes: The acquisition module is used to acquire usage detection data of the photobiologically regulated PBM terminal device during use. The usage detection data includes at least one of the following: eye alignment status, blinking status, device posture, and usage duration. The calculation module is used to calculate compliance index data based on the usage detection data, wherein the compliance index includes at least one of the following: usage frequency, on-time rate, completion rate, and consecutive usage days; The generation module is used to group and aggregate the compliance indicator data according to a preset time window, calculate the compliance indicator statistics within each time window, establish the mapping relationship between compliance indicators and timestamps, and generate a compliance indicator dataset containing a time series structure. The generation module is also used to generate a compliance report based on the compliance indicator dataset. The compliance report includes a numerical display area of ​​the compliance indicators, a trend curve of the compliance indicators over time, and compliance fluctuation nodes identified and labeled based on the trend curve.

9. An electronic device, characterized in that, The electronic device includes: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements the compliance monitoring method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, implement the compliance monitoring method as described in any one of claims 1-7.

Images