Campus vision screening data visualization and regional prevention strategy generation system

Abstract

The application discloses a campus vision screening data visualization and regional prevention and control strategy generation system, comprising: a data acquisition unit for acquiring campus student vision screening core data, eye environment data, individual behavior data and regional public health resource data; a data preprocessing unit in communication connection with the data acquisition unit, for cleaning, fusing and feature extraction of the collected multi-source heterogeneous data. The application overcomes the technical problems of existing campus vision screening system, such as data isolation, single visualization form, extensive prevention and control strategy, unbalanced regional resource allocation, insufficient privacy protection and lack of iterative optimization mechanism, and provides an intelligent system integrating data acquisition, preprocessing, spatio-temporal visualization, risk assessment, hierarchical strategy generation, interactive output, privacy protection and iterative optimization, so as to realize data management, visualization, analysis, strategy generation and efficiency evaluation, and improve the accuracy of campus myopia prevention and control and the efficiency of regional management.

Description

Technical Field

[0001] This invention relates to the field of health big data technology, and in particular to a system for visualizing campus vision screening data and generating regional prevention and control strategies. Background Technology

[0002] The high rate of myopia among children and adolescents in my country has become a major public health issue, and school vision screening is a core component of early detection and intervention. However, the existing school vision screening and prevention system has many technical shortcomings: At the data level: the screening data is stored only in paper or simple Excel spreadsheets. The multi-source data (vision indicators, eye use environment, behavioral habits, regional medical resources) are isolated from each other, lacking standardized integration and structured processing, resulting in extremely low data utilization and inability to support in-depth analysis. At the visualization level: the existing system only supports static displays such as simple tables, bar charts, and pie charts, and lacks the ability to analyze spatiotemporal correlations. It cannot intuitively present the regional characteristics of visual abnormality clustering, differences in campus distribution, and evolutionary trends, making it difficult to assist in macro-level decision-making. At the level of prevention and control strategies: the prevention and control plans are mostly uniform and extensive document notifications, without differentiated allocation based on individual risk, campus environment and regional resources, and lack a precise strategy generation mechanism that links the "individual-class-campus-region" four levels. In terms of resource allocation: regional ophthalmological medical resources, prevention and control equipment, screening manpower are not matched with high-risk vision areas, and there is no GIS-based spatial analysis and dynamic scheduling capability; Data security: There is a lack of mechanisms to protect students' vision privacy information, and there are compliance risks in cross-departmental (education, health, disease control) data sharing; At the system iteration level: After the prevention and control strategies are implemented, there is no feedback on the effectiveness or a model optimization mechanism, and the strategies remain fixed for a long time, failing to adapt to the changing patterns of vision health in the region.

[0003] While some existing publicly available technologies exist for vision data management systems, none have achieved an integrated technical solution that combines deep fusion of multi-source heterogeneous data, 3D GIS spatiotemporal visualization, machine learning risk prediction, automatic generation of regional hierarchical prevention and control strategies, privacy protection, and dynamic iterative optimization. This makes it impossible to meet the actual needs of precise myopia prevention and control in schools and efficient management of regional public health.

[0004] To address the shortcomings of existing technologies, this invention proposes a system for visualizing campus vision screening data and generating regional prevention and control strategies. Through multi-module collaboration and multi-technology integration, it achieves standardized processing, visual presentation, intelligent analysis, and strategic output of vision screening data, filling the gaps in existing technologies. Summary of the Invention

[0005] This invention discloses a campus vision screening data visualization and regional prevention and control strategy generation system, which includes a data acquisition unit, a data preprocessing unit, a visualization engine, a strategy generation module, an interactive output unit, a strategy iteration and optimization module, and a privacy protection module. The units are interconnected and work together to complete the entire process of data processing, analysis, display, and strategy output.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: A system for visualizing campus vision screening data and generating regional prevention and control strategies, including: The data acquisition unit is used to acquire core data from campus student vision screening, eye-use environment data, individual behavior data, and regional public health resource data. The data preprocessing unit is communicatively connected to the data acquisition unit to clean, fuse, and extract features from the acquired multi-source heterogeneous data to generate a standardized spatiotemporal dataset. The visualization engine communicates with the data preprocessing unit to construct a three-dimensional geographic information model and a dynamic visualization interface, thereby realizing the multi-dimensional spatiotemporal presentation of vision data. The strategy generation module is connected to the data preprocessing unit and the visualization engine respectively. It analyzes the data correlation patterns based on machine learning algorithms and generates hierarchical regional prevention and control strategies. The interactive output unit is connected to the visualization engine and the strategy generation module respectively, and supports multi-terminal data display and strategy push. The system addresses the technical problems of low utilization rate of vision screening data and lack of regional specificity in prevention and control strategies in existing technologies by deeply integrating multi-source data, spatializing visualization analysis, and generating intelligent strategies.

[0007] As a further improvement of the present invention, the data acquisition unit includes: The vision screening data interface is compatible with devices such as computer optometry instruments and eye biometers to collect core indicators such as uncorrected visual acuity, refractive error, and axial length. The environmental sensing module is deployed in areas such as classrooms and dormitories on campus to collect eye-use environment parameters such as light intensity, color temperature, and matching degree of desk and chair height. The behavioral data collection subunit acquires behavioral data such as students' screen time, outdoor activity time, and reading and writing posture through mobile terminal APP or smart wearable device interface; The resource data interface connects to the regional health commission database, the GIS coordinates of ophthalmology medical institutions, and the configuration information of campus epidemic prevention and control facilities to form a regional resource dataset. The data acquisition unit supports real-time incremental acquisition and historical data backtracking, and the data transmission uses an encryption protocol to ensure privacy and security.

[0008] As a further improvement of the present invention, the data preprocessing unit includes: The data cleaning module uses a missing value filling algorithm based on spatiotemporal interpolation to fill in missing values ​​that account for ≤15% of the screened data. It uses box plots combined with medical knowledge to verify outliers and marks extreme data that cannot be corrected. The data fusion module uses a weighted Bayesian fusion algorithm to assign weights to data from different sources according to their credibility, thereby achieving spatiotemporal alignment of vision indicators, environmental parameters, and behavioral data. The feature extraction subunit decomposes time series data into multi-scale features through wavelet transform, and combines the random forest algorithm to screen key features affecting vision, generating a structured dataset containing individual risk factors and regional clustering features.

[0009] As a further improvement of the present invention, the visualization engine includes: The GIS spatial modeling module uses WebGL technology to construct a regional 3D geographic information model and overlays spatial data such as administrative boundaries, campus distribution, and coordinates of medical institutions. The multi-dimensional visualization sub-unit provides four core visualization formats: ① Spatiotemporal heat map of regional vision abnormality rate, supporting layered display by grade, season, and administrative region; ② Individual vision change trajectory map, dynamically annotated with eye use behavior and environmental data; ③ Radar chart of resource allocation balance, intuitively presenting the gap in regional prevention and control resources; ④ Risk prediction trend map, predicting the evolution trend of vision abnormality in the next 6-12 months based on time series data. The interactive control module supports zooming, rotation, layer switching, and custom queries, enabling two-way linkage from macro-level regional analysis to micro-level individual tracking.

[0010] As a further improvement of the present invention, the strategy generation module includes: The risk assessment model, based on an LSTM neural network that integrates individual characteristics and regional environmental factors, constructs a dual prediction model for the risk of myopia occurrence and the rate of myopia progression, with a prediction accuracy of ≥85%. The tiered strategy generates sub-units, which generate graded prevention and control strategies based on the prediction results: ① Individual student level: output personalized eye care guidance plans, including suggestions on outdoor activity time, key points for correcting reading and writing posture, and reminders for regular check-ups; ② Class / campus level: generate environmental modification plans, including classroom lighting optimization parameters, desk and chair adjustment standards, and eye care course setting plans; ③ Regional management level: provide resource allocation plans, including screening frequency optimization, medical institution collaboration mechanisms, and prevention and control material distribution plans. The strategy matching module, based on reinforcement learning algorithms, dynamically adjusts the strategy execution priority according to the regional resource carrying capacity.

[0011] As a further improvement of the present invention, the strategy generation module further includes a regional resource dynamic matching unit, which uses a GIS spatial analysis algorithm: Calculate the optimal path and travel time from each campus to the nearest ophthalmology clinic; Based on regional visual aberration rate heatmaps and resource distribution density maps, areas with weak prevention and control resources are identified; The system generates resource allocation suggestions, including deployment routes for mobile screening vehicles, scheduling plans for expert consultations, and cross-school allocation plans for prevention and control equipment, to achieve a balanced allocation of regional prevention and control resources.

[0012] As a further improvement of the present invention, the interactive output unit includes: The multi-terminal adaptation module supports adaptation and display on PC web platforms, mobile apps, WeChat mini programs, and regional health commission command screens. The access control sub-unit sets three levels of access permissions: ① Parents can only view the vision data and individual prevention and control suggestions of their associated students; ② Schools can view the overall data of the school, class analysis reports and campus-level strategies; ③ Health departments can obtain regional data, resource allocation analysis and regional prevention and control plans. The message push module pushes screening results, strategy reminders, and abnormal warning information in real time through APP notifications, SMS, and official account pushes.

[0013] As a further improvement of the present invention, a strategy iteration optimization module is also included, which: Collect feedback data on strategy implementation, including data on changes in student vision, implementation status of school environment renovations, and effectiveness of resource allocation. Based on feedback data, the gradient descent algorithm is used to update the parameters of the risk assessment model, and a strategy optimization report is generated every quarter. It supports a manual intervention interface, allowing professionals to adjust the strategy generation rules based on clinical experience, thus combining automatic algorithm optimization with human experience correction.

[0014] As a further improvement of the present invention, the data preprocessing unit also includes a privacy protection module, which uses differential privacy technology to de-identify student personal identity information, and ensures compliance with the Personal Information Protection Law and data security standards in the education industry through encrypted data storage and access log auditing; the visualization engine supports cross-departmental sharing of de-identified data and can open standardized data interfaces to education, health, disease control and other departments.

[0015] As a further improvement of the present invention, the visualization engine also supports customized report generation, and can export a comprehensive report that includes regional vision health status analysis, evaluation of the effectiveness of prevention and control strategy implementation, and resource allocation optimization suggestions. The report format supports PDF, Excel and GIS vector files. The strategy generation module is connected to the regional public health emergency command system, and can automatically trigger an early warning when the vision abnormality rate suddenly increases, generate an emergency prevention and control plan and push it to the relevant responsible units.

[0016] The beneficial effects of this invention are: At the data integration level: standardize and integrate multi-source data such as vision, environment, behavior, and resources to solve the problems of data isolation and low utilization, and provide a data foundation for in-depth analysis; Visualization: Breaking through the limitations of traditional static charts, it achieves spatiotemporal linkage visualization through 3D GIS, intuitively presenting regional clustering characteristics and evolutionary trends, and assisting in macro-level decision-making; At the strategy generation level: a pioneering three-tiered precise prevention and control strategy of "individual-campus-region" has been developed to replace the traditional extensive approach, enabling differentiated and targeted configuration of prevention and control measures; At the resource allocation level: Based on GIS spatial analysis, the optimal matching of regional prevention and control resources is achieved, solving the technical problems of unbalanced resource distribution and low utilization rate; Privacy and security: It adopts triple protection of differential privacy desensitization, encrypted storage, and access control, which complies with data security regulations and enables compliant sharing across departments; At the system iteration level: a closed-loop mechanism of "execution-feedback-optimization" is constructed, and strategies are dynamically updated to continuously adapt to the changing patterns of regional vision health. At the emergency management level: enable automatic early warning of abnormal data and improve the efficiency of regional public health emergency response. Attached Figure Description

[0017] Figure 1 This is a system diagram of the campus vision screening data visualization and regional prevention and control strategy generation system proposed in this invention. Detailed Implementation

[0018] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0019] To further illustrate the technical solution of the present invention, the following detailed description is provided in conjunction with specific embodiments: Example 1: System Overall Setup This embodiment provides a system for visualizing campus vision screening data and generating regional prevention and control strategies, such as... Figure 1 As shown, it includes: The system comprises 1 data acquisition unit, 2 data preprocessing unit, 3 visualization engine, 4 strategy generation module, 5 interactive output unit, 6 strategy iteration and optimization module, and 7 emergency early warning docking module. Each unit is connected via LAN / Internet and is built using a B / S architecture, supporting both cloud and local deployment modes.

[0020] Example 2: Data Acquisition Unit Workflow Data acquisition unit 1 includes: Vision screening data interface 11: Directly connects to computer optometry and eye biometer, automatically collects core indicators such as uncorrected visual acuity, refractive error, axial length, and astigmatism, and supports batch import of historical screening data; Environmental sensing module 12: Deployed in classrooms, libraries, and dormitories to collect environmental parameters in real time, such as light intensity, color temperature, matching degree of table and chair height, and duration of eye use; Behavioral data collection subunit 13: Acquire behavioral data such as screen usage time, outdoor activity time, reading and writing posture, and sleep duration through APP and smart wearable devices; Resource Data Interface 14: Connects to the databases of the National Health Commission, the Center for Disease Control and Prevention, and ophthalmology hospitals to obtain resource data such as the coordinates of regional medical institutions, prevention and control personnel, screening equipment, and prevention and control materials.

[0021] All data is transmitted using SSL encryption, and supports real-time incremental data collection and timed backtracking to ensure data integrity and security.

[0022] Example 3: Data Preprocessing Unit Workflow Data preprocessing unit 2 performs the following steps: Data cleaning module 21: For data with a missing value ratio of ≤15%, spatiotemporal interpolation algorithm is used to fill the missing value, outliers are removed by box plot method combined with medical standards, and invalid data is marked; Data fusion module 22: Employs a weighted Bayesian fusion algorithm, assigning weights based on the credibility of the data source to achieve spatiotemporal alignment of vision, environment, behavior, and resource data; Feature extraction subunit 23: Decompose time series data through wavelet transform, and combine random forest algorithm to screen key influencing features such as outdoor activity duration, light intensity, and axial length to generate structured dataset; Privacy Protection Module 24: Employs differential privacy technology to anonymize identity information such as name, ID number, and home address, combined with encrypted storage and access log auditing, to meet the requirements of the Personal Information Protection Law.

[0023] Example 4: Visualization Engine Visualization Implementation Visualization Engine 3 uses WebGL to build 3D GIS models and achieves four core visualization methods: Spatiotemporal heat map of regional vision abnormality rate: displayed in layers by grade, gender, season and administrative region, with the shade of color corresponding to the level of abnormality rate, intuitively presenting high-risk cluster areas; Individual vision change trajectory map: correlates behavioral and environmental data, dynamically marks the nodes of vision decline and influencing factors, and supports full-cycle tracking of individuals; Radar chart of resource allocation balance: Compare the differences in the allocation of regional medical resources, prevention and control facilities, and screening frequency to intuitively show the weak links; Risk prediction trend chart: Based on time series data, predict the evolution trend of vision abnormalities in the next 6-12 months to assist in early prevention and control.

[0024] The interactive control module 33 supports zooming, rotation, layer switching, and custom queries, enabling two-way linkage from macro to micro levels of the region. It also supports exporting reports in PDF, Excel, and GIS vector formats.

[0025] Example 5: Intelligent Decision-Making in Strategy Generation Module Strategy Generation Module 4 Workflow: Risk assessment model 41: Based on LSTM neural network to fuse individual and regional characteristics, a dual prediction model for the occurrence and progression of myopia is constructed, with a prediction accuracy of ≥85%; Hierarchical strategy for generating sub-units 42: Individual level: Provide personalized guidance plans such as outdoor activity time, reading and writing posture, and follow-up examination cycle; Campus level: Generate environmental improvement plans such as lighting optimization, desk and chair adjustment, and eye-friendly curriculum design; Regional level: Develop management plans for screening frequency, collaboration among medical institutions, and resource allocation; Regional resource dynamic matching unit 43: Calculates the optimal route from the campus to the medical institution through GIS spatial analysis, identifies resource-deficient areas, and generates mobile screening vehicle routes, expert scheduling, and cross-school equipment dispatching plans; Policy matching module 44: Based on reinforcement learning algorithms, it dynamically adjusts the policy execution priority by combining regional resource carrying capacity to ensure that the policy can be implemented.

[0026] Example 6: Interactive Output and Permission Management Interactive output unit 5 implementation: Multi-terminal adaptation module 51: Supports full-terminal adaptation for PC Web, APP, mini-program, and command screen; Access Control Sub-Unit 52: Three-Tier Access Control – Parents can only view their children's data and individual suggestions; schools can view their own school's data and campus policies; and health authorities can view overall data and regional plans. Message push module 53: Pushes screening results, early warning information, and policy reminders via APP, SMS, and official account.

[0027] Example 7: Strategy Iteration and Emergency Early Warning Strategy Iteration and Optimization Module 6: Collects feedback data on vision changes, environmental modifications, and resource scheduling; updates model parameters using the gradient descent algorithm; generates an optimization report every quarter; and supports manual rule correction by ophthalmologists and public health personnel. Emergency Warning and Connection Module 7: Connects with the regional public health emergency command system. When the regional vision abnormality rate suddenly increases and exceeds the threshold, it will automatically issue an early warning, generate an emergency prevention and control plan, and push it to the responsible unit to achieve rapid response.

[0028] Example 8: Overall System Workflow Overall workflow of this system: Collect data on vision, environment, behavior, and resources through multiple channels; Data cleaning, fusion, feature extraction, and desensitization; 3D GIS spatiotemporal visualization and analysis; Machine learning risk assessment and three-level strategy generation; Multi-terminal tiered display and strategy push; Strategy execution feedback and model iterative optimization; Emergency warning and cross-departmental collaboration for abnormal data.

[0029] Through the above-mentioned technical solution, this invention realizes intelligent management of the entire process of campus vision screening data and precise generation of regional prevention and control strategies, effectively solving the defects of existing technologies, possessing outstanding creativity and practicality, and is applicable to education and health departments at all levels to carry out myopia prevention and control work for children and adolescents.

[0030] The above are merely preferred embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A system for visualizing campus vision screening data and generating regional prevention and control strategies, characterized in that: include: The data acquisition unit is used to acquire core data from campus student vision screening, eye-use environment data, individual behavior data, and regional public health resource data. The data preprocessing unit is communicatively connected to the data acquisition unit to clean, fuse, and extract features from the acquired multi-source heterogeneous data to generate a standardized spatiotemporal dataset. The visualization engine communicates with the data preprocessing unit to construct a three-dimensional geographic information model and a dynamic visualization interface, thereby realizing the multi-dimensional spatiotemporal presentation of vision data. The strategy generation module is connected to the data preprocessing unit and the visualization engine respectively. It analyzes the data correlation patterns based on machine learning algorithms and generates hierarchical regional prevention and control strategies. The interactive output unit is connected to the visualization engine and the strategy generation module respectively, and supports multi-terminal data display and strategy push. The system addresses the technical problems of low utilization rate of vision screening data and lack of regional specificity in prevention and control strategies in existing technologies by deeply integrating multi-source data, spatializing visualization analysis, and generating intelligent strategies.

2. The campus vision screening data visualization and regional prevention and control strategy generation system according to claim 1, characterized in that, The data acquisition unit includes: The vision screening data interface is compatible with devices such as computer optometry instruments and eye biometers to collect core indicators such as uncorrected visual acuity, refractive error, and axial length. The environmental sensing module is deployed in areas such as classrooms and dormitories on campus to collect eye-use environment parameters such as light intensity, color temperature, and matching degree of desk and chair height. The behavioral data collection subunit acquires behavioral data such as students' screen time, outdoor activity time, and reading and writing posture through mobile terminal APP or smart wearable device interface; The resource data interface connects to the regional health commission database, the GIS coordinates of ophthalmology medical institutions, and the configuration information of campus epidemic prevention and control facilities to form a regional resource dataset. The data acquisition unit supports real-time incremental acquisition and historical data backtracking, and the data transmission adopts an encryption protocol to ensure privacy and security.

3. The campus vision screening data visualization and regional prevention and control strategy generation system according to claim 1, characterized in that, The data preprocessing unit includes: The data cleaning module uses a missing value filling algorithm based on spatiotemporal interpolation to fill in missing values ​​that account for ≤15% of the screened data. It uses box plots combined with medical knowledge to verify outliers and marks extreme data that cannot be corrected. The data fusion module uses a weighted Bayesian fusion algorithm to assign weights to data from different sources according to their credibility, thereby achieving spatiotemporal alignment of vision indicators, environmental parameters, and behavioral data. The feature extraction subunit decomposes time series data into multi-scale features through wavelet transform, and combines the random forest algorithm to screen key features affecting vision, generating a structured dataset containing individual risk factors and regional clustering features.

4. The campus vision screening data visualization and regional prevention and control strategy generation system according to claim 1, characterized in that, The visualization engine includes: The GIS spatial modeling module uses WebGL technology to construct a regional 3D geographic information model and overlays spatial data such as administrative boundaries, campus distribution, and coordinates of medical institutions. The multi-dimensional visualization sub-unit provides four core visualization formats: ① Spatiotemporal heat map of regional vision abnormality rate, supporting layered display by grade, season, and administrative region; ② Individual vision change trajectory map, dynamically annotated with eye use behavior and environmental data; ③ Radar chart of resource allocation balance, intuitively presenting the gap in regional prevention and control resources; ④ Risk prediction trend map, predicting the evolution trend of vision abnormality in the next 6-12 months based on time series data. The interactive control module supports zooming, rotation, layer switching, and custom queries, enabling two-way linkage from macro-level regional analysis to micro-level individual tracking.

5. The campus vision screening data visualization and regional prevention and control strategy generation system according to claim 1, characterized in that, The strategy generation module includes: The risk assessment model, based on an LSTM neural network that integrates individual characteristics and regional environmental factors, constructs a dual prediction model for the risk of myopia occurrence and the rate of myopia progression, with a prediction accuracy of ≥85%. The tiered strategy generates sub-units, which generate graded prevention and control strategies based on the prediction results: ① Individual student level: output personalized eye care guidance plans, including suggestions on outdoor activity time, key points for correcting reading and writing posture, and reminders for regular check-ups; ② Class / campus level: generate environmental modification plans, including classroom lighting optimization parameters, desk and chair adjustment standards, and eye care course setting plans; ③ Regional management level: provide resource allocation plans, including screening frequency optimization, medical institution collaboration mechanisms, and prevention and control material distribution plans. The strategy matching module, based on reinforcement learning algorithms, dynamically adjusts the strategy execution priority according to the regional resource carrying capacity.

6. The campus vision screening data visualization and regional prevention and control strategy generation system according to claim 5, characterized in that, The strategy generation module also includes a regional resource dynamic matching unit, which uses GIS spatial analysis algorithms: Calculate the optimal path and travel time from each campus to the nearest ophthalmology clinic; Based on regional visual aberration rate heatmaps and resource distribution density maps, areas with weak prevention and control resources are identified; The system generates resource allocation suggestions, including deployment routes for mobile screening vehicles, scheduling plans for expert consultations, and cross-school allocation plans for prevention and control equipment, to achieve a balanced allocation of regional prevention and control resources.

7. The campus vision screening data visualization and regional prevention and control strategy generation system according to claim 1, characterized in that, The interactive output unit includes: The multi-terminal adaptation module supports adaptation and display on PC web platforms, mobile apps, WeChat mini programs, and regional health commission command screens. The access control sub-unit sets three levels of access permissions: ① Parents can only view the vision data and individual prevention and control suggestions of their associated students; ② Schools can view the overall data of the school, class analysis reports and campus-level strategies; ③ Health departments can obtain regional data, resource allocation analysis and regional prevention and control plans. The message push module pushes screening results, strategy reminders, and abnormal warning information in real time through APP notifications, SMS, and official account pushes.

8. The campus vision screening data visualization and regional prevention and control strategy generation system according to claim 1, characterized in that, It also includes a strategy iteration optimization module, which: Collect feedback data on strategy implementation, including data on changes in student vision, implementation status of school environment renovations, and effectiveness of resource allocation. Based on feedback data, the gradient descent algorithm is used to update the parameters of the risk assessment model, and a strategy optimization report is generated every quarter. It supports a manual intervention interface, allowing professionals to adjust the strategy generation rules based on clinical experience, thus combining automatic algorithm optimization with human experience correction.

9. The campus vision screening data visualization and regional prevention and control strategy generation system according to claim 1, characterized in that, The data preprocessing unit also includes a privacy protection module, which uses differential privacy technology to de-identify students' personal identity information and ensures compliance with the Personal Information Protection Law and data security standards in the education industry through encrypted data storage and access log auditing. The visualization engine supports cross-departmental sharing of de-identified data and can open standardized data interfaces to education, health, disease control and other departments.

10. The campus vision screening data visualization and regional prevention and control strategy generation system according to claim 1, characterized in that, The visualization engine also supports customized report generation, and can export comprehensive reports that include regional vision health status analysis, evaluation of the effectiveness of prevention and control strategies, and suggestions for resource allocation optimization. The report formats support PDF, Excel, and GIS vector files. The strategy generation module is connected to the regional public health emergency command system, and can automatically trigger early warnings when the vision abnormality rate suddenly increases, generate emergency prevention and control plans, and push them to relevant responsible units.

Images