Intelligent management system and method for occupational health monitoring files

Abstract

The invention discloses an intelligent management method and system for occupational health monitoring files, and relates to the field of occupational health monitoring management, and the system comprises a data collection layer, a data processing layer, a business logic layer and a user interaction layer. The data acquisition layer comprises a data acquisition and input module which is responsible for acquiring occupational health data from a data source; the data processing layer is used for cleaning, converting and storing the acquired data; the business logic layer comprises an archive storage and management module, an intelligent query and retrieval module, a data analysis and risk assessment module and an early warning and reminding module, and performs core business functions of the system; and the user interaction layer comprises a user authority management module and a system maintenance and update module. According to the invention, the consistency and reliability of data are improved, the utilization efficiency of information is improved, the occurrence probability of occupational diseases is reduced, the body health of employees is guaranteed, the stable operation of the system is guaranteed, and reliable technical support is provided for occupational health management of enterprises.

Description

Technical Field

[0001] The present invention relates to the field of occupational health monitoring management, and in particular to an intelligent management system and method for occupational health monitoring archives. Background Art

[0002] In modern business operations, occupational health monitoring file management is crucial, as it affects the protection of employees' health rights and interests and the compliance of corporate operations. However, the current status of occupational health monitoring file management has many problems that need to be solved.

[0003] Traditional management methods rely heavily on manual operations, resulting in extremely low efficiency. During the file entry process, staff members are required to manually enter a large amount of employee basic information, career history, physical examination reports, and other content. This not only consumes a significant amount of time and effort, but is also prone to entry errors, such as missing information and incorrect data entry. For example, for a company with thousands of employees, each annual physical examination report entry may take several staff members several weeks to complete, with a high error rate. Regarding file organization and storage, manually organized paper files are difficult to find, take up a large amount of storage space, and are prone to damage and loss over time.

[0004] Data accuracy and integrity are difficult to guarantee. Due to the lack of effective data verification mechanisms, manually entered data may contain biases, and data formats from different sources may be inconsistent, seriously compromising the accuracy and integrity of archival data. This can lead companies to make erroneous decisions when using this data to conduct occupational health risk assessments and develop preventive measures.

[0005] Accessing and utilizing archives is extremely inconvenient. When an enterprise needs to retrieve specific health information for an employee, traditional manual search methods can require a significant amount of time, searching through mountains of paper files or sifting through complex spreadsheets. This can delay optimal diagnosis and treatment in emergencies, such as when an employee develops an occupational illness and needs to quickly access their historical health data. Furthermore, traditional management methods struggle to effectively analyze and mine large amounts of archival data, failing to provide robust data support for formulating scientific and sound occupational health management strategies.

[0006] As enterprises continue to expand and the number of employees continues to increase, the requirements for occupational health monitoring file management are becoming increasingly stringent. Traditional management methods can no longer meet the needs of modern enterprises for efficient and precise management. An innovative and intelligent management system is urgently needed to improve management levels.

[0007] The present invention relates to the intersection of information technology and occupational health management, and in particular to an intelligent management system for occupational health monitoring files, which realizes efficient and accurate management of occupational health monitoring files by using advanced information technology means. Summary of the Invention

[0008] In view of the above-mentioned existing problems, the present invention aims to provide an intelligent management system for occupational health monitoring archives, aiming to solve the problems of low efficiency, poor data quality, and difficulty in query and utilization in the existing occupational health monitoring archive management, to realize intelligent, efficient and precise archive management, to improve the level of enterprise occupational health management, and to protect the occupational health rights and interests of employees.

[0009] In order to solve the above technical problems, an intelligent management system for occupational health monitoring archives is proposed, which includes data acquisition layer, data processing layer, business logic layer and user interaction layer.

[0010] The data collection layer includes a data collection and entry module, which is responsible for obtaining occupational health data from the data source;

[0011] The data processing layer cleans, converts and stores the collected data;

[0012] The business logic layer includes an archive storage and management module, an intelligent query and retrieval module, a data analysis and risk assessment module, and an early warning and reminder module, which perform the core business functions of the system, including archive management and data analysis;

[0013] The user interaction layer includes a user authority management module and a system maintenance and update module, which are operated through a user-friendly interface.

[0014] The present invention also provides an occupational health monitoring file intelligent management method, which is applied to an occupational health monitoring file intelligent management system.

[0015] As a preferred solution of the intelligent management method of occupational health monitoring archives described in the present invention, the data acquisition and entry module includes establishing a data interface with the system through multiple data acquisition to automatically acquire and update data in real time. At the same time, the data in the paper document is automatically identified and entered through the first recognition method.

[0016] As a preferred solution of the method for intelligent management of occupational health monitoring archives described in the present invention, the data collection and entry module further includes selecting a server and a database management system, and setting up a client device including a computer used by the client, which is connected to the server via a network;

[0017] In the database management system, the occupational health monitoring archive management database is established and the collected data is imported. According to the enterprise's organizational structure and personnel responsibilities, user roles are created and corresponding operation permissions are assigned to each role. The basic parameters of the system are set and personalized configuration is performed according to the actual needs of the enterprise.

[0018] As a preferred solution of the intelligent management method for occupational health monitoring archives described in the present invention, the archive storage and management module includes storing the collected data on multiple nodes of a distributed database according to a database table structure, and encrypting and storing the data using a preset encryption method;

[0019] Categorize and store the encrypted files and create an index directory;

[0020] Establish a data backup and recovery mechanism, back up data regularly, and quickly restore data when it is lost or damaged.

[0021] As a preferred solution of the intelligent management method for occupational health monitoring archives of the present invention, wherein: the intelligent query and retrieval module includes: the user enters keywords in the query interface, the system quickly retrieves relevant archive information, and displays the query results to the user;

[0022] The user sets the query conditions, and the system selects the archive records that meet the conditions according to the user's conditions, sorts them, and displays them;

[0023] The first processing technology is used to conduct natural language interaction between the user and the system, identify part of the information input by the user, and associate all related archival records.

[0024] As a preferred embodiment of the intelligent management method for occupational health monitoring files of the present invention, the data analysis and risk assessment module includes using big data analysis technology to conduct in-depth analysis of occupational health monitoring file data through an occupational disease risk assessment model to explore the potential patterns and risks behind the data;

[0025] By establishing a health indicator prediction model, we can predict the risk of occupational diseases and provide a scientific basis for enterprises to formulate preventive measures;

[0026] Use data analysis tools to conduct in-depth analysis of data and generate data analysis reports and visual charts.

[0027] As a preferred embodiment of the intelligent management method for occupational health monitoring files described in the present invention, the warning and reminder module includes setting warning rules in the module. When any of the following situations occurs: an employee's health indicators exceed the normal range, the physical examination time expires, or the risk of occupational disease increases, the system sends a warning message to the corresponding personnel via SMS, email, or system message;

[0028] The handling process of warning events is tracked and recorded. After receiving the warning information, the corresponding personnel take corresponding measures and record the handling results in the system.

[0029] As a preferred solution of the intelligent management method for occupational health monitoring archives described in the present invention, the user interaction layer includes: in the user rights management module, the system administrator is allowed to create, modify and delete user roles, and define different operation permissions and function menus for each role;

[0030] Conduct unified management of user accounts, including at least user registration, login verification, and password reset. Users log into the system using a unique account and password. User permissions are allocated and adjusted in a timely manner based on changes in the company's organizational structure and personnel responsibilities.

[0031] The system maintenance and update module establishes a system monitoring mechanism to monitor the system's operating status in real time, including server performance, network connection, and database load. When the system encounters an abnormality, it will promptly issue an alarm to notify the system administrator for processing;

[0032] Regularly perform security scans on the system to discover and repair system vulnerabilities, promptly update system security patches, and prevent network attacks and data leakage risks;

[0033] Optimize and upgrade the system's functions based on feedback from the user rights management module and business needs;

[0034] Record the system's operation logs and running logs, including user login records, data operation records, and system error information. By analyzing the system logs, determine the system's usage and operating status, and provide a basis for the early warning and reminder modules.

[0035] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, it implements the steps of the intelligent management system for occupational health monitoring archives.

[0036] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the intelligent management system for occupational health monitoring archives are implemented.

[0037] The present invention's beneficial effects: Through automated data collection and intelligent management, it significantly shortens the time required for file entry, query, and analysis, reduces manual workload, and improves management efficiency. This allows companies to devote more time and energy to employee occupational health services and management.

[0038] Advanced data verification and cleaning technologies are used to ensure the accuracy and completeness of input data. This improves the consistency and reliability of data and provides reliable data support for enterprises' occupational health decision-making.

[0039] Intelligent query and retrieval functions enable users to quickly and accurately obtain the required archival information, improving information utilization efficiency. Data analysis and visualization functions help companies better understand the occupational health of their employees and provide a basis for formulating scientific management strategies.

[0040] The early warning and reminder module can timely detect potential occupational health risks, remind enterprises to take corresponding measures for prevention and control, reduce the probability of occupational diseases, and protect the health of employees.

[0041] The user rights management module ensures the security and confidentiality of system data. Different users can only perform operations within their scope of authority, preventing data leakage and abuse. The system maintenance and update module ensures the stable operation of the system and provides reliable technical support for the company's occupational health management. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0043] Figure 1 This is a system solution module diagram of an intelligent management system for occupational health monitoring archives provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0044] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0045] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0046] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it individually or selectively refer to an embodiment that is mutually exclusive of other embodiments.

[0047] The present invention is described in detail with reference to schematic diagrams. For ease of illustration, cross-sectional views of device structures may be partially enlarged and not to scale when describing embodiments of the present invention. Furthermore, the schematic diagrams are merely illustrative and should not limit the scope of the present invention. Furthermore, in actual production, the three-dimensional dimensions of length, width, and depth should be included.

[0048] In the description of the present invention, it should be noted that the terms "upper, lower, inner, and outer" and other references to orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0049] In this disclosure, unless otherwise specified or limited, the terms "mounted," "connected," and "connected" should be interpreted broadly. For example, they may refer to fixed, removable, or integral connections. They may also refer to mechanical, electrical, or direct connections, indirect connections through an intermediary, or internal communication between two components. Those skilled in the art will understand the specific meanings of these terms in this disclosure.

[0050] Example 1, reference Figure 1 , which is the first embodiment of the present invention, provides an intelligent management system for occupational health monitoring archives, including:

[0051] This system adopts a layered architecture design, including data acquisition layer, data processing layer, business logic layer and user interaction layer;

[0052] The data collection layer includes a data collection and entry module, which is responsible for obtaining occupational health data from the data source;

[0053] The data processing layer cleans, converts and stores the collected data;

[0054] The business logic layer includes an archive storage and management module, an intelligent query and retrieval module, a data analysis and risk assessment module, and an early warning and reminder module, which perform the core business functions of the system, including archive management and data analysis;

[0055] The user interaction layer includes a user authority management module and a system maintenance and update module, which are operated through a user-friendly interface to facilitate user operations.

[0056] It should be noted that a server and a database management system are selected, and client devices including computers used by the client are set up and connected to the server through a network;

[0057] S1: The server uses a high-performance cloud computing server with sufficient computing power, storage capacity, and network bandwidth to meet the needs of system operation and data storage.

[0058] Client devices include computers and tablets used by enterprise employees and managers, which are connected to the server through the network;

[0059] The server operating system should be Windows Server or Linux, and the database management system (at least MySQL, Oracle, etc.) and application server software (at least Tomcat, Nginx, etc.) should be installed. The client operating system supports mainstream operating systems such as Windows, Mac OS, and Linux, and the browser supports Chrome, Firefox, Edge, etc.

[0060] It should also be noted that an occupational health monitoring archive management database should be created in the database management system, and the database table structure should be designed, including employee basic information table, occupational history table, physical examination report table, occupational disease diagnosis table, etc., and the relationship between the tables should be established;

[0061] Import the company's existing employee basic information, career history and other basic data into the system to ensure data integrity and accuracy;

[0062] Create different user roles based on the company's organizational structure and personnel responsibilities, such as administrators, occupational health managers, corporate employees, doctors, etc., and assign corresponding operation permissions to each role;

[0063] Set basic system parameters, such as warning thresholds, data backup cycles, report templates, etc., and perform personalized configuration based on the actual needs of the enterprise.

[0064] S2: The data processing layer cleans, converts and stores the collected data.

[0065] S3: Data collection and entry module, through multi-data collection, establishes a data interface with the system, automatically collects data and updates it in real time. At the same time, it automatically recognizes and enters data in paper documents through the first recognition method.

[0066] Supports multiple data collection, including manual entry, batch import, interface docking, etc.

[0067] Furthermore, manual data entry: For data that cannot be obtained through the interface, such as employees' occupational history and medical history, relevant personnel manually enter it into the system. During the data entry process, the system provides real-time data verification and prompts to ensure the accuracy of the entered data.

[0068] Batch import: Large amounts of employee physical examination data, training records, etc. can be organized using Excel spreadsheets and then imported into the system using the system's batch import function. The system automatically converts and verifies the imported data to ensure data consistency.

[0069] Interface connection: Establish data interfaces with medical institutions, physical examination centers, and other systems. Automatically transmit and update physical examination reports, diagnosis results, and other data in real time according to pre-defined data formats and interface specifications. When employees complete their physical examinations, the data is automatically synchronized to this system without manual intervention.

[0070] It should be noted that the purpose of the first recognition method is to improve data accuracy and reliability, providing a solid foundation for subsequent analysis and control. During the recognition phase, data from paper documents is automatically identified and entered, improving data collection efficiency and accuracy. Key information from paper documents (such as physical examination reports, occupational history registration forms, and hand-filled questionnaires) is extracted as structured data through automated means, reducing manual data entry costs.

[0071] In an optional embodiment, the first recognition method can adopt multimodal fusion recognition technology, combining multimodal data features such as text, images, and tables to jointly parse the mixed information in the document; enhance the ability to fully understand complex layouts (such as physical examination reports containing charts and annotations) and improve recognition integrity.

[0072] In an optional embodiment, the first recognition method can also establish a deep learning model, including CNN and RNN, which is good at extracting local features and spatial information of images, and can accurately identify complex tables, seals and text layouts in documents; it is suitable for sequence data processing (such as handwritten text), can capture the temporal correlation between characters, and improve the recognition rate of continuous handwriting.

[0073] In the embodiment of the present application, the first identification method includes:

[0074] Optical character recognition technology is used to automatically identify and enter data in paper documents to improve data collection efficiency and accuracy. The specific process is as follows:

[0075] The user takes pictures of paper documents through a high-speed document scanner, a scanner or a mobile phone camera, supporting continuous scanning of multiple pages. The system automatically detects the image clarity and prompts to retake the blurred area. An AR guidance frame is superimposed on the screen in real time, automatically selecting the area to be recognized (such as the name column, the test result table), and prompting "Please align the camera with the red frame"; after recognition, the key data is superimposed on the original paper document image in the form of floating labels, and the user can confirm by voice (such as "Save data" or "Recognize again");

[0076] Automatically crop irrelevant backgrounds (such as desktop clutter), correct tilted and distorted pages, remove shadow and fold interference, and enhance text contrast;

[0077] Adopt multi-engine collaboration (such as Tesseract + commercial API) to distinguish printed text from handwritten text:

[0078] Recognition of printed text: directly extract the text content, recognize the table frame lines and reconstruct the structured data;

[0079] Recognition of handwritten text: analyze scribbled handwriting and correct errors based on context semantics (such as "hemoglobin" → "hemoglobin").

[0080] Automatically match the recognition results with database fields (such as employee ID, physical examination date), and a pop-up window will be triggered to remind the user to supplement the missing data; for numerical data (such as blood pressure value), the rationality will be automatically verified (such as if the systolic blood pressure > 300, it will be marked in red for alarm).

[0081] When a doctor or administrator reviews the recognition results, they can add annotation labels (such as "suspected pneumoconiosis") to the document image. The system will automatically associate them with the employee's health risk assessment module and trigger subsequent follow-up tasks (such as "arrange a re-examination").

[0082] S4: Archive storage and management module. Using distributed database technology, the collected data is stored on multiple nodes of the distributed database according to the database table structure, ensuring the security and reliability of the data;

[0083] Encrypt the data for storage through a preset encryption method to prevent data leakage;

[0084] It should be noted that the purpose of the preset encryption method is to ensure the security and reliability of the data and prevent data leakage.

[0085] In an optional embodiment, the preset encryption method can adopt data sharding encryption, splitting the occupational health surveillance archive data into multiple small pieces, and each piece of data has an independent encryption key. For example, the complete physical examination report data of an employee is divided into different segments according to items (such as blood tests, imaging tests, etc.), and each segment is encrypted using a different AES (Advanced Encryption Standard) key.

[0086] Even if data from a shard is stolen, the thief will have difficulty obtaining valuable information due to the lack of the corresponding decryption key. Furthermore, sharded data can be more flexibly stored in different media or geographical locations, reducing the risk of data being destroyed or stolen as a whole.

[0087] In an optional embodiment, the preset encryption method can also provide redundant storage encryption, storing multiple identical copies of the encrypted data in different storage locations. For example, using RAID (Redundant Array of Independent Disks) technology, the encrypted occupational health monitoring file data can be stored simultaneously on multiple disks, and each copy of the data can be encrypted again, using the RSA asymmetric encryption algorithm, with different public-private key pairs to encrypt each copy.

[0088] On the one hand, if data in a particular storage location is lost or damaged due to hardware failure, natural disasters, or other reasons, it can be restored from other redundant copies, ensuring data integrity and availability. On the other hand, multiple encryption layers across different copies further enhance data security during storage and transmission. Even if some copies are compromised, it is extremely difficult to crack all the encryption layers.

[0089] In the embodiment of the present application, the preset encryption method includes the combined application of data sharding encryption and redundant storage encryption:

[0090] Occupational health monitoring file data is first encrypted in slices, then redundantly stored, and each redundant copy is encrypted again. For example, a file containing an employee's occupational history and historical physical examination results is first sliced by information category, and each slice is encrypted using AES. These encrypted slices are then stored on multiple servers in different locations, and all copies of the sliced data stored on each server are encrypted using the RSA algorithm. This combination of data sharding, redundant storage, and multiple encryption creates a multi-layered data security system that effectively protects the confidentiality, integrity, and availability of occupational health monitoring file data.

[0091] It should also be noted that the files are classified and stored according to the employees' positions, types of work, occupational hazard factors, etc., and an index directory is established to facilitate query and management; for example, the files of employees working in the chemical industry are classified into one category, and the files of employees exposed to dust are classified into another category, etc.; the classified management of files is realized, and the files are classified and stored according to the employees' positions, types of work, occupational hazard factors, etc., to facilitate query and management.

[0092] Regularly perform full and incremental backups of the database and store the backup data in an off-site storage device. In the event of a system failure or data loss, the backup data can be used for rapid recovery to ensure normal system operation.

[0093] S5: Intelligent query and retrieval module includes keyword query, conditional filter query, and natural language query;

[0094] Users enter keywords in the query interface, such as employee name, work number, physical examination items, etc. The system quickly retrieves relevant file information and displays the query results to the user.

[0095] Users can conduct precise searches by setting multiple search criteria, such as physical examination time range, job type, health index range, etc. The system will filter out the files that meet the conditions set by the user, sort them, and display them.

[0096] The first processing technology is used to conduct natural language interaction between users and the system, supporting fuzzy queries and associated queries. It can associate relevant archival records based on partial information input by the user and display other related information; such as "Query Zhang San's physical examination report for the past year" and "List all employees who are exposed to noise and have hearing abnormalities", etc. The system uses natural language processing technology to understand the user's questions and return accurate query results.

[0097] It should be noted that the purpose of the first processing technology is to achieve natural language interaction between users and the system. Users can ask questions in everyday language, and the system automatically understands and returns accurate query results.

[0098] In an optional embodiment, the first processing technology can adopt the fuzzy document repair technology enhanced by the Generative Adversarial Network (GAN), train the GAN model, input the fuzzy paper document image, the generator outputs the high-resolution repair result, and directly inputs the customized handwriting recognition model; significantly improve the data extraction accuracy of low-quality paper documents and reduce the need for manual reshooting.

[0099] In an optional embodiment, the first processing technology can also be a document parsing technology driven by a graph neural network (GNN) to construct a document graph structure, aggregate neighborhood information through a GNN model, learn semantic associations between fields, combine global graph context and local visual features, and infer missing field content; it is good at processing complex logical relationships in unstructured documents and improving field completion and error correction capabilities.

[0100] In the embodiment of the present application, the first processing technology includes using natural language processing (NLP) technology to realize natural language interaction between the user and the system, and the user can ask questions in everyday language;

[0101] Supports mixed voice and text input, and pre-trains a semantic model specifically for occupational health. This includes building a domain vocabulary based on occupational disease classifications, physical examination indicator terms (such as "pulmonary function FEV1 value"), and regulatory keywords (such as "GBZ 188") to improve the accuracy of professional terminology recognition. The system automatically associates user identity, historical operations, and current data focus. When queries are ambiguous, the system provides visual guidance for user clarification.

[0102] When converting natural language into structured queries, we combine the rule engine (which processes fixed sentences such as "Export the data of XX department in XX year") and the neural network model;

[0103] An occupational health knowledge graph is constructed, containing node relationships such as "position - hazard factor - mandatory inspection items - associated diseases." When a user queries, "Is A's physical examination complete?" the system compares the mandatory inspection items corresponding to their position, marks any missing items, and generates a prompt: "A's noise position does not contain any missing items."

[0104] Layered result display: First layer, core results are output as speech summaries;

[0105] Second layer: The screen displays interactive statistical charts (such as a heat map showing the annual trend of lung function among workers exposed to dust), which users can refine with voice commands ("see only the foundry data");

[0106] The third layer: Detailed data supports AR projection (such as viewing a 3D timeline of an employee's physical examination indicators over the years through smart glasses).

[0107] S6: Data analysis and risk assessment module includes data preprocessing, building data analysis models, data analysis and report generation;

[0108] It should be noted that the collected occupational health monitoring archive data is pre-processed by cleaning, deduplication, standardization and other operations to ensure the quality and availability of the data;

[0109] Specifically, the health indicator data of different dimensions are converted into a unified standard. For a set of data x1, x2, ..., x i ,…,x n , whose mean is The standard deviation is σ, and the expression of the standardized data is:

[0110]

[0111] Among them, n is the specific number of a set of data, and i is the variable index;

[0112] Taking mean filling as an example, when a health indicator y has missing values, it is filled with the mean y of the indicator:

[0113]

[0114] Among them, y j is the non-missing value data of the indicator, m is the number of non-missing value data, j is the variable index, Fill in the missing value locations.

[0115] Furthermore, big data analysis technology can be used to conduct in-depth analysis of occupational health monitoring file data through occupational disease risk assessment models to explore the potential patterns and risks behind the data. For example, by analyzing employees' work environment, occupational history, physical examination data, etc., the risk probability of employees contracting occupational diseases can be predicted.

[0116] In the embodiment of the present application, an occupational disease risk assessment model and a health index prediction model are established;

[0117] Specifically, the occupational disease risk assessment model is to build a risk assessment model based on logistic regression, assuming that the occurrence of occupational diseases (z = 1 means occupational disease, z = 0 means no occupational disease) is related to multiple influencing factors a1, a2, ..., a p (such as exposure to harmful substances, exposure time, personal physical indicators, etc.). The expression of the logistic regression model is:

[0118]

[0119] Among them, β0 is the intercept term, β1,β2,…,β p is the regression coefficient, which can be solved by methods such as maximum likelihood estimation;

[0120] The weights are determined by the hierarchical analysis method and combined with the comprehensive evaluation model to construct a judgment matrix to determine the weights of each influencing factor w1, w2, ..., w i ,…,w p , suppose the comprehensive score of occupational disease risk assessment is S, and there are p influencing factors a1, a2, ..., a i ,…,a p , then the comprehensive evaluation model is:

[0121]

[0122] Different risk levels are divided according to the size of S, including low risk (S≤3), medium risk (3<S<6.5), and high risk (S≥6.5).

[0123] It should also be noted that by establishing a health indicator prediction model, the risk of occupational diseases can be predicted, providing a scientific basis for enterprises to formulate preventive measures.

[0124] Specifically, the health index prediction model is as follows: assuming that the health index y is related to multiple influencing factors 1, a1, a2, ..., a i ,…,ap There is a linear relationship between them, and the linear regression model expression is:

[0125] y=β0+β1a1+β2a2+…+β p a p +∈

[0126] Among them, β0 is the intercept term, β1,β2,…,β p is the regression coefficient, ∈ is the error term, and it obeys the normal distribution with mean 0;

[0127] The regression coefficient is estimated by the least square method and other methods, and then the future health index k is predicted;

[0128] Based on the ARIMA model of time series, let the time series {k t}, the expression of the ARIMA(p,d,q) model is:

[0129] Φ(B)(1-B) d k t =Θ(B)∈ t

[0130] Where B is the lag operator, (1-B) d is the difference operator, d is the difference order, is a p-order autoregressive polynomial, Θ(B)=1+θ1B+…+θ q B q is a q-order sliding mean polynomial, ∈ t is a white noise sequence;

[0131] By analyzing historical health indicator data, appropriate (p, d, q) values are determined, and a model is constructed to predict health indicators.

[0132] Generate and analyze reports and visual charts to intuitively display the company's occupational health status, such as the incidence of occupational diseases in different positions, changing trends in employee health indicators, etc., to help company management make decisions.

[0133] S7: The warning and reminder module includes setting warning rules, sending warning information, and tracking warning processing;

[0134] It should be noted that warning rules are set in the module. When an employee's health indicators exceed the normal range, the physical examination time expires, or the risk of occupational disease increases, the system will send warning information to the corresponding personnel via SMS, email, or system message;

[0135] For example: when an employee's blood pressure, blood sugar and other health indicators exceed the normal range, when an employee's physical examination time expires, when the occupational disease risk of a certain position reaches a certain threshold, etc., the system automatically triggers an early warning.

[0136] Among them, the employee physical examination is due within one year. If the employee's health indicators exceed the normal range, when the data value in the employee's physical examination report is greater than or equal to the occupational disease data, an alert will be triggered. For example, if the employee's blood pressure exceeds the hypertension standard (systolic pressure 140mmHg or diastolic pressure 90mmHg), an alert will be triggered;

[0137] It should also be noted that when a warning event occurs, the system sends warning information to relevant personnel via SMS, email, in-system messages, etc. For example, it sends physical examination reminder SMS to employees and occupational disease risk warning emails to occupational health managers to reduce the risk of occupational diseases.

[0138] Track and record the handling process of warning events to ensure that warning issues are resolved in a timely manner. After receiving warning information, relevant personnel will take appropriate measures and record the handling results in the system.

[0139] S8: User rights management module includes user role management, user account management, rights allocation and adjustment;

[0140] It should be noted that system administrators can create, modify, and delete user roles, defining different operational permissions and function menus for each role to ensure the security and confidentiality of system data. For example, administrators have the highest permissions, allowing them to fully manage and configure the system; employees can only view and modify their own personal files; occupational health managers can view and manage the files of their department's employees; and doctors can enter and view employee physical examination reports and diagnosis results.

[0141] Unified management of user accounts, including user registration, login verification, password reset, etc. Users use a unique account and password to log in to the system to ensure account security;

[0142] Assign and adjust user permissions in a timely manner based on changes in the company's organizational structure and personnel responsibilities. For example, when an employee's position changes, their permissions in the system will be adjusted accordingly.

[0143] Specifically, the system maintenance and update module includes system monitoring, vulnerability repair and security upgrades, function optimization and upgrades, and system log management;

[0144] It should be noted that a system monitoring mechanism is established to monitor the system's operating status in real time, including server performance, network connection, database load, etc. When the system is abnormal, an alarm is issued in time to notify the system administrator to handle it.

[0145] Regularly perform security scans on the system to identify and fix system vulnerabilities. Timely update system security patches to prevent network attacks and data leakage risks, optimize system performance, and ensure stable system operation.

[0146] Based on user feedback and business needs, we optimize and upgrade the system's functionality. For example, we add new data analysis functions, improve the user interface design, and enhance the system's usability and practicality.

[0147] Record system operation and operation logs, including user login records, data operation records, system error messages, etc. Provide system log management functions to record system operation records and operating status, facilitating system troubleshooting and auditing. By analyzing system logs, understand system usage and operating status, providing a basis for system maintenance and optimization. Based on the company's business needs and technological development trends, timely upgrade and expand system functions to meet the company's ever-changing occupational health management needs.

[0148] Embodiment 2, the second embodiment of the present invention, is different from the previous embodiment in that:

[0149] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0150] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0151] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0152] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0153] Example 3 is the third embodiment of the present invention, which provides an intelligent management system for occupational health monitoring archives. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0154] To verify the effectiveness of this system, a chemical company (employee size: 2,000) was selected as a test subject, comparing the existing traditional Excel + paper file management model (control group) with this system (experimental group). The trial period lasted for 6 months, and the test scenarios included data entry, storage security, query efficiency, risk assessment, and early warning response.

[0155] 1. System deployment and environment construction

[0156] Server configuration: Use Alibaba Cloud ECS instance (16-core CPU / 64GB memory / 1TB SSD), deploy CentOS 8 system, install MySQL 8.0 database and Nginx application server, and use HTTPS protocol to ensure communication security.

[0157] Client devices: The enterprise side is equipped with 10 Windows 10 workstations, and the medical institution side is connected to 3 Mac devices, installed with Chrome browser and customized client software.

[0158] Data initialization: Import historical enterprise data (12,000 employee files from 2018 to 2023), including occupational history and physical examination reports (including 5TB of imaging data), and use data cleaning tools to process missing values (fill rate > 98%).

[0159] 2. Data collection and identification verification

[0160] Multimodal Recognition Test: 500 paper medical examination reports (containing a mix of handwritten annotations and charts) were randomly selected and recognized using the system's built-in OCR module. The scanning device used was a Fujitsu fi-8170 high-speed scanner, and the test environment was set to 300-500 Lux.

[0161] Data verification process: The recognition results are compared with the manually entered data, and the system automatically marks the difference fields (such as blood pressure values and lung function indicators) to trigger the manual review mechanism.

[0162] 3. Risk assessment and early warning testing

[0163] Model training: Based on logistic regression and ARIMA models, the occupational disease risk prediction model was trained using historical data (2018-2022). The input variables included the duration of exposure to hazardous substances (months), the deviation of physical examination indicators (σ value), and the job type (encoded as a one-hot vector).

[0164] Warning rule setting: define systolic blood pressure ≥ 140 mmHg and lung function FEV1 / FVC < 70% as thresholds, and the warning information will be pushed to the responsible person in real time through the enterprise WeChat API.

[0165] 4. Security and performance stress testing

[0166] Encrypted storage verification: AES-256 shard encryption (shard size 1MB) and off-site RAID-6 redundant storage are used to simulate hard drive failures and network attack scenarios (such as DDOS and SQL injection).

[0167] Concurrent performance testing: Use JMeter to simulate 200 users executing complex queries simultaneously (such as "Export liver function data of employees exposed to styrene for the past three years") and record the system response time and error rate.

[0168] In a field test of this system with 2,000 employees at a chemical company, compared with the traditional Excel + paper file management model and ordinary database systems, the core performance indicators were significantly improved:

[0169] Based on OCR technology, the system achieves a data entry efficiency of 89.2 documents per hour, a 382% improvement over the traditional model (18.5 documents per hour). The handwriting recognition error rate has been reduced from 27.7% to 1.9%, and the field positioning accuracy for mixed layouts has reached 99.3%. Through semantic error correction and batch processing optimization, the manual review rate for 500 paper reports has been reduced to only 1.8%, significantly reducing labor costs.

[0170] Using AES-256 shard encryption and off-site RAID-6 redundant storage, the system achieves NIST SP 800-57 Level 5 security (traditional systems are Level 1). Data shard encryption ensures 99.7% of valid information remains unleashed. In a simulated attack, data recovery time was reduced to 15 minutes (compared to a traditional four hours), and off-site replica switching latency was less than three seconds, ensuring business continuity.

[0171] Natural language processing (NLP) technology reduced complex query response time to 1.2 seconds (compared to 4.8 seconds for conventional databases), achieved 93.4% semantic parsing accuracy, and detected 23 cases missed by traditional methods. The occupational disease prediction model achieved an AUC of 0.92 (compared to 0.78 for traditional models), providing six months' advance warning for 58 high-risk employees and confirming 12 early cases of pneumoconiosis, validating the model's clinical value.

[0172] A multi-channel, real-time push notification mechanism ensures 96.4% timely warnings (compared to 65.2% with traditional models). Dynamic thresholds adapt to different job risks (e.g., a 5dB lower hearing threshold for noise exposure). The system automatically generates tracking tasks and implements closed-loop management. Unprocessed tasks are reported escalating to avoid management loopholes.

[0173] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0174] Example 4

[0175] In an optional embodiment, a detailed method based on the above system and method can be designed, specifically including:

[0176] The server uses a high-performance cloud computing server with sufficient computing power, storage capacity and network bandwidth to meet the needs of system operation and data storage.

[0177] Client devices include computers and tablets used by enterprise employees and managers, which are connected to the server through the network;

[0178] The server operating system should be Windows Server or Linux, and the database management system (at least MySQL, Oracle, etc.) and application server software (at least Tomcat, Nginx, etc.) should be installed. The client operating system supports mainstream operating systems such as Windows, Mac OS, and Linux, and the browser supports Chrome, Firefox, Edge, etc.

[0179] It should also be noted that an occupational health monitoring archive management database should be created in the database management system, and the database table structure should be designed, including employee basic information table, occupational history table, physical examination report table, occupational disease diagnosis table, etc., and the relationship between the tables should be established;

[0180] Import the company's existing employee basic information, career history and other basic data into the system to ensure data integrity and accuracy;

[0181] Create different user roles based on the company's organizational structure and personnel responsibilities, such as administrators, occupational health managers, corporate employees, doctors, etc., and assign corresponding operation permissions to each role;

[0182] Set basic system parameters, such as warning thresholds, data backup cycles, report templates, etc., and perform personalized configuration based on the actual needs of the enterprise.

[0183] Clean, transform and store the collected data.

[0184] Through multi-data collection, establish a data interface with the system to automatically collect data and update it in real time. Support multi-data collection, including manual entry, batch import, interface docking, etc.

[0185] Furthermore, manual data entry: For data that cannot be obtained through the interface, such as employees' occupational history and medical history, relevant personnel manually enter it into the system. During the data entry process, the system provides real-time data verification and prompts to ensure the accuracy of the entered data.

[0186] Batch import: Large amounts of employee physical examination data, training records, etc. can be organized using Excel spreadsheets and then imported into the system using the system's batch import function. The system automatically converts and verifies the imported data to ensure data consistency.

[0187] Interface connection: Establish data interfaces with medical institutions, physical examination centers, and other systems. Automatically transmit and update physical examination reports, diagnosis results, and other data in real time according to pre-defined data formats and interface specifications. When employees complete their physical examinations, the data is automatically synchronized to this system without manual intervention.

[0188] It should be noted that at the same time, the data in the paper document is automatically recognized and entered through the first recognition method.

[0189] The first recognition method uses optical character recognition technology to automatically recognize and enter the data in the paper document, improving the efficiency and accuracy of data collection. The specific process is as follows:

[0190] The user takes pictures of the paper document through a high-speed camera, scanner or mobile phone camera, supporting continuous multi-page scanning. The system automatically detects the image clarity and prompts to retake the blurred area. An AR guidance frame is superimposed on the screen in real time, automatically selecting the area to be recognized (such as the name column, test result table), and prompting "Please align the camera with the red frame"; after recognition, the key data is superimposed on the original paper document image in the form of floating labels, and the user can confirm by voice (such as "Save data" or "Re-recognize");

[0191] Automatically crop irrelevant backgrounds (such as desktop clutter), correct tilted and distorted pages, remove shadow and fold interference, and enhance the contrast of text;

[0192] Adopt multi-engine collaboration (such as Tesseract + commercial API) to distinguish printed text from handwritten text:

[0193] Recognition of printed text: Directly extract the text content, recognize the table frame lines and reconstruct the structured data;

[0194] Recognition of handwritten text: Analyze scribbled handwriting and correct errors in combination with context semantics (such as "hemoglobin" → "hemoglobin").

[0195] Automatically match the recognition results with database fields (such as employee ID, physical examination date), and missing data triggers a pop-up window to remind the user to supplement; numerical data (such as blood pressure value) is automatically verified for reasonableness (such as systolic blood pressure > 300 is marked red for alarm).

[0196] When doctors or administrators review the recognition results, they can add annotation labels (such as "suspected pneumoconiosis") to the document image. The system automatically associates them with the employee's health risk assessment module and triggers subsequent tracking tasks (such as "arrange a re-examination").

[0197] Adopt distributed database technology to store the collected data on multiple nodes of the distributed database according to the database table structure, ensuring the security and reliability of the data;

[0198] Encrypt the data for storage through a preset encryption method to prevent data leakage;

[0199] It should be noted that the preset encryption method is the combined application of data sharding encryption and redundant storage encryption:

[0200] Occupational health monitoring file data is first encrypted in slices, then redundantly stored, and each redundant copy is encrypted again. For example, a file containing an employee's occupational history and historical physical examination results is first sliced by information category, and each slice is encrypted using AES. These encrypted slices are then stored on multiple servers in different locations, and all copies of the sliced data stored on each server are encrypted using the RSA algorithm. This combination of data sharding, redundant storage, and multiple encryption creates a multi-layered data security system that effectively protects the confidentiality, integrity, and availability of occupational health monitoring file data.

[0201] It should also be noted that the files are classified and stored according to the employees' positions, types of work, occupational hazard factors, etc., and an index directory is established to facilitate query and management; for example, the files of employees working in the chemical industry are classified into one category, and the files of employees exposed to dust are classified into another category, etc.; the classified management of files is realized, and the files are classified and stored according to the employees' positions, types of work, occupational hazard factors, etc., to facilitate query and management.

[0202] Regularly perform full and incremental backups of the database and store the backup data in an off-site storage device. In the event of a system failure or data loss, the backup data can be used for rapid recovery to ensure normal system operation.

[0203] Users enter keywords in the query interface, such as employee name, work number, physical examination items, etc. The system quickly retrieves relevant file information and displays the query results to the user.

[0204] Users can conduct precise searches by setting multiple search criteria, such as physical examination time range, job type, health index range, etc. The system will filter out the files that meet the conditions set by the user, sort them, and display them.

[0205] The first processing technology is used to conduct natural language interaction between users and the system, supporting fuzzy queries and associated queries. It can associate relevant archival records based on partial information input by the user and display other related information; such as "Query Zhang San's physical examination report for the past year" and "List all employees who are exposed to noise and have hearing abnormalities", etc. The system uses natural language processing technology to understand the user's questions and return accurate query results.

[0206] It should be noted that the first processing technology uses natural language processing (NLP) technology to achieve natural language interaction between users and the system, and users can ask questions in everyday language;

[0207] Supports mixed voice and text input, and pre-trains a semantic model specifically for occupational health. This includes building a domain vocabulary based on occupational disease classifications, physical examination indicator terms (such as "pulmonary function FEV1 value"), and regulatory keywords (such as "GBZ 188") to improve the accuracy of professional terminology recognition. The system automatically associates user identity, historical operations, and current data focus. When queries are ambiguous, the system provides visual guidance for user clarification.

[0208] When converting natural language into structured queries, we combine the rule engine (which processes fixed sentences such as "Export the data of XX department in XX year") and the neural network model;

[0209] An occupational health knowledge graph is constructed, containing node relationships such as "position - hazard factor - mandatory inspection items - associated diseases." When a user queries, "Is A's physical examination complete?" the system compares the mandatory inspection items corresponding to their position, marks any missing items, and generates a prompt: "A's noise position does not contain any missing items."

[0210] Layered result display: First layer, core results are output as speech summaries;

[0211] Second layer: The screen displays interactive statistical charts (such as a heat map showing the annual trend of lung function among workers exposed to dust), which users can refine with voice commands ("see only the foundry data");

[0212] The third layer: Detailed data supports AR projection (such as viewing a 3D timeline of an employee's physical examination indicators over the years through smart glasses).

[0213] It should be noted that the collected occupational health monitoring archive data is pre-processed by cleaning, deduplication, standardization and other operations to ensure the quality and availability of the data;

[0214] Specifically, the health indicator data of different dimensions are converted into a unified standard. For a set of data x1, x2, ..., x i ,…,x n , whose mean is The standard deviation is σ, and the expression of the standardized data is:

[0215]

[0216] Among them, n is the specific number of a set of data, and i is the variable index;

[0217] Taking mean filling as an example, when a health indicator y has missing values, it is filled with the mean y of the indicator:

[0218]

[0219] Among them, y jis the non-missing value data of the indicator, m is the number of non-missing value data, j is the variable index, Fill in the missing value locations.

[0220] Furthermore, big data analysis technology can be used to conduct in-depth analysis of occupational health monitoring file data through occupational disease risk assessment models to explore the potential patterns and risks behind the data. For example, by analyzing employees' work environment, occupational history, physical examination data, etc., the risk probability of employees contracting occupational diseases can be predicted.

[0221] In the embodiment of the present application, an occupational disease risk assessment model and a health index prediction model are established;

[0222] Specifically, the occupational disease risk assessment model is to build a risk assessment model based on logistic regression, assuming that the occurrence of occupational diseases (z = 1 means occupational disease, z = 0 means no occupational disease) is related to multiple influencing factors a1, a2, ..., a p (such as exposure to harmful substances, exposure time, personal physical indicators, etc.). The expression of the logistic regression model is:

[0223]

[0224] Among them, β0 is the intercept term, β1,β2,…,β p is the regression coefficient, which can be solved by methods such as maximum likelihood estimation;

[0225] The weights are determined by the hierarchical analysis method and combined with the comprehensive evaluation model to construct a judgment matrix to determine the weights of each influencing factor w1, w2, ..., w i ,…,w p , suppose the comprehensive score of occupational disease risk assessment is S, and there are p influencing factors a1, a2, ..., a i ,…,a p , then the comprehensive evaluation model is:

[0226]

[0227] Different risk levels are divided according to the size of S, including low risk (S≤3), medium risk (3<S<6.5), and high risk (S≥6.5).

[0228] It should also be noted that by establishing a health indicator prediction model, the risk of occupational diseases can be predicted, providing a scientific basis for enterprises to formulate preventive measures.

[0229] Specifically, the health index prediction model is as follows: assuming that the health index y is related to multiple influencing factors 1, a1, a2, ..., a i ,…,a p There is a linear relationship between them, and the linear regression model expression is:

[0230] y=β0+β1a1+β2a2+…+β p a p +∈

[0231] Among them, β0 is the intercept term, β1,β2,…,β p is the regression coefficient, ∈ is the error term, and it obeys the normal distribution with mean 0;

[0232] The regression coefficient is estimated by the least square method and other methods, and then the future health index k is predicted;

[0233] Based on the ARIMA model of time series, let the time series {k t}, the expression of the ARIMA(p,d,q) model is:

[0234] Φ(B)(1-B) d k t =Θ(B)∈ t

[0235] Where B is the lag operator, (1-B) d is the difference operator, d is the difference order, is a p-order autoregressive polynomial, Θ(B)=1+θ1B+…+θ q B q is a q-order sliding mean polynomial, ∈ t is a white noise sequence;

[0236] By analyzing historical health indicator data, appropriate (p, d, q) values are determined, and a model is constructed to predict health indicators.

[0237] Use data analysis tools to conduct in-depth analysis of data, generate data analysis reports and visual charts, and intuitively display the company's occupational health status, such as the incidence of occupational diseases in different positions, changing trends in employee health indicators, etc., to help corporate management make decisions.

[0238] It should be noted that warning rules are set in the module. When an employee's health indicators exceed the normal range, the physical examination time expires, or the risk of occupational disease increases, the system will send warning information to the corresponding personnel via SMS, email, or system message;

[0239] For example: when an employee's blood pressure, blood sugar and other health indicators exceed the normal range, when an employee's physical examination time expires, when the occupational disease risk of a certain position reaches a certain threshold, etc., the system automatically triggers an early warning.

[0240] Among them, the employee physical examination is due within one year. If the employee's health indicators exceed the normal range, when the data value in the employee's physical examination report is greater than or equal to the occupational disease data, an alert will be triggered. For example, if the employee's blood pressure exceeds the hypertension standard (systolic pressure 140mmHg or diastolic pressure 90mmHg), an alert will be triggered;

[0241] It should also be noted that when a warning event occurs, the system sends warning information to relevant personnel via SMS, email, in-system messages, etc. For example, it sends physical examination reminder SMS to employees and occupational disease risk warning emails to occupational health managers to reduce the risk of occupational diseases.

[0242] Track and record the handling process of warning events to ensure that warning issues are resolved in a timely manner. After receiving warning information, relevant personnel will take appropriate measures and record the handling results in the system.

[0243] It should be noted that system administrators can create, modify, and delete user roles, defining different operational permissions and function menus for each role to ensure the security and confidentiality of system data. For example, administrators have the highest permissions, allowing them to fully manage and configure the system; employees can only view and modify their own personal files; occupational health managers can view and manage the files of their department's employees; and doctors can enter and view employee physical examination reports and diagnosis results.

[0244] Unified management of user accounts, including user registration, login verification, password reset, etc. Users use a unique account and password to log in to the system to ensure account security;

[0245] Assign and adjust user permissions in a timely manner based on changes in the company's organizational structure and personnel responsibilities. For example, when an employee's position changes, their permissions in the system will be adjusted accordingly.

[0246] It should be noted that a system monitoring mechanism is established to monitor the system's operating status in real time, including server performance, network connection, database load, etc. When the system is abnormal, an alarm is issued in time to notify the system administrator to handle it.

[0247] Regularly perform security scans on the system to identify and fix system vulnerabilities. Timely update system security patches to prevent network attacks and data leakage risks, optimize system performance, and ensure stable system operation.

[0248] Based on user feedback and business needs, we optimize and upgrade the system's functionality. For example, we add new data analysis functions, improve the user interface design, and enhance the system's usability and practicality.

[0249] Record system operation and operation logs, including user login records, data operation records, system error messages, etc. Provide system log management functions to record system operation records and operating status, facilitating system troubleshooting and auditing. By analyzing system logs, understand system usage and operating status, providing a basis for system maintenance and optimization. Based on the company's business needs and technological development trends, timely upgrade and expand system functions to meet the company's ever-changing occupational health management needs.

Claims

1. An intelligent management system for occupational health monitoring archives, characterized by: Includes data acquisition layer, data processing layer, business logic layer and user interaction layer; The data collection layer includes a data collection and entry module, which is responsible for obtaining occupational health data from the data source; The data processing layer cleans, converts and stores the collected data; The business logic layer includes an archive storage and management module, an intelligent query and retrieval module, a data analysis and risk assessment module, and an early warning and reminder module, which perform the core business functions of the system, including archive management and data analysis; The user interaction layer includes a user authority management module and a system maintenance and update module, which are operated through a user-friendly interface.

2. A method for intelligent management of occupational health monitoring files, applied to the intelligent management system for occupational health monitoring files as claimed in claim 1, characterized in that: The data acquisition and entry module includes establishing a data interface with the system through multiple data acquisition to automatically acquire and update data in real time. At the same time, it automatically recognizes and enters data in paper documents through a first recognition method.

3. The intelligent management method for occupational health monitoring files according to claim 2, characterized in that: The data collection and entry module also includes selecting a server and a database management system, and setting up client devices including computers used by the client, connected to the server via a network; In the database management system, the occupational health monitoring archive management database is established and the collected data is imported. According to the enterprise's organizational structure and personnel responsibilities, user roles are created and corresponding operation permissions are assigned to each role. The basic parameters of the system are set and personalized configuration is performed according to the actual needs of the enterprise.

4. The intelligent management method for occupational health monitoring files according to claim 3, characterized in that: The file storage and management module includes storing the collected data on multiple nodes of a distributed database according to the database table structure and encrypting the data using a preset encryption method; Categorize and store the encrypted files and create an index directory; Establish a data backup and recovery mechanism, back up data regularly, and quickly restore data when it is lost or damaged.

5. The intelligent management method for occupational health monitoring files according to claim 4, characterized in that: The intelligent query and retrieval module includes: users input keywords in the query interface, the system quickly retrieves relevant archive information, and displays the query results to the user; The user sets the query conditions, and the system selects the archive records that meet the conditions according to the user's conditions, sorts them, and displays them; The first processing technology is used to conduct natural language interaction between the user and the system, identify part of the information input by the user, and associate all related archival records.

6. The intelligent management method for occupational health monitoring files according to claim 5, characterized in that: The data analysis and risk assessment module includes using big data analysis technology to conduct in-depth analysis of occupational health monitoring file data through occupational disease risk assessment models to explore the potential patterns and risks behind the data; By establishing a health indicator prediction model, we can predict the risk of occupational diseases and provide a scientific basis for enterprises to formulate preventive measures; Use data analysis tools to conduct in-depth analysis of data and generate data analysis reports and visual charts.

7. The intelligent management method for occupational health monitoring files according to claim 6, characterized in that: The warning and reminder module includes setting warning rules in the module. When any of the following situations occurs: an employee's health indicators exceed the normal range, the physical examination time expires, or the risk of occupational disease increases, the system will send a warning message to the corresponding personnel via SMS, email, or system message; The handling process of warning events is tracked and recorded. After receiving the warning information, the corresponding personnel take corresponding measures and record the handling results in the system.

8. The intelligent management method for occupational health monitoring files according to claim 7, characterized in that: The user interaction layer includes, in the user rights management module, the system administrator is allowed to create, modify and delete user roles, and define different operation permissions and function menus for each role; Conduct unified management of user accounts, including at least user registration, login verification, and password reset. Users log into the system using a unique account and password. User permissions are allocated and adjusted in a timely manner based on changes in the company's organizational structure and personnel responsibilities. The system maintenance and update module establishes a system monitoring mechanism to monitor the system's operating status in real time, including server performance, network connection, and database load. When the system encounters an abnormality, it will promptly issue an alarm to notify the system administrator for processing; Regularly perform security scans on the system to discover and repair system vulnerabilities, promptly update system security patches, and prevent network attacks and data leakage risks; Optimize and upgrade the system's functions based on feedback from the user rights management module and business needs; Record the system's operation logs and running logs, including user login records, data operation records, and system error information. By analyzing the system logs, determine the system's usage and operating status, and provide a basis for the early warning and reminder modules.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the occupational health monitoring file intelligent management method described in any one of claims 2 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for intelligent management of occupational health monitoring files according to any one of claims 2 to 8 are implemented.

Images