Occupational health risk assessment system
Through multi-dimensional data acquisition and multi-modal analysis models, combined with artificial intelligence technology, the problem of single data dimensions and strong subjectivity in the occupational health risk assessment system is solved, real-time and accurate risk assessment and auxiliary decision support are achieved.
Patent Information
- Application Number
- CN202510491740.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-18
- Publication Date
- 2025-07-25
AI Technical Summary
The existing occupational health risk assessment system has a single data dimension, lacks real-time and strong subjectivity, making it difficult to conduct real-time and accurate assessments.
The multi-dimensional data acquisition module, data preprocessing module, multi-modal analysis model construction module, risk assessment module and decision-making module are adopted, and combined with artificial intelligence technology, a multi-factor comprehensive analysis intelligent model is established to evaluate the occupational health risks of individuals and groups in real time, and provide auxiliary decision-making support.
Real-time and accurate assessment of occupational health risks has been achieved, the objectivity and accuracy of assessment results have been improved, potential risks have been discovered in a timely manner, and timely support for prevention and control measures have been provided.
Smart Images
Figure CN120376108A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of occupational health management, and particularly to an occupational health risk assessment system. Background Art
[0002] With the rapid development of industrialization and urbanization, occupational health problems have become increasingly prominent. In the workplace, workers are faced with various occupational hazard factors, such as chemical substances, physical factors (noise, dust, radiation, etc.), biological factors, as well as poor working postures and labor intensity. These factors may not only lead to the occurrence of occupational diseases, but also affect the physical health and work efficiency of workers.
[0003] Traditional occupational health risk assessment methods mainly rely on regular occupational health examinations and simple environmental monitoring data, and have the following many deficiencies:
[0004] Single data dimension: Traditional methods often only focus on data in a certain aspect, such as only considering the concentration of hazard factors in the workplace or the physical examination results of workers, while ignoring multi-dimensional data such as the exposure intensity of hazard factors, the effectiveness of preventive measures, the susceptible genes of workers, and personal health conditions, resulting in incomplete and inaccurate assessment results.
[0005] Lack of real-time nature: Due to relying on regular inspections and monitoring, traditional methods cannot obtain occupational health-related data in real time, making it difficult to detect potential occupational health risks in a timely manner, and thus unable to take effective preventive and control measures.
[0006] Strong subjectivity: In the assessment process, traditional methods often rely on the experience and subjective judgment of experts, lacking objective and scientific assessment criteria and methods, resulting in certain deviations in the assessment results.
[0007] Difficult to conduct group analysis: Traditional methods are difficult to statistically analyze the health status of occupational groups, unable to timely discover common problems and potential risks existing in occupational groups, and not conducive to formulating targeted preventive and management measures.
[0008] In summary, the existing occupational health risk assessment systems have the disadvantages of single data dimension, lack of real-time nature, and strong subjectivity, and cannot conduct real-time and accurate assessment of occupational health risks. Summary of the Invention
[0009] The purpose of the present invention is to provide an occupational health risk assessment system, aiming to solve the technical problems that the existing occupational health risk assessment systems have the disadvantages of single data dimension, lack of real-time nature, and strong subjectivity, and cannot conduct real-time and accurate assessment of occupational health risks.
[0010] To achieve the above object, the present invention provides an occupational health risk assessment system, including a multi-dimensional data collection module, a data preprocessing module, a multi-modal analysis model construction module, a risk assessment module, a decision-making module, and a visualization interaction module. The multi-dimensional data collection module is used to capture multi-dimensional occupational health-related data. The data preprocessing module is used to preprocess the collected multi-dimensional occupational health-related data. The multi-modal analysis model construction module combines artificial intelligence technology with the occupational health knowledge system to establish a multi-factor comprehensive analysis intelligent model. The risk assessment module is based on the constructed multi-modal analysis model to real-time evaluate the risk of occupational-related diseases of an individual. The decision-making module, according to the risk assessment results, monitors and warns of hazard factors, and provides auxiliary decision-making support for the prevention and management of occupational health problems. The visualization interaction module displays the risk assessment results and decision-making suggestions to the user in an intuitive way, facilitating the user to view and analyze.
[0011] Among them, the multi-dimensional data collection module includes a hazard factor collection sub-module, an exposure intensity collection sub-module, a prevention measure collection sub-module, a susceptible gene collection sub-module, and an individual health status collection sub-module. The hazard factor collection sub-module is used to real-time collect hazard factor data in the workplace. The exposure intensity collection sub-module is used to record information on the time, frequency, and intensity of workers' exposure to various hazard factors. The prevention measure collection sub-module is used to collect information on prevention measures taken in the workplace. The susceptible gene collection sub-module is used to obtain the susceptible gene information of workers. The individual health status collection sub-module is used to obtain the individual health status data of workers.
[0012] Among them, the data preprocessing module includes a data cleaning sub-module, a data standardization sub-module, and a data fusion sub-module. The data cleaning sub-module is used to remove noise, duplicate data, and error data in the data, fill in missing values, and ensure the integrity and accuracy of the data. The data standardization sub-module is used to standardize data in different formats and different dimensions. The data fusion sub-module is used to fuse data from different data sources to construct a unified occupational health data set.
[0013] Among them, the multimodal analysis model construction module includes a feature extraction sub-module, a model selection sub-module, a model training sub-module, and a model evaluation sub-module. The feature extraction sub-module is used to extract features related to occupational health risks from the preprocessed data. The model selection sub-module is used to select a suitable machine learning or deep learning model according to the data characteristics and evaluation requirements. The model training sub-module trains the selected model by using the preprocessed historical data and adjusts the parameters of the model. The model evaluation sub-module evaluates the trained model by adopting the methods of cross-validation and confusion matrix, tests the performance and accuracy of the model, and optimizes the model according to the evaluation results.
[0014] Among them, the risk assessment module includes an individual risk assessment sub-module and a group risk assessment sub-module. The individual risk assessment sub-module is used to input the occupational health-related data of an individual into the multimodal analysis model to calculate the probability and risk level of the individual suffering from occupation-related diseases. The group risk assessment sub-module is used to statistically analyze the health data of an occupational group, evaluate the occupational health risk level and distribution of the group, and discover the common problems and potential risks existing in the group.
[0015] Among them, the decision-making module includes an early warning rule setting sub-module, an early warning information publishing sub-module, and a decision-making suggestion generating sub-module. The early warning rule setting sub-module is used to set early warning rules for different risk levels according to occupational health standards and actual situations. The early warning information publishing sub-module is used to timely publish early warning information to relevant departments and personnel when the early warning conditions are met. The decision-making suggestion generating sub-module is used to generate targeted decision-making suggestions according to the risk assessment and early warning results, combined with the occupational health knowledge system.
[0016] Among them, the occupational health risk assessment system further includes a laborer health management module, which is used to comprehensively and systematically manage the health status of laborers.
[0017] Among them, the laborer health management module includes a health record management sub-module, a health intervention plan formulation sub-module, and a health follow-up sub-module. The health record management sub-module collects occupational health-related data based on the multi-dimensional data collection module and establishes a detailed health record for each laborer. The health intervention plan formulation sub-module formulates a personalized health intervention plan for each laborer based on the health assessment results of the risk assessment module. The health follow-up sub-module is used to conduct regular follow-up on laborers who receive health interventions to understand the changes in their health status and the implementation effects of the intervention measures.
[0018] An occupational health risk assessment system of the present invention includes a multi-dimensional data acquisition module, a data preprocessing module, a multi-modal analysis model construction module, a risk assessment module, a decision-making module, and a visualization interaction module. After the multi-dimensional data acquisition module captures multi-dimensional occupational health-related data, the data preprocessing module is used to preprocess the acquired multi-dimensional occupational health-related data. Then, the multi-modal analysis model construction module combines artificial intelligence technology with the occupational health knowledge system to establish a multi-factor comprehensive analysis intelligent model. The risk assessment module is used to evaluate the occupational-related disease risk situation of an individual in real time, and the decision-making module is used to provide auxiliary decision-making support for the prevention and management of occupational health problems according to the risk assessment results. Finally, the visualization interaction module displays the risk assessment results and decision-making suggestions to the user in an intuitive manner, facilitating the user to view and analyze. This technical solution integrates multi-dimensional occupational health-related data, and through real-time data acquisition and analysis, can timely discover potential occupational health risks, provide timely support for the implementation of prevention and control measures. At the same time, by adopting artificial intelligence technology and a scientific multi-modal analysis model, it avoids the influence of subjective factors in traditional methods and improves the objectivity and accuracy of the assessment results. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.
[0020] Figure 1 It is a schematic block diagram of the occupational health risk assessment system according to the first embodiment of the present invention.
[0021] Figure 2 It is a schematic block diagram of the occupational health risk assessment system according to the second embodiment of the present invention.
[0022] 101 - Multidimensional data acquisition module, 102 - Data preprocessing module, 103 - Multimodal analysis model construction module, 104 - Risk assessment module, 105 - Decision-making module, 106 - Visualization and interaction module, 107 - Hazard factor acquisition sub-module, 108 - Exposure intensity acquisition sub-module, 109 - Preventive measure acquisition sub-module, 110 - Susceptible gene acquisition sub-module, 111 - Personal health status acquisition sub-module, 112 - Data cleaning sub-module, 113 - Data standardization sub-module, 114 - Data fusion sub-module, 115 - Feature extraction sub-module, 116 - Model selection sub-module, 117 - Model training sub-module, 118 - Model evaluation sub-module, 119 - Individual risk assessment sub-module, 120 - Group risk assessment sub-module, 121 - Early warning rule setting sub-module, 122 - Early warning information publishing sub-module, 123 - Decision-making recommendation generation sub-module, 201 - Worker health management module, 202 - Health record management sub-module, 203 - Health intervention plan formulation sub-module, 204 - Health follow-up sub-module. Detailed implementation manners
[0023] The embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are intended to explain the present invention and should not be construed as a limitation to the present invention.
[0024] First embodiment:
[0025] Please refer to Figure 1 , in which Figure 1 is the principle block diagram of the occupational health risk assessment system of the first embodiment.
[0026] The present invention provides an occupational health risk assessment system, which includes a multi-dimensional data acquisition module 101, a data preprocessing module 102, a multi-modal analysis model construction module 103, a risk assessment module 104, a decision-making module 105, and a visualization interaction module 106. The multi-dimensional data acquisition module 101 includes a hazard factor acquisition sub-module 107, an exposure intensity acquisition sub-module 108, a preventive measure acquisition sub-module 109, a susceptible gene acquisition sub-module 110, and a personal health status acquisition sub-module 111. The data preprocessing module 102 includes a data cleaning sub-module 112, a data standardization sub-module 113, and a data fusion sub-module 114. The multi-modal analysis model construction module 103 includes a feature extraction sub-module 115, a model selection sub-module 116, a model training sub-module 117, and a model evaluation sub-module 118. The risk assessment module 104 includes an individual risk assessment sub-module 119 and a group risk assessment sub-module 120. The decision-making module 105 includes an early warning rule setting sub-module 121, an early warning information release sub-module 122, and a decision-making suggestion generation sub-module 123. By the foregoing solution, the problems of the existing occupational health risk assessment system, such as single data dimension, lack of real-time nature, and strong subjectivity, and the inability to perform real-time and accurate assessment of occupational health risks are solved. It can be understood that the foregoing solution can be used in the architecture of the occupational health risk assessment system.
[0027] For this specific embodiment, after the multi-dimensional data acquisition module 101 captures multi-dimensional occupational health-related data, the data preprocessing module 102 preprocesses the captured multi-dimensional occupational health-related data. Then, the multi-modal analysis model construction module 103 combines artificial intelligence technology with the occupational health knowledge system to establish a multi-factor comprehensive analysis intelligent model. The risk assessment module 104 real-time assesses the occupational-related disease risk situation of an individual, and the decision-making module 105 provides auxiliary decision-making support for the prevention and management of occupational health problems according to the risk assessment results. Finally, the visualization interaction module 106 intuitively displays the risk assessment results and decision-making suggestions to the user, facilitating the user to view and analyze. This technical solution integrates multi-dimensional occupational health-related data. By real-time collecting and analyzing data, potential occupational health risks can be discovered in a timely manner, providing timely support for the implementation of prevention and control measures. At the same time, the use of artificial intelligence technology and a scientific multi-modal analysis model avoids the influence of subjective factors in traditional methods and improves the objectivity and accuracy of the assessment results.
[0028] Among them, the hazard factor collection sub-module 107 collects hazard factor data such as chemical substance concentrations, physical factor intensities (such as noise decibel levels, dust concentrations, radiation doses, etc.), and types and quantities of biological factors in the workplace in real time through sensors, monitoring devices, etc. The exposure intensity collection sub-module 108 is used to record information such as the time, frequency, and intensity of workers' exposure to various hazard factors, which can be obtained through intelligent wearable devices (such as smart bracelets, smart watches, etc.) or work record systems. The preventive measure collection sub-module 109 is used to collect information related to preventive measures taken in the workplace, such as the operation status of ventilation equipment, the usage of protective equipment, etc. The susceptible gene collection sub-module 110 obtains the susceptible gene information of workers by cooperating with gene testing institutions or using existing gene databases. The personal health status collection sub-module 111 is used to integrate personal health status data of workers, such as physical examination reports, medical records, and living habits (such as diet, exercise, smoking, drinking, etc.).
[0029] Secondly, the data cleaning sub-module 112 is used to remove noise, duplicate data, and error data in the data, fill in missing values, and ensure the integrity and accuracy of the data. The data standardization sub-module 113 is used to standardize data in different formats and different dimensions to make them comparable and facilitate subsequent analysis and modeling. The data fusion sub-module 114 is used to fuse data from different data sources to construct a unified occupational health data set, providing a basis for subsequent multi-modal analysis.
[0030] Meanwhile, the feature extraction sub-module 115 is used to extract features related to occupational health risks from the preprocessed data, such as the types, concentrations, and exposure times of hazard factors, effectiveness indicators of preventive measures, and mutation conditions of susceptible genes, etc. The model selection sub-module 116 is used to select appropriate machine learning or deep learning models according to data characteristics and evaluation requirements, such as decision trees, support vector machines, neural networks, etc. The model training sub-module 117 trains the selected model using the preprocessed historical data, adjusts the parameters of the model, so that it can accurately predict occupational health risks. The model evaluation sub-module 118 evaluates the trained model by using methods such as cross-validation and confusion matrices, tests the performance and accuracy of the model, and optimizes the model according to the evaluation results.
[0031] In addition, the individual risk assessment sub-module 119 is used to input the individual's occupational health-related data into the multi-modal analysis model to calculate the probability and risk level of the individual suffering from occupation-related diseases. The group risk assessment sub-module 120 is used to statistically analyze the health data of the occupational group, evaluate the occupational health risk level and distribution of the group, and discover common problems and potential risks existing in the group.
[0032] Moreover, the warning rule setting sub-module 121 is used to set warning rules for different risk levels according to occupational health standards and actual situations. For example, when the occupational health risk of an individual or a group exceeds a certain threshold, the warning mechanism is triggered. The warning information publishing sub-module 122 is used to publish warning information to relevant departments and personnel in a timely manner when the warning conditions are met, including risk types, risk levels, possible affected ranges, etc. The decision-making suggestion generating sub-module 123 is used to generate targeted decision-making suggestions according to the risk assessment and warning results, combined with the occupational health knowledge system, such as adjusting the management measures of the workplace, improving the use of protective equipment, and conducting health interventions on workers.
[0033] When using the occupational health risk assessment system of this embodiment, after the multi-dimensional data acquisition module 101 captures multi-dimensional occupational health-related data, the data preprocessing module 102 is used to preprocess the acquired multi-dimensional occupational health-related data. Then, the multi-modal analysis model construction module 103 combines artificial intelligence technology with the occupational health knowledge system to establish a multi-factor comprehensive analysis intelligent model. The risk assessment module 104 is used to real-time evaluate the occupational-related disease risk situation of an individual, and the decision-making module 105 is used to provide auxiliary decision-making support for the prevention and management of occupational health problems according to the risk assessment results. Finally, the visualization interaction module 106 displays the risk assessment results and decision-making suggestions to the user in an intuitive manner, facilitating the user to view and analyze. This technical solution integrates multi-dimensional occupational health-related data. By real-time collecting and analyzing data, it can timely discover potential occupational health risks, provide timely support for the implementation of prevention and control measures, and at the same time adopt artificial intelligence technology and a scientific multi-modal analysis model to avoid the influence of subjective factors in traditional methods, improving the objectivity and accuracy of the assessment results.
[0034] Second Embodiment:
[0035] Based on the first embodiment, please refer to Figure 2 , Figure 2 which is the principle block diagram of the occupational health risk assessment system of the second embodiment.
[0036] The occupational health risk assessment system provided by the present invention further includes a worker health management module 201. The worker health management module 201 includes a health record management sub-module 202, a health intervention plan formulation sub-module 203, and a health follow-up sub-module 204.
[0037] For this specific embodiment, the worker health management module 201 is used to comprehensively and systematically manage the health status of workers.
[0038] Among them, the health record management sub-module 202 collects occupational health-related data based on the multi-dimensional data collection module 101, and establishes a detailed health record for each worker. The health intervention plan formulation sub-module 203 formulates a personalized health intervention plan for each worker based on the health assessment results of the risk assessment module 104. The health follow-up sub-module 204 is used to conduct regular follow-ups on the workers who receive health interventions to understand the changes in their health conditions and the implementation effects of the intervention measures.
[0039] When using an occupational health risk assessment system of this embodiment, the health record management sub-module 202 collects occupational health-related data based on the multi-dimensional data collection module 101, and establishes a detailed health record for each worker, including personal basic information, physical examination reports, occupational disease diagnosis records, treatment conditions, etc. It is convenient to conduct long-term tracking and management of the health conditions of workers. The health intervention plan formulation sub-module 203 formulates a personalized health intervention plan for each worker based on the health assessment results of the risk assessment module 104. For example, for workers with occupational health risks, targeted health suggestions are provided, such as adjusting work positions, strengthening protective measures, and performing rehabilitation training. The health follow-up sub-module 204 is used to conduct regular follow-ups on the workers who receive health interventions to understand the changes in their health conditions and the implementation effects of the intervention measures, and timely adjust the intervention plan to ensure the effective improvement of the health of workers.
[0040] The above-disclosed is only a preferred embodiment of the present invention. Of course, the scope of the rights of the present invention cannot be limited thereby. Those of ordinary skill in the art can understand the entire or part of the processes of implementing the above embodiments, and the equivalent changes made according to the claims of the present invention still fall within the scope covered by the present invention.
Claims
1. An occupational health risk assessment system, characterized in that it includes a multi-dimensional data collection module, a data preprocessing module, a multi-modal analysis model construction module, a risk assessment module, a decision-making module, and a visualization interaction module. The multi-dimensional data collection module is used to capture multi-dimensional occupational health-related data. The data preprocessing module is used to preprocess the collected multi-dimensional occupational health-related data. The multi-modal analysis model construction module combines artificial intelligence technology with the occupational health knowledge system to establish a multi-factor comprehensive analysis intelligent model. The risk assessment module, based on the constructed multi-modal analysis model, real-time assesses the occupational-related disease risk situation of an individual. The decision-making module, according to the risk assessment results, monitors and warns of hazard factors, and provides auxiliary decision-making support for the prevention and management of occupational health problems. The visualization interaction module displays the risk assessment results and decision-making suggestions to the user in an intuitive way, facilitating the user to view and analyze.
2. The occupational health risk assessment system according to claim 1, characterized in that the multi-dimensional data collection module includes a hazard factor collection sub-module, an exposure intensity collection sub-module, a prevention measure collection sub-module, a susceptible gene collection sub-module, and a personal health status collection sub-module. The hazard factor collection sub-module is used to collect hazard factor data in the workplace in real time. The exposure intensity collection sub-module is used to record information on the time, frequency, and intensity of a worker's exposure to various hazard factors. The prevention measure collection sub-module is used to collect information on the prevention measures taken in the workplace. The susceptible gene collection sub-module is used to obtain the susceptible gene information of a worker. The personal health status collection sub-module is used to obtain the personal health status data of a worker.
3. The occupational health risk assessment system according to claim 2, characterized in that the data preprocessing module includes a data cleaning sub-module, a data standardization sub-module, and a data fusion sub-module. The data cleaning sub-module is used to remove noise, duplicate data, and error data in the data, fill in missing values, and ensure the integrity and accuracy of the data. The data standardization sub-module is used to standardize data in different formats and different dimensions. The data fusion sub-module is used to fuse data from different data sources to construct a unified occupational health data set.
4. The occupational health risk assessment system according to claim 3, characterized in that the multi-modal analysis model construction module includes a feature extraction sub-module, a model selection sub-module, a model training sub-module, and a model evaluation sub-module. The feature extraction sub-module is used to extract features related to occupational health risks from the preprocessed data. The model selection sub-module is used to select a suitable machine learning or deep learning model according to the data characteristics and evaluation requirements. The model training sub-module trains the selected model by using the preprocessed historical data and adjusts the parameters of the model. The model evaluation sub-module evaluates the trained model by using methods such as cross-validation and confusion matrix, tests the performance and accuracy of the model, and optimizes the model according to the evaluation results.
5. The occupational health risk assessment system according to claim 4, wherein the risk assessment module includes an individual risk assessment sub-module and a group risk assessment sub-module. The individual risk assessment sub-module is used to input the occupational health-related data of an individual into the multi-modal analysis model, calculate the probability and risk level of the individual suffering from occupation-related diseases. The group risk assessment sub-module is used to statistically analyze the health data of an occupational group, evaluate the occupational health risk level and distribution of the group, and discover the common problems and potential risks existing in the group.
6. The occupational health risk assessment system according to claim 5, wherein the decision-making module includes an early warning rule setting sub-module, an early warning information publishing sub-module, and a decision-making suggestion generating sub-module. The early warning rule setting sub-module is used to set early warning rules for different risk levels according to occupational health standards and actual situations. The early warning information publishing sub-module is used to timely publish early warning information to relevant departments and personnel when the early warning conditions are met. The decision-making suggestion generating sub-module is used to generate targeted decision-making suggestions based on the risk assessment and early warning results, combined with the occupational health knowledge system.
7. The occupational health risk assessment system according to claim 1, wherein the occupational health risk assessment system further includes a laborer health management module, which is used to comprehensively and systematically manage the health status of laborers.
8. The occupational health risk assessment system according to claim 7, wherein the laborer health management module includes a health record management sub-module, a health intervention plan formulation sub-module, and a health follow-up sub-module. The health record management sub-module collects occupational health-related data based on the multi-dimensional data collection module and establishes a detailed health record for each laborer. The health intervention plan formulation sub-module formulates a personalized health intervention plan for each laborer based on the health assessment results of the risk assessment module. The health follow-up sub-module is used to conduct regular follow-up on laborers who receive health interventions to understand the changes in their health status and the implementation effects of the intervention measures.