Labor employment risk early warning method and system based on multi-source data
Through multi-source data acquisition and analysis, combined with EDA framework and LSTM-DRL model, VR and AR technology are used to solve the problems of single and lagging labor risk management data in the existing technology, real-time identification of labor risk and Forecasting improves the accuracy and efficiency of risk management.
Patent Information
- Application Number
- CN202411114619.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-14
- Publication Date
- 2024-11-19
AI Technical Summary
The existing labor risk management methods have single data and cannot reflect the risk situation in real time, resulting in lagging management and increasing the probability of accidents and the degree of loss.
Multi-source data collection, including labor activities, environment and equipment operation data on the construction site, process and analyze through the EDA framework, identify risk events, and set up an early warning rule base, combine the LSTM-DRL model to make risk scores and early warning level decisions, and use VR and AR technologies provide real-time early warning interfaces and logos.
It realizes the accurate identification and prediction of labor employment risks, provides a real-time early warning mechanism, improves the accuracy and efficiency of risk management, and reduces the probability and losses of accidents.
Smart Images

Figure CN118981649A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of labor employment risk early warning, and in particular to a labor employment risk early warning method and system based on multi-source data. Background Art
[0002] With the development of the industrial and construction industries, safety and labor risk management in construction site management have become important concerns. Traditionally, these industries rely on experience and rules to manage potential safety risks, such as accident frequency and working conditions. The current labor risk management methods have some limitations. The data sources of traditional methods are usually not diverse enough, and there may be data quality issues. In addition, there is a lag in risk warning, and it is impossible to reflect the labor risk situation in real time. Managers often need to wait for accidents to occur before taking countermeasures, which increases the probability of accidents and the extent of losses. Summary of the invention
[0003] The purpose of the present invention is to provide a labor employment risk early warning method and system based on multi-source data to solve the problem that the existing technology has single data and cannot reflect the labor employment risk situation in real time.
[0004] To solve the above technical problems, the present invention provides the following technical solutions, including: collecting labor data, including labor activity data, environmental data and equipment operation data on the construction site; filling in or deleting missing values, and deleting duplicate and erroneous data for the labor data; processing and analyzing the labor data based on the EDA framework, identifying and generating labor employment risk events; establishing an early warning rule library to determine the early warning level of the labor employment risk event; and pushing early warning information to managers at different levels according to the early warning level of the risk event.
[0005] As a preferred solution of the labor employment risk warning method based on multi-source data described in the present invention, the identifying and generating labor employment risk events includes: performing cluster analysis on the labor data through a clustering algorithm to identify and generate labor employment risk events.
[0006] As a preferred solution of the labor employment risk early warning method based on multi-source data described in the present invention, wherein: establishing an early warning rule base includes: defining influencing factors, the influencing factors include equipment failure rate factors, time influence factors, and environmental factor comprehensive factors; wherein, the equipment failure rate factor is calculated according to the number of equipment failures and the total equipment operating time, the time influence factor is calculated according to the actual working time and the standard working time, and the environmental factor comprehensive factor is calculated according to the environmental adjustment parameters, and the environmental adjustment parameters are used to adjust the influence weights of different environmental factors on the overall risk assessment; the labor employment risk score R is calculated according to the influencing factors; warning thresholds T1 and T2 are set, and according to the labor employment risk score R, the warning levels are set: high risk, medium risk and low risk; when R>T1, the warning level is high risk; when T1≥R>T2, the warning level is medium risk; when R≤T2, the warning level is low risk.
[0007] As a preferred solution of the labor employment risk warning method based on multi-source data described in the present invention, it also includes: taking the historical influencing factor sequence as the input of the LSTM network, and outputting the prediction result of the labor employment risk score R; inputting the prediction result of the environmental state and the labor employment risk score R into the DRL model, deciding the warning level through the Actor network in the DRL model, and evaluating the decision effect of the Actor network through the Critic network.
[0008] As a preferred solution of the labor risk warning method based on multi-source data described in the present invention, it also includes: embedding a real-time risk warning interface in a virtual scene through VR technology, and displaying the warning level of different areas and equipment based on the existing labor risk score R; using AR technology to superimpose risk warning information in the real field of vision of managers. When managers use AR glasses or equipment, they use the device's camera and AR technology to superimpose risk warning signs on the actual construction site to display the warning level of the current area and equipment.
[0009] As a preferred solution of the labor employment risk early warning system based on multi-source data described in the present invention, it includes: a data acquisition module, configured to execute the collection of labor data, including labor activity data, environmental data and equipment operation data on the construction site; a data processing module, configured to execute filling or deleting missing values, deleting duplicate and erroneous data on the labor data; a risk event identification module, configured to execute processing and analysis of the labor data based on the EDA framework, and identify and generate labor employment risk events; a warning level identification module, configured to execute the establishment of a warning rule base, and determine the warning level of the labor employment risk event; a warning information push module, configured to execute the push of warning information to managers at different levels according to the warning level of the risk event.
[0010] As a preferred solution of the labor employment risk warning system based on multi-source data described in the present invention, the risk event identification module is specifically configured to execute: clustering analysis of the labor data through a clustering algorithm to identify and generate labor employment risk events.
[0011] As a preferred solution of the labor employment risk early warning system based on multi-source data described in the present invention, the early warning level identification module is specifically configured to execute: define influencing factors, the influencing factors include equipment failure rate factor, time impact factor, and environmental factor comprehensive factor; wherein, the equipment failure rate factor is calculated according to the number of equipment failures and the total equipment operating time, the time impact factor is calculated according to the actual working time and the standard working time, and the environmental factor comprehensive factor is calculated according to the environmental adjustment parameters, and the environmental adjustment parameters are used to adjust the influence weights of different environmental factors on the overall risk assessment; calculate the labor employment risk score R according to the influencing factors; set early warning thresholds T1 and T2, and set the early warning level according to the labor employment risk score R: high risk, medium risk and low risk; when R>T1, the early warning level is high risk; when T1≥R>T2, the early warning level is medium risk; when R≤T2, the early warning level is low risk.
[0012] As a preferred solution of the labor employment risk early warning system based on multi-source data described in the present invention, it also includes an early warning level prediction module, which is specifically configured to execute: taking the historical influencing factor sequence as the input of the LSTM network, and outputting the prediction result of the labor employment risk score R; inputting the prediction results of the environmental status and the labor employment risk score R into the DRL model, deciding the early warning level through the Actor network in the DRL model, and evaluating the decision effect of the Actor network through the Critic network.
[0013] As a preferred solution of the labor risk warning system based on multi-source data described in the present invention, it also includes a visualization module, which is specifically configured to execute: embedding a real-time risk warning interface in a virtual scene through VR technology, and displaying the warning level of different areas and equipment based on the existing labor risk score R; using AR technology to superimpose risk warning information in the real field of vision of managers. When managers use AR glasses or equipment, they use the device's camera and AR technology to superimpose risk warning signs on the actual construction site to display the warning level of the current area and equipment.
[0014] Beneficial effects of the present invention: The present invention utilizes the EDA framework to process and analyze the integrated data, introduces dynamic early warning rules and personalized push mechanisms, realizes accurate identification of labor risk levels, and predicts potential labor risks through the LSTM-DRL model, which can effectively prevent and control labor risks and provide more accurate support for management decisions. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing 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 labor. Among them:
[0016] Figure 1 This is a flow chart of a labor employment risk early warning method based on multi-source data according to the first embodiment of the present invention;
[0017] Figure 2 This is a schematic diagram of the process of establishing an early warning rule library according to the first embodiment of the present invention. DETAILED DESCRIPTION
[0018] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.
[0019] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and 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.
[0020] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.
[0021] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.
[0022] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.
[0023] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0024] Example 1
[0025] Reference Figure 1-2 , which is the first embodiment of the present invention, and provides a labor employment risk early warning method based on multi-source data, comprising:
[0026] S1: Collect labor data, including labor activity data, environmental data and equipment operation data within the construction site.
[0027] Sensors and monitoring equipment are used to collect real-time labor activity data (such as worker activities, equipment operation, etc.), environmental data (such as temperature, humidity, air quality, etc.), and equipment operation data (such as operating status, fault information, etc.) on the construction site.
[0028] S2: Fill in or delete missing values, and remove duplicate and erroneous data in labor data.
[0029] S3: Based on the EDA framework, process and analyze labor data, identify and generate labor risk events.
[0030] Use event-driven architecture (EDA) to process data streams, monitor and analyze data in real time, and identify potential labor risk events, such as equipment anomalies, working hours anomalies, and environmental anomalies.
[0031] Specifically, the distribution of working hours can be understood through histograms, box plots, etc., to see whether there are abnormal working hours or overtime. Based on the data distribution analysis results, the labor data is clustered and analyzed through clustering algorithms, taking into account various factors such as equipment operation, the nature of work activities and environmental conditions, to identify and generate labor risk events.
[0032] Ideally, the EDA architecture ensures real-time monitoring and diagnostics while data is being collected, enabling any irregularities or abnormal behavior to be captured quickly.
[0033] S4: Establish an early warning rule base to determine the early warning level of labor employment risk events.
[0034] Reference Figure 2 ,Establish an early warning rule base: (1) define influencing factors, which include equipment failure rate factor, time impact factor, and environmental factor comprehensive factor;
[0035] Calculate the equipment failure rate factor R based on the number of equipment failures and the total equipment operating time 设备 :
[0036] R 设备 =F 设备 / T 总设备
[0037] In the formula, F 设备 is the number of equipment failures, T 总设备 is the total equipment operation time, i.e., the total operation time of the equipment during the observation period;
[0038] Calculate the time impact factor R based on the actual working time and standard working time 工作 :
[0039] R 工作 =T 工作 / T 标准
[0040] Where, T 工作 is the actual working time, T 标准 Standard working hours, i.e. theoretical working hours;
[0041] Calculate the comprehensive factor R of environmental factors based on the environmental adjustment parameter α 环境 ,Environmental adjustment parameters are used to adjust the impact weights of different environmental factors on the overall risk assessment.,Environmental factor scores include temperature, humidity, air quality, etc.
[0042] R 环境 =1 / (1+e -α )
[0043] In order to gradually optimize and adjust the environmental adjustment parameter α, a more accurate comprehensive factor of environmental factors R 环境 In this embodiment, the environmental adjustment parameter α is dynamically adjusted by the following formula:
[0044]
[0045] In the formula, α old is the current α value, α new is the updated α value, η is the learning rate, which is used to control the step size of each update, and η is 0.01. It is the partial derivative of the loss function J with respect to α, which is used to measure the influence of α on the comprehensive factors of environmental factors.
[0046] (2) Calculate the labor employment risk score R based on the influencing factors;
[0047] R=w 设备 ·R 设备 +w 工作 ·R 工作 +w 环境 ·R 环境
[0048] In the formula, w 设备 、w 工作 、w 环境 are the weights of equipment failure rate factor, time impact factor, and comprehensive environmental factor, respectively. Considering the high impact of equipment factors on risk score and ensuring that the score R is more accurate, this embodiment uses w 设备 The value is 0.4, w 工作 The value is 0.3, w 环境 The value is 0.3.
[0049] (3) Set warning thresholds T1 and T2, and set warning levels according to the labor employment risk score R: high risk, medium risk and low risk; among them, the warning thresholds T1 and T2 can be set based on the experience and suggestions of experts in the field. Experts will combine historical data, industry standards and actual operation experience to set appropriate warning thresholds T1 and T2.
[0050] a. When R>T1, the warning level is high risk;
[0051] b. When T1≥R>T2, the warning level is medium risk;
[0052] c. When R≤T2, the warning level is low risk.
[0053] Furthermore, in order to predict potential labor risks in the future, this embodiment introduces the LSTM-DRL model to predict labor risks. Specifically, the historical influencing factor sequence is used as the input of the LSTM network, and the prediction result of the labor risk score R is output; this embodiment selects the mean square error (MSE) as the loss function, and updates the weight of the LSTM network through the Adam optimizer.
[0054] The predicted results of environmental conditions (temperature, humidity, light intensity, equipment operating status and fault conditions, etc.) and labor risk score R are input into the DRL model. The probability distribution of each warning level, that is, the decision warning level, is output through the Actor network in the DRL model (Deep Reinforcement Learning), and the decision effect of the Actor network is evaluated through the Critic network.
[0055] Specifically, the Actor network will output the probability of each warning level based on the risk score predicted by LSTM and the current environmental status. The role of the Critic network is to help the Actor network optimize the decision-making strategy to ensure that the output warning level can maximize the risk management effect in the long run. Furthermore, the REINFORCE algorithm or A3C algorithm is used to optimize the parameters of the deep reinforcement learning model to maximize the accuracy and real-time performance of the warning.
[0056] Preferably, EDA provides an agile response capability to immediate events, can quickly detect those foreseeable events, and through in-depth analysis of data combined with the LSTM-DRL model, predict potential risks in the future, and achieve more intelligent and comprehensive early warning.
[0057] S5: Push warning information to managers at different levels based on the warning level of the risk event.
[0058] According to the warning level of risk events, early warning information is pushed to managers at different levels. For example, high-risk risk events are pushed to the project level, company level and group level, medium-risk risk events are pushed to the project level and company level, and low-risk early warning information is pushed to the project level.
[0059] Furthermore, in order to enhance user experience and interaction, this embodiment uses VR (virtual reality) and AR (augmented reality) technologies to provide managers with intuitive risk warning and interactive interfaces, enabling them to monitor and manage construction site risks more efficiently and dynamically adjust warning rules according to actual conditions. Specifically, a real-time risk warning interface is embedded in a virtual scene through VR technology, and the warning levels of different areas and equipment are displayed based on the existing labor risk score R; AR technology is used to overlay risk warning information in the manager's real field of view. When the manager uses AR glasses or equipment, the risk warning logo is overlaid on the actual construction site through the device's camera and AR technology to display the warning level of the current area and equipment.
[0060] Managers can dynamically adjust the warning thresholds T1 and T2 based on actual conditions and through VR or AR interfaces, as well as adjust the weights of environmental factors to reflect the actual conditions and changes on the current construction site.
[0061] Example 2
[0062] This embodiment is different from the first embodiment in that it provides a labor employment risk early warning system based on multi-source data, including:
[0063] The data collection module is configured to collect labor data, including labor activity data, environmental data and equipment operation data within the construction site; it uses sensors, monitoring equipment, etc. to collect labor activity data (such as worker activities, equipment operation, etc.), environmental data (such as temperature, humidity, air quality, etc.), and equipment operation data (such as operating status, fault information, etc.) within the construction site in real time.
[0064] A data processing module is configured to perform filling or deleting missing values, deleting duplicate and erroneous data on the labor data;
[0065] The risk event identification module is configured to execute based on the EDA framework, process and analyze labor data, identify and generate labor risk events; specifically, it is configured to execute: cluster analysis of labor data through clustering algorithms, identify and generate labor risk events, such as equipment anomalies, working hours anomalies, and environmental anomalies.
[0066] The warning level identification module is configured to execute the establishment of a warning rule base to determine the warning level of a labor employment risk event; the warning level identification module is specifically configured to execute: define influencing factors, which include equipment failure rate factors, time impact factors, and comprehensive environmental factors; wherein, the equipment failure rate factor is calculated based on the number of equipment failures and the total equipment operating time, the time impact factor is calculated based on the actual working time and the standard working time, and the comprehensive environmental factor is calculated based on the environmental adjustment parameters, and the environmental adjustment parameters are used to adjust the influence weights of different environmental factors on the overall risk assessment; the labor employment risk score R is calculated based on the influencing factors; the warning thresholds T1 and T2 are set, and according to the labor employment risk score R, the warning levels are set: high risk, medium risk, and low risk; when R>T1, the warning level is high risk; when T1≥R>T2, the warning level is medium risk; when R≤T2, the warning level is low risk.
[0067] The early warning information push module is configured to push early warning information to managers at different levels according to the early warning level of the risk event.
[0068] The warning level prediction module is specifically configured to perform:
[0069] The historical impact factor sequence is used as the input of the LSTM network, and the predicted result of the labor employment risk score R is output;
[0070] The prediction results of the environmental status and the labor risk score R are input into the DRL model, the warning level is decided through the Actor network in the DRL model, and the decision effect of the Actor network is evaluated through the Critic network. That is, the prediction results of the environmental status (temperature, humidity, light intensity, equipment operation status and fault conditions, etc.) and the labor risk score R are input into the DRL model, and the probability distribution of each warning level, that is, the decision warning level, is output through the Actor network in the DRL model (Deep Reinforcement Learning), and the decision effect of the Actor network is evaluated through the Critic network.
[0071] Visualization module, the visualization module is specifically configured to execute: embed a real-time risk warning interface in a virtual scene through VR technology, and display the warning level of different areas and equipment based on the existing labor risk score R; use AR technology to superimpose risk warning information in the manager's real field of vision. When the manager uses AR glasses or equipment, the device's camera and AR technology are used to superimpose risk warning signs on the actual construction site to display the warning level of the current area and equipment.
[0072] It should be appreciated that embodiments of the present invention may be implemented or enforced by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable memory. The method may be implemented in a computer program using standard programming techniques - including a non-transitory computer-readable storage medium configured with a computer program, wherein the storage medium so configured causes the computer to operate in a specific and predefined manner - according to the methods and drawings described in the specific embodiments. Each program may be implemented in a high-level procedural or object-oriented programming language to communicate with a computer system. However, if desired, the program may be implemented in an assembly or machine language. In any case, the language may be a compiled or interpreted language. In addition, the program may be run on a programmed ASIC for this purpose.
[0073] Furthermore, the operations of the processes described herein may be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and / or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) that is executed collectively on one or more processors, by hardware, or a combination thereof. The computer program includes a plurality of instructions that may be executed by one or more processors.
[0074] Further, the method can be implemented in any type of computing platform that is operably connected to a suitable computer, including but not limited to a personal computer, a minicomputer, a mainframe, a workstation, a network or distributed computing environment, a separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, etc. Aspects of the present invention can be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, an optical read and / or write storage medium, a RAM, a ROM, etc., so that it can be read by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the process described herein. In addition, the machine-readable code, or part thereof, can be transmitted via a wired or wireless network. When such media includes instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor, the invention described herein includes these and other different types of non-transitory computer-readable storage media. When programmed according to the methods and techniques described in the present invention, the present invention also includes the computer itself. The computer program can be applied to input data to perform the functions described herein, thereby converting the input data to generate output data stored in a non-volatile memory. The output information can also be applied to one or more output devices such as a display. In a preferred embodiment of the present invention, the converted data represents a physical and tangible object, including a specific visual depiction of the physical and tangible object produced on a display.
[0075] As used in this application, the terms "component", "module", "system", etc. are intended to refer to a computer-related entity, which can be hardware, firmware, a combination of hardware and software, software, or software in operation. For example, a component can be, but is not limited to: a process running on a processor, a processor, an object, an executable file, a thread in execution, a program, and / or a computer. As an example, an application running on a computing device and the computing device can both be components. One or more components can exist in a process and / or thread in execution, and a component can be located in a computer and / or distributed between two or more computers. In addition, these components can be executed from various computer-readable media having various data structures thereon. These components can communicate in a local and / or remote process manner, such as according to a signal having one or more data packets (e.g., data from a component that interacts with another component in a local system, a distributed system, and / or interacts with other systems in a signal manner through a network such as the Internet).
[0076] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the 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.
Claims
1. A labor employment risk early warning method based on multi-source data, characterized in that: include: Collect labor data, including labor activity data, environmental data, and equipment operation data within the construction site; Filling or deleting missing values, and deleting duplicate and erroneous data from the service data; Based on the EDA framework, process and analyze the labor data, identify and generate labor employment risk events; Establish an early warning rule base to determine the early warning level of the labor employment risk event; According to the warning level of the risk event, warning information is pushed to managers at different levels.
2. The labor employment risk early warning method based on multi-source data according to claim 1 is characterized in that: The identifying and generating labor employment risk events includes: performing cluster analysis on the labor data through a clustering algorithm to identify and generate labor employment risk events.
3. The labor employment risk early warning method based on multi-source data as claimed in claim 2 is characterized in that: The establishment of an early warning rule library includes: Define influencing factors, which include equipment failure rate factor, time impact factor, and environmental factor comprehensive factor; wherein the equipment failure rate factor is calculated based on the number of equipment failures and the total equipment operating time, the time impact factor is calculated based on the actual working time and the standard working time, and the environmental factor comprehensive factor is calculated based on the environmental adjustment parameters, and the environmental adjustment parameters are used to adjust the influence weights of different environmental factors on the overall risk assessment; Calculate the labor employment risk score R according to the influencing factors; Set warning thresholds T1 and T2, and set warning levels according to the labor employment risk score R: high risk, medium risk and low risk; When R>T1, the warning level is high risk; when T1≥R>T2, the warning level is medium risk; when R≤T2, the warning level is low risk.
4. The labor employment risk early warning method based on multi-source data according to claim 3 is characterized in that: Also includes: The historical impact factor sequence is used as the input of the LSTM network, and the predicted result of the labor employment risk score R is output; The prediction results of environmental status and labor employment risk score R are input into the DRL model, the warning level is determined by the Actor network in the DRL model, and the decision effect of the Actor network is evaluated by the Critic network.
5. The labor employment risk early warning method based on multi-source data according to claim 4 is characterized in that: Also includes: Through VR technology, a real-time risk warning interface is embedded in the virtual scene, and based on the existing labor risk score R, the warning levels of different areas and equipment are displayed; AR technology is used to superimpose risk warning information in the manager's real field of vision. When the manager uses AR glasses or equipment, the device's camera and AR technology are used to superimpose risk warning signs on the actual construction site to display the warning level of the current area and equipment.
6. A labor employment risk early warning system based on multi-source data, characterized in that: include: A data collection module is configured to collect labor data, including labor activity data, environmental data, and equipment operation data within the construction site; A data processing module is configured to fill in or delete missing values, and delete duplicate and erroneous data on the service data; A risk event identification module is configured to execute, based on the EDA framework, processing and analyzing the labor data, identifying and generating labor employment risk events; An early warning level identification module is configured to execute the establishment of an early warning rule base to determine the early warning level of the labor employment risk event; The early warning information push module is configured to push early warning information to managers at different levels according to the early warning level of the risk event.
7. The labor employment risk early warning system based on multi-source data according to claim 6 is characterized in that: The risk event identification module is specifically configured to execute: performing cluster analysis on the labor data through a clustering algorithm to identify and generate labor employment risk events.
8. The labor employment risk early warning system based on multi-source data as claimed in claim 7, characterized in that: The warning level identification module is specifically configured to perform: defining influencing factors, wherein the influencing factors include equipment failure rate factors, time influencing factors, and environmental factor comprehensive factors; wherein the equipment failure rate factor is calculated according to the number of equipment failures and the total equipment operation time, the time influencing factor is calculated according to the actual working time and the standard working time, and the environmental factor comprehensive factor is calculated according to the environmental adjustment parameters, wherein the environmental adjustment parameters are used to adjust the influence weights of different environmental factors on the overall risk assessment; Calculate the labor employment risk score R according to the influencing factors; Set warning thresholds T1 and T2, and set warning levels according to the labor employment risk score R: high risk, medium risk and low risk; When R>T1, the warning level is high risk; when T1≥R>T2, the warning level is medium risk; when R≤T2, the warning level is low risk.
9. The labor employment risk early warning system based on multi-source data as claimed in claim 8, characterized in that: It also includes a warning level prediction module, which is specifically configured to execute: The historical impact factor sequence is used as the input of the LSTM network, and the predicted result of the labor employment risk score R is output; The prediction results of environmental status and labor employment risk score R are input into the DRL model, the warning level is determined by the Actor network in the DRL model, and the decision effect of the Actor network is evaluated by the Critic network.
10. The labor employment risk early warning system based on multi-source data as claimed in claim 9, characterized in that: Also included is a visualization module, wherein the visualization module is specifically configured to execute: Through VR technology, a real-time risk warning interface is embedded in the virtual scene, and based on the existing labor risk score R, the warning levels of different areas and equipment are displayed; AR technology is used to superimpose risk warning information in the manager's real field of vision. When the manager uses AR glasses or equipment, the device's camera and AR technology are used to superimpose risk warning signs on the actual construction site to display the warning level of the current area and equipment.
Citation Information
Cited By
Intelligent management and control method and system for accidents of labor dispatched personnel
CN120806643A
