Field operation risk early warning system and method integrating positioning, access control and two-ticket information

Abstract

The invention discloses a field operation risk early warning system and method fusing positioning, access control and two-ticket information. The system comprises a three-dimensional model establishment module, a two-ticket information management module, a maintenance operation management module, a data cloud processing module and an alarm early warning module. The system constructs a workplace three-dimensional model through an unmanned aerial vehicle and 3D laser scanning, the two-ticket information management module stores and manages incoming personnel, special personnel and notification information, the maintenance operation management module realizes synchronization of data and the three-dimensional model, the data cloud processing module constructs an edge-cloud inference model, training and optimization are performed by using AI, and the maintenance operation management module realizes maintenance operation management. Intelligent analysis and risk prediction are realized, and an alarm early warning module summarizes data of each module and generates a job log; an edge-cloud-based reasoning model is built in the data cloud processing module, and AI aid decision is utilized to train and optimize the model, so that intelligent analysis and risk prediction of operation field data are realized.

Description

Technical Field

[0001] The present invention relates to a field operation risk early warning system, and in particular to a field operation risk early warning system and method that integrates positioning, access control and two-ticket information. Background Art

[0002] In recent years, the prediction and decision-making optimization systems built around artificial intelligence have created huge value in many social fields such as industrial production, enterprise management, medical management, traffic management, judicial management, financial management, and tourism management. With the accumulation of big data in different fields in various prediction and decision-making scenarios, the mining of nonlinear domain knowledge, the deep representation of data features, and the deep learning of intelligent models, the prediction and decision-making systems based on artificial intelligence are becoming more and more abundant.

[0003] In the industrial production process, due to the high risk of special operations, strict management and control are required. Traditional operation permits and operation process management methods often involve multiple links and departments, which are cumbersome and inefficient. In order to solve this problem, an operation safety risk management system based on artificial intelligence came into being.

[0004] The operation safety risk management system is a comprehensive platform that integrates operation permits and operation process management. Through this system, users can easily complete the whole process management of special operation application, approval, execution and monitoring. The system adopts advanced information technology to simplify the operation process and improve management efficiency.

[0005] However, the existing operation safety risk management system lacks effective risk prediction and intelligent decision-making support, which makes it difficult to timely and accurately identify and respond to potential risks when facing complex operation sites. At the same time, the existing risk warning system often uses static models, which makes it difficult to adapt to the dynamic changes of the operation site. Summary of the invention

[0006] The present invention overcomes the shortcomings of the prior art and provides a field operation risk warning system and method that integrates positioning, access control and two-ticket information.

[0007] In order to achieve the above object, the present invention adopts the following technical solution: The on-site operation risk warning system integrates positioning, access control and two-ticket information, including: 3D model building module, two-ticket information management module, maintenance operation management module, data cloud processing module and alarm warning module; Positioning equipment and network equipment are deployed at various locations in the workplace. The 3D model building module is used to build a 3D model of the workplace through drone oblique photography and 3D laser scanning technology, which serves as the basis for positioning and business function display; The two-ticket information management module stores information about personnel entering the factory, special personnel, and notification information; the two-ticket information management module is electrically connected to the visualization device to display the relevant information in the two-ticket information management module in real time; The maintenance operation management module is used to synchronize the information in the two ticket information management modules with the three-dimensional model of the workplace. The maintenance operation management module monitors the situation in the workplace in real time through the control ball; The data cloud processing module is used to receive the real-time monitoring status of the maintenance operation management module, build an edge-cloud based reasoning model, use AI-assisted decision-making to train the reasoning model, analyze and process the received data, predict potential risks and give corresponding countermeasures; The alarm and warning module is used to summarize the data generated by each module, generate a job log, and distinguish priorities, and use alarms and enhanced displays to remind management personnel in real time to handle important warnings or major hidden dangers in a timely manner.

[0008] A further improvement of the present invention is that the positioning device is used to obtain personnel location data, locate personnel in real time, analyze personnel historical trajectories, and establish an electronic fence; the network equipment includes a video surveillance system and a door access control system, and the door access control system is electrically connected to the video surveillance system and the positioning device to achieve the linkage between personnel location and video surveillance and door access control, and the linkage between personnel location and operating conditions.

[0009] A further improvement of the present invention is that the information of personnel entering the factory includes: information of regular employees, temporary employees and logistics support personnel; special personnel information includes: information of contractors, outsourced personnel and management personnel; notification information includes: information filling status, safety education information and review process information.

[0010] A further improvement of the present invention is that a mobile surveillance ball is set up at the operation site to monitor the operation process in real time, and the monitoring video stream is uploaded to the cloud analysis service terminal using a wired / wireless network.

[0011] A further improvement of the present invention is that the edge-cloud based reasoning model includes edge nodes and a cloud. The edge nodes are used to provide infrastructure resources, have local resource scheduling and management capabilities, and are also used to receive and execute resource scheduling and management strategies of the cloud. The cloud is used to provide resource scheduling and management strategies, including device management, resource management, and network connection management of edge nodes. The edge nodes receive the data uploaded by the maintenance operation management module, perform preliminary processing and analysis on the data, and then send the processed data to the cloud. The cloud stores, analyzes, and mines the value of the processed data.

[0012] A further improvement of the present invention is that the steps of AI-assisted decision-making training reasoning model are: A1. Use AI technology to read the public data stored in the cloud by the inference model, pre-process and semi-automatically annotate the public data, and train the AI ​​application model. A2. The cloud uploads the AI ​​application model to the edge node in the form of a container or function to establish a data transmission channel between the edge node and the cloud; A3. The AI ​​application model reads private data in the edge node, uses incremental learning to link private data between the edge node and the cloud, and generates an edge model based on the edge node for reasoning on the user side. A4. The edge model uploads the generated data and inference results to the cloud analysis service terminal in a cyclical manner for continuous inference model training and optimization.

[0013] A further improvement of the present invention is that the edge node is responsible for the reasoning of the deep learning AI application model to realize distributed intelligence; the cloud is responsible for the centralized training of the deep learning AI application model, and then the trained model is sent to the edge node.

[0014] A further improvement of the present invention is that the operation log includes the work status of regular workers, the work status of temporary workers, logistics support personnel information, contractor information, outsourced personnel entering the factory, outsourced team operation status, on-site violation warning information, major equipment defect information, and dynamics of fire points and high-risk operation points.

[0015] The on-site operation risk warning method integrating positioning, access control and two-ticket information includes: The 3D model building module uses drone oblique photography and 3D laser scanning technology to build a 3D model of the workplace as the basis for positioning and business function display; The two-ticket information management module displays the factory entry personnel information, special personnel information and notification information in real time through visual equipment; The maintenance operation management module synchronizes the information in the two ticket information management modules with the three-dimensional model of the workplace. The maintenance operation management module monitors the situation in the workplace in real time through the control ball. The data cloud processing module receives the real-time monitoring status of the maintenance operation management module, builds an edge-cloud-based reasoning model, uses AI-assisted decision-making to train the reasoning model, and analyzes and processes the received data to predict potential risks and provide corresponding countermeasures; The alarm and warning module summarizes the data generated by each module, generates a job log, and based on the priority, uses alarms and enhanced displays to alert managers of important warnings or major hidden dangers in real time to handle them in a timely manner.

[0016] A further improvement of the present invention is that the information of personnel entering the factory includes: information of regular employees, temporary employees and logistics support personnel; special personnel information includes: information of contractors, outsourced personnel and management personnel; notification information includes: information filling status, safety education information and review process information.

[0017] Compared with the prior art, the present invention has at least the following beneficial technical effects: The on-site operation risk warning system and method provided by the present invention, which integrates positioning, access control and two-ticket information, realizes intelligent analysis and risk prediction of the operation site data by building an edge-cloud based reasoning model in the data cloud processing module and using AI-assisted decision-making to train and optimize the model. Incremental learning is also used to link private data between edge nodes and the cloud to generate edge models based on edge nodes for user-side reasoning, thereby improving the adaptability and accuracy of the model, so that the system can better cope with complex situations at the operation site. At the same time, distributed intelligence is realized by learning and optimizing AI application models; the cloud is responsible for centralized training and sends the trained model to the edge node, thus forming an efficient data processing and analysis mechanism.

[0018] The present invention constructs a three-dimensional model of the workplace through drone oblique photography and 3D laser scanning technology, providing an accurate spatial basis for positioning, monitoring and business function display. The real-time monitoring is combined with the three-dimensional model to achieve all-round and three-dimensional monitoring of the work site. At the same time, positioning equipment and network equipment are deployed in the workplace to achieve linkage management of personnel location and video monitoring, access control and work status, and two-ticket information management modules are used to store and display information on factory personnel, special personnel and notifications in real time, thereby improving the efficiency and accuracy of information management. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a system flow chart of a preferred embodiment of the present invention; Figure 2 This is the step of training the inference model for AI-assisted decision making in a preferred embodiment of the present invention; Figure 3 It is an edge-cloud based reasoning model of a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] 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. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0022] What needs to be explained here is that the combination of edge computing and artificial intelligence forms the concept of edge intelligence, which not only moves the training and reasoning of AI models to edge devices closer to users, such as smartphones, sensors, routers, surveillance cameras, etc., but also processes data in real time on these edge devices, responds to and analyzes data quickly, and makes decisions locally, thus avoiding the delays and security risks of sending all data to the cloud for processing.

[0023] Decision-making is the process of analyzing and comparing several feasible solutions and selecting the best solution in a specific scenario. The essence of prediction is to analyze, identify and characterize the historical records, internal mechanisms and evolution patterns of the predicted object to achieve a higher probability of describing the state, characteristics and development trends of the predicted object in the future time window. It is a prerequisite for judging the occurrence of decision-making optimization scenarios. Its goal is to provide a basis for scientific decision-making, thereby improving the effectiveness and efficiency of decision-making. Data-prediction-decision is the main model for scientific decision-making in the current field of management science. The emergence of artificial intelligence has made data processing more efficient, decision-making scenario prediction more accurate, and decision-making result optimization more intelligent. Its core advantage lies in the efficient transformation of data-prediction-decision.

[0024] Example 1 like Figure 1 As shown, the on-site operation risk warning system that integrates positioning, access control and two-ticket information provided by the present invention includes: a three-dimensional model building module, a two-ticket information management module, a maintenance operation management module, a data cloud processing module and an alarm warning module; through real-time positioning and historical trajectory analysis, potential safety risks can be discovered and prevented in a timely manner.

[0025] Positioning equipment and network equipment are deployed in various locations in the workplace. The 3D model building module uses drone oblique photography and 3D laser scanning technology to build a 3D model of the workplace as the basis for positioning and business function display; Furthermore, the positioning equipment is used to obtain personnel location data, locate personnel in real time, analyze personnel historical trajectories, and establish electronic fences; the network equipment includes a video surveillance system and an access control system. The access control system is electrically connected to the video surveillance system and the positioning equipment to achieve the linkage between personnel location and video surveillance and access control, and the linkage between personnel location and work status.

[0026] The two-ticket information management module stores information about personnel entering the factory, special personnel, and notification information; the two-ticket information management module is electrically connected to the visualization device to display the relevant information in the two-ticket information management module in real time; Furthermore, the information of personnel entering the factory includes: information of regular employees, temporary employees and logistics support personnel; the information of special personnel includes: information of contractors, outsourced personnel and management personnel; the notification information includes: information filling status, safety education information and review process information.

[0027] The maintenance operation management module synchronizes the information in the two ticket information management modules with the three-dimensional model of the workplace. The maintenance operation management module monitors the situation in the workplace in real time through the control ball. Furthermore, a mobile surveillance camera is set up at the operation site to monitor the operation process in real time, and the monitoring video stream is uploaded to the cloud analysis service terminal using the wired / wireless network.

[0028] The data cloud processing module receives the real-time monitoring information of the maintenance operation management module and builds Figure 3 The edge-cloud based reasoning model shown uses AI-assisted decision-making to train the reasoning model, analyze and process the received data, predict potential risks and give corresponding response measures; through data synchronization and AI-assisted decision-making, it can quickly respond to changes in the work site and improve work efficiency.

[0029] Further, such as Figure 3 As shown, the device is in edge-cloud mode, and the device is responsible for collecting input data and executing the inference model through cloud-edge collaboration.

[0030] Furthermore, the edge-cloud based reasoning model includes edge nodes and cloud. The edge nodes are used to provide infrastructure resources, have local resource scheduling and management capabilities, and are also used to receive and execute resource scheduling and management strategies of the cloud. The cloud is used to provide resource scheduling and management strategies, including device management, resource management and network connection management of edge nodes. The edge nodes receive the data uploaded by the maintenance operation management module, perform preliminary processing and analysis on the data, and then send the processed data to the cloud. The cloud stores, analyzes and mines the value of the processed data.

[0031] The data cloud processing module receives real-time monitoring data from the maintenance operation management module and builds an edge-cloud based reasoning model. This model is trained using AI-assisted decision-making technology, and can analyze and process data, predict potential risks, and provide corresponding countermeasures; the edge-cloud model ensures rapid data processing and response, while reducing dependence on the cloud and improving the flexibility and scalability of the system.

[0032] Further, such as Figure 2 As shown in the figure, the steps of AI-assisted decision-making training reasoning model are: A1. Use AI technology to read the public data stored in the cloud by the inference model, pre-process and semi-automatically annotate the public data, and train the AI ​​application model. Furthermore, the inference formula of the AI ​​application model is expressed as:

[0033] In the formula, are the model parameters after training and optimization, indicating the optimal parameters obtained through cloud training; It is public data, including a large amount of labeled data for model training; is a loss function used to evaluate the difference between the model prediction and the true label. Common loss functions include mean square error, cross entropy, etc. For model prediction, it is used to indicate the use of parameters The output obtained by reasoning about the input data x; x is the input data, which can be an image, text, or other type of data, used for reasoning of the AI ​​application model; y is the true label, the correct output or target value corresponding to the input data x.

[0034] A2. The cloud uploads the AI ​​application model to the edge node in the form of a container or function to establish a data transmission channel between the edge node and the cloud; A3. The AI ​​application model reads private data in the edge node, uses incremental learning to link private data between the edge node and the cloud, and generates an edge model based on the edge node for reasoning on the user side. Furthermore, incremental learning is used to link the private data between the edge node and the remote end. The formula expression of the linkage process is:

[0035] In the formula, It is the model parameter of the AI ​​application after linkage, which is used to indicate that the parameters are updated at the edge node through incremental learning; The learning rate is a hyperparameter used to update the parameters of the AI ​​application model. Represents the gradient, which represents the loss function L about the model parameters after training and optimization The derivative of is used to guide parameter updates, and the remaining variables are consistent with the above.

[0036] A4. The edge model uploads the generated data and inference results to the cloud analysis service terminal in a cyclical manner for continuous inference model training and optimization.

[0037] Furthermore, the formula for training and optimizing the inference model is expressed as:

[0038] In the formula, are the parameters after edge model parameter optimization, It is the model parameter of the linked AI application, which is used to indicate that the parameters are updated at the edge node through incremental learning.

[0039] The edge nodes are responsible for the reasoning of deep learning AI application models to realize distributed intelligence; the cloud is responsible for the centralized training of deep learning AI application models, and then sends the trained models to the edge nodes.

[0040] The alarm and early warning module aggregates the data generated by each module, generates a job log, and uses alarms and enhanced displays to alert managers of important warnings or major hidden dangers in real time for timely processing. The automated monitoring and early warning system can reduce errors caused by human negligence.

[0041] The operation log includes the work status of regular workers, the work status of temporary workers, logistics support personnel information, contractor information, outsourced personnel entering the factory, outsourced team operation status, on-site violation warning information, major equipment defect information, and the dynamics of fire points and high-risk operation points.

[0042] The edge-cloud reasoning model is combined with AI-assisted decision-making to achieve a high-performance, low-cost, and highly flexible on-site operation risk warning system. The on-site operation risk warning system built with this technical solution also has the following advantages: The system provided by the present invention is applicable to various workplaces that require strict safety management and risk control, such as industrial production lines, construction sites, chemical plants, etc. Through real-time monitoring and early warning, the probability of safety accidents is effectively reduced, and the operating efficiency and personnel safety are improved.

[0043] When the present invention is used, drone oblique photography and 3D laser scanning technology are utilized to construct a three-dimensional model of the workplace, and the three-dimensional model serves as the basis for subsequent positioning, business function display, and data analysis.

[0044] Positioning equipment is deployed at the workplace to obtain real-time personnel location data, conduct historical trajectory analysis, and establish electronic fences. After that, network equipment is deployed, including video surveillance systems and access control systems, to achieve the linkage between personnel location and video surveillance, access control, and between personnel location and work status.

[0045] The two-ticket information management module stores information about people entering the factory, special personnel and notification information, and this information can be displayed in real time on a visualization device.

[0046] The maintenance operation management module synchronizes the information in the two information management modules with the three-dimensional model of the workplace, monitors the situation in the workplace in real time through the control ball, and uploads the monitoring video stream to the cloud analysis service terminal.

[0047] The data cloud processing module receives real-time monitoring information from the maintenance operation management module, builds an edge-cloud-based reasoning model, uses AI-assisted decision-making to train the reasoning model, analyzes and processes data, predicts potential risks and provides countermeasures.

[0048] The training process of AI-assisted decision-making includes: reading and preprocessing public data to train AI application models; uploading AI application models to edge nodes; using incremental learning to link private data between edge nodes and the cloud to generate edge models; and edge models uploading data and inference results to the cloud analysis service terminal for continuous model training and optimization.

[0049] The alarm and warning module aggregates the data generated by each module, generates a job log, and based on priority, reminds management personnel of important warnings or major hidden dangers in real time through alarms and enhanced displays for timely processing.

[0050] Based on the above, cloud-edge collaboration is a new computing paradigm that combines the powerful resource capabilities of cloud computing with the ultra-low latency characteristics of edge computing, achieving the collaborative optimization goal of edge supporting cloud applications and cloud helping edge localization needs.

[0051] AI and edge computing have received widespread attention and recognition from academia and industry at home and abroad, and have played a role in many business scenarios. Deploying AI applications to the edge has become an effective way to enhance intelligent services.

[0052] Example 2 The on-site operation risk warning method integrating positioning, access control and two-ticket information provided by the present invention comprises: a three-dimensional model building module constructs a three-dimensional model of the operation site through unmanned aerial vehicle oblique photography and 3D laser scanning technology as a basis for positioning and business function display; The two-ticket information management module displays the factory entry personnel information, special personnel information and notification information in real time through visual equipment; The maintenance operation management module synchronizes the information in the two ticket information management modules with the three-dimensional model of the workplace. The maintenance operation management module monitors the situation in the workplace in real time through the control ball. The data cloud processing module receives the real-time monitoring status of the maintenance operation management module, builds an edge-cloud-based reasoning model, uses AI-assisted decision-making to train the reasoning model, and analyzes and processes the received data to predict potential risks and provide corresponding countermeasures; The alarm and warning module summarizes the data generated by each module, generates a job log, and based on the priority, uses alarms and enhanced displays to alert managers of important warnings or major hidden dangers in real time to handle them in a timely manner.

[0053] In this embodiment, the information of personnel entering the factory includes: regular employee information, temporary employee information and logistics support personnel information; special personnel information includes: contractor information, outsourced personnel information and management personnel information; notification information includes: information filling status, safety education information and review process information.

[0054] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved.

[0055] In addition, it should be understood that although this specification is described in accordance with the implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other implementation modes that can be understood by those skilled in the art. The above content is only to illustrate the technical idea of ​​the present invention, and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution according to the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. The on-site operation risk warning system that integrates positioning, access control and two-ticket information is characterized by: include: 3D model building module, two-ticket information management module, maintenance operation management module, data cloud processing module and alarm warning module; Positioning equipment and network equipment are deployed at various locations in the workplace. The 3D model building module is used to build a 3D model of the workplace through drone oblique photography and 3D laser scanning technology, which serves as the basis for positioning and business function display; The two-ticket information management module stores information about personnel entering the factory, special personnel, and notification information; the two-ticket information management module is electrically connected to the visualization device to display the relevant information in the two-ticket information management module in real time; The maintenance operation management module is used to synchronize the information in the two ticket information management modules with the three-dimensional model of the workplace. The maintenance operation management module monitors the situation in the workplace in real time through the control ball; The data cloud processing module is used to receive the real-time monitoring status of the maintenance operation management module, build an edge-cloud based reasoning model, use AI-assisted decision-making to train the reasoning model, analyze and process the received data, predict potential risks and give corresponding countermeasures; The alarm and warning module is used to summarize the data generated by each module, generate a job log, and distinguish priorities, and use alarms and enhanced displays to remind management personnel in real time to handle important warnings or major hidden dangers in a timely manner.

2. The on-site operation risk warning system integrating positioning, access control and two-ticket information according to claim 1 is characterized in that: The positioning equipment is used to obtain personnel location data, locate personnel in real time, analyze personnel historical trajectories, and establish electronic fences; the network equipment includes a video surveillance system and an access control system. The access control system is electrically connected to the video surveillance system and the positioning equipment to achieve the linkage between personnel location and video surveillance and access control, and between personnel location and work status.

3. The on-site operation risk warning system integrating positioning, access control and two-ticket information according to claim 1 is characterized in that: The information of personnel entering the factory includes: information of regular employees, temporary employees and logistics support personnel; the information of special personnel includes: information of contractors, outsourced personnel and management personnel; the notification information includes: information filling status, safety education information and review process information.

4. The on-site operation risk warning system integrating positioning, access control and two-ticket information according to claim 1 is characterized in that: Set up a mobile surveillance camera at the work site to monitor the work process in real time, and upload the surveillance video stream to the cloud analysis service terminal using wired / wireless networks.

5. The on-site operation risk warning system integrating positioning, access control and two-ticket information according to claim 1 is characterized in that: The edge-cloud based reasoning model includes edge nodes and cloud. The edge nodes are used to provide infrastructure resources, have local resource scheduling and management capabilities, and are also used to receive and execute resource scheduling and management strategies on the cloud. The cloud is used to provide resource scheduling and management strategies, including device management, resource management, and network connection management of edge nodes. The edge nodes receive the data uploaded by the maintenance operation management module, perform preliminary processing and analysis on the data, and then send the processed data to the cloud. The cloud stores, analyzes and mines the value of processed data.

6. The on-site operation risk warning system integrating positioning, access control and two-ticket information according to claim 1 is characterized in that: The steps for training the inference model for AI-assisted decision making are: A1. Use AI technology to read the public data stored in the cloud by the inference model, pre-process and semi-automatically annotate the public data, and train the AI ​​application model. A2. The cloud uploads the AI ​​application model to the edge node in the form of a container or function to establish a data transmission channel between the edge node and the cloud; A3. The AI ​​application model reads private data in the edge node, uses incremental learning to link private data between the edge node and the cloud, and generates an edge model based on the edge node for reasoning on the user side. A4. The edge model uploads the generated data and inference results to the cloud analysis service terminal in a cyclical manner for continuous inference model training and optimization.

7. The on-site operation risk warning system integrating positioning, access control and two-ticket information according to claim 6 is characterized in that: The edge nodes are responsible for the reasoning of deep learning AI application models to realize distributed intelligence; the cloud is responsible for the centralized training of deep learning AI application models, and then sends the trained models to the edge nodes.

8. The on-site operation risk warning system integrating positioning, access control and two-ticket information according to claim 1 is characterized in that: The operation log includes the work status of regular workers, the work status of temporary workers, logistics support personnel information, contractor information, outsourced personnel entering the factory, outsourced team operation status, on-site violation warning information, major equipment defect information, and the dynamics of fire points and high-risk operation points.

9. A field operation risk warning method integrating positioning, access control and two-ticket information, characterized in that: include: The 3D model building module uses drone oblique photography and 3D laser scanning technology to build a 3D model of the workplace as the basis for positioning and business function display; The two-ticket information management module displays the factory entry personnel information, special personnel information and notification information in real time through visual equipment; The maintenance operation management module synchronizes the information in the two ticket information management modules with the three-dimensional model of the workplace. The maintenance operation management module monitors the situation in the workplace in real time through the control ball. The data cloud processing module receives the real-time monitoring status of the maintenance operation management module, builds an edge-cloud-based reasoning model, uses AI-assisted decision-making to train the reasoning model, and analyzes and processes the received data to predict potential risks and provide corresponding countermeasures; The alarm and warning module summarizes the data generated by each module, generates a job log, and based on the priority, uses alarms and enhanced displays to alert managers of important warnings or major hidden dangers in real time to handle them in a timely manner.

10. The on-site operation risk warning method integrating positioning, access control and two-ticket information according to claim 9 is characterized in that: The information of personnel entering the factory includes: information of regular employees, temporary employees and logistics support personnel; the information of special personnel includes: information of contractors, outsourced personnel and management personnel; the notification information includes: information filling status, safety education information and review process information.

Images