Intelligent job ticket fusion method and system based on large model, and medium

Abstract

The invention discloses an operation ticket intelligent fusion method and system based on a large model, and a medium, mainly relates to the technical field of operation ticket intelligent fusion, and is used for solving the problems of low efficiency and high error rate in an operation ticket generation process, insufficient risk analysis and early warning of an operation site, and lack of an effective fusion mechanism in an existing scheme. Comprising the following steps: acquiring operation basic data through a front-end Web interface; the method comprises the following steps: acquiring multi-source field acquisition data through preset monitoring equipment; based on the work basic data, extracting corresponding work ticket filling information from a preset work knowledge graph, and further generating a work ticket; based on the data type of the multi-source field collection data, determining a corresponding large model analysis program, and further obtaining risk analysis content and risk early warning information; and filling the risk analysis content and the risk early warning information into the work ticket to obtain a final work ticket.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent fusion of job tickets, and in particular to a method, system and medium for intelligent fusion of job tickets based on a large model. Background Art

[0002] In the current field of job ticket management and generation, traditional solutions mainly rely on manual operations and simple information systems, and there are many problems that need to be solved urgently.

[0003] On the one hand, the process of generating work tickets is often inefficient and error-prone. Traditionally, workers must manually collect basic data for the work and rely on their personal experience and memory to find information to fill in the work ticket. This not only consumes a significant amount of time and effort, but also easily leads to missing information or incorrect entries. Furthermore, due to the lack of a unified knowledge management and retrieval mechanism, work tickets filled out by different workers may have irregular formats and inconsistent content, significantly complicating subsequent work management and safety assessments.

[0004] On the other hand, existing solutions for risk analysis and early warning at work sites have significant shortcomings. Currently, methods for collecting on-site data are relatively limited, typically capturing only a limited range of data types, making it difficult to fully and accurately reflect the actual conditions at the work site. Furthermore, traditional, rule-based methods are often used to analyze this collected data, making it difficult to address complex and changing work scenarios and potential risks. Due to the lack of effective intelligent analysis methods, it is impossible to promptly and accurately identify risk factors at the work site, making it even more difficult to issue early warning information, thus hindering the provision of timely and effective safety protection for workers.

[0005] In addition, there is a lack of an effective integration mechanism between the existing work ticket generation and risk analysis systems. The generation of work tickets and risk analysis are often two independent processes, resulting in the information in the work ticket being unable to timely reflect the risk status of the work site and unable to provide comprehensive and accurate work guidance for operators. Summary of the Invention

[0006] The present application provides a large-model-based intelligent fusion method, system and medium for job tickets to solve the problems of existing solutions such as inefficient and error-prone job ticket generation process, insufficient risk analysis and early warning for the job site, and lack of an effective fusion mechanism.

[0007] In a first aspect, the present application provides a method for intelligent fusion of job tickets based on a large model, the method comprising: Obtain basic operation data through the front-end web interface; obtain multi-source field data through preset monitoring equipment; Based on the basic data of the job, the corresponding job ticket filling information is extracted from the preset job knowledge graph to generate the job ticket; Based on the data type of multi-source field data, determine the corresponding large model analysis program, and then obtain risk analysis content and risk warning information; Fill in the risk analysis content and risk warning information into the work ticket to obtain the final work ticket.

[0008] In one implementation of the present application, the basic operation data includes at least: operation type, operation location, operator information, and operation time.

[0009] In one implementation of the present application, multi-source field data is obtained by pre-setting monitoring equipment, specifically including: Through IoT sensors, environmental parameters are collected in real time at a preset frequency as on-site data collection; Through the on-site camera, the video stream is collected in real time as on-site collection data.

[0010] In one implementation of the present application, based on the basic job data, the corresponding job ticket filling information is extracted from the preset job knowledge graph to generate the job ticket, specifically including: The basic operation data is input into the preset matching large model algorithm, and then the corresponding preset operation ticket filling information is extracted from the preset operation knowledge graph; wherein, the preset operation knowledge graph is composed of the association relationship between the basic operation data and the preset operation ticket filling information, and the preset operation ticket filling information at least includes: the operation steps and safety precautions required for intelligent generation of the operation ticket.

[0011] In one implementation of the present application, after extracting corresponding job ticket filling information from a preset job knowledge graph based on the job basic data and then generating the job ticket, the method further includes: Obtain the selected job ticket verification program or the imported job ticket verification program through the preset interface; The generated job ticket is verified through the job ticket verification program to see if it complies with the preset verification rules in the job ticket verification program. If it does not comply with the preset verification rules, the job ticket will be automatically rejected to the draft state, and the preset verification rules that failed the review will be fed back to the operator through the front-end web interface.

[0012] In one implementation of the present application, based on the data type of multi-source field data collected, a corresponding large model analysis program is determined to obtain risk analysis content and risk warning information, specifically including: When the multi-source field data is video data, the coordinates of the preset key resource points of the target person in the video data are identified through the YOLOv11 network. The coordinates of the preset key resource points are uploaded to the large model analysis program. The large model analysis program calculates the relationship between the coordinates of the preset key resource points, and then uses the relationship between the coordinates and the relationship between the preset behavior relationship to determine the behavior of the target person. The relationship between the coordinates includes the angle between the two coordinates along the preset direction and the straight-line distance between the two coordinates. Output the preset risk analysis content and risk warning information corresponding to the target person's behavior.

[0013] In a second aspect, the present application provides a large-scale model-based intelligent fusion system for job tickets, comprising: The acquisition module is used to obtain basic operation data through the front-end Web interface; it obtains multi-source field data through preset monitoring equipment; The generation module is used to extract the corresponding job ticket filling information from the preset job knowledge graph based on the job basic data, and then generate the job ticket; The acquisition module is used to determine the corresponding large model analysis program based on the data type of multi-source field collected data, and then obtain the risk analysis content and risk warning information; fill the risk analysis content and risk warning information into the operation ticket to obtain the final operation ticket.

[0014] In one implementation of the present application, the generation module includes a generation unit, It is used to input the basic operation data into the preset matching large model algorithm, and then extract the corresponding preset operation ticket filling information from the preset operation knowledge graph; wherein, the preset operation knowledge graph is composed of the association relationship between the basic operation data and the preset operation ticket filling information, and the preset operation ticket filling information at least includes: the operation steps and safety precautions required for intelligent generation of the operation ticket.

[0015] In one implementation of the present application, the system further includes a verification module. Used to obtain the selected job ticket verification program or the imported job ticket verification program through the preset interface; The generated job ticket is verified through the job ticket verification program to see if it complies with the preset verification rules in the job ticket verification program. If it does not comply with the preset verification rules, the job ticket will be automatically rejected to the draft state, and the preset verification rules that failed the review will be fed back to the operator through the front-end web interface.

[0016] In a third aspect, the present application provides a non-volatile computer storage medium on which computer instructions are stored. When the computer instructions are executed, they implement a large-model-based intelligent fusion method for job tickets as described above.

[0017] It can be seen from the above technical solutions that this application has the following advantages: 1. Improved efficiency and accuracy of job ticket generation: Accessing basic job data through a front-end web interface enables rapid data entry and integration, avoiding the tedious process of traditional manual data collection and organization. Furthermore, by extracting corresponding job ticket information based on a pre-set job knowledge graph, job tickets can be automatically and accurately generated, reducing potential errors and omissions that may occur with manual entry and improving the efficiency and accuracy of job ticket generation.

[0018] 2. Enhanced risk analysis and early warning capabilities: Utilizing pre-configured monitoring equipment to collect multi-source on-site data provides a comprehensive, real-time overview of the actual worksite conditions. Based on the data type, a corresponding large-scale model analysis program is determined to delve deeper into the underlying risks, resulting in more accurate risk analysis and early warning information. This intelligent risk analysis and early warning mechanism helps operators proactively identify and address potential risks, ensuring operational safety.

[0019] 3. Realize the intelligent integration of work tickets and risk analysis: By embedding risk analysis and risk warning information into job tickets, we achieve the intelligent integration of job tickets and risk analysis. This integration ensures that job tickets not only contain basic job information but also incorporate real-time risk analysis and warnings, providing operators with more comprehensive and accurate work guidance. This also helps managers better understand the risk situation at the job site and develop more scientific and reasonable work plans and safety measures.

[0020] 4. Improved the intelligent level of operation management: The method in this application uses large-scale model analysis technology to achieve intelligent processing of job ticket generation and risk analysis, thereby enhancing the intelligent level of job management. This intelligent job management method helps reduce the degree of manual intervention, improve management efficiency, reduce safety accidents caused by human factors, and provide strong protection for enterprise safety production. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for the description. 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 paying any creative work.

[0022] Figure 1 This is a flow chart of a method for intelligent fusion of job tickets based on a large model provided in an embodiment of the present application.

[0023] Figure 2 This is a schematic diagram of the internal structure of a large-model-based intelligent fusion system for job tickets provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0025] It should be understood by those skilled in the art that the embodiments described below are merely preferred embodiments of the present disclosure and do not imply that the present disclosure can only be implemented through these preferred embodiments. These preferred embodiments are merely intended to explain the technical principles of the present disclosure and are not intended to limit the scope of protection of the present disclosure. Based on the preferred embodiments provided by the present disclosure, all other embodiments obtained by those skilled in the art without creative effort should still fall within the scope of protection of the present disclosure.

[0026] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0027] The technical solutions proposed in the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0028] The embodiment provides a method for intelligent fusion of work orders based on a large model, such as Figure 1 As shown, the method provided in the embodiment of the present application mainly includes the following steps: Step 110: Obtain basic operation data through the front-end Web interface; obtain multi-source on-site collection data through preset monitoring equipment.

[0029] In some embodiments, multi-source field data is obtained through preset monitoring equipment, specifically including: Through IoT sensors, environmental parameters are collected in real time at a preset frequency as on-site data collection; Through the on-site camera, the video stream is collected in real time as on-site collection data.

[0030] It will be understood by those skilled in the art that obtaining basic operation data through the front-end Web interface enables rapid data entry and centralized management, reducing the time and error rate of manual data collection.

[0031] Preset monitoring devices (such as IoT sensors and on-site cameras) can collect on-site data at a preset frequency or in real time, ensuring the timeliness and accuracy of the data and providing reliable data support for subsequent operation analysis and decision-making.

[0032] IoT sensors can collect environmental parameters (such as temperature, humidity, gas concentration, etc.) in real time, which are crucial for assessing the safety status and risk level of the work site.

[0033] The video stream collected in real time by on-site cameras provides an intuitive on-site picture, which helps managers to promptly identify potential safety hazards or violations and take appropriate measures to intervene.

[0034] Specific examples: Assume that at a chemical plant operation site, it is necessary to monitor the safety of the working environment in real time and ensure the safety of the workers.

[0035] ‌Get basic job data through the front-end web interface‌: The operator enters basic information of the work task through the front-end web interface, such as work type, work location, work time, etc.

[0036] At the same time, operators can also upload relevant operation files or drawings for subsequent operation analysis and decision-making.

[0037] ‌Get multi-source field data through pre-set monitoring equipment‌: IoT sensors collect environmental parameters: Multiple IoT sensors are deployed at the work site to collect real-time environmental parameters such as temperature, humidity, and toxic gas concentrations.

[0038] These sensors upload data to a central server at a preset frequency (e.g., once per minute) for subsequent analysis.

[0039] ‌Live camera captures video stream‌: On-site cameras are installed at key locations on the job site to capture real-time video streams.

[0040] Video stream data is transmitted to the central server via the network, and managers can view the work site images in real time through the web interface to promptly identify potential safety hazards or violations.

[0041] Step 120: Based on the basic operation data, the corresponding operation ticket filling information is extracted from the preset operation knowledge graph to generate the operation ticket.

[0042] This step can be specifically as follows: The basic operation data is input into the preset matching large model algorithm, and then the corresponding preset operation ticket filling information is extracted from the preset operation knowledge graph; wherein, the preset operation knowledge graph is composed of the association relationship between the basic operation data and the preset operation ticket filling information, and the preset operation ticket filling information at least includes: the operation steps and safety precautions required for intelligent generation of the operation ticket.

[0043] Those skilled in the art will understand that in this step, by inputting the basic data of the job into the preset matching large model algorithm, the system can automatically extract the corresponding job ticket filling information from the preset job knowledge graph, avoiding the tedious process of manually filling in the job ticket and improving the generation efficiency.

[0044] The preset job knowledge graph consists of the association between the basic job data and the preset job ticket filling information, which ensures the accuracy and consistency of the extracted information and reduces human errors.

[0045] The preset job ticket filling information includes the work steps and safety precautions required for intelligently generating job tickets, which helps standardize the work process and ensures that each operation follows the same steps and safety specifications.

[0046] Standardized operating procedures help improve work quality and reduce safety accidents and efficiency losses caused by improper operations.

[0047] The automatically generated work tickets contain clear work steps and safety precautions, making it easier for workers to understand and perform work tasks.

[0048] The improved readability and usability of work tickets help operators quickly grasp the key points of the work and improve work efficiency.

[0049] The construction and storage of preset job knowledge graphs enable job-related knowledge and experience to be effectively managed and reused.

[0050] When encountering similar tasks, relevant information can be directly extracted from the knowledge graph to quickly generate a task ticket, reducing duplication of work and knowledge waste.

[0051] Specific examples: Assume that in an electric maintenance operation scenario, an electric maintenance operation ticket needs to be generated.

[0052] ‌Job-based data input‌: The operator enters basic operation data through the front-end web interface, such as operation type (power maintenance), operation location (a substation), operation time (October 10, 2023), etc.

[0053] ‌Preset matching large model algorithm processing‌: The system inputs the basic data of the operation into the preset matching large model algorithm, which searches for the corresponding operation ticket filling information in the preset operation knowledge graph based on key information such as operation type and location.

[0054] Extract information from the preset job knowledge graph: The preset operation knowledge graph stores relevant knowledge and experience of power maintenance operations, including operation steps (such as power off, equipment inspection, maintenance, testing, etc.) and safety precautions (such as wearing protective equipment, complying with operating procedures, and paying attention to preventing electric shock, etc.).

[0055] The algorithm extracts the operation steps and safety precautions that match the current operation basic data from the knowledge graph.

[0056] Generate a job ticket: The system fills the extracted work steps and safety precautions into the work ticket template to generate a complete power maintenance work ticket.

[0057] The work ticket clearly lists the work steps and safety precautions. Workers can follow the instructions on the work ticket to ensure the safety and efficiency of the work.

[0058] After extracting corresponding job ticket filling information from a preset job knowledge graph based on the job basic data and then generating the job ticket, the method further includes: Obtain the selected job ticket verification program or the imported job ticket verification program through the preset interface; The generated job ticket is verified through the job ticket verification program to see if it complies with the preset verification rules in the job ticket verification program. If it does not comply with the preset verification rules, the job ticket will be automatically rejected to the draft state, and the preset verification rules that failed the review will be fed back to the operator through the front-end web interface.

[0059] Those skilled in the art will appreciate that by verifying the generated job ticket using a preset job ticket verification program, it is possible to ensure that the information in the job ticket complies with preset verification rules, such as the completeness of the work steps and compliance with safety precautions. This helps reduce operational risks caused by inaccurate or non-compliant job ticket information and improves operational safety and efficiency.

[0060] The job ticket verification program automatically verifies generated job tickets and returns them to draft status if they do not meet pre-set verification rules. Furthermore, it provides feedback to operators via the front-end web interface regarding any pre-set verification rules that fail review, allowing them to promptly identify the issues and make appropriate corrections. This automated verification and feedback mechanism reduces the workload and time of manual verification and improves verification efficiency.

[0061] The pre-set job ticket verification process reflects the normative and standardized requirements of job management. This verification process ensures that all generated job tickets follow the same standards and rules, helping to improve the overall level and quality of job management.

[0062] The preset verification rules in the work ticket verification program can be adjusted and optimized according to the actual work situation. If certain verification rules are found to be unreasonable or need to be supplemented, the verification program can be updated in a timely manner, thereby promoting the continuous optimization and improvement of the work process.

[0063] Specific examples: Suppose at a construction site, you need to generate a high-altitude work ticket and ensure its accuracy and compliance.

[0064] Operators input basic operation data such as operation type (high-altitude operation), operation location, operation time, etc. through the front-end web interface.

[0065] Based on the basic operation data, the system extracts the corresponding operation ticket filling information from the preset operation knowledge graph, such as operation steps, safety precautions, etc., and then generates a high-altitude operation ticket.

[0066] Through the preset interface, managers can select the verification program suitable for high-altitude work from the list of available work ticket verification programs, or import a customized work ticket verification program.

[0067] The system verifies the generated high-altitude work permit through the selected work permit verification program.

[0068] The verification program checks whether the information in the work ticket complies with the preset verification rules, such as whether the work steps are complete, whether the safety precautions are compliant, and whether the operator has the corresponding qualifications.

[0069] If the job ticket does not meet the preset verification rules, the system will automatically reject the job ticket and return it to the draft status.

[0070] At the same time, the preset verification rules that fail the review are fed back to the operators through the front-end web interface, such as "the operation steps lack safety protection measures" or "the qualifications of the operators do not meet the requirements".

[0071] The operator makes modifications based on the feedback information and resubmits the work ticket for verification.

[0072] Managers adjust and optimize the preset verification rules in the work ticket verification program based on actual work conditions and feedback.

[0073] For example, adding new safety precautions or adjusting operator qualification requirements can improve the accuracy and compliance of work tickets.

[0074] Step 130: Based on the data types of the multi-source field collected data, determine the corresponding large model analysis program to obtain risk analysis content and risk warning information.

[0075] This step can be specifically as follows: When the multi-source on-site collected data is video data, the coordinates of the preset key resource points of the target person in the video data are identified through the YOLOv11 network, and the coordinates of the preset key resource points are uploaded to the large model analysis program. The relationship between the coordinates of the preset key resource points is calculated by the large model analysis program, and then the relationship between the coordinates and the preset behavior relationship is used to determine the behavior of the target person; wherein the relationship between the coordinates includes the angle between the two coordinates along the preset direction and the straight-line distance between the two coordinates; the preset risk analysis content and risk warning information corresponding to the target person's behavior are output.

[0076] Specific examples: Assume that at a chemical production site, the behavior of operators needs to be monitored to ensure that they comply with safe operating procedures.

[0077] Multiple cameras were installed on site to collect video data of operators in real time.

[0078] ‌Determine the large model analysis procedure‌: When the collected data is video data, the system automatically selects the YOLOv11 network as the recognition tool to identify the target person (operator) in the video data and the coordinates of its preset key resource points (such as operating equipment, safe areas, etc.).

[0079] Coordinate relationship calculation and behavior recognition: The system uploads the coordinates of the identified preset key resource points to the large model analysis program.

[0080] The large model analysis program calculates the relationship between the coordinates of preset key resource points, such as the angle between two coordinates along a preset direction and the straight-line distance between the two coordinates.

[0081] By comparing the relationship between coordinates with preset behavioral relationships, the system determines the target person's behavior, such as whether he is approaching a dangerous area or operating equipment improperly.

[0082] Output risk analysis content and risk warning information: Based on the identified behavior of the target person, the system outputs the corresponding preset risk analysis content, such as "the operator is approaching a dangerous area and there is a safety risk."

[0083] At the same time, the system issues risk warning information to remind managers to take timely measures, such as notifying operators to leave dangerous areas and strengthening on-site monitoring.

[0084] Step 140: Fill the risk analysis content and risk warning information into the operation ticket to obtain the final operation ticket.

[0085] In addition, this application Figure 2 The embodiment of the present application provides a large model-based intelligent fusion system for job tickets. Figure 2 As shown, the system provided in the embodiment of the present application mainly includes: The acquisition module 210 is used to obtain basic operation data through the front-end Web interface and obtain multi-source field acquisition data through preset monitoring equipment.

[0086] The generation module 220 is used to extract the corresponding job ticket filling information from the preset job knowledge graph based on the job basic data, and then generate the job ticket.

[0087] The generation module 220 includes a generation unit, It is used to input the basic operation data into the preset matching large model algorithm, and then extract the corresponding preset operation ticket filling information from the preset operation knowledge graph; wherein, the preset operation knowledge graph is composed of the association relationship between the basic operation data and the preset operation ticket filling information, and the preset operation ticket filling information at least includes: the operation steps and safety precautions required for intelligent generation of the operation ticket.

[0088] The system also includes a verification module for obtaining a selected job ticket verification program or an imported job ticket verification program through a preset interface; verifying whether the generated job ticket complies with the preset verification rules in the job ticket verification program through the job ticket verification program, so that when the preset verification rules are not met, the job ticket is automatically rejected to the draft state, and the preset verification rules that fail the review are fed back to the operator through the front-end Web interface.

[0089] The acquisition module 230 is used to determine the corresponding large model analysis program based on the data type of multi-source field collected data, and then obtain risk analysis content and risk warning information; fill the risk analysis content and risk warning information into the operation ticket to obtain the final operation ticket.

[0090] In addition, an embodiment of the present application further provides a non-volatile computer storage medium on which executable instructions are stored. When the executable instructions are executed, a large model-based intelligent fusion method for job tickets as described above is implemented.

[0091] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for intelligent fusion of work orders based on a large model, characterized in that: The method comprises: Obtain basic operation data through the front-end web interface; obtain multi-source field data through preset monitoring equipment; Based on the basic data of the job, the corresponding job ticket filling information is extracted from the preset job knowledge graph to generate the job ticket; Based on the data type of multi-source field data, determine the corresponding large model analysis program, and then obtain risk analysis content and risk warning information; Fill in the risk analysis content and risk warning information into the work ticket to obtain the final work ticket.

2. The method for intelligent fusion of job tickets based on a large model according to claim 1 is characterized in that: Basic operation data includes at least: operation type, operation location, operator information, and operation time.

3. The method for intelligent fusion of job tickets based on a large model according to claim 1 is characterized in that: Through the preset monitoring equipment, multi-source field data is obtained, including: Through IoT sensors, environmental parameters are collected in real time at a preset frequency as on-site data collection; Through the on-site camera, the video stream is collected in real time as on-site collection data.

4. The method for intelligent fusion of job tickets based on a large model according to claim 1 is characterized in that: Based on the basic job data, the corresponding job ticket filling information is extracted from the preset job knowledge graph to generate the job ticket, specifically including: The basic operation data is input into the preset matching large model algorithm, and then the corresponding preset operation ticket filling information is extracted from the preset operation knowledge graph; wherein, the preset operation knowledge graph is composed of the association relationship between the basic operation data and the preset operation ticket filling information, and the preset operation ticket filling information at least includes: the operation steps and safety precautions required for intelligent generation of the operation ticket.

5. The method for intelligent fusion of job tickets based on a large model according to claim 1 is characterized in that: After extracting corresponding job ticket filling information from a preset job knowledge graph based on the job basic data and then generating the job ticket, the method further includes: Obtain the selected job ticket verification program or the imported job ticket verification program through the preset interface; The generated job ticket is verified through the job ticket verification program to see if it complies with the preset verification rules in the job ticket verification program. If it does not comply with the preset verification rules, the job ticket will be automatically rejected to the draft state, and the preset verification rules that failed the review will be fed back to the operator through the front-end web interface.

6. The method for intelligent fusion of job tickets based on a large model according to claim 1 is characterized in that: Based on the data type of multi-source field data, the corresponding large model analysis program is determined to obtain risk analysis content and risk warning information, including: When the multi-source field data is video data, the coordinates of the preset key resource points of the target person in the video data are identified through the YOLOv11 network. The coordinates of the preset key resource points are uploaded to the large model analysis program. The large model analysis program calculates the relationship between the coordinates of the preset key resource points, and then uses the relationship between the coordinates and the relationship between the preset behavior relationship to determine the behavior of the target person. The relationship between the coordinates includes the angle between the two coordinates along the preset direction and the straight-line distance between the two coordinates. Output the preset risk analysis content and risk warning information corresponding to the target person's behavior.

7. A large-scale model-based intelligent fusion system for job tickets, characterized by: The system comprises: The acquisition module is used to obtain basic operation data through the front-end Web interface; it obtains multi-source field data through preset monitoring equipment; The generation module is used to extract the corresponding job ticket filling information from the preset job knowledge graph based on the job basic data, and then generate the job ticket; The acquisition module is used to determine the corresponding large model analysis program based on the data type of multi-source field collected data, and then obtain the risk analysis content and risk warning information; fill the risk analysis content and risk warning information into the operation ticket to obtain the final operation ticket.

8. The large model-based intelligent fusion system for job tickets according to claim 7 is characterized in that: The generation module includes a generation unit, It is used to input the basic operation data into the preset matching large model algorithm, and then extract the corresponding preset operation ticket filling information from the preset operation knowledge graph; wherein, the preset operation knowledge graph is composed of the association relationship between the basic operation data and the preset operation ticket filling information, and the preset operation ticket filling information at least includes: the operation steps and safety precautions required for intelligent generation of the operation ticket.

9. The large-scale model-based intelligent fusion system for job tickets according to claim 7 is characterized in that: The system further includes a verification module, Used to obtain the selected job ticket verification program or the imported job ticket verification program through the preset interface; The generated job ticket is verified through the job ticket verification program to see if it complies with the preset verification rules in the job ticket verification program. If it does not comply with the preset verification rules, the job ticket will be automatically rejected to the draft state, and the preset verification rules that failed the review will be fed back to the operator through the front-end web interface.

10. A non-volatile computer storage medium, characterized in that Computer instructions are stored thereon, and when the computer instructions are executed, they implement a large-model-based intelligent fusion method for job tickets as described in any one of claims 1-6.

Images