Digital work card generation method and device, computer equipment and storage medium

Abstract

The invention relates to a digital work card generation method and device, computer equipment and a storage medium. According to the method, the equipment operation data, the historical maintenance archive and the three-dimensional model information are automatically collected, intelligent matching and case reasoning are carried out in combination with the maintenance knowledge base, multiple sets of maintenance plans can be automatically generated, deduction evaluation is completed based on the digital twinborn model, and therefore the optimal scheme is selected to generate the digital work card. The method is further combined with immersive rehearsal of operators, operation behaviors and jamming points are recorded in real time, and information is automatically integrated and optimized to form a final digital work card. Compared with a manual compilation mode, the technology realizes automatic generation, verification and optimization of the digital work card, significantly improves the maintenance efficiency and accuracy, reduces manual errors, enables the content of the work card to dynamically respond to the difference between equipment and personnel, improves the intelligentization and self-adaptive capability of a system, and reduces the maintenance cost. And the generation efficiency, rationality and performability of the digital work card are remarkably improved.

Description

Technical Field

[0001] This application relates to the field of equipment maintenance technology, and in particular to a method, apparatus, computer equipment, and storage medium for generating digital work cards. Background Technology

[0002] Digital work cards are used to digitally record maintenance operation steps, materials, personnel signatures, and real-time data, supporting dynamic updates, automated signing, and full-process traceability. Currently, the equipment maintenance field is undergoing a transformation from paper-based and digital methods to intelligent systems. Digital tools, represented by digital work cards, are widely used, but their core paradigm remains at the stage of static electronic transmission of instructions. A gap exists between the generated maintenance plans and actual execution, and optimization of maintenance plans relies on post-event feedback, leading to inefficient optimization processes. Currently, the design of digital work cards in the maintenance field mainly adopts two technical paths: one is the unstructured work card compilation method based on traditional documents (such as Word), and the other is a basic digital system based on structured data parsing.

[0003] Although existing digital work card design methods have made some progress in structured processing and tool management, they still have the following significant drawbacks: (1) Work card generation relies on human experience. Existing systems cannot automatically generate maintenance plans and engineers still need to manually write work card content, which is inefficient and prone to errors; (2) Data is isolated between systems. The work card system lacks deep integration with tool management, production planning, training systems, etc., and data cannot be automatically transferred; (3) There is a lack of intelligent recommendation capabilities. Existing systems cannot automatically recommend optimized maintenance steps or tool configurations based on historical maintenance records or fault modes; (4) Work card content cannot dynamically respond to changes in configuration, environmental conditions, personnel skills, etc., and lacks real-time adjustment capabilities; (5) Existing systems lack an automated verification mechanism for the logical rationality, process integrity, and data consistency of work cards, and rely on manual review. Summary of the Invention

[0004] Based on this, a method, apparatus, computer equipment, and storage medium for generating digital work cards are provided to solve the technical problems of low efficiency due to manual writing of digital work cards, isolated data that cannot be transferred, inability to optimize digital work card content based on historical data, inability to adjust digital work card content in real time, and reliance on manual review for content rationality verification.

[0005] On the one hand, a method for generating digital work cards is provided, the method comprising: When a maintenance task trigger instruction is received, the system collects the real-time operating data, historical maintenance records, and associated bill of materials (BOM) and 3D model data of the target equipment corresponding to the maintenance task trigger instruction to form target task data. The target task data is matched in multiple dimensions in the maintenance knowledge base, and multiple alternative maintenance plans are generated by combining rule engine and case reasoning. The digital twin model of the target device is invoked to perform simulation tests on the multiple alternative maintenance plans, simulation data is collected, the simulation performance score of each alternative maintenance plan is determined based on the simulation data, and the alternative maintenance plan with the highest simulation performance score is selected to generate a benchmark digital work card. Operators are matched based on the content of the benchmark digital work card. The operators then perform an immersive rehearsal by executing the benchmark digital work card, recording their operational behaviors and points of stagnation. Auxiliary information is added to the points of stagnation and integrated to form the final digital work card.

[0006] In one embodiment, the step of performing multi-dimensional matching of the target task data in the maintenance knowledge base, combined with a rule engine and case reasoning, generates multiple alternative maintenance plans, including: The target task data is analyzed to extract key feature information, including equipment type, fault type, and maintenance requirements. Based on the extracted key feature information, the system is matched against the maintenance knowledge base from multiple dimensions, including equipment parameters, historical maintenance cases, and industry standard requirements. The rule engine is used to initially filter and combine the matched information according to the preset rules, and case reasoning is used to learn from the handling methods of similar historical cases to generate at least two alternative maintenance plans.

[0007] In one embodiment, the step of calling the digital twin model of the target device to perform simulation tests on the multiple sets of alternative maintenance plans, collecting simulation data, determining the simulation performance score of each alternative maintenance plan based on the simulation data, and selecting the alternative maintenance plan with the highest simulation performance score to generate a benchmark digital work card includes: Based on the identifier of the target device, its corresponding digital twin model is invoked and loaded. The digital twin model includes geometric attributes, physical attributes, and functional attributes, and is synchronized with the state of the target device. In the environment of the digital twin model, a virtual executor is injected into each of the multiple alternative maintenance plans, and the virtual executor performs maintenance simulation tests according to the corresponding alternative maintenance plan; During the simulation test, simulation data is collected, including virtual total time consumption, tool path complexity, number of virtual disassembly and assembly actions, number of spatial interference warnings, and simulated risk factors. Based on the simulation data, a preset weighted evaluation algorithm is used to determine the simulation effectiveness score of each alternative maintenance plan; The multiple alternative maintenance plans are sorted in descending order of simulation effectiveness score, and the alternative maintenance plan with the highest simulation effectiveness score is selected to generate a benchmark digital work card.

[0008] In one embodiment, determining the simulation effectiveness score of each alternative maintenance plan based on the simulation data using a preset weighted evaluation algorithm includes: The simulated data, including the virtual total time T, tool path complexity C, number of virtual disassembly and assembly actions A, number of spatial interference warnings I, and simulated risk factor R, are normalized to obtain the normalized virtual total time f_T, normalized tool path complexity f_C, normalized number of virtual disassembly and assembly actions f_A, normalized number of spatial interference warnings f_I, and normalized simulated risk factor f_R. The virtual total time consumption, tool path complexity, number of virtual disassembly and assembly actions, number of spatial interference warnings, and simulated risk factors are respectively assigned a time efficiency weight a1, a path complexity weight a2, a spatial interference weight a3, and a comprehensive action and risk weight a4. The weight values ​​of each dimension are dynamically adjusted according to the task type, and the comprehensive simulation effectiveness score E is calculated as E=a1×f_T+a2×f_C+a3×f_A+a4×(0.5×f_I+0.5×f_R).

[0009] In one embodiment, the step of matching operators based on the content of the benchmark digital work card, performing an immersive rehearsal by having the operators execute the benchmark digital work card, recording operational behaviors and pause points, and adding auxiliary information to the pause points to integrate and form the final digital work card includes: Retrieve historical work records and qualification information of engineers scheduled to execute the benchmark digital work card from the personnel database, and determine their proficiency level based on their years of service, number of successful completions of similar tasks, and the level of operation certification they hold. Based on the engineer's proficiency level, the baseline digital work card is dynamically configured, and the engineer with the highest matching degree and the highest proficiency level is selected as the operator. The operator receives and begins executing the baseline digital work card in the environment of the digital twin model through a three-dimensional interactive interface. The system monitors the virtual operations of the operators in real time, verifies whether the sequence of steps, tool selection, and safety procedures comply with the standards, and provides real-time prompts and records for any violations. During the operator's virtual operation, the points of hesitation, the number of times the steps were repeated, the unconventional but effective operation paths used, and the virtual time of final completion were marked. Based on the marking information, identify the lag points, and add auxiliary information to the lag points, including unconventional but effective operation paths; The auxiliary information is integrated into the baseline digital work card as an alternative or recommended step to form the final digital work card.

[0010] In one embodiment, the method further includes: The final digital work card is executed on-site, key operations and results are recorded synchronously, and a mapping relationship is established with the corresponding virtual operation node in the digital twin model to form a real execution mirror; After a single execution of the final digital work card is completed, the simulation data, pre-simulation behavior data, and actual execution mirror data are aggregated, compared and analyzed to obtain the analysis results. Using the analysis results, the scheme deduction logic, the physical rules of the digital twin model, and the standard operating procedures in the knowledge base are calibrated and iteratively updated.

[0011] In one embodiment, the method further includes: The maintenance knowledge base is constructed using a knowledge graph structure, which includes equipment nodes, operation step nodes, tool nodes, and risk nodes. Semantic links are used to map the target equipment information, action sequence, tool selection and fault type of the maintenance plan to the equipment node, operation step node, tool node and risk node of the knowledge graph structure, respectively.

[0012] On the other hand, a device for generating digital work cards is provided, the device comprising: The task data acquisition module is used to collect real-time operating data, historical maintenance records, and associated bill of materials (BOM) and 3D model data of the target equipment corresponding to the maintenance task triggering instruction when a maintenance task triggering instruction is received, so as to form target task data. The maintenance plan generation module is used to perform multi-dimensional matching of the target task data in the maintenance knowledge base, and generate multiple alternative maintenance plans by combining the rule engine and case reasoning. The digital twin simulation and evaluation module is used to call the digital twin model of the target device, perform simulation tests on the multiple alternative maintenance plans, collect simulation data, determine the simulation performance score of each alternative maintenance plan based on the simulation data, and select the alternative maintenance plan with the highest simulation performance score to generate a benchmark digital work card. The operation rehearsal and work card optimization module is used to match operators with the content of the benchmark digital work card, and to conduct an immersive rehearsal by having the operators execute the benchmark digital work card, record operation behaviors and stuttering points, and add auxiliary information to the stuttering points to form the final digital work card.

[0013] In another aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of a method for generating a digital work card.

[0014] In another aspect, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of a method for generating a digital work card.

[0015] The aforementioned method, device, computer equipment, and storage medium for generating digital work cards automatically collect equipment operation data, historical maintenance records, and 3D model information. Combined with a maintenance knowledge base, they perform intelligent matching and case reasoning to automatically generate multiple maintenance plans and conduct simulations and evaluations based on digital twin models, thereby selecting the optimal solution to generate the digital work card. This method further incorporates immersive pre-rehearsals by operators, recording operational behaviors and bottlenecks in real time, and automatically integrating and optimizing information to form the final digital work card. Compared to manual compilation methods, this technology achieves automated generation, verification, and optimization of digital work cards, significantly improving maintenance efficiency and accuracy, reducing human error, and enabling work card content to dynamically respond to differences in equipment and personnel, enhancing the system's intelligence and adaptability, and significantly improving the efficiency, rationality, and feasibility of digital work card generation. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating a method for generating a digital work card in one embodiment of this application; Figure 2 Here is a logic diagram of a method for generating a digital work card in one embodiment of this application; Figure 3 This is a schematic diagram of the virtual simulation test process in one embodiment of this application; Figure 4 This is a structural block diagram of a device for generating digital work cards in one embodiment of this application; Figure 5 This is an internal structural diagram of a computer device in one embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0019] In one embodiment, such as Figure 1 , Figure 2 , Figure 3 As shown, a method for generating digital work cards is provided, including the following steps: Step S1: When a maintenance task trigger instruction is received, the real-time operating data, historical maintenance records, and associated bill of materials (BOM) and 3D model data of the target equipment corresponding to the maintenance task trigger instruction are collected to form target task data. Step S2: Perform multi-dimensional matching of the target task data in the maintenance knowledge base, and generate multiple alternative maintenance plans by combining the rule engine and case reasoning. Step S3: Call the digital twin model of the target device to perform simulation tests on the multiple alternative maintenance plans, collect simulation data, determine the simulation performance score of each alternative maintenance plan based on the simulation data, and select the alternative maintenance plan with the highest simulation performance score to generate a benchmark digital work card. Step S4: Match the operator with the content of the benchmark digital work card, and have the operator perform an immersive rehearsal by executing the benchmark digital work card. Record the operation behavior and stuttering points, and add auxiliary information to the stuttering points to form the final digital work card.

[0020] Specifically, by automatically collecting equipment operation data, historical maintenance records, and 3D model information, and combining this with a maintenance knowledge base for intelligent matching and case reasoning, multiple maintenance plans can be automatically generated. These plans are then evaluated and simulated based on a digital twin model, ultimately selecting the optimal solution to generate a digital work card. This method further incorporates immersive pre-exercise by operators, recording operational behaviors and bottlenecks in real time, and automatically integrating and optimizing information to form the final digital work card. Compared to manual compilation, this technology automates the generation, verification, and optimization of digital work cards, significantly improving maintenance efficiency and accuracy, reducing human error, and enabling the work card content to dynamically respond to differences in equipment and personnel. This enhances the system's intelligence and adaptability, significantly improving the efficiency, rationality, and feasibility of digital work card generation.

[0021] In this embodiment, the step of performing multi-dimensional matching of the target task data in the maintenance knowledge base, combined with a rule engine and case reasoning, generates multiple alternative maintenance plans, including: The target task data is analyzed to extract key feature information, including equipment type, fault type, and maintenance requirements. Based on the extracted key feature information, the system is matched against the maintenance knowledge base from multiple dimensions, including equipment parameters, historical maintenance cases, and industry standard requirements. The rule engine is used to initially filter and combine the matched information according to the preset rules, and case reasoning is used to learn from the handling methods of similar historical cases to generate at least two alternative maintenance plans.

[0022] This method, through the analysis and key feature extraction of target task data, and multi-dimensional matching and case reasoning based on a maintenance knowledge base, enables the system to automatically consider factors such as equipment type, failure mode, and maintenance standards when generating maintenance plans, thereby achieving personalized maintenance plan design for complex equipment. The introduction of a rule engine ensures that the generated plans conform to established industry specifications and internal standards, while the case reasoning mechanism allows the system to reuse historical successful experiences and perform structured migration. The implementation of this technical solution provides the digital work card generation process with traceable knowledge and logical reasoning foundations, realizing the transition from manual experience-driven to knowledge and data-driven approaches, thereby improving the intelligence and reliability of maintenance plans.

[0023] In this embodiment, the step of calling the digital twin model of the target device to perform simulation tests on the multiple alternative maintenance plans, collecting simulation data, determining the simulation effectiveness score of each alternative maintenance plan based on the simulation data, and selecting the alternative maintenance plan with the highest simulation effectiveness score to generate a benchmark digital work card includes: Based on the identifier of the target device, its corresponding digital twin model is invoked and loaded. The digital twin model includes geometric attributes, physical attributes, and functional attributes, and is synchronized with the state of the target device. In the environment of the digital twin model, a virtual executor is injected into each of the multiple alternative maintenance plans, and the virtual executor performs maintenance simulation tests according to the corresponding alternative maintenance plan; During the simulation test, simulation data is collected, including virtual total time consumption, tool path complexity, number of virtual disassembly and assembly actions, number of spatial interference warnings, and simulated risk factors. Based on the simulation data, a preset weighted evaluation algorithm is used to determine the simulation effectiveness score of each alternative maintenance plan; The multiple alternative maintenance plans are sorted in descending order of simulation effectiveness score, and the alternative maintenance plan with the highest simulation effectiveness score is selected to generate a benchmark digital work card.

[0024] The virtual actuator can be understood as a virtual robot that performs simulated operations. The physics engine calculates collisions and constraints during the assembly and disassembly process in real time.

[0025] This technology involves using a digital twin model of the target device to virtually simulate multiple alternative maintenance plans. This allows the system to comprehensively verify and evaluate the performance of maintenance plans before physical execution. The digital twin model possesses geometric, physical, and functional attributes and is synchronized with the device's status, thus the simulation results accurately reflect the actual operating characteristics of the device. By collecting multi-dimensional data, including time, path, action, interference, and risk, through simulation testing, the system can quantitatively compare and optimize the plans, thereby determining the optimal maintenance plan without manual trial and error. This mechanism effectively solves the problems of traditional work card content lacking verification and requiring manual review of logical errors, achieving automated work card rationality verification and dynamic optimization.

[0026] In this embodiment, determining the simulation effectiveness score of each alternative maintenance plan based on the simulation data using a preset weighted evaluation algorithm includes: The simulated data, including the virtual total time T, tool path complexity C, number of virtual disassembly and assembly actions A, number of spatial interference warnings I, and simulated risk factor R, are normalized to obtain the normalized virtual total time f_T, normalized tool path complexity f_C, normalized number of virtual disassembly and assembly actions f_A, normalized number of spatial interference warnings f_I, and normalized simulated risk factor f_R. The virtual total time consumption, tool path complexity, number of virtual disassembly and assembly actions, number of spatial interference warnings, and simulated risk factors are respectively assigned a time efficiency weight a1, a path complexity weight a2, a spatial interference weight a3, and a comprehensive action and risk weight a4. The weight values ​​of each dimension are dynamically adjusted according to the task type, and the comprehensive simulation effectiveness score E is calculated as follows: E = a1×f_T + a2×f_C + a3×f_A + a4×(0.5×f_I + 0.5×f_R), where T represents the total virtual time, C represents the tool path complexity, A represents the number of virtual disassembly and assembly actions, I represents the number of spatial interference warnings, R represents the simulated risk factor, f_T represents the normalized total virtual time, f_C represents the normalized tool path complexity, f_A represents the normalized number of virtual disassembly and assembly actions, f_I represents the normalized number of spatial interference warnings, and f_R represents the normalized simulated risk factor.

[0027] This system employs a weighted evaluation algorithm to quantify and score the simulation data, constructing an effectiveness evaluation system for maintenance plans. By normalizing multi-dimensional simulation indicators, the algorithm eliminates the influence between different units, making the effectiveness score calculation more objective. Simultaneously, the system dynamically adjusts weight coefficients based on task type, giving the evaluation model adaptive capabilities and automatically balancing factors such as time, risk, and operational complexity for different tasks. This technical solution eliminates reliance on single-factor manual experience in the generation of digital work cards, instead enabling scientific and quantitative decision-making for maintenance plans through standardized algorithms, thereby significantly improving the rationality and execution efficiency of digital work card content.

[0028] In this embodiment, the step of matching operators based on the content of the benchmark digital work card, having the operators perform an immersive rehearsal using the benchmark digital work card, recording operational behaviors and pause points, and adding auxiliary information to the pause points to integrate and form the final digital work card includes: Retrieve historical work records and qualification information of engineers scheduled to execute the benchmark digital work card from the personnel database, and determine their proficiency level based on their years of service, number of successful completions of similar tasks, and the level of operation certification they hold. Based on the engineer's proficiency level, the baseline digital work card is dynamically configured, and the engineer with the highest matching degree and the highest proficiency level is selected as the operator. The operator receives and begins executing the baseline digital work card in the environment of the digital twin model through a three-dimensional interactive interface. The system monitors the virtual operations of the operators in real time, verifies whether the sequence of steps, tool selection, and safety procedures comply with the standards, and provides real-time prompts and records for any violations. During the operator's virtual operation, the points of hesitation, the number of times the steps were repeated, the unconventional but effective operation paths used, and the virtual time of final completion were marked. Based on the marking information, identify the lag points, and add auxiliary information to the lag points, including unconventional but effective operation paths; The auxiliary information is integrated into the baseline digital work card as an alternative or recommended step to form the final digital work card.

[0029] By linking the baseline digital work card with the operator database, the system dynamically matches the work card content with the executor's capabilities. The system automatically identifies operator proficiency and assigns tasks accordingly, ensuring that complex maintenance tasks are performed by the most suitable engineer, thereby reducing operational errors. During immersive rehearsals, real-time monitoring of operational behavior and identification of bottlenecks enable the system to automatically detect potential design flaws or unreasonable processes in the work card and optimize the execution path by adding auxiliary information. The resulting digital work card not only meets standard operating procedure requirements but also incorporates real operational feedback, achieving a closed-loop transformation from "theoretical solutions" to "executable work orders," effectively solving the problem of traditional systems lacking interactive verification and intelligent optimization.

[0030] In this embodiment, the method further includes: The final digital work card is executed on-site, key operations and results are recorded synchronously, and a mapping relationship is established with the corresponding virtual operation node in the digital twin model to form a real execution mirror; After a single execution of the final digital work card is completed, the simulation data, pre-simulation behavior data, and actual execution mirror data are aggregated, compared and analyzed to obtain the analysis results. Using the analysis results, the scheme deduction logic, the physical rules of the digital twin model, and the standard operating procedures in the knowledge base are calibrated and iteratively updated.

[0031] By recording real operational data during on-site execution and establishing a mapping relationship between virtual and reality, dynamic linkage between the digital twin and actual operations is achieved. Through comparative analysis of simulation data, pre-simulation data, and actual execution data, the system can automatically identify model deviations, operational process defects, and missing content in the knowledge base, thereby enabling self-learning and self-correction of the digital twin model and knowledge base. This "virtual-real fusion—feedback update" mechanism transforms the digital work card from a one-time generated static file into a continuously evolving, intelligent maintenance tool that optimizes with execution experience, completely solving the problem of traditional work cards' inability to be dynamically updated and continuously improved.

[0032] In this embodiment, the method further includes: The maintenance knowledge base is constructed using a knowledge graph structure, which includes equipment nodes, operation step nodes, tool nodes, and risk nodes. Semantic links are used to map the target equipment information, action sequence, tool selection and fault type of the maintenance plan to the equipment node, operation step node, tool node and risk node of the knowledge graph structure, respectively.

[0033] Specifically, by employing a knowledge graph structure to construct a maintenance knowledge base, semantic associations are formed between equipment information, operating procedures, tools, and risks. This structure not only achieves cross-system data fusion but also supports semantic-level reasoning and association during maintenance plan generation. This allows the system to generate reasonable alternative solutions based on the knowledge network even when facing new equipment or unknown faults. Multi-node mapping achieved through semantic links ensures logical consistency and structural traceability in work card content generation, significantly improving the intelligent recommendation capabilities and automation level of digital work card generation, and overcoming the drawbacks of data silos and knowledge gaps in existing systems.

[0034] The aforementioned method for generating digital work cards automatically collects equipment operation data, historical maintenance records, and 3D model information. Combined with a maintenance knowledge base, it performs intelligent matching and case reasoning to automatically generate multiple maintenance plans and conduct simulations and evaluations based on a digital twin model, thereby selecting the optimal solution to generate the digital work card. This method further incorporates immersive pre-rehearsals by operators, recording operational behaviors and bottlenecks in real time, and automatically integrating and optimizing information to form the final digital work card. Compared to manual compilation, this technology achieves automated generation, verification, and optimization of digital work cards, significantly improving maintenance efficiency and accuracy, reducing human error, and enabling work card content to dynamically respond to differences in equipment and personnel, enhancing the system's intelligence and adaptability, and significantly improving the efficiency, rationality, and feasibility of digital work card generation.

[0035] In one embodiment, such as Figure 4 As shown, a device 10 for generating digital work cards is provided, including: a task data acquisition module 1, a maintenance plan generation module 2, a digital twin simulation and evaluation module 3, an operation simulation and work card optimization module 4, an execution mirror and model calibration module 5, and a knowledge graph construction and semantic mapping module 6.

[0036] The task data acquisition module 1 is used to collect real-time operating data, historical maintenance records, and associated bill of materials (BOM) and 3D model data of the target equipment corresponding to the maintenance task triggering instruction when receiving the maintenance task triggering instruction, so as to form target task data.

[0037] The maintenance plan generation module 2 is used to perform multi-dimensional matching of the target task data in the maintenance knowledge base, and generate multiple alternative maintenance plans by combining the rule engine and case reasoning.

[0038] The digital twin simulation and evaluation module 3 is used to call the digital twin model of the target device, perform simulation tests on the multiple alternative maintenance plans, collect simulation data, determine the simulation performance score of each alternative maintenance plan based on the simulation data, and select the alternative maintenance plan with the highest simulation performance score to generate a benchmark digital work card.

[0039] The operation rehearsal and work card optimization module 4 is used to match operators according to the content of the benchmark digital work card, and to conduct immersive rehearsal by having the operators execute the benchmark digital work card, record operation behaviors and stuttering points, and add auxiliary information to the stuttering points to form the final digital work card.

[0040] This device, through modular design, integrates functional units such as data acquisition, knowledge matching, deduction verification, and interactive optimization into a single system architecture, forming an independently operable digital work card generation device. Data flow and control logic between modules are automatically connected, achieving fully automated processing from maintenance task triggering to final work card generation. The implementation of this device transforms the digital work card generation process from scattered manual operations into a systematic, intelligent, and integrated execution process, significantly reducing the need for manual intervention, improving cross-system data flow efficiency, and realizing a fully closed-loop function for automatic digital work card generation, verification, and optimization.

[0041] In this embodiment, the step of performing multi-dimensional matching of the target task data in the maintenance knowledge base, combined with a rule engine and case reasoning, generates multiple alternative maintenance plans, including: The target task data is analyzed to extract key feature information, including equipment type, fault type, and maintenance requirements. Based on the extracted key feature information, the system is matched against the maintenance knowledge base from multiple dimensions, including equipment parameters, historical maintenance cases, and industry standard requirements. The rule engine is used to initially filter and combine the matched information according to the preset rules, and case reasoning is used to learn from the handling methods of similar historical cases to generate at least two alternative maintenance plans.

[0042] In this embodiment, the step of calling the digital twin model of the target device to perform simulation tests on the multiple alternative maintenance plans, collecting simulation data, determining the simulation effectiveness score of each alternative maintenance plan based on the simulation data, and selecting the alternative maintenance plan with the highest simulation effectiveness score to generate a benchmark digital work card includes: Based on the identifier of the target device, its corresponding digital twin model is invoked and loaded. The digital twin model includes geometric attributes, physical attributes, and functional attributes, and is synchronized with the state of the target device. In the environment of the digital twin model, a virtual executor is injected into each of the multiple alternative maintenance plans, and the virtual executor performs maintenance simulation tests according to the corresponding alternative maintenance plan; During the simulation test, simulation data is collected, including virtual total time consumption, tool path complexity, number of virtual disassembly and assembly actions, number of spatial interference warnings, and simulated risk factors. Based on the simulation data, a preset weighted evaluation algorithm is used to determine the simulation effectiveness score of each alternative maintenance plan; The multiple alternative maintenance plans are sorted in descending order of simulation effectiveness score, and the alternative maintenance plan with the highest simulation effectiveness score is selected to generate a benchmark digital work card.

[0043] In this embodiment, determining the simulation effectiveness score of each alternative maintenance plan based on the simulation data using a preset weighted evaluation algorithm includes: The simulated data, including the virtual total time T, tool path complexity C, number of virtual disassembly and assembly actions A, number of spatial interference warnings I, and simulated risk factor R, are normalized to obtain the normalized virtual total time f_T, normalized tool path complexity f_C, normalized number of virtual disassembly and assembly actions f_A, normalized number of spatial interference warnings f_I, and normalized simulated risk factor f_R. The virtual total time consumption, tool path complexity, number of virtual disassembly and assembly actions, number of spatial interference warnings, and simulated risk factors are respectively assigned a time efficiency weight a1, a path complexity weight a2, a spatial interference weight a3, and a comprehensive action and risk weight a4. The weight values ​​of each dimension are dynamically adjusted according to the task type, and the comprehensive simulation effectiveness score E is calculated as follows: E = a1×f_T + a2×f_C + a3×f_A + a4×(0.5×f_I + 0.5×f_R), where T represents the total virtual time, C represents the tool path complexity, A represents the number of virtual disassembly and assembly actions, I represents the number of spatial interference warnings, R represents the simulated risk factor, f_T represents the normalized total virtual time, f_C represents the normalized tool path complexity, f_A represents the normalized number of virtual disassembly and assembly actions, f_I represents the normalized number of spatial interference warnings, and f_R represents the normalized simulated risk factor.

[0044] In this embodiment, the step of matching operators based on the content of the benchmark digital work card, having the operators perform an immersive rehearsal using the benchmark digital work card, recording operational behaviors and pause points, and adding auxiliary information to the pause points to integrate and form the final digital work card includes: Retrieve historical work records and qualification information of engineers scheduled to execute the benchmark digital work card from the personnel database, and determine their proficiency level based on their years of service, number of successful completions of similar tasks, and the level of operation certification they hold. Based on the engineer's proficiency level, the baseline digital work card is dynamically configured, and the engineer with the highest matching degree and the highest proficiency level is selected as the operator. The operator receives and begins executing the baseline digital work card in the environment of the digital twin model through a three-dimensional interactive interface. The system monitors the virtual operations of the operators in real time, verifies whether the sequence of steps, tool selection, and safety procedures comply with the standards, and provides real-time prompts and records for any violations. During the operator's virtual operation, the points of hesitation, the number of times the steps were repeated, the unconventional but effective operation paths used, and the virtual time of final completion were marked. Based on the marking information, identify the lag points, and add auxiliary information to the lag points, including unconventional but effective operation paths; The auxiliary information is integrated into the baseline digital work card as an alternative or recommended step to form the final digital work card.

[0045] In this embodiment, the mirroring and model calibration module 5 is used for: The final digital work card is executed on-site, key operations and results are recorded synchronously, and a mapping relationship is established with the corresponding virtual operation node in the digital twin model to form a real execution mirror; After a single execution of the final digital work card is completed, the simulation data, pre-simulation behavior data, and actual execution mirror data are aggregated, compared and analyzed to obtain the analysis results. Using the analysis results, the scheme deduction logic, the physical rules of the digital twin model, and the standard operating procedures in the knowledge base are calibrated and iteratively updated.

[0046] In this embodiment, the knowledge graph construction and semantic mapping module 6 is used for: The maintenance knowledge base is constructed using a knowledge graph structure, which includes equipment nodes, operation step nodes, tool nodes, and risk nodes. Semantic links are used to map the target equipment information, action sequence, tool selection and fault type of the maintenance plan to the equipment node, operation step node, tool node and risk node of the knowledge graph structure, respectively.

[0047] The aforementioned digital work card generation device automatically collects equipment operation data, historical maintenance records, and 3D model information. Combined with a maintenance knowledge base, it performs intelligent matching and case reasoning to automatically generate multiple maintenance plans and conduct simulations and evaluations based on a digital twin model, thereby selecting the optimal plan to generate the digital work card. This method further incorporates immersive pre-rehearsals by operators, recording operational behaviors and bottlenecks in real time, and automatically integrating and optimizing information to form the final digital work card. Compared to manual compilation, this technology achieves automated generation, verification, and optimization of digital work cards, significantly improving maintenance efficiency and accuracy, reducing human error, and enabling the work card content to dynamically respond to differences in equipment and personnel, enhancing the system's intelligence and adaptability, and significantly improving the efficiency, rationality, and feasibility of digital work card generation.

[0048] Specific limitations regarding the digital work card generation device can be found in the limitations of the digital work card generation method described above, and will not be repeated here. Each module in the aforementioned digital work card generation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0049] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system, computer programs, and the database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage medium. The database stores data for generating digital work cards. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for generating digital work cards.

[0050] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0051] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: When a maintenance task trigger instruction is received, the system collects the real-time operating data, historical maintenance records, and associated bill of materials (BOM) and 3D model data of the target equipment corresponding to the maintenance task trigger instruction to form target task data. The target task data is matched in multiple dimensions in the maintenance knowledge base, and multiple alternative maintenance plans are generated by combining rule engine and case reasoning. The digital twin model of the target device is invoked to perform simulation tests on the multiple alternative maintenance plans, simulation data is collected, the simulation performance score of each alternative maintenance plan is determined based on the simulation data, and the alternative maintenance plan with the highest simulation performance score is selected to generate a benchmark digital work card. Operators are matched based on the content of the benchmark digital work card. The operators then perform an immersive rehearsal by executing the benchmark digital work card, recording their operational behaviors and points of stagnation. Auxiliary information is added to the points of stagnation and integrated to form the final digital work card.

[0052] For specific limitations on the steps a processor takes when executing a computer program, please refer to the limitations on the method for generating digital work cards mentioned above, which will not be repeated here.

[0053] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor: When a maintenance task trigger instruction is received, the system collects the real-time operating data, historical maintenance records, and associated bill of materials (BOM) and 3D model data of the target equipment corresponding to the maintenance task trigger instruction to form target task data. The target task data is matched in multiple dimensions in the maintenance knowledge base, and multiple alternative maintenance plans are generated by combining rule engine and case reasoning. The digital twin model of the target device is invoked to perform simulation tests on the multiple alternative maintenance plans, simulation data is collected, the simulation performance score of each alternative maintenance plan is determined based on the simulation data, and the alternative maintenance plan with the highest simulation performance score is selected to generate a benchmark digital work card. Operators are matched based on the content of the benchmark digital work card. The operators then perform an immersive rehearsal by executing the benchmark digital work card, recording their operational behaviors and points of stagnation. Auxiliary information is added to the points of stagnation and integrated to form the final digital work card.

[0054] For specific limitations on the steps implemented when a computer program is executed by a processor, please refer to the limitations on the method for generating digital work cards mentioned above, which will not be repeated here.

[0055] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0056] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0057] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for generating digital work cards, characterized in that, include: When a maintenance task trigger instruction is received, the system collects the real-time operating data, historical maintenance records, and associated bill of materials and 3D model data of the target equipment corresponding to the maintenance task trigger instruction to form target task data. The target task data is matched in multiple dimensions in the maintenance knowledge base, and multiple alternative maintenance plans are generated by combining rule engine and case reasoning. The digital twin model of the target device is invoked to perform simulation tests on the multiple alternative maintenance plans, simulation data is collected, the simulation performance score of each alternative maintenance plan is determined based on the simulation data, and the alternative maintenance plan with the highest simulation performance score is selected to generate a benchmark digital work card. Operators are matched based on the content of the benchmark digital work card. The operators then perform an immersive rehearsal by executing the benchmark digital work card, recording their operational behaviors and points of stagnation. Auxiliary information is added to the points of stagnation and integrated to form the final digital work card.

2. The method for generating a digital work card according to claim 1, characterized in that, The process involves multi-dimensional matching of the target task data within the maintenance knowledge base, combined with a rule engine and case reasoning, to generate multiple alternative maintenance plans, including: The target task data is analyzed to extract key feature information, including equipment type, fault type, and maintenance requirements. Based on the extracted key feature information, the system is matched against the maintenance knowledge base from multiple dimensions, including equipment parameters, historical maintenance cases, and industry standard requirements. The rule engine is used to initially filter and combine the matched information according to the preset rules, and case reasoning is used to learn from the handling methods of similar historical cases to generate at least two alternative maintenance plans.

3. The method for generating a digital work card according to claim 1, characterized in that, The process involves calling the digital twin model of the target device to perform simulation tests on the multiple alternative maintenance plans, collecting simulation data, determining the simulation effectiveness score of each alternative maintenance plan based on the simulation data, and selecting the alternative maintenance plan with the highest simulation effectiveness score to generate a benchmark digital work card, including: Based on the identifier of the target device, its corresponding digital twin model is invoked and loaded. The digital twin model includes geometric attributes, physical attributes, and functional attributes, and is synchronized with the state of the target device. In the environment of the digital twin model, a virtual executor is injected into each of the multiple alternative maintenance plans, and the virtual executor performs maintenance simulation tests according to the corresponding alternative maintenance plan; During the simulation test, simulation data is collected, including virtual total time consumption, tool path complexity, number of virtual disassembly and assembly actions, number of spatial interference warnings, and simulated risk factors. Based on the simulation data, a preset weighted evaluation algorithm is used to determine the simulation effectiveness score of each alternative maintenance plan; The multiple alternative maintenance plans are sorted in descending order of simulation effectiveness score, and the alternative maintenance plan with the highest simulation effectiveness score is selected to generate a benchmark digital work card.

4. The method for generating digital work cards according to claim 3, characterized in that, The step of determining the simulation effectiveness score of each alternative maintenance plan based on the simulation data and using a preset weighted evaluation algorithm includes: The simulated data, including the virtual total time T, tool path complexity C, number of virtual disassembly and assembly actions A, number of spatial interference warnings I, and simulated risk factor R, are normalized to obtain the normalized virtual total time f_T, normalized tool path complexity f_C, normalized number of virtual disassembly and assembly actions f_A, normalized number of spatial interference warnings f_I, and normalized simulated risk factor f_R. The virtual total time consumption, tool path complexity, number of virtual disassembly and assembly actions, number of spatial interference warnings, and simulated risk factors are respectively assigned a time efficiency weight a1, a path complexity weight a2, a spatial interference weight a3, and a comprehensive action and risk weight a4. The weight values ​​of each dimension are dynamically adjusted according to the task type, and the comprehensive simulation effectiveness score E is calculated as E=a1×f_T+a2×f_C+a3×f_A+a4×(0.5×f_I+0.5×f_R).

5. The method for generating a digital work card according to claim 1, characterized in that, The process of matching operators based on the content of the benchmark digital work card, performing immersive rehearsals by having the operators execute the benchmark digital work card, recording operational behaviors and points of lag, and adding auxiliary information to the points of lag to form the final digital work card includes: Retrieve historical work records and qualification information of engineers scheduled to execute the benchmark digital work card from the personnel database, and determine their proficiency level based on their years of service, number of successful completions of similar tasks, and the level of operation certification they hold. Based on the engineer's proficiency level, the baseline digital work card is dynamically configured, and the engineer with the highest matching degree and the highest proficiency level is selected as the operator. The operator receives and begins executing the baseline digital work card in the environment of the digital twin model through a three-dimensional interactive interface. The system monitors the virtual operations of the operators in real time, verifies whether the sequence of steps, tool selection, and safety procedures comply with the standards, and provides real-time prompts and records for any violations. During the operator's virtual operation, the points of hesitation, the number of times the steps were repeated, the unconventional but effective operation paths used, and the virtual time of final completion were marked. Based on the marking information, identify the lag points, and add auxiliary information to the lag points, including unconventional but effective operation paths; The auxiliary information is integrated into the baseline digital work card as an alternative or recommended step to form the final digital work card.

6. The method for generating a digital work card according to claim 1, characterized in that, The method further includes: The final digital work card is executed on-site, key operations and results are recorded synchronously, and a mapping relationship is established with the corresponding virtual operation node in the digital twin model to form a real execution mirror; After a single execution of the final digital work card is completed, the simulation data, pre-simulation behavior data, and actual execution mirror data are aggregated, compared and analyzed to obtain the analysis results. Using the analysis results, the scheme deduction logic, the physical rules of the digital twin model, and the standard operating procedures in the knowledge base are calibrated and iteratively updated.

7. The method for generating a digital work card according to claim 1, characterized in that, The method further includes: The maintenance knowledge base is constructed using a knowledge graph structure, which includes equipment nodes, operation step nodes, tool nodes, and risk nodes. Semantic links are used to map the target equipment information, action sequence, tool selection and fault type of the maintenance plan to the equipment node, operation step node, tool node and risk node of the knowledge graph structure, respectively.

8. A device for generating digital work cards, characterized in that, The device includes: The task data acquisition module is used to collect real-time operating data, historical maintenance records, and associated bill of materials (BOM) and 3D model data of the target equipment corresponding to the maintenance task triggering instruction when a maintenance task triggering instruction is received, so as to form target task data. The maintenance plan generation module is used to perform multi-dimensional matching of the target task data in the maintenance knowledge base, and generate multiple alternative maintenance plans by combining the rule engine and case reasoning. The digital twin simulation and evaluation module is used to call the digital twin model of the target device, perform simulation tests on the multiple alternative maintenance plans, collect simulation data, determine the simulation performance score of each alternative maintenance plan based on the simulation data, and select the alternative maintenance plan with the highest simulation performance score to generate a benchmark digital work card. The operation rehearsal and work card optimization module is used to match operators with the content of the benchmark digital work card, and to conduct an immersive rehearsal by having the operators execute the benchmark digital work card, record operation behaviors and stuttering points, and add auxiliary information to the stuttering points to form the final digital work card.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images