Airport operation and maintenance distributed intelligent collaboration method and system based on field state driving

Abstract

The application provides an airport operation and maintenance distributed intelligent collaboration method and system based on field state driving, and belongs to the technical field of airport operation and maintenance; the method comprises the following steps: generating a versioned intelligent work order based on obtained operation and maintenance equipment state data and task constraint information; performing consistency checking on field evidence data and step execution conditions corresponding to target steps, and executing the target steps after the consistency checking is passed; determining whether the current work order version is invalid; if it is determined that the current work order version is invalid, performing local re-planning on the affected steps based on step dependency relationships and field state change information, so as to generate a new version of the intelligent work order and switch execution. When an unplanned change occurs in the field, the application can automatically perceive and determine whether the original plan is invalid, then only the affected part is accurately adjusted and re-planned, so that it is ensured that the maintenance task will not be easily interrupted or completely overturned.

Description

Technical Field

[0001] This invention relates to the field of airport operation and maintenance technology, specifically to a distributed intelligent collaborative method and system for airport operation and maintenance based on on-site status. Background Technology

[0002] Airport operations and maintenance involve various critical equipment such as baggage sorting, boarding bridges, and navigational lighting. The timeliness and accuracy of maintenance and support directly impact flight safety and efficiency. Currently, airport operations and maintenance commonly use digital work order systems to manage maintenance tasks. These systems typically generate predefined static work orders based on historical equipment data, fault codes, or planned inspections, and then issue them to on-site maintenance personnel for execution.

[0003] However, existing technologies of this kind all employ static work order processes, which cannot adapt to dynamically changing on-site operating environments. Work orders are generated based on equipment status information and predetermined rules at a specific moment; once issued, their step sequence and execution logic are fixed. By the time maintenance personnel arrive on-site, the actual situation may have changed, rendering the original work order steps invalid or inapplicable. In this case, the system lacks effective on-site status awareness and real-time decision-making capabilities, often only able to suspend the current work order, requiring manual feedback and replanning of the entire task, or relying on on-site experience for maintenance personnel to handle the situation. This not only causes maintenance interruptions, time delays, and resource waste, but also introduces operational errors and safety risks due to the disconnect between work orders and the actual on-site conditions. Summary of the Invention

[0004] The purpose of this invention is to provide a distributed intelligent collaborative method and system for airport operation and maintenance based on on-site status, which can instantly replan the operation process when unexpected situations such as incompatible spare parts or new faults occur on-site, without requiring maintenance personnel to start all maintenance procedures from scratch.

[0005] To achieve the above objectives, this invention provides a distributed intelligent collaborative method for airport operation and maintenance based on on-site state-driven processes, comprising: generating a versioned intelligent work order containing a step sequence, step dependencies, and corresponding execution conditions for each step based on acquired operation and maintenance equipment status data and task constraint information; before executing the target step in the versioned intelligent work order, collecting on-site evidence data corresponding to the target step, and performing a consistency check between the on-site evidence data and the execution conditions corresponding to the target step, and executing the target step after the consistency check passes; determining whether the current work order version is invalid based on the on-site evidence data fed back during execution; if the current work order version is invalid, performing local replanning on the affected steps based on the step dependencies and on-site state change information to generate a new version of the intelligent work order and switching its execution.

[0006] Optionally, the versioned smart work order further includes a parent version identifier and a work order status identifier; wherein, the parent version identifier is used to indicate the previous work order version corresponding to the current work order version, and the work order status identifier is used to characterize the valid status of the current work order version.

[0007] Optionally, the on-site evidence data includes one or more of the following: on-site image data, on-site video data, voice data, equipment operating parameter data, location information, and timestamp information.

[0008] Optionally, the consistency verification includes: matching and verifying the on-site evidence data with the evidence type requirements, step-level local state requirements, and step-level local security constraint requirements corresponding to the target step; Based on the results of the matching verification, it is determined whether the execution conditions of the target step are met.

[0009] Optionally, the consistency verification further includes: weighting each matching verification result according to the credibility weight corresponding to different types of on-site evidence data to obtain the corresponding consistency score; when the consistency score is less than a preset score threshold, it is determined that the target step does not meet the step execution conditions.

[0010] Optionally, determining whether the current work order version is invalid includes: determining the current field status parameters based on the field evidence data, and verifying the current field status parameters with the overall status conditions corresponding to the current work order version; wherein, the overall status conditions include at least one of equipment operating status conditions, operating environment conditions, and task execution constraints; when the state mismatch value of the current field status parameters relative to the preset status parameters corresponding to the overall status conditions is greater than a preset failure threshold, the current work order version is determined to be invalid.

[0011] Optionally, the local replanning includes: determining the set of affected steps caused by the change in on-site status information based on the step dependencies; replanning the step execution conditions and step execution order only for the set of affected steps and their subsequent dependent steps; and for unaffected steps, inheriting the original step content and corresponding on-site evidence association relationships in the current work order version.

[0012] Optionally, the local replanning also includes: setting rollback anchors for the affected steps; the rollback anchors are used to restore the equipment site to a preset safe state before switching to the new version of the smart work order.

[0013] Optionally, it also includes: after the work order is executed, associating the work order version evolution record, on-site evidence data, local replanning information and final processing result generated during the execution process to generate a structured maintenance case; based on the structured maintenance case, modifying and updating at least one of the step execution conditions, step dependencies and local replanning rules.

[0014] On the other hand, the present invention provides a distributed intelligent collaborative system for airport operation and maintenance based on field status, which is used to realize a distributed intelligent collaborative method for airport operation and maintenance based on field status. The system includes a control module, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to realize a distributed intelligent collaborative method for airport operation and maintenance based on field status.

[0015] The above technical solution ensures operational safety by setting up real-time evidence-based security checks for each step, preventing erroneous operations caused by unmet conditions. When unforeseen changes occur on-site, the system can automatically detect and determine whether the original plan has failed. It then makes precise adjustments and replans only for the affected parts, while inheriting all unaffected valid steps. This ensures that the maintenance task is not easily interrupted or completely overturned, thereby improving the success rate, overall efficiency, and continuity of the operation.

[0016] Other features and advantages of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0017] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the following detailed description to explain the invention, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of a distributed intelligent collaborative method for airport operation and maintenance based on on-site conditions.

[0018] Figure 2 This is a flowchart for verifying the consistency of on-site evidence and making a permission decision before the execution of the steps. Detailed Implementation

[0019] The following is in conjunction with the appendix Figure 1 - Appendix Figure 2 The specific implementation methods of the embodiments of the present invention will be described in detail below. It should be understood that the specific implementation methods described herein are only for illustrating and explaining the embodiments of the present invention, and are not intended to limit the embodiments of the present invention.

[0020] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application all comply with the relevant provisions of national laws and regulations. In the embodiments of this application, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solution of this application, and do not imply that the applicant has already used or necessarily used such solutions.

[0021] In the process of realizing this invention, the inventors of this application discovered that the static work order process used in the prior art cannot adapt to dynamic changes on site, which will lead to work interruption and low efficiency.

[0022] Example 1 Reference Figures 1-2 This is the first embodiment of the present invention, which provides a distributed intelligent collaborative method for airport operation and maintenance based on on-site state-driven operation, including: S100: Based on the acquired equipment status data and task constraint information, generate versioned smart work orders that include a sequence of steps, step dependencies, and execution conditions for each step.

[0023] In the embodiments of this application, the versioned smart work order also includes a parent version identifier and a work order status identifier; wherein, the parent version identifier is used to indicate the previous work order version corresponding to the current work order version, and the work order status identifier is used to characterize the valid status of the current work order version.

[0024] In some optional implementations, the acquisition of maintenance equipment status data is achieved through a management agent. This management agent communicates with the airport's SCADA (Supervisory Control and Data Acquisition) system, local equipment control systems, distributed sensor networks, high-definition video surveillance equipment, and on-site environmental monitoring terminals to collect status data for all maintenance equipment across the airport. The maintenance equipment includes at least one type of equipment: baggage sorting equipment, boarding bridge equipment, navigation lighting equipment, airport power supply equipment, conveying equipment, and their associated control units.

[0025] In some optional implementations, the equipment status data includes equipment operating condition data, fault alarm data, structural status data, runtime data, and environmental parameter data such as temperature and humidity, dust concentration, and personnel distribution around the work area.

[0026] In some optional implementations, anomaly detection is performed on the collected operational status data. Based on preset rules or algorithms (e.g., calculating the comprehensive abnormal values ​​of multiple parameters such as equipment temperature and vibration), a target maintenance task is automatically generated when the equipment is determined to have entered an abnormal state. This task includes core information such as equipment identification, preliminary fault type, and risk level.

[0027] In some optional implementations, the acquisition and integration of task constraint information includes: 1. Acquisition of Maintenance Strategy Data: Based on the generated target maintenance task, the management agent identifies the matching specialized agent (such as the baggage system diagnostic agent) and sends a diagnostic request to it. The specialized agent performs in-depth fault analysis based on real-time data, historical records, and a mechanism rule base, outputting maintenance strategy data. This data includes at least the specific fault cause, recommended maintenance steps, required tools / spare parts, safety constraints, and suggested execution order.

[0028] 2. Synchronous Acquisition of Other Constraint Information: The management agent synchronously connects with the airport flight operation scheduling system, warehouse inventory management system, and personnel access and location system to obtain real-time task constraint information related to this maintenance operation. This information includes operational safety specifications, available maintenance time windows (flight windows), inventory status of required spare parts, and the location and status of maintenance personnel with the corresponding skill levels.

[0029] Furthermore, after acquiring and integrating the aforementioned data, the management agent, based on the acquired equipment status data (generated through anomaly detection), the maintenance strategy data output by the professional agent, and real-time task constraint information such as personnel, inventory, and flight schedules, executes the work order generation logic. This includes constructing a sequence of steps and dependencies, defining step execution conditions and on-site evidence conditions, and initializing the work order's versioning attributes (version number, status identifier, parent version identifier, etc.), ultimately generating a structured, versioned intelligent work order initial version (such as V0).

[0030] The aforementioned solution generates versioned intelligent work orders based on equipment status data and task constraint information. It establishes step sequences, dependencies, and execution conditions within these work orders, enabling a transformation from traditional static work orders to dynamic, structured work orders for airport operations and maintenance. This improves the standardization and traceability of task organization in complex operations and maintenance scenarios. Furthermore, by introducing version numbers, parent version identifiers, and work order status identifiers, the solution allows for version evolution, facilitating dynamic adjustments as on-site conditions change. This enhances task adaptability and overall scheduling efficiency in collaborative operations and maintenance involving multiple devices and disciplines at the airport.

[0031] S200: Before executing the target step in the versioned smart work order, collect the on-site evidence data corresponding to the target step, and perform a consistency check between the on-site evidence data and the execution conditions of the target step. After the consistency check passes, execute the target step.

[0032] In the embodiments of this application, the on-site evidence data includes one or more of the following: on-site image data, on-site video data, voice data, equipment operating parameter data, location information, and timestamp information.

[0033] In some alternative implementations, the edge agent is deployed on the mobile terminal, wearable device, or field edge computing unit of the maintenance personnel. Before executing the target step, the edge agent loads the interactive operation interface corresponding to the target step. The interactive operation interface includes at least the step operation instructions, safety prompts, required tools and spare parts information, step dependencies, and an interactive entry point for triggering step verification.

[0034] In some optional implementations, after the maintenance personnel complete the procedure preparation, the edge agent sends a procedure execution permission request to the management agent. This permission request includes at least the current work order version number, the target procedure number, the device identifier, and the maintenance personnel identifier.

[0035] In some optional implementations, after receiving a permission request to execute a step, the management agent verifies the validity of the current work order version and the completion status of the prerequisite steps corresponding to the target step. When the verification passes, the authorized edge agent enters the on-site evidence collection and consistency verification process.

[0036] In some optional implementations, the edge agent controls the field sensing device to collect corresponding field evidence data based on the step execution conditions corresponding to the target step. These step execution conditions include at least evidence type requirements, step-level local state requirements, and step-level local security constraint requirements.

[0037] In some alternative implementations, step-level local state requirements are used to characterize the local operational states that must be satisfied before executing the current target step. Local safety constraint requirements are used to characterize the safety restrictions within the local operational area corresponding to the current target step.

[0038] In some alternative implementations, collecting on-site evidence data includes: To verify that the target device is in a power-off state, read the current parameter data of the corresponding power supply circuit or collect the indicator light image of the power distribution cabinet; To verify that the tools required for the current step are in place, obtain the RFID scan results or tool location information of the tools; To verify that maintenance personnel are in the designated work area, their location information is obtained; To verify that the local work area corresponding to the current step meets the safety requirements, on-site images or video data of the work area are collected.

[0039] In the embodiments of this application, the consistency verification includes: matching and verifying the on-site evidence data with the evidence type requirements, step-level local state requirements, and step-level local security constraint requirements corresponding to the target step; and determining whether the step execution conditions of the target step are met based on the matching and verification results.

[0040] In some alternative implementations, consistency checks include: Evidence type matching is used to verify whether the form of evidence collected on-site conforms to the evidence type requirements of the target step. This is achieved through structured metadata verification. When the edge agent or management agent parses the on-site evidence data, it first verifies the standardized evidence type identifier it carries. The system performs an exact string match or a whitelist match between this identifier and the predefined evidence type requirements in the execution conditions of the target step. If the type identifier does not meet the requirements, the verification is directly deemed unsuccessful.

[0041] Step-level state matching is used to verify whether the local operational state represented by on-site evidence meets the step-level local state requirements corresponding to the target step. This is achieved through numerical comparison and feature recognition algorithms. The system calls the parsing module corresponding to the evidence type to process the evidence content. For numerical evidence, the measured values ​​in the data stream are directly read and arithmetically compared with the preset state thresholds in the step conditions. For image / video evidence, computer vision algorithms are used for processing. For example, to verify equipment status, the algorithm performs target detection to locate key components and parses information such as instrument readings and indicator light statuses through feature comparison or optical character recognition (OCR). The extracted state feature values ​​are compared with preset state templates or reference values, and a quantified similarity or matching score is output.

[0042] Step-level local safety constraint matching is used to verify whether there are unisolated personnel, hazards, or safety restriction conflicts within the local work area corresponding to the current target step. This is achieved through multi-source sensing data fusion and rule-based reasoning. The edge agent integrates data from on-site environmental sensors (such as personnel positioning UWB signals, LiDAR point clouds, and video streams), equipment safety signals (such as emergency stop button status and safety lock status), and the safety rule base in the work order to perform real-time logical judgments.

[0043] In some optional implementations, the consistency verification further includes: weighting each matching verification result according to the credibility weights corresponding to different types of on-site evidence data to obtain the corresponding consistency score S, wherein the formula for calculating S is as follows:

[0044] in, The matching result corresponding to the i-th on-site evidence is set to 1 when the match is successful and 0 when the match is unsuccessful, or the similarity score is used to represent the degree of matching. denoted by , where i represents the serial number of the evidence item corresponding to the i-th on-site evidence, and n represents the total number of on-site evidence items participating in the consistency score calculation.

[0045] In some optional implementations, when the consistency score S is greater than or equal to a preset score threshold, the current target step is determined to meet the step execution conditions, and execution of the current target step is allowed. When the consistency score S is less than the preset score threshold, the current target step is determined to not meet the step execution conditions, and corresponding step verification alarm information is generated.

[0046] In some optional implementations, the preset scoring threshold is preset or adaptively adjusted based on the security level, operational risk level, importance of the step, and historical operation and maintenance data statistics of the target step.

[0047] Specifically, for high-risk target steps involving power outage confirmation, disassembly and assembly of high-risk components, and personnel safety isolation, the corresponding preset scoring thresholds are increased; for low-risk auxiliary operation steps, the corresponding preset scoring thresholds are decreased.

[0048] In some optional implementations, during and after the execution of the target step, the edge agent continuously collects corresponding process site evidence data and generates a site evidence package associated with the current work order version number and the target step number.

[0049] The aforementioned solution, by collecting on-site evidence data before the execution of the target step and verifying the consistency between the on-site evidence data and the corresponding execution conditions of the target step, enables real-time confirmation of the local on-site status, safety conditions, and resource readiness status before step execution. This prevents maintenance personnel from mistakenly executing steps when conditions are not met. Furthermore, by introducing a weighted consistency scoring mechanism based on multiple types of on-site evidence, the reliability and robustness of step verification results can be improved, reducing erroneous execution problems caused by misjudgment based on single pieces of evidence. This is beneficial for improving operational safety and execution accuracy in high-risk airport maintenance scenarios.

[0050] S300: Determine whether the current work order version is invalid based on the on-site evidence data fed back during the execution process.

[0051] In the embodiments of this application, determining whether the current work order version is invalid includes: determining the current field status parameters based on field evidence data, and verifying the current field status parameters with the overall status conditions corresponding to the current work order version; wherein, the overall status conditions include at least one of equipment operating status conditions, operating environment conditions, and task execution constraints; when the state mismatch value of the current field status parameters relative to the preset status parameters corresponding to the overall status conditions is greater than a preset failure threshold, the current work order version is determined to be invalid.

[0052] In some optional implementations, the on-site evidence data refers to the process on-site evidence data continuously collected and uploaded by the edge agent during the execution of the target step. The process on-site evidence data includes one or more of the following: process image data, process video data, equipment operating parameter data, location data, timestamp data, and process operation records.

[0053] In some optional implementations, the management agent parses the on-site evidence data fed back during execution to extract the corresponding current on-site state parameters. These current on-site state parameters characterize the current equipment operating status, on-site environmental status, and task execution status.

[0054] In some alternative implementations, parsing on-site evidence data includes: Perform structural identification, status identification, or damage identification on on-site image or video data to determine the structural status of equipment, the status of key components, or the status of newly added damage. Perform time-series analysis on equipment operating parameter data to extract characteristics of equipment temperature, vibration, current, pressure, or speed parameters; The location data and timestamp data are parsed to determine the current work area status and the current task execution sequence status; The process operation records are parsed to determine the current step execution status and resource usage status.

[0055] In some optional implementations, the overall state conditions corresponding to the current work order version are a set of basic task execution conditions preset when the current work order version is generated, which are used to characterize the basic state constraints that the current work order version needs to satisfy to remain valid.

[0056] Among them, the equipment operating status conditions include at least one of the following: equipment structural integrity conditions, equipment fault type conditions, equipment operating parameter safety range conditions, and key component status conditions.

[0057] The working environment conditions include at least one of the following: safety isolation conditions, environmental safety conditions, area occupancy conditions, and environmental parameter conditions corresponding to the target working area.

[0058] Task execution constraints include at least one of the following: operation time window conditions, spare parts model conditions, maintenance resource allocation conditions, and step execution sequence conditions.

[0059] In some optional implementations, the management agent performs item-by-item matching and verification between the current site status parameters and the overall status conditions corresponding to the current work order version in order to determine whether the current site status has deviated from the preset status parameters corresponding to the current work order version.

[0060] In some alternative implementations, item-by-item matching verification includes: Perform structural similarity matching between the currently identified device structure state and the preset device structure state; Compare the current equipment operating parameters with the corresponding safety range to determine the numerical deviation. Match the current spare parts identification results with the pre-installed spare parts models for consistency; Compare and verify the current task execution time with the preset job time window; The current on-site environmental conditions are matched and verified against the preset safety isolation conditions.

[0061] In the embodiments of this application, the state mismatch value is the comprehensive deviation of the current field state parameters from the preset state parameters corresponding to the overall state conditions.

[0062] In some alternative implementations, the management agent calculates the state mismatch value D based on the verification deviation corresponding to each overall state condition, as shown in the following formula:

[0063]

[0064] in, This represents the deviation degree corresponding to the overall state condition of the kth item. The deviation degree is calculated by normalization based on the degree of deviation of the current field state parameter from the corresponding preset state parameter. The value range is 0 to 1, and the higher the degree of deviation, the higher the value. represents the weight coefficient corresponding to the k-th overall state condition, n represents the total number of overall state conditions participating in the calculation of the state mismatch value, and k represents the condition item number corresponding to the overall state condition.

[0065] In some optional implementations, the weighting coefficients for each overall state condition are set based on the safety impact level, task criticality, and fault risk level of the corresponding condition. Specifically, higher weighting coefficients are assigned to the overall state conditions corresponding to newly added equipment damage states, critical operating parameter exceedance states, and spare part model abnormalities.

[0066] In some optional implementations, the preset failure threshold is preset or dynamically adjusted based on the maintenance task risk level, equipment safety level, task complexity, and historical work order failure statistics.

[0067] In a preferred embodiment of this application, the preset failure threshold ranges from 0.4 to 0.8. For high-risk maintenance tasks, the corresponding preset failure threshold is lowered, while for low-risk maintenance tasks, the corresponding preset failure threshold is increased.

[0068] In some optional implementations, when the state mismatch value D is greater than or equal to a preset failure threshold, it is determined that the current field state has deviated from the preset state parameter corresponding to the current work order version, and the current work order version is determined to be faulty.

[0069] In some optional implementations, when the deviation of any critical state condition exceeds the corresponding single failure threshold, the current work order version is directly determined to be faulty.

[0070] Among them, the key overall status conditions include at least: identifying newly damaged equipment areas; key operating parameters continuously exceeding the safe range; on-site spare parts models being inconsistent with preset models; and the current task execution time exceeding the preset operation time window.

[0071] In some optional implementations, when the current work order version is determined to be invalid, the management agent updates the work order status identifier corresponding to the current work order version and locks the current work order version to prevent subsequent steps from continuing to be executed and to terminate the subsequent execution process corresponding to the currently incomplete steps.

[0072] The aforementioned solution dynamically determines whether the current work order version is invalid based on on-site evidence data fed back during execution. This enables real-time perception of changes in equipment operating status, work environment status, and task execution constraints, thereby promptly identifying mismatches between the current work order version and the actual on-site status. Compared to traditional work orders that lack dynamic validity verification during execution, this application can promptly determine work order invalidity and prevent subsequent steps from continuing when new equipment damage occurs, operating parameters become abnormal, or task constraints change. This helps reduce the risk of erroneous maintenance due to changes in on-site status and improves safety assurance capabilities and work order execution reliability in complex airport operation and maintenance scenarios.

[0073] S400: If the current work order version is determined to be invalid, the affected steps will be partially replanned based on the step dependencies and on-site status change information to generate a new version of the smart work order and switch to execution.

[0074] In some optional implementations, the field status change information is the change information of the current field status parameters determined based on the field evidence data fed back during the execution process, relative to the preset status parameters corresponding to the current work order version. The change information is used to characterize at least one of the changes in equipment operating status, changes in field environmental status, and changes in task execution constraints.

[0075] In some optional implementations, the management agent performs an impact propagation analysis on the field status change information based on the step dependencies in the current work order version, in order to determine the target step corresponding to the current field status change and the subsequent steps affected by the target step. The step dependencies include at least one of the following: step execution dependencies, resource consumption dependencies, safety constraint dependencies, and equipment status associations.

[0076] In some optional implementations, the management agent constructs a step dependency graph from the step dependencies in the current work order version and locates the corresponding abnormal step nodes based on the information on changes in the field status; it then performs follow-up propagation analysis along the step dependency graph to determine the set of affected steps.

[0077] In the embodiments of this application, local replanning includes: determining the set of affected steps caused by changes in the field status based on step dependencies; replanning the step execution conditions and step execution order only for the set of affected steps and their subsequent dependent steps; and inheriting the original step content and corresponding field evidence association relationships in the current work order version for unaffected steps.

[0078] In some alternative implementations, replanning the execution conditions of the steps includes updating at least one of the evidence type requirements, step-level local state requirements, step-level local security constraint requirements, and resource configuration requirements corresponding to the affected steps, based on the current site state parameters and real-time task constraint information.

[0079] In some alternative implementations, reordering the execution sequence of steps includes: reordering the set of affected steps based on the dependencies between affected steps, the risk level of step execution, the estimated recovery time, and the remaining operation time window, and prioritizing the execution priority of key steps associated with the current flight operation window, in order to generate a new sequence of steps suitable for the current site conditions.

[0080] In some alternative implementations, for unaffected steps, the corresponding step execution results, step execution conditions, and on-site evidence correlations in the current work order version are retained to reduce redundant verification and planning.

[0081] In embodiments of this application, local replanning further includes: setting rollback anchors for affected steps; the rollback anchors are used to restore the equipment site to a preset safe state before switching to a new version of the smart work order.

[0082] In some alternative implementations, the retraction anchor point includes at least one or more of the following states: equipment power off, hazard source removed, tool retrieved, work area isolated, and personnel evacuated.

[0083] In some optional implementations, after generating a new version of the smart work order, the management agent performs a safety rollback verification on the current site status; if it is confirmed that the site meets the preset safety status corresponding to the rollback anchor point, the edge agent is allowed to switch to the new version of the smart work order to continue execution; otherwise, switching execution is prohibited and corresponding safety alarm information is generated.

[0084] In some optional implementations, the new version of the smart work order includes a new work order version number, a parent version identifier, updated step execution conditions, updated step execution order, and corresponding step dependencies.

[0085] In some optional implementations, the management agent synchronously writes the execution results of completed steps, the content of unaffected steps, and the local replanning results corresponding to affected steps in the current work order version into the new version of the smart work order, so as to form a work order version evolution chain.

[0086] In the embodiments of this application, after the work order is executed, the work order version evolution record, on-site evidence data, local replanning information and final processing result generated during the execution process are correlated to generate a structured maintenance case; based on the structured maintenance case, at least one of the step execution conditions, step dependencies and local replanning rules is modified and updated.

[0087] In some optional implementations, the correction update includes: adjusting the execution conditions of high-frequency abnormal steps based on the frequency of occurrence of the affected step set statistically based on historical structured maintenance cases; reconstructing the step dependencies based on the work order failure cause analysis results; and optimizing and updating the local replanning rules based on the local replanning success rate.

[0088] In some alternative implementations, the correction update can be implemented in one or more of the following ways: Case-based reasoning: Structured maintenance cases are stored in a case knowledge base. When generating new work orders, similar historical cases are retrieved to reuse the corresponding step execution conditions, step dependencies, and local replanning strategies.

[0089] Model parameter update: By utilizing historical structured maintenance cases and corresponding execution results (success / failure), the credibility weight in consistency verification, the state condition weight in work order failure determination, and the feature weights relied upon by the professional intelligent agent for fault diagnosis are updated to improve the accuracy of subsequent state recognition and work order failure determination.

[0090] Rule engine optimization: Based on the causes of high-frequency work order failures and local replanning scenarios, the safety constraint rules, local replanning rules, and corresponding threshold parameters are adjusted and optimized.

[0091] The aforementioned correction and update process enables the system to continuously optimize subsequent work order generation, step verification, and local replanning processes based on historical operation and maintenance data, thereby improving the collaborative processing capabilities and dynamic adaptability in complex airport operation and maintenance scenarios.

[0092] In some optional implementations, the work order version evolution record includes at least the original work order version number, the new work order version number, the version switch time, the reason for the work order failure, the set of affected steps, and the execution result of the rollback anchor point.

[0093] In some optional implementations, structured maintenance cases are used to build a maintenance knowledge base; the maintenance knowledge base is used to iteratively optimize the step execution conditions, step dependencies, local replanning rules, and work order failure thresholds in the subsequent work order generation stage.

[0094] The above solution, by partially replanning only the affected set of steps and their subsequent dependencies after determining that the current work order version is invalid, and generating a new version of the smart work order for continued execution, avoids the repetitive planning problems caused by regenerating work orders throughout the entire process, thereby improving work order adjustment efficiency and on-site response speed. Simultaneously, by setting rollback anchor points and performing safety rollback checks before switching to the new version of the work order, it ensures that the site is restored to a preset safe state before version switching, which helps reduce the security risks caused by dynamic work order adjustments in complex airport operation and maintenance environments. Furthermore, by performing correlation learning on work order version evolution records and structured maintenance cases, it is possible to continuously optimize work order rules, improving the system's subsequent operation and maintenance decision-making capabilities and adaptive collaboration capabilities.

[0095] The present invention also provides a distributed intelligent collaborative system for airport operation and maintenance based on field status, which is used to implement a distributed intelligent collaborative method for airport operation and maintenance based on field status. The system includes a control module, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement a distributed intelligent collaborative method for airport operation and maintenance based on field status.

[0096] This invention provides a storage medium storing a program that, when executed by a processor, implements a distributed intelligent collaborative method for airport operation and maintenance based on on-site state.

[0097] This invention provides a processor for running a program, wherein the program executes a distributed intelligent collaborative method for airport operation and maintenance based on on-site state during runtime.

[0098] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements a distributed intelligent collaborative method for airport operation and maintenance based on on-site state. The device described herein can be a server, PC, PAD, mobile phone, etc.

[0099] This application also provides a computer program product that, when executed on a data processing device, is suitable for executing a distributed intelligent collaborative method for airport operation and maintenance based on on-site status.

[0100] Those skilled in the art will understand that embodiments of this application can provide methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0101] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0102] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0103] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0104] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0105] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0106] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0107] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0108] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. An airport operation and maintenance distributed intelligent collaboration method based on field state driving, characterized in that, include: Based on the acquired equipment status data and task constraint information, a versioned smart work order is generated, which includes a step sequence, step dependencies, and execution conditions for each step. Before executing the target step in the versioned smart work order, on-site evidence data corresponding to the target step is collected, and the on-site evidence data is checked for consistency with the step execution conditions corresponding to the target step. After the consistency check is passed, the target step is executed. Based on the on-site evidence data fed back during the execution process, determine whether the current work order version is invalid; If the current work order version is determined to be invalid, then based on the aforementioned step dependencies and on-site status change information, the affected steps are partially replanned to generate a new version of the smart work order and switch to execution.

2. The airport operation and maintenance distributed intelligent collaboration method based on field state driving according to claim 1, characterized in that, The versioned smart work order also includes a parent version identifier and a work order status identifier; wherein, the parent version identifier is used to indicate the previous work order version corresponding to the current work order version, and the work order status identifier is used to characterize the valid status of the current work order version. 3.The airport operation and maintenance distributed intelligent collaborative method based on field state driving according to claim 1, wherein, The on-site evidence data includes one or more of the following: on-site image data, on-site video data, audio data, equipment operating parameter data, location information, and timestamp information.

4. The field state driving-based airport operation distributed intelligent collaboration method according to claim 1, characterized in that, The consistency check includes: The on-site evidence data is matched and verified against the evidence type requirements, step-level local state requirements, and step-level local security constraint requirements corresponding to the target step. Based on the results of the matching verification, it is determined whether the execution conditions of the target step are met.

5. The field state driving-based airport operation distributed intelligent collaboration method according to claim 4, characterized in that, The consistency check also includes: Based on the credibility weights corresponding to different types of on-site evidence data, the matching verification results are weighted and calculated to obtain the corresponding consistency score; When the consistency score is less than the preset score threshold, the target step is determined to not meet the step execution conditions.

6. The field state driving-based airport operation distributed intelligent collaboration method according to claim 1, characterized in that, The determination of whether the current work order version is invalid includes: Based on the on-site evidence data, the current on-site status parameters are determined, and the current on-site status parameters are verified with the overall status conditions corresponding to the current work order version. The overall state conditions include at least one of equipment operating state conditions, working environment conditions, and task execution constraints. When the state mismatch value of the current field state parameter relative to the preset state parameter corresponding to the overall state condition is greater than the preset failure threshold, the current work order version is determined to be faulty.

7. The field state driving-based airport operation distributed intelligent collaboration method according to claim 1, characterized in that, The local replanning includes: Based on the step dependencies, determine the set of affected steps resulting from the information on changes in the field status; Only for the affected set of steps and its subsequent dependent steps, the execution conditions and execution order of the steps are replanned; For steps that are not affected, the original steps and corresponding on-site evidence relationships in the current work order version will be inherited. 8.The airport operation and maintenance distributed intelligent collaboration method based on field state driving according to claim 1, wherein, The local replanning also includes: setting rollback anchors for affected steps; the rollback anchors are used to restore the equipment site to a preset safe state before switching to the new version of the smart work order.

9. The airport operation and maintenance distributed intelligent collaborative method based on field state driving according to claim 1, characterized in that, Also includes: After the work order is completed, the work order version evolution record, on-site evidence data, local replanning information and final processing results generated during the execution process will be correlated and processed to generate a structured maintenance case. Based on the structured maintenance case, at least one of the following is modified and updated: step execution conditions, step dependencies, and local replanning rules.

10. A distributed intelligent collaborative system for airport operation and maintenance based on on-site state-driven operation, characterized in that, The system includes a control module, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement the distributed intelligent collaborative airport operation and maintenance method based on field status as described in any one of claims 1-9.

Images