An intelligent inspection management method and system based on cloud-edge collaboration

Abstract

This invention relates to the field of inspection management technology and discloses an intelligent inspection management method and system based on cloud-edge collaboration. The method includes: acquiring inspection task work orders to be executed; acquiring the path length and number of inspection points for each inspection segment in the inspection task work order; analyzing the path length and number of inspection points to obtain the time quota for each inspection segment; obtaining differentiated time quotas by analyzing the path length and number of inspection points for each inspection segment; generating a task delay risk coefficient by combining real-time basic data and inspection point status; collaboratively calculating additional time requirements when an inspection point is abnormal; and evaluating the buffer capacity of the remaining work period to obtain an inspection management adaptation value. This solution can intelligently and flexibly adjust the inspection time during the inspection process to avoid insufficient inspection and effectively prevent excessive extension from impacting the overall inspection task. It achieves dynamic optimization of inspection path time and ensures the management effect of cloud-edge collaborative intelligent inspection.

Description

Technical Field

[0001] This invention relates to the field of inspection management technology, specifically to an intelligent inspection management method and system based on cloud-edge collaboration. Background Technology

[0002] Currently, in cloud-edge collaborative intelligent inspection, the cloud is mainly responsible for the overall planning of the inspection path and divides the inspection path into multiple inspection segments according to the time sequence. Each inspection segment has a preset start and end time, which is then sent to the corresponding edge nodes. The edge nodes control the inspection equipment, such as inspection robots, according to the received segments to carry out inspections according to the path and send the collected inspection data back to the cloud.

[0003] However, the above-mentioned inspection management method still has the following defects: Since each inspection segment in the path planning has a fixed inspection duration, when the inspection data is found to be abnormal during the inspection process, it is impossible to extend the inspection time of that segment automatically, resulting in insufficient inspection of abnormal inspection segments. The inspection path is only allocated according to a fixed time, which cannot achieve optimal inspection path time optimization and reduces the management effect of intelligent inspection. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides an intelligent inspection management method and system based on cloud-edge collaboration, which solves the aforementioned problems.

[0005] The above-mentioned technical objective of the present invention is achieved through the following technical solution:

[0006] A cloud-edge collaborative intelligent inspection management method includes:

[0007] Step S1: Obtain the inspection task work order to be executed, obtain the path length and number of inspection points of each inspection segment in the inspection task work order, analyze the path length and number of inspection points, and obtain the time quota of each inspection segment.

[0008] Step S2: The task execution entity performs the inspection task, and the basic data of the task execution entity and the status of the inspection points are obtained in real time. The basic data and the status of the inspection points are analyzed to obtain the task delay risk coefficient, which represents the complexity of the current inspection segment task and the overall impact of unforeseen circumstances on working hours.

[0009] Basic data includes: the location of the task executor, execution speed, and elapsed time;

[0010] Step S3: When any inspection point is in an abnormal state, it is determined that the time quota of the inspection segment needs to be adjusted. The path length, number of abnormal points, time quota and task delay risk coefficient of the inspection segment are calculated together to obtain the additional time requirement of the inspection segment.

[0011] Step S4: Based on the additional working hours required, analyze its impact on the overall inspection task to obtain the inspection management fit value for determining whether the additional working hours required are suitable.

[0012] Furthermore, the path length and the number of inspection points were analyzed to obtain the time quota for each inspection segment, including:

[0013] Obtain the historical inspection duration of the inspection segment, perform workload analysis based on the historical inspection duration and path length, and obtain the distance man-hour base representing the basic workload of the inspection segment.

[0014] Furthermore, analysis of the path length and the number of inspection points yields the time quota for each inspection segment, which also includes:

[0015] Path analysis is performed based on the number of inspection points to obtain an operational complexity index that indicates the increase in operation time caused by the density of inspection points.

[0016] By integrating the distance work hour base with the operation complexity index, the work hour quota for each inspection segment is obtained.

[0017] Furthermore, the status of the inspection points includes:

[0018] Inspection points are the objects that need to be inspected in the inspection task work order. There are two statuses for inspection points: abnormal and normal.

[0019] Furthermore, analysis of basic data and inspection point status yields a task delay risk coefficient representing the complexity of the current inspection segment and the overall impact of unforeseen circumstances on working hours, including:

[0020] When the status of an inspection point is abnormal, mark the inspection point as an abnormal point.

[0021] Obtain the location of the anomaly point, and based on the location of the anomaly point and the location of the task execution subject, analyze the path distance between each anomaly point in the current inspection segment and the trigger time of the anomaly point to obtain the anomaly disturbance factor that represents the impact of the anomaly distribution on the inspection efficiency.

[0022] Based on the time elapsed in the anomaly points and the basic data, the spatiotemporal correlation of each anomaly point is calculated, and all spatiotemporal correlations are analyzed to obtain the cumulative anomaly value representing the additional time required for anomaly handling.

[0023] Furthermore, analysis of basic data and inspection point status yields a task delay risk coefficient representing the complexity of the current inspection segment and the overall impact of unforeseen circumstances on working hours. This coefficient also includes:

[0024] Based on the distance working hours base, the location and execution speed of the task execution subject in the basic data, analyze the changes in task efficiency of the current inspection segment, and generate a processing obstruction coefficient that represents the degree of decrease in work efficiency caused by abnormal handling;

[0025] By integrating the abnormal disturbance factor, the abnormal cumulative value, and the processing stagnation coefficient, a task delay risk coefficient representing the complexity of the current inspection segment task and the overall impact of unforeseen circumstances on working hours is obtained.

[0026] Furthermore, when any inspection point is in an abnormal state, it is determined that the work hour quota for that inspection segment needs to be adjusted. The path length, number of abnormal points, work hour quota, and task delay risk coefficient for that inspection segment are calculated collaboratively to obtain the additional work hour requirements for that inspection segment, including:

[0027] The task delay risk coefficient, time quota, and path length of the inspection segment are calculated to determine the additional operation time and generate a defect delay base quantity representing the increase in time base caused by the defect.

[0028] Based on the number of outliers, analyze the resource conflicts and concurrent pressures of multiple outliers, and generate a resource saturation factor that represents the degree of increase in working hours caused by resource competition.

[0029] Furthermore, when any inspection point is in an abnormal state, it is determined that the work hour quota for that inspection segment needs to be adjusted. The path length, number of abnormal points, work hour quota, and task delay risk coefficient for that inspection segment are calculated collaboratively to obtain the additional work hour requirement for that inspection segment, which also includes:

[0030] Obtain the historical execution speed of the task execution entity in the inspection segment, compare the current execution speed with the historical execution speed, analyze the number of remaining inspection points and the total number of inspection points in the inspection segment, and generate an adjustment coefficient representing the current execution capacity to correct the working hours;

[0031] By integrating the defect delay base, resource saturation factor, and adjustment coefficient, the additional working hours required for this inspection segment are obtained.

[0032] Furthermore, based on the additional working hours required, the impact on the overall inspection task is analyzed to obtain the inspection management suitability value for determining whether the additional working hours requirement is appropriate, including:

[0033] Based on the distance working hours base and operation complexity index of each inspection segment in the remaining inspection path, analyze the time fluctuation space of each inspection segment, and generate the remaining time buffer coefficient representing the overall digestion and bearing capacity of the remaining tasks for additional working hours.

[0034] The additional working hours requirement and the buffer coefficient of the remaining construction period are calculated together to obtain the inspection management fit value to determine whether the additional working hours requirement is suitable.

[0035] Furthermore, a cloud-edge collaborative intelligent inspection management system, applied to the aforementioned inspection management method, includes:

[0036] The time analysis unit is used to obtain the inspection task work order to be executed, obtain the path length and number of inspection points of each inspection segment in the inspection task work order, analyze the path length and number of inspection points, and obtain the time quota of each inspection segment.

[0037] The task analysis unit is used to perform inspection tasks through the task execution entity, obtain the basic data of the task execution entity and the status of the inspection points in real time, and analyze the basic data and the status of the inspection points to obtain the task delay risk coefficient, which represents the complexity of the current inspection segment task and the overall impact of unforeseen circumstances on working hours.

[0038] Basic data includes: the location of the task executor, execution speed, and elapsed time;

[0039] The demand calculation unit is used to determine that the time quota of the inspection segment needs to be adjusted when any inspection point is in an abnormal state. It performs collaborative calculations on the path length, number of abnormal points, time quota and task delay risk coefficient of the inspection segment to obtain the additional time demand of the inspection segment.

[0040] The time adaptation unit is used to analyze the impact of additional time requirements on the overall inspection task and obtain an inspection management adaptation value to determine whether the additional time requirements are suitable.

[0041] In summary, the present invention has the following main beneficial effects:

[0042] Step S1 analyzes the path length and number of inspection points to generate a distance time base and a work complexity index, which are then integrated to obtain a time quota. A differentiated baseline time is established for each inspection segment. Step S2 analyzes the location, execution speed, and elapsed time of the task executor to obtain a task delay risk coefficient, thus comprehensively reflecting the combined impact of anomaly distribution, spatiotemporal correlation, and efficiency decline on time. Step S3, when an anomaly occurs at any inspection point, collaboratively calculates the defect delay base, resource saturation factor, and adjustment coefficient to generate additional time requirements, accurately reflecting multiple... The additional time required for resource contention at anomalies and changes in current execution capabilities is considered. In the final step S4, the remaining project duration buffer coefficient is calculated based on the distance time base of the remaining segments and the operation complexity index. This coefficient is then analyzed in conjunction with the additional time requirements to obtain the inspection management adaptation value. If the adaptation is successful, the inspection duration is automatically extended; otherwise, it is handled manually. This solution breaks the limitation of fixed inspection duration, realizes intelligent and flexible adjustment of inspection time, avoids the problem of insufficient inspection, and avoids the impact of excessive extension on the overall inspection task, thereby improving the management efficiency of cloud-edge collaborative intelligent inspection. Attached Figure Description

[0043] Figure 1 This is a flowchart illustrating the steps of an intelligent inspection and management method based on cloud-edge collaboration according to the present invention.

[0044] Figure 2 This is a schematic diagram of an intelligent inspection management system based on cloud-edge collaboration according to the present invention. Detailed Implementation

[0045] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] refer to Figure 1 and Figure 2 A cloud-edge collaborative intelligent inspection management method includes:

[0047] Step S1: Obtain the inspection task work order to be executed, obtain the path length and number of inspection points of each inspection segment in the inspection task work order, analyze the path length and number of inspection points, and obtain the time quota of each inspection segment.

[0048] Step S2: The task execution entity performs the inspection task, and the basic data of the task execution entity and the status of the inspection points are obtained in real time. The basic data and the status of the inspection points are analyzed to obtain the task delay risk coefficient, which represents the complexity of the current inspection segment task and the overall impact of unforeseen circumstances on working hours.

[0049] The main body responsible for carrying out the task is the inspection equipment;

[0050] Basic data includes: the location of the task executor, execution speed, and elapsed time;

[0051] Step S3: When any inspection point is in an abnormal state, it is determined that the time quota of the inspection segment needs to be adjusted. The path length, number of abnormal points, time quota and task delay risk coefficient of the inspection segment are calculated together to obtain the additional time requirement of the inspection segment.

[0052] Step S4: Based on the additional working hours required, analyze its impact on the overall inspection task to obtain the inspection management fit value for determining whether the additional working hours required are suitable.

[0053] In one embodiment, the path length and the number of inspection points are analyzed to obtain the time quota for each inspection segment, including:

[0054] Obtain the historical inspection duration of the inspection segment, perform workload analysis based on the historical inspection duration and path length, and obtain the distance man-hour base representing the basic workload of the inspection segment. Specifically, this includes: obtaining the historical inspection duration of the inspection segment for the most recent 5 days from the cloud, and calculating the average of all historical inspection durations in minutes to obtain the historical average inspection duration of the inspection segment.

[0055] Divide the historical average inspection time by the path length of the current inspection segment to obtain the average path time.

[0056] Multiply the average path time by the path length of the current segment to obtain the distance-time baseline representing the basic workload of the inspection segment.

[0057] In one embodiment, the analysis of path length and number of inspection points to obtain the time quota for each inspection segment also includes:

[0058] Based on the number of inspection points, path analysis is performed to obtain the operation complexity index, which represents the increase in operation time caused by the density of inspection points. Specifically, it includes: traversing all inspection points in the current inspection segment in turn, calculating the path interval length between adjacent inspection points, adding all the interval lengths together and dividing by the difference between the number of inspection points and 1 to obtain the average interval length of the inspection points.

[0059] Divide the path length of the current inspection segment by the average interval length to obtain the density value of the inspection points. Use the total number of inspection points as the base and the density value as the exponent to perform a power operation. Then normalize the calculation result to the 0-1 interval to obtain the operation complexity index, which represents the increase in operation time caused by the density of inspection points.

[0060] The distance working time base and the operation complexity index are integrated to obtain the working time quota for each inspection segment. Specifically, this includes: calculating the average of the distance working time base and the operation complexity index to obtain the working time integration benchmark value.

[0061] Divide the total number of inspection points by the path length of the current inspection segment to obtain the inspection point density per unit length. Then multiply the average interval length of the inspection points by the inspection point density and normalize the calculation result to the 0-1 interval to obtain the scale correction factor. Multiply the time fusion benchmark value by the scale correction factor to obtain the initial standard time reference value. Round the initial standard time reference value to obtain the time quota for each inspection segment.

[0062] By analyzing the historical inspection duration of the inspection segment over the past 5 days and the density of inspection points, a distance-based working hour baseline is obtained, which accurately reflects the basic workload. Simultaneously, by calculating the interval length between adjacent inspection points, the density value, and exponentiation with the total number of inspection points as the base, an operational complexity index is obtained. This compensates for the increased operation time caused by the dense distribution of inspection points, ultimately yielding the working hour quota for each inspection segment. This solution overcomes the limitations of traditional fixed inspection durations, enabling each inspection point to autonomously extend the inspection time of abnormal inspection segments based on real-time inspection data anomalies, avoiding insufficient inspections and improving the management effectiveness of cloud-edge collaborative intelligent inspections.

[0063] In one embodiment, the status of the inspection point includes:

[0064] Inspection points are the objects that need to be inspected in the inspection task work order. The status of inspection points is divided into abnormal or normal.

[0065] When the task execution entity inspects the inspection segment, it will collect the data of the inspection segment in real time and upload it to the cloud. If any parameter in the data exceeds its preset threshold, the status of the inspection point is judged to be abnormal; otherwise, it is normal. For example, if the temperature in the data exceeds its preset threshold, the status of the inspection point is abnormal.

[0066] In one embodiment, the basic data and the status of inspection points are analyzed to obtain a task delay risk coefficient representing the complexity of the current inspection segment and the overall impact of unforeseen circumstances on working hours, including:

[0067] When the status of an inspection point is abnormal, mark the inspection point as an abnormal point.

[0068] The location of anomalies is obtained. Based on this location and the location of the task execution entity, the path distance between anomalies within the current inspection segment and the trigger time of the anomalies are analyzed to obtain the anomaly disturbance factor representing the impact of anomaly distribution on inspection efficiency. The specific calculation formula is as follows: ;

[0069] In the formula, FR represents the abnormal disturbance factor affecting the inspection efficiency of abnormal distribution. , This indicates the total number of anomalies identified within the current inspection segment. Indicates the sequence number of the outlier. This indicates the anomaly trigger time of the last anomaly point after being arranged in the order of the inspection path. After arranging the inspection paths in sequence, the anomaly trigger time of the first anomaly point is the time when the status of that inspection point changes to an anomaly. Indicates the first The path distance between each anomaly point and the starting point of the current inspection segment. This indicates the time quota for the inspection segment, and L represents the path length of the inspection segment.

[0070] Based on the time elapsed in the anomaly points and basic data, the spatiotemporal correlation of each anomaly point is calculated, and all spatiotemporal correlations are analyzed to obtain the cumulative anomaly value representing the additional time required for anomaly handling. Specifically, this includes: dividing the path distance from the corresponding anomaly point to the task execution subject by the total path length of the inspection segment to obtain the distance weight; dividing the elapsed time by the work hour quota of the current inspection segment to obtain the time progress ratio; and multiplying the distance weight by the time progress ratio to obtain the spatiotemporal correlation of a single anomaly point.

[0071] Sum the spatiotemporal correlation values ​​of all anomalies to obtain the cumulative anomaly value representing the additional time required for anomaly handling.

[0072] In one embodiment, the analysis of basic data and inspection point status yields a task delay risk coefficient representing the complexity of the current inspection segment and the overall impact of unforeseen circumstances on working hours. This also includes:

[0073] Based on the distance working time base, the location and execution speed of the task execution subject in the basic data, analyze the changes in task efficiency of the current inspection segment, and generate a processing obstruction coefficient that represents the degree of decrease in work efficiency caused by abnormal handling. Specifically, this includes: obtaining the remaining path length from the current location of the task execution subject to the end point of the inspection segment, multiplying the distance working time base by the execution speed, and normalizing the calculation result to the 0-1 interval to obtain the working time speed correlation quantity. At the same time, divide the working time speed correlation quantity by the remaining path length and normalize the calculation result to the 0-1 interval to obtain the first correlation factor.

[0074] Divide the remaining path length by the time-speed correlation factor and normalize the result to the 0-1 interval to obtain the path-time coupling ratio. Perform a power operation with the first correlation factor as the base and the path-time coupling ratio as the exponent, and normalize the result to the 0-1 interval. This is the processing hindrance coefficient, which represents the degree of decrease in work efficiency caused by abnormal processing.

[0075] By integrating the abnormal disturbance factor, the abnormal cumulative value, and the processing delay coefficient, a task delay risk coefficient representing the complexity of the current inspection segment task and the comprehensive impact of unforeseen circumstances on working hours is obtained. Specifically, this includes: multiplying the abnormal cumulative value by the processing delay coefficient to obtain the spatiotemporal delay cumulative amount; performing a power operation with the spatiotemporal delay cumulative amount as the base and the abnormal disturbance factor as the exponent to obtain the initial value of risk coupling; and then calculating the mean of the abnormal disturbance factor, the abnormal cumulative value, and the processing delay coefficient to obtain the risk equilibrium reference amount.

[0076] Then, the mean of the initial value of risk coupling and the reference value of risk equilibrium are calculated, and the calculation results are normalized to the 0-1 interval, which is the task delay risk coefficient representing the complexity of the current inspection segment task and the comprehensive impact of emergencies on working hours.

[0077] By analyzing basic data and the status of inspection points, the system calculates the anomaly disturbance factor, the anomaly cumulative value, and the processing bottleneck coefficient, and integrates them to obtain the task delay risk coefficient. This accurately reflects the additional time requirements in the current inspection segment caused by factors such as the distribution of anomalies, the trigger time of anomalies, the elapsed time, and the location and execution speed of the task execution entity. Among them, the anomaly disturbance factor, by considering the trigger time interval and path distance of the anomaly sequence, reflects the impact of anomaly distribution on inspection efficiency. The anomaly cumulative value represents the additional processing time required for each anomaly point. The processing bottleneck coefficient, based on the distance working time base, execution speed, and remaining path length, assesses the degree of decrease in work efficiency caused by anomaly processing. The final task delay risk coefficient enables each inspection point to autonomously extend the inspection time based on the real-time anomaly status, effectively avoiding the problem of insufficient inspection of anomaly inspection segments due to fixed inspection time, and improving the adaptability and management effect of cloud-edge collaborative intelligent inspection.

[0078] In one embodiment, when any inspection point is in an abnormal state, it is determined that the time quota for that inspection segment needs to be adjusted. The path length, number of abnormal points, time quota, and task delay risk coefficient for that inspection segment are calculated collaboratively to obtain the additional time requirement for that inspection segment, including:

[0079] The task delay risk coefficient, time quota, and path length of the inspection segment are calculated to determine the additional operation time and generate a defect delay base quantity representing the increase in time base caused by the defect. The specific calculation formula is as follows: ;

[0080] In the formula, The defect delay base quantity is used to represent the increase in working hours caused by defects. For work hour quotas, Represents the natural constant. For the risk factor of mission delay, It is the natural logarithm. This indicates the average interval length of the inspection points within the inspection segment.

[0081] Based on the number of anomalies, analyze the resource conflicts and concurrent pressures of multiple anomalies, and generate a resource saturation factor that represents the degree of increase in working hours caused by resource competition. Specifically, for the total number of anomalies in the current inspection segment, when the number of anomalies is <2, the resource saturation factor is directly set to 0, indicating that there is no resource competition; when the number of anomalies is ≥2, calculate the pairwise logarithm of the anomalies, that is, multiply the number of anomalies by the difference between the number of anomalies and 1, and then divide by two to obtain the number of competition conflicts.

[0082] Multiply the time elapsed by the execution speed to obtain the equivalent path distance, and divide the equivalent path distance by the average interval length to obtain the number of completed nodes factor. The number of completed nodes factor mainly reflects the proportion of the currently completed inspection nodes to the total node density.

[0083] Using the natural constant e as the base and the product of the number of competing conflicts and the number of completed nodes as the exponent, the exponential function value is calculated. Then, the exponential function value is divided by the number of outliers to obtain the original concurrent pressure value. This calculation amplifies the superlinear growth effect of concurrent conflicts through the exponential function.

[0084] The original concurrent pressure value is normalized to the 0-1 range to obtain the resource saturation factor. The resource saturation factor increases rapidly with the increase of the number of outliers and the progress of the completed schedule, but tends to saturate, which truly reflects the degree of increase in working hours caused by resource competition.

[0085] In one embodiment, when any inspection point is in an abnormal state, it is determined that the time quota for that inspection segment needs to be adjusted. The path length, number of abnormal points, time quota, and task delay risk coefficient for that inspection segment are calculated collaboratively to obtain the additional time requirement for that inspection segment. This also includes:

[0086] The historical execution speed of the task execution entity in the inspection segment is obtained. The current execution speed is compared with the historical execution speed, and the number of remaining inspection points and the total number of inspection points in the inspection segment are analyzed. An adjustment coefficient representing the current execution capacity to correct the working hours is generated. Specifically, this includes: obtaining the historical execution speed of the task execution entity from the inspection records of the last 5 complete executions of the inspection segment from the cloud, calculating the average of the 5 historical execution speeds in meters per minute, and using it as the historical average execution speed; dividing the current execution speed of the task execution entity by the historical average execution speed to obtain the speed ratio, which mainly reflects the speed of the current speed relative to the historical benchmark.

[0087] Subtract the completed number from the total number of inspection points in the inspection segment to get the remaining number of inspection points. Then divide the remaining number of inspection points by the total number of inspection points and normalize the result to the 0-1 range to get the percentage of remaining workload.

[0088] Subtracting the speed ratio from 1 and multiplying it by the remaining workload percentage yields the fusion variable. Using the natural constant e as the base and the fusion variable as the exponent, the exponential growth factor is calculated. The sum of 1 and the fusion variable is multiplied by the exponential growth factor, and the calculation result is normalized to the 0-1 interval to obtain the adjustment coefficient representing the current execution capacity's adjustment of working hours.

[0089] The additional working hours required for this inspection segment are obtained by integrating the defect delay base, resource saturation factor, and adjustment coefficient. Specifically, the power value is calculated using the adjustment coefficient as the base and the square root of the resource saturation factor as the exponent. This calculation can make the response of the adjustment coefficient to concurrent pressure grow exponentially, and the closer the resource saturation factor is to 1, the more severe the amplification effect.

[0090] Multiply the defect delay base value by the power value to obtain the initial coupling value. At the same time, multiply the resource saturation factor by the adjustment coefficient and then take the square root to obtain the modulation factor. Then multiply the initial coupling value by the modulation factor to obtain the secondary modulation value.

[0091] Furthermore, to prevent the additional working hours requirement from growing indefinitely under abnormal and extreme conditions, a negative exponential decay method is adopted for correction. That is, the decay factor can be calculated by taking the natural constant e as the base, the absolute value of the sum of the negative resource saturation factor and the adjustment coefficient, and multiplying the secondary modulation amount by the decay factor to obtain the additional working hours requirement of this inspection segment.

[0092] In one embodiment, based on the additional working hours required, the impact on the overall inspection task is analyzed to obtain an inspection management suitability value for determining whether the additional working hours are suitable, including:

[0093] Based on the distance time base and operation complexity index of each inspection segment in the remaining inspection path, the schedule fluctuation space of each inspection segment is analyzed, and a remaining schedule buffer coefficient representing the overall digestion and bearing capacity of the remaining tasks for additional time is generated. The specific calculation formula is as follows: ;

[0094] In the formula, The remaining project duration buffer coefficient represents the overall capacity to absorb and handle additional work hours from the remaining tasks. Its value ranges from 0 to 1. Let M be the hyperbolic tangent function, and M represent the total number of remaining inspection segments after the current inspection segment. The index representing the remaining inspection segments. Indicates the first The distance and working hours base for each remaining inspection segment Indicates the first The operational complexity index of the remaining inspection segments. Indicates the distance from the end of the current inspection segment to the... The cumulative path distance of the starting points of each remaining inspection segment This represents the total path length of all remaining inspection segments;

[0095] The additional working hours requirement and the buffer coefficient of the remaining construction period are calculated in a coordinated manner to obtain the inspection management adaptation value for judging whether the additional working hours requirement is suitable. Specifically, this includes: calculating the sum of the working hours quota of all remaining inspection segments after the current inspection segment, dividing the additional working hours requirement by the sum of the working hours quota to obtain the additional working hours pressure ratio. The additional working hours pressure ratio mainly reflects the proportion of the current additional time to the remaining planned working hours.

[0096] If the additional working hours pressure ratio is less than or equal to the remaining construction period buffer coefficient, it is considered compatible; otherwise, it is considered incompatible. If compatible, the inspection time of the inspection segment is extended according to the additional working hours requirement; if incompatible, the abnormal points are inspected and investigated manually.

[0097] When an inspection point is in an abnormal state, the system calculates the defect latency base, resource saturation factor, and adjustment coefficient by collaboratively calculating the path length, number of abnormal points, time quota, and task delay risk coefficient. This data is then integrated to generate additional time requirements, accurately reflecting the extra time investment caused by defect handling, resource competition among multiple abnormal points, and changes in current execution capabilities. Combined with the remaining project duration buffer coefficient, the system calculates the inspection management adaptation value to determine whether the additional time requirements can be borne by the remaining segments. If they are compatible, the inspection time is automatically extended; otherwise, it is transferred to manual processing. This solution breaks the limitation of fixed inspection time, enabling intelligent and elastic adjustment of inspection time in abnormal scenarios. At the same time, it avoids excessive extension leading to overall task loss of control, thus improving the management efficiency of cloud-edge collaborative intelligent inspection.

[0098] In one embodiment, a cloud-edge collaborative intelligent inspection management system is applied to the above-described inspection management method, comprising:

[0099] The time analysis unit is used to obtain the inspection task work order to be executed, obtain the path length and number of inspection points of each inspection segment in the inspection task work order, analyze the path length and number of inspection points, and obtain the time quota of each inspection segment.

[0100] The task analysis unit is used to perform inspection tasks through the task execution entity, obtain the basic data of the task execution entity and the status of the inspection points in real time, and analyze the basic data and the status of the inspection points to obtain the task delay risk coefficient, which represents the complexity of the current inspection segment task and the overall impact of unforeseen circumstances on working hours.

[0101] Basic data includes: the location of the task executor, execution speed, and elapsed time;

[0102] The demand calculation unit is used to determine that the time quota of the inspection segment needs to be adjusted when any inspection point is in an abnormal state. It performs collaborative calculations on the path length, number of abnormal points, time quota and task delay risk coefficient of the inspection segment to obtain the additional time demand of the inspection segment.

[0103] The time adaptation unit is used to analyze the impact of additional time requirements on the overall inspection task and obtain an inspection management adaptation value to determine whether the additional time requirements are suitable.

[0104] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A cloud-edge collaborative intelligent inspection management method, characterized in that, include: Step S1: Obtain the inspection task work order to be executed, obtain the path length and number of inspection points of each inspection segment in the inspection task work order, analyze the path length and number of inspection points, and obtain the time quota of each inspection segment. Step S2: The task execution entity performs the inspection task, and the basic data of the task execution entity and the status of the inspection points are obtained in real time. The basic data and the status of the inspection points are analyzed to obtain the task delay risk coefficient, which represents the complexity of the current inspection segment task and the overall impact of unforeseen circumstances on working hours. Basic data includes: the location of the task executor, execution speed, and elapsed time; Step S3: When any inspection point is in an abnormal state, it is determined that the time quota of the inspection segment needs to be adjusted. The path length, number of abnormal points, time quota and task delay risk coefficient of the inspection segment are calculated together to obtain the additional time requirement of the inspection segment. Step S4: Based on the additional working hours required, analyze its impact on the overall inspection task to obtain the inspection management fit value for determining whether the additional working hours required are suitable.

2. The intelligent inspection management method based on cloud-edge collaboration according to claim 1, characterized in that, Analyzing the path length and the number of inspection points yields the time quotas for each inspection segment, including: Obtain the historical inspection duration of the inspection segment, perform workload analysis based on the historical inspection duration and path length, and obtain the distance man-hour base representing the basic workload of the inspection segment.

3. The intelligent inspection management method based on cloud-edge collaboration according to claim 2, characterized in that, The analysis of path length and number of inspection points yields the time quota for each inspection segment, which also includes: Path analysis is performed based on the number of inspection points to obtain an operational complexity index that indicates the increase in operation time caused by the density of inspection points. By integrating the distance work hour base with the operation complexity index, the work hour quota for each inspection segment is obtained.

4. The intelligent inspection management method based on cloud-edge collaboration according to claim 1, characterized in that, The status of the inspection points includes: Inspection points are the objects that need to be inspected in the inspection task work order. There are two statuses for inspection points: abnormal and normal.

5. The intelligent inspection management method based on cloud-edge collaboration according to claim 4, characterized in that, Analyzing the basic data and the status of inspection points yields a task delay risk coefficient that represents the complexity of the current inspection segment and the overall impact of unforeseen circumstances on working hours. This coefficient includes: When the status of an inspection point is abnormal, mark the inspection point as an abnormal point. Obtain the location of the anomaly point, and based on the location of the anomaly point and the location of the task execution subject, analyze the path distance between each anomaly point in the current inspection segment and the trigger time of the anomaly point to obtain the anomaly disturbance factor that represents the impact of the anomaly distribution on the inspection efficiency. Based on the time elapsed in the anomaly points and the basic data, the spatiotemporal correlation of each anomaly point is calculated, and all spatiotemporal correlations are analyzed to obtain the cumulative anomaly value representing the additional time required for anomaly handling.

6. The intelligent inspection management method based on cloud-edge collaboration according to claim 5, characterized in that, Analyzing the basic data and the status of inspection points yields a task delay risk coefficient that represents the complexity of the current inspection segment and the overall impact of unforeseen circumstances on working hours. This also includes: Based on the distance working hours base, the location and execution speed of the task execution subject in the basic data, analyze the changes in task efficiency of the current inspection segment, and generate a processing obstruction coefficient that represents the degree of decrease in work efficiency caused by abnormal handling; By integrating the abnormal disturbance factor, the abnormal cumulative value, and the processing stagnation coefficient, a task delay risk coefficient representing the complexity of the current inspection segment task and the overall impact of unforeseen circumstances on working hours is obtained.

7. The intelligent inspection management method based on cloud-edge collaboration according to claim 6, characterized in that, When any inspection point is in an abnormal state, it is determined that the time quota for that inspection segment needs to be adjusted. The path length, number of abnormal points, time quota, and task delay risk coefficient of that inspection segment are calculated together to obtain the additional time requirement for that inspection segment, including: The task delay risk coefficient, time quota, and path length of the inspection segment are calculated to determine the additional operation time and generate a defect delay base quantity representing the increase in time base caused by the defect. Based on the number of outliers, analyze the resource conflicts and concurrent pressures of multiple outliers, and generate a resource saturation factor that represents the degree of increase in working hours caused by resource competition.

8. The intelligent inspection management method based on cloud-edge collaboration according to claim 7, characterized in that, When any inspection point is in an abnormal state, it is determined that the time quota for that inspection segment needs to be adjusted. The path length, number of abnormal points, time quota, and task delay risk coefficient of that inspection segment are calculated collaboratively to obtain the additional time requirement for that inspection segment, which also includes: Obtain the historical execution speed of the task execution entity in the inspection segment, compare the current execution speed with the historical execution speed, analyze the number of remaining inspection points and the total number of inspection points in the inspection segment, and generate an adjustment coefficient representing the current execution capacity to correct the working hours; By integrating the defect delay base, resource saturation factor, and adjustment coefficient, the additional working hours required for this inspection segment are obtained.

9. The intelligent inspection management method based on cloud-edge collaboration according to claim 8, characterized in that, Based on the additional working hours required, analyze its impact on the overall inspection task to obtain an inspection management suitability value for determining whether the additional working hours are appropriate, including: Based on the distance working hours base and operation complexity index of each inspection segment in the remaining inspection path, analyze the time fluctuation space of each inspection segment, and generate the remaining time buffer coefficient representing the overall digestion and bearing capacity of the remaining tasks for additional working hours. The additional working hours requirement and the buffer coefficient of the remaining construction period are calculated together to obtain the inspection management fit value to determine whether the additional working hours requirement is suitable.

10. A cloud-edge collaborative intelligent inspection management system, applied in the inspection management method as described in any one of claims 1-9, characterized in that, include: The time analysis unit is used to obtain the inspection task work order to be executed, obtain the path length and number of inspection points of each inspection segment in the inspection task work order, analyze the path length and number of inspection points, and obtain the time quota of each inspection segment. The task analysis unit is used to perform inspection tasks through the task execution entity, obtain the basic data of the task execution entity and the status of the inspection points in real time, and analyze the basic data and the status of the inspection points to obtain the task delay risk coefficient, which represents the complexity of the current inspection segment task and the overall impact of unforeseen circumstances on working hours. Basic data includes: the location of the task executor, execution speed, and elapsed time; The demand calculation unit is used to determine that the time quota of the inspection segment needs to be adjusted when any inspection point is in an abnormal state. It performs collaborative calculations on the path length, number of abnormal points, time quota and task delay risk coefficient of the inspection segment to obtain the additional time demand of the inspection segment. The time adaptation unit is used to analyze the impact of additional time requirements on the overall inspection task and obtain an inspection management adaptation value to determine whether the additional time requirements are suitable.

Images