Performance management-oriented poise administrator inspection anomaly detection method and system

Abstract

The invention relates to a performance management-oriented method and a performance management-oriented system for detecting polling abnormity of a parking manager, and the method comprises the steps: obtaining an individual real-time parking space data set managed by each parking manager from collected parking space real-time state data according to a management attribution rule of the parking manager; and obtaining the total number of real-time abnormal events of free parking and the total number of real-time abnormal events of unlicensed vehicles from the individual real-time parking space data set. And according to the total number of the free parking real-time abnormal events and the total number of the unlicensed vehicle real-time abnormal events, generating an inspection efficiency abnormal result and an inspection operation abnormal result of the parking manager. And performing abnormal responsibility affiliation on the current abnormal road section according to the road section real-time supervision rate of the current abnormal road section and the individual real-time supervision rate corresponding to the parking manager governing the current abnormal road section, and generating a performance evaluation result based on the obtained abnormal responsibility affiliation result, the inspection efficiency abnormal result and the inspection operation abnormal result. Therefore, the performance evaluation accuracy of the berth manager is improved, and the performance management efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of performance management, and in particular to a parking attendant inspection abnormality detection method and system for performance management. BACKGROUND

[0002] Currently, the road parking management system has generally realized the collection and monitoring of basic operation data such as parking space state, vehicle entry / exit, order flow, and some advanced systems can further complete simple trend analysis and ranking comparison for a single parking space or road section. However, in the method of performance management of parking attendants, the basic operation data of the existing system and the individual performance of the parking attendants lack effective correlation. When the basic operation data is abnormal or the road supervision rate is low, the management party usually can only rely on personal experience or simple comparison of similar road sections for qualitative judgment, and cannot effectively correlate the abnormal situation with the specific inspection behavior of the parking attendants, affecting the accuracy of the performance evaluation of the parking attendants and the efficiency of the performance management and the supervision efficiency of the road parking management system. SUMMARY

[0003] The technical problem to be solved by the present application is to provide a parking attendant inspection abnormality detection method and system for performance management, which can effectively correlate the abnormal situation with the specific inspection behavior of the parking attendants, improve the accuracy of the performance evaluation of the parking attendants, and improve the efficiency of the performance management and the supervision efficiency of the road parking management system.

[0004] To solve the above technical problems, the technical scheme adopted by the present application is as follows: In a first aspect, the present application provides a parking attendant inspection abnormality detection method for performance management, comprising: Collecting real-time state data of parking spaces, dividing and aggregating the real-time state data of the parking spaces according to parking attendant management attribution rules to obtain individual real-time parking space data sets of each parking attendant, grouping and summarizing free parking abnormality parking space events with a parking time of 0 and unlicensed vehicle abnormality parking space events existing in the individual real-time parking space data sets of each parking attendant, and generating a total number of free parking real-time abnormality events and a total number of unlicensed vehicle real-time abnormality events corresponding to each parking attendant; Comparing the total number of free parking real-time abnormality events of each parking attendant with a personalized free parking benchmark constructed based on historical management data of each parking attendant to generate an inspection efficiency abnormality result of each parking attendant, and comparing the total number of unlicensed vehicle real-time abnormality events of each parking attendant with a group unlicensed benchmark constructed based on the total number of unlicensed vehicle real-time abnormality events of all parking attendants in the same jurisdiction area to generate an inspection operation abnormality result of each parking attendant; Collect real-time road segment monitoring data of the patrol section, calculate the real-time road segment monitoring rate based on the real-time road segment monitoring data, obtain the current abnormal road segment based on the real-time road segment monitoring rate, and at the same time obtain the individual real-time monitoring rate of the parking attendant in charge of the current abnormal road segment. Based on the real-time road segment monitoring rate and the individual real-time monitoring rate, assign the responsibility for the current abnormal road segment and generate the abnormal responsibility assignment result. Based on the results of the attribution of responsibility for the anomalies, the results of the abnormal inspection efficiency, and the results of the abnormal inspection operations, the performance of the berth rangers is evaluated, and the performance evaluation results are generated.

[0005] The beneficial effects of this invention are as follows: Real-time parking space status data is collected and divided and aggregated according to the parking attendant management rules, thus binding the real-time parking space status data with individual parking attendants. This ensures the accuracy of the two types of abnormal parking space events obtained from the real-time parking space datasets managed by each attendant, while transforming scattered abnormal parking space events into quantifiable indicators of parking attendant responsibility. Different abnormal parking space events are judged using different abnormality criteria, generating different inspection abnormality results. This approach considers both the differences in individual parking attendant work and the operational norms of the parking attendant group, effectively binding abnormal parking space events with specific inspection behaviors of parking attendants. For current abnormal road sections, responsibility is not simply attributed to parking attendants, but rather based on the real-time monitoring rate of the road section and the individual real-time monitoring rate, avoiding ambiguity in responsibility. When evaluating the performance of parking attendants, the evaluation is based on three dimensions: abnormality responsibility attribution results, abnormal inspection efficiency results, and abnormal inspection operation results. This improves the accuracy of the performance evaluation results, thereby increasing the enthusiasm of parking attendants and improving the efficiency of performance management and the supervision efficiency of the road parking management system.

[0006] Optionally, the step of comparing the total number of real-time abnormal events for free parking for each parking attendant with the personalized free parking benchmark constructed based on the historical jurisdiction data of each parking attendant to generate an abnormal inspection efficiency result for each parking attendant includes: Obtain the historical management data of each parking attendant within a preset period. Based on the historical management data, calculate the total number of historical abnormal events related to free parking for each parking attendant. Input the total number of historical abnormal events related to free parking for each parking attendant into a first personalized formula for calculation, and obtain the corresponding personalized free parking benchmark for each parking attendant. The first personalized formula is: ; in, This represents the personalized baseline of the parking attendant i. This represents the average number of abnormal events in the free parking history of parking attendant i. This represents the first preset coefficient. The standard deviation of the total number of abnormal events in the free parking history of parking attendant i; The total number of real-time abnormal events for free parking for each parking attendant is compared with the corresponding personalized free parking benchmark. It is determined whether the total number of real-time abnormal events for free parking exceeds the personalized free parking benchmark. If so, the number of times the total number of real-time abnormal events for free parking exceeds the personalized free parking benchmark is obtained. It is determined whether the number of times the free parking exceeds the first lower limit threshold is greater than the first lower limit threshold. If so, the inspection efficiency of the parking attendant is marked as suspected abnormal, so as to obtain the parking attendants suspected of being abnormal. The total number of real-time abnormal events for free parking corresponding to the suspected abnormal parking attendant is compared with the group-based free parking benchmark constructed based on the total number of real-time abnormal events for free parking of all parking attendants in the same jurisdiction area. It is determined whether the total number of real-time abnormal events for free parking corresponding to the suspected abnormal parking attendant exceeds the group-based free parking benchmark. If so, the inspection efficiency corresponding to the suspected abnormal parking attendant is marked as confirmed abnormal, the confirmed abnormal parking attendant is obtained and the corresponding inspection efficiency abnormal result is generated. If not, the inspection efficiency corresponding to the suspected abnormal parking attendant is corrected to normal. The comparison of the total number of real-time abnormal free parking events corresponding to suspected abnormal parking attendants with the grouped free parking benchmark constructed based on the total number of real-time abnormal free parking events of all parking attendants in the same jurisdiction includes: Obtain the jurisdiction area of ​​each parking attendant, and summarize the total number of real-time abnormal events of free parking for all parking attendants in the same jurisdiction area to generate the total number of real-time abnormal events of free parking in each area for each parking attendant. The total number of real-time no-parking exception events for each parking attendant's area is input into the first grouping formula for calculation, resulting in the grouped no-parking benchmark for each attendant. The first grouping formula is as follows: ; in, This indicates the group-based exemption criteria for parking attendant i. This represents the average number of real-time no-parking exception events in the area for parking attendant i. This represents the second preset coefficient. This represents the standard deviation of the total number of real-time no-parking exceptions in the area for parking attendant i.

[0007] As described above, the dual judgment method employing both individualized and group-based exemption criteria first calculates an individualized exemption criterion based on the parking attendant's historical jurisdictional data, eliminating interference from individual differences and initially screening out suspected abnormal parking attendants. Furthermore, a multi-dimensional judgment approach is used to further filter suspected abnormal parking attendants, effectively eliminating interference from single abnormalities and reducing the probability of false labeling. Finally, a group-based exemption criterion, constructed based on the total number of real-time abnormal free parking events for all parking attendants within the same jurisdiction, is used for judgment. This avoids situations where parking attendants are in a consistently low-efficiency or high-efficiency baseline state, thus failing to identify genuine abnormalities. This effectively corrects the judgment distortion problem caused by the individualized exemption criterion, improving the accuracy of inspection efficiency and anomaly identification.

[0008] Optionally, the step of simultaneously comparing the total number of real-time abnormal events of unlicensed vehicles for each parking attendant with a grouped unlicensed vehicle baseline constructed based on the total number of real-time abnormal events of unlicensed vehicles for all parking attendants within the same jurisdiction, and generating abnormal inspection operation results for each parking attendant, includes: Obtain the jurisdiction area of ​​each parking attendant, and summarize the total number of real-time abnormal events of unlicensed vehicles of all parking attendants in the same jurisdiction area to generate the total number of real-time abnormal events of unlicensed vehicles in each parking attendant's area. The total number of unlicensed incidents in each parking attendant's area in real time is input into the second grouping formula for calculation, resulting in the grouped unlicensed baseline for each parking attendant. The second grouping formula is as follows: ; in, This represents the group of unlicensed berth attendants i. This represents the average number of real-time unlicensed incidents in the area where parking attendant i resides. This represents the third preset coefficient. The standard deviation of the total number of real-time unlicensed incidents in the area of ​​parking attendant i; The total number of real-time abnormal events of unlicensed vehicles for each parking attendant is compared with the corresponding group-based unlicensed vehicle benchmark. It is determined whether the total number of real-time abnormal events of unlicensed vehicles exceeds the group-based unlicensed vehicle benchmark. If so, the number of times the total number of real-time abnormal events of unlicensed vehicles exceeds the group-based unlicensed vehicle benchmark is obtained. It is determined whether the number of times ...

[0009] As described above, the mean and standard deviation of the total number of real-time unlicensed vehicle anomalies within the same jurisdiction are used to generate a grouped unlicensed benchmark. This benchmark objectively reflects the normal inspection operation level of the jurisdiction, provides a reasonable reference for individual inspection operations, avoids subjective influence, objectively identifies inspection operations that deviate from the grouped unlicensed benchmark, and uses a dual-judgment logic when determining anomalies in inspection operations, thereby improving the accuracy of the obtained results.

[0010] Optionally, obtaining the current abnormal road segment based on the real-time monitoring rate of the road segment includes: Obtain historical road segment monitoring data for the inspected road segment within a preset period, calculate the historical road segment monitoring rate based on the historical road segment monitoring data, input the historical road segment monitoring rate into a first road segment formula for calculation, and obtain the road segment benchmark. The first road segment formula is: ; in, This represents the road segment baseline for inspected road segment j. This represents the average historical monitoring rate of inspection segment j. This represents the third preset coefficient. The standard deviation of the historical monitoring rate of inspected road segment j; The real-time monitoring rate of the road segment is compared with the road segment benchmark to determine whether the real-time monitoring rate of the road segment is lower than the road segment benchmark. If so, the inspected road segment is marked as an abnormal road segment to obtain the current abnormal road segment.

[0011] As described above, when determining the current abnormal road segment, the real-time monitoring rate of the road segment is compared with the road segment benchmark obtained based on the historical monitoring rate of the inspected road segment. This makes the determination of the current abnormal road segment objective and targeted. Furthermore, the inspected road segments with a real-time monitoring rate lower than the road segment benchmark are marked as abnormal road segments, thereby achieving accurate location of inspected road segments with declining monitoring rates.

[0012] Optionally, the step of simultaneously obtaining the individual real-time monitoring rate of the parking attendant in charge of the current abnormal road segment, and assigning responsibility for the current abnormal road segment based on the road segment real-time monitoring rate and the individual real-time monitoring rate, and generating an abnormal responsibility assignment result includes: Simultaneously, the individual real-time monitoring rate of all parking attendants in charge of the current abnormal road section is obtained, and the individual real-time monitoring rates are summarized to generate the total individual real-time monitoring rate; Calculate the difference between the individual real-time total monitoring rate and the road segment real-time monitoring rate, and determine whether the difference exceeds a first critical threshold. If so, assign the abnormal responsibility of the current abnormal road segment to the parking attendant with the lowest individual real-time monitoring rate, generating an abnormal responsibility attribution result for individual responsibility. If not, assign the abnormal responsibility of the current abnormal road segment to all parking attendants in charge of the current abnormal road segment, generating an abnormal responsibility attribution result for group responsibility.

[0013] As described above, by comparing the difference between the individual real-time total monitoring rate and the real-time monitoring rate of the current abnormal road segment with the first critical threshold, the attribution of abnormal responsibility is realized, the individual responsibility and the group responsibility are distinguished by the benchmark, and the problems of generalization of abnormal responsibility and ambiguity of responsibility attribution are solved.

[0014] Secondly, the present invention provides a berth maintenance worker inspection anomaly detection system for performance management, comprising: The abnormal event grouping module is used to collect real-time parking space status data, divide and aggregate the real-time parking space status data according to the parking attendant management rules, so as to obtain the individual real-time parking space dataset under the jurisdiction of each parking attendant. The module groups and summarizes the free parking abnormal parking space events with a parking duration of 0 and the license plate vehicle abnormal parking space events in the individual real-time parking space dataset under the jurisdiction of each parking attendant, and generates the corresponding total number of free parking real-time abnormal events and the total number of license plate vehicle real-time abnormal events for each parking attendant. The inspection anomaly detection module is used to compare the total number of real-time abnormal events of free parking for each parking attendant with the personalized free parking benchmark constructed based on the historical jurisdiction data of each parking attendant, and generate an abnormal inspection efficiency result for each parking attendant. At the same time, it compares the total number of real-time abnormal events of unlicensed vehicles for each parking attendant with the grouped unlicensed vehicle benchmark constructed based on the total number of real-time abnormal events of unlicensed vehicles of all parking attendants in the same jurisdiction, and generates an abnormal inspection operation result for each parking attendant. The anomaly responsibility attribution module is used to collect real-time road segment monitoring data of the inspected road segments, calculate the real-time monitoring rate of the road segments based on the real-time monitoring data, obtain the current abnormal road segments based on the real-time monitoring rate of the road segments, and obtain the individual real-time monitoring rate of the parking attendant in charge of the current abnormal road segments. Based on the real-time monitoring rate of the road segments and the individual real-time monitoring rate, the anomaly responsibility attribution is assigned to the current abnormal road segments, and an anomaly responsibility attribution result is generated. The performance evaluation module is used to evaluate the performance of the berth manager based on the results of the abnormal responsibility attribution, the abnormal inspection efficiency, and the abnormal inspection operation, and to generate performance evaluation results.

[0015] The beneficial effects of this invention are as follows: Real-time parking space status data is collected and divided and aggregated according to the parking attendant management rules, thus binding the real-time parking space status data with individual parking attendants. This ensures the accuracy of the two types of abnormal parking space events obtained from the real-time parking space datasets managed by each attendant, while transforming scattered abnormal parking space events into quantifiable indicators of parking attendant responsibility. Different abnormal parking space events are judged using different abnormality criteria, generating different inspection abnormality results. This approach considers both the differences in individual parking attendant work and the operational norms of the parking attendant group, effectively binding abnormal parking space events with specific inspection behaviors of parking attendants. For current abnormal road sections, responsibility is not simply attributed to parking attendants, but rather based on the real-time monitoring rate of the road section and the individual real-time monitoring rate, avoiding ambiguity in responsibility. When evaluating the performance of parking attendants, the evaluation is based on three dimensions: abnormality responsibility attribution results, abnormal inspection efficiency results, and abnormal inspection operation results. This improves the accuracy of the performance evaluation results, thereby increasing the enthusiasm of parking attendants and improving the efficiency of performance management and the supervision efficiency of the road parking management system.

[0016] Optionally, the inspection anomaly detection module includes: The inspection efficiency anomaly module is used to acquire historical management data for each parking attendant within a preset period, calculate the total number of historical anomalies in free parking for each attendant based on the historical management data, and input the total number of historical anomalies in free parking for each attendant into a first personalized formula for calculation to obtain the corresponding personalized free parking benchmark for each attendant. The first personalized formula is: ; in, This represents the personalized baseline of the parking attendant i. This represents the average number of abnormal events in the free parking history of parking attendant i. This represents the first preset coefficient. The standard deviation of the total number of abnormal events in the free parking history of parking attendant i; The total number of real-time abnormal events for free parking for each parking attendant is compared with the corresponding personalized free parking benchmark. It is determined whether the total number of real-time abnormal events for free parking exceeds the personalized free parking benchmark. If so, the number of times the total number of real-time abnormal events for free parking exceeds the personalized free parking benchmark is obtained. It is determined whether the number of times the free parking exceeds the first lower limit threshold is greater than the first lower limit threshold. If so, the inspection efficiency of the parking attendant is marked as suspected abnormal, so as to obtain the parking attendants suspected of being abnormal. The total number of real-time abnormal events for free parking corresponding to the suspected abnormal parking attendant is compared with the group-based free parking benchmark constructed based on the total number of real-time abnormal events for free parking of all parking attendants in the same jurisdiction area. It is determined whether the total number of real-time abnormal events for free parking corresponding to the suspected abnormal parking attendant exceeds the group-based free parking benchmark. If so, the inspection efficiency corresponding to the suspected abnormal parking attendant is marked as confirmed abnormal, the confirmed abnormal parking attendant is obtained and the corresponding inspection efficiency abnormal result is generated. If not, the inspection efficiency corresponding to the suspected abnormal parking attendant is corrected to normal. The comparison of the total number of real-time abnormal free parking events corresponding to suspected abnormal parking attendants with the grouped free parking benchmark constructed based on the total number of real-time abnormal free parking events of all parking attendants in the same jurisdiction includes: Obtain the jurisdiction area of ​​each parking attendant, and summarize the total number of real-time abnormal events of free parking for all parking attendants in the same jurisdiction area to generate the total number of real-time abnormal events of free parking in each area for each parking attendant. The total number of real-time no-parking exception events for each parking attendant's area is input into the first grouping formula for calculation, resulting in the grouped no-parking benchmark for each attendant. The first grouping formula is as follows: ; in, This indicates the group-based exemption criteria for parking attendant i. This represents the average number of real-time no-parking exception events in the area for parking attendant i. This represents the second preset coefficient. This represents the standard deviation of the total number of real-time no-parking exceptions in the area for parking attendant i.

[0017] As described above, the dual judgment method employing both individualized and group-based exemption criteria first calculates an individualized exemption criterion based on the parking attendant's historical jurisdictional data, eliminating interference from individual differences and initially screening out suspected abnormal parking attendants. Furthermore, a multi-dimensional judgment approach is used to further filter suspected abnormal parking attendants, effectively eliminating interference from single abnormalities and reducing the probability of false labeling. Finally, a group-based exemption criterion, constructed based on the total number of real-time abnormal free parking events for all parking attendants within the same jurisdiction, is used for judgment. This avoids situations where parking attendants are in a consistently low-efficiency or high-efficiency baseline state, thus failing to identify genuine abnormalities. This effectively corrects the judgment distortion problem caused by the individualized exemption criterion, improving the accuracy of inspection efficiency and anomaly identification.

[0018] Optionally, the inspection anomaly detection module includes: The inspection operation anomaly module is used to obtain the jurisdiction area of ​​each parking manager and summarize the total number of real-time anomaly events of unlicensed vehicles of all parking managers in the same jurisdiction area to generate the total number of real-time unlicensed vehicle anomaly events of each parking manager's area. The total number of unlicensed incidents in each parking attendant's area in real time is input into the second grouping formula for calculation, resulting in the grouped unlicensed baseline for each parking attendant. The second grouping formula is as follows: ; in, This represents the group of unlicensed berth attendants i. This represents the average number of real-time unlicensed incidents in the area where parking attendant i resides. This represents the third preset coefficient. The standard deviation of the total number of real-time unlicensed incidents in the area of ​​parking attendant i; The total number of real-time abnormal events of unlicensed vehicles for each parking attendant is compared with the corresponding group-based unlicensed vehicle benchmark. It is determined whether the total number of real-time abnormal events of unlicensed vehicles exceeds the group-based unlicensed vehicle benchmark. If so, the number of times the total number of real-time abnormal events of unlicensed vehicles exceeds the group-based unlicensed vehicle benchmark is obtained. It is determined whether the number of times ...

[0019] As described above, the mean and standard deviation of the total number of real-time unlicensed vehicle anomalies within the same jurisdiction are used to generate a grouped unlicensed benchmark. This benchmark objectively reflects the normal inspection operation level of the jurisdiction, provides a reasonable reference for individual inspection operations, avoids subjective influence, objectively identifies inspection operations that deviate from the grouped unlicensed benchmark, and uses a dual-judgment logic when determining anomalies in inspection operations, thereby improving the accuracy of the obtained results.

[0020] Optionally, the anomaly attribution module includes: The abnormal road segment identification module is used to acquire historical road segment monitoring data of the inspected road segment within a preset period, calculate the historical monitoring rate of the road segment based on the historical monitoring data, and input the historical monitoring rate of the road segment into a first road segment formula for calculation to obtain the road segment benchmark. The first road segment formula is: ; in, This represents the road segment baseline for inspected road segment j. This represents the average historical monitoring rate of inspection segment j. This represents the third preset coefficient. The standard deviation of the historical monitoring rate of inspected road segment j; The real-time monitoring rate of the road segment is compared with the road segment benchmark to determine whether the real-time monitoring rate of the road segment is lower than the road segment benchmark. If so, the inspected road segment is marked as an abnormal road segment to obtain the current abnormal road segment.

[0021] As described above, when determining the current abnormal road segment, the real-time monitoring rate of the road segment is compared with the road segment benchmark obtained based on the historical monitoring rate of the inspected road segment. This makes the determination of the current abnormal road segment objective and targeted. Furthermore, the inspected road segments with a real-time monitoring rate lower than the road segment benchmark are marked as abnormal road segments, thereby achieving accurate location of inspected road segments with declining monitoring rates.

[0022] Optionally, the anomaly responsibility attribution module specifically comprises: Simultaneously, the individual real-time monitoring rate of all parking attendants in charge of the current abnormal road section is obtained, and the individual real-time monitoring rates are summarized to generate the total individual real-time monitoring rate; Calculate the difference between the individual real-time total monitoring rate and the road segment real-time monitoring rate, and determine whether the difference exceeds a first critical threshold. If so, assign the abnormal responsibility of the current abnormal road segment to the parking attendant with the lowest individual real-time monitoring rate, generating an abnormal responsibility attribution result for individual responsibility. If not, assign the abnormal responsibility of the current abnormal road segment to all parking attendants in charge of the current abnormal road segment, generating an abnormal responsibility attribution result for group responsibility.

[0023] As described above, by comparing the difference between the individual real-time total monitoring rate and the real-time monitoring rate of the current abnormal road segment with the first critical threshold, the attribution of abnormal responsibility is realized, the individual responsibility and the group responsibility are distinguished by the benchmark, and the problems of generalization of abnormal responsibility and ambiguity of responsibility attribution are solved. Attached Figure Description

[0024] Figure 1 This is a flowchart of a method for detecting anomalies in berth maintenance worker inspections for performance management, provided in this embodiment. Figure 2 This is a schematic diagram of the overall process of a berth maintenance worker inspection anomaly detection method for performance management provided in this embodiment. Figure 3 This is a schematic diagram of the structure of a berth maintenance worker inspection anomaly detection system for performance management provided in this embodiment.

[0025] Explanation of reference numerals in the attached figures 1. A system for detecting abnormalities in berth maintenance worker inspections for performance management purposes; 2. Abnormal event grouping module; 3. Inspection anomaly detection module; 31. Inspection efficiency anomaly module; 32. Inspection operation anomaly module; 4. Abnormal responsibility attribution module; 41. Abnormal road section identification module; 5. Performance evaluation module. Detailed Implementation

[0026] To better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present invention can be understood more clearly and thoroughly, and that the scope of the present invention can be fully conveyed to those skilled in the art.

[0027] Example 1 Please refer to Figures 1 to 2 This invention provides a method for detecting anomalies during berth maintenance worker inspections for performance management, comprising the following steps: S1. Collect real-time parking space status data, divide and aggregate the real-time parking space status data according to the parking attendant management rules to obtain the individual real-time parking space dataset under the jurisdiction of each parking attendant, and group and summarize the free parking abnormal parking space events with a parking duration of 0 and the license plate vehicle abnormal parking space events in the individual real-time parking space dataset under the jurisdiction of each parking attendant to generate the corresponding total number of free parking real-time abnormal events and the total number of license plate vehicle real-time abnormal events for each parking attendant. In this embodiment, as Figure 2 As shown, real-time parking space status data is collected from IoT devices such as geomagnetic sensors and curb markers. This data is then divided and aggregated according to the parking attendant's management affiliation rules. Specifically, the data is divided based on the parking attendant's jurisdiction, and the real-time status data for parking spaces managed by the same attendant are aggregated to obtain an individual real-time parking space dataset for each attendant. This data division and aggregation can be performed on a daily basis, resulting in a dataset for each day. For each attendant's dataset, events such as free parking with a duration of 0 and unlicensed vehicles are grouped and summarized. In this embodiment, abnormal parking events are categorized into two types: free parking with a duration of 0 and unlicensed vehicles. Grouping and summarizing these types generates the total number of free parking abnormal events and the total number of unlicensed vehicle abnormal events for each attendant.

[0028] S2. Compare the total number of real-time abnormal events for free parking for each parking attendant with the personalized free parking benchmark constructed based on the historical jurisdiction data of each parking attendant to generate an abnormal inspection efficiency result for each parking attendant. At the same time, compare the total number of real-time abnormal events for unlicensed vehicles for each parking attendant with the grouped unlicensed vehicle benchmark constructed based on the total number of real-time abnormal events for unlicensed vehicles of all parking attendants in the same jurisdiction to generate an abnormal inspection operation result for each parking attendant. In this embodiment, as Figure 2 As shown, the anomaly determination of inspection efficiency is quantified by comparing the total number of real-time abnormal events related to free parking with a personalized free parking benchmark constructed based on the historical jurisdiction data of parking attendants. The anomaly determination of inspection operations is quantified by comparing the total number of real-time abnormal events involving vehicles without license plates with a group-based benchmark for vehicles without license plates constructed based on the historical jurisdiction data of parking attendants. Different total numbers of real-time abnormal events correspond to different anomaly results and employ different determination benchmarks.

[0029] At this point, step S2, which compares the total number of real-time abnormal events for free parking for each parking attendant with the personalized free parking benchmark constructed based on the historical jurisdiction data of each parking attendant, generates abnormal inspection efficiency results for each parking attendant, including: S21. Obtain the historical management data of each parking attendant within a preset period. Calculate the total number of historical abnormal events related to free parking for each parking attendant based on the historical management data. Input the total number of historical abnormal events related to free parking for each parking attendant into a first personalized formula for calculation to obtain the corresponding personalized free parking benchmark for each parking attendant. The first personalized formula is: ; in, This represents the personalized baseline of the parking attendant i. This represents the average number of abnormal events in the free parking history of parking attendant i. This represents the first preset coefficient. The standard deviation of the total number of abnormal events in the free parking history of parking attendant i; S22. Compare the total number of real-time abnormal events for free parking for each parking attendant with the corresponding personalized free parking benchmark, and determine whether the total number of real-time abnormal events for free parking exceeds the personalized free parking benchmark. If so, obtain the number of times the total number of real-time abnormal events for free parking exceeds the personalized free parking benchmark, and determine whether the number of times is greater than the first lower limit threshold. If so, mark the inspection efficiency of the parking attendant as suspected abnormal, so as to obtain the parking attendant suspected of being abnormal. S23. Compare the total number of real-time abnormal events for free parking corresponding to the suspected abnormal parking attendant with the group-based free parking benchmark constructed based on the total number of real-time abnormal events for free parking of all parking attendants in the same jurisdiction area, and determine whether the total number of real-time abnormal events for free parking corresponding to the suspected abnormal parking attendant exceeds the group-based free parking benchmark. If so, mark the inspection efficiency corresponding to the suspected abnormal parking attendant as confirmed abnormal, obtain the confirmed abnormal parking attendant and generate the corresponding abnormal inspection efficiency result. If not, correct the inspection efficiency corresponding to the suspected abnormal parking attendant to normal. Before comparing the total number of real-time abnormal free parking events corresponding to suspected abnormal parking attendants with the grouped free parking benchmark constructed based on the total number of real-time abnormal free parking events of all parking attendants in the same jurisdiction, as described in S23, the following is included: S231. Obtain the jurisdiction area of ​​each parking attendant, and summarize the total number of real-time abnormal events of free parking for all parking attendants in the same jurisdiction area to generate the total number of real-time abnormal events of free parking in each area for each parking attendant. S232. Input the total number of real-time no-parking exception events in the area for each parking attendant into the first grouping formula for calculation to obtain the grouped no-parking benchmark for each parking attendant. The first grouping formula is: ; in, This indicates the group-based exemption criteria for parking attendant i. This represents the average number of real-time no-parking exception events in the area for parking attendant i. This represents the second preset coefficient. This represents the standard deviation of the total number of real-time no-parking exceptions in the area for parking attendant i.

[0030] In this embodiment, as Figure 2As shown, when determining anomalies in the inspection efficiency of parking attendants, a dual determination method using individualized and group-based free parking benchmarks is employed. Historical jurisdiction data for each parking attendant is acquired within a preset period (30 days). The total number of historical abnormal free parking events for each attendant is calculated based on this historical data. This total number is input into a first personalized formula for calculation. According to this formula, the personalized benchmark is calculated by combining the average and standard deviation of the total number of historical abnormal free parking events for each attendant with a first preset coefficient, which dynamically changes with the attendant's historical jurisdiction data. In this case, the first preset coefficient is set to 1.5. The total number of real-time abnormal free parking events for each attendant is compared with the corresponding personalized free parking benchmark. If the total number of real-time abnormal free parking events for an attendant exceeds the personalized free parking benchmark, and the number of times this exceeds the benchmark is greater than a first lower threshold, then the attendant's inspection efficiency is marked as potentially abnormal, thus identifying the attendants with suspected abnormalities.

[0031] The total number of real-time abnormal events related to free parking for suspected abnormal parking attendants is compared with the group-based free parking benchmark. If the total number of real-time abnormal events related to free parking for suspected abnormal parking attendants exceeds the group-based free parking benchmark, the inspection efficiency of the suspected abnormal parking attendant is marked as confirmed abnormal, and the confirmed abnormal parking attendant is identified, generating the corresponding abnormal inspection efficiency result. Conversely, if the total number of real-time abnormal events related to free parking for suspected abnormal parking attendants does not exceed the group-based free parking benchmark, the inspection efficiency of the suspected abnormal parking attendant is corrected to normal. This avoids the inability to identify true abnormalities due to parking attendants being in a long-term low-efficiency or high-efficiency baseline state, effectively correcting the judgment distortion problem caused by the individualized free parking benchmark. The group-based free parking benchmark is actually calculated based on the average and standard deviation of the total number of real-time free parking abnormal events for each parking attendant in the region, combined with a second preset coefficient. This coefficient dynamically changes with the total number of real-time free parking abnormal events for parking attendants in the same jurisdiction. The first lower limit threshold is 2 times. In this embodiment, the preset period, the first preset coefficient, and the first lower limit threshold can all be adjusted according to the actual situation.

[0032] At this point, step S2 involves comparing the total number of real-time abnormal events involving unlicensed vehicles for each parking attendant with the grouped unlicensed vehicle baseline constructed based on the total number of real-time abnormal events involving unlicensed vehicles for all parking attendants within the same jurisdiction. The resulting abnormal inspection operation results for each parking attendant include: S24. Obtain the jurisdiction area of ​​each parking attendant, and summarize the total number of real-time abnormal events of unlicensed vehicles of all parking attendants in the same jurisdiction area to generate the total number of real-time abnormal events of unlicensed vehicles in each parking attendant's area. S25. Input the total number of real-time unlicensed incidents in each berth manager's area into the second grouping formula for calculation, to obtain the grouped unlicensed baseline for each berth manager. The second grouping formula is: ; in, This represents the group of unlicensed berth attendants i. This represents the average number of real-time unlicensed incidents in the area where parking attendant i resides. This represents the third preset coefficient. The standard deviation of the total number of real-time unlicensed incidents in the area of ​​parking attendant i; S26. Compare the total number of real-time abnormal events of unlicensed vehicles for each parking attendant with the corresponding group-based unlicensed vehicle benchmark, and determine whether the total number of real-time abnormal events of unlicensed vehicles exceeds the group-based unlicensed vehicle benchmark. If so, obtain the number of times the total number of real-time abnormal events of unlicensed vehicles exceeds the group-based unlicensed vehicle benchmark, and determine whether the number of times ...

[0033] In this embodiment, as Figure 2 As shown, the jurisdiction area of ​​each parking attendant is obtained. The total number of real-time abnormal events of unlicensed vehicles for all parking attendants within the same jurisdiction is summarized. The total number of real-time abnormal events of unlicensed vehicles for each parking attendant's area is then input into the second grouping formula for calculation. According to the second grouping formula, the grouped unlicensed vehicle benchmark is actually calculated based on the average and standard deviation of the total number of real-time abnormal events of unlicensed vehicles for each parking attendant's area, combined with a second preset coefficient. This coefficient dynamically changes with the total number of real-time abnormal events of unlicensed vehicles for parking attendants within the same jurisdiction. The third preset coefficient can be the same as or different from the first or second preset coefficient, depending on the actual situation. If the total number of real-time abnormal events of unlicensed vehicles for a parking attendant exceeds its corresponding grouped unlicensed vehicle benchmark, and the number of times the benchmark is exceeded is greater than the second lower limit threshold, then the parking attendant's inspection operation is marked as abnormal, and an abnormal inspection operation result is generated. The second lower limit threshold is 4 times, which can be adjusted according to the actual situation.

[0034] S3. Collect real-time road segment monitoring data of the inspected road segment, calculate the real-time road segment monitoring rate based on the real-time road segment monitoring data, obtain the current abnormal road segment based on the real-time road segment monitoring rate, and at the same time obtain the individual real-time monitoring rate corresponding to the parking attendant in charge of the current abnormal road segment. Assign abnormal responsibility to the current abnormal road segment based on the real-time road segment monitoring rate and the individual real-time monitoring rate, and generate abnormal responsibility assignment result. In this embodiment, as Figure 2As shown, the real-time road segment monitoring rate is calculated based on the collected real-time road segment monitoring data. Based on the real-time road segment monitoring rate, the current abnormal road segment is obtained. For the current abnormal road segment, the responsibility for the abnormality is assigned. The result of the responsibility assignment is generated by comparing the real-time monitoring rate of the individual parking attendant in charge of the current abnormal road segment with the real-time road segment monitoring rate.

[0035] At this point, the step S3, which involves obtaining the current abnormal road segment based on the real-time monitoring rate of the road segment, includes: S31. Obtain historical road segment monitoring data of the inspected road segment within a preset period, calculate the historical road segment monitoring rate based on the historical road segment monitoring data, input the historical road segment monitoring rate into the first road segment formula for calculation, and obtain the road segment benchmark. The first road segment formula is: ; in, This represents the road segment baseline for inspected road segment j. This represents the average historical monitoring rate of inspection segment j. This represents the third preset coefficient. The standard deviation of the historical monitoring rate of inspected road segment j; S32. Compare the real-time monitoring rate of the road segment with the road segment benchmark, and determine whether the real-time monitoring rate of the road segment is lower than the road segment benchmark. If so, mark the inspected road segment as an abnormal road segment to obtain the current abnormal road segment.

[0036] In this embodiment, as Figure 2 As shown, historical road segment monitoring data for the inspected road segment within a preset period is obtained. This preset period is the same as the preset period in step S21, both being 30 days. The historical monitoring rate of the road segment is calculated based on the obtained historical monitoring data. This historical monitoring rate is then input into the first road segment formula for calculation, generating the road segment benchmark for the inspected road segment. In reality, the road segment benchmark is calculated based on the average and standard deviation of the historical monitoring rate of the road segment, combined with a third preset coefficient. This third preset coefficient dynamically changes with the changes in the historical monitoring data of the inspected road segment. This third preset coefficient can be the same as or different from the first or second preset coefficient, depending on the actual situation. The real-time monitoring rate of the road segment is compared with the road segment benchmark. If the real-time monitoring rate is lower than the road segment benchmark, it indicates a decline in the monitoring rate of the inspected road segment. The inspected road segment is then marked as an abnormal road segment to obtain the current abnormal road segment.

[0037] At this point, step S3, which involves simultaneously obtaining the individual real-time monitoring rate of the parking attendant in charge of the current abnormal road segment, and assigning responsibility for the current abnormal road segment based on the road segment real-time monitoring rate and the individual real-time monitoring rate, generates the following abnormal responsibility assignment results: S33. Simultaneously obtain the individual real-time monitoring rate of all parking attendants in charge of the current abnormal road section, and summarize the individual real-time monitoring rates to generate the total individual real-time monitoring rate; S34. Calculate the difference between the individual real-time total monitoring rate and the road segment real-time monitoring rate, and determine whether the difference exceeds the first critical threshold. If so, assign the abnormal responsibility of the current abnormal road segment to the parking attendant with the lowest individual real-time monitoring rate, and generate an abnormal responsibility attribution result for individual responsibility. If not, assign the abnormal responsibility of the current abnormal road segment to all parking attendants in charge of the current abnormal road segment, and generate an abnormal responsibility attribution result for group responsibility.

[0038] In this embodiment, as Figure 2 As shown, the system simultaneously acquires and aggregates the individual real-time monitoring rates of all parking attendants managing the current abnormal road segment to generate an overall individual real-time monitoring rate. The difference between the overall individual real-time monitoring rate and the road segment's real-time monitoring rate is calculated. If this difference exceeds a first critical threshold, the responsibility for the current abnormal road segment is assigned to the parking attendant with the lowest individual real-time monitoring rate, generating an individual responsibility assignment result. In this embodiment, the specific parking attendant is marked with this individual responsibility assignment result for subsequent traceability and performance evaluation. Conversely, if the difference does not exceed the first critical threshold, the responsibility for the current abnormal road segment is assigned to all parking attendants managing the current abnormal road segment, generating a group responsibility assignment result. Similarly, all parking attendants corresponding to the group responsibility assignment result are marked for subsequent traceability and performance evaluation. The first critical threshold is 0.05, which can be adjusted according to actual circumstances.

[0039] S4. Based on the results of the abnormal responsibility attribution, the abnormal inspection efficiency, and the abnormal inspection operation, the performance evaluation of the berth manager is carried out, and the performance evaluation results are generated.

[0040] In this embodiment, as Figure 2 As shown, the performance evaluation of berth rangers is based on the results of abnormal responsibility attribution, abnormal inspection efficiency, and abnormal inspection operation. Specifically, different results are scored according to pre-set scoring rules to obtain corresponding scores for abnormal responsibility attribution, abnormal inspection efficiency, and abnormal inspection operation. The obtained scores are then input into a first weighted evaluation formula for performance evaluation to generate the berth ranger's performance evaluation result. The first weighted evaluation formula is as follows: ; in, This indicates the performance evaluation results of berth attendant i. The score indicates the result of assigning responsibility for the anomaly. The score indicates the result of abnormal inspection efficiency. The score indicates the result of abnormal inspection operations. Indicates the first weight. Indicates the second weight. This indicates the third weight.

[0041] Example 2 Please refer to Figure 2 Figure 3 The present invention provides a parking attendant inspection anomaly detection system 1 for performance management, including: an anomaly event grouping module 2, an inspection anomaly detection module 3, an inspection efficiency anomaly module 31, an inspection operation anomaly module 32, an anomaly responsibility attribution module 4, an anomaly road section identification module 41, and a performance evaluation module 5.

[0042] Among them, the abnormal event grouping module 2 is used to collect real-time parking space status data, divide and aggregate the real-time parking space status data according to the parking attendant management affiliation rules, so as to obtain the individual real-time parking space dataset under the jurisdiction of each parking attendant, and group and summarize the free parking abnormal parking space events with a parking duration of 0 and the license plate vehicle abnormal parking space events in the individual real-time parking space dataset under the jurisdiction of each parking attendant, and generate the corresponding total number of free parking real-time abnormal events and the total number of license plate vehicle real-time abnormal events for each parking attendant. The inspection anomaly detection module 3 is used to compare the total number of real-time abnormal events of free parking for each parking attendant with the personalized free parking benchmark constructed based on the historical jurisdiction data of each parking attendant, and generate the inspection efficiency anomaly result for each parking attendant. At the same time, it compares the total number of real-time abnormal events of unlicensed vehicles for each parking attendant with the grouped unlicensed vehicle benchmark constructed based on the total number of real-time abnormal events of unlicensed vehicles of all parking attendants in the same jurisdiction area, and generates the inspection operation anomaly result for each parking attendant. The anomaly responsibility attribution module 4 is used to collect real-time road segment monitoring data of the inspected road segments, calculate the real-time monitoring rate of the road segments based on the real-time road segment monitoring data, obtain the current abnormal road segments based on the real-time road segment monitoring rate, and obtain the individual real-time monitoring rate of the parking attendant in charge of the current abnormal road segment. Based on the real-time road segment monitoring rate and the individual real-time monitoring rate, the anomaly responsibility attribution is performed on the current abnormal road segment, and an anomaly responsibility attribution result is generated. The performance evaluation module 5 is used to evaluate the performance of the berth manager based on the results of the abnormal responsibility attribution, the abnormal inspection efficiency, and the abnormal inspection operation, and to generate performance evaluation results.

[0043] Specifically, the inspection anomaly detection module 3 includes: The inspection efficiency anomaly module 31 is used to acquire historical management data of each parking attendant within a preset period, calculate the total number of historical anomalies in free parking for each parking attendant based on the historical management data, input the total number of historical anomalies in free parking for each parking attendant into a first personalized formula for calculation, and obtain the corresponding personalized free parking benchmark for each parking attendant. The first personalized formula is: ; in, This represents the personalized baseline of the parking attendant i. This represents the average number of abnormal events in the free parking history of parking attendant i. This represents the first preset coefficient. The standard deviation of the total number of abnormal events in the free parking history of parking attendant i; The total number of real-time abnormal events for free parking for each parking attendant is compared with the corresponding personalized free parking benchmark. It is determined whether the total number of real-time abnormal events for free parking exceeds the personalized free parking benchmark. If so, the number of times the total number of real-time abnormal events for free parking exceeds the personalized free parking benchmark is obtained. It is determined whether the number of times the free parking exceeds the first lower limit threshold is greater than the first lower limit threshold. If so, the inspection efficiency of the parking attendant is marked as suspected abnormal, so as to obtain the parking attendants suspected of being abnormal. The total number of real-time abnormal events for free parking corresponding to the suspected abnormal parking attendant is compared with the group-based free parking benchmark constructed based on the total number of real-time abnormal events for free parking of all parking attendants in the same jurisdiction area. It is determined whether the total number of real-time abnormal events for free parking corresponding to the suspected abnormal parking attendant exceeds the group-based free parking benchmark. If so, the inspection efficiency corresponding to the suspected abnormal parking attendant is marked as confirmed abnormal, the confirmed abnormal parking attendant is obtained and the corresponding inspection efficiency abnormal result is generated. If not, the inspection efficiency corresponding to the suspected abnormal parking attendant is corrected to normal. The comparison of the total number of real-time abnormal free parking events corresponding to suspected abnormal parking attendants with the grouped free parking benchmark constructed based on the total number of real-time abnormal free parking events of all parking attendants in the same jurisdiction includes: Obtain the jurisdiction area of ​​each parking attendant, and summarize the total number of real-time abnormal events of free parking for all parking attendants in the same jurisdiction area to generate the total number of real-time abnormal events of free parking in each area for each parking attendant. The total number of real-time no-parking exception events for each parking attendant's area is input into the first grouping formula for calculation, resulting in the grouped no-parking benchmark for each attendant. The first grouping formula is as follows: ; in, This indicates the group-based exemption criteria for parking attendant i. This represents the average number of real-time no-parking exception events in the area for parking attendant i. This represents the second preset coefficient. This represents the standard deviation of the total number of real-time no-parking exceptions in the area for parking attendant i.

[0044] Specifically, the inspection anomaly detection module 3 includes: The inspection operation anomaly module 32 is used to obtain the jurisdiction area of ​​each parking manager and summarize the total number of real-time abnormal events of unlicensed vehicles of all parking managers in the same jurisdiction area to generate the total number of real-time abnormal events of unlicensed vehicles in each parking manager's area. The total number of unlicensed incidents in each parking attendant's area in real time is input into the second grouping formula for calculation, resulting in the grouped unlicensed baseline for each parking attendant. The second grouping formula is as follows: ; in, This represents the group of unlicensed berth attendants i. This represents the average number of real-time unlicensed incidents in the area where parking attendant i resides. This represents the third preset coefficient. The standard deviation of the total number of real-time unlicensed incidents in the area of ​​parking attendant i; The total number of real-time abnormal events of unlicensed vehicles for each parking attendant is compared with the corresponding group-based unlicensed vehicle benchmark. It is determined whether the total number of real-time abnormal events of unlicensed vehicles exceeds the group-based unlicensed vehicle benchmark. If so, the number of times the total number of real-time abnormal events of unlicensed vehicles exceeds the group-based unlicensed vehicle benchmark is obtained. It is determined whether the number of times ...

[0045] Specifically, the anomaly responsibility attribution module 4 includes: The abnormal road segment identification module 41 is used to acquire historical road segment monitoring data of the inspected road segment within a preset period, calculate the historical monitoring rate of the road segment based on the historical monitoring data, and input the historical monitoring rate of the road segment into a first road segment formula for calculation to obtain the road segment benchmark. The first road segment formula is: ; in, This represents the road segment baseline for inspected road segment j. This represents the average historical monitoring rate of inspection segment j. This represents the third preset coefficient. The standard deviation of the historical monitoring rate of inspected road segment j; The real-time monitoring rate of the road segment is compared with the road segment benchmark to determine whether the real-time monitoring rate of the road segment is lower than the road segment benchmark. If so, the inspected road segment is marked as an abnormal road segment to obtain the current abnormal road segment.

[0046] Specifically, the anomaly responsibility attribution module is as follows: Simultaneously, the individual real-time monitoring rate of all parking attendants in charge of the current abnormal road section is obtained, and the individual real-time monitoring rates are summarized to generate the total individual real-time monitoring rate; Calculate the difference between the individual real-time total monitoring rate and the road segment real-time monitoring rate, and determine whether the difference exceeds a first critical threshold. If so, assign the abnormal responsibility of the current abnormal road segment to the parking attendant with the lowest individual real-time monitoring rate, generating an abnormal responsibility attribution result for individual responsibility. If not, assign the abnormal responsibility of the current abnormal road segment to all parking attendants in charge of the current abnormal road segment, generating an abnormal responsibility attribution result for group responsibility.

[0047] Since the systems / devices described in the above embodiments of the present invention are systems / devices used to implement the methods of the above embodiments of the present invention, those skilled in the art can understand the specific structure and modifications of the systems / devices based on the methods described in the above embodiments of the present invention, and therefore will not be repeated here. All systems / devices used in the methods of the above embodiments of the present invention fall within the scope of protection of the present invention.

[0048] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention 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.

[0049] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions.

[0050] It should be noted that any reference numerals placed between parentheses in the claims should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In claims that enumerate several means, several of these means may be embodied by the same hardware. The use of the terms first, second, third, etc., is merely for convenience of expression and does not indicate any order. These terms can be understood as part of the component names.

[0051] Furthermore, it should be noted that in the description of this specification, the terms "one embodiment," "some embodiments," "embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0052] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the claims should be interpreted to include both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0053] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, then this invention should also include these modifications and variations.

Claims

1. A method for detecting anomalies during berth maintenance worker inspections for performance management, characterized in that, include: Real-time parking space status data is collected, and the data is divided and aggregated according to the parking attendant management rules to obtain the individual real-time parking space dataset under the jurisdiction of each parking attendant. The abnormal parking space events with a parking duration of 0 and the abnormal parking space events without license plates in the individual real-time parking space dataset under the jurisdiction of each parking attendant are grouped and summarized to generate the corresponding total number of real-time abnormal events for free parking and the total number of real-time abnormal events for vehicles without license plates for each parking attendant. The total number of real-time abnormal events for free parking for each parking attendant is compared with the personalized free parking benchmark constructed based on the historical jurisdiction data of each parking attendant to generate an abnormal inspection efficiency result for each parking attendant. At the same time, the total number of real-time abnormal events for unlicensed vehicles for each parking attendant is compared with the grouped unlicensed vehicle benchmark constructed based on the total number of real-time abnormal events for unlicensed vehicles for all parking attendants in the same jurisdiction to generate an abnormal inspection operation result for each parking attendant. Collect real-time road segment monitoring data of the patrol section, calculate the real-time road segment monitoring rate based on the real-time road segment monitoring data, obtain the current abnormal road segment based on the real-time road segment monitoring rate, and at the same time obtain the individual real-time monitoring rate of the parking attendant in charge of the current abnormal road segment. Based on the real-time road segment monitoring rate and the individual real-time monitoring rate, assign the responsibility for the current abnormal road segment and generate the abnormal responsibility assignment result. Based on the results of the attribution of responsibility for the anomalies, the results of the abnormal inspection efficiency, and the results of the abnormal inspection operations, the performance of the berth rangers is evaluated, and the performance evaluation results are generated.

2. The method for detecting anomalies in berth maintenance worker inspections as described in claim 1, characterized in that, The process of comparing the total number of real-time abnormal events related to free parking for each parking attendant with the personalized free parking benchmark constructed based on each attendant's historical jurisdiction data to generate abnormal inspection efficiency results for each attendant includes: Obtain the historical management data of each parking attendant within a preset period. Based on the historical management data, calculate the total number of historical abnormal events related to free parking for each parking attendant. Input the total number of historical abnormal events related to free parking for each parking attendant into a first personalized formula for calculation, and obtain the corresponding personalized free parking benchmark for each parking attendant. The first personalized formula is: ； in, This represents the personalized baseline of the parking attendant i. This represents the average number of abnormal events in the free parking history of parking attendant i. This represents the first preset coefficient. The standard deviation of the total number of abnormal events in the free parking history of parking attendant i; The total number of real-time abnormal events for free parking for each parking attendant is compared with the corresponding personalized free parking benchmark. It is determined whether the total number of real-time abnormal events for free parking exceeds the personalized free parking benchmark. If so, the number of times the total number of real-time abnormal events for free parking exceeds the personalized free parking benchmark is obtained. It is determined whether the number of times the free parking exceeds the first lower limit threshold is greater than the first lower limit threshold. If so, the inspection efficiency of the parking attendant is marked as suspected abnormal, so as to obtain the parking attendants suspected of being abnormal. The total number of real-time abnormal events for free parking corresponding to the suspected abnormal parking attendant is compared with the group-based free parking benchmark constructed based on the total number of real-time abnormal events for free parking of all parking attendants in the same jurisdiction area. It is determined whether the total number of real-time abnormal events for free parking corresponding to the suspected abnormal parking attendant exceeds the group-based free parking benchmark. If so, the inspection efficiency corresponding to the suspected abnormal parking attendant is marked as confirmed abnormal, the confirmed abnormal parking attendant is obtained and the corresponding inspection efficiency abnormal result is generated. If not, the inspection efficiency corresponding to the suspected abnormal parking attendant is corrected to normal. The comparison of the total number of real-time abnormal free parking events corresponding to suspected abnormal parking attendants with the grouped free parking benchmark constructed based on the total number of real-time abnormal free parking events of all parking attendants in the same jurisdiction includes: Obtain the jurisdiction area of ​​each parking attendant, and summarize the total number of real-time abnormal events of free parking for all parking attendants in the same jurisdiction area to generate the total number of real-time abnormal events of free parking in each area for each parking attendant. The total number of real-time no-parking exception events for each parking attendant's area is input into the first grouping formula for calculation, resulting in the grouped no-parking benchmark for each attendant. The first grouping formula is as follows: ； in, This indicates the group-based exemption criteria for parking attendant i. This represents the average number of real-time no-parking exception events in the area for parking attendant i. This represents the second preset coefficient. This represents the standard deviation of the total number of real-time no-parking exceptions in the area for parking attendant i.

3. The method for detecting anomalies in berth maintenance worker inspections as described in claim 1, characterized in that, Simultaneously, the total number of real-time abnormal events involving unlicensed vehicles for each parking attendant is compared with a grouped unlicensed vehicle baseline constructed based on the total number of real-time abnormal events involving unlicensed vehicles for all parking attendants within the same jurisdiction. This generates abnormal inspection operation results for each parking attendant, including: Obtain the jurisdiction area of ​​each parking attendant, and summarize the total number of real-time abnormal events of unlicensed vehicles of all parking attendants in the same jurisdiction area to generate the total number of real-time abnormal events of unlicensed vehicles in each parking attendant's area. The total number of unlicensed incidents in each parking attendant's area in real time is input into the second grouping formula for calculation, resulting in the grouped unlicensed baseline for each parking attendant. The second grouping formula is as follows: ； in, This represents the group of unlicensed berth attendants i. This represents the average number of real-time unlicensed incidents in the area where parking attendant i resides. This represents the third preset coefficient. The standard deviation of the total number of real-time unlicensed incidents in the area of ​​parking attendant i; The total number of real-time abnormal events of unlicensed vehicles for each parking attendant is compared with the corresponding group-based unlicensed vehicle benchmark. It is determined whether the total number of real-time abnormal events of unlicensed vehicles exceeds the group-based unlicensed vehicle benchmark. If so, the number of times the total number of real-time abnormal events of unlicensed vehicles exceeds the group-based unlicensed vehicle benchmark is obtained. It is determined whether the number of times ...

4. The method for detecting anomalies in berth maintenance worker inspections as described in claim 1, characterized in that, The method of obtaining the current abnormal road segments based on the real-time monitoring rate of the road segments includes: Obtain historical road segment monitoring data for the inspected road segment within a preset period, calculate the historical road segment monitoring rate based on the historical road segment monitoring data, input the historical road segment monitoring rate into a first road segment formula for calculation, and obtain the road segment benchmark. The first road segment formula is: ； in, This represents the road segment baseline for inspected road segment j. This represents the average historical monitoring rate of inspection segment j. This represents the third preset coefficient. The standard deviation of the historical monitoring rate of inspected road segment j; The real-time monitoring rate of the road segment is compared with the road segment benchmark to determine whether the real-time monitoring rate of the road segment is lower than the road segment benchmark. If so, the inspected road segment is marked as an abnormal road segment to obtain the current abnormal road segment.

5. The method for detecting anomalies in berth maintenance worker inspections as described in claim 1, characterized in that, The process of simultaneously obtaining the individual real-time monitoring rate of the parking attendant in charge of the current abnormal road segment, and assigning responsibility for the current abnormal road segment based on the road segment real-time monitoring rate and the individual real-time monitoring rate, and generating an anomaly responsibility assignment result includes: Simultaneously, the individual real-time monitoring rate of all parking attendants in charge of the current abnormal road section is obtained, and the individual real-time monitoring rates are summarized to generate the total individual real-time monitoring rate; Calculate the difference between the individual real-time total monitoring rate and the road segment real-time monitoring rate, and determine whether the difference exceeds a first critical threshold. If so, assign the abnormal responsibility of the current abnormal road segment to the parking attendant with the lowest individual real-time monitoring rate, generating an abnormal responsibility attribution result for individual responsibility. If not, assign the abnormal responsibility of the current abnormal road segment to all parking attendants in charge of the current abnormal road segment, generating an abnormal responsibility attribution result for group responsibility.

6. A system for detecting anomalies in berth maintenance worker inspections for performance management, characterized in that: include: The abnormal event grouping module is used to collect real-time parking space status data, divide and aggregate the real-time parking space status data according to the parking attendant management rules, so as to obtain the individual real-time parking space dataset under the jurisdiction of each parking attendant. The module groups and summarizes the free parking abnormal parking space events with a parking duration of 0 and the license plate vehicle abnormal parking space events in the individual real-time parking space dataset under the jurisdiction of each parking attendant, and generates the corresponding total number of free parking real-time abnormal events and the total number of license plate vehicle real-time abnormal events for each parking attendant. The inspection anomaly detection module is used to compare the total number of real-time abnormal events of free parking for each parking attendant with the personalized free parking benchmark constructed based on the historical jurisdiction data of each parking attendant, and generate an abnormal inspection efficiency result for each parking attendant. At the same time, it compares the total number of real-time abnormal events of unlicensed vehicles for each parking attendant with the grouped unlicensed vehicle benchmark constructed based on the total number of real-time abnormal events of unlicensed vehicles of all parking attendants in the same jurisdiction, and generates an abnormal inspection operation result for each parking attendant. The anomaly responsibility attribution module is used to collect real-time road segment monitoring data of the inspected road segments, calculate the real-time monitoring rate of the road segments based on the real-time monitoring data, obtain the current abnormal road segments based on the real-time monitoring rate of the road segments, and obtain the individual real-time monitoring rate of the parking attendant in charge of the current abnormal road segments. Based on the real-time monitoring rate of the road segments and the individual real-time monitoring rate, the anomaly responsibility attribution is assigned to the current abnormal road segments, and an anomaly responsibility attribution result is generated. The performance evaluation module is used to evaluate the performance of the berth manager based on the results of the abnormal responsibility attribution, the abnormal inspection efficiency, and the abnormal inspection operation, and to generate performance evaluation results.

7. The berth maintenance worker inspection anomaly detection system for performance management as described in claim 6, characterized in that, The inspection anomaly detection module includes: The inspection efficiency anomaly module is used to acquire historical management data for each parking attendant within a preset period, calculate the total number of historical anomalies in free parking for each attendant based on the historical management data, and input the total number of historical anomalies in free parking for each attendant into a first personalized formula for calculation to obtain the corresponding personalized free parking benchmark for each attendant. The first personalized formula is: ； in, This represents the personalized baseline of the parking attendant i. This represents the average number of abnormal events in the free parking history of parking attendant i. This represents the first preset coefficient. The standard deviation of the total number of abnormal events in the free parking history of parking attendant i; The total number of real-time abnormal events for free parking for each parking attendant is compared with the corresponding personalized free parking benchmark. It is determined whether the total number of real-time abnormal events for free parking exceeds the personalized free parking benchmark. If so, the number of times the total number of real-time abnormal events for free parking exceeds the personalized free parking benchmark is obtained. It is determined whether the number of times the free parking exceeds the first lower limit threshold is greater than the first lower limit threshold. If so, the inspection efficiency of the parking attendant is marked as suspected abnormal, so as to obtain the parking attendants suspected of being abnormal. The total number of real-time abnormal events for free parking corresponding to the suspected abnormal parking attendant is compared with the group-based free parking benchmark constructed based on the total number of real-time abnormal events for free parking of all parking attendants in the same jurisdiction area. It is determined whether the total number of real-time abnormal events for free parking corresponding to the suspected abnormal parking attendant exceeds the group-based free parking benchmark. If so, the inspection efficiency corresponding to the suspected abnormal parking attendant is marked as confirmed abnormal, the confirmed abnormal parking attendant is obtained and the corresponding inspection efficiency abnormal result is generated. If not, the inspection efficiency corresponding to the suspected abnormal parking attendant is corrected to normal. The comparison of the total number of real-time abnormal free parking events corresponding to suspected abnormal parking attendants with the grouped free parking benchmark constructed based on the total number of real-time abnormal free parking events of all parking attendants in the same jurisdiction includes: Obtain the jurisdiction area of ​​each parking attendant, and summarize the total number of real-time abnormal events of free parking for all parking attendants in the same jurisdiction area to generate the total number of real-time abnormal events of free parking in each area for each parking attendant. The total number of real-time no-parking exception events for each parking attendant's area is input into the first grouping formula for calculation, resulting in the grouped no-parking benchmark for each attendant. The first grouping formula is as follows: ； in, This indicates the group-based exemption criteria for parking attendant i. This represents the average number of real-time no-parking exception events in the area for parking attendant i. This represents the second preset coefficient. This represents the standard deviation of the total number of real-time no-parking exceptions in the area for parking attendant i.

8. The berth maintenance worker inspection anomaly detection system for performance management as described in claim 6, characterized in that, The inspection anomaly detection module includes: The inspection operation anomaly module is used to obtain the jurisdiction area of ​​each parking manager and summarize the total number of real-time anomaly events of unlicensed vehicles of all parking managers in the same jurisdiction area to generate the total number of real-time unlicensed vehicle anomaly events of each parking manager's area. The total number of unlicensed incidents in each parking attendant's area in real time is input into the second grouping formula for calculation, resulting in the grouped unlicensed baseline for each parking attendant. The second grouping formula is as follows: ； in, This represents the group of unlicensed berth attendants i. This represents the average number of real-time unlicensed incidents in the area where parking attendant i resides. This represents the third preset coefficient. The standard deviation of the total number of real-time unlicensed incidents in the area of ​​parking attendant i; The total number of real-time abnormal events of unlicensed vehicles for each parking attendant is compared with the corresponding group-based unlicensed vehicle benchmark. It is determined whether the total number of real-time abnormal events of unlicensed vehicles exceeds the group-based unlicensed vehicle benchmark. If so, the number of times the total number of real-time abnormal events of unlicensed vehicles exceeds the group-based unlicensed vehicle benchmark is obtained. It is determined whether the number of times ...

9. A berth maintenance worker inspection anomaly detection system for performance management as described in claim 6, characterized in that, The anomaly attribution module includes: The abnormal road segment identification module is used to acquire historical road segment monitoring data of the inspected road segment within a preset period, calculate the historical monitoring rate of the road segment based on the historical monitoring data, and input the historical monitoring rate of the road segment into a first road segment formula for calculation to obtain the road segment benchmark. The first road segment formula is: ； in, This represents the road segment baseline for inspected road segment j. This represents the average historical monitoring rate of inspection segment j. This represents the third preset coefficient. The standard deviation of the historical monitoring rate of inspected road segment j; The real-time monitoring rate of the road segment is compared with the road segment benchmark to determine whether the real-time monitoring rate of the road segment is lower than the road segment benchmark. If so, the inspected road segment is marked as an abnormal road segment to obtain the current abnormal road segment.

10. A berth maintenance worker inspection anomaly detection system for performance management as described in claim 6, characterized in that, The specific module for assigning responsibility for anomalies is as follows: Simultaneously, the individual real-time monitoring rate of all parking attendants in charge of the current abnormal road section is obtained, and the individual real-time monitoring rates are summarized to generate the total individual real-time monitoring rate; Calculate the difference between the individual real-time total monitoring rate and the road segment real-time monitoring rate, and determine whether the difference exceeds a first critical threshold. If so, assign the abnormal responsibility of the current abnormal road segment to the parking attendant with the lowest individual real-time monitoring rate, generating an abnormal responsibility attribution result for individual responsibility. If not, assign the abnormal responsibility of the current abnormal road segment to all parking attendants in charge of the current abnormal road segment, generating an abnormal responsibility attribution result for group responsibility.

Images