A parking management system for intelligent parking management system performance evaluation method

Abstract

The application relates to a parking attendant performance evaluation method for a smart parking management system and belongs to the technical field of parking management. In the method, the historical difference value between the historical payment time and the corresponding historical departure time in all historical parking payment orders is calculated, a time difference data set composed of all the historical difference values is input into a statistical analysis model for time distribution analysis, a time evaluation window with different correlation strengths with the parking attendant is generated according to the output distribution inflection point and a preset business logic, a corresponding weight coefficient is allocated to each time evaluation window through a dynamic weight calculator, the current difference value between the order payment time and the vehicle departure time in all parking performance attribution records of the parking attendant is matched with the time evaluation window, so that the weight coefficient corresponding to each parking performance attribution record is obtained, and the performance evaluation result of the parking attendant is generated in combination with multidimensional indexes. The application guarantees the fairness of the performance evaluation of the parking attendant and improves the working enthusiasm of the parking attendant.

Description

Technical Field

[0001] This invention relates to the field of parking management technology, and in particular to a method for evaluating the performance of parking attendants in a smart parking management system. Background Technology

[0002] Intelligent parking management systems are an important means to optimize urban static traffic management and improve parking space utilization efficiency. As key implementers of intelligent parking management systems, the fairness and accuracy of performance evaluations of parking attendants directly affect their work enthusiasm and the operational effectiveness of the intelligent parking management system.

[0003] Currently, the performance evaluation of parking attendants mainly relies on static, linear data association technology based on license plate numbers and timestamps. This technology matches payment records with entry and exit records and uses static attribution rules, simply attributing pre-departure payment records to the entry supervisor and post-departure payment records to the exit supervisor. Therefore, it cannot effectively distinguish between driver-initiated payments and payments facilitated by effective guidance and intervention from parking attendants, resulting in an extremely low signal-to-noise ratio in the performance evaluation. This fails to accurately reflect the value of the parking attendants' work and negatively impacts their motivation. This also forces operators to introduce extensive manual review for data cleaning and correction, significantly increasing operating costs and introducing unavoidable subjective biases, further undermining the fairness of the performance evaluation and affecting the operational efficiency of the smart parking management system. Summary of the Invention

[0004] The technical problem to be solved by this invention is: to provide a method for evaluating the performance of parking attendants in a smart parking management system, so as to ensure the fairness of the performance evaluation, improve the work enthusiasm of parking attendants and the operation and maintenance efficiency of the smart parking management system.

[0005] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows:

[0006] In a first aspect, the present invention provides a method for evaluating the performance of parking attendants in an intelligent parking management system, comprising:

[0007] The system retrieves the historical payment time and historical departure time of all historical parking payment orders, calculates the historical difference between the historical payment time and the corresponding historical departure time for the same historical parking payment order, and obtains a time difference dataset composed of all historical differences. The time difference dataset is then input into a statistical analysis model for time distribution analysis, outputting the distribution inflection point. Based on the distribution inflection point and preset business logic, time evaluation windows with different correlation strengths with parking attendants are generated, and a dynamic weight calculator is used to assign corresponding weight coefficients to each time evaluation window. The distribution inflection point changes dynamically with all historical parking payment orders.

[0008] Obtain all parking performance attribution records of parking attendants, and calculate the current difference between order payment time and vehicle departure time in each parking performance attribution record. Match the current difference with the time evaluation window to obtain the time evaluation window and corresponding weight coefficient for each parking performance attribution record.

[0009] The weight coefficient corresponding to each parking performance record is integrated with multi-dimensional evaluation indicators to generate the performance evaluation results of the parking attendant.

[0010] The beneficial effects of this invention are as follows: Time distribution analysis is performed on the time difference dataset, which is composed of the historical differences between all historical payment times and the corresponding historical departure times, to obtain the distribution inflection point. Based on the distribution inflection point and the preset business logic, time evaluation windows with different correlation strengths with parking attendants are generated. This ensures that the time evaluation window is consistent with the actual historical parking payment orders, avoiding the problem of the correlation strength being out of touch with the actual situation. At the same time, it accurately quantifies the correlation between payment behavior and parking attendant work. Moreover, the distribution inflection point changes dynamically with all historical parking payment orders, that is, the time evaluation window is dynamically changing, which improves the accuracy and adaptability of the time evaluation window. Each parking performance record of a parking attendant is matched with a time assessment window. Based on the weight coefficient corresponding to the matched time assessment window, combined with multi-dimensional indicators, the parking attendant's performance evaluation result is generated. This solves the problem of extremely low signal-to-noise ratio in traditional performance evaluation results, ensuring that the performance evaluation result matches the actual work contribution of the parking attendant, guaranteeing the fairness of the performance evaluation result, and improving the work enthusiasm of the parking attendant. Moreover, the entire process is automated through data-driven processes, from historical parking payment orders to time assessment windows and then to the generation of performance evaluation results. There is no need for manual data cleaning and correction, reducing labor costs while improving the operation and maintenance efficiency of the smart parking management system.

[0011] Optionally, the preset business logic is whether the historical payment time is earlier than the historical departure time. The step of inputting the time difference dataset into a statistical analysis model for time distribution analysis, outputting a distribution inflection point, and generating time assessment windows with different correlation strengths with the berth manager based on the distribution inflection point and the preset business logic includes:

[0012] The statistical analysis model evaluates the kernel density of the time difference dataset to obtain a kernel density distribution map, and outputs the distribution inflection point based on the kernel density distribution map.

[0013] The negative time ranges corresponding to the historical differences that are all negative in the time difference dataset are all divided into first time assessment windows that are strongly correlated with the berth manager;

[0014] Simultaneously, using the distribution inflection point as the boundary, the positive time range corresponding to the historical differences in the time difference data that are positive before the distribution inflection point is divided into a second time evaluation window with moderate correlation to the berth manager, and the positive time range corresponding to the historical differences in the time difference data that are positive after the distribution inflection point is divided into a third time evaluation window with weak correlation to the berth manager.

[0015] As described above, the statistical analysis model performs kernel density evaluation on the time difference dataset and outputs the distribution inflection point based on the obtained kernel density distribution map. That is, it outputs the distribution inflection point based on the distribution characteristics of the time difference dataset itself, ensuring that the division of the time assessment window is based on real data rather than subjective experience, reducing human bias. Combined with the preset business logic of whether historical payment time is earlier than historical departure time, a dual judgment of the distribution inflection point and the temporal relationship is formed. This ensures that the division of time assessment windows with different correlation strengths not only conforms to objective laws but also improves accuracy. The multi-layered time assessment window enables refined management of berth managers.

[0016] Optionally, assigning corresponding weight coefficients to each time evaluation window using a dynamic weight calculator includes:

[0017] The dynamic weight calculator assigns a corresponding differentiated weight coefficient to each time evaluation window according to a preset weight allocation strategy. The preset weight allocation strategy is positively correlated with the correlation strength of the time evaluation window.

[0018] As described above, the dynamic weight calculator assigns weight coefficients to the time assessment window according to a preset weight allocation strategy that is positively correlated with the correlation strength of the time assessment window. This ensures that the subsequent performance evaluation results are more objective and better reflect the actual work contributions of the berth rangers. Moreover, it does not use fixed weight coefficients; the flexible and dynamic weight coefficients improve the adaptability of the scenario.

[0019] Optionally, the process of obtaining all parking performance attribution records of parking attendants includes:

[0020] Obtain the historical parking time of all historical parking payment orders and the duty period of the parking attendant. Match the historical parking time of each historical parking payment order with the duty period to determine whether the historical parking time falls within the duty period. If so, the match is successful. Bind the historical parking payment order to the parking attendant and generate a parking performance attribution record belonging to the parking attendant.

[0021] As described above, matching historical parking times with parking attendants' on-duty times ensures that historical parking payment orders are attributed to the actual on-duty parking attendants, avoiding mismatches and omissions in parking performance attribution records, and avoiding subjective human intervention, thus further guaranteeing the accuracy and fairness of subsequent performance evaluation results.

[0022] Optionally, binding the historical parking payment order with the parking attendant includes:

[0023] Determine whether the historical parking time period of the same historical parking payment order falls within the duty period of at least one parking attendant. If so, obtain the vehicle entry time and vehicle exit time of the historical parking time period, and assign the historical parking payment order to the parking attendant whose duty period covers the vehicle entry time in order of priority over vehicle exit time.

[0024] As described above, when the same historical parking payment order falls under the duty periods of multiple parking attendants, it is allocated according to the priority order of vehicle entry time over vehicle exit time. This aligns with the business management logic of parking attendants and ensures the rationality of the attribution of parking performance records.

[0025] Optionally, the multi-dimensional evaluation indicators include comprehensive actual collection rate, comprehensive payment completion rate, and supervision rate. The step of integrating the weight coefficient corresponding to each parking performance attribution record with the multi-dimensional evaluation indicators to generate the parking attendant's performance evaluation results includes:

[0026] The supervision rate is calculated based on all parking performance attribution records of parking attendants. At the same time, all parking performance attribution records of parking attendants are classified according to the corresponding time assessment window, and the basic actual collection rate and basic payment completion rate of each parking performance attribution record under the corresponding time assessment window are calculated separately.

[0027] The basic actual collection rate and the basic payment completion rate are combined with their corresponding weighting coefficients and then summed using a weighted summation formula to obtain the comprehensive actual collection rate and the comprehensive payment completion rate. The weighted summation formula includes a first weighted summation formula and a second weighted summation formula. The first weighted summation formula is as follows:

[0028] ;

[0029] ;

[0030] in, This represents the overall effective recovery rate, where n represents the total number of time assessment windows. This represents the base actual return rate for time assessment window i. This represents the actual amount received in time assessment window i. This represents the amount receivable within the current assessment period j. Represents the weighting coefficient of time evaluation window i;

[0031] The second weighted summation formula is:

[0032] ;

[0033] ;

[0034] in, This represents the overall payment completion rate, where n represents the total number of time assessment windows. This represents the baseline payment completion rate for time assessment window i. This represents the number of paid orders in time evaluation window i. This represents the total number of accounts receivable within the current assessment period j. Represents the weighting coefficient of time evaluation window i;

[0035] The overall actual collection rate, the overall payment completion rate, and the supervision rate are input into the first evaluation formula to generate the performance evaluation results of the parking attendant. The first evaluation formula is:

[0036] ;

[0037] ;

[0038] in, Indicates the performance evaluation results. Indicates the first influence weight. This indicates the second influence weight. Indicates the regulatory rate, This represents the number of supervised orders attributed to the berth manager within the current assessment period j. This represents the total number of all regulatory orders within the current assessment period j. This indicates the third influence weight.

[0039] As described above, the performance evaluation results for parking attendants are generated from three dimensions: profitability, service, and standardization. This avoids the one-sidedness of a single indicator evaluation and makes the performance evaluation results more in line with actual business needs. The multi-dimensional indicators are deeply integrated with the correlation strength through a weighted summation formula, which realizes the binding between the actual work contribution of parking attendants and the performance evaluation results. Furthermore, the comprehensive collection rate and comprehensive payment completion rate are obtained by combining the weight coefficients corresponding to the time evaluation window, so that the performance evaluation results can better reflect the difference between the payment behavior of car owners on their own and the payment behavior facilitated by the effective guidance and intervention of parking attendants.

[0040] Optionally, the multi-dimensional evaluation indicators include the unlicensed vehicle recognition rate and the abnormal parking order rate. The step of inputting the comprehensive actual collection rate, the comprehensive payment completion rate, and the supervision rate into the first evaluation formula to generate the parking attendant's performance evaluation results includes:

[0041] Based on all parking performance records of parking attendants, the unlicensed vehicle identification rate and abnormal parking order rate are calculated. The unlicensed vehicle identification rate, the abnormal parking order rate, and the performance evaluation results are then input into a second evaluation formula to generate the final performance evaluation result for the parking attendant. The second evaluation formula is:

[0042] ;

[0043] ;

[0044] ;

[0045] in, This indicates the final performance evaluation result. Indicates the performance evaluation results. Indicates the recognition rate of vehicles without license plates. This indicates the rate of abnormal order dwell times. This indicates the fourth influence weight. This indicates the fifth influence weight. This indicates the number of orders for vehicles without license plates. This represents the number of supervised orders attributed to the parking attendant within the current assessment period j. This indicates the number of orders that were abnormally delayed.

[0046] As described above, the final performance evaluation results incorporated license plate recognition rate and abnormal stay order rate, supplementing indicators for special scenarios and achieving a comprehensive assessment of the parking attendants' routine and challenging abilities. Attached Figure Description

[0047] Figure 1 A flowchart illustrating a method for evaluating the performance of parking attendants in a smart parking management system, as provided in this embodiment;

[0048] Figure 2 This is a schematic diagram of the overall process of a performance evaluation method for parking attendants in a smart parking management system provided in this embodiment. Detailed Implementation

[0049] 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.

[0050] Example 1

[0051] Please refer to Figures 1 to 2 This invention provides a method for evaluating the performance of parking attendants in a smart parking management system, comprising the following steps:

[0052] S1. Obtain the historical payment time and historical departure time of all historical parking payment orders, and calculate the historical difference between the historical payment time and the corresponding historical departure time in the same historical parking payment order to obtain a time difference dataset composed of all historical differences. Input the time difference dataset into a statistical analysis model for time distribution analysis, output the distribution inflection point, generate time evaluation windows with different correlation strengths with parking attendants based on the distribution inflection point and preset business logic, and assign corresponding weight coefficients to each time evaluation window through a dynamic weight calculator, wherein the distribution inflection point changes dynamically with all historical parking payment orders;

[0053] In this embodiment, as Figure 2 As shown, the system retrieves the historical payment time and historical departure time of all historical parking payment orders. These orders are obtained by accessing historical parking data from multiple heterogeneous data sources, and only those containing complete historical payment and departure times are selected, excluding those with missing time information. The system then calculates the historical difference between the historical payment time and the corresponding historical departure time for each historical parking payment order, obtaining time difference data. All time difference data are aggregated to form a time difference dataset. This dataset is input into a statistical analysis model for time distribution analysis, outputting a distribution inflection point. This inflection point dynamically changes with all historical parking payment orders; that is, when historical parking payment orders change, the inflection point also changes dynamically. Based on the distribution inflection point and preset business logic, time evaluation windows with different correlation strengths with parking attendants are generated. This quantifies the correlation between payment behavior and parking attendant work, and a dynamic weight calculator assigns corresponding weight coefficients to each time evaluation window.

[0054] At this point, the preset business logic in step S1 is whether the historical payment time is earlier than the historical departure time. The step of inputting the time difference dataset into a statistical analysis model for time distribution analysis, outputting a distribution inflection point, and generating a time assessment window with different correlation strengths with the berth manager based on the distribution inflection point and the preset business logic includes:

[0055] S11. The statistical analysis model evaluates the kernel density of the time difference dataset to obtain a kernel density distribution map, and outputs the distribution inflection point based on the kernel density distribution map.

[0056] S12. Divide the negative time ranges corresponding to the historical differences in the time difference data that are all negative into first time assessment windows that are strongly correlated with the berth manager.

[0057] S13. Simultaneously, taking the distribution inflection point as the boundary, the positive time range corresponding to the historical differences in the time difference data that are positive before the distribution inflection point is divided into a second time evaluation window with moderate correlation to the berth manager, and the positive time range corresponding to the historical differences in the time difference data that are positive after the distribution inflection point is divided into a third time evaluation window with weak correlation to the berth manager.

[0058] In this embodiment, as Figure 2 As shown, the statistical analysis model evaluates the kernel density of the time difference dataset to obtain a kernel density distribution map. Based on the kernel density distribution map, it outputs distribution inflection points, using the natural boundaries of kernel density abrupt changes in the map as the distribution inflection points. A kernel density abrupt change refers to a kernel density difference exceeding a preset density threshold. Since the time difference dataset consists of all historical differences, which are obtained based on historical payment and departure times, historical differences can be positive or negative. The negative time range corresponding to negative historical differences is defined as the first time assessment window strongly correlated with the berth manager. That is, the time range where historical payment time is earlier than historical departure time is defined as the first time assessment window strongly correlated with the berth manager. This means that payment behavior within the first time assessment window is considered strongly correlated with the berth manager's guidance and intervention. The negative time range is used to distinguish it from the positive time range in step S13; in reality, both refer to the corresponding time ranges. The positive time range corresponding to historical differences that are positive before the distribution inflection point is divided into a second time assessment window with moderate correlation to the berth manager. The positive time range corresponding to historical differences that are positive after the distribution inflection point is divided into a third time assessment window with weak correlation to the berth manager. That is, the case where the historical payment time is later than the historical departure time is further divided into time assessment windows with the distribution inflection point as the boundary.

[0059] Meanwhile, if there are multiple distribution inflection points, the time evaluation window is divided sequentially by the first, second, and third distribution inflection points, and the division is carried out in accordance with the principle of decreasing correlation.

[0060] At this point, the step S1, which involves assigning corresponding weight coefficients to each time evaluation window using a dynamic weight calculator, includes:

[0061] S14. The dynamic weight calculator assigns a corresponding differentiated weight coefficient to each time evaluation window according to a preset weight allocation strategy. The preset weight allocation strategy is positively correlated with the correlation strength of the time evaluation window.

[0062] In this embodiment, as Figure 2 As shown, the dynamic weight calculator assigns a corresponding differentiated weight coefficient to each time evaluation window according to a preset weight allocation strategy. That is, the weight coefficient corresponding to each time evaluation window is not the same, and the preset weight allocation strategy is positively correlated with the correlation strength of the time evaluation window. In other words, the stronger the correlation strength of the time evaluation window, the higher its corresponding weight coefficient, and vice versa.

[0063] S2. Obtain all parking performance attribution records of parking attendants, and calculate the current difference between order payment time and vehicle departure time in each parking performance attribution record. Match the current difference with the time evaluation window to obtain the time evaluation window and corresponding weight coefficient for each parking performance attribution record.

[0064] In this embodiment, as Figure 2 As shown, all parking performance attribution records of parking attendants are obtained. The parking performance attribution records include order payment time and vehicle departure time. The current difference between the two is calculated and matched with the time evaluation window obtained in step S1 to obtain the corresponding time evaluation window and corresponding weight coefficient for each parking performance attribution record.

[0065] At this point, before obtaining all parking performance attribution records of parking attendants in step S2, the following is included:

[0066] S21. Obtain the historical parking time and the duty period of all historical parking payment orders. Match the historical parking time of each historical parking payment order with the duty period. Determine whether the historical parking time falls within the duty period. If so, the match is successful. Bind the historical parking payment order to the parking manager and generate a parking performance attribution record belonging to the parking manager.

[0067] In this embodiment, as Figure 2As shown, considering the reliance on area division and manual registration to bind historical parking payment orders with parking attendants, issues such as historical parking payment order A being located in area a but actually processed by a parking attendant in area b, or cross-area parking, can easily arise. Therefore, parking performance records are assigned based on the duty period. The historical parking time period of each historical parking payment order is matched with the parking attendant's duty period. If the historical parking time period falls within the duty period, the match is considered successful, and the successfully matched historical parking payment order is bound to the corresponding parking attendant, generating a parking performance record for the parking attendant. This parking performance record includes, but is not limited to, historical parking payment orders, historical parking time periods, and duty periods.

[0068] At this point, the step S21 of binding the historical parking payment order with the parking attendant includes:

[0069] S211. Determine whether the historical parking time period of the same historical parking payment order falls within the duty period of at least one parking attendant. If so, obtain the vehicle entry time and vehicle exit time of the historical parking time period, and assign the historical parking payment order to the parking attendant whose duty period covers the vehicle entry time in order of priority over vehicle exit time.

[0070] In this embodiment, as Figure 2 As shown, if the historical parking time segment of the same historical parking payment order falls into the duty periods of multiple parking attendants, such as: the vehicle entry time of historical parking time segment C falls into the duty period of parking attendant c, and the vehicle exit time of historical parking time segment C falls into the duty period of parking attendant D, then the historical parking payment order will be assigned to the parking attendant whose duty period covers the vehicle entry time in the priority order of vehicle entry time over vehicle exit time.

[0071] S3. The weight coefficient corresponding to each parking performance attribution record is integrated with the multi-dimensional evaluation indicators to generate the performance evaluation results of the parking attendant.

[0072] In this embodiment, as Figure 2 As shown, the weight coefficient corresponding to each parking performance attribution record is integrated with multi-dimensional evaluation indicators to generate the performance evaluation results of parking attendants. The multi-dimensional evaluation indicators include, but are not limited to, comprehensive actual collection rate, comprehensive payment completion rate, supervision rate, unlicensed vehicle identification rate, and abnormal stay order rate.

[0073] At this point, step S3 includes:

[0074] S31. Calculate the supervision rate based on all parking performance attribution records of parking managers. At the same time, classify all parking performance attribution records of parking managers according to the corresponding time assessment window, and calculate the basic actual collection rate and basic payment completion rate of each parking performance attribution record under the corresponding time assessment window.

[0075] S32. The basic actual collection rate and the basic payment completion rate are combined with their corresponding weighting coefficients and weighted summation formulas to obtain the comprehensive actual collection rate and the comprehensive payment completion rate. The weighted summation formulas include a first weighted summation formula and a second weighted summation formula. The first weighted summation formula is as follows:

[0076] ;

[0077] ;

[0078] in, This represents the overall effective recovery rate, where n represents the total number of time assessment windows. This represents the base actual return rate for time assessment window i. This represents the actual amount received in time assessment window i. This represents the amount receivable within the current assessment period j. Represents the weighting coefficient of time evaluation window i;

[0079] The second weighted summation formula is:

[0080] ;

[0081] ;

[0082] in, This represents the overall payment completion rate, where n represents the total number of time assessment windows. This represents the baseline payment completion rate for time assessment window i. This represents the number of paid orders in time evaluation window i. This represents the total number of accounts receivable within the current assessment period j. Represents the weighting coefficient of time evaluation window i;

[0083] The overall actual collection rate, the overall payment completion rate, and the supervision rate are input into the first evaluation formula to generate the performance evaluation results of the parking attendant. The first evaluation formula is:

[0084] ;

[0085] ;

[0086] in, Indicates the performance evaluation results. Indicates the first influence weight. This indicates the second influence weight. Indicates the regulatory rate, This represents the number of supervised orders attributed to the berth manager within the current assessment period j. This represents the total number of all regulatory orders within the current assessment period j. This indicates the third influence weight.

[0087] In this embodiment, as Figure 2 As shown, the supervision rate is calculated based on all parking performance attribution records of parking attendants. This supervision rate is calculated by comparing the number of supervised orders attributable to parking attendants within the current performance assessment period j with the total number of supervised orders within that period. The total number of supervised orders within the current assessment period j refers to the total number of parking orders within that road segment. All parking performance attribution records of parking attendants are categorized according to their corresponding time assessment windows. The basic actual collection rate and basic payment completion rate for each parking performance attribution record under its corresponding time assessment window are calculated separately. These rates are then combined with their corresponding weighting coefficients using a weighted summation formula to obtain the comprehensive actual collection rate and comprehensive payment completion rate. The basic actual collection rate is obtained by summing the actual collection amounts across all time assessment windows and comparing it to the amount due within the current assessment period j. The basic payment completion rate is obtained by summing the number of paid orders across all time assessment windows and comparing it to the total number of orders due within the current assessment period j. The total number of orders due within the current assessment period j refers to the number of orders within the area managed by the parking attendant that actually generated a due amount. This is not equivalent to the total number of all regulated orders within the current assessment period j. The total number of regulated orders within the current assessment period j includes orders for which no receivables have been generated, such as orders for free parking that do not require payment. The comprehensive actual collection rate and comprehensive payment completion rate are obtained by multiplying the basic actual collection rate and basic payment completion rate under each time assessment window by their corresponding weighting coefficients and then summing the results. The comprehensive actual collection rate, comprehensive payment completion rate, and regulatory rate are then input into the first assessment formula to generate the parking attendant's performance evaluation results, i.e., from three dimensions: profitability, service, and compliance. The first, second, and third influence weights can be designed according to specific circumstances to adapt to different performance evaluation objectives.

[0088] At this point, step S33 includes:

[0089] S331. Calculate the unlicensed vehicle identification rate and abnormal parking order rate based on all parking performance records of the parking attendant. Input the unlicensed vehicle identification rate, the abnormal parking order rate, and the performance evaluation results into the second evaluation formula to generate the final performance evaluation result of the parking attendant. The second evaluation formula is:

[0090] ;

[0091] ;

[0092] ;

[0093] in, This indicates the final performance evaluation result. Indicates the performance evaluation results. Indicates the recognition rate of vehicles without license plates. This indicates the rate of abnormal order dwell times. This indicates the fourth influence weight. This indicates the fifth influence weight. This indicates the number of orders for vehicles without license plates. This represents the number of supervised orders attributed to the parking attendant within the current assessment period j. This indicates the number of orders that were abnormally delayed.

[0094] In this embodiment, as Figure 2 As shown, the unlicensed vehicle recognition rate and abnormal parking order rate are incorporated into the final performance evaluation result of the parking attendant. That is, the parking attendant's performance capability in special scenarios is taken into account. Similarly, the calculation is based on all parking performance attribution records within the current performance evaluation period. The unlicensed vehicle recognition rate, abnormal parking order rate, and the performance evaluation result obtained in step S32 are input into the second evaluation formula to generate the final performance evaluation result of the parking attendant. The unlicensed vehicle recognition rate is obtained by the ratio of the number of unlicensed vehicle orders to the number of supervised orders attributable to the parking attendant within the current evaluation period j. The abnormal parking order rate is obtained by the ratio of the number of abnormal parking orders to the number of supervised orders attributable to the parking attendant within the current evaluation period j.

[0095] In this embodiment, the performance evaluation results will not only show the final score, but also the specific values ​​of comprehensive actual collection rate, comprehensive payment completion rate, supervision rate, unlicensed vehicle identification rate, and abnormal stay order rate, so as to identify the performance shortcomings of the parking attendants and generate targeted training suggestions for the parking attendants based on the performance shortcomings.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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 evaluating the performance of parking attendants in an intelligent parking management system, characterized in that, include: The system retrieves the historical payment time and historical departure time of all historical parking payment orders, calculates the historical difference between the historical payment time and the corresponding historical departure time for the same historical parking payment order, and obtains a time difference dataset composed of all historical differences. The time difference dataset is then input into a statistical analysis model for time distribution analysis, outputting the distribution inflection point. Based on the distribution inflection point and preset business logic, time evaluation windows with different correlation strengths with parking attendants are generated, and a dynamic weight calculator is used to assign corresponding weight coefficients to each time evaluation window. The distribution inflection point changes dynamically with all historical parking payment orders. Obtain all parking performance attribution records of parking attendants, and calculate the current difference between order payment time and vehicle departure time in each parking performance attribution record. Match the current difference with the time evaluation window to obtain the time evaluation window and corresponding weight coefficient for each parking performance attribution record. The weight coefficient corresponding to each parking performance record is integrated with multi-dimensional evaluation indicators to generate the performance evaluation results of the parking attendant. The preset business logic determines whether the historical payment time is earlier than the historical departure time. The step of inputting the time difference dataset into a statistical analysis model for time distribution analysis, outputting a distribution inflection point, and generating time assessment windows with different correlation strengths with the berth manager based on the distribution inflection point and the preset business logic includes: The statistical analysis model evaluates the kernel density of the time difference dataset to obtain a kernel density distribution map, and outputs the distribution inflection point based on the kernel density distribution map. The negative time ranges corresponding to the historical differences that are centrally negative in the time difference data are all divided into the first time assessment window, which is strongly correlated with the berth manager; the payment behavior within the first time assessment window is strongly correlated with the guidance and intervention of the berth manager; Simultaneously, using the distribution inflection point as the boundary, the positive time range corresponding to the historical differences in the time difference data that are positive before the distribution inflection point is divided into a second time evaluation window with moderate correlation to the berth manager, and the positive time range corresponding to the historical differences in the time difference data that are positive after the distribution inflection point is divided into a third time evaluation window with weak correlation to the berth manager.

2. The method for evaluating the performance of parking attendants in a smart parking management system as described in claim 1, characterized in that, The process of assigning corresponding weight coefficients to each time evaluation window using a dynamic weight calculator includes: The dynamic weight calculator assigns a corresponding differentiated weight coefficient to each time evaluation window according to a preset weight allocation strategy. The preset weight allocation strategy is positively correlated with the correlation strength of the time evaluation window.

3. The method for evaluating the performance of parking attendants in a smart parking management system as described in claim 1, characterized in that, Prior to obtaining all parking performance attribution records for parking attendants, the following was included: Obtain the historical parking time of all historical parking payment orders and the duty period of the parking attendant. Match the historical parking time of each historical parking payment order with the duty period to determine whether the historical parking time falls within the duty period. If so, the match is successful. Bind the historical parking payment order to the parking attendant and generate a parking performance attribution record belonging to the parking attendant.

4. The method for evaluating the performance of parking attendants in a smart parking management system as described in claim 3, characterized in that, The step of binding the historical parking payment orders with the parking attendant includes: Determine whether the historical parking time period of the same historical parking payment order falls within the duty period of at least one parking attendant. If so, obtain the vehicle entry time and vehicle exit time of the historical parking time period, and assign the historical parking payment order to the parking attendant whose duty period covers the vehicle entry time in order of priority over vehicle exit time.

5. The method for evaluating the performance of parking attendants in a smart parking management system as described in claim 1, characterized in that, The multi-dimensional evaluation indicators include comprehensive actual collection rate, comprehensive payment completion rate, and supervision rate. The process of integrating the weight coefficients corresponding to each parking performance record with the multi-dimensional evaluation indicators to generate the parking attendant's performance evaluation results includes: The supervision rate is calculated based on all parking performance attribution records of parking attendants. At the same time, all parking performance attribution records of parking attendants are classified according to the corresponding time assessment window, and the basic actual collection rate and basic payment completion rate of each parking performance attribution record under the corresponding time assessment window are calculated separately. The basic actual collection rate and the basic payment completion rate are combined with their corresponding weighting coefficients and then summed using a weighted summation formula to obtain the comprehensive actual collection rate and the comprehensive payment completion rate. The weighted summation formula includes a first weighted summation formula and a second weighted summation formula. The first weighted summation formula is as follows: ； ； in, This represents the overall effective recovery rate, where n represents the total number of time assessment windows. This represents the base actual return rate for time assessment window i. This represents the actual amount received in time assessment window i. This represents the amount receivable within the current assessment period j. Represents the weighting coefficient of time evaluation window i; The second weighted summation formula is: ； ； in, This represents the overall payment completion rate, where n represents the total number of time assessment windows. This represents the baseline payment completion rate for time assessment window i. This represents the number of paid orders in time evaluation window i. This represents the total number of accounts receivable within the current assessment period j. Represents the weighting coefficient of time evaluation window i; The overall actual collection rate, the overall payment completion rate, and the supervision rate are input into the first evaluation formula to generate the performance evaluation results of the parking attendant. The first evaluation formula is: ； ； in, Indicates the performance evaluation results. Indicates the weight of the first influence. This indicates the second influence weight. Indicates the regulatory rate, This represents the number of supervised orders attributed to the berth manager within the current assessment period j. This represents the total number of all regulatory orders within the current assessment period j. This indicates the third influence weight.

6. The method for evaluating the performance of parking attendants in a smart parking management system as described in claim 5, characterized in that, The multi-dimensional evaluation indicators also include the unlicensed vehicle identification rate and the abnormal parking order rate. The process of inputting the comprehensive actual collection rate, the comprehensive payment completion rate, and the supervision rate into the first evaluation formula to generate the parking attendant's performance evaluation results includes: Based on all parking performance records of parking attendants, the unlicensed vehicle identification rate and abnormal parking order rate are calculated. The unlicensed vehicle identification rate, the abnormal parking order rate, and the performance evaluation results are then input into a second evaluation formula to generate the final performance evaluation result for the parking attendant. The second evaluation formula is: ； ； ； in, This indicates the final performance evaluation result. Indicates the performance evaluation results. Indicates the recognition rate of vehicles without license plates. This indicates the rate of abnormal order dwell times. This indicates the fourth influence weight. This indicates the fifth influence weight. This indicates the number of orders for vehicles without license plates. This represents the number of supervised orders attributed to the berth manager within the current assessment period j. This indicates the number of orders that were abnormally delayed.

Images