Vehicle dispatch optimization system and method for a car rental platform

Abstract

The present application relates to the technical field of scheduling optimization, in particular to a car rental platform vehicle scheduling optimization system and method, the system comprises a rental saturation identification module, a scheduling level setting module, a candidate path reconstruction module, a adjustable vehicle screening module and a scheduling path binding module.In the present application, by analyzing the time and geographical data of the car rental order, the accurate determination of the vehicle usage status is realized, and the allocation of the vehicle is optimized, through the continuous monitoring and evaluation of the regional vehicle usage saturation state, the high demand area can be identified, and the vehicle distribution can be adjusted accordingly, to ensure the optimal configuration of resources, according to the actual operation data and scheduling history of the vehicle, the scheduling path is intelligently reconstructed, the empty running time of the vehicle is reduced, the scheduling efficiency is improved, the customer waiting time is shortened, and the operation cost is reduced, by analyzing the urgency of the task, the order with high urgency is processed preferentially, and the timeliness and customer satisfaction of the service are guaranteed.

Description

Technical Field

[0001] This invention relates to the field of scheduling optimization technology, and in particular to a vehicle scheduling optimization system and method for car rental platforms. Background Technology

[0002] The field of scheduling optimization technology involves the efficient matching and allocation of multiple resources, tasks, and constraints, aiming to improve overall system efficiency, reduce resource waste, and lower costs. This area is widely applied in scenarios such as transportation, warehousing and logistics, manufacturing scheduling, and personnel scheduling. Common methods include linear programming, integer programming, heuristic algorithms, multi-objective optimization, graph-based path planning, and reinforcement learning scheduling strategies. In dynamic and complex environments, this technology needs to combine real-time data, constraint update mechanisms, and feedback closed-loop scheduling schemes to support the rapid generation and deployment of optimal or near-optimal decisions.

[0003] The car rental platform vehicle dispatch optimization system refers to a system that uses dispatch optimization methods to orderly dispatch and allocate vehicle resources within the car rental platform. The system's purpose is to automatically generate reasonable vehicle allocation and dispatch routes based on parameters such as user rental needs, geographical distribution, vehicle availability, return time, and vehicle type. This addresses issues such as high vehicle vacancy rates, supply-demand mismatch, and response delays, thereby improving the platform's vehicle utilization rate and service level.

[0004] Traditional dispatching systems suffer from insufficient flexibility and slow response speed when dealing with dynamic changes and complex constraints, especially during peak car rental demand periods. Traditional systems struggle to update vehicle status and customer needs in real time, leading to unreasonable resource allocation, high vehicle empty-running rates, and a lack of refined management in regional vehicle allocation. They are unable to effectively identify and resolve supply and demand imbalances, resulting in vehicle surpluses or shortages, which negatively impact service quality and customer experience. In handling emergency orders, they lack effective forecasting and dispatching mechanisms, resulting in slow system responses that fail to meet customers' demands for rapid response. This affects overall operational efficiency and market competitiveness, limits the performance of the dispatching system under high-pressure environments, and leads to increased operating costs and decreased customer satisfaction. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by proposing a vehicle dispatch optimization system and method for car rental platforms.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a vehicle dispatch optimization system for a car rental platform, the system comprising:

[0007] The rental saturation identification module obtains the order records of the car rental platform, maps the rental duration of each order to the time period, evaluates the saturation status within the time period, and generates a set of regional continuous rental saturation identifiers.

[0008] The scheduling level setting module calls the regional continuous rental saturation identifier set, extracts the regions marked as high-density rental status, obtains the number of available vehicles at each rental station in the region, and calculates the scheduling level of the station by combining the vehicle shortage and the high frequency index value, thus obtaining the regional overload node scheduling level table.

[0009] The candidate path reconstruction module, based on the regional overload node scheduling level table, performs weighted calculation and sorting of the average vehicle scheduling response time and empty driving distance index after standardization, and selects the optimal path for executing scheduling tasks, generating a path transferable vehicle scheduling group.

[0010] The adjustable vehicle filtering module obtains orders marked as high urgency from the task list, extracts the vehicle's previous task completion time, the average of the three most recent call intervals, and the standard deviation of historical response time, and compares them with the maximum response time limit of the order task. If any indicator exceeds the response limit standard, the vehicle number is removed, resulting in a list of vehicles matching high urgency tasks.

[0011] As a further aspect of the present invention, the regional continuous rental saturation identifier set includes a time period vehicle occupancy ratio label, a regional number index, a continuous saturation status marker, and a corresponding time period adjustable vehicle limit. The regional overload node scheduling level table specifically includes a station vehicle shortage value, a historical high occupancy frequency factor, a scheduling level index, and a station number label. The path-transferable vehicle scheduling group includes a transfer node number, a target station path pair, an empty driving distance ratio, and a scheduling response time interval. The high-urgency task matching vehicle list specifically refers to a task number label, a vehicle response interval index, a task response restriction status, and a vehicle scheduling feasibility identifier.

[0012] As a further aspect of the present invention, the rental saturation identification module includes:

[0013] The order time period mapping submodule obtains the order records of the car rental platform, extracts the start and end time of the car rental, the number of the rented vehicle and the geographical area label, maps the duration of each order to the time period and geographical area, and establishes a dual index structure of region and time period to generate a regional time period mapping dataset.

[0014] The occupancy index calculation submodule calls the regional time period mapping dataset, extracts the number of orders and the average usage time of orders in each time period of each region, obtains the vehicle dispatch capacity of the corresponding time period of the region, calculates the occupancy saturation score of the regional time period, and constructs a score structure by region to obtain the regional occupancy score matrix.

[0015] The formula for calculating the occupancy saturation score of the time period in the calculation area is:

[0016]

[0017] Among them, S ij T represents the occupancy saturation score of region i during time period j. ijk Let n be the normalized value of the rental duration of the k-th order within region i and time period j. ij Let C be the total number of orders in region i within time period j. ij R is the normalized value of the vehicle dispatch capacity configured for region i within time period j. ij M is the normalized value of the total amount of scheduled resources for region i in time period j. ij This is the normalized value of the average task resource requirement of region i during time period j;

[0018] The saturation state determination submodule compares each score value with the scheduling load reference threshold set by the platform based on the regional occupancy score matrix. It marks regions and time periods whose score values ​​exceed the reference threshold three times or more consecutively, and merges them into interval labels to generate a set of regional continuous rental saturation identifiers.

[0019] As a further aspect of the present invention, the scheduling level setting module includes:

[0020] The high-density region extraction submodule calls the region continuous rental saturation identifier set, filters the region numbers marked as saturated, establishes a region site mapping index, and generates a high-density region label set;

[0021] The resource gap identification submodule, based on the high-density area label set, extracts the number of available vehicles for each rental station in the corresponding area according to the recorded area number, obtains the minimum number of operating vehicles set by the platform, performs difference calculation, filters out the station numbers with insufficient available vehicles, and calculates their gap value to obtain the vehicle resource gap set.

[0022] The grade weight calculation submodule calls the vehicle resource gap set, extracts the high-density occurrence frequency of the area where the station is located in the most recent three scheduling cycles, performs superimposed weight scoring based on the frequency value and the corresponding gap amount, calculates the scheduling grade index value of the station, constructs the station grade mapping structure, and generates the regional overload node scheduling grade table.

[0023] As a further aspect of the present invention, the formula for the scheduling level index value of the computing station is:

[0024]

[0025] Among them, L x D represents the scheduling level index value of the x-th station. x K represents the frequency of high-density occurrences of the area where the x-th station is located within three scheduling cycles. xzm represents the number of vehicle resource gaps at station x during time period z. x H represents the number of time periods during which the x-th station recorded a gap. x F is the sorting factor for the x-th station in the region. x This represents the number of redundant scheduling failures for the x-th site within the historical period.

[0026] As a further aspect of the present invention, the candidate path reconstruction module includes:

[0027] The priority node extraction submodule, based on the regional overload node scheduling level table, filters the station numbers marked with scheduling level as priority transfer, establishes the transfer target node index, and extracts the adjacent regional range of each target node to generate a set of transferable target nodes.

[0028] The vehicle status calculation submodule extracts the station number, current location, previous return time and current empty driving status of vehicles in adjacent areas based on the set of transferable target nodes. It calculates the driving distance from the current location to the target node and the return interval, and calls the station information for normalization processing to obtain a standardized vehicle status data table.

[0029] The route filtering and sorting submodule, based on the standardized vehicle status data table, performs a weighted calculation and sorting of the two indicators according to the normalized driving distance and normalized response time of the vehicles, and filters the vehicle numbers and corresponding route records that are within the target range in terms of score ranking, thereby generating a route-transferable vehicle dispatch group.

[0030] As a further aspect of the present invention, the adjustable vehicle screening module includes:

[0031] The time limit construction submodule retrieves orders marked with high urgency level from the task list, extracts the creation time and maximum response time limit for each order, combines the two data items into time limit record entries by task number, and generates a task time limit dataset.

[0032] The response index extraction submodule calls the path-transferable vehicle dispatch group to extract the previous task completion time, the average time interval of the three most recent task calls, and the standard deviation of the historical dispatch response time of the corresponding vehicle. It then establishes an index correspondence relationship by vehicle number to obtain a vehicle response performance parameter table.

[0033] The task vehicle screening submodule, based on the task timeliness limit dataset and the vehicle response performance parameter table, compares each of the three indicators of task timeliness and vehicle response one by one, determines whether each indicator is less than the task response limit standard, screens out any vehicle number that exceeds the limit, and marks the scheduling adaptation relationship between the remaining vehicles and the task, thus obtaining a list of vehicles matching high urgency tasks.

[0034] As a further aspect of the present invention, the system further includes:

[0035] The scheduling path binding module matches the vehicle list for high-urgency tasks, matches the path and station information in the path-transferable vehicle scheduling group, reconstructs the vehicle ID, starting station ID, and target path segment in the scheduling instruction structure, and records the task number and scheduling level label in an itemized format to generate task-bound path scheduling information.

[0036] The task-bound path scheduling information includes vehicle instruction structure items, task scheduling number, station path identifier, and scheduling level entry.

[0037] As a further aspect of the present invention, the scheduling path binding module includes:

[0038] The path field matching submodule matches the vehicle list based on the high urgency task, extracts the vehicle number, and matches the corresponding starting station ID and target path segment number in the path transferable vehicle scheduling group. At the same time, it extracts the vehicle ID information, constructs a three-field combination structure, and generates a path field association set.

[0039] The instruction content update submodule calls the path field association set, and according to each group of vehicle field combinations, replaces the corresponding positions in the scheduling instruction structure in the order of vehicle ID, starting station ID, and target path segment, and records the task number corresponding to the replaced field to obtain a structured scheduling instruction set.

[0040] The item format generation submodule extracts the task number and vehicle corresponding scheduling level identifier of each instruction based on the structured scheduling instruction set, integrates them into a parallel structure of task field and scheduling field, reorganizes them into item-style standardized expression content, and generates task-bound path scheduling information.

[0041] A method for optimizing vehicle dispatching on a car rental platform, the method being used to implement the aforementioned vehicle dispatching optimization system for a car rental platform, includes the following steps:

[0042] S1: Obtain the order records of the car rental platform, map the rental duration of each order to the time period, evaluate the saturation status within the time period, and generate a set of regional continuous rental saturation identifiers;

[0043] S2: Call the region continuous rental saturation identifier set, extract the regions marked as high-density rental status, combine the vehicle shortage and high frequency index value, calculate the station scheduling level, and obtain the region overload node scheduling level table;

[0044] S3: Based on the regional overload node scheduling level table, the average vehicle scheduling response time and empty driving distance index are standardized, weighted and sorted to select the optimal path for executing scheduling tasks and generate a path transferable vehicle scheduling group.

[0045] S4: Get the orders marked as high urgency in the task list, extract the vehicle's previous task completion time, the average of the three most recent call intervals and the standard deviation of historical response time, and compare them with the maximum response time limit of the order task. If any indicator is higher than the response limit standard, remove the vehicle number to obtain a list of vehicles matching high urgency tasks.

[0046] S5: Based on the vehicle list matching the high urgency task, reconstruct the vehicle ID, starting station ID, and target path segment in the scheduling instruction structure, and record the task number and scheduling level label in an itemized format to generate task-bound path scheduling information.

[0047] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0048] This invention achieves accurate judgment of vehicle usage status by analyzing the time and geographical data of car rental orders, optimizing vehicle allocation. Through continuous monitoring and evaluation of regional vehicle saturation, high-demand areas can be identified, and vehicle distribution can be adjusted accordingly to ensure optimal resource allocation. Based on actual vehicle operation data and scheduling history, scheduling routes are intelligently reconstructed, reducing vehicle idle time, improving scheduling efficiency, shortening customer waiting time, and lowering operating costs. By analyzing the urgency of tasks, high-urgency orders are prioritized, ensuring service timeliness and customer satisfaction, improving overall scheduling performance, and bringing a dual boost to the car rental platform in terms of economic benefits and customer loyalty. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a system flowchart of the present invention;

[0051] Figure 2 This is a schematic diagram of the system framework of the present invention;

[0052] Figure 3 This is a flowchart of the saturation recognition module of the present invention;

[0053] Figure 4 This is a flowchart of the scheduling level setting module of the present invention;

[0054] Figure 5 This is a flowchart of the candidate path reconstruction module of the present invention;

[0055] Figure 6 This is a flowchart of the adjustable vehicle screening module of the present invention;

[0056] Figure 7 This is a flowchart of the scheduling path binding module of the present invention;

[0057] Figure 8 This is a schematic diagram of the method steps of the present invention. Detailed Implementation

[0058] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0059] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0060] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, their intended meanings are consistent. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, their intended meanings are consistent.

[0061] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0062] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0063] Please see Figure 1 This invention provides a technical solution: a vehicle dispatch optimization system for a car rental platform, the system comprising:

[0064] The rental saturation identification module obtains order records from the car rental platform, extracts the rental start and end time, the rented vehicle number and geographical area label, divides the rental time of the order into time periods according to the region, maps the rental duration of each order to the time period, and cross-aggregates statistics by region and time period. It calculates the vehicle occupancy saturation score by using the ratio of the average usage duration to the vehicle dispatch capacity within the time period. The saturation status within the time period is evaluated by the occupancy saturation score, and a set of regional continuous rental saturation identifiers is generated.

[0065] Average usage time refers to the sum of the rental time of all orders within a unit time period divided by the number of orders; vehicle dispatch capacity refers to the maximum number of vehicles that the platform can support dispatching in this area and time period. This data comes from the platform's vehicle distribution and dispatch system capacity settings; the ratio of the two reflects the vehicle occupancy rate during this time period.

[0066] The scheduling level setting module calls the area continuous rental saturation identifier set, extracts the areas marked as high-density rental status, obtains the number of available vehicles at each rental station in the area, and compares it with the minimum number of operating vehicles. If it is less than the standard, the station number is recorded and the number of vehicles in short supply is extracted. At the same time, the high occupancy frequency of the area in the past three scheduling cycles is counted. Combining the vehicle shortage and the high frequency index value, the scheduling level of the station is calculated by setting weights, and the scheduling level table of overloaded nodes in the area is obtained.

[0067] Minimum number of operating vehicles refers to the minimum vehicle configuration standard set by the platform to ensure service continuity, which is generally set based on the daily average rental frequency and user density; High occupancy frequency index value refers to the number of times an area is in a high occupancy state within a unit period, which is usually expressed as the statistical frequency within a sliding time window.

[0068] The candidate path reconstruction module is based on the regional overload node scheduling level table. According to the station number marked as the priority transfer node, it extracts the current station number and vehicle status information of the vehicle in the adjacent area, obtains the current driving distance from the vehicle's current location to the target node, the current empty driving status of the vehicle, and the previous return time, calculates the average scheduling response time and empty driving distance index, and performs weighted calculation and sorting after standardization of the average scheduling response time and empty driving distance index to screen the optimal path for executing scheduling tasks and generate a path transferable vehicle scheduling group.

[0069] Average dispatch response time refers to the average time required for a vehicle of this type to complete an instruction and reach the dispatch target point on the platform, which is statistically derived from historical dispatch records; the empty driving distance index is the ratio of the distance between the vehicle's current location and the dispatch target station to the maximum allowable empty driving distance of the platform, reflecting the risk of resource waste in vehicle dispatch.

[0070] The adjustable vehicle filtering module obtains orders marked as high urgency from the task list, reads the creation time and maximum response time limit to form a time limit data group, calls the transferable vehicle scheduling group, extracts the vehicle's previous task completion time, the average of the three most recent call intervals and the standard deviation of historical response time, and compares them with the maximum response time limit of the order task. If any indicator is higher than the response limit standard, the vehicle number is removed to obtain a list of vehicles matching high urgency tasks.

[0071] The maximum response time limit is the longest tolerable time from the creation of the task to the start of the scheduling operation, which is usually defined by the user's car rental reservation time and the platform's service response agreement.

[0072] The scheduling path binding module matches the vehicle list based on high-urgency tasks, matches the path and station information in the path-transferable vehicle scheduling group, reconstructs the vehicle ID, starting station ID, and target path segment in the scheduling instruction structure, and records the task number and scheduling level label in an itemized format to generate task-bound path scheduling information.

[0073] The regional continuous rental saturation identifier set includes a time period vehicle occupancy ratio label, a regional number index, a continuous saturation status marker, and the corresponding time period adjustable vehicle limit. The regional overload node scheduling level table specifically includes the station vehicle shortage value, historical high occupancy frequency factor, scheduling level index, and station number label. The route-transferable vehicle scheduling group includes the transfer node number, target station path pair, empty driving distance ratio, and scheduling response time range. The high urgency task matching vehicle list specifically refers to the task number label, vehicle response range index, task response restriction status, and vehicle scheduling feasibility identifier. The task-bound path scheduling information includes vehicle instruction structure items, task scheduling number, station path identifier, and scheduling level entry.

[0074] Please see Figure 2 and Figure 3 The rental saturation identification module includes an order time period mapping submodule, an occupancy index calculation submodule, and a saturation state determination submodule;

[0075] The order time period mapping submodule obtains the order records of the car rental platform, extracts the start and end time of the car rental, the number of the rented vehicle and the geographical area label, maps the duration of each order to the time period and geographical area, and establishes a dual index structure of region and time period to generate a regional time period mapping dataset.

[0076] After obtaining the order records from the car rental platform, the start and end times of each order are extracted. The rental duration for each order is calculated by the difference between these two times. For example, if order A starts at 8:00 AM on July 1, 2024, and ends at 6:00 PM on July 1, the rental duration is 10 hours. The vehicle ID for each order is then extracted to associate it with specific vehicle usage. The location of vehicle usage is spatially categorized based on the geographic region tag associated with each order. Finally, the duration of all orders is divided into specific time periods at an hourly granularity to form a time-region aggregated statistical unit. If order A is located in region X, its 10-hour duration is distributed within the time period from 8:00 AM to 6:00 PM on July 1, and is marked within that region. Based on this, a dual index structure of region and time period is established. This structure uses the region number and time period number as index keys, summarizes all order IDs under this index and their corresponding rental duration information, and stores them in a two-level structure table. At the same time, the number of orders in each time period in this structure is counted. For example, in region X, there are 5 orders mapped in the time period from 8:00 to 9:00 on July 1, 2024, with a total time of 5.3 hours. Then the total rental time in region X for this time period is 5.3 hours. The statistical structure adopts a two-dimensional table form, with each row representing a different region and each column corresponding to the time period number. The corresponding cell is filled with the total order duration value of the region for that time period, and the relevant vehicle number and order ID are retained for subsequent processing. Combining the above operation steps, a region time period mapping dataset is generated.

[0077] The occupancy index calculation submodule calls the regional time period mapping dataset, extracts the number of orders and the average usage time of orders in each time period of each region, obtains the vehicle dispatch capacity of the corresponding time period of the region, calculates the occupancy saturation score of the regional time period, and combines and constructs the score structure by region to obtain the regional occupancy score matrix.

[0078] The formula for calculating the occupancy saturation score for a given time period is:

[0079]

[0080] Among them, S ij T represents the occupancy saturation score of region i during time period j. ijk Let n be the normalized value of the rental duration of the k-th order within region i and time period j. ij Let C be the total number of orders in region i within time period j. ij R is the normalized value of the vehicle dispatch capacity configured for region i within time period j. ij M is the normalized value of the total amount of scheduled resources for region i in time period j. ij This is the normalized value of the average task resource requirement of region i during time period j;

[0081] The system calls the regional time-slot mapping dataset to extract the number of orders and the average usage time of all orders within each time slot for each region. For example, if there are 4 orders in region A and time slot T1, with rental durations of 2, 3, 4, and 5 hours respectively, the average usage time is (2+3+4+5) / 4 = 3.5 hours. Then, it obtains the vehicle dispatch capacity configured by the platform for region A in time slot T1. The dispatch capacity is the maximum number of vehicles that can be dispatched in the system. If this value is 10 vehicles, then the capacity value in the formula is 10. The capacity value is normalized. Assuming the platform's total scheduling capacity is 100 vehicles, the normalized capacity value is 10 / 100 = 0.1. Simultaneously, the total scheduling resources and task resource requirements for the region within the time period are extracted. For example, if the current region has 12 vehicles and the average task requirement is 9 vehicles, the normalized values ​​are 0.12 and 0.09 respectively. The absolute value of the resource difference is then calculated to obtain 0.03, followed by square root calculation to obtain approximately 0.1732. Finally, according to the formula, the occupancy saturation score of region A in time period T1 is calculated as 3.5 × 4 ÷

[0082] (0.1+0.1732)=14÷0.2732≈51.25. The above calculation results are combined with other regions and time periods to establish a scoring matrix structure. The matrix rows represent the region number, the columns represent the time period number, and the cells are filled with the saturation score value under the combination to obtain the region occupancy scoring matrix.

[0083] The saturation state determination submodule compares each score value with the scheduling load reference threshold set by the platform based on the regional occupancy score matrix. It marks the regions and time periods whose score values ​​exceed the reference threshold three times or more consecutively, and merges them into interval labels to generate a set of regional continuous rental saturation identifiers.

[0084] Based on the regional occupancy scoring matrix, each score value is compared with the scheduling load reference threshold set by the platform. This threshold is preset by the platform and is set with reference to the 75th percentile of the daily average saturation score data of all regions in the past month. If the saturation score of region X is 42 and the 75th percentile score is 40, it is marked as exceeding the threshold. Then, the number of time periods in each region that exceed the threshold consecutively is counted. When the score of a region exceeds the threshold for three or more consecutive time periods, it is marked as continuously saturated. The region and time period number are combined to create an interval label. For example, if region X exceeds the threshold in time periods T3, T4, and T5, then the region is marked as being in a saturated state in the T3–T5 interval. The label information is summarized into a triplet structure, which includes the region number, the start time period number, and the end time period number. The output format is {X, T3, T5}. The saturation state labels of all regions are output as a structured set to generate a set of regional continuous rental saturation identifiers.

[0085] Please see Figure 2 and Figure 4 The scheduling level setting module includes a high-density area extraction submodule, a resource gap identification submodule, and a level weight calculation submodule;

[0086] The high-density area extraction submodule calls the area continuous rental saturation identifier set, filters the area numbers marked as saturated, establishes the area site mapping index, and generates a high-density area tag set;

[0087] The system calls upon the saturation identifier set for continuous rental in different regions to identify all region IDs marked as saturated. The filtering operation is performed based on the flag information indicating that the scores continuously exceed a reference threshold. First, it extracts the region ID and the consecutive time period exceeding the threshold from each record, determining if there are three or more consecutive time periods. If a region is continuously marked as exceeding the threshold in T3, T4, and T5, then that region ID is considered a saturated region and its ID X is added to the saturated region set. Next, using each region ID in this set as an index, it retrieves the station distribution records in the car rental platform's structure database. Based on the region-station affiliation relationship, it extracts the unique IDs of all available stations in that region. For example, if there are stations S1, S2, S3, and S4 under region X, then an index structure {X: [S1, S2, S3, S4]} is established. This structure is constructed using a hash mapping method, supporting subsequent fast retrieval of all station IDs within the region using the region ID as the key. Through the above extraction operations, the data preparation for the spatial clustering index is completed. Finally, all region IDs that meet the continuous saturation state and their corresponding station sets are output uniformly, generating a high-density region label set.

[0088] The resource gap identification submodule is based on a high-density regional label set. According to the recorded regional number, it extracts the number of available vehicles for each rental station in the corresponding region, obtains the minimum number of operating vehicles set by the platform, performs difference calculation, filters out the station numbers with insufficient available vehicles, and calculates their gap value to obtain the vehicle resource gap set.

[0089] Based on a high-density regional label set, site-level operations are performed on each regional ID record. First, all mapped site IDs under that region are extracted. Then, the current number of available vehicles is read for each site ID. For example, if site S1 currently has 4 idle vehicles, this value is compared with the minimum number of operating vehicles set by the platform. If the platform defines the minimum number of operating vehicles as 6, the difference is 4-6=-2. Since the result is negative, it indicates that S1 is a site with insufficient resources, with a shortage of 2 vehicles. This benchmark value is set with reference to the platform's regional vehicle scheduling pressure balancing rules, based on the regional average over the past seven days. The average number of tasks initiated and the average adjustable frequency per vehicle are used for estimation. A fixed lower limit is set for each region. For example, if a region has an average of 10 tasks per day and the frequency per vehicle is 2 times / day, then the baseline value is 10 / 2 = 5 vehicles. After the gap station number is extracted through the negative value filtering mechanism, a one-to-one correspondence between the station number and the gap amount is formed. The result is recorded as a mapping structure of {station number: gap amount}. For example, {S1:2, S4:1} indicates that there are insufficient vehicles at two stations, and the total gap is 3 vehicles. This set can be used in groups by station number or region number to obtain the vehicle resource gap set.

[0090] The grade weight calculation submodule calls the vehicle resource gap set, extracts the high-density occurrence frequency of the area where the station is located in the most recent three scheduling cycles, performs superimposed weight scoring based on the frequency value and the corresponding gap amount, calculates the scheduling grade index value of the station, constructs the station grade mapping structure, and generates the regional overload node scheduling grade table.

[0091] The formula for calculating the scheduling level index value of a site is:

[0092]

[0093] Among them, L x D represents the scheduling level index value of the x-th station. x K represents the frequency of high-density occurrences of the area where the x-th station is located within three scheduling cycles. xz m represents the number of vehicle resource gaps at station x during time period z. x H represents the number of time periods during which the x-th station recorded a gap. x F is the sorting factor for the x-th station in the region. x This represents the number of redundant scheduling failures for the x-th site within the historical period.

[0094] For each station number in the vehicle resource gap set, extract the corresponding region number to which the station belongs, and further obtain the frequency value of that region being marked as high-density in the last three scheduling cycles, denoted as D. x If station S1 belongs to region X, and region X has been classified as high-density twice in the scheduling score over the last three scheduling cycles, then Dx =2, then extract the total number of time periods m in which the station appears in the gap record. x And the gap value K for each time period xz For example, if station S1 has a shortage of 2 vehicles in time periods Z1 and Z2 respectively, this indicates that m x =2,K x1 =2,K x2 =1, and then calculate the sum of the absolute values ​​of the gaps. Then extract the site number sorting factor H x This factor is determined based on the station's sequential number within its region. Let S1 be the second station in region X, then H... x =2, then obtain the number of redundant scheduling failures F in the historical period of this site. x If a failure is recorded as one during the scheduling process due to reasons such as path failure or vehicle scheduling failure, then F x =1, substitute into the following formula:

[0095]

[0096] Therefore, the scheduling level index value L of station S1 x The value is approximately 7.07. Repeating the above process allows for the corresponding scoring operation to be performed on each gap site. Subsequently, the numbers of all sites are integrated with their corresponding scheduling level scores to construct a key-value mapping structure. The key is the site number, and the value is the scoring result, such as {S1:7.07,S4:6.50,S8:8.10}. Finally, a complete structured data is formed, generating a regional overload node scheduling level table.

[0097] Please see Figure 2 and Figure 5 The candidate path reconstruction module includes a priority node extraction submodule, a vehicle status calculation submodule, and a path filtering and sorting submodule.

[0098] The priority node extraction submodule is based on the regional overload node scheduling level table, filters the station numbers marked as priority transfers by scheduling level, establishes the target node index for transfer, and extracts the adjacent area range of each target node to generate a set of target nodes that can be transferred.

[0099] Based on the regional overload node scheduling level table, all site numbers with a level score higher than the priority scheduling threshold are identified. The priority scheduling threshold is set by the platform according to the 90th percentile of the regional score. If the threshold is 6.5, then all sites with a score greater than or equal to 6.5 are judged as priority transfer sites. For example, site S3 with a score of 7.1 and site S4 with a score of 6.8 both meet the screening criteria. The platform records this score structure as {S1:4.2, S2:5.9, S3:7.1, S4:6.8}, where S3 and S4 are the screening results. Subsequently, the above-screened site numbers are used to build a target node index table, forming the target node {S3, S4}. The point index set uses each station in the set as the center to find the adjacent regional units in the map structure corresponding to its geographical area. The adjacent region is defined as the adjacent administrative area on the map that is less than 5 kilometers away from the station in a straight line or shares a boundary line. If S3 belongs to region A and its adjacent regions are B, C, and D, then the adjacent regions of the target node of the station are recorded as the set {B, C, D}. In this way, a reverse association regional index is established for all target nodes. Each target node is linked to multiple adjacent resource regions that can be overflowed and allocated. Finally, a multi-dictionary structure is constructed with the station number as the key and the adjacent region set as the value to generate a set of target nodes that can be transferred.

[0100] The vehicle status calculation submodule extracts the station number, current location, previous return time and current empty driving status of vehicles in adjacent areas based on the set of transferable target nodes. It calculates the driving distance from the current location to the target node and the return interval, and calls the station information for normalization processing to obtain a standardized vehicle status data table.

[0101] Based on the set of transferable target nodes, the adjacent area number corresponding to each target node is extracted sequentially. All vehicles in that area are then filtered in the platform's vehicle database to obtain their current station number and location coordinates as basic location information. The vehicle's real-time status record table is called to determine if the vehicle is currently in an idle state. If the status value is "idle," it is marked as an idle vehicle. The end time field of the vehicle's last completed task is then read and compared with the current system time to calculate the time interval. For example, if vehicle V201 completed its task at 12:30 on April 1st, and the current time is 14:00 on April 1st, the return interval is 1.5 hours. Next, based on the vehicle's current location and the station coordinates of the transferable target node, the straight-line distance formula is used to calculate the travel distance from the current location to the target node. If the current location... With coordinates (100.4, 20.6) and target node coordinates (101.0, 21.2), the straight-line distance is approximately 0.848 kilometers. The three parameters for each vehicle—empty driving status, return time interval, and driving distance—are normalized in their respective dimensions using the maximum-min normalization method. The normalized value is calculated as (X - Xmin) / (Xmax - Xmin). Taking the driving distance as an example, the maximum distance is 3.0 kilometers, and the minimum is 0.4 kilometers. Therefore, the normalized distance for V201 is (0.848 - 0.4) / (3.0 - 0.4) ≈ 0.185. After normalizing all parameters for all vehicles, the resulting structure uses the vehicle number as the key and the three standardized parameters as values ​​to form a triplet, resulting in a standardized vehicle status data table.

[0102] The route selection and sorting submodule is based on a standardized vehicle status data table. It performs weighted calculation and sorting of two indicators based on the normalized driving distance and normalized response time of the vehicles, and selects the vehicle numbers and corresponding route records that are within the target range in terms of score ranking, and generates a route transferable vehicle dispatch group.

[0103] Based on a standardized vehicle status data table, normalized travel distance and normalized response time are read one by one according to vehicle number. The comprehensive scheduling score for each vehicle is calculated using a weighted average method. The weight of travel distance is set to 0.6 and the weight of response time is set to 0.4. The normalized travel distance of vehicle V201 is 0.185 and the response time is 0.25. The comprehensive score is 0.6×0.185+0.4×0.25=0.111+0.1=0.211. All candidate vehicles are comprehensively scored and sorted in this way. The vehicle numbers and their corresponding target path records in the top 10% of the scores are selected. If there are 100 candidate vehicles, the top 10 vehicles are selected. The vehicle number is merged with its current home station number, target transfer node number, path distance, response time and other basic scheduling information records to construct a path scheduling record structure table. The record content structure is uniformly formatted as {vehicle ID, starting station ID, target node ID, score value}, and a path transferable vehicle scheduling group is generated.

[0104] Please see Figure 2 and Figure 6 The adjustable vehicle screening module includes a time limit construction submodule, a response indicator extraction submodule, and a task vehicle screening submodule.

[0105] The time limit construction submodule retrieves orders marked with high urgency level from the task list, extracts the creation time and maximum response time limit for each order, combines the two data items into time limit record entries by task number, and generates a task time limit dataset.

[0106] Retrieve orders marked with a high urgency level from the task list, identifying records where the "priority_level" field is "high". Extract the task number, creation time, and maximum response time limit from these orders. The creation time is the timestamp when the order was submitted to the system, and the maximum response time limit represents the longest possible scheduling response time the platform can tolerate after the order is generated, in minutes or hours. For example, task T01 was created on April 5, 2024 at 9:00 AM, and its maximum response time limit is 30 minutes. After extraction, combine these two data points by task number to form a structured entry format: {task number, creation time, maximum response time limit}. All high-urgency orders... Orders are uniformly constructed as a set of time-limit records to provide scheduling time boundaries for subsequent vehicle response determination. During the construction process, time fields need to be uniformly formatted and converted. The creation time is uniformly converted to a timestamp format (such as a Unix timestamp), and the response time limit is converted to seconds or minutes to support subsequent comparison and calculation operations. For example, if the creation time of task T02 is 13:30 on April 5, 2024, the corresponding timestamp is 1712295000, and the maximum response time limit is set to 45 minutes, which is converted to 2700 seconds, the constructed entry will be {T02, 1712295000, 2700}. All entries are ultimately uniformly output as task key-value pairs to generate a task time limit dataset.

[0107] The response index extraction submodule can be transferred to the vehicle dispatch group. It extracts the previous task completion time, the average time interval of the last three task calls, and the standard deviation of the historical dispatch response time for the corresponding vehicle. It establishes the index correspondence by vehicle number and obtains the vehicle response performance parameter table.

[0108] The call path can be transferred to the vehicle dispatch group. The dispatch information associated with each vehicle number is extracted. First, the previous task completion time of vehicle number V is read as the end timestamp of the most recent valid task for that vehicle. For example, if the last task completion time for vehicle V125 was April 5, 2024, at 11:00, the corresponding timestamp is 1712288400. Then, the time interval between the three most recent task calls recorded in the dispatch log for that vehicle is extracted. The time interval is the difference between the task dispatch start time and the previous task completion time. If the three intervals are set to 20 minutes, 15 minutes, and 25 minutes respectively, then the average value is (20+15+25) / 3 = 20 minutes, corresponding to 1200 seconds. Continue reading all response time fields in the vehicle's historical dispatch records and calculate the standard deviation to measure its response stability. If the response time records are 14, 18, 22, and 16 minutes, then its standard deviation σ = √[(14-17.5)² + (18-17.5)² + (22-17.5)² + (16-17.5)²] / 4 = √

[0109] [(12.25+0.25+20.25+2.25) / 4]=√(35 / 4)=√8.75≈2.96 minutes. The above data is recorded in a structured format with the vehicle number as the key and the three response indicators as the values. The record structure is {Vehicle ID, previous completion timestamp, average call interval, standard deviation of response time}. Each indicator value is uniformly converted to a uniform unit (seconds) for easy alignment with the task response time limit, resulting in a vehicle response performance parameter table.

[0110] The task vehicle screening submodule is based on the task time limit dataset and the vehicle response performance parameter table. It compares the task time limit and vehicle response three indicators one by one to determine whether each indicator is less than the task response limit standard. It screens out any vehicle number that exceeds the limit and marks the scheduling adaptation relationship between the remaining vehicles and the task to obtain a list of vehicles that match high urgency tasks.

[0111] Based on the task timeliness constraint dataset and vehicle response performance parameter table, for each task number, the task creation timestamp and maximum response time limit are read from the task record. The allowed response deadline is calculated by adding the response time limit in seconds to the creation timestamp. For example, if task T03 was created at 1712292000 seconds and has a maximum response time limit of 1800 seconds, then the task response deadline is 1712293800 seconds. Subsequently, for each candidate vehicle number, the corresponding previous task completion timestamp, average call interval, and response time standard deviation are read. The task deadline is subtracted from the vehicle's previous task completion time. If the result is less than the sum of the average call interval and the response standard deviation, then the vehicle is considered unsuitable. If a vehicle poses a scheduling risk, its ID will be removed. The judgment formula is: if 1712293800 - previous completion timestamp < average call interval + response standard deviation, then the vehicle does not meet the scheduling conditions. For example, if vehicle V208's previous completion timestamp is 1712292600, the average interval is 800 seconds, and the response standard deviation is 400 seconds, then the remaining response time is 1200 seconds, while the expected response time is 800 + 400 = 1200 seconds. If the two are equal, the vehicle is marginally available. The platform sets the judgment threshold to remove vehicles if they are less than or equal to the threshold. Therefore, V208 is not selected. Finally, the vehicle IDs that meet all the judgment conditions and their associated task IDs are retained to obtain the list of vehicles matching high-urgency tasks.

[0112] Please see Figure 2 and Figure 7 The scheduling path binding module includes a path field matching submodule, an instruction content update submodule, and an entry format generation submodule;

[0113] The path field matching submodule matches the vehicle list based on high-urgency tasks, extracts the vehicle number, and matches the corresponding starting station ID and target path segment number in the path transferable vehicle scheduling group. At the same time, it extracts the vehicle ID information, constructs a three-field combination structure, and generates a path field association set.

[0114] Based on the vehicle list for high-urgency tasks, the vehicle number is extracted from each record. The dispatch groups for transferable vehicles along the path are traversed, and the vehicle number is matched with its associated dispatch field. The origin station ID and target path segment number fields in the matching item are read. If a match is successful, the record is retained; otherwise, it is skipped. For example, if vehicle number V205 is matched with origin station ID S102 and target path segment number P307 in the dispatch group, these three pieces of information are assembled with the vehicle number into a field combination structure {V205, S102, P307}. The field order in the structure is fixed as vehicle I D. Starting station ID and target path segment number. Ensure consistency of subsequent data binding. Repeat the above operation until all vehicle numbers in the list have been retrieved. The structure must not be missing any items and the field content must not be empty. If data is missing in the dispatch group, it must be supplemented from the real-time vehicle status data. Then, store the structure of all three-field combinations into the mapping structure, saving it in the form of vehicle number as key and field combination as value. For example, the final structure is: {V205:{S102,P307},V210:{S108,P322}}. After the construction is completed, archive it uniformly to generate a path field association set.

[0115] The instruction content update submodule calls the path field association set. Based on each group of vehicle field combinations, it replaces the corresponding positions in the scheduling instruction structure in the order of vehicle ID, starting station ID, and target path segment, and records the task number corresponding to the replaced field to obtain a structured scheduling instruction set.

[0116] The path field association set is invoked, and the three fields extracted from each record are sequentially bound to the corresponding positions in the scheduling instruction structure. First, the vehicle ID field in the original scheduling instruction structure is replaced with the vehicle number in the current field combination. Then, the original starting station ID field is replaced with the second station number in the field combination. Finally, the target path segment number field is replaced with the third path number in the field combination. The replacement operation is performed in the scheduling structure template according to the field position order to ensure that the corresponding positions of the field content are not misaligned. At the same time, according to the task number corresponding to the current field combination, it is bound to the above three fields to form a structured scheduling instruction record. For example, if the task number is T048 and the corresponding field combination is {V205,S102,P307}, then the structured scheduling record {T048,V205,S102,P307} is formed. The remaining field combinations are processed in the same way. All records are stored in a unified set in a structured format. The structure of this set is fixed with four fields: task number, vehicle ID, starting station ID, and target path segment number. The field order is fixed, and the storage format supports retrieval by task number to obtain the structured scheduling instruction set.

[0117] The item format generation submodule extracts the task number and vehicle corresponding scheduling level identifier of each instruction from the set of structured scheduling instructions, integrates them into a parallel structure of task field and scheduling field, reorganizes them into item-style standardized expression content, and generates task-bound path scheduling information.

[0118] Based on the structured scheduling instruction set, the task number field and the corresponding vehicle number field are extracted from each record. Using the overload node scheduling level table in the vehicle number index area, the scheduling level score corresponding to the station to which the vehicle belongs is obtained. The score value is normalized according to a unified range, from 0 to 10, with 0-3 defined as low level, 4-7 as medium level, and 8-10 as high level. For example, if vehicle V205 has a scheduling level of 8.4, it is classified as high level. After obtaining the value, a record with parallel fields for task and level is constructed. The field content consists of five items: task number, vehicle number, starting station ID, target path segment number, and scheduling level score, such as {T048,V205,S102,P307,8.4}. All records in the structured scheduling instruction set are reassembled according to this structure and uniformly converted into an itemized record format. The field order is consistent with the system scheduling processing field template, and no fields are missing. The generated record format supports quick retrieval by task number or scheduling level. After storing in a unified format, the record is output, generating task-bound path scheduling information.

[0119] Please see Figure 8 The vehicle dispatch optimization method for car rental platforms includes the following steps:

[0120] S1: Obtain the order records of the car rental platform, map the rental duration of each order to the time period, evaluate the saturation status within the time period, and generate a set of regional continuous rental saturation identifiers;

[0121] S2: Call the region continuous rental saturation identifier set, extract the regions marked as high-density rental status, obtain the number of available vehicles at each rental station in the region, combine the vehicle shortage and high frequency index value, calculate the station scheduling level, and obtain the region overload node scheduling level table.

[0122] S3: Based on the regional overload node scheduling level table, the average vehicle scheduling response time and empty driving distance index are standardized, weighted and sorted to select the optimal path for executing scheduling tasks and generate a path transferable vehicle scheduling group.

[0123] S4: Get the orders marked as high urgency in the task list, extract the vehicle's previous task completion time, the average of the three most recent call intervals and the standard deviation of historical response time, and compare them with the maximum response time limit of the order task. If any indicator is higher than the response limit standard, remove the vehicle number to obtain a list of vehicles matching high urgency tasks.

[0124] S5: Based on the vehicle list for high-urgency tasks, match the path and station information in the route-transferable vehicle scheduling group, reconstruct the vehicle ID, starting station ID, and target path segment in the scheduling instruction structure, and record the task number and scheduling level label in an itemized format to generate task-bound path scheduling information.

[0125] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0126] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0127] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0128] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0129] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0130] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0131] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0132] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0133] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0134] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A car rental platform vehicle dispatch optimization system, characterized in that, The system comprises: The rental saturation identification module obtains order records of the rental platform, maps the rental duration of each order to the time period, evaluates the saturation state of the area time period, and generates an area continuous rental saturation identification set; The rental saturation identification module comprises: The order period mapping submodule obtains order records of the rental platform, extracts rental start and end times, rented vehicle numbers, and geographical area labels, maps the duration of each order to the time period and geographical area to which it belongs, and establishes a double-index structure of area and time period to generate an area period mapping dataset; The occupancy index calculation submodule calls the area period mapping dataset, extracts the number of orders and the average use time of each order in each time period of each area, obtains the vehicle scheduling capacity of the corresponding time period of the area, calculates the occupancy saturation score of the area time period, and combines the score structure in units of areas to obtain an area occupancy score matrix; The formula for calculating the occupancy saturation score of the area time period is: ; wherein, representative area in a time period occupancy saturation score, is the normalized value of the rental duration of the nth order in the area , time period , and is the total number of orders in the area , time period , is the normalized value of the configured vehicle dispatching capacity in the area , time period , is the normalized value of the total amount of dispatching resources in the area , time period , is the normalized value of the average task resource demand in the area , time period .​ The saturation state determination submodule compares each score value with the scheduling load reference threshold set by the platform based on the area occupancy score matrix, marks the area and time period combination whose score value continuously exceeds the reference threshold for more than three times, and merges it into an interval label to generate an area continuous rental saturation identification set; The scheduling level setting module calls the area continuous rental saturation identification set, extracts the area marked as a high-density rental state, obtains the number of available vehicles at each rental site in the area, combines the vehicle gap and high-frequency index value, calculates the scheduling level of the site, and obtains an area overload node scheduling level table; The candidate path reconstruction module, based on the area overload node scheduling level table, performs weighted calculation and sorting on the average vehicle scheduling response time and the empty running distance index after standardization, screens the optimal path for executable scheduling tasks, and generates a path transferable vehicle scheduling group; The adjustable vehicle screening module obtains orders marked as high urgency in the task list, extracts the previous task completion time of the vehicle, the average value of the latest three call intervals, and the historical response time standard deviation, compares them with the maximum response time limit of the order task, and if any of the indicators is higher than the response limit standard, the vehicle number is excluded, and a high-urgency task matching vehicle list is obtained.

2. The car rental platform vehicle dispatch optimization system of claim 1, wherein, The area continuous rental saturation identification set comprises a time period vehicle occupancy proportion label, an area number index, a continuous saturation state mark, and a corresponding period adjustable vehicle upper limit. The area overload node scheduling level table specifically comprises a site vehicle gap value, a historical high-occupancy frequency factor, a scheduling level index, and a site number label. The path transferable vehicle scheduling group comprises a transfer-out node number, a target site path pair, an empty running distance ratio, and a scheduling response time interval. The high-urgency task matching vehicle list specifically comprises a task number label, a vehicle response interval index, a task response limit state, and a vehicle scheduling feasibility mark.

3. The rental platform vehicle dispatch optimization system of claim 1, wherein, The scheduling level setting module comprises: The high-density area extraction submodule calls the area continuous rental saturation identification set, screens the area number whose state mark is saturation, and establishes an area site mapping index to generate a high-density area label set; The resource gap identification submodule extracts the number of available vehicles in each rental station in the corresponding area according to the recorded area number based on the high-density area label set, obtains the minimum operating vehicle number benchmark set by the platform, performs a difference operation, screens the station numbers with insufficient available quantity, and calculates the gap value to obtain a vehicle resource gap set; The level weight calculation submodule calls the vehicle resource gap set, extracts the high-density occurrence frequency of the area where the station is located in the last three scheduling periods, performs superposition proportion scoring according to the frequency value and the corresponding gap amount, calculates the scheduling level index value of the station, constructs a station level mapping structure, and generates an area overload node scheduling level table.

4. The rental car platform vehicle dispatch optimization system of claim 3, wherein, The formula of the scheduling level index value of the computing site is: ; wherein, denotes a scheduling level indicator value of the th site, denotes a high density occurrence frequency of the area where the th site is located within three scheduling periods, denotes a number of vehicle resource gaps of the th site in the time period , is a number of time periods in which the th site is recorded to have gaps, is a number ordering factor of the th site in the area, is a number of redundant scheduling failures of the th site within the historical period.

5. The car rental platform vehicle dispatch optimization system of claim 4, wherein, The candidate path reconstruction module comprises: The priority node extraction submodule screens the station numbers marked as priority transfer-in based on the area overload node scheduling level table, establishes a transfer-in target node index, and extracts the adjacent area range of each target node to generate a transferable target node set; The vehicle state calculation submodule extracts the home station number, current position, last return time and current empty driving state of the vehicle in the adjacent area according to the transferable target node set, calculates the driving distance from the current position to the target node and the return interval time, and calls the station information for normalization processing to obtain a standardized vehicle state data table; The path screening and sorting submodule performs weighted calculation and sorting on the two indexes according to the normalized driving distance and normalized response time of the vehicle based on the standardized vehicle state data table, and screens the vehicle numbers and corresponding path records with a ranking within the target range to generate a path transferable vehicle scheduling group.

6. The rental car platform vehicle dispatch optimization system of claim 5, wherein, The adjustable vehicle screening module comprises: The time limit construction submodule extracts the creation time and maximum response time limit of each order in the task list marked as high in the emergency level, combines the two data into a time limit record item according to the task number, and generates a task time limit data set; The response index extraction submodule calls the path transferable vehicle scheduling group, extracts the last task completion time, the average value of the time interval of the last three task calls, and the standard deviation of the historical scheduling response time of the corresponding vehicle, establishes an index correspondence according to the vehicle number, and obtains a vehicle response performance parameter table; The task vehicle screening submodule performs item-by-item comparison according to the task time limit and vehicle response three indexes based on the task time limit data set and vehicle response performance parameter table, judges whether each index is less than the task response limit standard, screens out any vehicle number exceeding the limit, and marks the scheduling adaptation relationship between the remaining vehicles and the task to obtain a high emergency task matching vehicle list.

7. The car rental platform vehicle dispatch optimization system of claim 6, wherein, The system further comprises: The scheduling path binding module matches the path and station information in the path transferable vehicle scheduling group based on the high emergency task matching vehicle list, reconstructs the vehicle ID, starting station ID and target path segment in the scheduling instruction structure, combines the task number and scheduling level label record into an entry type format, and generates task binding path scheduling information; The task binding path scheduling information comprises a vehicle instruction structure item, a task scheduling number, a station path identifier, and a scheduling level entry.

8. The rental car platform vehicle dispatch optimization system of claim 7, wherein, The scheduling path binding module comprises: The path field matching submodule extracts the vehicle number based on the high emergency task matching vehicle list and matches the corresponding starting station ID and target path segment number in the path transferable vehicle scheduling group, extracts the vehicle ID information, constructs a three-field combination structure, and generates a path field association set; The instruction content updating submodule calls the path field association set, replaces the corresponding position in the scheduling instruction structure according to the vehicle ID, starting station ID, and target path segment in each vehicle field combination, records the task number corresponding to the replaced field, and obtains a structured scheduling instruction set; The entry format generation submodule extracts the task number and vehicle scheduling level identifier corresponding to each instruction according to the structured scheduling instruction set, integrates the task field and the scheduling field in parallel structure, reorganizes the entry type standardized expression content, and generates the task binding path scheduling information.

9. A car rental platform vehicle dispatch optimization method, characterized by, The method is used for realizing the vehicle scheduling optimization system of the car rental platform according to any one of claims 1-8, comprising the following steps: S1: Obtain the order record of the car rental platform, map the rental duration of each order to the time period, evaluate the saturation state of the region time period, and generate a region continuous rental saturation identifier set; S2: Call the region continuous rental saturation identifier set, extract the region marked as high-density rental state, combine the vehicle gap and high-frequency index value, calculate the scheduling level of the station, and obtain a region overload node scheduling level table; S3: Based on the region overload node scheduling level table, the average scheduling response time and the empty driving distance index are standardized and weighted calculated and sorted, the optimal path of the executable scheduling task is screened, and a path transferable vehicle scheduling group is generated; S4: Obtain the order marked as high emergency in the task list, extract the previous task completion time, the average value of the latest three call intervals, and the historical response time standard deviation of the vehicle, compare them with the maximum response time limit of the order task, and if any index is higher than the response limit standard, the vehicle number is excluded, and a high emergency task matching vehicle list is obtained; S5: Based on the high emergency task matching vehicle list, the vehicle ID, starting station ID, and target path segment in the scheduling instruction structure are reconstructed, the task number and scheduling level label are recorded in entry type format, and the task binding path scheduling information is generated.

Images