Cigarette distribution vehicle platform parking space scheduling method, system, device and medium

Abstract

The embodiment of the specification provides a cigarette distribution vehicle platform parking space scheduling method, system, device and medium, wherein the method comprises the following steps: collecting distribution line data and historical queuing data of vehicles to be scheduled on the day; inputting the line mileage, line delivery volume and delivery number of each line into a pre-trained delivery time length prediction model to output the predicted delivery time length of the line; for each vehicle, calculating the comprehensive scheduling score of each vehicle based on the preset scheduling factors; according to the total capacity of the platform and the calculated comprehensive scheduling score, sorting all the vehicles to be scheduled, selecting the vehicles in the front of the sorting and not more than the platform capacity to be allocated to the platform parking space, and the remaining vehicles entering the queuing queue; according to the preset balancing strategy, determining the vehicles finally to be queued from the queuing queue or all the vehicles to be scheduled, and updating the historical cumulative queuing times thereof.

Description

Technical Field

[0001] This document relates to the field of logistics and warehousing technology, and in particular to a method, system, equipment and medium for scheduling parking spaces on a cigarette delivery vehicle platform. Background Technology

[0002] In cigarette logistics and distribution centers, parking spaces are a limited and valuable resource. Every day, dozens of delivery vehicles need to load and depart within a limited timeframe. Traditional vehicle scheduling methods typically rely on human experience or simple computer rules, primarily prioritizing based on factors such as delivery distance and administrative region priority. However, these existing methods suffer from the following significant problems: Uneven vehicle queuing: Some vehicles are frequently assigned to the back of the queue and are thus queued for a long time, resulting in a serious imbalance in vehicle workload, which affects the drivers' work enthusiasm and vehicle maintenance cycle. Excessive queuing time: The dispatching process failed to accurately estimate the actual loading and delivery time, resulting in some vehicles waiting for a long time at the platform, which reduced the overall logistics efficiency and may cause delivery delays. Low platform parking space turnover efficiency: Simple sorting rules cannot ensure the most efficient turnover of platform parking spaces. For example, if a vehicle with a large load and a long delivery distance is assigned to a later position, it will occupy the platform for a longer time, affecting the timely signing of subsequent delivery tasks.

[0003] There is a lack of intelligent scheduling methods in the current technology that can comprehensively consider historical queuing fairness, future task time prediction and multi-dimensional business factors. Therefore, how to scientifically and efficiently schedule vehicles to maximize the utilization of platform resources and achieve fair vehicle queuing is a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0004] This specification provides one or more embodiments of a method for scheduling parking spaces on a cigarette delivery vehicle platform, including: S1. Collect delivery route data and historical queuing data of vehicles to be dispatched on the same day; the delivery route data includes at least route mileage, route delivery volume, number of delivery households, and administrative region information; the historical queuing data includes the cumulative number of times each vehicle has queued in the past. S2. Input the route mileage, delivery volume, and number of customers for each route into the pre-trained delivery time prediction model, and output the predicted delivery time for that route. S3. For each vehicle, calculate the comprehensive scheduling score based on preset scheduling factors; S4. Based on the total platform capacity and the calculated comprehensive scheduling score, sort all vehicles to be scheduled, select the vehicles with the highest ranking and a number not exceeding the platform capacity to be assigned to platform parking spaces, and the remaining vehicles enter the queuing queue. S5. Based on the preset balancing strategy, determine the vehicle that will eventually need to queue from the queue or all vehicles to be dispatched, and update its historical cumulative queuing count.

[0005] Furthermore, the delivery time prediction model is a regression model trained based on the XGBoost algorithm. The XGBoost regression model is trained using historical delivery data, which includes route mileage, route delivery volume, number of delivery households, and corresponding actual delivery time.

[0006] Furthermore, the scheduling factors include a delivery volume factor negatively correlated with delivery volume, a mileage factor positively correlated with route mileage, a regional priority factor positively correlated with administrative region priority, a queue number priority factor positively correlated with historical cumulative queue number, and a delivery time factor positively correlated with predicted delivery time.

[0007] Furthermore, the specific formula for calculating the comprehensive scheduling score is as follows: Overall score = w1 * F1 + w2 * F2 + w3 * F3 + w4 * F4 + w5 * F5; Among them, F1, F2, F3, F4, and F5 are the scores of the normalized delivery volume factor, mileage factor, regional priority factor, queue number priority factor, and delivery time factor, respectively; w1 to w5 are the weight coefficients of each factor, and w1 + w2 + w3 + w4 + w5 = 1.

[0008] Furthermore, according to a preset balancing strategy, determining the vehicle that ultimately needs to queue from the queuing queue or all vehicles to be dispatched, and updating its historical cumulative queuing count specifically includes: From all vehicles to be dispatched, select a number of vehicles with the fewest historical cumulative queuing times. The number of these vehicles is equal to the number of vehicles that need to enter the queuing queue. These vehicles are then identified as the final queuing vehicles. The historical cumulative queuing count of the final queued vehicles is incremented by 1 for updating.

[0009] Furthermore, the method also includes: Calculate the statistical standard deviation and average of the historical cumulative queuing times for all vehicles, and calculate the scheduling balance based on the statistical standard deviation and average. The weighting coefficients in the overall scheduling score are adjusted and optimized based on the aforementioned scheduling balance.

[0010] Furthermore, the formula for calculating the scheduling balance is as follows: Balance = 1 - (Standard deviation of queue count / Average of queue count); The closer the balance is to 1, the more balanced the distribution of queuing times.

[0011] This specification provides one or more embodiments of a cigarette delivery vehicle platform parking space scheduling system, including: Data acquisition module: used to collect delivery route data and historical queuing data of vehicles to be dispatched on the same day; the delivery route data includes at least route mileage, delivery volume, number of delivery households, and administrative region information; the historical queuing data includes the cumulative number of times each vehicle has queued. Delivery time prediction module: This module takes the route mileage, delivery volume, and number of customers for each route as input into a pre-trained delivery time prediction model and outputs the predicted delivery time for that route. Comprehensive scoring module: used to calculate the comprehensive scheduling score of each vehicle based on preset scheduling factors; Platform parking space scheduling module: Based on the total platform capacity and the calculated comprehensive scheduling score, it sorts all vehicles to be scheduled, selects the vehicles with the highest ranking and a number not exceeding the platform capacity to be assigned to platform parking spaces, and the remaining vehicles enter the queuing queue. Queue balancing module: used to determine the vehicle that will eventually need to queue from the queue or all vehicles to be dispatched according to a preset balancing strategy, and update its historical cumulative queuing count.

[0012] This specification provides one or more embodiments of an electronic device, including: Processor; and, A memory is configured to store computer-executable instructions, which, when executed, cause the processor to implement the steps of the above-described cigarette delivery vehicle platform parking space scheduling method.

[0013] This specification provides one or more embodiments of a storage medium for storing computer-executable instructions that, when executed, implement the steps of the above-described cigarette delivery vehicle platform parking space scheduling method.

[0014] The embodiments of this invention employ the XGBoost model to accurately predict delivery times, enhancing the ability to scientifically predict operational load. A comprehensive scoring model integrating multiple factors such as delivery volume, mileage, regional priority, historical queuing frequency, and predicted duration is constructed. Through adjustable weights, it flexibly balances operational efficiency, scheduling fairness, and management orientation, designing a proactive queuing balancing mechanism to prevent some vehicles from waiting for extended periods and promote equal opportunity. By calculating the balance index of historical queuing frequency and adjusting the model weights accordingly, the scheduling strategy possesses adaptive and continuous optimization capabilities, enabling scientific and efficient vehicle scheduling in long-term operation, maximizing platform resource utilization and ensuring fair vehicle queuing.

[0015] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in one or more embodiments of this specification or in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A flowchart illustrating a method for scheduling parking spaces on a cigarette delivery vehicle platform, provided for one or more embodiments of this specification; Figure 2 A structural diagram of an XGBoost delivery time prediction model for a cigarette delivery vehicle platform parking space scheduling method provided in one or more embodiments of this specification; Figure 3 A flowchart illustrating the multi-factor comprehensive scoring calculation method for a cigarette delivery vehicle platform parking space scheduling method provided in one or more embodiments of this specification; Figure 4 A vehicle scheduling decision flowchart for a cigarette delivery vehicle platform parking space scheduling method provided in one or more embodiments of this specification; Figure 5 A schematic diagram illustrating the composition of a cigarette delivery vehicle platform parking space scheduling system provided in one or more embodiments of this specification; Figure 6 This is a schematic diagram of the structure of an electronic device provided for one or more embodiments of this specification. Detailed Implementation

[0018] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0019] Method Implementation Examples According to an embodiment of the present invention, a method for scheduling parking spaces on a cigarette delivery vehicle platform is provided. Figure 1 A flowchart illustrating a method for scheduling parking spaces on a cigarette delivery vehicle platform, provided in one or more embodiments of this specification, is shown below. Figure 1 As shown, the cigarette delivery vehicle platform parking space scheduling method according to an embodiment of the present invention specifically includes: S1. Collect delivery route data and historical queuing data of vehicles to be dispatched on the same day; the delivery route data includes at least route mileage, route delivery volume, number of delivery households, and administrative region information; the historical queuing data includes the historical cumulative number of times each vehicle has queued.

[0020] The collected raw data is preprocessed, including data cleaning, format standardization, and data fusion. Data cleaning includes removing outliers or null values ​​from fields such as mileage and delivery volume. Format standardization includes unifying the regional name coding.

[0021] S2. Input the route mileage, delivery volume, and number of customers for each route into the pre-trained delivery time prediction model, and output the predicted delivery time for that route.

[0022] The delivery time prediction model is a regression model trained based on the XGBoost algorithm, such as... Figure 2 As shown, the XGBoost regression model is trained using historical delivery data, which includes route mileage, delivery volume, number of customers delivered to, and corresponding actual delivery time. The model is input as route mileage, delivery volume, and number of customers, and the XGBoost delivery time prediction algorithm outputs the delivery time. After training, based on the daily delivery route data, the route mileage, delivery volume, and number of customers for each route are obtained. These are then input into the trained XGBoost regression model, which outputs the estimated delivery time for each route.

[0023] S3. For each vehicle, calculate the comprehensive scheduling score based on preset scheduling factors.

[0024] In this embodiment, as Figure 3 As shown, based on route data, vehicle data, and predicted delivery time, the scheduling factors include delivery volume, mileage, regional priority, queue count priority, and delivery time factor. Among these, the delivery volume factor prioritizes vehicles with smaller delivery volumes, and the score is negatively correlated with delivery volume; the mileage factor prioritizes long-distance vehicles with longer mileage, and the score is positively correlated with mileage; the regional priority factor prioritizes vehicles in specific priority areas, and the score is positively correlated with regional priority; the queue count priority factor prioritizes vehicles with more historically accumulated queue counts, and the score is positively correlated with historically accumulated queue counts; and the delivery time factor prioritizes vehicles with longer predicted delivery times, and the score is positively correlated with predicted delivery times.

[0025] The formula for calculating the comprehensive scheduling score is as follows: Overall score = w1 * F1 + w2 * F2 + w3 * F3 + w4 * F4 + w5 * F5; Among them, F1, F2, F3, F4, and F5 are the scores of the normalized delivery volume factor, mileage factor, regional priority factor, queue number priority factor, and delivery time factor, respectively; w1 to w5 are the weight coefficients of each factor, and w1 + w2 + w3 + w4 + w5 = 1.

[0026] S4. Based on the total platform capacity and the calculated comprehensive scheduling score, sort all vehicles to be scheduled, select the vehicles with the highest ranking and a number not exceeding the platform capacity to be assigned to platform parking spaces, and the remaining vehicles enter the queuing queue.

[0027] like Figure 4 As shown, all vehicles to be dispatched are first sorted in descending order according to their comprehensive dispatch scores to form a priority queue. Then, starting from the top of the sorted queue, a corresponding number of vehicles are selected, with the total platform capacity as the upper limit. These selected vehicles are assigned to platform parking spaces and can begin the first round of loading operations. The remaining vehicles that are ranked after the platform capacity are placed into a queuing queue as candidate vehicles for the second round of loading, waiting for subsequent dispatch instructions or the next round of allocation opportunities.

[0028] S5. Based on the preset balancing strategy, determine the vehicle that will eventually need to queue from the queue or all vehicles to be dispatched, and update its historical cumulative queuing count.

[0029] From all vehicles awaiting dispatch, select a number of vehicles with the fewest historical cumulative queuing times. The number of these vehicles is equal to the number of vehicles that need to queue in the second round. The number of vehicles selected is strictly equal to the total number of vehicles that must enter the queuing state in this round, calculated based on the platform capacity. These vehicles with the fewest historical queuing times are taken as the number of vehicles that need to enter the queuing queue, and these vehicles are determined as the final queuing vehicles. The historical cumulative queuing times of the final queuing vehicles are incremented by 1 for updating, and the record is saved.

[0030] Calculate the statistical standard deviation and average of the historical cumulative queuing times for all vehicles, and calculate the scheduling balance based on the statistical standard deviation and average. Then, perform feedback optimization and adjustment on the weight coefficients in the comprehensive scheduling score based on the scheduling balance.

[0031] The formula for calculating the scheduling balance is: Balance = 1 - (Standard deviation of queue count / Average of queue count); The closer the balance degree is to 1, the more balanced the distribution of queuing times is. If the balance degree remains low, it indicates insufficient fairness, and the system may automatically increase the weight of the queuing time factor, making vehicles with more historical waiting time more advantageous in the comprehensive score, so that they are more likely to obtain priority in subsequent scheduling to correct the unfair trend.

[0032] The technical solution of the present invention will be described in detail below in conjunction with the attached drawings and specific embodiments.

[0033] Suppose a cigarette logistics center has 35 platform parking spaces, and 48 vehicles need to be scheduled today.

[0034] Step S1: Data collection Obtain the route information table and historical queuing record table of 48 vehicles on the same day from the database: The example of the route information table is shown in Table 1: Table 1

[0035] The example of the historical queuing record table (JSON format): {"Gui A581E8": 3, "Gui A626J3": 5,...}.

[0036] Step S2: Delivery duration prediction The system loads the pre-trained XGBoost model. For the vehicle with the license plate number "Gui A581E8", the input features are: [85, 450, 35], and the model prediction output is: predicted delivery duration = 5.2 hours.

[0037] Predict for all 48 vehicles in sequence to obtain their respective predicted durations.

[0038] Step S3: Calculation of multi-factor comprehensive score Set the weight coefficients as: w1 = 0.2 (delivery volume), w2 = 0.2 (mileage), w3 = 0.2 (area), w4 = 0.2 (queuing times), w5 = 0.2 (predicted duration).

[0039] Take the vehicle "Gui A581E8" as an example: Data normalization (assuming the maximum and minimum values of the data on the same day are known): Normalized delivery volume = (450 - 150) / (500 - 150) = 0.86; Normalized mileage = (85 - 20) / (100 - 20) = 0.81; Normalized queuing times = (3 - 0) / (10 - 0) = 0.3; Normalized prediction duration = (5.2 - 2.0) / (6.0 - 2.0) = 0.8; Calculate the scores for each factor: F1 (delivery quantity) = 1 - 0.86 = 0.14; F2 (mileage) = 0.81; F3 (Region) = 1 (Kaiyang is the priority region); F4 (queue count) = 0.3; F5 (prediction duration) = 0.8; Calculate the overall score: Overall score = 0.2*0.14 + 0.2*0.81 + 0.2*1 + 0.2*0.3 + 0.2*0.8 = 0.61; Perform this calculation on all 48 vehicles to obtain their respective scores.

[0040] Step S4: Platform parking space scheduling decision The 48 vehicles were ranked from highest to lowest based on their overall scores. With a platform capacity of 35, the top 35 vehicles were assigned to the platform for the first round of loading, while the bottom 13 vehicles were temporarily placed in the queue.

[0041] Step S5: Queue Balancing Mechanism and Historical Record Update From all 48 vehicles, identify the 13 vehicles with the fewest historical queue counts and determine them as the final 13 vehicles in the queue. Then, increment the historical queue count of these 13 vehicles by 1.

[0042] Step S6: Balance Assessment and Feedback Optimization After scheduling is completed, the system calculates the balance of the new queuing times for all 48 vehicles.

[0043] Average = Total number of queues / 48; Standard deviation = sqrt(Σ(number of times each car queues - average value)² / 48); Balance = 1 - (standard deviation / mean); Assuming a calculated balance score of 0.88, this indicates very balanced scheduling. If the balance score falls below 0.7, an alert can be issued to the administrator, suggesting an adjustment to the weight w4 to enhance fairness.

[0044] The beneficial effects of this invention are as follows: This invention employs the XGBoost model to accurately predict delivery times, thereby shortening the average waiting time for vehicles. A comprehensive scoring model integrating multiple factors such as delivery volume, mileage, regional priority, historical queuing frequency, and predicted duration is constructed, making scheduling decisions more scientific and achieving dynamic and efficient allocation of platform parking resources, thus improving vehicle turnover rate per unit time. By introducing a priority factor based on queuing frequency and a dedicated queuing balancing mechanism, vehicles with more historical queuing frequency are given priority in scheduling and loading opportunities, fundamentally solving the problem of uneven vehicle queuing and improving driver satisfaction and management fairness. By calculating the balance index of historical queuing frequency and adjusting the model weights accordingly, the scheduling strategy possesses adaptive and continuous optimization capabilities, enabling scientific and efficient vehicle scheduling in long-term operation, maximizing platform resource utilization and ensuring fair vehicle queuing.

[0045] System Implementation Examples According to embodiments of the present invention, a platform parking space scheduling system for cigarette delivery vehicles is provided. Figure 5 This is a schematic diagram illustrating the composition of a cigarette delivery vehicle platform parking space scheduling system provided in one or more embodiments of this specification, such as... Figure 5 As shown, the cigarette delivery vehicle platform parking space scheduling system according to an embodiment of the present invention specifically includes: Data acquisition module 50: used to collect delivery route data and historical queuing data of vehicles to be dispatched on the same day; the delivery route data includes at least route mileage, delivery volume, number of delivery households, and administrative region information; the historical queuing data includes the cumulative number of times each vehicle has queued in the past. Delivery time prediction module 52: It is used to input the route mileage, route delivery volume and number of delivery households of each route into the pre-trained delivery time prediction model, and output the predicted delivery time of the route. Comprehensive scoring module 54: Used to calculate the comprehensive scheduling score of each vehicle based on preset scheduling factors; Platform parking space scheduling module 56: It is used to sort all vehicles to be scheduled based on the total platform capacity and the calculated comprehensive scheduling score, select the vehicles with the highest ranking and a number not exceeding the platform capacity to be assigned to platform parking spaces, and the remaining vehicles enter the queuing queue. Queuing balancing module 58: Used to determine the vehicle that ultimately needs to queue from the queuing queue or all vehicles to be dispatched according to a preset balancing strategy, and update its historical cumulative queuing count.

[0046] The embodiments of the present invention are system embodiments corresponding to the above method embodiments. The specific operation of each module can be understood by referring to the description of the method embodiments, and will not be repeated here.

[0047] Device Example 1 This invention provides an electronic device, such as... Figure 6 As shown, it includes: a memory 60, a processor 62, and a computer program stored in the memory 60 and executable on the processor 62. When the computer program is executed by the processor 62, it performs the following method steps: S1. Collect delivery route data and historical queuing data of vehicles to be dispatched on the same day; the delivery route data includes at least route mileage, route delivery volume, number of delivery households, and administrative region information; the historical queuing data includes the cumulative number of times each vehicle has queued in the past. S2. Input the route mileage, delivery volume, and number of customers for each route into the pre-trained delivery time prediction model, and output the predicted delivery time for that route. S3. For each vehicle, calculate the comprehensive scheduling score based on preset scheduling factors; S4. Based on the total platform capacity and the calculated comprehensive scheduling score, sort all vehicles to be scheduled, select the vehicles with the highest ranking and a number not exceeding the platform capacity to be assigned to platform parking spaces, and the remaining vehicles enter the queuing queue. S5. Based on the preset balancing strategy, determine the vehicle that will eventually need to queue from the queue or all vehicles to be dispatched, and update its historical cumulative queuing count.

[0048] Device Example 2 This invention provides a computer-readable storage medium storing an information transmission implementation program. When executed by a processor 62, the program performs the following method steps: S1. Collect delivery route data and historical queuing data of vehicles to be dispatched on the same day; the delivery route data includes at least route mileage, route delivery volume, number of delivery households, and administrative region information; the historical queuing data includes the cumulative number of times each vehicle has queued in the past. S2. Input the route mileage, delivery volume, and number of customers for each route into the pre-trained delivery time prediction model, and output the predicted delivery time for that route. S3. For each vehicle, calculate the comprehensive scheduling score based on preset scheduling factors; S4. Based on the total platform capacity and the calculated comprehensive scheduling score, sort all vehicles to be scheduled, select the vehicles with the highest ranking and a number not exceeding the platform capacity to be assigned to platform parking spaces, and the remaining vehicles enter the queuing queue. S5. Based on the preset balancing strategy, determine the vehicle that will eventually need to queue from the queue or all vehicles to be dispatched, and update its historical cumulative queuing count.

[0049] The computer-readable storage media described in this embodiment include, but are not limited to, ROM, RAM, disk, or optical disk.

[0050] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for scheduling parking spaces on a cigarette delivery vehicle platform, characterized in that, include: S1. Collect delivery route data and historical queuing data of vehicles to be dispatched on the same day; The delivery route data includes at least the route mileage, the volume of goods delivered, the number of customers delivered to, and administrative region information; The historical queuing data includes the cumulative number of times each vehicle has queued throughout its history. S2. Input the route mileage, delivery volume, and number of customers for each route into the pre-trained delivery time prediction model, and output the predicted delivery time for that route. S3. For each vehicle, calculate the comprehensive scheduling score based on preset scheduling factors; S4. Based on the total platform capacity and the calculated comprehensive scheduling score, sort all vehicles to be scheduled, select the vehicles with the highest ranking and a number not exceeding the platform capacity to be assigned to platform parking spaces, and the remaining vehicles enter the queuing queue. S5. Based on the preset balancing strategy, determine the vehicle that will eventually need to queue from the queue or all vehicles to be dispatched, and update its historical cumulative queuing count.

2. The method according to claim 1, characterized in that, The delivery time prediction model is a regression model trained based on the XGBoost algorithm. The XGBoost regression model is trained using historical delivery data, which includes route mileage, route delivery volume, number of delivery households, and corresponding actual delivery time.

3. The method according to claim 1, characterized in that, The scheduling factors include delivery volume factors that are negatively correlated with delivery volume, mileage factors that are positively correlated with route mileage, regional priority factors that are positively correlated with administrative region priority, queue number priority factors that are positively correlated with historical cumulative queue number, and delivery time factors that are positively correlated with predicted delivery time.

4. The method according to claim 3, characterized in that, The formula for calculating the comprehensive scheduling score is as follows: Overall score = w1 * F1 + w2 * F2 + w3 * F3 + w4 * F4 + w5 * F5; Among them, F1, F2, F3, F4, and F5 are the scores of the normalized delivery volume factor, mileage factor, regional priority factor, queue number priority factor, and delivery time factor, respectively; w1 to w5 are the weight coefficients of each factor, and w1 + w2 + w3 + w4 + w5 = 1.

5. The method according to claim 1, characterized in that, According to a preset balancing strategy, the vehicle that ultimately needs to queue is determined from the queuing queue or all vehicles to be dispatched, and its historical cumulative queuing count is updated. Specifically, this includes: From all vehicles to be dispatched, select a number of vehicles with the fewest historical cumulative queuing times. The number of these vehicles is equal to the number of vehicles that need to enter the queuing queue. These vehicles are then identified as the final queuing vehicles. The historical cumulative queuing count of the final queued vehicles is incremented by 1 for updating.

6. The method according to claim 1, characterized in that, The method further includes: Calculate the statistical standard deviation and average of the historical cumulative queuing times for all vehicles, and calculate the scheduling balance based on the statistical standard deviation and average. The weighting coefficients in the overall scheduling score are adjusted and optimized based on the aforementioned scheduling balance.

7. The method according to claim 6, characterized in that, The formula for calculating the scheduling balance is: Balance = 1 - (Standard deviation of queue count / Average of queue count); The closer the balance is to 1, the more balanced the distribution of queuing times.

8. A cigarette delivery vehicle platform parking space scheduling system, characterized in that, include: Data acquisition module: used to collect delivery route data and historical queuing data of vehicles to be dispatched on the same day; The delivery route data includes at least the route mileage, the volume of goods delivered, the number of customers delivered to, and administrative region information; The historical queuing data includes the cumulative number of times each vehicle has queued throughout its history. Delivery time prediction module: This module takes the route mileage, delivery volume, and number of customers for each route as input into a pre-trained delivery time prediction model and outputs the predicted delivery time for that route. Comprehensive scoring module: used to calculate the comprehensive scheduling score of each vehicle based on preset scheduling factors; Platform parking space scheduling module: Based on the total platform capacity and the calculated comprehensive scheduling score, it sorts all vehicles to be scheduled, selects the vehicles with the highest ranking and a number not exceeding the platform capacity to be assigned to platform parking spaces, and the remaining vehicles enter the queuing queue. Queue balancing module: used to determine the vehicle that will eventually need to queue from the queue or all vehicles to be dispatched according to a preset balancing strategy, and update its historical cumulative queuing count.

9. An electronic device, characterized in that, include: processor; as well as, A memory configured to store computer-executable instructions, which, when executed, cause the processor to implement the steps of the cigarette delivery vehicle platform parking scheduling method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, Used to store computer-executable instructions, which, when executed, implement the steps of the cigarette delivery vehicle platform parking space scheduling method as described in any one of claims 1 to 7.

Images