Logistics and Transportation Management Methods and Systems Based on Multi-Source Data Fusion

Abstract

This invention relates to the field of logistics management technology, specifically to a logistics transportation management method and system based on multi-source data fusion. The method includes the following steps: real-time monitoring of vehicle transportation time and calculation of congestion points; determining overlapping periods and generating rhythm windows based on estimated replenishment times; matching warehouse dispatch times and sorting them to generate path segment codes; fitting paths to filter vehicles and binding them with tags; sending instructions to monitor path consistency and generate scheduling results. In this invention, by real-time monitoring of transportation time and generation of congestion points, dynamically generating rhythm windows based on replenishment task times, encoding picking order, channel usage, and dispatch times into path segments, filtering vehicle resources based on path fitting and binding path tags, real-time monitoring of delivery consistency to generate scheduling instructions, unified analysis of multi-dimensional data and time-series-driven processing, reducing intervention and improving efficiency, matching trajectories with path codes and adjusting for congestion to avoid conflicts and redundancy, and shortening the response cycle.

Description

Technical Field

[0001] This invention relates to the field of logistics management technology, and in particular to a logistics transportation management method and system based on multi-source data fusion. Background Technology

[0002] The field of logistics management technology encompasses technologies related to the planning, organization, coordination, and control of goods throughout the entire process from supply to demand. Its core content revolves around transportation, warehousing, loading and unloading, and distribution, using scientific scheduling and resource allocation to improve the operational efficiency and responsiveness of the logistics system. Based on information management, this technology integrates key elements such as transportation route optimization, inventory management, and operational process control, forming a comprehensive management system covering procurement planning, transportation execution, order management, and customer service. It is widely used in various industries, including manufacturing, e-commerce, and retail, and is continuously expanding into smart logistics and supply chain collaborative management.

[0003] Among them, the logistics transportation management method based on multi-source data fusion refers to the unified integration of information from transportation vehicle positioning systems, warehousing equipment, logistics order platforms, and external environmental data sources to achieve information coordination and management throughout the entire logistics transportation task process. It primarily addresses the problems of data fragmentation, delayed updates, and lag in traditional logistics transportation. It employs data time synchronization technology, information entity association technology, and path status fusion calculation methods to uniformly model and integrate data such as delivery time and operational status of transportation vehicles along logistics routes in real time. Its components include standardized processing of data formats between logistics nodes, matching and verification between transportation vehicle trajectories and planned tasks, multi-dimensional temporal arrangement of logistics information, and rule-driven reconstruction of the transportation process. This falls under the subcategory of information fusion and path planning collaboration in intelligent logistics decision support systems.

[0004] Traditional logistics management relies on static route planning and discrete data sources. The lack of real-time data exchange between vehicle positioning, warehousing timing, and order status leads to low efficiency in cross-node collaboration. For example, when vehicles need to replan their routes due to sudden congestion, the system cannot quickly correlate warehousing operation status with available capacity, resulting in time-consuming and error-prone manual coordination. Existing technologies use fixed time windows to schedule replenishment tasks, failing to consider the impact of dynamic changes in transportation routes on warehousing resources. For instance, conflicts between replenishment periods and picking lane usage can easily cause warehousing operations to stall. Matching and verifying vehicle route records with transportation tasks relies on offline data, lacking fitting analysis of real-time route codes, resulting in high resource allocation redundancy. For example, the repeated scheduling of multiple empty vehicles in the same area, or insufficient capacity on high-demand routes, all stem from the lack of established time-series correlation rules between transportation tasks and warehousing operations. The data processing lag in existing technologies leads to a disconnect between transportation and warehousing, making it difficult to support the elastic scheduling needs of complex scenarios. Summary of the Invention

[0005] To address the technical problems existing in the prior art, embodiments of the present invention provide a logistics transportation management method and system based on multi-source data fusion. The technical solution includes the following:

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a logistics transportation management method based on multi-source data fusion, comprising the following steps:

[0007] S1: Monitor the transportation time of logistics vehicles in real time, input the vehicle transportation time into the principal component analysis model, calculate and record the congestion integral of the transportation route;

[0008] S2: Obtain the estimated start and end times of replenishment arrival for replenishment tasks in the next transportation cycle, determine overlapping replenishment periods by combining the congestion integral of the transportation route, generate multiple candidate periods for rhythm windows based on the start and end times, and determine the replenishment rhythm window.

[0009] S3: Match the expected start time and expected end time of replenishment in the replenishment rhythm window with the scheduled shipping time at the warehouse. Then, sort the picking and outbound order, handling channel usage order and scheduled shipping time data at the warehouse through a dynamic priority scheduling algorithm to generate path segment sequence codes.

[0010] S4: Call the path segment sequence code to calculate the fit of the vehicle path sequence records collected by the vehicle GPS, filter vehicle resources of the same sequence and bind the corresponding vehicle deployment path label;

[0011] S5: Based on the replenishment rhythm window matching judgment, send delivery instructions, monitor the consistency between the delivery path and the vehicle deployment path label in real time, and generate transportation scheduling adjustment results based on the monitoring results.

[0012] As a further aspect of the present invention, the congestion score of the transportation route includes vehicle transportation time, route congestion index, and node load compensation value; the replenishment rhythm window includes the rhythm window start time, rhythm window end time, and rhythm window alternative time period; the path segment sequence code specifically includes picking sorting code, channel occupancy sequence number, and dispatch time sequence number; the vehicle deployment path label includes path sequence fitting degree, vehicle matching sequence number, and path binding identifier; and the transportation scheduling adjustment result includes delivery path matching degree, vehicle path consistency, and real-time scheduling deviation.

[0013] As a further aspect of the present invention, the specific steps of real-time monitoring of the transportation time of logistics vehicles, inputting the vehicle transportation time into a principal component analysis model, calculating the congestion integral of the transportation route, supplementing node load integral data, and generating the congestion integral include the following:

[0014] S101: Monitor the start and end times of the transportation tasks of logistics vehicles. Based on the deviation between the start and end times of the transportation tasks obtained from the monitoring, analyze the duration of a single vehicle operation for the transportation task and obtain the transportation duration.

[0015] S102: Based on the input principal component analysis model of the transportation duration, and combined with the preset duration threshold range of the corresponding transportation route, the deviation is compared to establish the route congestion analysis result;

[0016] As a further aspect of the present invention, it is characterized by comparing the deviation of a preset time threshold range for the transportation route using the following formula:

[0017] ;

[0018] Calculate the current route congestion level of the node This yields the analysis results of the current route congestion level at the node;

[0019] in, is the total number of sample vehicles, and i is the index of the vehicle. It is the upper threshold. It is the lower threshold. It is the average transportation time of the transport vehicles. It is the standard deviation. This means that if the transportation time exceeds the upper threshold, a corresponding reward will be calculated. This indicates that if the transportation time is below the lower threshold, a corresponding penalty will be calculated. This represents the average congestion index of neighboring nodes. This is expressed as the baseline congestion index.

[0020] S103: Based on the analysis results of the route congestion level, perform integral mapping processing on the nodes associated with the transportation route to generate the congestion score of the node's current transportation route.

[0021] As a further aspect of the present invention, the specific steps for determining the replenishment rhythm window include: obtaining the estimated start and end times of replenishment tasks in the next transportation cycle, determining overlapping replenishment periods by combining the congestion integral of the transportation route, generating multiple candidate rhythm windows based on the start and end times, and performing displacement based on the start and end times.

[0022] S201: Arrival Time: Obtain the estimated arrival time and estimated departure time for each replenishment task in the next transportation cycle, classify the start and end times of each replenishment task according to the transportation cycle number, and locate the time boundary of the start and end time interval of the replenishment task in each cycle to generate the replenishment time interval.

[0023] S202: Based on the obtained replenishment time interval, call the congestion points of the transportation route, determine the overlap of time points between each replenishment time interval and the points of the corresponding node, and filter and collect the replenishment tasks with overlapping time periods to obtain conflict time period intervals.

[0024] S203: Based on the conflict time period interval, call the replenishment time period interval, perform time axis displacement processing on both ends of the conflict time period, including adjusting the start and end boundary times of the conflict time period as displacement operations, generating multiple non-overlapping new time periods, and removing windows that intersect with the start and end times of the replenishment task to obtain rhythm candidate intervals.

[0025] S204: Based on the obtained rhythm candidate intervals, sort all candidate intervals in ascending order according to their start time, filter out time window combinations that do not overlap within a single cycle, and generate replenishment rhythm windows.

[0026] As a further aspect of the present invention, the specific steps for matching and judging the expected arrival start time and expected arrival end time of replenishment in the replenishment rhythm window with the scheduled shipping time at the warehouse, and for serializing and sorting the picking and outbound order, the handling channel usage order, and the scheduled shipping time data at the warehouse to generate path segment sequence codes include:

[0027] S301: Obtain the expected start time and expected end time of replenishment in the replenishment rhythm window, match the start and end times of replenishment tasks in the replenishment rhythm window with the scheduled shipping time of the warehouse, call the warehouse task node information to make logical judgments on the matching group, gather the tasks with overlapping times into the same rhythm group, and generate the time matching result between replenishment tasks and warehouse nodes.

[0028] S302: Based on the time matching result between the replenishment task and the warehouse node, call the warehouse picking plan number, handling channel code and shipping appointment time corresponding to the task in the rhythm group, perform task association sequence binding on the three types of data, and perform joint sorting processing on the parameters in the task group according to the time sequence to obtain the sorted operation rhythm sorting sequence of the associated nodes.

[0029] S303: Based on the generated work rhythm sorting sequence, call the warehouse number, channel number and shipping number in the sorting sequence, and combine them in sequence to generate path segment structure information. Mark the path fields in the same rhythm group with unique picking sorting codes, establish sequence segment numbers and record the corresponding task path mapping relationships, and generate path segment sequence codes.

[0030] As a further aspect of the present invention, the specific steps of calling the path segment sequence code to perform similarity calculation on vehicle path sequence records collected by vehicle-mounted GPS, filtering vehicle resources with similar sequences, and binding corresponding vehicle path tags include:

[0031] S401: Call the path segment sequence encoding to obtain the vehicle path sequence record collected by the vehicle GPS, compare the matching degree of the three types of fields in the path segment, namely number node, time sequence and channel number, calculate the structural overlap rate between the current path segment and the preset benchmark value of the vehicle path segment, and generate the path fitting degree.

[0032] As a further aspect of the present invention, the current path segment and the vehicle path segment are processed using a preset reference value, employing the following formula:

[0033] ;

[0034] Calculate the structural overlap rate ;

[0035] in, It is a set of node numbers corresponding to the real-time data of the vehicle's current path status and the preset benchmark of the vehicle's path segment. The number of identical numbers is counted to form the node number matching count. It is the time difference tolerance threshold, which is determined by statistical quantiles. This indicates the total number of nodes in the current path segment. This represents the mean of the time sequence differences. Indicates the number of matching channel numbers. This represents the total number of channels in the current path segment.

[0036] S402: Based on the obtained path fitting degree, call the idle time and available loading status parameters of each vehicle in the vehicle status list in the current period, determine the path matching threshold through the path overlap rate, filter the vehicles with path fitting degree higher than the path matching threshold and meet the status conditions as a candidate set, and establish vehicle matching resources.

[0037] S403: Based on the acquired vehicle matching resources, calculate the distribution characteristics through time difference data to determine the path matching threshold, call the unique identifier code of each candidate vehicle and the corresponding path segment sequence code to generate a tag combination, collect the combined tags by vehicle, and write them into the vehicle task allocation field to establish vehicle deployment path tags.

[0038] As a further aspect of the present invention, based on the replenishment rhythm window matching judgment, sending delivery instructions, monitoring the consistency between the delivery route and the vehicle deployment route label in real time, and generating transportation scheduling adjustment results based on the monitoring results, the specific steps include:

[0039] S501: Obtain the arrival start and end time of the replenishment task in the replenishment rhythm window, call the vehicle delivery path label, match the start and end time of the replenishment task with the path segment time recorded in the corresponding vehicle path label segment by segment, and measure the time difference to generate the rhythm matching offset result of the current path task.

[0040] S502: Based on the obtained rhythm matching offset result, filter the path task numbers with time offset less than the offset threshold, call the corresponding vehicle number and replenishment task number to execute the combination, generate a delivery instruction for each pair of combinations, and record the path number and dispatch time to establish a delivery task.

[0041] S503: Call the obtained delivery task, collect the current location trajectory of the vehicle in delivery and compare it synchronously with the preset path segment sequence number, extract the current running number of the vehicle in each path segment and the path segment number of the delivery tag to determine the node consistency, obtain the proportion of the number of consistent nodes in each path segment to the total number, and generate the path consistency ratio.

[0042] S504: Based on the obtained path consistency ratio, call the path segment sequence encoding, replace the path segment number based on the real-time scheduling deviation of the path offset benchmark ratio, replace and record the path segment offset result and append it to the control scheduling log to generate the transportation scheduling adjustment result.

[0043] On the other hand, a logistics transportation management system based on multi-source data fusion is provided. This system is applied to a logistics transportation management method based on multi-source data fusion, and includes:

[0044] The node load integral module monitors the transportation time of logistics vehicles in real time, inputs the vehicle transportation time into the principal component analysis model, calculates the congestion integral of the transportation route, supplements the node load integral data, and transmits the generated congestion integral to the replenishment rhythm window module.

[0045] The replenishment rhythm window module obtains the estimated start and end times of replenishment tasks in the next transportation cycle, determines overlapping replenishment periods by combining the congestion integral of the transportation route, generates multiple rhythm window candidate periods based on the start and end times, and passes them to the path segment sequence generation module.

[0046] The path segment sequence generation module matches and judges the expected arrival start time and expected arrival end time of replenishment in the replenishment rhythm window with the scheduled shipping time at the warehouse end, and serializes and sorts the picking and outbound order, handling channel usage order and scheduled shipping time data at the warehouse end, generates path segment sequence codes and transmits them to the vehicle tag binding module.

[0047] The vehicle tag binding module calls the current path segment sequence in the path segment sequence encoding, compares the fit with the path segment sequence of the previous period, filters vehicle resources with similar sequences, binds the corresponding vehicle deployment path tags, and transmits them to the collaborative scheduling control module;

[0048] The collaborative scheduling and control module sends delivery instructions based on the replenishment rhythm window matching judgment, monitors the consistency between the delivery route and the vehicle deployment route label in real time, and generates transportation scheduling adjustment results based on the monitoring results.

[0049] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following:

[0050] This method monitors transportation time in real time and inputs it into a principal component analysis model to generate congestion scores. Combined with the start and end times of replenishment tasks, a dynamic rhythm window is generated to achieve precise alignment between transportation demand and warehousing operations. Path segment sequence coding is used to temporally orchestrate picking order, handling channel usage, and dispatch time, ensuring coordinated matching between warehousing resources and transportation tasks. Resources are screened based on the goodness of fit calculation of vehicle path sequence records. After binding path tags, delivery consistency is monitored in real time, and scheduling adjustment instructions are quickly generated. This method incorporates multi-dimensional data such as transportation time, congestion status, and warehousing operation processes into a unified analysis framework. Through temporal coding and dynamic rule-driven approaches, it reduces the need for manual intervention. Temporal coordination optimization of transportation routes and warehousing operations can reduce vehicle waiting and warehousing congestion, improving resource utilization. The similarity matching technology between path segment coding and vehicle trajectories, combined with a dynamic congestion score adjustment mechanism, proactively avoids route conflicts and capacity redundancy, shortening the delivery response cycle. Attached Figure Description

[0051] 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.

[0052] Figure 1 This is a schematic diagram of the workflow of the present invention;

[0053] Figure 2 This is a system flowchart of the present invention. Detailed Implementation

[0054] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0055] 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.

[0056] 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, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0057] 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.

[0058] 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.

[0059] Please see Figure 1 This invention provides a technical solution: a logistics transportation management method based on multi-source data fusion, comprising the following steps:

[0060] S1: Real-time monitoring of the transportation time of logistics vehicles, inputting the vehicle transportation time into the principal component analysis model, calculating and recording the congestion integral of the transportation route;

[0061] S2: Obtain the estimated start and end times of replenishment arrival for replenishment tasks in the next transportation cycle, determine overlapping replenishment periods by combining the congestion integral of the transportation route, generate multiple candidate periods for rhythm windows based on the start and end times, and determine the replenishment rhythm window.

[0062] S3: Match the expected start time and end time of replenishment in the replenishment rhythm window with the scheduled shipping time at the warehouse. Then, sort the picking and outbound order, the handling channel usage order, and the scheduled shipping time data at the warehouse through a dynamic priority scheduling algorithm to generate path segment sequence codes.

[0063] S4: Call the path segment sequence encoding to calculate the fit of the vehicle path sequence records collected by the vehicle GPS, filter vehicle resources with the same sequence, and bind the corresponding vehicle to the path tag.

[0064] S5: Based on the replenishment rhythm window matching judgment, send delivery instructions, monitor the consistency between the delivery route and the vehicle deployment route label in real time, and generate transportation scheduling adjustment results based on the monitoring results.

[0065] The congestion score of the transportation route includes vehicle transportation time, route congestion index, and node load compensation value. The replenishment rhythm window includes the start time of the rhythm window, the end time of the rhythm window, and the alternative time period of the rhythm window. The route segment sequence code specifically includes picking sorting code, channel occupancy sequence number, and dispatch time sequence number. The vehicle deployment route label includes route sequence fit degree, vehicle matching sequence number, and route binding identifier. The transportation scheduling adjustment results include delivery route matching degree, vehicle route consistency, and real-time scheduling deviation.

[0066] Please see Figure 1 The specific steps for real-time monitoring of logistics vehicle transport time, inputting vehicle transport time into the principal component analysis model, calculating the congestion integral of the transport route, supplementing node load integral data, and generating the congestion integral include:

[0067] S101: Monitor the start and end times of the transportation tasks of logistics vehicles. Based on the deviation between the start and end times of the transportation tasks obtained from the monitoring, analyze the duration of a single vehicle operation for the transportation task and obtain the transportation duration.

[0068] The vehicle's GPS module is used to collect the start time of the transportation mission of vehicle V001 in real time. and the end time Convert timestamps to minutes , Calculate the time difference Check if the timestamp synchronization error exceeds the threshold. If the clock deviation between GPS modules is 3 seconds, the data is retained; if the deviation is 7 seconds, it is marked as abnormal data and needs to be collected again. The same operation is performed on 5 sample vehicles to obtain the duration dataset. Excluding those that exceed physical limits The data outputs the effective transport duration result.

[0069] Table 1. Transportation Time Monitoring Data

[0070] Vehicle number Start time End time Duration (minutes) Data status V001 08:15:00 11:45:00 210 efficient V002 09:00:00 12:15:00 195 efficient V003 07:30:00 11:15:00 225 efficient V004 10:00:00 13:00:00 180 efficient V005 06:45:00 10:09:00 204 efficient

[0071] S102: Based on the input of transportation duration, the principal component analysis model is used to compare the deviations and establish the route congestion analysis results by combining the preset duration threshold range of the corresponding transportation route.

[0072] Call the transportation duration dataset for route R001 Calculate the mean minutes, standard deviation Minutes, set upper threshold Minutes, lower threshold Minutes, number of matching road segments for neighboring route R002 loaded. Total number of road sections Time difference Minutes, maximum tolerance Match congestion points by minute (based on the 95th percentile of historical data). Total number of congestion points Substitute the values ​​into the formula to calculate the coverage score:

[0073] ,

[0074] Comparison coverage threshold ,because The system determines that routes R001 and R002 have a significant spatiotemporal correlation and updates the congestion analysis results database accordingly.

[0075] Table 2 Route Matching Parameters

[0076] Vehicle number Number of matching road segments Total number of road sections Time difference (minutes) Maximum tolerance (minutes) Match congestion points Total congestion points V001 12 15 22.2 40 8 10 V002 10 15 18.5 40 6 10

[0077] ;

[0078] Calculate the current route congestion level of the node This yields the analysis results of the current route congestion level at the node;

[0079] in, is the total number of sample vehicles, and i is the index of the vehicle. It is the upper threshold. It is the lower threshold. It is the average transportation time of the transport vehicles. It is the standard deviation. This means that if the transportation time exceeds the upper threshold, a corresponding reward will be calculated. This indicates that if the transportation time is below the lower threshold, a corresponding penalty will be calculated. This represents the average congestion index of neighboring nodes. This is expressed as the baseline congestion index.

[0080] The signal is determined to be strongly correlated, triggering cross-route congestion warnings and route collaborative optimization. The association is determined to be weak, and only the local path is adjusted.

[0081] This result indicates the coverage score for route R001. If the baseline threshold is exceeded, the real-time congestion data of R002 (such as an average vehicle speed decrease of 20%) must be synchronized to R001.

[0082] S103: Based on the route congestion analysis results, perform integral mapping processing on the nodes associated with the transportation route to generate the congestion integral of the node's current transportation route;

[0083] The average speed of vehicles associated with nodes is obtained in real time based on the traffic monitoring platform. With delay time Call the predefined congestion level determination rules in the data, and and Each with a preset threshold , , , If a comparison is made, and If it is judged to be at a low congestion level, Located in the interval or Located in the interval If it is judged to be at the medium congestion level, or The system is classified as high congestion level, and points are assigned to each level. , , Call the road type database associated with the node to extract the road type parameters. (Main road) Secondary roads Branch roads ), calculate nodal integrals Traverse all nodes in the route and The total score is calculated by summing the scores. For example, the real-time data of node N004 is , ,because and It was determined to be at a medium level of congestion. The road type is a secondary arterial road. ,calculate The real-time data for node N005 is , ,because and It was determined to be at a high level of congestion. The road type is a main road. ,calculate Add them up to the total score;

[0084] Table 3. Examples of nodal integral accumulation representations

[0085]

[0086] As shown in Table 3, the total score Weighting coefficient The basis for this setting is: the average impact factor of main roads in 100 congestion events is... Secondary arterial roads are The branch road is Normalize the impact factor to the main channel Secondary roads branch road threshold By setting the integral distribution of highly congested routes in statistical data, for example, selecting 50 highly congested routes, the average total integral is set to... The standard deviation is The threshold is set as the mean minus the standard deviation. Rounded down to ,like This triggers a path optimization command.

[0087] Please see Figure 1 The process involves obtaining the estimated start and end times of replenishment tasks within the next transportation cycle, determining overlapping replenishment periods based on the congestion integral of the transportation route, and generating multiple candidate periods for the replenishment rhythm window based on the start and end times. The specific steps for determining the replenishment rhythm window include:

[0088] S201: Arrival Time: Obtain the estimated arrival time and estimated departure time for each replenishment task in the next transportation cycle, classify the start and end times of each replenishment task according to the transportation cycle number, and locate the time boundary of the start and end time interval of the replenishment task in each cycle to generate the replenishment time interval.

[0089] Based on the task scheduling database of the transportation management system, the estimated arrival time of all replenishment tasks in the next transportation cycle is extracted. Compared to the expected departure time Call the transportation cycle division rule (each cycle is numbered in 4-hour increments). (The cycle start time is 00:00, 04:00, 08:00, etc.), and each task's and Compared with the periodic time boundary, if Falling in the cycle Within the specified time frame, the task will be categorized as follows: After traversing all tasks, for each cycle Extreme value location is performed on the task time within the period, and the earliest arrival time of all tasks within the period is extracted. and latest departure time Generate replenishment time interval For example, a certain transportation cycle It includes 3 replenishment tasks, and their time data is as follows:

[0090] Table 4. Examples of Time Classification for Replenishment Tasks

[0091] Task ID Estimated arrival time (hours:minutes) Estimated departure time (hour:minute) Periodic number Periodic time interval (hours:minutes) T001 08:15 09:30 C001 08:00-12:00 T002 09:45 10:15 C001 08:00-12:00 T003 10:00 11:45 C001 08:00-12:00

[0092] As shown in Table 4, the period The time interval is 08:00-12:00. Iterate through the arrival and departure times of tasks T001-T003 and extract... and However, adjustments need to be made according to the cycle boundary rules: if the cycle start time is 08:00, then Force alignment to 08:00, if If the cycle ends at 12:00, it will be split into multiple cycles. For example, if task T003's departure time of 11:45 does not exceed the limit, then the cycle will continue. The final time interval is The length of the time interval is calculated as follows: .

[0093] S202: Based on the obtained replenishment time interval, call the congestion points of the transportation route, determine the overlap of time points between each replenishment time interval and the points of the corresponding node, and filter and collect the replenishment tasks with overlapping time periods to obtain the conflict time period interval.

[0094] Based on the obtained replenishment time intervals, the congestion score data table for the transportation routes (including Table 1) is accessed to extract the start and end times of each replenishment task. This includes replenishment task A, whose time interval is from 09:00 to 11:00 on April 18, 2025, and task B, whose time interval is from 14:30 to 16:00. The congestion score sequence [85, 90, 95] for node N1 from 09:00 to 12:00 and the score sequence [70, 75, 95] for node N2 from 14:00 to 17:00 are retrieved.

[80] The time interval of the replenishment task is aligned minute by minute with the time point of the node points. For example, if there is an overlap between 09:00-11:00 for task A and 09:00-12:00 for N1 in the 09:00-11:00 period, the points per minute are compared to see if they exceed the preset threshold of 70. If the points at a single time point are ≥70, it is marked as a conflict. For example, if all points of task A are ≥85 in the 09:00-11:00 period, it is judged as a conflict throughout the entire time period. If the points of task B rise from 75 to 80 in the 14:30-16:00 period, it is judged as a conflict throughout the entire time period. Finally, the conflict time periods are collected as [09:00-11:00, 14:30-16:00].

[0095] Table 5 Congestion Indicators for Transportation Routes

[0096] node Time range Congestion points N1 09：00-12：00 85-95 N2 14：00-17：00 70-80

[0097] As shown in Table 5, the congestion score range for node N1 from 09:00 to 12:00 is 85 to 95, and for node N2 from 14:00 to 17:00 it is 70 to 80. The threshold is set to 70. Data analysis shows that when the score is ≥70, the node's traffic efficiency decreases by more than 30%. By comparing the time interval of the replenishment task with the score interval, when the task time is completely included in the time period with a score ≥70, it is judged as a conflict. This includes task A from 09:00 to 11:00, which is completely within the high score period of N1, and task B from 14:30 to 16:00, which is completely within the high score period of N2. The screening of conflict time periods is completed by comparing minute by minute, and finally outputting a list of conflict time periods.

[0098] S203: Based on the conflict time period interval, call the replenishment time period interval, perform time axis displacement processing on both ends of the conflict time period, including adjusting the start and end boundary times of the conflict time period as displacement operations, generating multiple non-overlapping new time periods, and removing windows that intersect with the start and end times of the replenishment task to obtain the rhythm candidate interval.

[0099] Based on the conflict time intervals [09:00-11:00, 14:30-16:00], the original time intervals of replenishment task A (09:00-11:00) and task B (14:30-16:00) are called. The time axis displacement step is set to 30 minutes (calculated based on the median of historical data samples [20, 25, 30, 35, 40] minutes, and the third value of 30 is taken after sorting). The start and end points of the conflict time intervals are shifted forward and backward respectively. For example, the start point of the conflict time interval 09:00 is shifted forward 30 minutes to 08:30, and the end point 11:00 is shifted backward 30 minutes to 11:30, generating new time intervals 08:30-10:30 and 09:30-11:30. The new time intervals are then compared with the original replenishment time 09:00-11:00 for overlap judgment. The specific judgment criterion is: if the start time of the new time interval is... satisfy And the end time of the new time period satisfy If there is no intersection, then it is determined that there is no intersection; otherwise, if and If there is overlap (for example, the start time of the new time period 09:30-11:30 is 540 minutes, which is greater than or equal to the start time of the original task, and the end time is 690 minutes, which is less than or equal to the end time of the original task, 660 minutes, which is not true, so there is partial overlap), then the windows with overlap are removed, and the new time period 08:30-10:30 with no overlap is retained. Similarly, for the conflicting time period 14:30-16:00, the time period 14:00-15:30 is moved forward by 30 minutes to generate 14:00-15:30 and 15:00-16:30 is moved backward by 30 minutes to generate 15:00-16:30, and the following is judged. The start time of 14:00-15:30 is 840 minutes < the original task start time of 870 minutes (14:30) and the end time is 930 minutes ≤ the original task end time of 960 minutes (16:00), which is not true. Therefore, it is determined that there is no overlap and this interval is retained. However, the start time of 15:00-16:30 is 900 minutes ≥ 870 minutes and the end time is 990 minutes ≤ 960 minutes, which is not true. Since there is overlap, it is removed. Finally, the candidate rhythm intervals are obtained as [08:30-10:30, 14:00-15:30].

[0100] Table 6 Time axis displacement parameters and results

[0101] Conflict Time Period Displacement direction Step length (minutes) New time period Intersection determination result 09:00-11:00 Move forward 30 08:30-10:30 No intersection 09:00-11:00 Move back 30 09:30-11:30 There is overlap 14:30-16:00 Move forward 30 14:00-15:30 No intersection 14:30-16:00 Move back 30 15:00-16:30 There is overlap

[0102] As shown in Table 6, the displacement step size of 30 minutes is calculated from historical data samples. The specific steps are as follows: collect the difference between adjacent feasible time windows in the replenishment task adjustment records of the past three months. The recorded values ​​are [20, 25, 30, 35, 40] minutes. After sorting, the median of 30 minutes is taken. The time overlap is determined by converting minutes into numerical values. For example, 09:00 is converted to 540 minutes. The time period is changed from 11:00 to 660 minutes. The new time period, 08:30-10:30, starts at 510 minutes and ends at 630 minutes. Compared with the original task time of 540-660 minutes, if... and It is not true, but and If the new time period ends at 630 minutes (10:30), it is considered partially overlapping. However, according to the correction logic (only retained when the new time period is completely outside the original task time), since the end time of the new time period of 630 minutes (10:30) is earlier than the start time of the original task of 540 minutes (09:00), it is not valid. Therefore, it is corrected to allow partial non-inclusive overlap, only removing windows that completely contain or intersect, and finally calculating the range inclusion relationship of minute values. or ) Filter out candidate intervals with no overlap, for example, the 840-930 minute interval of 14:00-15:30 satisfies the original task's 870-960 minute interval. and It is not true, but and According to the correction logic, it is still determined that there is no intersection because it does not completely cover the original task time window, and finally the rhythm candidate interval list is output.

[0103] S204: Based on the obtained rhythm candidate intervals, sort all candidate intervals in ascending order according to their start time, filter the time window combinations that do not overlap within a single cycle, and generate replenishment rhythm windows.

[0104] Based on the candidate time intervals [08:30-10:30, 14:00-15:30], the start time parameters of all candidate intervals are called (e.g., 08:30 is converted to a minute value of 510, 14:00 is converted to 840). The intervals are then sorted in ascending order according to their start time values, generating a sorted list [510-630 (08:30-10:30), 840-930 (14:00-15:30)]. Each time interval in the list is iterated over, starting from the first interval, and its end time is compared. With the start time of the next time period ,like (in If the preset time interval threshold is 15 minutes (based on the shortest passage interval time of warehouse forklifts), then it is determined that there is no overlap and the next time period is retained; otherwise, it is discarded. For example, comparing 510-630 and 840-930, the calculation 630+15=645≤840 satisfies the condition and both are retained. If there is a third time period 960-1020 (16:00-17:00) in the list, then the comparison 930+15=945≤960 satisfies the condition and is retained. If there are overlapping time periods such as 840-930 and 900-1000, the calculation 930+15=945≤900 does not hold true, then 900-1000 is discarded. Finally, a non-overlapping time window combination [08:30-10:30, 14:00-15:30] is generated.

[0105] Table 7. Candidate Interval Ranking and Screening Results

[0106] Candidate time period Start time (minutes) End time (minutes) Should it be retained? 08:30-10:30 510 630 yes 14:00-15:30 840 930 yes 15:45-17:00 945 1020 yes

[0107] As shown in Table 7, the time interval threshold The interval is set to 15 minutes, determined by statistically analyzing the minimum buffer time required for a warehouse forklift to leave a node after loading and unloading goods until the start of the next task. Specifically, data on the intervals of 50 forklift tasks over the past week are collected, recording samples of [10, 12, 15, 18, 20 minutes]. The 80th percentile of 15 minutes is used. During filtering, starting from the first sorted time period, the interval between adjacent time periods is checked to see if it is ≥15 minutes. For example, the interval between the first time period 08:30-10:30 (510-630) and the second time period 14:00-15:30 (840-930) is 840- If 630 = 210 minutes ≥ 15 minutes, retain it. If a third time period exists (15:45-17:00 (945-1020), check that its interval with the second time period is 945-930 = 15 minutes, which meets the threshold, and retain it. If the interval between a time period and the previous time period is less than 15 minutes, for example, 14:00-15:30 (840-930) and 15:00-16:00 (900-960), then the calculation 930+15=945≤900 is not true, and it is judged as an overlap. 15:00-16:00 is removed. Finally, output a list of non-overlapping time window combinations.

[0108] Please see Figure 1 The specific steps for matching the expected start and end times of replenishment arrival in the replenishment rhythm window with the scheduled shipping times at the warehouse end, and serializing and sorting the picking and outbound order, handling channel usage order, and scheduled shipping time data at the warehouse end to generate path segment sequence codes include:

[0109] S301: Obtain the estimated start and end times of replenishment arrival in the replenishment rhythm window, match the start and end times of replenishment tasks within the replenishment rhythm window with the scheduled shipping times at the warehouse, call the warehouse task node information to perform logical judgment on the matching group, group tasks with overlapping times into the same rhythm group, and generate the time matching result between replenishment tasks and warehouse nodes.

[0110] Based on replenishment rhythm window Extract the estimated start time of replenishment task A. (Convert to minute values) ) and end time ( (minutes), Task B ( minutes) and ( (minutes), call the shipping schedule window of warehouse node N1. ( minutes) and ( (minutes), and node N2 ( minutes) and ( After converting the replenishment task time and warehousing node time into minute values, the following logical judgments are executed item by item.

[0111] 1. Time overlap determination: For each pair of replenishment tasks and warehouse nodes, check whether the time overlap is satisfied. For example, task A ( minutes) and N1 ( (minutes), calculation and If the conditions are met, group them into the same rhythm group, task B ( minutes) and N2 ( (minutes), calculation and If the condition is met, group them into the same rhythm group. 2. Non-overlapping task processing: If the time window of replenishment task C is... ( minutes) and N1 ( (minutes), calculation If a task is determined to be non-overlapping, it will be grouped separately. 3. Multi-node priority allocation: If a replenishment task overlaps with multiple nodes simultaneously (e.g., task A overlaps with both N1 and N3), the node load factor will be calculated. For example, N1 N3 ,choose Smaller N1 values ​​are grouped together.

[0112] Table 8 Time Matching Judgment Results

[0113] Replenishment task Restocking time (minutes) Warehouse Node Storage time (minutes) Do they overlap? A 510-630 N1 540-720 yes B 840-930 N2 780-960 yes C 480-510 N1 540-720 no

[0114] As shown in Table 8, the formula for determining time overlap is:

[0115] ,

[0116] in , , , All passed Transformation, such as N1 Convert to Minutes, node load factor The final list of rhythm groups is generated by dividing the number of real-time tasks by the preset maximum capacity (e.g., N1 can support a maximum of 5 tasks). .

[0117] S302: Based on the time matching results between the replenishment task and the warehouse node, call the warehouse picking plan number, handling channel code and shipping appointment time corresponding to the task in the rhythm group, perform task association sequence binding on the three types of data, and perform joint sorting processing on the parameters in the task group according to the time sequence to obtain the sorted operation rhythm sorting sequence of the associated nodes.

[0118] Based on the time matching results between replenishment tasks and warehouse nodes (e.g., replenishment task arrival time is 2025-04-18 10:00:00, warehouse node A's inbound deadline is 10:30:00, and node B's is 11:00:00), the picking plan number corresponding to the task within the rhythm group is called (e.g., task group T001 contains picking plans P001 and P002). The associated handling channel code of the picking plan is retrieved from the warehouse management system (e.g., channel C01 corresponds to P001, and C02 corresponds to P002). The picking plan number, handling channel code, and shipping appointment time (e.g., P001, P002, and P002) are then matched. The shipment times are 10:15:00 for P1 and 10:45:00 for P2. The shipments are arranged in chronological order. The specific operation is as follows: extract the hour and minute values ​​of the shipment appointment time (10:15 is converted to the value 1015, and 10:45 is converted to the value 1045), arrange the picking plan number and channel code in ascending order of value (P001-C01 are arranged before P002-C02), and if the times are the same, arrange them in ascending order of the last digit of the channel code (e.g., C01 takes priority over C03), and finally generate the sorted sequence (T001-P001-C01-10:15:00, T001-P002-C02-10:45:00).

[0119] Table 9 Sorted Sequences:

[0120] Warehouse node coding Replenishment task arrival time Warehouse entry deadline Number of available channels WH-A 2025-04-18 10:00:00 2025-04-18 10:30:00 2 WH-B 2025-04-18 10:00:00 2025-04-18 11:00:00 3

[0121] As shown in Table 9, the difference between the arrival time of the replenishment task and the inbound deadline of the warehouse node is used as the criterion (30 minutes for WH-A, 60 minutes for WH-B). If the time difference is ≤15 minutes (the threshold is set according to the "Emergency Task Processing Time Limit" clause in the warehouse node operation manual), then nodes with ≥2 available channels are prioritized for allocation (WH-A meets the condition). Otherwise, nodes with a larger time difference are selected (WH-B's time difference exceeds the threshold and requires manual review). In the example, the task arrival time is 10:00:00, and the inbound deadline of WH-A is 10:30:00. The calculated time difference is 30 minutes (exceeding the threshold of 15 minutes). Therefore, channel availability needs to be checked: WH-A currently has 2 available channels (meets the ≥2 condition), so it is allocated to WH-A; otherwise, a backup node needs to be called.

[0122] The sorting of shipping appointment times is as follows: Convert the times to 4-digit numbers (e.g., 10:15 → 1015, 10:30 → 1030), and sort them in ascending order. If the numbers are the same, sort them in ascending order by the last digit of the channel code (e.g., C01 comes first in C01 and C02). Task group T001 contains two shipping times (10:15 and 10:45), which are converted to 1015 and 1045 respectively. Sorting them in ascending order results in 1015 → 1045, with the corresponding associated parameters being P001-C01 and P002-C02 respectively. If there are tasks with the same time (e.g., both at 10:15), further sort them by the last digit of the channel code (e.g., C01 takes priority in C01 and C03).

[0123] The final generated job rhythm sorting sequence is: T001-P001-C01-10:15:00, T001-P002-C02-10:45:00. The logic is that time difference takes precedence over channel availability, and the last digit of the channel code is used as a secondary sorting criterion.

[0124] S303: Based on the generated work rhythm sorting sequence, call the warehouse number, channel number and shipping number in the sorting sequence, and combine them in sequence to generate path segment structure information. Mark the path fields within the same rhythm group with unique picking sorting codes, establish sequence segment numbers and record the corresponding task path mapping relationships, and generate path segment sequence codes.

[0125] Based on the work rhythm sorting sequence (e.g., a sequence containing warehouse number WH-A, channel number C01, and shipping number S001, arranged chronologically as WH-A→C01→S001), extract the warehouse number (WH-A), channel number (C01), and shipping number (S001), and concatenate them into a path segment structure information (WH-A-C01-S001) in the format of "warehouse-channel-shipment". Then, process the path fields within the same rhythm group (e.g., rhythm group T001 contains WH-A-C01-S001 and WH-A-C02-S002). Uniqueness check: Extract the last two characters of the warehouse number (A), the last two digits of the channel number (01), and the last three digits of the shipping number (001). Generate a unique code (A-01-001) according to the rule of "last digit of warehouse number + last digit of channel number + last digit of shipping number". If the code is duplicated (e.g., A-01-001 already exists), append a sequence identifier (A-01-001-1) to the end, establish a sequence segment number (incrementing from 001 in the generation order), bind the sequence segment number to the path segment code (001 corresponds to A-01-001), and store it in the task path mapping table.

[0126] Table 10 Task Path Mapping Relationship Table:

[0127] Warehouse Number Channel number Shipping number Path segment encoding Serial segment number WH-A C01 S001 A-01-001 001 WH-A C02 S002 A-02-002 002 WH-B C03 S003 B-03-003 003

[0128] As shown in Table 10, the generation rules for path segment codes are as follows: extract the last letter of the warehouse number (e.g., extract A from WH-A), the last two digits of the channel number (extract 01 from C01), and the last three digits of the shipping number (extract 001 from S001), and concatenate them to form A-01-001. If the same code exists within the same rhythm group (e.g., two A-01-001s), then append a sequence identifier (A-01-001-1). In the example, rhythm group T001 contains channels C01 and C02 of warehouse WH-A, with shipping numbers S001 and S002 respectively, generating path segment codes A-01-001 and A-02-002. The sequence segment numbers are assigned as 001 and 002 according to the generation order.

[0129] The specific steps for uniqueness verification are as follows: Call the path segment encoding library, compare the newly generated code (A-01-001) with each record in the library. If a complete match exists, append a "-" and the current time in minutes (e.g., if the current time is 10:15, append -15) to the end to generate A-01-001-15. If the match is still repeated (e.g., if A-01-001-15 already exists in the library), continue to append seconds (e.g., append -30 if the time is 10:15:30) until a unique match is found. Assuming A-01-001 already exists in the database, the new code is appended with -15, generating A-01-001-15. If another task generates the same code simultaneously, the number of seconds is further appended (e.g., A-01-001-15-30). The allocation rule for sequence segment numbers is as follows: starting from 001, the segment number increments by 1 for each new path segment code. If the same rhythm group contains multiple path segments (e.g., T001 contains A-01-001 and A-02-002), consecutive segment numbers (001 and 002) are assigned according to the generation order of the path segment codes. In the example, the path segment code B-03-003 is generated for warehouse WH-B's channel C03 and shipping S003, with a segment number of 003.

[0130] The task path mapping relationship is recorded as follows: the sequence segment number (001), path segment code (A-01-001), warehouse number (WH-A), channel number (C01), and shipping number (S001) are stored in a database table, with foreign keys connecting the fields. If the path segment code is modified due to a conflict (e.g., A-01-001-15), the code field in the mapping table is updated synchronously, and the original code is retained as a record. The final generated path segment sequence codes are: 001-A-01-001, 002-A-02-002, and 003-B-03-003. The logic is to bind the unique code and sequence segment number in chronological order to ensure the traceability of the task path.

[0131] Please see Figure 1The specific steps for calling the path segment sequence encoding to perform similarity calculations on vehicle path sequence records collected by vehicle-mounted GPS, filtering vehicle resources with similar sequences, and binding corresponding vehicle path tags include:

[0132] S401: Call the path segment sequence encoding to obtain the vehicle path sequence record collected by the vehicle GPS, compare the matching degree of the three types of fields in the path segment, namely number node, time sequence and channel number, calculate the structural overlap rate between the current path segment and the preset benchmark value of the vehicle path segment, and generate the path fitting degree.

[0133] Access vehicle route sequence records collected by the vehicle's GPS ,in Number the nodes of the path segment. For timestamps, Number the channel and extract the current path segment. traversal For each vehicle's path segment, the node number, time sequence, and channel number are matched item by item. For example, the path segment of vehicle A is... The current path segment is The node number matching number is 2 (101, 102), and the time sequence difference is calculated as follows: minutes and Minutes, mean Minutes, channel number matching count is 2 (all 5), path fit degree Set the path matching threshold to 85% and filter. Vehicle B's route segment is The number of nodes matching the current path segment is 1 (only 101), and the time sequence difference is... Minutes (exceeding tolerance of 10 minutes), channel number matching count 0. , The vehicle route matching data was excluded. Table 11 lists the vehicle route matching data.

[0134] Table 11 Vehicle Route Matching Data Table

[0135] Vehicle number Node matching ratio Time matching ratio Channel matching ratio Structural overlap rate Path fit (%) A 1.0 0.8 1.0 0.933 93.3 B 0.5 0.0 0.0 0.167 16.7 C 1.0 0.7 1.0 0.900 90.0

[0136] As shown in Table 11, vehicles A and C... All values ​​above 85% were added to the candidate set. Data analysis showed that a 10% reduction in node matching error improved task efficiency by 15%, while a 10% reduction in time sequence error only improved efficiency by 3%, and a 10% reduction in channel number error improved efficiency by 1%. Weights were assigned using linear regression, and the tolerance threshold for time sequence difference was set at 10 minutes. This was because a time deviation exceeding 10 minutes increases the task scheduling conflict rate by 25%, for example, if the time difference for vehicle D is 12 minutes. The calculation result is (Assigned 0 due to exceeding limits), in the channel number matching judgment, if the vehicle path is inconsistent with the current path channel (e.g., vehicle B's channel 6 vs. the current channel 5), it is directly counted as a 0 match. The threshold of 85% is based on the task success rate statistics. The task success rate was 92%. When the success rate dropped to 65%, the threshold was adjusted to 85% to filter out vehicle A. ) and C ( The three matching ratios are added together and the average is taken.

[0137] ;

[0138] Calculate the structural overlap rate ;

[0139] in, It is a set of node numbers corresponding to the real-time data of the vehicle's current path status and the preset benchmark of the vehicle's path segment. The number of identical numbers is counted to form the node number matching count. It is the time difference tolerance threshold, which is determined by statistical quantiles. This indicates the total number of nodes in the current path segment. This represents the mean of the time sequence differences. Indicates the number of matching channel numbers. This represents the total number of channels in the current path segment.

[0140] S402: Based on the obtained path fit degree, call the idle time and available loading status parameters of each vehicle in the vehicle status list in the current period, determine the path matching threshold through the path overlap rate, filter the vehicles with path fit degree higher than the path matching threshold and meet the status conditions as candidate sets, and establish vehicle matching resources.

[0141] Based on the current path coordinate point sequence With vehicle path coordinates sequence Calculate the path fit degree The specific process is as follows: extraction and Center front points ( ), calculate the lateral distance deviation for each point. Summing and then taking the mean ,Will Mapped to (like ,but For example, the route of a vehicle and the five points preceding the current route. The dimensions are 0.8, 1.2, 0.5, 1.0, and 0.7 meters respectively. Rice, then The path matching threshold is set to 85, and the idle time in the vehicle status list is compared. (Unit: minutes) and available load capacity (Unit: Percentage), Filter and The vehicle, in the example, vehicle A , , Vehicle B meets the criteria and is added to the candidate set. , , ,because Excluded, Table 12 lists the candidate vehicle state parameters.

[0142] Table 12 Candidate Vehicle Status Parameters

[0143] Vehicle number Free time during assignment (minutes) Available load capacity (%) Path fit A 45 90 91.6 C 35 95 86.2 D 40 85 87.5

[0144] As shown in Table 12, vehicles A, C, and D... All are above 85, and , This creates vehicle matching resources.

[0145] Path matching threshold The setting is based on the path fit degree in statistical tasks. The average delay rate for vehicles to complete tasks was 5%, while The average vehicle delay rate was 22%, which was adjusted... Keep the latency rate below 10%, for example, when At that time, the latency rate was 15%. The latency rate was reduced to 8%, and 85 was ultimately selected as the threshold for job idle time. The minute setting is based on an average vehicle loading and unloading time of 25 minutes, with a 5-minute tolerance. For example, if a task is expected to take 28 minutes, and the vehicle... Then the remaining time Minutes need to be excluded, but in practice... If the number of vehicles selected is 30, the system will automatically assign higher-priority vehicles based on the available loading capacity threshold. The setting is based on: when At that time, additional restocking of vehicles was required, resulting in an 18% increase in task time. In the example, vehicle E... The path fit is 89, because Excluded.

[0146] S403: Based on the acquired vehicle matching resources, calculate the distribution characteristics through time difference data to determine the path matching threshold, call the unique identifier code of each candidate vehicle and the corresponding path segment sequence code to generate a tag combination, collect the combined tags by vehicle, and write them into the vehicle task allocation field to establish vehicle deployment path tags.

[0147] Extract unique identifier codes from vehicle matching resources. (For example ), call the path segment sequence encoding corresponding to each vehicle (For example ),Will and according to" The format is concatenated to generate combined tags. In the example, the path segment code for vehicle VH001 is PS001-202404, generating the tag "VH001-PS001-202404". All candidate vehicles are traversed. If a vehicle has multiple path segments (e.g., vehicle VH003 is associated with PS003-202404 and PS004-202404), multiple tags are generated and merged into a comma-separated string "VH003-PS003-202404, VH003-PS004-202404". During aggregation, the tags are... Index groups, for example, the label for vehicle VH002 is "VH002-PS002-202404", and this is written into the database task assignment field. The “Path Labels” sub-item, Table 13 shows the label aggregation results for the three candidate vehicles.

[0148] Table 13 Vehicle Task Assignment Fields and Route Labels

[0149] Vehicle number Path segment encoding Combination tags VH001 PS001-202404 VH001-PS001-202404 VH002 PS002-202404 VH002-PS002-202404 VH003 PS003-202404PS004-202404 VH003-PS003-202404 VH003-PS004-202404

[0150] As shown in Table 13, vehicle VH003 contains two path segment codes, generating two labels separated by a comma. The label generation rules include a unique identifier code. The format is "VH" + 4 digits (e.g., VH001 to VH999), path segment code. The format is "PS" + 3 digits + "-" + 6 digits for year and month (e.g., PS001-202404 represents the first path segment in April 2024). When combining these characters, the original encoded characters must be strictly preserved; truncation or escaping is prohibited. For example, in the path segment PS002-202404, "202404" is the year and month identifier and can be directly concatenated as part of the tag. During the collection process, the system will... Hash values ​​are indexed to... The time complexity is used to locate vehicle task assignment fields, such as the hash value of vehicle VH001, through a hash function. Mapped to memory address 0x3A7D, tag data is directly written. For vehicles with multiple path segments, tags are sorted in ascending order of timestamps. For example, for vehicle VH003, the path segment PS003-202404 has a timestamp of 2024-04-2008:00:00, and PS004-202404 has a timestamp of 2024-04-2008:30:00. The tags are arranged in the order of "PS003-202404, PS004-202404". The path tag is written to the field. At that time, the system checks whether the field length exceeds 256 characters. If it does, a compression algorithm is triggered. For example, vehicle VH004 contains 10 path segments, and the original tag length is 215 characters, which is within the limit, so it is written directly. Vehicle VH005 contains 15 path segments, and the tag length is 310 characters. The LZW compression algorithm is used, and the compressed length is 172 characters. The writing is completed, and after the vehicle deployment path tags are established, the system will... The fields are synchronized to the dispatch center. For example, the tag "VH001-PS001-202404" of vehicle VH001 is parsed as a deployment instruction: allocate path segment PS001-202404 to VH001.

[0151] Please see Figure 1 Based on the replenishment rhythm window matching judgment, delivery instructions are sent, and the consistency between the delivery route and the vehicle deployment route label is monitored in real time. The specific steps for generating transportation scheduling adjustment results based on the monitoring results include:

[0152] S501: Obtain the arrival start and end times of the replenishment task in the replenishment rhythm window, call the vehicle deployment path label, match the start and end times of the replenishment task with the path segment time recorded in the corresponding vehicle path label segment by segment, and measure the time difference to generate the rhythm matching offset result of the current path task.

[0153] Extract the arrival time range of replenishment tasks from the replenishment rhythm window. (For example , ), parse the path segment time in the vehicle deployment path tags (For example, the path label "VH001-PS001-202404" for vehicle VH001 corresponds to the time of path segment PS001.) ), calculate the time difference for each path segment and If the path segment consists of multiple segments (such as PS003 and PS004 for vehicle VH003), then each segment is matched and the average value is taken. For example, the time for PS003 of VH003 is... PS004 is , minute, minute, minute, Minutes, mean , Total offset minutes (time difference weight) , ), set offset threshold minutes, if Then it is determined that the match is successful, in the example of VH003. Exceeding the threshold, it is excluded; the path time of vehicle VH002 is... , , , If the value is below the threshold, the match is successful. Table 14 shows the offset calculation results for the three vehicles.

[0154] Table 14 Replenishment Task Time and Route Segment Time Offset

[0155]

[0156] As shown in Table 14, vehicles VH001 and VH002... All values ​​below the threshold of 30 are marked as a successful match, and the weight is... and The setting is based on the fact that the deviation in the start time of replenishment tasks has a higher weighting on the impact of warehouse inventory preparation. Data analysis shows that... For every additional 10 minutes, the replenishment delay rate increases by 12%, while Adding 10 minutes only increases the delay rate by 5%, by assigning weights through linear regression and offsetting the threshold. The minute setting is based on actual operational tolerance: a time offset exceeding 30 minutes will increase the subsequent vehicle dispatch conflict rate by 40%, for example, vehicle VH004. The conflict rate is 42%, therefore the threshold is set to 30. In the time difference calculation, if a path segment crosses multiple replenishment windows (e.g., the path segment of vehicle VH005 is...), the conflict rate is 42%, therefore the threshold is set to 30. If the time period overlaps with the replenishment window, then only the time period that overlaps with the replenishment window will be matched. For example, if the overlapping time period is... ,calculate , , Match successful. For non-hourly time data (such as...) Convert the time to minutes (08:12:37 = 8 × 60 + 12 + 37 / 60 = 492.62 minutes) and then use it in the calculation. For example, the start time of the path segment, 08:10:00, is converted to 490 minutes. Minutes, rounded to two decimal places, is 2.62.

[0157] S502: Based on the obtained rhythm matching offset results, filter the path task numbers with time offset less than the offset threshold, call the corresponding vehicle number and replenishment task number to execute the combination, generate a delivery instruction for each pair of combinations, and record the path number and dispatch time to establish a delivery task.

[0158] filter The path tasks (such as PT001, PT002) will correspond to (VH001, VH002) and (RT001, RT002) spliced ​​together (VH001-RT001, VH002-RT002) Generate delivery instructions ,Include (PS001-202404) (Electronic products) (90%), Record (2024-04-20 09:00:00), Table 15 shows three sets of task data.

[0159] Table 15 Delivery Task Instruction Table

[0160] Vehicle number Replenishment Task Number Path number Sending time VH001 RT001 PS001-202404 2024-04-20 09:00:00 VH002 RT002 PS002-202404 2024-04-20 09:05:00 VH004 RT004 PS005-202404 2024-04-20 09:10:00

[0161] As shown in Table 15 Depend on and Generated by connecting with short horizontal lines, Strictly consistent with path labels, Retrieved from the system clock, if the path number is duplicated (e.g., PS005-202404 already exists), append the "-n" suffix (e.g., PS005-202404-1) and write it. When validating the uniqueness of a field, for example, if the path PS001-202404 for vehicle VH007 is duplicated, generate PS001-202404-2, using the formula. middle, Given the existing number of repetitions, ,get .

[0162] S503: Call the acquired delivery task, collect the current location trajectory of the vehicle in delivery and compare it synchronously with the preset path segment sequence number, extract the current running number of the vehicle in each path segment and compare it with the path segment number of the delivery tag to determine the node consistency, obtain the proportion of the number of consistent nodes in each path segment to the total number, and generate the path consistency ratio.

[0163] Call delivery task field Path number in (e.g., PS001-202404) Collects real-time vehicle location trajectory. (like Extract the preset path segment sequence. (e.g., PS001-202404) ), traverse each path segment, and compare node by node. and The number of matching numbers, for example, in path segment 1 and match, and match, and No match, number of matches Total number of nodes Node consistency ratio Synchronous calculation of timestamp deviation (like , , (seconds), if If a time is counted as a second (5 minutes), then it is considered a time match. The number of time matches is... (Assuming the time deviation between the two nodes is acceptable), total ratio Overall consistency ratio (weight) , Set a consistency threshold ,determination To be considered qualified, Table 16 shows the matching data for the three vehicles.

[0164] Table 16 Path Node and Time Consistency Matching Table

[0165] Vehicle number Path segment number Node matching count / total number Number of time matches / total number Overall consistency ratio VH001 PS001-202404 2 / 3 2 / 3 0.667 VH002 PS002-202404 3 / 3 3 / 3 1.000 VH004 PS005-202404 1 / 2 1 / 2 0.500

[0166] As shown in Table 16, vehicles VH001 and VH002... Node matching weight is above the threshold of 0.65. The setting is based on the following: Historical data shows that a 10% reduction in node matching error improves delivery accuracy by 18%, while a 10% reduction in time matching error only improves accuracy by 5%. Weights are allocated through linear regression, and a time deviation threshold is set. The second setting is based on the tolerance level for actual road conditions: a time deviation exceeding 5 minutes will increase the conflict rate of subsequent tasks by 35%, for example, vehicle VH005. In seconds, the conflict rate is 38%. During path segment node matching, if the actual vehicle trajectory node matches the preset node number exactly (e.g., a 3 / 3 match for VH002), then... If there are missing or offset values ​​(such as a 1 / 2 match for VH004), the calculation will be based on the actual proportion, and non-integer values ​​will be used. Round to three decimal places (e.g., 0.667). For tasks involving multiple path segments (e.g., the path of vehicle VH006 includes PS003 and PS004), calculate each segment separately. Then take the average, for example, PS003. PS004 ,final .

[0167] Formula explanation:

[0168] The formula for the overall consistency ratio is:

[0169] ;

[0170] The number of actual trajectory nodes that match the preset node numbers, determined by traversing... and Given a set of nodes, count the number of nodes with the same ID, for example, VH001. , : The preset total number of nodes in the path segment, for example , Time Deviation The number of nodes per second, for example, VH001. , The total number of nodes is consistent with the total number of time verifications. , .

[0171] The preset node for the path segment PS003-202404 of vehicle VH003 is... The actual trajectory nodes are The time deviation is Seconds, the calculation process is as follows:

[0172] 1. (Matching 201 and 202) 2. ( , , ), 3. 4. Compare thresholds ,because It was deemed qualified.

[0173] The results show that path segment PS003-202404 meets the consistency requirements. The formula avoids the deviation of the results by weighting the matching degree between nodes and time.

[0174] S504: Based on the obtained path consistency ratio, call the path segment sequence encoding, replace the path segment number based on the real-time scheduling deviation of the path offset benchmark ratio, replace and record the path segment offset result and append it to the control scheduling log to generate the transportation scheduling adjustment result.

[0175] Extraction path consistency ratio (include ) and path offset baseline ratio ,filter Vehicle number (including VH004) ), call its original path segment number (Including PS005-202404), from the path pool Select new path segment (Including PS006-202404), the selection rule is: prioritize matching the difference in the number of nodes. (include , , ), and time coverage Overlap rate with replenishment window The original path PS005-202404 has a time range of The new path PS006-202404 is The overlap time is 45 minutes, and the total duration is 60 minutes. (Not meeting the criteria), continue filtering for PS007-202404 ( Overlap for 55 minutes. Once the conditions are met, the replacement is performed, and the replacement operation is recorded in the scheduling log. The field includes the original path New Path Replacement time (Including 2024-04-2010:00:00), Table 17 shows the replacement results for 3 vehicles.

[0176] Table 17 Path Segment Replacement Record Table

[0177] Vehicle number Original path segment number New path segment number Replacement time VH004 PS005-202404 PS007-202404 2024-04-20 10：00：00 VH006 PS008-202404 PS009-202404 2024-04-20 10：05：00 VH007 PS010-202404 PS011-202404 2024-04-20 10：10：00

[0178] As shown in Table 17, the original route of vehicle VH004, PS005-202404, was due to... Replaced with PS007-202404, baseline ratio The settings are based on historical data analysis: when At that time, the delivery error rate rose to 25%, while When the error rate is less than 10%, the path pool Node number difference limit Calculated based on the actual path length, including the original path length. kilometers, new route length kilometer, kilometers correspond (Approximately one node every 2 kilometers), overlap rate threshold The system is configured to avoid the replenishment time window being segmented. For example, if the original window is 09:00-10:00, and the new route time is 09:30-10:30, the overlap rate is only 50%, which does not meet the condition. Therefore, the system will verify the route during replacement. The node sequence and the vehicle's current position Connectivity is required, including vehicle VH004 at node 105. The new path PS007-202404 must include node 105 or its adjacent node 106. If connectivity is not achieved (including if PS007-202404 starts at node 107), a secondary filtering is triggered, and a replacement record is written. The JSON format is:

[0179] ;

[0180] Log storage by Hash sharding, including the hash value of VH004 This corresponds to shard 3, ensuring query efficiency.

[0181] Formula explanation:

[0182] The formula for calculating the overlap rate is:

[0183] ;

[0184] - , Replenishment task time window, - , : Time range of the new path segment.

[0185] Replenishment window (540 minutes) (600 minutes), new route time (555 minutes) (605 minutes), calculate:

[0186] 1. Overlap start time 2. Overlap end time 3. Overlap duration Minutes, 4. Total duration of the new route 5 minutes. .

[0187] The results show that the new path meets the overlap rate threshold, and the formula ensures the timeliness of the task after path replacement by accurately calculating the proportion of time intersection.

[0188] Please see Figure 2 A logistics transportation management system based on multi-source data fusion is provided. This system is used to execute the aforementioned logistics transportation management method based on multi-source data fusion. The system includes:

[0189] The node load integral module monitors the transportation time of logistics vehicles in real time, inputs the vehicle transportation time into the principal component analysis model, calculates the congestion integral of the transportation route, supplements the node load integral data, and transmits the generated congestion integral to the replenishment rhythm window module.

[0190] The replenishment rhythm window module obtains the estimated start and end times of replenishment tasks in the next transportation cycle, determines overlapping replenishment periods by combining the congestion integral of the transportation route, generates multiple rhythm window candidate periods based on the start and end times, and passes them to the path segment sequence generation module.

[0191] The path segment sequence generation module matches and judges the expected arrival start time and expected arrival end time of replenishment in the replenishment rhythm window with the scheduled shipping time at the warehouse end, and serializes and sorts the picking and outbound order, handling channel usage order and scheduled shipping time data at the warehouse end, generates path segment sequence codes and transmits them to the vehicle tag binding module.

[0192] The vehicle tag binding module calls the current path segment sequence in the path segment sequence encoding, compares the fit with the path segment sequence of the previous period, filters vehicle resources with similar sequences, binds the corresponding vehicle deployment path tags, and transmits them to the collaborative scheduling control module;

[0193] The collaborative scheduling and control module sends delivery instructions based on the replenishment rhythm window matching judgment, monitors the consistency between the delivery route and the vehicle deployment route label in real time, and generates transportation scheduling adjustment results based on the monitoring results.

[0194] 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 alone, A and B simultaneously, or B 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.

[0195] 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 single or multiple.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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 this 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 this 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.

[0203] 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 logistics transportation management method based on multi-source data fusion, characterized in that, Includes the following steps: S1: Monitor the transportation time of logistics vehicles in real time, input the vehicle transportation time into the principal component analysis model, calculate and record the congestion integral of the transportation route; S2: Obtain the estimated start and end times of replenishment arrival for replenishment tasks in the next transportation cycle, determine overlapping replenishment periods by combining the congestion integral of the transportation route, generate multiple candidate periods for rhythm windows based on the start and end times, and determine the replenishment rhythm window. S3: Match the expected start time and expected end time of replenishment in the replenishment rhythm window with the scheduled shipping time at the warehouse. Then, sort the picking and outbound order, handling channel usage order and scheduled shipping time data at the warehouse through a dynamic priority scheduling algorithm to generate path segment sequence codes. The specific steps of S3 are as follows: S301: Obtain the expected start time and expected end time of replenishment in the replenishment rhythm window, match the start and end times of replenishment tasks in the replenishment rhythm window with the scheduled shipping time of the warehouse, call the warehouse task node information to make logical judgments on the matching group, gather the tasks with overlapping times into the same rhythm group, and generate the time matching result between replenishment tasks and warehouse nodes. S302: Based on the time matching result between the replenishment task and the warehouse node, call the warehouse picking plan number, handling channel code and shipping appointment time corresponding to the task in the rhythm group, perform task association sequence binding on the three types of data, and perform joint sorting processing on the parameters in the task group according to the time sequence to obtain the sorted operation rhythm sorting sequence of the associated nodes. S303: Based on the generated work rhythm sorting sequence, call the warehouse number, channel number and shipping number in the sorting sequence, and combine them in sequence to generate path segment structure information. Mark the path fields in the same rhythm group with unique picking sorting codes, establish sequence segment numbers and record the corresponding task path mapping relationships, and generate path segment sequence codes. S4: Call the path segment sequence code to calculate the fit of the vehicle path sequence records collected by the vehicle GPS, filter vehicle resources of the same sequence and bind the corresponding vehicle deployment path label; The specific steps of S4 are as follows: S401: Call the path segment sequence encoding to obtain the vehicle path sequence record collected by the vehicle GPS, compare the matching degree of the three types of fields in the path segment, namely number node, time sequence and channel number, calculate the structural overlap rate between the current path segment and the preset benchmark value of the vehicle path segment, and generate the path fitting degree. S402: Based on the obtained path fitting degree, call the idle time and available loading status parameters of each vehicle in the vehicle status list in the current period, filter the vehicles with path fitting degree higher than the path matching threshold and meet the status conditions as a candidate set, and establish vehicle matching resources. S403: Based on the acquired vehicle matching resources, calculate the distribution characteristics through time difference data to determine the path matching threshold, call the unique identifier code of each candidate vehicle and the corresponding path segment sequence code to generate a tag combination, collect the combined tags by vehicle, and write them into the vehicle task allocation field to establish vehicle deployment path tags. S5: Based on the replenishment rhythm window matching judgment, send delivery instructions, monitor the consistency between the delivery path and the vehicle deployment path label in real time, and generate transportation scheduling adjustment results based on the monitoring results.

2. The multi-source data fusion logistics transportation management method of claim 1, wherein, The congestion score of the transportation route includes vehicle transportation time, route congestion index, and node load compensation value. The replenishment rhythm window includes the start time of the rhythm window, the end time of the rhythm window, and the alternative time period of the rhythm window. The path segment sequence code specifically includes picking sorting code, channel occupancy sequence number, and dispatch time sequence number. The vehicle deployment path label includes path sequence fit degree, vehicle matching sequence number, and path binding identifier. The transportation scheduling adjustment result includes delivery path matching degree, vehicle path consistency, and real-time scheduling deviation.

3. The method of claim 1, wherein, The specific steps for real-time monitoring of logistics vehicle transport time, inputting the vehicle transport time into a principal component analysis model, calculating the congestion integral of the transport route, supplementing node load integral data, and generating the congestion integral include: S101: Monitor the start and end times of the transportation tasks of logistics vehicles. Based on the deviation between the start and end times of the transportation tasks obtained from the monitoring, analyze the duration of a single vehicle operation for the transportation task and obtain the transportation duration. S102: Based on the input principal component analysis model of the transportation duration, and combined with the preset duration threshold range of the corresponding transportation route, the deviation is compared to establish the route congestion analysis result; S103: Based on the analysis results of the route congestion level, perform integral mapping processing on the nodes associated with the transportation route to generate the congestion score of the node's current transportation route.

4. The logistics transportation management method based on multi-source data fusion according to claim 3, characterized in that, The deviation from the preset time threshold range of the transportation route is compared using the following formula: ； Calculate the current route congestion level of the node This yields the analysis results of the current route congestion level at the node; in, is the total number of sample vehicles, and i is the index of the vehicle. It is the upper threshold. It is the lower threshold. It is the average transportation time of the transport vehicles. It is the standard deviation. This means that if the transportation time exceeds the upper threshold, a corresponding reward will be calculated. This indicates that if the transportation time is below the lower threshold, a corresponding penalty will be calculated. This represents the average congestion index of neighboring nodes. This is expressed as the baseline congestion index.

5. The logistics transportation management method based on multi-source data fusion according to claim 1, characterized in that, The steps for determining the replenishment rhythm window include: obtaining the estimated start and end times of replenishment tasks in the next transportation cycle, determining overlapping replenishment periods based on the congestion integral of the transportation route, generating multiple candidate rhythm windows based on the start and end times, and performing displacement based on the start and end times. S201: Arrival Time: Obtain the estimated arrival time and estimated departure time for each replenishment task in the next transportation cycle, classify the start and end times of each replenishment task according to the transportation cycle number, and locate the time boundary of the start and end time interval of the replenishment task in each cycle to generate the replenishment time interval. S202: Based on the obtained replenishment time interval, call the congestion points of the transportation route, determine the overlap of time points between each replenishment time interval and the points of the corresponding node, and filter and collect the replenishment tasks with overlapping time periods to obtain conflict time period intervals. S203: Based on the conflict time period interval, call the replenishment time period interval, perform time axis displacement processing on both ends of the conflict time period, including adjusting the start and end boundary times of the conflict time period as displacement operations, generating multiple non-overlapping new time periods, and removing windows that intersect with the start and end times of the replenishment task to obtain rhythm candidate intervals. S204: Based on the obtained rhythm candidate intervals, sort all candidate intervals in ascending order according to their start time, filter out time window combinations that do not overlap within a single cycle, and generate replenishment rhythm windows.

6. The logistics transportation management method based on multi-source data fusion according to claim 1, characterized in that, The current path segment and the preset baseline value of the vehicle path segment are processed using the following formula: ； Calculate the structural overlap rate ; in, It is a set of node numbers corresponding to the real-time data of the vehicle's current path status and the preset benchmark of the vehicle's path segment. The number of identical numbers is counted to form the node number matching count. It is the time difference tolerance threshold, which is determined by statistical quantiles. This indicates the total number of nodes in the current path segment. This represents the mean of the time sequence differences. Indicates the number of matching channel numbers. This represents the total number of channels in the current path segment.

7. The logistics transportation management method based on multi-source data fusion according to claim 1, characterized in that, Based on the replenishment rhythm window matching judgment, the specific steps of sending delivery instructions, monitoring the consistency between the delivery route and the vehicle deployment route label in real time, and generating transportation scheduling adjustment results based on the monitoring results include: S501: Obtain the arrival start and end time of the replenishment task in the replenishment rhythm window, call the vehicle delivery path label, match the start and end time of the replenishment task with the path segment time recorded in the corresponding vehicle path label segment by segment, and measure the time difference to generate the rhythm matching offset result of the current path task. S502: Based on the obtained rhythm matching offset result, filter the path task numbers with time offset less than the offset threshold, call the corresponding vehicle number and replenishment task number to execute the combination, generate a delivery instruction for each pair of combinations, and record the path number and dispatch time to establish a delivery task. S503: Call the obtained delivery task, collect the current location trajectory of the vehicle in delivery and compare it synchronously with the preset path segment sequence number, extract the current running number of the vehicle in each path segment and the path segment number of the delivery tag to determine the node consistency, obtain the proportion of the number of consistent nodes in each path segment to the total number, and generate the path consistency ratio. S504: Based on the obtained path consistency ratio, call the path segment sequence encoding, replace the path segment number based on the real-time scheduling deviation of the path offset benchmark ratio, replace and record the path segment offset result and append it to the control scheduling log to generate the transportation scheduling adjustment result.

8. A logistics transportation management system based on multi-source data fusion, characterized in that, The system is used to implement the multi-source data fusion logistics transportation management method according to any one of claims 1-7, and the system includes: The node load integral module monitors the transportation time of logistics vehicles in real time, inputs the vehicle transportation time into the principal component analysis model, calculates the congestion integral of the transportation route, supplements the node load integral data, and transmits the generated congestion integral to the replenishment rhythm window module. The replenishment rhythm window module obtains the estimated start and end times of replenishment tasks in the next transportation cycle, determines overlapping replenishment periods by combining the congestion integral of the transportation route, generates multiple rhythm window candidate periods based on the start and end times, and passes them to the path segment sequence generation module. The path segment sequence generation module matches and judges the expected arrival start time and expected arrival end time of replenishment in the replenishment rhythm window with the scheduled shipping time at the warehouse end, and serializes and sorts the picking and outbound order, handling channel usage order and scheduled shipping time data at the warehouse end, generates path segment sequence codes and transmits them to the vehicle tag binding module. The vehicle tag binding module calls the current path segment sequence in the path segment sequence encoding, compares the fit with the path segment sequence of the previous period, filters vehicle resources with similar sequences, binds the corresponding vehicle deployment path tags, and transmits them to the collaborative scheduling control module; The collaborative scheduling and control module sends delivery instructions based on the replenishment rhythm window matching judgment, monitors the consistency between the delivery route and the vehicle deployment route label in real time, and generates transportation scheduling adjustment results based on the monitoring results.

Images