Intelligent logistics resource dynamic planning method and system based on global optimization

Abstract

This application relates to the field of big data processing technology, specifically to a method and system for dynamic coordination of intelligent logistics resources based on global optimization. The method includes: acquiring the road network of the required logistics transportation area and dividing each day into multiple time periods; for a single time period, dividing the locations of all customers awaiting delivery into delivery areas and planning the delivery sequence within each area; for a single delivery area, evaluating the correlation of traffic conditions between each road segment and its adjacent time periods for any two customers awaiting delivery, and obtaining the reliable speed of each road segment in the current time period; acquiring heuristic information on each path between the two customers awaiting delivery in the current time period, and planning delivery routes. This application aims to achieve efficient dynamic coordination of intelligent logistics resources in a dynamic traffic environment, significantly improving delivery efficiency and reliability.

Description

Technical Field

[0001] This application relates to the field of big data processing technology, specifically to a method and system for dynamic coordination of smart logistics resources based on global optimization. Background Technology

[0002] Smart logistics resource dynamic coordination is a management process that utilizes technologies such as the Internet of Things, big data, and artificial intelligence to perform real-time sensing, intelligent analysis, and dynamic optimization of elements such as transportation vehicles, warehousing, manpower, and information flow. Against the backdrop of rapid development in e-commerce and smart manufacturing, logistics demands are becoming increasingly fragmented, personalized, and immediate. Traditional static planning struggles to cope with transportation fluctuations, while dynamic coordination can improve response speed and operational efficiency, and reduce costs by optimizing routes, warehousing and distribution, and transportation capacity in real time.

[0003] In practice, such as express delivery, delivery personnel need to deliver goods from warehouses to customers in multiple areas within a specified time, which usually requires intelligent optimization of delivery routes. However, factors such as road congestion, malfunctions, and events cause road conditions to change in real time, and external interference makes it difficult to determine the optimal route, resulting in low delivery efficiency and poor dynamic coordination. Summary of the Invention

[0004] In view of the above, it is necessary to provide a method and system for dynamic coordination of smart logistics resources based on global optimization. Compared with traditional methods for dynamic coordination of smart logistics resources based on global optimization, this method achieves efficient dynamic coordination of smart logistics resources in dynamic traffic environments, significantly improving the efficiency and reliability of delivery. In a first aspect, embodiments of this application provide a method for dynamic coordination of intelligent logistics resources based on global optimization, the method comprising the following steps: Obtain the road network for the required logistics and transportation area, and divide each day into multiple time periods; For a single time period, by comparing the location of customers to be delivered, the scheduled delivery time, and the loading and unloading time, the locations of all customers to be delivered are divided into delivery areas. Based on the distance from the warehouse to the delivery area, the distance between delivery areas, the scheduled delivery time of customers to be delivered in each delivery area, and the loading and unloading time, the delivery order of the delivery areas is planned. For a single delivery area, for any road segment from any customer to any other customer, assess the correlation of traffic conditions of that road segment between the current time period and its adjacent time periods. Combine the real-time vehicle speed of the current time period with the predicted vehicle speed obtained from the historical vehicle speed of the current time period to obtain the reliable vehicle speed of that road segment in the current time period. Using the length of any path between any customer and any other customer, the reliable vehicle speed of all road segments in that path, and the scheduled delivery time of any other customer, obtain heuristic information for that path in the current time period. Using the heuristic information of all paths between any two customers, plan the delivery route.

[0005] In one embodiment, the process of obtaining the delivery area is as follows: By using the similarity between the coordinates of all customers awaiting delivery, the start and end times of the scheduled delivery period, and the loading and unloading time, a clustering algorithm is used to divide the locations of all customers awaiting delivery into multiple clusters, with each cluster serving as a delivery area.

[0006] In one embodiment, the delivery sequence planning process is as follows: The butterfly optimization algorithm is used to plan the delivery order of the delivery area. In the butterfly optimization algorithm, the method for calculating the stimulus factor in the measure value of the fragrance emitted by a single butterfly is as follows: for the delivery order corresponding to a single butterfly, the normalized value of the sum of the distance from the warehouse to the first delivery area and the total distance of the center of all adjacent delivery areas is recorded as the distance normalized value. Calculate the time by which the estimated arrival time in each delivery area exceeds the earliest scheduled delivery termination time in each delivery area, and calculate the normalized value of the sum of the excess times for all delivery areas, denoted as the time normalized value. The stimulation factors are negatively correlated with the distance normalization value and the time normalization value, respectively.

[0007] In one embodiment, the stimulus factor is the reciprocal of the weighted sum of the distance-normalized value and the time-normalized value.

[0008] In one embodiment, the process of obtaining the traffic condition relevance is as follows: The correlation coefficients of the historical traffic characteristic values ​​of any road segment in the current time period with its adjacent previous time period and adjacent next time period are respectively denoted as the first correlation coefficient and the second correlation coefficient. The traffic condition correlation is obtained by combining the first correlation coefficient and the second correlation coefficient.

[0009] In one embodiment, the traffic condition correlation is the mean of the absolute values ​​of the first correlation coefficient and the absolute values ​​of the second correlation coefficient.

[0010] In one embodiment, the reliable vehicle speed is a weighted sum of the predicted vehicle speed and the real-time vehicle speed, wherein the weight of the predicted vehicle speed is the correlation of the traffic conditions, and the weight of the real-time vehicle speed is the difference between 1 and the correlation of the traffic conditions.

[0011] In one embodiment, the process of obtaining the heuristic information is as follows: When delivering goods to any one of the customers via any of the routes, calculate the estimated time of arrival at any one of the customers exceeding the scheduled delivery termination time of any one of the customers; The heuristic information is negatively correlated with the length of any path and the time delay in reaching any customer to be delivered, and positively correlated with the reliable speed of all segments of any path.

[0012] In one embodiment, the method for planning delivery routes is as follows: Based on the heuristic information, an ant colony optimization algorithm is used to obtain the delivery route.

[0013] Secondly, embodiments of this application also provide a smart logistics resource dynamic coordination system based on global optimization, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any of the above-described smart logistics resource dynamic coordination methods based on global optimization.

[0014] This application has at least the following beneficial effects: This application addresses the issue that simply determining delivery order based on distance, given the dispersed locations of customers, leads to delivery personnel shuttling back and forth within the city, increasing unnecessary mileage. By leveraging the similarity between customer locations, scheduled delivery times, and loading / unloading durations, it aggregates customers with similar locations and delivery times, delivering to them together, significantly reducing cross-regional travel time. Furthermore, by comprehensively considering the distance from warehouses to delivery areas, the distance between delivery areas, and delivery delay factors, it precisely plans the delivery order within delivery areas, improving delivery efficiency. Through multi-factor dynamic adjustment of heuristic information, it considers basic distance costs, proactively avoids congested sections, and prevents delays, enabling route selection optimization based on real-time traffic conditions, further enhancing delivery efficiency. Finally, through a progressive strategy of global and local optimization, combined with a mechanism that drives delivery route planning based on real-time traffic conditions, it achieves efficient and dynamic coordination of smart logistics resources in a dynamic traffic environment, significantly improving delivery efficiency and reliability. Attached Figure Description

[0015] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A flowchart illustrating the steps of a method for dynamic coordination of intelligent logistics resources based on global optimization, provided in one embodiment of this application. Figure 2 This is a schematic diagram of the delivery route planning process. Detailed Implementation

[0017] In the description of the embodiments in this application, the words "exemplary," "or," and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary," "or," and "for example" is intended to present the relevant concepts in a specific manner.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. It should be understood that, unless otherwise stated, " / " in this application means "or".

[0019] It should also be noted that the terms "first" and "second" in this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0020] The following, in conjunction with the accompanying drawings, details the specific scheme of the intelligent logistics resource dynamic coordination method and system based on global optimization provided in this application.

[0021] Please see Figure 1 The diagram illustrates a flowchart of a method for dynamic coordination of intelligent logistics resources based on global optimization, according to an embodiment of this application. The method includes the following steps: Step 1: Obtain the road network for the required logistics transportation area and divide each day into multiple time periods.

[0022] In the dynamic coordination and operation of intelligent logistics resources, the road network of the required logistics transportation area is obtained by using a public map API. Each day is divided into multiple time periods, and the average vehicle speed and traffic density of each road segment within each time period are obtained in real time through TomTom's traffic flow query API. The location of each customer awaiting delivery within each time period is obtained, specifically presented in coordinate form. All paths between the warehouse and each customer awaiting delivery are obtained through the map API, as well as all paths between any two customers awaiting delivery. The historical average vehicle speed and traffic density of each road segment within each time period are obtained through TomTom's traffic flow query API. Here, a road segment refers to the path between two intersections.

[0023] In this embodiment, the length of the time period is 2 hours, for example, from 8:00 am to 10:00 am. The length of the time period is preset by the user, and the implementer can set it according to the actual situation. This application does not impose any special restrictions.

[0024] In this embodiment, the map API is specifically the Gaode Map API. In other implementations, the map API can be the Baidu Map API, Tencent Map API, etc., and this application does not impose any special restrictions.

[0025] Step 2: For a single time period, divide the locations of all customers to be delivered into delivery areas and plan the delivery order for each delivery area; for a single delivery area, for each road segment between any two customers to be delivered, evaluate the correlation of traffic conditions between each road segment in the current time period and its adjacent time periods to obtain the reliable vehicle speed of each road segment in the current time period; obtain heuristic information of each path between any two customers to be delivered in the current time period.

[0026] Taking express delivery as an example, delivery personnel usually need to deliver to customers within a fixed time period. Since there are significant differences in the customers and their locations served at different times, the delivery routes need to be dynamically adjusted to adapt to these changes. Therefore, the ant colony optimization algorithm is used to independently optimize the delivery routes in each time period. By leveraging the high robustness and dynamic environmental adaptability of the ant colony optimization algorithm in solving the traveling salesman problem, the delivery efficiency can be continuously improved.

[0027] In logistics and delivery scenarios, after a customer schedules a delivery time slot, the delivery person needs to depart from the warehouse within the specified time and deliver the goods to the customer's location. However, actual delivery route planning presents challenges: some sections of the delivery route may experience localized congestion during specific times, such as morning and evening rush hours, significantly increasing actual travel time. Therefore, in such cases, simply pursuing the shortest path distance may actually prolong the overall delivery time and reduce delivery efficiency. Thus, delivery route optimization needs to comprehensively consider both distance and real-time traffic conditions to maximize time efficiency. It should be noted that if the time period is from 8:00 AM to 10:00 AM, the scheduled delivery time slot for the customer can be any time range within this period, such as 8:00 AM to 9:00 AM, 8:30 AM to 9:30 AM, or 8:30 AM to 10:00 AM.

[0028] Considering that some customers may have similar scheduled delivery times and be located close to each other when delivering goods to customers, to avoid frequent changes to delivery routes during route planning, taking time period 'a' of the day as an example, by comparing the location of the customers, their scheduled delivery time, and loading and unloading time, the locations of all customers to be delivered are divided into different delivery areas, specifically: By analyzing the similarities between the coordinates of all customers awaiting delivery, the start and end times of their scheduled delivery slots, and the loading and unloading times, a clustering algorithm is used to divide the locations of all customers into multiple clusters, each serving as a delivery area. The purpose of clustering is to avoid repeated back-and-forth trips across areas, thus saving time spent traveling between regions.

[0029] In this embodiment, the coordinates of a single customer awaiting delivery, the start and end times of the scheduled delivery period, and the loading and unloading time are used to construct a feature vector for that single customer. ,in, This represents the coordinates of a single customer awaiting delivery. This indicates the start time of the scheduled delivery period for a single customer. The term "T" represents the end time of the scheduled delivery period for a single customer, and "T" represents the loading and unloading time for a single customer. The DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm divides the locations of all customers into multiple clusters based on their feature vectors. The Euclidean distance between feature vectors is used as the distance metric. It should be noted that since the feature vectors contain data with different dimensions, the data is normalized before calculating the Euclidean distance. In this embodiment, the Min-Max normalization method is used. Unless otherwise specified, the Min-Max normalization method is used throughout this application. Both the DBSCAN algorithm and the Min-Max normalization method are well-known technologies and will not be elaborated upon here. As other implementation methods, based on the ability to cluster the locations of customers based on feature vectors, implementers can use other existing feasible methods, such as density peak clustering algorithms. This application does not impose any special restrictions.

[0030] Furthermore, based on the distance from the warehouse to the distribution area, the distance between distribution areas, the scheduled delivery time for customers in each distribution area, and the loading and unloading time, the delivery sequence of the distribution areas is planned, specifically as follows: The butterfly optimization algorithm is used to plan the delivery order of the delivery area. In the butterfly optimization algorithm, the method for calculating the stimulus factor in the measure value of the fragrance emitted by a single butterfly is as follows: for the delivery order corresponding to a single butterfly, the normalized value of the sum of the distance from the warehouse to the first delivery area and the total distance of the center of all adjacent delivery areas is recorded as the distance normalized value. Calculate the time by which the estimated arrival time in each delivery area exceeds the earliest scheduled delivery termination time in each delivery area, and calculate the normalized value of the sum of the excess times for all delivery areas, denoted as the time normalized value. The stimulation factors are negatively correlated with the distance normalization value and the time normalization value, respectively. The butterfly optimization algorithm is a well-known technique and will not be described further in this application.

[0031] The formula for calculating the estimated arrival time in each delivery area is as follows: In the formula, This indicates the estimated time of arrival at the i-th delivery area; Indicates the moment when the delivery person begins delivery; This indicates the distance from the warehouse to the center of the first distribution area; This represents the average speed from the warehouse to the first delivery area, obtained through historical data; i represents the sequence number of the delivery area. This represents the distance from the center of the j-th delivery area to the center of the (j+1)-th delivery area; This represents the average speed from the j-th delivery area to the (j+1)-th delivery area, obtained through historical data; This represents the total loading and unloading time for all customers awaiting delivery within the j-th delivery area. The distances from the warehouse to the center of the delivery area, and the distances between the centers of the delivery areas, are Euclidean distances.

[0032] It should be noted that negative correlation means that the variables change in opposite directions; when one variable increases, the other decreases, and vice versa.

[0033] In this embodiment, the expression for the stimulating factor is: ; I represents the stimulating factor; , Both indicate a preset weight greater than 0; The distance normalization value represents the distance of a single butterfly; This represents the time-normalized value for a single butterfly.

[0034] In this embodiment, , The values ​​of are 0.6 and 0.4 respectively. The parameter c of the butterfly optimization algorithm is 0.01, the parameter a is 0.1, the number of butterflies is 30, and the maximum number of iterations is 100. , The values ​​of parameter c, parameter a, number of butterflies, and maximum number of iterations are all preset by the user. The implementer can set them according to the actual situation. This application does not impose any special restrictions.

[0035] During delivery, deliveries are made according to the delivery order within the delivery area. Within each delivery area, the ant colony optimization algorithm is used to further optimize the delivery route.

[0036] Considering that under normal circumstances, the traffic conditions of each time period are closely related to those of its adjacent time periods, but in the event of sudden accidents or special incidents, such as the end of large-scale events or sporting events, the traffic conditions of each time period and its adjacent time periods will be affected, and the correlation will change. Based on the above analysis, taking time period a, the i-th delivery area, and customers m and n to be delivered as an example, for the road segment v between customer m and customer n, the correlation of the traffic conditions of road segment v between time period a and its adjacent time periods is evaluated, specifically as follows: The correlation coefficients of the historical traffic characteristic values ​​of road segment v in time period a with its adjacent previous time period and adjacent subsequent time period are respectively denoted as the first correlation coefficient and the second correlation coefficient. The traffic condition correlation is the average of the absolute values ​​of the first correlation coefficient and the second correlation coefficient.

[0037] In this embodiment, the process of obtaining the correlation coefficient is as follows: If time period a is from 8:00 AM to 10:00 AM, then the traffic characteristic values ​​from 8:00 AM to 10:00 AM of each day in the past 30 days before that day are obtained. The traffic characteristic values ​​from 8:00 AM to 10:00 AM of all days in the past 30 days are arranged in chronological order to form the historical traffic characteristic sequence of time period a. The adjacent preceding time period of time period a is from 6:00 AM to 8:00 AM, and the adjacent following time period of time period a is from 10:00 AM to 12:00 PM. According to the method for obtaining the historical traffic characteristic sequence of time period a, the historical traffic characteristic sequence of the adjacent preceding time period of time period a and the historical traffic characteristic sequence of the adjacent following time period of time period a are obtained. The correlation coefficient between the historical traffic characteristic sequences of time period a and its adjacent preceding time period is calculated, and the correlation coefficient between the historical traffic characteristic sequences of time period a and its adjacent following time period is calculated.

[0038] In this embodiment, the traffic characteristic value is specifically defined as follows: taking time period a as an example, the ratio of the average vehicle speed to the traffic density between 8:00 AM and 10:00 AM each day is used as the traffic characteristic value between 8:00 AM and 10:00 AM each day. When calculating the traffic characteristic value, a value greater than 0 is added to the denominator to avoid the denominator being 0. In this embodiment, the value greater than 0 is 0.01, and the unit is the same as the unit of traffic density. The value of the value greater than 0 is preset by the user, and the implementer can set it according to the actual situation. This application does not impose any special restrictions.

[0039] In this embodiment, the correlation coefficient is specifically the Pearson correlation coefficient. The Pearson correlation coefficient is a well-known technology and will not be described in detail here. As other implementation methods, based on the ability to measure the correlation of traffic characteristic values ​​in time series, implementers may use other existing feasible technologies, such as the Spearman correlation coefficient, etc. This application does not impose any special restrictions.

[0040] It should be noted that: the higher the calculated correlation of traffic conditions, the more regular the transition of traffic conditions between adjacent time periods, and the higher the reliability of predicting the current average vehicle speed from historical average vehicle speeds; the lower the calculated correlation of traffic conditions, the more the regular connection between adjacent time periods is broken, and irregular abrupt changes occur, such as sudden traffic accidents, severe weather, or congestion caused by the end of an event, and the lower the reliability of predicting the current average vehicle speed from historical average vehicle speeds.

[0041] Furthermore, by analyzing the correlation of traffic conditions between road segment v in time period a and its adjacent time periods, combined with the real-time vehicle speed in time period a, and the predicted vehicle speed in time period a obtained using the historical vehicle speeds of time period a, the reliable vehicle speed of road segment v in time period a is obtained, specifically as follows: By using the historical vehicle speed of road segment v in time period a, the predicted vehicle speed of road segment v in time period a can be obtained. The reliable speed of road segment v in time period a is the weighted sum of the predicted speed of road segment v in time period a and the real-time speed of road segment v in time period a. The weight of the predicted speed of road segment v in time period a is the correlation of the traffic conditions, and the weight of the real-time speed of road segment v in time period a is the difference between 1 and the correlation of the traffic conditions.

[0042] In this embodiment, the method for obtaining the predicted vehicle speed is as follows: If time period a is from 8:00 AM to 10:00 AM, obtain the average vehicle speed from 8:00 AM to 10:00 AM for each of the past 30 days prior to the current day, arrange them chronologically, and use an Autoregressive Integrated Moving Average (ARIMA) model to predict the average vehicle speed from 8:00 AM to 10:00 AM on the current day, which is then used as the predicted vehicle speed. The parameters P, q, and d in ARIMA are set to values ​​of 2... 、 1.1 ARIMA is a well-known technology and will not be described in detail in this application. As other implementation methods, based on the ability to predict the current vehicle speed through historical vehicle speed, implementers may adopt other existing feasible technologies, and this application does not impose any special restrictions.

[0043] In this embodiment, the method for obtaining real-time vehicle speed is as follows: if time period a is from 8:00 AM to 10:00 AM and the current time is 8:30 AM, the average speed of vehicles between 8:00 AM and 8:30 AM is taken as the real-time vehicle speed; if the current time is 7:30 AM, the real-time vehicle speed is assigned as the predicted vehicle speed.

[0044] It should be noted that when the correlation of traffic conditions is greater, predicting vehicle speed can smooth out the instantaneous noise in real-time data and improve data stability; when the correlation of traffic conditions is smaller, historical speed change patterns become invalid, and the weight of real-time data needs to be increased to respond quickly to sudden changes.

[0045] Furthermore, in the dynamic coordination of intelligent logistics resources, path length is typically analyzed as the cost of the delivery path. However, under the influence of external interference, delivery via shorter paths may result in longer delivery times and poorer delivery performance. Based on the above analysis, heuristic information about path L in time period a is obtained by using the length of path L between customer m and customer n, the reliable vehicle speed of all segments in path L, the scheduled delivery time of customer n, and the loading and unloading time. Specifically: When calculating the time by which the estimated arrival time of goods to be delivered to customer n exceeds the scheduled delivery termination time of customer n when delivering goods to customer n via path L; The heuristic information of path L in time period a is negatively correlated with the length of path L and the time delay before reaching the customer n to be delivered, and positively correlated with the reliable speed of all road segments in path L in time period a.

[0046] It should be noted that positive correlation means that the variables change in the same direction; when one variable increases, the other variable also increases, and when one variable decreases, the other variable also decreases.

[0047] In this embodiment, the expression for the heuristic information of path L in time period a is: In the formula, This represents the heuristic information of path L within time period a; The normalized value representing the length of path L; e represents the natural constant; This represents the normalized value of the average reliable vehicle speed of all road segments in path L during time period a; This represents a preset value greater than 1, used to adjust the impact of delivery arrival timeouts on heuristic information. The larger the value of , the greater the impact of delivery timeout on heuristic information; This represents the time difference between the estimated arrival time of goods to customer n and the scheduled delivery termination time of customer n when delivering goods to customer n via path L. The value of is 3. The value is preset by the user, and the implementer can set it according to the actual situation. This application does not impose any special restrictions.

[0048] The formula for calculating the estimated arrival time of customer n to be delivered is as follows: In the formula, Indicates the expected time of arrival at customer n to be delivered; Indicates the estimated time of arrival at the customer m to be delivered; This indicates the loading and unloading time for customer m to be delivered; Indicates the length of path L; This represents the average reliable vehicle speed of all road segments in path L during time period a.

[0049] It should be noted that existing technologies typically use the reciprocal of the path length as heuristic information. However, during delivery, traffic congestion may occur, reducing delivery efficiency when setting delivery routes solely based on path length. Therefore, the heuristic information is adaptively adjusted by considering various factors in the delivery process. Generally, the longer the path L, the more time it takes and the greater the cost. Higher reliable vehicle speeds result in higher traffic efficiency, while lower reliable vehicle speeds lead to more congestion and higher costs. Longer timeouts also result in higher costs. The larger the calculated heuristic information, the more likely path L should be chosen as the delivery route between customer m and customer n.

[0050] Step 3: Plan the delivery route using heuristic information from all paths between any two customers to be delivered.

[0051] Based on the heuristic information obtained after reconstruction, an ant colony optimization algorithm is used to obtain the delivery route. A schematic diagram of the delivery route planning process is shown below. Figure 2 As shown.

[0052] In this embodiment, the pheromone weight and heuristic information weight of the ant colony optimization algorithm are set to 1 and 3, respectively. To avoid deviations due to insufficient ant quantity, the ant quantity is set to 30. To balance the computational load, the maximum number of iterations is set to 100. The ant colony optimization algorithm is a well-known technology and will not be described further in this application. The pheromone weight, heuristic information weight, ant quantity, and maximum number of iterations of the ant colony optimization algorithm are all preset manually. Implementers can set them according to actual conditions. For example, in densely networked central urban areas, the heuristic information weight is increased to improve the sensitivity of delivery routes to real-time traffic fluctuations; in sparsely networked suburban areas, the pheromone weight is increased to maintain the overall stability of the path. The ant colony optimization algorithm is a well-known technology and will not be described further in this application.

[0053] It should be added that if there is a case where the denominator is 0 during the calculation of the ratio, the denominator should be mapped to a positive number first, and then the subsequent calculation should be performed. There are many ways to map the data to a positive number, and the implementer can choose a feasible method. In this embodiment, the purpose of mapping the denominator to a positive number is achieved by calculating the sum of the denominator and a preset constant greater than 0. The value of the preset constant greater than 0 is 0.01, and it has the same unit as the denominator. The value of the preset constant greater than 0 is preset by the implementer, and the implementer can set it according to the actual situation. This application does not impose any special restrictions.

[0054] Based on the same inventive concept as the above methods, this application also provides a smart logistics resource dynamic coordination system based on global optimization, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-described smart logistics resource dynamic coordination methods based on global optimization.

[0055] In summary, this application addresses the issue that simply determining delivery order based on distance, given the dispersed locations of customers, leads to delivery personnel crisscrossing the city and increasing unnecessary mileage. By leveraging the similarity between customer locations, scheduled delivery times, and loading / unloading durations, it aggregates customers with similar locations and delivery times, delivering to them together, significantly reducing cross-regional travel time. Furthermore, by comprehensively considering the distance from warehouses to delivery areas, the distance between delivery areas, and delivery delay factors, it precisely plans the delivery order within delivery areas, improving delivery efficiency. Through multi-factor dynamic adjustment of heuristic information, it considers basic distance costs, proactively avoids congested sections, and prevents delays, enabling route selection optimization based on real-time traffic conditions, further enhancing delivery efficiency. Finally, by employing a progressive strategy of global and local optimization, combined with a mechanism for driving delivery route planning based on real-time traffic conditions, it achieves efficient and dynamic coordination of intelligent logistics resources in a dynamic traffic environment, significantly improving delivery efficiency and reliability.

[0056] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0057] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from its essential characteristics. Therefore, the embodiments described above should be considered exemplary and non-limiting in all respects.

Claims

1. A method for dynamic coordination of intelligent logistics resources based on global optimization, characterized in that: The method includes the following steps: Obtain the road network for the required logistics and transportation area, and divide each day into multiple time periods; For a single time period, by comparing the location of customers to be delivered, the scheduled delivery time, and the loading and unloading time, the locations of all customers to be delivered are divided into delivery areas. Based on the distance from the warehouse to the delivery area, the distance between delivery areas, the scheduled delivery time of customers to be delivered in each delivery area, and the loading and unloading time, the delivery order of the delivery areas is planned. For a single delivery area, for any road segment from any customer to any other customer, assess the correlation of traffic conditions of that road segment between the current time period and its adjacent time periods. Combine the real-time vehicle speed of the current time period with the predicted vehicle speed obtained from the historical vehicle speed of the current time period to obtain the reliable vehicle speed of that road segment in the current time period. Using the length of any path between any customer and any other customer, the reliable vehicle speed of all road segments in that path, and the scheduled delivery time of any other customer, obtain heuristic information for that path in the current time period. Using the heuristic information of all paths between any two customers, plan the delivery route.

2. The method for dynamic coordination of intelligent logistics resources based on global optimization as described in claim 1, characterized in that, The process of obtaining the delivery area is as follows: By using the similarity between the coordinates of all customers awaiting delivery, the start and end times of the scheduled delivery period, and the loading and unloading time, a clustering algorithm is used to divide the locations of all customers awaiting delivery into multiple clusters, with each cluster serving as a delivery area.

3. The method for dynamic coordination of intelligent logistics resources based on global optimization as described in claim 1, characterized in that, The process of planning the delivery sequence is as follows: The butterfly optimization algorithm is used to plan the delivery order of the delivery area. In the butterfly optimization algorithm, the method for calculating the stimulus factor in the measure value of the fragrance emitted by a single butterfly is as follows: for the delivery order corresponding to a single butterfly, the normalized value of the sum of the distance from the warehouse to the first delivery area and the total distance of the center of all adjacent delivery areas is recorded as the distance normalized value. Calculate the time by which the estimated arrival time in each delivery area exceeds the earliest scheduled delivery termination time in each delivery area, and calculate the normalized value of the sum of the excess times for all delivery areas, denoted as the time normalized value. The stimulation factors are negatively correlated with the distance normalization value and the time normalization value, respectively.

4. The method for dynamic coordination of intelligent logistics resources based on global optimization as described in claim 3, characterized in that, The stimulus factor is the reciprocal of the weighted sum of the distance normalized value and the time normalized value.

5. The method for dynamic coordination of intelligent logistics resources based on global optimization as described in claim 1, characterized in that, The process of obtaining the traffic condition relevance is as follows: The correlation coefficients of the historical traffic characteristic values ​​of any road segment in the current time period with its adjacent previous time period and adjacent next time period are respectively denoted as the first correlation coefficient and the second correlation coefficient. The traffic condition correlation is obtained by combining the first correlation coefficient and the second correlation coefficient.

6. The method for dynamic coordination of intelligent logistics resources based on global optimization as described in claim 5, characterized in that, The traffic condition correlation is the average of the absolute values ​​of the first correlation coefficient and the second correlation coefficient.

7. The method for dynamic coordination of intelligent logistics resources based on global optimization as described in claim 1, characterized in that, The reliable vehicle speed is the weighted sum of the predicted vehicle speed and the real-time vehicle speed, wherein the weight of the predicted vehicle speed is the correlation of the traffic conditions, and the weight of the real-time vehicle speed is the difference between 1 and the correlation of the traffic conditions.

8. The method for dynamic coordination of intelligent logistics resources based on global optimization as described in claim 1, characterized in that, The process of obtaining the heuristic information is as follows: When delivering goods to any one of the customers via any of the routes, calculate the estimated time of arrival at any one of the customers exceeding the scheduled delivery termination time of any one of the customers; The heuristic information is negatively correlated with the length of any path and the time delay in reaching any customer to be delivered, and positively correlated with the reliable speed of all segments of any path.

9. The method for dynamic coordination of intelligent logistics resources based on global optimization as described in claim 1, characterized in that, The method for planning delivery routes is as follows: Based on the heuristic information, an ant colony optimization algorithm is used to obtain the delivery route.

10. A smart logistics resource dynamic coordination system based on global optimization, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the intelligent logistics resource dynamic coordination method based on global optimization as described in any one of claims 1-9.

Images