Intelligent logistics overall management method and system based on data analysis

Abstract

The invention relates to the technical field of path optimization, in particular to an intelligent logistics overall management method and system based on data analysis, and the method comprises the steps: obtaining the related logistics information of a to-be-analyzed region; acquiring a pheromone heuristic factor from each transfer station to another transfer station in each transfer time period; acquiring a path selection expected heuristic factor from each transfer station to another transfer station in each transfer time period; obtaining a final pheromone volatilization coefficient between each transfer station at the current time and the previous transfer station; and according to the final pheromone volatilization coefficient, the final pheromone heuristic factor, the final path selection expected heuristic factor and an ant colony algorithm, obtaining an optimal path from the initial transfer station to the final transfer station in the to-be-analyzed region. According to the invention, the optimal path during logistics transportation can be planned in real time, the logistics efficiency is improved, and the burden of overall management of intelligent logistics is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of route optimization, and in particular to a smart logistics overall management method and system based on data analysis. Background Art

[0002] Smart logistics management refers to the use of modern information technology, such as the Internet of Things, big data analysis, artificial intelligence, cloud computing, etc., to comprehensively plan, organize, coordinate and control logistics activities in order to achieve optimal allocation of logistics resources, efficient operation of logistics processes, reduction of logistics costs and improvement of customer service levels. In the smart logistics system, route optimization plays a vital role because it determines whether the transportation route of goods from the starting point to the destination is optimal.

[0003] When planning logistics transportation routes, the ant colony algorithm with fixed parameters is generally used to determine the optimal transportation route from the starting point to the end point. The key parameters in the ant colony algorithm are: pheromone volatility coefficient, pheromone heuristic factor and path selection expectation heuristic factor. These parameters will affect the selection of the optimal transportation route. Since logistics information is generally dynamic, the carrying capacity and cargo accumulation of different transfer stations are different. Therefore, to achieve the optimal route, real-time analysis is required. It is difficult to determine the optimal transportation route when the logistics information changes in real time by only using the ant colony algorithm with fixed parameters between different transfer stations in the analyzed area, which increases the burden of smart logistics overall management. Summary of the invention

[0004] In order to solve the above problems, the present invention provides a smart logistics overall management method and system based on data analysis.

[0005] The present invention provides a smart logistics overall management method and system based on data analysis, which adopts the following technical solutions:

[0006] An embodiment of the present invention provides a smart logistics overall management method based on data analysis, the method comprising the following steps:

[0007] Obtain the transshipment volume sequence of each transfer station in the area to be analyzed in the past year, the number of daily transportations from each transfer station to another transfer station, the transportation time of each transportation, and the first transshipment speed of each cargo in each transfer station; obtain several optimal paths from the starting transfer station to the final transfer station in the area to be analyzed; obtain the time between the shipment time and the entry time of the cargo in each transfer station in the area to be analyzed in the past year; obtain the distance length between each transfer station and the shipment point in the area to be analyzed; obtain the cargo accumulation volume of each transfer station in the area to be analyzed every day in the current year, the second transshipment speed of each cargo in each transfer station, and obtain the current time of each transfer station in the area to be analyzed;

[0008] The transfer volume sequence is segmented to obtain several transfer time periods for each transfer station; according to the changes in the number of transportations and transportation time from a transfer station to another transfer station within the transfer time period, the transportation stability from each transfer station to another transfer station within each transfer time period is obtained; the probability of each transfer station to another transfer station within each transfer time period is obtained;

[0009] The initial pheromone heuristic factor is adjusted according to the transportation stability and probability from a transfer station to another transfer station, and the pheromone heuristic factor from each transfer station to another transfer station in each transfer time period is obtained; the initial path selection expectation heuristic factor is adjusted according to the transportation stability and probability from a transfer station to another transfer station, and the path selection expectation heuristic factor from each transfer station to another transfer station in each transfer time period is obtained;

[0010] According to the first transfer speed of the goods at the transfer station in the transfer time period, the transfer volume of the transfer station and the number of times the transfer station appears in all optimal paths, the carrying capacity coefficient of each transfer station in each transfer time period is obtained; according to the carrying capacity coefficient, the distance between the transfer station and the shipping point, and the time between the shipping time and the entry time of the goods at the transfer station, the initial pheromone volatility coefficient between each transfer station and the previous transfer station in the transfer time period is obtained; according to the transfer time period, the initial pheromone volatility coefficient, the second transfer speed and the cargo accumulation amount, the final pheromone volatility coefficient between each transfer station at the current time and the previous transfer station is obtained;

[0011] According to the current time of the transfer station, the pheromone heuristic factor and the expected heuristic factor of path selection, the final pheromone heuristic factor and the final expected heuristic factor of path selection from each transfer station to another transfer station at the current time are obtained; according to the final pheromone volatility coefficient, the final pheromone heuristic factor, the final expected heuristic factor of path selection and the ant colony algorithm, the optimal path from the starting transfer station to the final transfer station in the area to be analyzed is obtained.

[0012] Furthermore, the transportation stability from each transfer station to another transfer station in each transfer time period is obtained according to the change in the number of transportations and the transportation duration from the transfer station to another transfer station in the transfer time period, and the specific steps include the following:

[0013] Any transfer time period of the i-th transfer station is recorded as the transfer time period to be analyzed;

[0014]

[0015] Where, T1 i,j is the extreme value of the transportation time from the i-th transfer station to the j-th transfer station during the transfer period to be analyzed; Si,j is the number of transportations from the i-th transfer station to the j-th transfer station during the transfer period to be analyzed; T i,j,s+1 T is the transportation time from the i-th transfer station to the j-th transfer station in the s+1-th transportation within the transfer time period to be analyzed; i,j,s is the transportation time from the i-th transfer station to the j-th transfer station in the s-th transportation during the transfer period to be analyzed; || is the absolute value; exp() is an exponential function with a natural constant as the base; H i,j It is the transportation stability from the i-th transfer station to the j-th transfer station during the transfer time period to be analyzed.

[0016] Furthermore, the specific method for obtaining the probability of each transfer station to another transfer station in each transfer time period is as follows:

[0017] Obtain the number of transportations from the i-th transfer station to all other transfer stations during the transfer time period to be analyzed, and record it as the total number of transportations of the i-th transfer station; obtain the number of transportations from the i-th transfer station to the j-th transfer station during the transfer time period to be analyzed; take the ratio of the number of transportations from the i-th transfer station to the j-th transfer station to the total number of transportations of the i-th transfer station as the probability of the i-th transfer station to the j-th transfer station during the transfer time period to be analyzed.

[0018] Furthermore, the initial pheromone heuristic factor is adjusted according to the transportation stability and probability from one transfer station to another transfer station to obtain the pheromone heuristic factor from each transfer station to another transfer station in each transit time period, including the following specific steps:

[0019] α i,j =α0×(1―H i,j ×P i,j )

[0020] Where α0 is the preset initial pheromone heuristic factor; H i,j is the transportation stability from the i-th transfer station to the j-th transfer station during the transfer period to be analyzed; P i,j is the probability of the i-th transfer station to the j-th transfer station during the transfer period to be analyzed; α i,j is the pheromone heuristic factor from the i-th transfer station to the j-th transfer station during the transfer period to be analyzed.

[0021] Furthermore, the initial path selection expectation heuristic factor is adjusted according to the transportation stability and probability from the transfer station to another transfer station to obtain the path selection expectation heuristic factor from each transfer station to another transfer station in each transfer time period, including the following specific steps:

[0022]

[0023] Where β0 is the expected heuristic factor for the preset initial path selection; H i,j is the transportation stability from the i-th transfer station to the j-th transfer station during the transfer period to be analyzed; P i,j is the probability of the i-th transfer station to the j-th transfer station during the transfer period to be analyzed; nrom() is the linear normalization function; β i,j Select the expected heuristic factor for the path from the i-th transfer station to the j-th transfer station during the transfer time period to be analyzed.

[0024] Furthermore, the carrying capacity coefficient of each transfer station in each transfer time period is obtained according to the first transfer speed of the goods at the transfer station in the transfer time period, the transfer volume of the transfer station and the number of times the transfer station appears in all optimal paths, and the specific steps include the following:

[0025] The time period occupied by the transfer volume sequence of the i-th transfer station is recorded as the total transfer time period to be analyzed;

[0026]

[0027] Where V i is the average first transfer speed of all goods at the i-th transfer station during the transfer time period to be analyzed; is the average first transfer speed of all goods at the i-th transfer station during the total transfer time period to be analyzed; L i is the number of times the i-th transfer station appears in all optimal paths; M1 is the mean value of the transfer volume sequence of the i-th transfer station in the transfer time period to be analyzed; i is the maximum transfer volume of the transfer volume sequence of the i-th transfer station in the total transfer time period to be analyzed; norm() is the linear normalization function; Q i is the carrying capacity coefficient of the i-th transfer station in the transfer time period to be analyzed.

[0028] Furthermore, the initial pheromone volatility coefficient between each transfer station and the previous transfer station in the transit time period is obtained according to the carrying capacity coefficient, the distance length between the transfer station and the shipping point, and the time between the shipping time and the arrival time of the goods at the transfer station, and the specific steps include the following:

[0029] ρ0 i,i―1 =ρ×[1―Q i ×exp(―(th i ―J))]

[0030] Where, ρ is the preset volatility coefficient; Q i is the carrying capacity coefficient of the i-th transfer station in the transfer time period to be analyzed; i is the expected delivery time of the i-th transfer station,i =TH2+TH3×norm(d i ), TH2 is a preset second value, TH3 is a preset third value, d i is the distance between the i-th transfer station and the shipping point, norm() is a linear normalization function; J is the average time between the shipping time and the entry time of all goods at the i-th transfer station during the transit time period to be analyzed; ρ0 i,i―1 is the initial pheromone volatility coefficient between the i-th transfer station and the i-1-th transfer station during the transfer period to be analyzed.

[0031] Furthermore, the method of obtaining the final pheromone volatility coefficient between each transfer station at the current time and the previous transfer station according to the transfer time period, the initial pheromone volatility coefficient, the second transfer speed and the cargo accumulation amount includes the following specific steps:

[0032] The transfer time period corresponding to the current time of the qth transfer station in the area to be analyzed is recorded as the target transfer time period; the time period from the start time of the target transfer time period to the current time of the qth transfer station is recorded as the first time period;

[0033]

[0034] Where ρ0 q,q―1 V2 is the initial pheromone volatility coefficient between the qth transfer station and the q-1th transfer station during the transfer period to be analyzed; q V1 is the average second transfer speed of all goods at the qth transfer station in the first time period; q is the average first transfer speed of all goods at the qth transfer station during the target transfer time period; Y q is the cargo accumulation amount of the qth transfer station on the current day; norm() is the linear normalization function; ε is the first preset hyperparameter; ρ q,q―1 It is the final pheromone volatility coefficient between the qth transfer station and the q-1th transfer station at the current time.

[0035] Furthermore, the method of obtaining the final pheromone heuristic factor and the final path selection expected heuristic factor from each transfer station to another transfer station at the current time according to the current time, the pheromone heuristic factor and the path selection expected heuristic factor of the transfer station includes the following specific steps:

[0036] The pheromone heuristic factor from the qth transfer station to the fth transfer station within the target transfer time period is used as the final pheromone heuristic factor from the qth transfer station to the fth transfer station at the current time; the expected heuristic factor of the path selection from the qth transfer station to the fth transfer station within the target transfer time period is used as the final expected heuristic factor of the path selection from the qth transfer station to the fth transfer station at the current time.

[0037] The present invention also proposes a smart logistics coordination and management system based on data analysis, including a memory and a processor, wherein the processor executes a computer program stored in the memory to implement the steps of the aforementioned method.

[0038] The beneficial effect of the technical solution of the present invention is that when determining the optimal path of different transfer station times in the area to be analyzed based on the ant colony algorithm, the present invention can accurately analyze the impact of different logistics information on cargo transshipment and transportation when the logistics information changes dynamically, and then determine the parameters that affect the selection of transfer stations, plan the optimal path during logistics transportation in real time, improve logistics efficiency, reduce costs, and reduce the burden of smart logistics overall management. When determining the final pheromone heuristic factor and the final path selection expected heuristic factor from each transfer station to another transfer station at the current time, by analyzing the transportation stability and probability from the transfer station to another transfer station, the initial pheromone heuristic factor and the initial path selection expected heuristic factor are adjusted based on the transportation stability and probability, and the final pheromone heuristic factor and the final path selection expected heuristic factor are determined, thereby improving the scientificity, accuracy and objectivity of the final pheromone heuristic factor and the final path selection expected heuristic factor. When determining the final pheromone volatility coefficient between each transfer station at the current time and the previous transfer station, the final pheromone volatility coefficient is determined by analyzing the carrying capacity of the transfer station and the current cargo accumulation volume, which accurately describes the relationship between the pheromone volatility coefficient and the carrying capacity of the transfer station and the current cargo accumulation volume, thereby improving the accuracy, scientificity and objectivity of the final pheromone volatility coefficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 A flowchart of a method for intelligent logistics overall management based on data analysis provided by an embodiment of the present invention;

[0041] Figure 2A schematic diagram of the relationship between transfer stations in the area to be analyzed provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, characteristics and effects of a smart logistics overall management method and system based on data analysis proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0043] Unless defined otherwise, 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 invention belongs.

[0044] The following is a detailed description of a specific solution of a smart logistics coordinated management method and system based on data analysis provided by the present invention in conjunction with the accompanying drawings.

[0045] See also Figure 1 , which shows a flowchart of a method for intelligent logistics overall management based on data analysis provided by an embodiment of the present invention, the method comprising the following steps:

[0046] Step S001, obtain the transfer volume sequence of each transfer station in the area to be analyzed in the past year, the number of transportations from each transfer station to another transfer station every day and the transportation time of each transportation, and the first transfer speed of each cargo in each transfer station; obtain several optimal paths from the starting transfer station to the final transfer station in the area to be analyzed; obtain the time between the shipment time and the entry time of the cargo at each transfer station in the area to be analyzed in the past year; obtain the distance length between each transfer station and the shipment point in the area to be analyzed; obtain the cargo accumulation volume of each transfer station in the area to be analyzed every day in the current year, the second transfer speed of each cargo in each transfer station, and obtain the current time of each transfer station in the area to be analyzed.

[0047] It should be noted that the main purpose of this embodiment is to adjust the pheromone volatility coefficient, pheromone heuristic factor and path selection expectation heuristic factor in the ant colony algorithm according to the logistics information of the area to be analyzed, so as to obtain better parameters, and then use the ant colony algorithm to plan the optimal path between different transfer stations in the area to be analyzed according to these optimized parameters, so as to improve the effect of path optimization in the smart logistics system. Before starting the analysis, first collect the relevant logistics information of the area to be analyzed.

[0048] Specifically, the sequence of daily transshipment volume of each transfer station in the area to be analyzed in the past year is recorded as the transshipment volume sequence of each transfer station, the number of daily transportations from each transfer station to another transfer station in the past year and the transportation time of each transportation are obtained, and the inverse of the time from each cargo entering each transfer station to leaving the same transfer station in the past year is recorded as the first transshipment speed of each cargo in the transfer station; several optimal paths from the starting transfer station to the final transfer station in the area to be analyzed are obtained; the time between the shipment time and the entry time of the cargo at each transfer station in the area to be analyzed in the past year is obtained; the distance length between each transfer station and the shipment point in the area to be analyzed is obtained.

[0049] Furthermore, the daily cargo accumulation volume of each transfer station in the area to be analyzed in the current year is obtained. It should be noted that the cargo accumulation volume is the number of cargoes that stay in the transfer station for more than 24 hours. The inverse of the time from when each cargo enters each transfer station to when it leaves the same transfer station in the current year is recorded as the second transfer speed of each cargo in the transfer station. The current time of each transfer station in the area to be analyzed is obtained.

[0050] It should be noted that there are multiple transfer stations in the area to be analyzed, and the transfer volume sequence includes the daily cargo transfer volume of the transfer station in the past year. The transfer speed of the cargo is the reciprocal of the time the cargo enters the transfer station to the time it leaves the transfer station. The shorter the stay time, the faster the transfer speed. This embodiment uses a greedy algorithm to obtain the five best paths from the starting transfer station to the final transfer station in the area to be analyzed. The specific method can be adjusted according to actual conditions, and this embodiment does not limit it. The number of transportations from a transfer station to another transfer station per day, the transportation time of each transportation, the amount of cargo accumulation and other logistics information are obtained through the logistics management system. The specific acquisition is an existing method, which will not be repeated in this embodiment.

[0051] Please note that Figure 2 , Figure 2 This is a schematic diagram of the transfer station relationship in the area to be analyzed in this embodiment. Figure 2 The route along the dotted line is an optimal path. The starting transfer station and the final transfer station are fixed stations, and there are several other transfer stations between them. The starting transfer station is used to transfer goods sent from the shipping point, and the final transfer station is used to transfer goods to be received by users at the receiving point.

[0052] At this point, the relevant logistics information of the area to be analyzed is obtained.

[0053] Step S002, segment the transfer volume sequence to obtain several transfer time periods for each transfer station; obtain the transportation stability from each transfer station to another transfer station in each transfer time period according to the changes in the number of transportations and transportation duration from the transfer station to another transfer station in the transfer time period; obtain the probability of each transfer station to another transfer station in each transfer time period.

[0054] It should be noted that due to the different transfer volumes of the transfer stations in different periods of logistics transportation, for example, during the period of e-commerce activities, the transfer volume of the transfer stations is large. In order to make the subsequent analysis more accurate, it is necessary to segment the transfer volume sequence to obtain different transfer time periods of the transfer stations, and then analyze each transfer time period to reduce the impact of different transfer volumes of the transfer stations at different times.

[0055] Specifically, the transfer volume sequence is segmented to obtain several transfer time periods for each transfer station, as follows:

[0056] Will As the basic change value of the transfer volume of the i-th transfer station, TR i (max) is the maximum value of the transfer volume in the transfer volume sequence of the i-th transfer station, TR i (min) is the minimum value of the transfer volume in the transfer volume sequence of the i-th transfer station, TH1 is a preset first value, and this embodiment is described as TH1=10; for the transfer volumes of two adjacent days in the transfer volume sequence of the i-th transfer station, if the absolute difference between the transfer volumes of two adjacent days is less than the basic change value of the transfer volume of the i-th transfer station, the transfer volumes of the two adjacent days are merged into one time period; all the transfer volumes of two adjacent days in the transfer volume sequence of the i-th transfer station are merged and judged to obtain several initial transfer time periods of the i-th transfer station; for the unmerged transfer volumes in the transfer volume sequence of the i-th transfer station, the unmerged transfer volumes are merged into the nearest initial transfer time period, and all the unmerged transfer volumes are merged into the nearest initial transfer time period to obtain several transfer time periods of the i-th transfer station.

[0057] It should be noted that if the unmerged transfer volume has two closest initial transfer time periods when it is merged, this embodiment will uniformly merge the unmerged transfer volume into the closest initial transfer time period on the left to ensure complete implementation.

[0058] It should be noted that the above-mentioned several transfer time periods for each transfer station are analyzed in detail to determine the transportation stability and probability of each transfer station to another transfer station within each transfer time period, so as to better adjust the relevant parameters of the ant colony algorithm in the future.

[0059] Specifically, according to the changes in the number of transportations and transportation time from one transfer station to another transfer station during the transfer time period, the transportation stability from each transfer station to another transfer station during each transfer time period is obtained, as follows:

[0060] Any transfer time period of the i-th transfer station is recorded as the transfer time period to be analyzed.

[0061]

[0062] Where, T1 i,j is the extreme value of the transportation time from the i-th transfer station to the j-th transfer station during the transfer period to be analyzed; S i,j is the number of transportations from the i-th transfer station to the j-th transfer station during the transfer period to be analyzed; T i,j,s+1 T is the transportation time from the i-th transfer station to the j-th transfer station in the s+1-th transportation within the transfer time period to be analyzed; i,j,s is the transportation time from the i-th transfer station to the j-th transfer station in the s-th transportation during the transfer period to be analyzed; || is the absolute value; exp() is an exponential function with a natural constant as the base. This embodiment adopts the exp[―U] model to present the inverse proportional relationship and normalization processing, and U is the input of the model; H i,j It is the transportation stability from the i-th transfer station to the j-th transfer station during the transfer time period to be analyzed.

[0063] The description is that T1 i,j It represents the maximum value of the change in transportation time from the i-th transfer station to the j-th transfer station during the transfer time period to be analyzed. i,j The smaller it is, the overall transportation time from the i-th transfer station to the j-th transfer station will not change significantly during the transfer time period to be analyzed, and the transportation time is basically stable. The better the transportation stability from the i-th transfer station to the j-th transfer station during the transfer time period to be analyzed; |T i,j,s+1 ―T i,j,s | represents the change in the transportation time between the i-th transfer station and the j-th transfer station during the transfer time period to be analyzed. When the difference between the two adjacent transportation times is smaller, the transportation time is more stable and will not change significantly. The transportation stability from the i-th transfer station to the j-th transfer station during the transfer time period to be analyzed is better.

[0064] Furthermore, the probability of each transfer station to another transfer station in each transfer time period is obtained as follows:

[0065] Obtain the number of transportations from the i-th transfer station to all other transfer stations during the transfer time period to be analyzed, and record it as the total number of transportations of the i-th transfer station; obtain the number of transportations from the i-th transfer station to the j-th transfer station during the transfer time period to be analyzed; take the ratio of the number of transportations from the i-th transfer station to the j-th transfer station to the total number of transportations of the i-th transfer station as the probability of the i-th transfer station to the j-th transfer station during the transfer time period to be analyzed.

[0066] At this point, the probability of each transfer station going to another transfer station in each transfer time period is obtained.

[0067] Step S003, adjusting the initial pheromone heuristic factor according to the transportation stability and probability from the transfer station to another transfer station, and obtaining the pheromone heuristic factor from each transfer station to another transfer station in each transfer time period; adjusting the initial path selection expectation heuristic factor according to the transportation stability and probability from the transfer station to another transfer station, and obtaining the path selection expectation heuristic factor from each transfer station to another transfer station in each transfer time period.

[0068] It should be noted that the above steps analyze the transportation stability from each transfer station to another transfer station during the transfer period, and the probability of each transfer station to another transfer station during the transfer period. Next, the pheromone heuristic factor and the path selection expectation heuristic factor of the ant colony algorithm are adjusted according to the transportation stability and probability, so as to reduce the impact of dynamic changes in logistics information when determining the optimal path in the subsequent process.

[0069] Specifically, the initial pheromone heuristic factor is adjusted according to the transportation stability and probability from one transfer station to another transfer station, and the pheromone heuristic factor from each transfer station to another transfer station in each transfer time period is obtained, as follows:

[0070] α i，j =α0×(1―H i,j ×P i,j )

[0071] Wherein, α0 is the preset initial pheromone heuristic factor, and this embodiment is described as α0=2; H i,j is the transportation stability from the i-th transfer station to the j-th transfer station during the transfer period to be analyzed; P i,j is the probability of the i-th transfer station to the j-th transfer station during the transfer period to be analyzed; α i,j is the pheromone heuristic factor from the i-th transfer station to the j-th transfer station during the transfer period to be analyzed.

[0072] It should be noted that the greater the transportation stability from the i-th transfer station to the j-th transfer station within the transfer time period to be analyzed, the greater the probability of the i-th transfer station to the j-th transfer station within the transfer time period to be analyzed, indicating that the transportation effect from the i-th transfer station to the j-th transfer station is better, and multiple transportations often choose to go from the i-th transfer station to the j-th transfer station. The pheromone heuristic factor should be reduced to reduce randomness in order to increase the probability of subsequent selection from the i-th transfer station to the j-th transfer station.

[0073] Furthermore, the initial path selection expected heuristic factor is adjusted according to the transportation stability and probability from one transfer station to another transfer station, and the path selection expected heuristic factor from each transfer station to another transfer station in each transfer time period is obtained, as follows:

[0074]

[0075] Wherein, β0 is the preset initial path selection expected heuristic factor, and this embodiment is described as β0=2; H i,j is the transportation stability from the i-th transfer station to the j-th transfer station during the transfer period to be analyzed; P i,j is the probability of the i-th transfer station to the j-th transfer station during the transfer period to be analyzed; norm() is a linear normalization function used for normalization processing; β i,j Select the expected heuristic factor for the path from the i-th transfer station to the j-th transfer station during the transfer time period to be analyzed.

[0076] It should be noted that when the transportation stability from the i-th transfer station to the j-th transfer station within the transfer time period to be analyzed is relatively small, it means that the transportation road conditions are poor, and the expectation of choosing to transport from the i-th transfer station to the j-th transfer station should be reduced, that is, the path selection expectation heuristic factor should be reduced; when the probability of transporting from the i-th transfer station to the j-th transfer station within the transfer time period to be analyzed is greater, it may be due to the special transportation route. Even if the transportation stability is poor, there are still many people who choose it, and the path selection expectation heuristic factor should be appropriately increased.

[0077] At this point, the expected heuristic factor and pheromone heuristic factor of the path selection from each transfer station to another transfer station in each transfer time period are obtained.

[0078] Step S004, according to the first transfer speed of the goods at the transfer station, the transfer volume of the transfer station and the number of times the transfer station appears in all optimal paths during the transfer time period, the carrying capacity coefficient of each transfer station in each transfer time period is obtained; according to the carrying capacity coefficient, the distance length between the transfer station and the shipping point, and the time between the shipping time and the entry time of the goods at the transfer station, the initial pheromone volatility coefficient between each transfer station and the previous transfer station in the transfer time period is obtained; according to the transfer time period, the initial pheromone volatility coefficient, the second transfer speed and the cargo accumulation amount, the final pheromone volatility coefficient between each transfer station at the current time and the previous transfer station is obtained.

[0079] It should be noted that the above-mentioned expected heuristic factors and pheromone heuristic factors for path selection from each transfer station to another transfer station in each transfer time period are determined, and the pheromone volatility coefficient of the ant colony algorithm is determined next. Since there are multiple optimal paths, some of these optimal paths may serve multiple optimal paths due to line advantages, which makes the carrying capacity of the transfer station change greatly. Therefore, it is considered to determine the pheromone volatility coefficient by analyzing the carrying capacity of the transfer station in the transfer time period. The stronger the carrying capacity, the less pheromone volatility on the path during subsequent transportation, and the higher the probability of selecting the same transfer station during subsequent transportation, so as to improve the transportation efficiency of logistics.

[0080] Specifically, according to the first transfer speed of the goods at the transfer station in the transfer time period, the transfer volume of the transfer station and the number of times the transfer station appears in all optimal paths, the carrying capacity coefficient of each transfer station in each transfer time period is obtained, as follows:

[0081] The time period occupied by the transfer volume sequence of the i-th transfer station is recorded as the total transfer time period to be analyzed.

[0082]

[0083] Where V i is the average first transfer speed of all goods at the i-th transfer station during the transfer time period to be analyzed; is the average first transfer speed of all goods at the i-th transfer station during the total transfer time period to be analyzed; L i is the number of times the i-th transfer station appears in all optimal paths; M1 is the mean value of the transfer volume sequence of the i-th transfer station in the transfer time period to be analyzed; i is the maximum transfer volume of the transfer volume sequence of the i-th transfer station within the total transfer time period to be analyzed; norm() is a linear normalization function used for normalization processing; exp() is an exponential function with a natural constant as the base. This embodiment uses the exp[―U] model to present the inverse proportional relationship and normalization processing, and U is the input of the model; Q iis the carrying capacity coefficient of the i-th transfer station in the transfer time period to be analyzed.

[0084] It should be noted that It represents the difference between the average first transfer speed of the i-th transfer station in the transfer time period to be analyzed and the average first transfer speed in the total time period. The larger the difference, the faster the first transfer speed of the i-th transfer station in the transfer time period to be analyzed. The stronger the carrying capacity of the transfer station, the more goods can be transferred. i The larger it is, the more transfers are made at the i-th transfer station in all the optimal paths, the more cargo it receives and the weaker its carrying capacity. It represents the relationship between the average transshipment volume and the maximum transshipment volume. When the average transshipment volume is closer to the maximum transshipment volume, it means that the i-th transshipment station has basically achieved the optimal operating efficiency and can no longer accept other goods. The carrying capacity of the transshipment station is relatively weak.

[0085] It should be noted that the purpose of coordinated logistics management is to enable goods to reach their destination as soon as possible. During e-commerce activities, merchants often send goods to possible transfer stations in advance when pre-ordering, so that they can arrive the next day or the same day. However, under the pressure of transshipment, there is also some accumulation of goods, causing the goods to be stranded for a long time. Therefore, an expected time should also be set and the volatility coefficient should be adjusted according to the transportation time of the goods.

[0086] Furthermore, according to the carrying capacity coefficient, the distance between the transfer station and the shipping point, and the time between the shipping time and the arrival time of the goods at the transfer station, the initial pheromone volatility coefficient between each transfer station and the previous transfer station during the transit time period is obtained, as follows:

[0087] ρ0 i,i―1 =ρ×[1―Q i ×exp(―(th i ―j))]

[0088] Wherein, ρ is the preset volatility coefficient, and this embodiment is described as γ=0.5; Q i is the carrying capacity coefficient of the i-th transfer station in the transfer time period to be analyzed; i is the expected delivery time of the i-th transfer station, i =TH2+TH3×norm(d i ), the unit is day, TH2 is the preset second value, TH3 is the preset third value, and this embodiment is described as TH2=2, TH3=3, d iis the distance between the i-th transfer station and the shipping point, norm() is a linear normalization function used for normalization processing; J is the average time between the shipping time and the entry time of all goods at the i-th transfer station during the transit time period to be analyzed; exp() is an exponential function with a natural constant as the base. This embodiment uses the exp[-U] model to present the inverse proportional relationship and normalization processing, and U is the input of the model; ρ0 i,i―1 is the initial pheromone volatility coefficient between the i-th transfer station and the i-1-th transfer station during the transfer period to be analyzed.

[0089] It should be noted that the smaller the carrying capacity coefficient is, the weaker the carrying capacity of the i-th transfer station is in the subsequent logistics transfer. When the pheromone evaporates, the volatilization should be increased to reduce the probability of selecting the i-th transfer station in the subsequent transfer to ensure the efficiency of logistics transfer. i The larger the value of ―J, the faster the cargo transportation is than expected, the higher the transportation efficiency is, the i-th transfer station will receive more cargo, and the carrying capacity will deteriorate. It is necessary to enhance the volatilization of pheromones to reduce the probability of selecting the i-th transfer station in the future. Therefore, the inverse proportional function is used to realize the inverse proportion and normalization, and the initial pheromone volatilization coefficient between the i-th transfer station and the i-1-th transfer station in the transfer time period to be analyzed is obtained.

[0090] It should be noted that the above analysis is based on historical information. In order to reduce the impact of real-time changes in logistics information on the optimal path, it is necessary to analyze the logistics information at the current time to determine a more reasonable pheromone volatility coefficient.

[0091] Specifically, according to the transfer time period, the initial pheromone volatility coefficient, the second transfer speed and the cargo accumulation amount, the final pheromone volatility coefficient between each transfer station at the current time and the previous transfer station is obtained, as follows:

[0092] The transfer time period corresponding to the current time of the qth transfer station in the area to be analyzed is recorded as the target transfer time period; the time period from the start time of the target transfer time period to the current time of the qth transfer station is recorded as the first time period.

[0093]

[0094] Where ρ0 q,q―1 V2 is the initial pheromone volatility coefficient between the qth transfer station and the q-1th transfer station during the transfer period to be analyzed; q V1 is the average second transfer speed of all goods at the qth transfer station in the first time period; q is the average first transfer speed of all goods at the qth transfer station during the target transfer time period; Y qis the cargo accumulation amount of the qth transfer station on the current day; norm() is a linear normalization function used for normalization processing; ε is the first preset hyperparameter, the purpose is to prevent the denominator from being 0, and this embodiment is described as ε=0.1; ρ q,q―1 It is the final pheromone volatility coefficient between the qth transfer station and the q-1th transfer station at the current time.

[0095] It should be noted that V2 q ―V1 q The larger it is, the faster the transfer speed of the qth transfer station in the recent period is than that in the corresponding transfer period of the previous year. At the same time, if the current cargo accumulation at the qth transfer station is smaller, it means that the current qth transfer station can accommodate more logistics goods, and the initial pheromone volatilization coefficient should be appropriately reduced to increase the probability of selecting the qth transfer station in subsequent logistics transportation.

[0096] At this point, the final pheromone volatility coefficient between each transfer station at the current time and the previous transfer station is obtained.

[0097] Step S005: According to the current time of the transfer station, the pheromone heuristic factor and the expected heuristic factor for path selection, the final pheromone heuristic factor and the expected heuristic factor for path selection from each transfer station to another transfer station at the current time are obtained; according to the final pheromone volatility coefficient, the final pheromone heuristic factor, the expected heuristic factor for final path selection and the ant colony algorithm, the optimal path from the starting transfer station to the final transfer station in the area to be analyzed is obtained.

[0098] It should be noted that with the activities of e-commerce, logistics transportation has the characteristics of periodic fluctuations, and there are certain similarities in the transportation rules at different times. Therefore, this embodiment determines the final pheromone heuristic factor and the final path selection expectation heuristic factor at the current time based on the pheromone heuristic factor and the path selection expectation heuristic factor determined based on the historical logistics information.

[0099] Specifically, according to the current time of the transfer station, the pheromone heuristic factor and the expected heuristic factor of the path selection, the final pheromone heuristic factor and the expected heuristic factor of the path selection from each transfer station to another transfer station at the current time are obtained, as follows:

[0100] The pheromone heuristic factor from the qth transfer station to the fth transfer station within the target transfer time period is used as the final pheromone heuristic factor from the qth transfer station to the fth transfer station at the current time; the expected heuristic factor of the path selection from the qth transfer station to the fth transfer station within the target transfer time period is used as the final expected heuristic factor of the path selection from the qth transfer station to the fth transfer station at the current time.

[0101] Furthermore, according to the final pheromone volatility coefficient, the final pheromone heuristic factor, the final path selection expectation heuristic factor and the ant colony algorithm, the optimal path from the starting transfer station to the final transfer station in the area to be analyzed is obtained.

[0102] It should be noted that, according to the final pheromone volatility coefficient, the final pheromone heuristic factor, the final path selection expected heuristic factor and the ant colony algorithm, the optimal path from the starting transfer station to the final transfer station in the area to be analyzed is obtained by the existing method of the ant colony algorithm, which will not be repeated in this embodiment. After obtaining the optimal path from the starting transfer station to the final transfer station in the area to be analyzed, the optimal path analysis result is integrated into the existing smart logistics management system, making it a part of the decision support system, thereby improving logistics efficiency, reducing costs, and reducing the burden of smart logistics overall management.

[0103] Through the above steps, a smart logistics overall management method based on data analysis is completed.

[0104] Another embodiment of the present invention provides a smart logistics coordination management system based on data analysis, the system comprising a memory and a processor, and when the processor executes a computer program stored in the memory, the processor performs the following operations:

[0105] Obtain the transshipment volume sequence of each transfer station in the area to be analyzed in the past year, the number of daily transportations from each transfer station to another transfer station, the transportation time of each transportation, and the first transshipment speed of each cargo in each transfer station; obtain several optimal paths from the starting transfer station to the final transfer station in the area to be analyzed; obtain the time between the shipment time and the entry time of the cargo in each transfer station in the area to be analyzed in the past year; obtain the distance length between each transfer station and the shipment point in the area to be analyzed; obtain the cargo accumulation volume of each transfer station in the area to be analyzed every day in the current year, and the second transshipment speed of each cargo in each transfer station, and obtain Take the current time of each transfer station in the area to be analyzed; segment the transfer volume sequence to obtain several transfer time periods for each transfer station; obtain the transportation stability of each transfer station to another transfer station in each transfer time period according to the changes in the number of transportations and transportation time from the transfer station to another transfer station in the transfer time period; obtain the probability of each transfer station to another transfer station in each transfer time period; adjust the initial pheromone heuristic factor according to the transportation stability and probability from the transfer station to another transfer station, and obtain the pheromone heuristic factor from each transfer station to another transfer station in each transfer time period; adjust the initial pheromone heuristic factor according to the transportation stability and probability from the transfer station to another transfer station, and obtain the pheromone heuristic factor from each transfer station to another transfer station in each transfer time period; adjust the initial pheromone heuristic factor according to the transportation stability and probability from the transfer station to another transfer station. The expected heuristic factor of initial path selection is adjusted based on the transportation stability and probability of each transfer station, and the expected heuristic factor of path selection from each transfer station to another transfer station in each transfer time period is obtained; the carrying capacity coefficient of each transfer station in each transfer time period is obtained according to the first transfer speed of the goods at the transfer station in the transfer time period, the transfer volume of the transfer station and the number of times the transfer station appears in all optimal paths; the initial pheromone volatility between each transfer station and the previous transfer station in the transfer time period is obtained according to the carrying capacity coefficient, the distance length between the transfer station and the shipping point, and the time between the shipping time and the entry time of the goods at the transfer station Coefficient; according to the transfer time period, the initial pheromone volatility coefficient, the second transfer speed and the cargo accumulation amount, the final pheromone volatility coefficient between each transfer station at the current time and the previous transfer station is obtained; according to the current time of the transfer station, the pheromone heuristic factor and the expected heuristic factor for path selection, the final pheromone heuristic factor and the final expected heuristic factor for path selection from each transfer station at the current time to another transfer station are obtained; according to the final pheromone volatility coefficient, the final pheromone heuristic factor, the final expected heuristic factor for path selection and the ant colony algorithm, the optimal path from the starting transfer station to the final transfer station in the area to be analyzed is obtained.

[0106] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A smart logistics overall management method based on data analysis, characterized in that: The method comprises the following steps: Obtain the transshipment volume sequence of each transfer station in the area to be analyzed in the past year, the number of daily transportations from each transfer station to another transfer station, the transportation time of each transportation, and the first transshipment speed of each cargo in each transfer station; obtain several optimal paths from the starting transfer station to the final transfer station in the area to be analyzed; obtain the time between the shipment time and the entry time of the cargo in each transfer station in the area to be analyzed in the past year; obtain the distance length between each transfer station and the shipment point in the area to be analyzed; obtain the cargo accumulation volume of each transfer station in the area to be analyzed every day in the current year, the second transshipment speed of each cargo in each transfer station, and obtain the current time of each transfer station in the area to be analyzed; The transfer volume sequence is segmented to obtain several transfer time periods for each transfer station; according to the changes in the number of transportations and transportation time from a transfer station to another transfer station within the transfer time period, the transportation stability from each transfer station to another transfer station within each transfer time period is obtained; the probability of each transfer station to another transfer station within each transfer time period is obtained; The initial pheromone heuristic factor is adjusted according to the transportation stability and probability from a transfer station to another transfer station, and the pheromone heuristic factor from each transfer station to another transfer station in each transfer time period is obtained; the initial path selection expectation heuristic factor is adjusted according to the transportation stability and probability from a transfer station to another transfer station, and the path selection expectation heuristic factor from each transfer station to another transfer station in each transfer time period is obtained; According to the first transfer speed of the goods at the transfer station in the transfer time period, the transfer volume of the transfer station and the number of times the transfer station appears in all optimal paths, the carrying capacity coefficient of each transfer station in each transfer time period is obtained; according to the carrying capacity coefficient, the distance between the transfer station and the shipping point, and the time between the shipping time and the entry time of the goods at the transfer station, the initial pheromone volatility coefficient between each transfer station and the previous transfer station in the transfer time period is obtained; according to the transfer time period, the initial pheromone volatility coefficient, the second transfer speed and the cargo accumulation amount, the final pheromone volatility coefficient between each transfer station at the current time and the previous transfer station is obtained; According to the current time of the transfer station, the pheromone heuristic factor and the expected heuristic factor of path selection, the final pheromone heuristic factor and the final expected heuristic factor of path selection from each transfer station to another transfer station at the current time are obtained; according to the final pheromone volatility coefficient, the final pheromone heuristic factor, the final expected heuristic factor of path selection and the ant colony algorithm, the optimal path from the starting transfer station to the final transfer station in the area to be analyzed is obtained.

2. According to claim 1, a smart logistics overall management method based on data analysis is characterized in that: The method of obtaining the transportation stability from each transfer station to another transfer station in each transfer time period according to the changes in the transportation times and transportation duration from the transfer station to another transfer station in the transfer time period includes the following specific steps: Any transfer time period of the i-th transfer station is recorded as the transfer time period to be analyzed; Where, T1 i,j is the extreme value of the transportation time from the i-th transfer station to the j-th transfer station during the transfer period to be analyzed; S i,j is the number of transportations from the i-th transfer station to the j-th transfer station during the transfer period to be analyzed; T i,j,s+1 is the transportation time from the i-th transfer station to the j-th transfer station in the s+1-th transportation within the transfer time period to be analyzed; T i,j,s is the transportation time from the i-th transfer station to the j-th transfer station in the s-th transportation during the transfer period to be analyzed; || is the absolute value; exp() is an exponential function with a natural constant as the base; H i,j It is the transportation stability from the i-th transfer station to the j-th transfer station during the transfer time period to be analyzed.

3. According to claim 2, a smart logistics overall management method based on data analysis is characterized in that: The specific method for obtaining the probability of each transfer station to another transfer station in each transfer time period is as follows: Obtain the number of transportations from the i-th transfer station to all other transfer stations during the transfer time period to be analyzed, and record it as the total number of transportations of the i-th transfer station; obtain the number of transportations from the i-th transfer station to the j-th transfer station during the transfer time period to be analyzed; take the ratio of the number of transportations from the i-th transfer station to the j-th transfer station to the total number of transportations of the i-th transfer station as the probability of the i-th transfer station to the j-th transfer station during the transfer time period to be analyzed.

4. According to claim 2, a smart logistics overall management method based on data analysis is characterized in that: The initial pheromone heuristic factor is adjusted according to the transportation stability and probability from a transfer station to another transfer station to obtain the pheromone heuristic factor from each transfer station to another transfer station in each transit time period, and the specific steps include the following: a i,j =α0×(1―H i,j ×P i,j ) Where α0 is the preset initial pheromone heuristic factor; H i,j is the transportation stability from the i-th transfer station to the j-th transfer station during the transfer period to be analyzed; P i,j is the probability of the i-th transfer station to the j-th transfer station during the transfer period to be analyzed; α i,j is the pheromone heuristic factor from the i-th transfer station to the j-th transfer station during the transfer period to be analyzed.

5. According to claim 2, a smart logistics overall management method based on data analysis is characterized in that: The initial path selection expectation heuristic factor is adjusted according to the transportation stability and probability from the transfer station to another transfer station to obtain the path selection expectation heuristic factor from each transfer station to another transfer station in each transfer time period, and the specific steps include the following: Where β0 is the expected heuristic factor for the preset initial path selection; H i,j is the transportation stability from the i-th transfer station to the j-th transfer station during the transfer period to be analyzed; P i,j is the probability of the i-th transfer station to the j-th transfer station during the transfer period to be analyzed; norm() is the linear normalization function; β i,j Select the expected heuristic factor for the path from the i-th transfer station to the j-th transfer station during the transfer time period to be analyzed.

6. According to claim 2, a smart logistics overall management method based on data analysis is characterized in that: The method of obtaining the carrying capacity coefficient of each transfer station in each transfer time period according to the first transfer speed of the goods at the transfer station in the transfer time period, the transfer volume of the transfer station and the number of times the transfer station appears in all optimal paths includes the following specific steps: The time period occupied by the transfer volume sequence of the i-th transfer station is recorded as the total transfer time period to be analyzed; Where V i is the average first transfer speed of all goods at the i-th transfer station during the transfer time period to be analyzed; is the average first transfer speed of all goods at the i-th transfer station during the total transfer time period to be analyzed; L i is the number of times the i-th transfer station appears in all optimal paths; M1 is the mean value of the transfer volume sequence of the i-th transfer station in the transfer time period to be analyzed; i is the maximum transfer volume of the transfer volume sequence of the i-th transfer station in the total transfer time period to be analyzed; norm() is the linear normalization function; Q i is the carrying capacity coefficient of the i-th transfer station in the transfer time period to be analyzed.

7. According to claim 2, a smart logistics overall management method based on data analysis is characterized in that: The method of obtaining the initial pheromone volatility coefficient between each transfer station and the previous transfer station during the transit time period according to the carrying capacity coefficient, the distance between the transfer station and the shipping point, and the time between the shipping time and the arrival time of the goods at the transfer station includes the following specific steps: ρ0 i,i―1 =ρ×[1―Q i ×exp(―(th i ―J))] Where, ρ is the preset volatility coefficient; Q i is the carrying capacity coefficient of the i-th transfer station in the transfer time period to be analyzed; i is the expected delivery time of the i-th transfer station, i =TH2+TH3×norm(d i ), TH2 is a preset second value, TH3 is a preset third value, d i is the distance between the i-th transfer station and the shipping point, norm() is a linear normalization function; J is the average time between the shipping time and the entry time of all goods at the i-th transfer station during the transit time period to be analyzed; ρ0 i,i―1 is the initial pheromone volatility coefficient between the i-th transfer station and the i-1-th transfer station during the transfer period to be analyzed.

8. According to claim 1, a smart logistics overall management method based on data analysis is characterized in that: The method of obtaining the final pheromone volatility coefficient between each transfer station at the current time and the previous transfer station according to the transfer time period, the initial pheromone volatility coefficient, the second transfer speed and the cargo accumulation amount includes the following specific steps: The transfer time period corresponding to the current time of the qth transfer station in the area to be analyzed is recorded as the target transfer time period; the time period from the start time of the target transfer time period to the current time of the qth transfer station is recorded as the first time period; In the formula, ρ0 q,q―1 V2 is the initial pheromone volatility coefficient between the qth transfer station and the q-1th transfer station during the transfer period to be analyzed; q V1 is the average second transfer speed of all goods at the qth transfer station in the first time period; q is the average first transfer speed of all goods at the qth transfer station during the target transfer time period; Y q is the cargo accumulation amount of the qth transfer station on the current day; norm() is the linear normalization function; ε is the preset first hyperparameter; ρ q,q―1 It is the final pheromone volatility coefficient between the qth transfer station and the q-1th transfer station at the current time.

9. According to claim 8, a smart logistics overall management method based on data analysis is characterized in that: The method of obtaining the final pheromone heuristic factor and the final path selection expected heuristic factor from each transfer station to another transfer station at the current time according to the current time of the transfer station, the pheromone heuristic factor and the path selection expected heuristic factor includes the following specific steps: The pheromone heuristic factor from the qth transfer station to the fth transfer station within the target transfer time period is used as the final pheromone heuristic factor from the qth transfer station to the fth transfer station at the current time; the expected heuristic factor of the path selection from the qth transfer station to the fth transfer station within the target transfer time period is used as the final expected heuristic factor of the path selection from the qth transfer station to the fth transfer station at the current time.

10. A smart logistics coordination management system based on data analysis, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the computer program is executed by the processor, the steps of the intelligent logistics overall management method based on data analysis as described in any one of claims 1 to 9 are implemented.

Images