CN-122022628-A - Logistics information visual management system and method based on big data

CN122022628ACN 122022628 ACN122022628 ACN 122022628ACN-122022628-A

Abstract

The invention discloses a logistics information visual management system and method based on big data, and relates to the technical field of logistics information management. The logistics information visual management method based on big data comprises the steps of obtaining logistics operation information, constructing a visual scheduling management interface, identifying a target scheduling order set in the order visual layer based on a preset business rule, extracting a primary screening capacity set of each target scheduling order in the capacity visual layer, and carrying out matching optimization processing on the primary screening capacity set of each target scheduling order based on a multi-target optimization algorithm to obtain a scheduling matching set corresponding to the target scheduling order set.

Inventors

ZHOU MAOLIN
Mei Yachen
Zhong Rongjie

Assignees

易派数字科技(惠州)有限公司

Dates

Publication Date: 20260512
Application Date: 20260130

Claims (10)

1. The logistics information visual management method based on big data is characterized by comprising the following steps of: acquiring logistics operation information, and constructing a visual scheduling management interface, wherein the visual scheduling management interface comprises an order visual layer and a transport capacity visual layer; identifying a target scheduling order set in the order visualization layer based on a preset business rule, wherein the target scheduling order set comprises a plurality of target scheduling orders; performing preliminary screening processing on the target scheduling order sets in the capacity visualization layer, and extracting a primary screening capacity set of each target scheduling order; Based on a multi-objective optimization algorithm, carrying out matching optimization processing on the primary screening capacity set of each objective scheduling order to obtain a scheduling matching set corresponding to the objective scheduling order set; And generating a capacity recommendation scheme of the target scheduling order set based on the scheduling matching set, and displaying the capacity recommendation scheme on the visual scheduling management interface.
2. The big data-based logistics information visual management method of claim 1, wherein the logistics operation information comprises order information and logistics information, the order information is specifically an order attribute set of each order, the logistics information is specifically an capacity attribute set of each capacity object, and the specific steps of constructing a visual scheduling management interface are as follows: Generating an order visualization layer based on an order attribute set of each order and combining a preset geographic coordinate system, wherein the order visualization layer comprises a plurality of demand nodes and corresponding label sets; Generating the capacity visualization layer based on the capacity attribute set of each capacity object and combining a preset geographic coordinate system, wherein the capacity visualization layer comprises a plurality of capacity nodes and corresponding capacity label sets; and carrying out space-time alignment and superposition processing on the order visualization layer and the transport capacity visualization layer to generate a visual dispatching management interface.
3. The big data based logistics information visualization management method of claim 2, wherein the specific step of identifying the target scheduling order set is as follows: analyzing a scheduling urgency assessment set of each demand node based on a label set of each demand node; and selecting the target scheduling order set based on the scheduling urgency evaluation value and in combination with a preset business rule.
4. A method of visual management of big data based logistics information according to claim 3, wherein the specific step of analyzing the scheduling urgency assessment set of each of the demand nodes is as follows: performing feature extraction processing on the label set of each demand node to obtain an initial urgency evaluation set of each demand node; based on a preset space association rule, selecting an association capacity node set of each demand node in the visual scheduling management interface, and analyzing a supply and demand pressure regulation coefficient of each demand node; and carrying out fusion processing on the initial urgency evaluation value and the supply and demand pressure regulation coefficient, and analyzing a scheduling urgency evaluation set of each demand node.
5. The big data based logistics information visualization management method of claim 2, wherein the specific steps of obtaining the primary screening capacity set of each of the target scheduling orders are as follows: constructing a transport capacity set based on the capacity visualization layer; reading a label set of each demand node, and extracting a constraint condition set of each target scheduling order; extracting a capacity matching evaluation set of each target scheduling order based on the constraint condition set and the transport capacity set; And generating a primary screening capacity set of each target scheduling order based on the capacity matching evaluation sets.
6. The big data based logistics information visualization management method of claim 5, wherein the specific steps of extracting the capacity matching evaluation set of each of the target scheduling orders are as follows: performing step-by-step screening processing in the transport capacity set based on the constraint condition set, and extracting an initial candidate capacity set of each target scheduling order; And carrying out multi-criterion matching evaluation processing on the initial candidate capacity sets based on a preset matching algorithm, and generating capacity matching evaluation sets of each target scheduling order.
7. The big data based logistics information visualization management method of claim 1, wherein the specific steps of obtaining the scheduling matching set of the target scheduling order set are as follows: defining allocation variables for the corresponding target scheduling orders based on the primary screening capacity set of each target scheduling order; Based on a preset constraint condition set, and combining the allocation variable of each target scheduling order, constructing a multi-target optimization model which comprises a minimum total transportation cost function, a minimum latest completion time function and a maximum resource utilization rate function; And carrying out iterative solving and verification processing on the multi-objective optimization model based on a multi-objective optimization algorithm to generate the scheduling matching set.
8. The big data based logistics information visualization management method of claim 7, wherein the specific steps of the iterative solving and verifying process are as follows: Performing iterative analysis on the multi-objective optimization model based on a multi-objective optimization algorithm to obtain a pareto optimal solution set, wherein each solution corresponds to a preliminary allocation scheme; and performing post verification processing on each preliminary allocation scheme in the pareto optimal solution set, wherein the post verification processing comprises path planning and feasibility verification, and screening the scheduling matching set, which comprises a plurality of candidate scheduling schemes and corresponding scheduling evaluation sets.
9. The big data based logistics information visualization management method of claim 8, wherein the specific steps of generating the capacity recommendation scheme of the target scheduling order set are as follows: generating a scheduling evaluation value of each candidate scheduling scheme based on a scheduling evaluation set of each candidate scheduling scheme; And carrying out descending order arrangement on the scheduling evaluation values of each candidate scheduling scheme, generating a target scheduling scheme sorting table, and generating the capacity recommendation scheme of the target scheduling order set.
10. The big data-based logistics information visual management system, applying the big data-based logistics information visual management method as set forth in any one of claims 1 to 9, comprising: The logistics information visualization module is used for acquiring logistics operation information and constructing a visual scheduling management interface, and comprises an order visualization layer and a transport capacity visualization layer; The target order identification module is used for identifying a target scheduling order set in the order visualization layer based on a preset business rule, wherein the target scheduling order set comprises a plurality of target scheduling orders; the capacity primary screening module is used for carrying out primary screening treatment on the target scheduling order sets in the capacity visualization layer and extracting a primary screening capacity set of each target scheduling order; The capacity matching optimization module is used for carrying out matching optimization processing on the primary screening capacity set of each target scheduling order based on a multi-target optimization algorithm to obtain a scheduling matching set corresponding to the target scheduling order set; And the scheme management display module is used for generating a capacity recommendation scheme of the target scheduling order set based on the scheduling matching set and displaying the capacity recommendation scheme on the visual scheduling management interface.

Description

Logistics information visual management system and method based on big data Technical Field The invention relates to the technical field of logistics information management, in particular to a logistics information visual management system and method based on big data. Background With the deep penetration of digital economy, new business states such as electronic commerce, new retail, instant distribution and the like are vigorously developed, logistics industry is driven to enter a high-speed increasing period, the scale of logistics orders is exponentially increased, goods are increasingly diversified, distribution scenes are increasingly complex, and higher requirements are provided for the refinement and intelligence level of logistics management. In the process of upgrading logistics industry, the logistics information is taken as a core production element, the integration and utilization capacity of the logistics information becomes a key for determining the operation efficiency of logistics enterprises, in a traditional logistics management mode, data such as order information, transport capacity information, geographic information and the like are stored in different business systems in a scattered mode, the data formats are not uniform and poor in interactivity, a synergistic effect is difficult to form, mature application of a big data technology provides technical support for efficient integration and deep analysis of logistics full-link information, quantitative mining of key information such as order characteristics, transport capacity states and distribution paths can be realized, and a data basis is provided for intelligent scheduling decision. A large-data-based logistics information visual management system and method disclosed in the patent application with the bulletin number of CN116205555B in the prior art comprises the steps of collecting all transaction order records without return commodity circulation information, collecting all transaction order records with return commodity circulation information, respectively sorting a first transaction order record set and a second transaction order record set of each user, mining all condition data which cause each user to make false approval of a transaction commodity, extracting and sorting measured reference data of each user before the transaction commodity is made to be non-approved in the transaction order records, carrying out data verification on condition data corresponding to each user, analyzing to obtain an image label existing when the commodity is traded, and carrying out visual identification on the transaction order records which accord with the image labels of the corresponding users and feeding back the image labels to the target shop. Based on the above scheme, the limitations of the prior art at least include the following problems that the prior art does not touch the whole flow of order scheduling and capacity matching of a logistics operation core, so that the prior art is difficult to support the key decision requirement of logistics enterprises in order performance links, the logistics scheduling links still depend on manual experience driving, accurate docking of orders and capacity is difficult to realize, the prior art does not construct an integrated visual management interface covering the space distribution of the orders and the real-time state of the capacity, the space-time alignment and superposition display of the order and the capacity information are not realized, the key logistics situations such as order dense areas, capacity idle distribution and the like are difficult to intuitively grasp by scheduling staff, the problems of capacity resource mismatch, over-high idle rate, order distribution delay and the like are easy to occur, the time of logistics scheduling decisions is greatly restricted, the operation management requirement of complex logistics scenes is difficult to adapt, meanwhile, the logistics resource configuration is easy to be rough, and the fine development requirement of logistics industry is difficult to be satisfied. Disclosure of Invention Aiming at the defects of the prior art, the invention provides a logistics information visual management system and method based on big data, which solve the problems of low scheduling efficiency and rough resource allocation caused by matching and visualization of order missing capacity in the prior art. The logistics information visual management method based on big data comprises the following steps of obtaining logistics operation information, constructing a visual scheduling management interface which comprises an order visual layer and an operation capacity visual layer, identifying a target scheduling order set in the order visual layer based on a preset business rule, wherein the target scheduling order set comprises a plurality of target scheduling orders, performing primary screening processing on the target scheduling order set in the ope