Waybill intelligent optimization method and system

Abstract

The invention discloses a waybill intelligent optimization method and system, and relates to the technical field of artificial intelligence, and the method comprises the steps: constructing a multi-dimensional attribute map of a waybill network; searching candidate waybill combinations meeting spatial-temporal continuity constraints in the multi-dimensional attribute atlas through a graph theory algorithm; on the basis of the candidate waybill combination, constructing a mixed integer programming model comprising decision variables, an objective function and constraint conditions; submitting the mixed integer programming model to a solver to obtain an optimal solution set which meets all constraint conditions and enables the target function to reach the maximum value; and generating a visual scheduling scheme based on the optimal solution set. The problem that intelligent optimization of scattered waybills cannot be realized in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a method and system for intelligent optimization of waybills. Background Technology

[0002] In modern logistics, especially in long-haul transportation, there are numerous scattered, one-way transport orders (i.e., "fragmented waybills"). The core demand of carriers and platforms is to efficiently organize transport capacity and connect independent waybills into a continuous and efficient transport task chain. However, existing waybill combination matching schemes have significant shortcomings: manual scheduling and matching rely on personal experience, resulting in low efficiency, slow response, and inability to guarantee economic viability, making it difficult to cope with the dynamic changes of massive number of waybills; rule-based simple matching methods are rigid, only suitable for single return trips or short-distance waybill combinations, and cannot discover complex high-value combination opportunities such as multilateral closed loops; locally optimal greedy algorithms are prone to falling into the limitation of "taking it one step at a time," missing the globally optimal combination, resulting in poor transport capacity network efficiency.

[0003] Existing technologies still suffer from core defects such as distorted model abstraction, incomplete search space, lack of business constraints, and rigid and singular optimization objectives: Traditional methods ignore key differences in customer, price, and vehicle requirements of different waybills, thus becoming disconnected from business reality; they are difficult to systematically explore complex combinations of multiple segments, limiting their optimization potential; the generated solutions often ignore actual constraints such as the availability frequency of waybills, making them unexecutable; and they can only optimize in a single dimension, failing to meet the multi-dimensional business objectives that enterprises dynamically adjust.

[0004] Therefore, there is an urgent need for an intelligent optimization method for combining scattered waybills. Summary of the Invention

[0005] In view of this, the present invention proposes a method and system for intelligent optimization of waybills, which can realize intelligent optimization of scattered waybills.

[0006] To achieve the above objectives, the present invention provides the following technical solution: A smart waybill optimization method includes: Constructing a multi-dimensional attribute graph of the waybill network; Candidate waybill combinations that satisfy the spatiotemporal continuity constraint are searched in the multidimensional attribute graph using graph theory algorithms; Based on the combination of candidate waybills, a mixed integer programming model is constructed, which includes decision variables, objective function and constraints. The mixed-integer programming model is submitted to the solver to obtain the optimal solution set that satisfies all constraints and maximizes the objective function; A visual scheduling scheme is generated based on the optimal solution set.

[0007] Based on the above technical solution, the present invention can be further improved as follows: Optionally, the construction of the multidimensional attribute map of the waybill network includes: The origin, destination city, or specific station of the waybill is abstracted as a node in a multi-dimensional attribute graph, and each unique waybill is abstracted as a directed edge in the multi-dimensional attribute graph. Each directed edge is associated with the multi-dimensional attribute vector of the waybill. The multidimensional attribute vector includes waybill ID, revenue, cost, gross profit, transportation timeliness requirements, departure time window, arrival time window, vehicle type requirements, vehicle length requirements, waybill availability frequency, and waybill availability shifts.

[0008] Optionally, the spatiotemporal continuity constraint includes spatial continuity constraints and temporal continuity constraints: The spatial continuity constraint requires that the destination of the previous waybill must be the origin of the next waybill. The time continuity constraint requires that the estimated arrival time of the previous waybill must be earlier than the latest departure time of the next waybill, with turnaround time allowed.

[0009] Optionally, the candidate waybill combinations include closed-loop combinations and link combinations; The closed-loop combination is a combination of waybills whose origin node of the first waybill is the same as the destination node of the last waybill. The link combination is a long-distance task chain in which the origin node of each waybill is sequentially connected to the destination node of the previous waybill, and the origin node of the first waybill is different from the destination node of the last waybill.

[0010] Optionally, the decision variable is a binary variable, where a value of 1 indicates that the candidate waybill combination is adopted, and a value of 0 indicates that the candidate waybill combination is not adopted.

[0011] Optionally, the objective function includes: The comprehensive value score of each candidate waybill combination is calculated using formula (1); Formula (1); In the formula, The comprehensive value score for each candidate waybill combination. For the number of business indicators, Let k be the weight coefficient of the k-th indicator. Let be the standardized score of the i-th combination on the k-th indicator.

[0012] Optionally, the constraint condition is that the total number of selected candidate waybill combinations among all candidate waybill combinations containing waybill j is less than or equal to the available frequency of waybill j.

[0013] A waybill intelligent optimization system, comprising: The graph construction module is used to construct a multi-dimensional attribute graph of the waybill network. The candidate combination generation module is used to search for candidate waybill combinations that satisfy the spatiotemporal continuity constraints in the multidimensional attribute graph using graph theory algorithms; The model building module is used to construct a mixed-integer programming model based on candidate waybill combinations, including decision variables, objective functions, and constraints. The model solving module is used to submit the mixed integer programming model to the solver to obtain the optimal solution set that satisfies all constraints and maximizes the objective function; The scheme generation module is used to generate a visual scheduling scheme based on the optimal solution set.

[0014] An electronic device includes a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the method described herein.

[0015] A non-transitory computer-readable storage medium having a computer program stored thereon, the computer program implementing the steps of the method when executed by a processor.

[0016] The present invention has the following advantages: This invention presents an intelligent waybill optimization method that constructs a multi-dimensional attribute graph of waybills and uses graph theory algorithms to search for candidate waybill combinations that satisfy spatiotemporal constraints, achieving global combination opportunity mining and overcoming the limitations of local optima. Based on the candidate waybill combinations, a mixed-integer programming model is constructed and solved using a solver, ensuring that the solution meets business constraints and maximizes the objective function, balancing economy and feasibility. A visual scheduling scheme is generated based on the optimal solution set, reducing the operational threshold for scheduling personnel and improving decision-making efficiency. This invention significantly improves the scientific and intelligent level of scattered waybill combination optimization, effectively increasing capacity utilization and transportation revenue. Attached Figure Description

[0017] For illustrative and not limiting purposes, the present invention will now be described in conjunction with embodiments and accompanying drawings, wherein: Figure 1 This is a flowchart illustrating the intelligent waybill optimization method in an embodiment of the present invention. Figure 2 This is a schematic diagram of the main components of the waybill intelligent optimization system in an embodiment of the present invention; Figure 3 This is a schematic diagram of the physical structure of the electronic device provided by the present invention. Detailed Implementation

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

[0019] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be used interchangeably where appropriate for the embodiments of the invention described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] It should be noted that, where there is no conflict, the embodiments and features of the present invention can be combined with each other. The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0021] Figure 1 This is a flowchart illustrating the intelligent waybill optimization method in an embodiment of the present invention, as shown below. Figure 1 As shown, the intelligent waybill optimization method provided in this embodiment of the invention includes the following steps S101 to S105.

[0022] S101, Construct a multi-dimensional attribute map of the waybill network.

[0023] By abstracting the origin, destination city, or specific station of a waybill as nodes in a multi-dimensional attribute graph, and abstracting each unique waybill as a directed edge in the multi-dimensional attribute graph, with each directed edge associated with the waybill's multi-dimensional attribute vector, this means that multiple parallel edges can coexist between two city nodes (e.g., Shanghai → Beijing), each edge representing a real, attribute-unique waybill. This refined modeling approach, compared to the traditional graph model that aggregates all business transactions between A and B into a weighted edge, preserves the commercial information of each waybill without loss, which is a fundamental prerequisite for subsequent accurate and feasible optimization.

[0024] The multidimensional attribute vector includes waybill ID, revenue, cost, gross profit, transportation timeliness requirements, departure time window, arrival time window, vehicle type requirements, vehicle length requirements, waybill availability frequency, and waybill availability shifts.

[0025] Each individual waybill with a unique commercial attribute (price, timeliness, vehicle type, etc.) is mapped to an independent directed edge in the graph, thereby achieving lossless and accurate modeling of complex logistics networks.

[0026] S102 uses graph theory algorithms to search for candidate waybill combinations that satisfy spatiotemporal continuity constraints in a multidimensional attribute graph.

[0027] A complete and spatiotemporally feasible candidate waybill combination solution space is generated using graph algorithms.

[0028] Algorithms such as Depth-First Search (DFS) or Simple Cycles are employed.

[0029] The spatiotemporal continuity constraints include spatial continuity constraints and temporal continuity constraints: The spatial continuity constraint requires that the destination of the previous waybill must be the origin of the next waybill. The time continuity constraint requires that the estimated arrival time of the previous waybill must be earlier than the latest departure time of the next waybill, with turnaround time allowed.

[0030] The candidate waybill combinations include closed-loop combinations and link combinations; The closed-loop combination is a combination of waybills where the origin node of the first waybill is the same as the destination node of the last waybill; look for combinations such as A→B→C→A that allow the vehicle to return to its origin.

[0031] The link combination is a long-distance task chain in which the origin node of each waybill is sequentially connected to the destination node of the previous waybill, and the origin node of the first waybill is different from the destination node of the last waybill. The goal is to find long-distance continuous task chains such as A→B→C→D.

[0032] Output a set containing all potentially feasible waybill combinations. For example, combination `i1 = {waybill j1(A→B), waybill j2(B→C), waybill j3(C→A)}`.

[0033] S103, based on the combination of candidate waybills, constructs a mixed integer programming model including decision variables, objective function and constraints.

[0034] For each candidate waybill combination `i`, define a binary decision variable `x_i`. The decision variable is a binary variable. A value of 1 (`x_i = 1`) indicates that the candidate waybill combination is adopted, and a value of 0 (`x_i = 0`) indicates that the candidate waybill combination is not adopted.

[0035] The objective function includes: The comprehensive value score of each candidate waybill combination is calculated using formula (1); Formula (1); In the formula, The comprehensive value score for each candidate waybill combination. For the number of business indicators, Let k be the weight coefficient of the k-th indicator. Let be the standardized score of the i-th combination on the k-th indicator.

[0036] Construct a dynamically configurable, weighted multi-objective function to maximize business value.

[0037] `Maximize: W1Σ(Value(i) xi) + W2 *Σxi`; `Value(i)`: The overall business value of portfolio `i`. This value is calculated using a flexible "revenue function". This function maps multiple indicators such as total gross profit, revenue per kilometer, and total mileage of the portfolio to a standardized value score through a non-linear or piecewise function (such as `y = (x-35)³ / 6 + 20` shown in the PPT). This allows the business to flexibly define "what is optimal" as needed; for example, in the current stage, "gross profit margin" may be more important than "total revenue".

[0038] `W1`, `W2`: Weighting coefficients. `W1` focuses on the economics of the solution (profit, value), while `W2` focuses on the breadth of coverage of the solution (the number of combinations adopted). By increasing the weight of `W2`, the model can be encouraged to choose the solution that can activate more shipping orders when economic values ​​are similar.

[0039] The constraint condition is that, among all candidate waybill combinations containing waybill j, the total number of selected candidate waybill combinations is less than or equal to the available frequency of waybill j.

[0040] Constraints: `Subject to: Σ(i∈Ij) xi≤freq_j, for each unique waybill j`; `j`: represents any unique waybill (as shown by an edge in the diagram).

[0041] `Ij`: represents the set of all candidate waybill combinations that contain waybill `j`.

[0042] `freq_j`: The number of times or frequency of waybill `j` is available (e.g., 3 times per week).

[0043] The business implications of this constraint: In all the finalized and adopted combinations, the total number of times any specific waybill `j` is used must never exceed its available shifts. This constraint fundamentally guarantees the feasibility of the final solution and avoids the "pie-in-the-sky" over-allocation of scarce resources.

[0044] The mixed-integer programming model includes a constraint based on the available frequency / number of waybills to ensure that the total number of times any waybill resource is used in the final solution does not exceed its supply limit, thus guaranteeing the practical feasibility of the solution.

[0045] The comprehensive business value of each waybill combination is defined and calculated by using a flexible revenue function that can include nonlinear transformations, so that the optimization objectives can be dynamically adjusted according to corporate strategies (maintaining profits, improving turnover, expanding network, etc.).

[0046] S104. Submit the mixed-integer programming model to the solver to obtain the optimal solution set that satisfies all constraints and maximizes the objective function.

[0047] Submit the completed Mixed Integer Programming (MIP) model (containing decision variables, objective function, and constraints) to a professional optimization solver (such as CPLEX, Gurobi, or the open-source CBC). The solver can efficiently find the optimal solution set `{x_i}` that satisfies all constraints and maximizes the objective function value within a huge solution space.

[0048] By constructing and solving a mixed-integer programming model, a globally optimal set of solutions that satisfy complex business constraints is selected from this space.

[0049] S105 generates a visual scheduling scheme based on the optimal solution set.

[0050] From the results returned by the solver, filter out all decision variables where `x_i = 1`.

[0051] Restoration: Each `x_i = 1` corresponds to a selected optimal waybill combination. The detailed information of these combinations (including waybills, total profit, total mileage, empty run rate, etc.) is restored.

[0052] Demonstration: At the application layer, a clear and visual interface is used to present the Top-N optimal combination solutions to dispatchers or managers, along with key performance indicators (KPIs), providing strong data support for the final vehicle dispatch decision.

[0053] Figure 2 This is a schematic diagram illustrating the main components of the waybill intelligent optimization system in an embodiment of the present invention. Figure 2As shown, the waybill intelligent optimization system 1 provided in this embodiment of the invention includes a map construction module 10, a candidate combination generation module 20, a model construction module 30, a model solving module 40, and a scheme generation module 50.

[0054] Graph construction module 10 is used to construct a multi-dimensional attribute graph of the waybill network; The candidate combination generation module 20 is used to search for candidate waybill combinations that satisfy the spatiotemporal continuity constraints in the multidimensional attribute graph using graph theory algorithms; Model building module 30 is used to build a mixed integer programming model based on candidate waybill combinations, including decision variables, objective functions and constraints. The model solving module 40 is used to submit the mixed integer programming model to the solver to obtain the optimal solution set that satisfies all constraints and maximizes the objective function; The scheme generation module 50 is used to generate a visual scheduling scheme based on the optimal solution set.

[0055] Figure 3 This is a schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as... Figure 3 As shown, the electronic device 60 includes: a processor 601, a memory 602, and a bus 603; The processor 601 and the memory 602 communicate with each other via the bus 603. The processor 601 is used to call program instructions in the memory 602 to execute the methods provided in the above-described method embodiments, and to execute the methods provided in the embodiments of the present invention.

[0056] This embodiment provides a non-transitory computer-readable storage medium that stores computer instructions, which cause a computer to execute the method provided in this embodiment of the invention.

[0057] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various storage media capable of storing program code, such as ROM, RAM, magnetic disk, or optical disk.

[0058] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A smart waybill optimization method, characterized in that, include: Constructing a multi-dimensional attribute graph of the waybill network; Candidate waybill combinations that satisfy the spatiotemporal continuity constraint are searched in the multidimensional attribute graph using graph theory algorithms; Based on the combination of candidate waybills, a mixed integer programming model is constructed, which includes decision variables, objective function and constraints. The mixed-integer programming model is submitted to the solver to obtain the optimal solution set that satisfies all constraints and maximizes the objective function; A visual scheduling scheme is generated based on the optimal solution set.

2. The intelligent waybill optimization method according to claim 1, characterized in that, The construction of the multi-dimensional attribute graph of the waybill network includes: The origin, destination city, or specific station of the waybill is abstracted as a node in a multi-dimensional attribute graph, and each unique waybill is abstracted as a directed edge in the multi-dimensional attribute graph. Each directed edge is associated with the multi-dimensional attribute vector of the waybill. The multidimensional attribute vector includes waybill ID, revenue, cost, gross profit, transportation timeliness requirements, departure time window, arrival time window, vehicle type requirements, vehicle length requirements, waybill availability frequency, and waybill availability shifts.

3. The intelligent waybill optimization method according to claim 1, characterized in that, The spatiotemporal continuity constraints include spatial continuity constraints and temporal continuity constraints: The spatial continuity constraint requires that the destination of the previous waybill must be the origin of the next waybill. The time continuity constraint requires that the estimated arrival time of the previous waybill must be earlier than the latest departure time of the next waybill, with turnaround time allowed.

4. The intelligent waybill optimization method according to claim 1, characterized in that, The candidate waybill combinations include closed-loop combinations and link combinations; The closed-loop combination is a combination of waybills whose origin node of the first waybill is the same as the destination node of the last waybill. The link combination is a long-distance task chain in which the origin node of each waybill is sequentially connected to the destination node of the previous waybill, and the origin node of the first waybill is different from the destination node of the last waybill.

5. The intelligent waybill optimization method according to claim 1, characterized in that, The decision variable is a binary variable. A value of 1 indicates that the candidate waybill combination is adopted, and a value of 0 indicates that the candidate waybill combination is not adopted.

6. The intelligent waybill optimization method according to claim 1, characterized in that, The objective function includes: The comprehensive value score of each candidate waybill combination is calculated using formula (1); Official (1); In the formula, The comprehensive value score for each candidate waybill combination. For the number of business indicators, Let k be the weight coefficient of the k-th indicator. Let be the standardized score of the i-th combination on the k-th indicator.

7. The intelligent waybill optimization method according to claim 1, characterized in that, The constraint condition is that, among all candidate waybill combinations containing waybill j, the total number of selected candidate waybill combinations is less than or equal to the available frequency of waybill j.

8. A system for intelligent optimization of waybills, characterized in that, include: The graph construction module is used to construct a multi-dimensional attribute graph of the waybill network. The candidate combination generation module is used to search for candidate waybill combinations that satisfy the spatiotemporal continuity constraints in the multidimensional attribute graph using graph theory algorithms; The model building module is used to construct a mixed-integer programming model based on candidate waybill combinations, including decision variables, objective functions, and constraints. The model solving module is used to submit the mixed integer programming model to the solver to obtain the optimal solution set that satisfies all constraints and maximizes the objective function; The scheme generation module is used to generate a visual scheduling scheme based on the optimal solution set.

9. An electronic device 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 method as described in any one of claims 1 to 7.

10. A non-transitory computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images