CN-122022385-A - Multi-dimensional dynamic fusion intelligent logistics scheduling method and system

CN122022385ACN 122022385 ACN122022385 ACN 122022385ACN-122022385-A

Abstract

The invention relates to a multi-dimensional dynamic fusion intelligent logistics scheduling method and system, which relate to the technical field of logistics scheduling and comprise the steps of collecting logistics task parameters, transport capacity resource parameters and historical scheduling data; the method comprises the steps of carrying out quantization conversion according to logistics task parameters to generate task quantized values, carrying out quantization conversion according to capacity resource parameters to generate capacity quantized values, determining optimal matching scheduling strategies according to historical scheduling data, the task quantized values and the capacity quantized values, carrying out dynamic optimization according to the optimal matching scheduling strategies to generate optimal scheduling strategies, carrying out logistics scheduling based on the optimal scheduling strategies and collecting abnormal condition parameters, determining scheduling adjustment strategies according to the abnormal condition parameters and the optimal scheduling strategies, and executing the scheduling adjustment strategies. The method has the effect of being convenient for logistics scheduling and adapting to the full-dimension requirement of complex logistics scenes.

Inventors

LIU ZHENGTIAN
WENG CAIPING
FENG WEI
CHEN JUNRONG
HU BIN
YANG SHIQIAN

Assignees

杭州高达软件系统股份有限公司

Dates

Publication Date: 20260512
Application Date: 20260402

Claims (10)

1. A multi-dimensional dynamic fusion intelligent logistics scheduling method is characterized by comprising the following steps: Collecting logistics task parameters, transport capacity resource parameters and historical scheduling data; Performing quantization conversion according to the logistics task parameters to generate task quantized values, and performing quantization conversion according to the capacity resource parameters to generate capacity quantized values; determining an optimal matching scheduling strategy by combining historical scheduling data, task quantized values and capacity quantized values; dynamically optimizing according to the optimal matching scheduling strategy to generate an optimal scheduling strategy; carrying out logistics scheduling based on an optimized scheduling strategy, and collecting abnormal condition parameters; And determining a scheduling adjustment strategy by combining the abnormal condition parameters and the optimized scheduling strategy, and executing the scheduling adjustment strategy.
2. The multi-dimensional dynamic fusion intelligent logistics scheduling method of claim 1, wherein the specific steps of quantitative conversion comprise: Retrieving parameter types and type data based on logistics task parameters or transport capacity resource parameters; Determining a conversion type according to the parameter types, wherein the conversion type comprises a hierarchical coding type, a normalization type and a Boolean coding type; The category data is converted based on the conversion type.
3. The multi-dimensional dynamic fusion intelligent logistics scheduling method of claim 2, wherein converting the category data based on the conversion type comprises: retrieving a data maximum value, a data minimum value and a data real-time value based on the category data; When the conversion type is the normalization type, calculating a difference value between the maximum value and the minimum value of the data and taking the difference value as a data reference deviation value; calculating the difference between the real-time data value and the minimum data value and taking the difference as a real-time data deviation value; calculating according to the proportion between the data real-time deviation value and the data reference deviation value to perform conversion; and when the conversion type is the Boolean coding type, the type reference data is called based on the parameter type, and the conversion is carried out according to the matching result between the type data and the type reference data.
4. The multi-dimensional dynamic fusion intelligent logistics scheduling method of claim 2, wherein converting the category data based on the conversion type further comprises: when the conversion type is a hierarchical coding type, the related type and related data are called based on the parameter type; determining a correlation coefficient according to the correlation type, and determining a correlation single reference value by combining the correlation data; weighting calculation is carried out by combining the correlation coefficient and the correlation single reference value to obtain a correlation comprehensive reference value; And calling the reference level interval according to the parameter types and matching the reference level interval with the relevant comprehensive reference value for conversion.
5. The multi-dimensional dynamic fusion intelligent logistics scheduling method of claim 1, wherein the method for determining the optimal matching scheduling strategy comprises the following steps: Determining a basic weight and a trigger condition set according to the historical scheduling data; Matching and comparing the task quantized value, the transport capacity quantized value and the trigger condition set to determine a fluctuation adjusting value; adjusting the base weight based on the fluctuation adjustment value to obtain an adjustment weight; and inputting the adjustment weight, the task quantized value and the transport capacity quantized value into a preset integer programming model to obtain a programming strategy, and taking the programming strategy as an optimal matching scheduling strategy.
6. The multi-dimensional dynamic fusion intelligent logistics scheduling method of claim 5, wherein the method for determining the basic weight and the trigger condition set comprises the following steps: Scheduling sample types and single sample data are selected based on the historical scheduling data; determining a distribution maximum deviation value, a distribution intermediate value and a distribution degree reference value according to single sample data; determining a trigger selection value according to the distribution degree reference value; Determining a class number value based on the scheduling sample class; Determining single class weights by combining class number values with distribution degree reference values; calculating a product value between the trigger selection value and the distribution maximum deviation value and taking the product value as a distribution single trigger deviation value; And combining the single type weight corresponding to each scheduling sample type as a basic weight, and combining the distributed intermediate value and the distributed single trigger deviation value corresponding to each scheduling sample type as a trigger condition set.
7. The multi-dimensional dynamic fusion intelligent logistics scheduling method of claim 6, wherein the method for determining the fluctuation adjustment value comprises the following steps: Selecting a corresponding distribution intermediate value from the trigger condition set according to the task quantized value or the capacity quantized value and taking the distribution intermediate value as a selected reference value; Defining a task quantized value or a transport capacity quantized value as a current selected value, and calling a current selected category based on the current selected value; calculating a difference value between the current selected value and the selected reference value and taking the difference value as a selected deviation value; Calculating a proportion value between the selected deviation value and the selected reference value and taking the proportion value as a selected proportion value; determining a category sensitivity coefficient according to the currently selected category; and calculating and selecting a product value between the proportional value and the class sensitivity coefficient to serve as a fluctuation adjusting value.
8. The multi-dimensional dynamic fusion intelligent logistics scheduling method of claim 6, wherein the generation method of the optimal scheduling strategy comprises the following steps: The method comprises the steps of collecting, optimizing and selecting algorithm types; retrieving a sample number based on the single sample data; Determining algorithm configuration parameters by combining the optimization selection algorithm types, sample number values and type number values; Configuring an algorithm corresponding to the type of the optimization selection algorithm based on the algorithm configuration parameters and taking the algorithm as an optimization configuration algorithm; And inputting the optimal matching scheduling strategy to an optimal configuration algorithm for optimization to obtain an optimal scheduling strategy.
9. The multi-dimensional dynamic fusion intelligent logistics scheduling method of claim 1, wherein the method for determining the scheduling adjustment strategy comprises the following steps: calling an abnormal type and an influence range based on the abnormal condition parameters; Determining a response grade by combining the anomaly type and the influence range; Determining an adjustment type according to the response level; determining an intervention adjustment strategy by combining the adjustment type and the abnormality type; And adjusting the optimized scheduling strategy based on the intervention adjustment strategy to obtain the scheduling adjustment strategy.
10. A multi-dimensional dynamic fusion intelligent logistics scheduling system, comprising: the acquisition module is used for acquiring logistics task parameters, capacity resource parameters, historical scheduling data, abnormal condition parameters and optimization selection algorithm types; a memory storing a program for implementing a multi-dimensional dynamic fusion intelligent logistics scheduling method as set forth in any one of claims 1 to 9; and a processor loading and executing the program stored in the memory.

Description

Multi-dimensional dynamic fusion intelligent logistics scheduling method and system Technical Field The invention relates to the technical field of logistics scheduling, in particular to a multi-dimensional dynamic fusion intelligent logistics scheduling method and system. Background The logistics scheduling refers to the steps of comprehensively allocating various resources of a logistics full link according to actual operation requirements and coordinating the work of operation flows of all links, so that the goods can be ensured to circulate accurately, timely and at low cost according to the requirements. At present, when logistics scheduling is carried out, logistics orders in links of purchasing, production, sales and the like are generally received, basic information such as a transportation line, ageing requirements, material properties, budget ranges and the like of goods in the orders are combed, then vehicles and carriers meeting the basic vehicle types and load requirements are screened out from transportation resources based on indexes of time or cost, and a fixed transportation route and a loading scheme are formulated and scheduling is carried out. Because compliance conditions of different logistics orders are different, and required service quality is also different, logistics scheduling is generally carried out only by focusing on time or cost indexes at present, so that the method cannot adapt to the full-dimension requirements of complex logistics scenes. Disclosure of Invention The invention provides a multi-dimensional dynamic fusion intelligent logistics scheduling method and system for facilitating the adaptation to the full-dimensional requirements of complex logistics scenes during logistics scheduling. In a first aspect, the invention provides a multi-dimensional dynamic fusion intelligent logistics scheduling method, which adopts the following technical scheme: a multi-dimensional dynamic fusion intelligent logistics scheduling method comprises the following steps: Collecting logistics task parameters, transport capacity resource parameters and historical scheduling data; Performing quantization conversion according to the logistics task parameters to generate task quantized values, and performing quantization conversion according to the capacity resource parameters to generate capacity quantized values; determining an optimal matching scheduling strategy by combining historical scheduling data, task quantized values and capacity quantized values; dynamically optimizing according to the optimal matching scheduling strategy to generate an optimal scheduling strategy; carrying out logistics scheduling based on an optimized scheduling strategy, and collecting abnormal condition parameters; And determining a scheduling adjustment strategy by combining the abnormal condition parameters and the optimized scheduling strategy, and executing the scheduling adjustment strategy. By adopting the technical scheme, the logistics task parameters, the capacity resource parameters and the historical scheduling data are collected, the task quantized value and the capacity quantized value are generated through quantization conversion, the optimal matching scheduling strategy is determined and dynamically optimized by combining the three types of data, and the scheduling adjustment strategy is generated based on the abnormal condition parameters, so that the comprehensive fusion of the multidimensional parameters and the dynamic adaptation of the whole scheduling process are realized, the limitation of single parameter dependence of the traditional scheduling is effectively avoided, the logistics scheduling is ensured to be in accordance with the historical scheduling experience, the real-time task, the capacity change and the sudden abnormality can be responded, the whole dimension requirement of the complex logistics scene is conveniently met during the logistics scheduling, and the accuracy, the flexibility and the reliability of the scheduling are remarkably improved. Optionally, the specific steps of quantization conversion include: Retrieving parameter types and type data based on logistics task parameters or transport capacity resource parameters; Determining a conversion type according to the parameter types, wherein the conversion type comprises a hierarchical coding type, a normalization type and a Boolean coding type; The category data is converted based on the conversion type. By adopting the technical scheme, the parameter type and the type data of the logistics task parameter or the transport capacity resource parameter are firstly acquired, and then the conversion is carried out according to the parameter type adaptation hierarchical coding type, the normalization type or the Boolean coding type, so that the accurate matching of the quantitative conversion and the parameter characteristics is realized, and the standardized and high-quality data support is provided for the subsequent d