CN-121981789-A - Big data-based supply management method, system and storage medium

CN121981789ACN 121981789 ACN121981789 ACN 121981789ACN-121981789-A

Abstract

The invention discloses a supply management method, a system and a storage medium based on big data, which are characterized in that the big data of a supply chain order are obtained, the big data of the supply chain order are subjected to data classification based on a support vector machine, the obtained food supply data are subjected to data fluctuation analysis to obtain a data fluctuation curve, the data prediction is performed on the basis of the data fluctuation curve based on a linear regression algorithm, the price prediction fluctuation data and the supply quantity prediction fluctuation data of each supply unit are obtained, the supply demand information of the next preset supply period is obtained, the supply demand information is taken as a supply target, the price prediction fluctuation data and the supply quantity prediction fluctuation data of each supply unit are combined, the matching degree of each supply area is analyzed, the joint supply analysis and the logistics aging matching optimization are performed on a plurality of supply areas based on the matching degree and the geographic position of each supply area in a map model, and the optimal supply scheme under the next preset supply period is obtained.

Inventors

HUANG XUDONG
HUANG XUXING
ZHONG TING

Assignees

广州中厨信息产业有限公司

Dates

Publication Date: 20260505
Application Date: 20240112

Claims (10)

1. A big data based provisioning management method, comprising: constructing a map model based on visualization based on the target food supply chain region information; acquiring food supply chain unit information, and dividing supply unit areas through a map model based on the food supply chain unit information to obtain a plurality of supply areas, wherein one supply area corresponds to one supply unit; Acquiring large supply chain order data, classifying the large supply chain order data based on a support vector machine, and acquiring food supply data of each supply unit; Based on a time dimension, carrying out data extraction and data fluctuation analysis on price and delivery of the food supply data to obtain a data fluctuation curve, and based on a linear regression algorithm, carrying out data prediction on the basis of the data fluctuation curve to obtain price prediction fluctuation data and delivery prediction fluctuation data of each supply unit; Acquiring supply demand information of the next preset supply period, taking the supply demand information as a supply target, and analyzing the matching degree of each supply area by combining the price forecast fluctuation data and the supply quantity forecast fluctuation data of each supply unit; and in the map model, based on the matching degree and the geographic position of each supply area, carrying out joint supply analysis and logistics aging matching optimization on a plurality of supply areas, and obtaining an optimal supply scheme under the next preset supply period.
2. The big data-based supply management method according to claim 1, wherein the constructing a map model based on visualization based on the target food supply chain region information is specifically: acquiring target food supply chain region information; The target food supply chain region information comprises region area, region outline and supply unit information of a supply chain region; and constructing a map model based on three-dimensional visualization based on the target food supply chain region information.
3. The big data-based supply management method according to claim 1, wherein the acquiring the food supply chain unit information, based on the food supply chain unit information, performs supply unit area division through a map model to obtain a plurality of supply areas, one supply area corresponding to each supply unit, specifically comprises: acquiring food supply chain region information including position information of all supply units in a food supply chain; The method comprises the steps of importing position information of supply units into a map model, dividing areas of a supply chain based on different positions of the supply units, ensuring that the divided areas meet preset standards, and forming a plurality of supply areas; one supply area corresponds to one supply unit.
4. The big data-based supply management method according to claim 1, wherein the acquiring the big data of the supply chain order, classifying the big data of the supply chain order based on a support vector machine, and obtaining the food supply data of each supply unit comprises: Acquiring historical supply chain order data; Constructing a classification model based on a support vector machine; initializing parameters of the classification model, selecting an initial preset kernel function, importing historical supply chain order data into the classification model for classification training, verification and optimization, and carrying out model evaluation and parameter optimization on the classification model based on K-fold cross verification; performing model training circularly until the classification model reaches preset accuracy; Acquiring big data of a supply chain order in a preset time period, and performing data cleaning and data conversion pretreatment on the big data of the supply chain order; Importing big data of the supply chain order into a classification model to carry out data classification, and obtaining food supply data of each supply unit based on classification results; the food supply data includes commodity kind data, price data, and supply amount data.
5. The big data-based supply management method according to claim 1, wherein the time dimension-based data extraction and data fluctuation analysis of price and delivery of the food supply data are performed to obtain a data fluctuation curve, the linear regression algorithm-based data prediction is performed on the basis of the data fluctuation curve, and price prediction fluctuation data and delivery prediction fluctuation data of each supply unit are obtained, specifically: Taking a supply unit as an analysis unit, extracting data of price and supply quantity of food supply data to obtain data of price and supply quantity; serializing the price and the supply data based on the time dimension to form serialized data; generating a price discrete data map and a goods discrete data map based on the serialized data; based on a linear regression analysis method, carrying out discrete point continuity prediction and data supplementation on the price discrete data graph and the goods discrete data graph to form a complete price fluctuation curve and a complete goods fluctuation curve; The data fluctuation curve comprises a price fluctuation curve and a goods fluctuation curve; based on the price fluctuation curve and the goods fluctuation curve, carrying out data prediction of the next preset supply period by combining a linear regression analysis method to obtain price prediction fluctuation data and goods supply quantity prediction fluctuation data; Food supply data of each supply unit is analyzed and price prediction fluctuation data and supply quantity prediction fluctuation data of each supply unit are obtained.
6. The big data-based supply management method according to claim 1, wherein the obtaining the supply demand information of the next preset supply period, taking the supply demand information as a supply target, and analyzing the matching degree of each supply area by combining the price forecast fluctuation data and the supply quantity forecast fluctuation data of each supply unit comprises: Data analysis based on price and cargo quantity is carried out according to the supply demand information, and price and cargo demand range information is obtained; calculating demand and cargo matching degree by combining price and cargo demand range information based on price forecast fluctuation data and cargo supply forecast fluctuation data of each supply unit; The demand matching degree calculating process is used for calculating and analyzing duration time T1 and maximum deviation value D1 when the price demand is met in the price forecast fluctuation data, wherein the maximum deviation value D1 is the maximum difference value between the price forecast fluctuation data and the price demand value; calculating a bid lattice matching degree based on the duration T1 and a maximum deviation value D1; calculating and analyzing duration time T2 and maximum deviation value D2 when the goods forecast fluctuation data meets the goods quantity demand, wherein the maximum deviation value D2 is the maximum difference value between the price forecast fluctuation data and the price demand value; calculating the matching degree of the goods based on the duration time T2 and the maximum deviation value D2; Calculating the average value of the price matching degree and the goods matching degree, and taking the calculation result as the comprehensive matching degree; And calculating the comprehensive matching degree of all the supply areas.
7. The big data-based supply management method according to claim 1, wherein in the map model, based on the matching degree and the geographic position of each supply area, performing joint supply analysis and logistics aging matching optimization on a plurality of supply areas, and obtaining an optimal supply scheme under a next preset supply period, specifically: setting a target end point of a supply chain through a map model, and carrying out logistics ageing evaluation calculation based on the geographic position of each supply area and the target end point, wherein the evaluation analysis dimension comprises path length and road complexity, so as to obtain a corresponding logistics ageing predicted value; taking a supply area with the comprehensive matching degree larger than a preset matching threshold value as a region to be selected; performing combined analysis of a plurality of supply units from a region to be selected, forming a supply scheme by the combined plurality of supply units, evaluating a supply chain scheme by taking the comprehensive matching degree and the logistics aging predicted value in the supply scheme as evaluation indexes and optimization targets, and performing combined and scheme optimization analysis of the plurality of supply units from the region to be selected circularly to obtain an optimal supply scheme; the optimal supply scheme comprises the combination of the selection of the supply area and the corresponding supply units and the order transaction information of the supply units.
8. The big data-based supply management system is characterized by comprising a memory and a processor, wherein the memory comprises a big data-based supply management program, and the big data-based supply management program realizes the following steps when being executed by the processor: constructing a map model based on visualization based on the target food supply chain region information; acquiring food supply chain unit information, and dividing supply unit areas through a map model based on the food supply chain unit information to obtain a plurality of supply areas, wherein one supply area corresponds to one supply unit; Acquiring large supply chain order data, classifying the large supply chain order data based on a support vector machine, and acquiring food supply data of each supply unit; Based on a time dimension, carrying out data extraction and data fluctuation analysis on price and delivery of the food supply data to obtain a data fluctuation curve, and based on a linear regression algorithm, carrying out data prediction on the basis of the data fluctuation curve to obtain price prediction fluctuation data and delivery prediction fluctuation data of each supply unit; Acquiring supply demand information of the next preset supply period, taking the supply demand information as a supply target, and analyzing the matching degree of each supply area by combining the price forecast fluctuation data and the supply quantity forecast fluctuation data of each supply unit; and in the map model, based on the matching degree and the geographic position of each supply area, carrying out joint supply analysis and logistics aging matching optimization on a plurality of supply areas, and obtaining an optimal supply scheme under the next preset supply period.
9. The big data based supply management system of claim 8, wherein the constructing a visual based map model based on the target food supply chain region information is specifically: acquiring target food supply chain region information; The target food supply chain region information comprises region area, region outline and supply unit information of a supply chain region; and constructing a map model based on three-dimensional visualization based on the target food supply chain region information.
10. A computer-readable storage medium, wherein a big data based provisioning management program is included in the computer-readable storage medium, which when executed by a processor, implements the steps of the big data based provisioning management method according to any of claims 1 to 7.

Description

Big data-based supply management method, system and storage medium Technical Field The present invention relates to the field of big data analysis, and more particularly, to a method, a system, and a storage medium for managing provisioning based on big data. Background With increasing concern about food safety and sustainability, analysis and management of the food supply chain has become increasingly important. The traditional food supply chain analysis method mainly depends on manual analysis and simple data analysis technology, cannot process massive, diversified and real-time big data, and is difficult to find hidden rules and predict future development trends. In addition, due to the fact that the prior art is limited, the current reasonable analysis and optimization selection of the video supply chain are weak in analysis capability, and the problem that the supply scheme is unreasonable and the risk of the food supply chain is increased due to the fact that the effective analysis of big data of the supply chain is lacking in advance, the development of the food processing industry is hindered. Therefore, there is a need for a method, system and storage medium for managing provisioning based on big data. Disclosure of Invention The invention overcomes the defects of the prior art and provides a supply management method, a supply management system and a storage medium based on big data. The first aspect of the present invention provides a big data based provisioning management method, comprising: constructing a map model based on visualization based on the target food supply chain region information; acquiring food supply chain unit information, and dividing supply unit areas through a map model based on the food supply chain unit information to obtain a plurality of supply areas, wherein one supply area corresponds to one supply unit; Acquiring large supply chain order data, classifying the large supply chain order data based on a support vector machine, and acquiring food supply data of each supply unit; Based on a time dimension, carrying out data extraction and data fluctuation analysis on price and delivery of the food supply data to obtain a data fluctuation curve, and based on a linear regression algorithm, carrying out data prediction on the basis of the data fluctuation curve to obtain price prediction fluctuation data and delivery prediction fluctuation data of each supply unit; Acquiring supply demand information of the next preset supply period, taking the supply demand information as a supply target, and analyzing the matching degree of each supply area by combining the price forecast fluctuation data and the supply quantity forecast fluctuation data of each supply unit; and in the map model, based on the matching degree and the geographic position of each supply area, carrying out joint supply analysis and logistics aging matching optimization on a plurality of supply areas, and obtaining an optimal supply scheme under the next preset supply period. In this scheme, based on target food supply chain area information, the map model based on visualization is constructed, specifically: acquiring target food supply chain region information; The target food supply chain region information comprises region area, region outline and supply unit information of a supply chain region; and constructing a map model based on three-dimensional visualization based on the target food supply chain region information. In this scheme, obtain food supply chain unit information, based on food supply chain unit information carries out supply unit regional division through map model, obtains a plurality of supply areas, and a supply area corresponds a supply unit, specifically is: acquiring food supply chain region information including position information of all supply units in a food supply chain; The method comprises the steps of importing position information of supply units into a map model, dividing areas of a supply chain based on different positions of the supply units, ensuring that the divided areas meet preset standards, and forming a plurality of supply areas; one supply area corresponds to one supply unit. In this scheme, the acquiring the big data of the supply chain order, classifying the big data of the supply chain order based on the support vector machine, and obtaining the food supply data of each supply unit specifically includes: Acquiring historical supply chain order data; Constructing a classification model based on a support vector machine; initializing parameters of the classification model, selecting an initial preset kernel function, importing historical supply chain order data into the classification model for classification training, verification and optimization, and carrying out model evaluation and parameter optimization on the classification model based on K-fold cross verification; performing model training circularly until the classification model reaches preset accuracy; Acq