Supply chain management method and system based on multi-source data

Abstract

The embodiment of the invention relates to the technical field of supply chain management, and particularly discloses a supply chain management method and system based on multi-source data. According to the embodiment of the invention, multi-source data acquisition is carried out, and the multi-source acquired data is preprocessed; performing data fusion and feature extraction to obtain fused feature data; carrying out demand prediction and inventory optimization analysis, and calculating an optimal demand order quantity, a safe inventory quantity and a total inventory quantity; and carrying out network optimization analysis on transportation and distribution, and constructing a transportation cost optimization model and a distribution path optimization model. Multi-source data acquisition and preprocessing can be carried out, then data fusion and feature extraction are carried out, demand prediction and inventory optimization are carried out according to fused feature data, network optimization of transportation and distribution is carried out, the problems of data splitting and serious information islands can be effectively solved, the prediction accuracy in supply chain management is improved, and the prediction efficiency is improved. Therefore, the upstream and downstream cooperation efficiency and response speed of the supply chain are improved, and the current supply chain management requirement is met.

Description

Technical Field

[0001] The present invention belongs to the technical field of supply chain management, and in particular relates to a supply chain management method and system based on multi-source data. Background Art

[0002] Supply chain management is the process of integrated management of the flow of products, information, and funds from suppliers to end consumers. It aims to achieve efficient operation of the entire supply chain by coordinating activities across all links, including raw material procurement, manufacturing, product transportation, warehousing management, sales and distribution. Effective supply chain management enables companies to optimize resource allocation and reduce costs, such as by reducing inventory backlogs and transportation costs. It also improves responsiveness to quickly meet market demand, enhances product quality and service levels, and ultimately increases customer satisfaction. It is a key means for companies to enhance their overall competitiveness in complex market environments.

[0003] In existing technologies, since data in the supply chain usually comes from different systems, has diverse formats and different sampling frequencies, and lacks a unified data interface and fusion mechanism, it has serious problems of data fragmentation and information silos. When conducting supply chain management, it is easy to cause inaccurate predictions, which in turn leads to inefficient upstream and downstream collaboration and slow response, making it difficult to meet current supply chain management needs. Summary of the Invention

[0004] The purpose of the embodiments of the present invention is to provide a supply chain management method and system based on multi-source data, aiming to solve the problems raised in the background technology.

[0005] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions: A supply chain management method based on multi-source data, the method specifically comprising the following steps: Determining multiple data collection sources, performing multi-source data collection, obtaining multi-source collected data, and preprocessing the multi-source collected data to obtain a multi-source preprocessed data set; Perform data fusion and feature extraction on multi-source preprocessed data sets to obtain fused feature data; Based on the fused feature data, perform demand forecasting and inventory optimization analysis to calculate the optimal demand order quantity, safety stock, and total inventory; Based on the fused feature data, network optimization analysis of transportation and distribution is performed, and a transportation cost optimization model and a distribution path optimization model are constructed.

[0006] As a further limitation of the technical solution of the embodiment of the present invention, the steps of determining multiple data collection sources, performing multi-source data collection, obtaining multi-source collected data, and preprocessing the multi-source collected data to obtain a multi-source preprocessed data set specifically include the following steps: Identify multiple data collection sources, including internal enterprise sources, sensor records, external public sources, and user behavior sources; Perform multi-source data collection according to the plurality of data collection sources to obtain multi-source collected data; Performing data cleaning on the multi-source collected data; Standardizing the multi-source collected data; Performing time alignment on the multi-source collected data; Filling in gaps in the multi-source collected data; Generate multi-source preprocessed datasets.

[0007] As a further limitation of the technical solution of the embodiment of the present invention, the data fusion and feature extraction of the multi-source pre-processed data sets to obtain fused feature data specifically includes the following steps: Performing data fusion on the multi-source pre-processed data sets to obtain multi-source fused data; Feature selection and dimension reduction are performed on the multi-source fusion data to obtain fusion feature data.

[0008] As a further limitation of the technical solution of the embodiment of the present invention, performing demand forecasting and inventory optimization analysis based on the fused feature data and calculating the optimal demand order quantity, safety stock, and total inventory specifically includes the following steps: Extracting prediction-related data and inventory-related data from the fused feature data; Perform demand forecast optimization analysis based on the forecast correlation data and calculate the optimal demand order quantity; Conduct inventory optimization analysis and calculate safety stock levels based on the inventory-related data; The total inventory quantity is calculated according to the optimal demand order quantity and the safety stock quantity.

[0009] As a further limitation of the technical solution of the embodiment of the present invention, the calculation formula of the optimal required order quantity is: ; in, is the optimal order quantity, is the total annual demand, is the fixed cost of each order, is the annual inventory holding cost; The calculation formula for the safety stock is: ; in, is the safety stock, is the preset service level factor, is the standard deviation of demand, The time from order to delivery; The calculation formula for the total inventory is: ; in, is the total inventory.

[0010] As a further limitation of the technical solution of the embodiment of the present invention, performing network optimization analysis of transportation and distribution based on the fused feature data and constructing a transportation cost optimization model and a distribution path optimization model specifically include the following steps: Extracting transportation-related data and delivery-related data from the fused feature data; Conducting transportation optimization analysis based on the transportation-related data, determining the objective function and constraints, and building a transportation cost optimization model; Based on the distribution-related data, a distribution network optimization analysis is performed to build a distribution path optimization model.

[0011] A supply chain management system based on multi-source data, the system specifically includes a multi-source collection and pre-processing unit, a data fusion processing unit, a forecast inventory optimization unit, and a transportation and distribution optimization unit, wherein: A multi-source acquisition preprocessing unit is used to determine multiple data acquisition sources, perform multi-source data acquisition, obtain multi-source acquired data, and preprocess the multi-source acquired data to obtain a multi-source preprocessed data set; A data fusion processing unit is used to perform data fusion and feature extraction on multi-source pre-processed data sets to obtain fused feature data; A forecast inventory optimization unit, configured to perform demand forecasting and inventory optimization analysis based on the fused feature data, and calculate the optimal demand order quantity, safety stock, and total inventory; The transport and distribution optimization unit is used to perform network optimization analysis of transport and distribution based on the fused feature data, and to build a transport cost optimization model and a distribution path optimization model.

[0012] As a further limitation of the technical solution of the embodiment of the present invention, the multi-source acquisition preprocessing unit specifically includes: The data source determination module is used to determine multiple data collection sources, including internal enterprise sources, sensor record sources, external public sources, and user behavior sources; A multi-source data acquisition module, configured to perform multi-source data acquisition according to a plurality of data acquisition sources and obtain multi-source acquired data; A data cleaning module, used for cleaning the multi-source collected data; A standardization module, used for standardizing the multi-source collected data; A time alignment module, configured to perform time alignment on the multi-source collected data; A missing filling module is used to fill in the missing data of the multi-source collection data; The dataset generation module is used to generate multi-source preprocessed datasets.

[0013] As a further limitation of the technical solution of the embodiment of the present invention, the forecast inventory optimization unit specifically includes: A first correlation extraction module, configured to extract prediction correlation data and inventory correlation data from the fused feature data; An optimal demand order quantity calculation module is used to perform demand forecast optimization analysis and calculate the optimal demand order quantity according to the forecast correlation data; A safety stock calculation module is used to perform inventory optimization analysis and calculate the safety stock according to the inventory-related data; The total inventory calculation module is used to calculate the total inventory according to the optimal demand order quantity and the safety stock.

[0014] As a further limitation of the technical solution of the embodiment of the present invention, the transportation and distribution optimization unit specifically includes: A second association extraction module is used to extract transportation-related data and delivery-related data from the fused feature data; A transportation cost optimization model building module is used to perform transportation optimization analysis based on the transportation-related data, determine the objective function and constraint conditions, and build a transportation cost optimization model; The distribution path optimization model building module is used to perform distribution network optimization analysis based on the distribution related data and build a distribution path optimization model.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The embodiments of the present invention collect and preprocess multi-source data; perform data fusion and feature extraction to obtain fused feature data; perform demand forecasting and inventory optimization analysis to calculate the optimal demand order quantity, safety stock, and total inventory; perform network optimization analysis for transportation and distribution, and construct a transportation cost optimization model and a distribution path optimization model. The ability to collect and preprocess multi-source data, then perform data fusion and feature extraction, optimize demand forecasting and inventory based on the fused feature data, and optimize the transportation and distribution network can effectively solve the problems of data fragmentation and serious information silos, improve the prediction accuracy in supply chain management, and thus improve the efficiency and response speed of upstream and downstream collaboration in the supply chain, meeting current supply chain management needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention.

[0017] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0018] Figure 2 The flowchart of multi-source data collection and preprocessing in the method provided by the embodiment of the present invention is shown.

[0019] Figure 3 A flow chart of data fusion and feature extraction in the method provided by an embodiment of the present invention is shown.

[0020] Figure 4 A flow chart of demand forecasting and inventory optimization analysis in the method provided by an embodiment of the present invention is shown.

[0021] Figure 5 A flow chart of network optimization analysis for transportation and distribution in the method provided by an embodiment of the present invention is shown.

[0022] Figure 6 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0023] Figure 7 The structure block diagram of the multi-source acquisition preprocessing unit in the system provided by the embodiment of the present invention is shown.

[0024] Figure 8 The structure block diagram of the forecast inventory optimization unit in the system provided by the embodiment of the present invention is shown.

[0025] Figure 9 The structure block diagram of the transportation and distribution optimization unit in the system provided by the embodiment of the present invention is shown. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0027] It is understandable that in the existing technology, since the data in the supply chain usually comes from different systems, has diverse formats and different sampling frequencies, and lacks a unified data interface and fusion mechanism, there are serious problems of data fragmentation and information silos. When conducting supply chain management, it is easy to cause inaccurate predictions, which in turn leads to inefficient upstream and downstream collaboration and slow response, making it difficult to meet current supply chain management needs.

[0028] To solve the above problems, the embodiment of the present invention determines multiple data collection sources, performs multi-source data collection, obtains multi-source collected data, and pre-processes the multi-source collected data to obtain a multi-source pre-processed data set; performs data fusion and feature extraction on the multi-source pre-processed data set to obtain fused feature data; based on the fused feature data, performs demand forecasting and inventory optimization analysis, calculates the optimal demand order quantity, safety stock, and total inventory; based on the fused feature data, performs network optimization analysis of transportation and distribution, and constructs a transportation cost optimization model and a distribution path optimization model. The ability to perform multi-source data collection and pre-processing, then perform data fusion and feature extraction, and perform demand forecasting and inventory optimization based on the fused feature data, as well as network optimization of transportation and distribution, can effectively solve the problems of data fragmentation and serious information islands, improve the prediction accuracy in supply chain management, thereby improving the collaborative efficiency and response speed of upstream and downstream supply chains, and meet current supply chain management needs.

[0029] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0030] Specifically, the supply chain management method based on multi-source data includes the following steps: Step S101 : determining multiple data collection sources, performing multi-source data collection, acquiring multi-source collected data, and preprocessing the multi-source collected data to obtain a multi-source preprocessed data set.

[0031] In an embodiment of the present invention, multiple data collection sources, including internal enterprise sources, sensor recording sources, external public sources, and user behavior sources, are determined, and multi-source data collection is performed from the multiple data collection sources to obtain multi-source collected data. The multi-source collected data is then pre-processed by data cleaning (anomaly identification and elimination), standardization (unification of quantity units, monetary units, weight, and other indicators), time alignment (unification of data at different time resolutions), and missing fill (mean filling, median filling, or nearest neighbor filling) to generate a multi-source pre-processed data set. The multi-source collected data specifically includes: internal enterprise data (inventory records, purchase orders, sales history, ERP system data, etc.), sensor recording data (warehouse temperature and humidity, transport vehicle location and status, production equipment operating parameters, etc.), external public data (weather information, traffic data, social media hot spot analysis, competitor prices, etc.), and user behavior data (social media comments, search popularity, click-through rate, user evaluation, etc.).

[0032] Specifically, Figure 2 The flowchart of multi-source data collection and preprocessing in the method provided by the embodiment of the present invention is shown.

[0033] In a preferred embodiment of the present invention, the steps of determining multiple data collection sources, performing multi-source data collection, obtaining multi-source collected data, and preprocessing the multi-source collected data to obtain a multi-source preprocessed data set specifically include the following steps: Step S1011, determining multiple data collection sources, including internal enterprise sources, sensor record sources, external public sources, and user behavior sources; Step S1012, performing multi-source data collection according to the plurality of data collection sources to obtain multi-source collected data; Step S1013, performing data cleaning on the multi-source collected data; Step S1014, standardizing the multi-source collected data; Step S1015, performing time alignment on the multi-source collected data; Step S1016, performing missing filling on the multi-source collected data; Step S1017: Generate a multi-source pre-processed data set.

[0034] Furthermore, the supply chain management method based on multi-source data further includes the following steps: Step S102 : performing data fusion and feature extraction on the multi-source pre-processed data sets to obtain fused feature data.

[0035] In an embodiment of the present invention, multi-source fused data is obtained by performing data fusion on multi-source pre-processed data sets (feature-level fusion, decision-level fusion and / or embedding-level fusion may be used), and then feature selection and dimensionality reduction are performed on the multi-source fused data to obtain fused feature data.

[0036] Specifically, Figure 3 A flow chart of data fusion and feature extraction in the method provided by an embodiment of the present invention is shown.

[0037] In a preferred embodiment of the present invention, the step of performing data fusion and feature extraction on multi-source pre-processed data sets to obtain fused feature data specifically includes the following steps: Step S1021, performing data fusion on the multi-source pre-processed data set to obtain multi-source fused data; Step S1022: performing feature selection and dimensionality reduction on the multi-source fusion data to obtain fusion feature data.

[0038] Furthermore, the supply chain management method based on multi-source data further includes the following steps: Step S103: performing demand forecasting and inventory optimization analysis based on the fused feature data, and calculating the optimal demand order quantity, safety stock quantity, and total inventory quantity.

[0039] In an embodiment of the present invention, forecast-related data and inventory-related data are extracted from the fused feature data, and then demand forecast optimization analysis is performed according to the forecast-related data to calculate the optimal demand order quantity. In addition, inventory optimization analysis is performed according to the inventory-related data to calculate the safety stock. Then, the total inventory is calculated based on the optimal demand order quantity and the safety stock. Specifically, the calculation formula for the optimal demand order quantity is: ; in, is the optimal order quantity, is the total annual demand, is the fixed cost of each order, is the annual inventory holding cost; The formula for calculating safety stock is: ; in, is the safety stock, is the preset service level factor, is the standard deviation of demand, The time from order to delivery; The formula for calculating total inventory is: ; in, is the total inventory.

[0040] Specifically, Figure 4 A flow chart of demand forecasting and inventory optimization analysis in the method provided by an embodiment of the present invention is shown.

[0041] In a preferred embodiment of the present invention, performing demand forecasting and inventory optimization analysis based on the fused feature data and calculating the optimal demand order quantity, safety stock, and total inventory specifically includes the following steps: Step S1031, extracting prediction-related data and inventory-related data from the fused feature data; Step S1032: performing demand forecast optimization analysis according to the forecast related data to calculate the optimal demand order quantity; Step S1033: performing inventory optimization analysis according to the inventory-related data and calculating the safety stock amount; Step S1034: Calculate the total inventory quantity based on the optimal demand order quantity and the safety stock quantity.

[0042] Furthermore, the supply chain management method based on multi-source data further includes the following steps: Step S104: performing network optimization analysis of transportation and distribution based on the fused feature data, and constructing a transportation cost optimization model and a distribution path optimization model.

[0043] In an embodiment of the present invention, transportation-related data and distribution-related data are extracted from the fused feature data, and then transportation optimization analysis is performed based on the transportation-related data to determine the objective function and constraints for minimizing transportation costs, thereby constructing a transportation cost optimization model. Furthermore, based on the distribution-related data, a distribution network optimization analysis is performed to construct a distribution path optimization model.

[0044] Specifically, Figure 5 A flow chart of network optimization analysis for transportation and distribution in the method provided by an embodiment of the present invention is shown.

[0045] In a preferred embodiment of the present invention, the network optimization analysis of transportation and distribution is performed based on the fused feature data, and the construction of a transportation cost optimization model and a distribution path optimization model specifically includes the following steps: Step S1041, extracting transportation-related data and delivery-related data from the fused feature data; Step S1042: performing transportation optimization analysis based on the transportation-related data, determining the objective function and constraints, and constructing a transportation cost optimization model; Step S1043: Perform a distribution network optimization analysis based on the distribution-related data and construct a distribution path optimization model.

[0046] Further, Figure 6 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0047] In another preferred embodiment of the present invention, the supply chain management system based on multi-source data includes: The multi-source acquisition preprocessing unit 101 is used to determine multiple data acquisition sources, perform multi-source data acquisition, obtain multi-source acquired data, and preprocess the multi-source acquired data to obtain a multi-source preprocessed data set.

[0048] In an embodiment of the present invention, the multi-source acquisition preprocessing unit 101 determines multiple data acquisition sources including internal enterprise sources, sensor recording sources, external public sources and user behavior sources, and performs multi-source data acquisition from the multiple data acquisition sources to obtain multi-source acquired data. The multi-source acquired data is then preprocessed by data cleaning (anomaly identification and elimination), standardization (unification of quantity units, currency units, weight and other indicators), time alignment (unification of data at different time resolutions) and missing fill (mean filling, median filling or nearest neighbor filling) to generate a multi-source preprocessed data set. The multi-source acquired data specifically includes: internal enterprise data (inventory records, purchase orders, sales history, ERP system data, etc.), sensor recording data (warehouse temperature and humidity, transportation vehicle location and status, production equipment operating parameters, etc.), external public data (weather information, traffic data, social media hot spot analysis, competitor prices, etc.) and user behavior data (social media comments, search popularity, click-through rate, user evaluation, etc.).

[0049] Specifically, Figure 7 FIG. 1 shows a structural block diagram of the multi-source acquisition preprocessing unit 101 in the system provided by an embodiment of the present invention.

[0050] In a preferred embodiment of the present invention, the multi-source acquisition preprocessing unit 101 specifically includes: The data source determination module 1011 is used to determine multiple data collection sources, including internal enterprise sources, sensor record sources, external public sources, and user behavior sources; A multi-source data collection module 1012 is used to collect multi-source data according to the plurality of data collection sources and obtain multi-source collected data; A data cleaning module 1013 is used to clean the multi-source collected data; A standardization module 1014 is used to standardize the multi-source collected data; A time alignment module 1015 is used to perform time alignment on the multi-source collected data; A gap filling module 1016 is used to fill gaps in the multi-source collected data; The data set generation module 1017 is used to generate a multi-source pre-processed data set.

[0051] Furthermore, the supply chain management system based on multi-source data also includes: The data fusion processing unit 102 is used to perform data fusion and feature extraction on multi-source pre-processed data sets to obtain fused feature data.

[0052] In an embodiment of the present invention, the data fusion processing unit 102 obtains multi-source fusion data by performing data fusion (feature-level fusion, decision-level fusion and / or embedding-level fusion may be used) on multi-source pre-processed data sets, and then performs feature selection and dimensionality reduction on the multi-source fusion data to obtain fused feature data.

[0053] The forecast inventory optimization unit 103 is used to perform demand forecasting and inventory optimization analysis based on the fused feature data, and calculate the optimal demand order quantity, safety stock quantity and total inventory quantity.

[0054] In an embodiment of the present invention, the forecast inventory optimization unit 103 extracts forecast correlation data and inventory correlation data from the fused feature data, performs demand forecast optimization analysis based on the forecast correlation data, calculates the optimal demand order quantity, and performs inventory optimization analysis based on the inventory correlation data to calculate the safety stock. Then, the total inventory is calculated based on the optimal demand order quantity and the safety stock. Specifically, the calculation formula for the optimal demand order quantity is: ; in, is the optimal order quantity, is the total annual demand, is the fixed cost of each order, is the annual inventory holding cost; The formula for calculating safety stock is: ; in, is the safety stock, is the preset service level factor, is the standard deviation of demand, The time from order to delivery; The formula for calculating total inventory is: ;

[0055] in, is the total inventory.

[0056] Specifically, Figure 8 It shows a structural block diagram of the forecast inventory optimization unit 103 in the system provided by an embodiment of the present invention.

[0057] In a preferred embodiment of the present invention, the forecast inventory optimization unit 103 specifically includes: A first correlation extraction module 1031 is configured to extract prediction correlation data and inventory correlation data from the fused feature data; The optimal demand order quantity calculation module 1032 is used to perform demand forecast optimization analysis according to the forecast correlation data and calculate the optimal demand order quantity; A safety stock calculation module 1033 is configured to perform inventory optimization analysis and calculate safety stock based on the inventory-related data; The total inventory calculation module 1034 is used to calculate the total inventory according to the optimal demand order quantity and the safety stock.

[0058] Furthermore, the supply chain management system based on multi-source data also includes: The transportation and distribution optimization unit 104 is used to perform network optimization analysis of transportation and distribution based on the fused feature data, and to build a transportation cost optimization model and a distribution path optimization model.

[0059] In an embodiment of the present invention, the transportation and distribution optimization unit 104 extracts transportation-related data and distribution-related data from the fused feature data, and then performs transportation optimization analysis based on the transportation-related data to determine the objective function and constraints for minimizing transportation costs, thereby constructing a transportation cost optimization model. Furthermore, based on the distribution-related data, it performs network optimization analysis on distribution and constructs a distribution path optimization model.

[0060] Specifically, Figure 9 It shows a structural block diagram of the transportation and delivery optimization unit 104 in the system provided by an embodiment of the present invention.

[0061] In the preferred embodiment of the present invention, the transportation and distribution optimization unit 104 specifically includes: A second correlation extraction module 1041 is used to extract transportation correlation data and delivery correlation data from the fused feature data; The transportation cost optimization model building module 1042 is used to perform transportation optimization analysis based on the transportation-related data, determine the objective function and constraints, and build a transportation cost optimization model; The delivery path optimization model building module 1043 is used to perform a delivery network optimization analysis based on the delivery related data and build a delivery path optimization model.

[0062] It should be understood that, although the various steps in the flow chart of each embodiment of the present invention are shown in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in order, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0063] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When executed, the program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0064] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0065] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0066] 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 and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A supply chain management method based on multi-source data, characterized by: The method specifically comprises the following steps: Determining multiple data collection sources, performing multi-source data collection, obtaining multi-source collected data, and preprocessing the multi-source collected data to obtain a multi-source preprocessed data set; Perform data fusion and feature extraction on multi-source preprocessed data sets to obtain fused feature data; Based on the fused feature data, perform demand forecasting and inventory optimization analysis to calculate the optimal demand order quantity, safety stock, and total inventory; Based on the fused feature data, network optimization analysis of transportation and distribution is performed, and a transportation cost optimization model and a distribution path optimization model are constructed.

2. The supply chain management method based on multi-source data according to claim 1, characterized in that: The steps of determining multiple data collection sources, performing multi-source data collection, obtaining multi-source collected data, and preprocessing the multi-source collected data to obtain a multi-source preprocessed data set specifically include the following steps: Identify multiple data collection sources, including internal enterprise sources, sensor records, external public sources, and user behavior sources; Perform multi-source data collection according to the plurality of data collection sources to obtain multi-source collected data; Performing data cleaning on the multi-source collected data; Standardizing the multi-source collected data; Performing time alignment on the multi-source collected data; Filling in gaps in the multi-source collected data; Generate multi-source preprocessed datasets.

3. The supply chain management method based on multi-source data according to claim 1, characterized in that: The data fusion and feature extraction of the multi-source pre-processed data sets to obtain fused feature data specifically includes the following steps: Performing data fusion on the multi-source pre-processed data sets to obtain multi-source fused data; Feature selection and dimension reduction are performed on the multi-source fusion data to obtain fusion feature data.

4. The supply chain management method based on multi-source data according to claim 1, characterized in that: The process of performing demand forecasting and inventory optimization analysis based on the fused feature data and calculating the optimal demand order quantity, safety stock, and total inventory specifically includes the following steps: Extracting prediction-related data and inventory-related data from the fused feature data; Perform demand forecast optimization analysis based on the forecast correlation data and calculate the optimal demand order quantity; Conduct inventory optimization analysis and calculate safety stock levels based on the inventory-related data; The total inventory quantity is calculated according to the optimal demand order quantity and the safety stock quantity.

5. The supply chain management method based on multi-source data according to claim 4, characterized in that: The calculation formula for the optimal demand order quantity is: ； in, is the optimal order quantity, is the total annual demand, is the fixed cost of each order, is the annual inventory holding cost; The calculation formula for the safety stock is: ； in, is the safety stock, is the preset service level factor, is the standard deviation of demand, The time from order to delivery; The calculation formula for the total inventory is: ； in, is the total inventory.

6. The supply chain management method based on multi-source data according to claim 1, characterized in that: The method of performing network optimization analysis for transportation and distribution based on the fused feature data and constructing a transportation cost optimization model and a distribution path optimization model specifically includes the following steps: Extracting transportation-related data and delivery-related data from the fused feature data; Conducting transportation optimization analysis based on the transportation-related data, determining the objective function and constraints, and building a transportation cost optimization model; Based on the distribution-related data, a distribution network optimization analysis is performed to build a distribution path optimization model.

7. Supply chain management system based on multi-source data, characterized by: The system specifically includes a multi-source acquisition pre-processing unit, a data fusion processing unit, a forecast inventory optimization unit, and a transportation and distribution optimization unit, wherein: A multi-source acquisition preprocessing unit is used to determine multiple data acquisition sources, perform multi-source data acquisition, obtain multi-source acquired data, and preprocess the multi-source acquired data to obtain a multi-source preprocessed data set; A data fusion processing unit is used to perform data fusion and feature extraction on multi-source pre-processed data sets to obtain fused feature data; A forecast inventory optimization unit, configured to perform demand forecasting and inventory optimization analysis based on the fused feature data, and calculate the optimal demand order quantity, safety stock, and total inventory; The transport and distribution optimization unit is used to perform network optimization analysis of transport and distribution based on the fused feature data, and to build a transport cost optimization model and a distribution path optimization model.

8. The supply chain management system based on multi-source data according to claim 7, characterized in that: The multi-source acquisition preprocessing unit specifically includes: The data source determination module is used to determine multiple data collection sources, including internal enterprise sources, sensor record sources, external public sources, and user behavior sources; A multi-source data acquisition module, configured to perform multi-source data acquisition according to a plurality of data acquisition sources and obtain multi-source acquired data; A data cleaning module, used for cleaning the multi-source collected data; A standardization module, used for standardizing the multi-source collected data; A time alignment module, configured to perform time alignment on the multi-source collected data; A missing filling module is used to fill in the missing data of the multi-source collection data; The dataset generation module is used to generate multi-source preprocessed datasets.

9. The supply chain management system based on multi-source data according to claim 7, characterized in that: The forecast inventory optimization unit specifically includes: A first correlation extraction module, configured to extract prediction correlation data and inventory correlation data from the fused feature data; An optimal demand order quantity calculation module is used to perform demand forecast optimization analysis and calculate the optimal demand order quantity according to the forecast correlation data; A safety stock calculation module is used to perform inventory optimization analysis and calculate the safety stock according to the inventory-related data; The total inventory calculation module is used to calculate the total inventory according to the optimal demand order quantity and the safety stock.

10. The supply chain management system based on multi-source data according to claim 7, characterized in that: The transportation and distribution optimization unit specifically includes: A second association extraction module is used to extract transportation-related data and delivery-related data from the fused feature data; A transportation cost optimization model building module is used to perform transportation optimization analysis based on the transportation-related data, determine the objective function and constraint conditions, and build a transportation cost optimization model; The distribution path optimization model building module is used to perform distribution network optimization analysis based on the distribution related data and build a distribution path optimization model.

Images