Enterprise purchase collaborative management method and system based on cloud platform

Abstract

The invention discloses an enterprise purchase collaborative management method and system based on a cloud platform, and relates to the technical field of cloud platform and supply chain management, and the method comprises the steps: collecting multi-factor demand prediction model data; predicting a purchase demand and performing optimization; and executing purchasing based on the demand prediction and optimization result. According to the enterprise purchase collaborative management method based on the cloud platform, purchase demand prediction is carried out through a multi-factor dynamic time sequence model, high precision and high adaptability of demand prediction are realized in combination with a dynamic weight adjustment mechanism and adaptive optimization of model parameters, a purchase demand trend chart and influence factor analysis can be provided, and the enterprise purchase collaborative management method based on the cloud platform can be applied to enterprise purchase collaborative management. According to the method and the system, the enterprise is helped to make a purchase plan in advance, the purchase cost, the inventory holding cost and the stockout risk are balanced by taking the minimization of the total purchase cost as the target through the demand-inventory joint optimization model, and the method and the system have better effects in the aspects of accuracy, controllability and stability of enterprise purchase.

Description

Technical Field

[0001] The present invention relates to the technical field of cloud platforms and supply chain management, and specifically provides an enterprise procurement collaborative management method and system based on a cloud platform. Background Art

[0002] With the rapid development of cloud computing, big data, and artificial intelligence technologies, enterprise supply chain management has gradually moved towards digitalization, intelligentization, and high efficiency. As an efficient tool for data storage, computing, and sharing, cloud platforms provide new technical support for enterprise procurement management. Traditional enterprise procurement management relies on single systems such as ERP (Enterprise Resource Planning), SCM (Supply Chain Management), and WMS (Warehouse Management System), and the data interaction and collaboration between these systems are relatively limited. With the increasing complexity of enterprise supply chains, procurement demand forecasting, inventory management, and supplier collaboration have become important guarantees for the efficient operation of enterprises. Therefore, constructing an enterprise procurement collaborative management method based on a cloud platform to break through multi-source data barriers and achieve cross-system collaboration has become an important research direction in current technology.

[0003] Existing enterprise procurement management technologies have many deficiencies in demand forecasting, inventory management, and supplier collaboration. First, in terms of procurement demand forecasting, traditional methods often rely on a single data source (such as historical procurement data), ignoring the impact of multi-dimensional data such as inventory levels, seasonal factors, market price fluctuations, and emergencies on demand forecasting, resulting in poor accuracy and timeliness of forecasting results. Second, in terms of inventory management, most systems cannot achieve adaptive adjustment of dynamic safety inventory thresholds and lack a real-time linkage mechanism between inventory levels and demand forecasting, which easily leads to overstocking or shortages. In addition, in terms of supplier collaboration, traditional supply chain management systems have significant limitations in supplier performance evaluation, supply chain visualization monitoring, and supplier intelligent recommendation, and cannot achieve efficient supplier matching and real-time tracking. Finally, in terms of procurement execution and risk response, traditional systems usually rely on manual intervention for order generation and approval, cannot quickly respond to emergencies, and there are significant potential supply chain risks. Therefore, existing technologies have significant deficiencies in multi-factor procurement demand forecasting, demand-inventory joint optimization, supplier intelligent recommendation, and dynamic emergency response, and it is difficult to meet the high-efficiency and intelligent requirements of enterprise procurement management in a complex supply chain environment. Summary of the Invention

[0004] In view of the above problems, the present invention is proposed.

[0005] Therefore, the technical problems solved by the present invention are: the existing enterprise procurement management methods have insufficient accuracy in demand forecasting, lack of dynamic linkage in inventory management, low degree of intelligentization in supplier matching, and problems in how to achieve efficient procurement execution and risk response.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: An enterprise procurement collaborative management method based on a cloud platform, including collecting multi-factor demand forecasting model data; forecasting procurement demands and optimizing them; and executing procurement based on the demand forecasting and optimization results.

[0007] As a preferred solution of the enterprise procurement collaborative management method based on a cloud platform according to the present invention, wherein: The collecting of multi-factor demand forecasting model data includes collecting historical procurement demand data, inventory level data, seasonal factor data, market price fluctuation data, and emergency event data;

[0008] For the historical procurement demand data, export the historical procurement data table from the ERP system, use the API interface to conduct data docking with the SCM system, and collect including historical procurement records, procurement cycles, material categories, procurement frequencies, and procurement sources;

[0009] For the inventory level data, obtain real-time inventory data through the WMS system interface, regularly conduct inventory checks, and collect including the current inventory quantity, safety inventory threshold, inventory turnover rate, inbound and outbound records, and material shelf life;

[0010] For the seasonal factor data, combine the historical procurement data, extract the seasonal demand pattern, and use data visualization tools to conduct seasonal demand characteristic analysis, and collect including time periods, high-demand seasons, seasonal indices, and holiday data;

[0011] For the market price fluctuation data, conduct API docking with the supplier system, obtain real-time quotation data, subscribe to a third-party market price monitoring service, and conduct monthly raw material price market research, and collect including raw material prices, price fluctuation trends, supplier quotations, and commodity price indices;

[0012] For the emergency event data, use data scraping tools to monitor emergency event information in real time, and collect including emergency event types, event impact ranges, event durations, and event impact intensities.

[0013] As a preferred solution of the enterprise procurement collaborative management method based on a cloud platform according to the present invention, wherein: The forecasting of procurement demands and optimizing them includes that the procurement demands are affected by historical procurement demands, inventory levels, seasonal changes, market price fluctuations, and emergency events. Use a multi-factor dynamic time series model to introduce different factors into the forecasting model through weight and dynamic adjustment mechanisms, expressed as:

[0014]

[0015] Wherein, Y t represents the forecast procurement demand quantity at time t, μ represents the model bias term, Ht-i The historical purchase data at time t-i, I t-j The inventory level data at time t-j, S t-k The seasonal factor data at time t-k, M t-l The market price data at time t-l, E t-h The impact data of unexpected events at time t-h, α i , β j , γ k , δ l , λ h , representing the dynamic weight coefficient, ∈ t Represents the prediction error term;

[0016] The weight dynamic adjustment mechanism is expressed as:

[0017]

[0018] Where, W h and W i Represent the weight adjustment parameters of the data source, and are dynamically optimized according to real-time data feedback;

[0019] Provide the predicted procurement demand data and demand trend charts for future time points through the prediction results, and conduct impact factor analysis.

[0020] As a preferred solution of the enterprise procurement collaborative management method based on the cloud platform described in the present invention, wherein: the predicting and optimizing the procurement demand includes, on the basis of demand prediction, combining with the inventory status for joint optimization, and the goal is to minimize the total procurement cost, including procurement cost, inventory holding cost, shortage cost and emergency response cost, and constructing a demand-inventory cost optimization model expressed as:

[0021]

[0022] Apply demand constraints, inventory constraints, safety inventory constraints, supplier supply constraints and non-negativity constraints:

[0023] Q t +I t-1 ≥D t -S t

[0024] I t =I t-1 +Q t -D t

[0025] I t ≥SS t

[0026] Q t ≤Qmax

[0027] Q t ,I t ,S t ,E t ≥0

[0028] Among them, Z represents the total procurement cost, C p represents the procurement cost per unit of material, C h represents the inventory holding cost per unit, C s represents the shortage cost per unit, C e represents the emergency procurement cost per unit, Q t represents the procurement quantity at time t, I t represents the inventory level at time t, D t represents the demand at time t, SS t represents the safety stock threshold at time t, Q max represents the maximum supply quantity of the supplier, (D t -Q t -I t ) + represents the shortage quantity of unmet demand;

[0029] Outputs a procurement plan, an inventory analysis report, and an exception warning based on the demand-inventory cost optimization model;

[0030] When the system detects that the inventory level is approaching the safety threshold, it automatically generates a replenishment plan and conducts supplier matching.

[0031] As a preferred solution of the enterprise procurement collaborative management method based on the cloud platform described in the present invention, wherein: the prediction of procurement demand and optimization includes combining seasonal demand patterns and market price fluctuations to establish a dynamic adjustment model to balance the procurement timing, procurement quantity, and cost, expressed as:

[0032]

[0033] Applying seasonal demand constraints, price fluctuation constraints, and risk tolerance constraints:

[0034] Q t ≥D t (1 + S index )

[0035] P t ≤P max

[0036] η ≤ R threshold

[0037] Among them, F t represents the seasonal demand influencing factor, P tDenote the influencing factors of market price fluctuations, R t Denote the influencing factors of emergency risks, α, β, γ denote weight parameters, η denotes the adjustment factor of the procurement quantity to inventory ratio, ξ denotes the shortage quantity risk coefficient, S index Denote the seasonal index, P max Denote the maximum threshold of market price, R threshold Denote the risk tolerance;

[0038] Based on the seasonal-price-risk dynamic adjustment model, output procurement timing suggestions, dynamic inventory strategies, and risk warning reports;

[0039] When the market price of the supplier drops, the system will prompt to conduct bulk procurement in advance to reduce the overall cost.

[0040] As a preferred solution of the enterprise procurement collaborative management method based on the cloud platform described in the present invention, wherein: the procurement executed based on the demand forecast and optimization results includes automatically generating a procurement order based on the demand forecast and optimization results, including automatically extracting the procurement requirements, quantity, and time nodes of materials, and automatically generating a procurement order, including the order number, material details, and delivery time;

[0041] Recommend based on supplier performance evaluation and historical cooperation data, use the cloud platform for process visualization and real-time tracking, and make adjustments for unforeseen supply chain risks.

[0042] As a preferred solution of the enterprise procurement collaborative management method based on the cloud platform described in the present invention, wherein: the procurement executed based on the demand forecast and optimization results includes evaluating procurement performance, feeding back the procurement execution results to the demand forecast model and optimization model for parameter adjustment, comparing the forecast data with the actual execution data, evaluating the forecast accuracy of the model, and adaptively optimizing the model parameters.

[0043] Another object of the present invention is to provide an enterprise procurement collaborative management system based on the cloud platform, which can solve the problem of insufficient demand forecast accuracy in the current enterprise procurement management method by predicting procurement demand and optimizing it.

[0044] As a preferred solution of the enterprise procurement collaborative management system based on the cloud platform described in the present invention, wherein: it includes an initialization module, a procurement demand forecast module, and a procurement execution module; the initialization module is used to collect multi-factor demand forecast model data; the procurement demand forecast module is used to construct a procurement demand forecast model for procurement forecasting; the procurement execution module is used to execute procurement and process coordination

[0045] A computer device includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of an enterprise procurement collaborative management method based on a cloud platform.

[0046] A computer-readable storage medium stores a computer program thereon. When the computer program is executed by a processor, it implements the steps of an enterprise procurement collaborative management method based on a cloud platform.

[0047] Advantages of the present invention: The enterprise procurement collaborative management method based on a cloud platform provided by the present invention collects data through a multi-factor demand forecasting model, comprehensively integrates multi-dimensional data such as historical procurement data, inventory levels, seasonal patterns, market price fluctuations, and emergencies, ensuring the comprehensiveness, timeliness, and accuracy of the data, and laying a foundation for subsequent forecasting and optimization. Secondly, through a multi-factor dynamic time series model for procurement demand forecasting, combined with a dynamic weight adjustment mechanism, the model parameters are adaptively optimized, achieving high-precision and high-adaptability in demand forecasting, and providing a procurement demand trend chart and analysis of influencing factors to help enterprises make procurement plans in advance. On this basis, through a demand-inventory joint optimization model, with the goal of minimizing the total procurement cost, balancing procurement costs, inventory holding costs, and shortage risks, dynamically adjusting the procurement batch and time point, ensuring the stability of the supply chain and controllability of costs. In addition, combined with seasonal demand patterns and market price fluctuations, a dynamic adjustment model is established to balance the procurement timing, procurement quantity, and cost, reducing the risks brought by market price fluctuations, and making advance reserves during peak demand periods to avoid material shortages. At the execution level, through automatically generating purchase orders, intelligent supplier recommendations, and real-time process monitoring, ensuring the efficiency and visualization of procurement execution, and quickly responding when supply chain risks occur to ensure the smooth progress of the procurement process. Finally, through a feedback mechanism, the procurement execution data is fed back to the model for adaptive optimization, forming a closed-loop optimization process to continuously improve the system performance. The present invention achieves better results in terms of the accuracy, controllability, and stability of enterprise procurement. Description of the Drawings

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for description in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0049] Figure 1 It is the overall flowchart of an enterprise procurement collaborative management method based on a cloud platform provided by the first embodiment of the present invention.

[0050] Figure 2Schematic diagram of an ERP system for an enterprise procurement collaborative management method provided in the second embodiment of the present invention.

[0051] Figure 3 Overall flowchart of an enterprise procurement collaborative management system based on a cloud platform provided in the third embodiment of the present invention. Detailed implementation manners

[0052] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will describe in detail the specific implementation manners of the present invention with reference to the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0053] Embodiment 1, referring to Figure 1 - Figure 2 , which is an embodiment of the present invention, provides an enterprise procurement collaborative management method based on a cloud platform, including:

[0054] S1: Collect multi-factor demand forecasting model data.

[0055] Furthermore, in practical applications, the accuracy of the multi-factor demand forecasting model depends on the comprehensiveness, accuracy, and timeliness of the data. The following will detail the data categories, sources, and collection methods required for this model to ensure that scientific and comprehensive data support can be provided for procurement demand forecasting.

[0056] The content of historical procurement demand data includes:

[0057] Historical procurement records: Procurement demand quantities in past time periods.

[0058] Procurement cycle: The time interval between each procurement.

[0059] Material category: The procurement quantity and category of each material.

[0060] Procurement frequency: The number of procurement times per month, per quarter, or per year.

[0061] Procurement source: Supplier information, procurement channels, etc.

[0062] Historical procurement demand data is collected through the enterprise ERP system (Enterprise Resource Planning system), SCM system (Supply Chain Management system), and historical procurement reports and record documents.

[0063] Export the historical procurement data table from the ERP system. Use the API interface to dock with the SCM system to obtain procurement historical data in real time. Manually check and verify the accuracy of the procurement reports regularly.

[0064] Table 1 Example Table of Historical Purchase Requirement Data

[0065]

[0066] The content of inventory level data includes:

[0067] Current inventory: The real-time inventory of each material.

[0068] Safety stock threshold: The minimum safety inventory level of each material.

[0069] Inventory turnover rate: The number of times inventory turns over within a period of time.

[0070] Inbound and outbound records: Inbound and outbound data on a daily, weekly, and monthly basis.

[0071] Shelf life of materials: Shelf life information of perishable materials.

[0072] Inventory level data is collected through the WMS system (Warehouse Management System), the ERP inventory management module, and material inventory monitoring sensors (IoT Internet of Things devices).

[0073] Obtain real-time inventory data through the WMS system interface. Regularly conduct physical inventory of inventory data to ensure the accuracy of system data. Use RFID (Radio Frequency Identification Technology) and barcode scanning to track the inbound and outbound status of materials in real time.

[0074] Table 2 Example Table of Inventory Level Data

[0075] Material Number Current Inventory Safety Stock Turnover Rate Receiving Date Shipping Date A001 500 200 3.5 2024 / 1 / 1 2024 / 2 / 1 B002 150 300 1.2 2024 / 1 / 15 2024 / 2 / 10

[0076] Seasonal factor data includes:

[0077] Time period: Monthly, quarterly, and annual time nodes.

[0078] High-demand season: Demand peak data for specific months or quarters.

[0079] Seasonal index: The demand weight for each time period.

[0080] Holiday data: Demand changes during special time periods such as the Spring Festival, Double Eleven, and Black Friday.

[0081] Seasonal factor data is collected through user and historical sales and purchase data analysis, business operation logs, and external market research reports (such as industry white papers).

[0082] Extract seasonal demand patterns by combining historical purchase data. Use data visualization tools for seasonal demand feature analysis. Collect the enterprise's annual activity plans (such as promotional activities, exhibitions, etc.).

[0083] Table 3 Example Table of Seasonal Factor Data

[0084] Month Seasonal Index Demand Peak Main Influencing Factor January 1.5 High Stock Preparation before Spring Festival June 0.8 Low Off-season November 2 High Double Eleven Big Promotion

[0085] Market price fluctuation data includes:

[0086] Raw material price: The market purchase price of the main materials.

[0087] Price fluctuation trend: The increase or decrease range of the recent price.

[0088] Supplier quotes: The price differences among different suppliers.

[0089] Commodity price index: Such as raw material indexes for copper, steel, rubber, etc.

[0090] Market price fluctuation data is collected through the enterprise's supplier management system (SRM), external price monitoring platforms (such as commodity market data interfaces), and data reports from third - party market research institutions.

[0091] Obtain real - time quote data by conducting API docking with the supplier system. Subscribe to third - party market price monitoring services. Conduct monthly market research on raw material prices.

[0092] Table 4 Example Table of Market Price Fluctuation Data

[0093] Material Number Current Unit Price Unit Price of Last Month Increase / Decrease Rate Supplier Remarks A001 50 45 11％ Supplier A Stable B002 40 42 -5％ Supplier B Downward Trend

[0094] Emergency event data includes:

[0095] Emergency event types: Natural disasters, epidemics, policy changes, transportation disruptions, etc.

[0096] Event impact scope: Local, regional, global.

[0097] Event duration: How long is it expected to last.

[0098] Event impact intensity: The degree of impact on procurement, production, and transportation.

[0099] Emergency event data is collected through government announcements and policy and regulation documents, early warning notices from industry associations, and external news data interfaces.

[0100] Subscribe to industry early warning and policy announcement platforms. Use data scraping tools to monitor relevant information in real - time. Conduct regular risk assessments and simulation drills.

[0101] Table 5 Example Table of Emergency Event Data

[0102] Event Type Occurrence Time Duration Influence Strength Influence Description Typhoon 2024 / 7 / 1 5 days High Port Transportation Disruption Raw Material Embargo 2024 / 8 / 15 30 days Medium Risk of Raw Material Shortage

[0103] S2: Predict procurement demand and optimize it.

[0104] Furthermore, procurement demand forecasting is a typical multi-factor time series problem. The demand is not only affected by historical procurement data, but also closely related to inventory levels, seasonal factors, market price fluctuations, and unexpected events. Therefore, this model constructs a dynamic and adaptable forecasting framework by introducing a multi-dimensional time series model and decomposing various influencing factors into quantifiable variables.

[0105] The multi-dimensional dynamic procurement demand forecasting model is expressed as:

[0106]

[0107] where Y t represents the predicted procurement demand at time t, μ represents the model bias term, H t-i represents the historical procurement data at time t - i, I t-j represents the inventory level data at time t - j, S t-k represents the seasonal factor data at time t - k, M t-l represents the market price data at time t - l, E t-h represents the unexpected event impact data at time t - h, α i , β j , γ k , δ l , λ h represent dynamic weight coefficients, ∈ t represents the prediction error term;

[0108] The weight dynamic adjustment mechanism is expressed as:

[0109]

[0110] where W h and W i represent the weight adjustment parameters of the data source, which are dynamically optimized according to real-time data feedback;

[0111] The weight coefficients are dynamically allocated through an adaptive adjustment algorithm, continuously optimized with the input of new data, and the accuracy and robustness of the prediction are improved.

[0112] Multi-dimensional data fusion realizes the global and multi-angle forecasting of procurement demand, avoiding the deviation caused by a single factor. Dynamic forecasting adaptively adjusts the weights according to real-time data to adapt to the procurement demand fluctuations in different scenarios. Early warning warns in advance of potential procurement demand peaks or shortages, reducing the risk of supply chain disruptions.

[0113] Provide the procurement demand forecast data at future time points through a multi-dimensional dynamic procurement demand forecast model. Visualize the change trend of the demand volume to facilitate managers to intuitively understand the demand fluctuations. Identify the core variables affecting the procurement demand and optimize the procurement strategy.

[0114] Before the peak season of seasonal demand, the system can predict the peak procurement demand according to the model and generate a procurement plan in advance to avoid the risk of shortage.

[0115] It should be noted that the procurement demand forecast results must be linked with inventory management to minimize the overall cost. This model incorporates procurement cost, inventory holding cost, shortage cost, and emergency response cost into the optimization objective and solves for the optimal procurement quantity and inventory level through linear programming methods.

[0116] The demand-inventory joint optimization model is expressed as:

[0117]

[0118] Apply demand constraints, inventory constraints, safety stock constraints, supplier supply constraints, and non-negativity constraints:

[0119] Q t +I t-1 ≥D t -S t

[0120] I t =I t-1 +Q t -D t

[0121] I t ≥SS t

[0122] Q t ≤Q max

[0123] Q t ,I t ,S t ,E t ≥0

[0124] Among them, Z represents the total procurement cost, C p represents the unit procurement cost of materials, C h represents the unit inventory holding cost, C s represents the unit shortage cost, C e represents the unit emergency procurement cost, Q t represents the procurement quantity at time t, I t represents the inventory level at time t, D t represents the demand volume at time t, SSt represents the safety stock threshold at time t, Q max represents the maximum supply quantity of the supplier, (D t -Q t -I t ) + represents the shortage quantity of unmet demand;

[0125] Achieve the balance of procurement cost, inventory cost and shortage cost through the demand-inventory joint optimization model. Reduce the risk of supply chain disruption through safety stock constraints. Ensure the optimal configuration of procurement batch and replenishment timing.

[0126] The demand-inventory joint optimization model outputs a procurement plan to provide accurate procurement batch and time nodes. Display key indicators such as inventory turnover rate and holding cost through the output inventory analysis report. Provide real-time warnings of insufficient inventory or abnormal costs through the output of abnormal warnings.

[0127] When the system detects that the inventory level is close to the safety threshold, it automatically generates a replenishment plan and conducts supplier matching to ensure the timely replenishment of materials.

[0128] Furthermore, on the basis of procurement demand forecasting and inventory optimization, consider the impact of seasonal demand peaks, market price fluctuations and emergencies on procurement. This model introduces a dynamic adjustment coefficient to optimize the procurement quantity and time nodes.

[0129] Construct a seasonal-price-risk dynamic adjustment model expressed as:

[0130]

[0131] Apply seasonal demand constraints, price fluctuation constraints and risk tolerance constraints:

[0132] Q t ≥D t (1 + S index )

[0133] P t ≤P max

[0134] η ≤ R threshold

[0135] where, F t represents the seasonal demand impact factor, P t represents the market price fluctuation impact factor, R t represents the emergency risk impact factor, α, β, γ represent weight parameters, η represents the procurement quantity to inventory ratio adjustment factor, ξ represents the shortage quantity risk coefficient, S index represents the seasonal index, P maxRepresents the maximum threshold of the market price, R threshold Represents the risk tolerance;

[0136] Flexibly respond to seasonal fluctuations by constructing a seasonal - price - risk dynamic adjustment model, and replenish inventory in advance during the peak demand period. Adjust price sensitivity, purchase in advance when the price is low to reduce the purchase cost. Respond to emergencies, provide emergency procurement strategies, and reduce the risk of supply chain disruption.

[0137] The seasonal - price - risk dynamic adjustment model provides the best procurement timing to adjust the inventory level according to seasonal and price changes. Perceive and warn of market risks in real - time.

[0138] When the market price of the supplier drops, the system will prompt to make bulk purchases in advance to reduce the overall cost.

[0139] S3: Execute procurement based on demand forecasting and optimization results.

[0140] Furthermore, procurement execution and process coordination is the process of transforming the results of demand forecasting and optimization models into actual operations. This step covers purchase order generation, supplier management, process approval, and real - time monitoring to ensure that procurement execution is efficient, compliant, and can respond quickly in case of emergencies.

[0141] Automatically generate and approve purchase orders. Based on demand forecasting and optimization results, automatically generate purchase orders.

[0142] Automatically extract material procurement requirements, quantity, and time nodes. Automatically generate purchase orders, including order numbers, material details, delivery times, etc. Support custom approval processes, and hierarchical approval to ensure compliance.

[0143] Intelligent recommendation based on supplier performance evaluation and historical cooperation data, including comprehensive evaluation of supplier performance (on - time delivery rate, quality stability, price competitiveness), intelligent matching of the best suppliers, dynamically adjusting the supplier portfolio strategy, providing alternative supplier solutions, and ensuring the stability and reliability of procurement.

[0144] Use the cloud platform for process visualization and real - time tracking, including visualizing the status of each stage of the purchase order on the cloud platform, providing real - time tracking and warning functions for the procurement process. In case of abnormal situations (such as delayed delivery, supply chain disruption), trigger the emergency response mechanism.

[0145] Rapid adjustment for unforeseen supply chain risks, including real - time monitoring of emergency information during the procurement process, automatically triggering the emergency procurement process, making dynamic adjustments, and quantitatively evaluating the impact of emergencies to ensure the stability of the supply chain.

[0146] When a certain supplier fails to deliver on time, the system automatically recommends alternative suppliers and generates supplementary orders to prevent production line stoppages.

[0147] It should be noted that the continuous optimization and intelligent learning of the procurement system are important means to achieve the self-evolution of the system. In this step, through data feedback, performance evaluation, and self-learning algorithms, the prediction model and optimization strategy are continuously adjusted to ensure the high efficiency and stability of the system during long-term operation.

[0148] Example 2, an embodiment of the present invention, provides an enterprise procurement collaborative management method based on a cloud platform. To verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0149] First, a manufacturing enterprise with an annual procurement amount of approximately 50 million yuan was selected for the experiment. The enterprise's procurement categories cover raw materials, components, and auxiliary production materials. The supply chain involves multiple suppliers and has information systems such as ERP, SCM, and WMS.

[0150] Before the experiment began, the following preparatory work was first completed:

[0151] Export the historical procurement data tables of the past 3 years from the enterprise's ERP system. Use the API interface to connect to the SCM supply chain management system to collect data such as procurement records, cycles, and frequencies. Collect data such as real-time inventory levels, safety inventory thresholds, inventory turnover rates, and shelf lives through the WMS interface. Combining historical procurement data, use data visualization tools to extract seasonal demand patterns and analyze factors such as time cycles, high-demand seasons, and holidays. Obtain raw material market prices, price fluctuation trends, and commodity price indices from the supplier system and third-party market monitoring platforms. Use data scraping tools to monitor supply chain emergencies in real time and collect data such as event types, impact ranges, and durations.

[0152] Import the collected multi-dimensional data into the cloud platform for preprocessing, cleaning, and standardization. Use a multi-factor dynamic time series model for demand forecasting training to generate demand trend charts and key influencing factor reports. Combining the demand forecasting results, construct a demand-inventory joint optimization model and set constraints for procurement costs, inventory costs, shortage costs, and emergency response costs. Introduce a seasonal-price-risk dynamic adjustment model to adjust the procurement quantity and procurement timing according to seasonal demand, market prices, and the impact of emergencies.

[0153] Based on the results of the optimization model, automatically generate procurement orders, specifying the procurement quantity, time nodes, and suppliers. Use the cloud platform for visual tracking of the procurement process and real-time monitoring of order status. When the inventory approaches the safety threshold, automatically trigger the replenishment process and match supplier resources.

[0154] Export historical procurement data (procurement records, material categories, procurement frequencies, etc.) from ERP and SCM systems. Obtain real-time inventory data (current inventory levels, safety stock thresholds, etc.) through the WMS system. Conduct visual analysis on seasonal factors and market price fluctuation data to extract key patterns. Use data scraping tools to monitor emergencies and collect relevant data.

[0155] Use a multi-factor dynamic time series model for demand forecasting and generate a procurement demand trend chart. Based on the forecasting results, identify high-demand periods and low-demand periods at different time nodes and determine procurement priorities. Combine the demand forecasting data with inventory data and use a demand-inventory joint optimization model for global optimization. Determine the optimal procurement batch and replenishment time to reduce inventory holding costs and stockout risks.

[0156] In the peak demand season, make material reserves in advance. When the market price drops, purchase in batches in a timely manner to reduce costs. When an emergency occurs, quickly adjust the procurement plan to ensure the stability of the supply chain.

[0157] Automatically generate procurement orders and submit them to suppliers for delivery. Track the procurement process in real time to ensure that orders are delivered on time. Feed the procurement execution data back into the model for parameter optimization to improve forecasting accuracy.

[0158] Table 6 Experimental data table

[0159]

[0160] It can be seen from the above test data that remarkable results have been achieved in aspects such as procurement demand forecasting, inventory management, and procurement execution.

[0161] The deviation between the procurement forecast data and the actual procurement volume is small (the error rate is controlled within ±5%). In peak demand months (such as May and June), the system made demand forecasts and material reserves in advance, avoiding the risk of inventory shortages. The safety stock threshold is dynamically adjusted according to demand forecasts, and the inventory level is maintained within a reasonable range. The inventory holding cost has been significantly reduced, reducing the occupation of funds. When the market price drops, the system automatically conducts batch procurement, effectively reducing the procurement cost. The total procurement cost is reduced by about 12% compared with the traditional procurement model. The system can monitor emergencies in real time and automatically trigger the emergency procurement process to ensure the stability of the supply chain.

[0162] In terms of demand forecasting, the limitations of a single data source have been broken through, achieving multi-factor comprehensive forecasting. In terms of inventory management, the system has realized the dynamic adjustment of the safety stock threshold, avoiding overstocking or shortages. In terms of procurement execution, process automation and visual management have significantly improved procurement efficiency and risk response capabilities.

[0163] In summary, the invention demonstrates strong innovation and practicality in procurement forecasting, inventory management, cost control, and risk response, providing a scientific and efficient solution for enterprise supply chain management.

[0164] Example 3. Refer to Figure 3 , which is an embodiment of the present invention, provides an enterprise procurement collaborative management system based on a cloud platform, including an initialization module, a procurement demand forecasting module, and a procurement execution module.

[0165] Among them, the initialization module is used to collect multi-factor demand forecasting model data, the procurement demand forecasting module is used to construct a procurement demand forecasting model for procurement forecasting, and the procurement execution module is used to execute procurement and process collaboration.

[0166] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, etc., which can store program codes.

[0167] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0168] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable media can even be paper or other suitable media on which a program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then stored in a computer memory.

[0169] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well-known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc. It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

[0170] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A cloud platform-based enterprise procurement collaborative management method, characterized in that: include: Collect data for multi-factor demand forecasting models; Forecast and optimize purchasing needs; Execute procurement based on demand forecast and optimization results.

2. The enterprise procurement collaborative management method based on a cloud platform as claimed in claim 1, characterized in that: The collecting of multi-factor demand forecasting model data includes collecting historical purchase demand data, inventory level data, seasonal factor data, market price fluctuation data and emergency event data; For historical procurement demand data, export the historical procurement data table from the ERP system, use the API interface to connect with the SCM system for data collection, including historical procurement records, procurement cycle, material category, procurement frequency and procurement source; For inventory level data, obtain real-time inventory data through the WMS system interface, and regularly count inventory data, including current inventory, safety stock threshold, inventory turnover rate, inbound and outbound records, and material shelf life; Based on seasonal factor data, combined with historical procurement data, seasonal demand patterns are extracted, and seasonal demand characteristics are analyzed using data visualization tools, including time periods, high-demand seasons, seasonal indexes, and holiday data; In view of market price fluctuation data, we connect with the supplier system through API to obtain real-time quotation data, subscribe to third-party market price monitoring services, conduct monthly market research on raw material prices, and collect information including raw material prices, price fluctuation trends, supplier quotations, and commodity price indices; For emergency event data, use data capture tools to monitor emergency event information in real time, including the type of emergency event, scope of event impact, event duration, and event impact intensity.

3. The enterprise procurement collaborative management method based on a cloud platform as claimed in claim 2, characterized in that: The procurement demand forecasting and optimization includes that the procurement demand is affected by historical procurement demand, inventory level, seasonal changes, market price fluctuations and emergencies, and a multi-factor dynamic time series model is used to introduce different factors into the forecasting model through weights and dynamic adjustment mechanisms, which is expressed as: Among them, Y t represents the predicted purchase demand at time t, μ represents the model bias term, and H t-i represents the historical purchase data at time ti, I t-j represents the inventory level data at time tj, S t-k represents the seasonal factor data at time tk, M t-l represents the market price data at time tl, E t-h represents the impact data of the sudden event at time th, α i , β j , γ k , δ l ,λ h represents the dynamic weight coefficient, ∈ t represents the prediction error term; The dynamic weight adjustment mechanism is expressed as: Among them, W h and W i The weight adjustment parameters representing the data source are dynamically optimized based on real-time data feedback; The forecast results provide procurement demand forecast data and demand trend charts at various time points in the future, and analyze influencing factors.

4. The enterprise procurement collaborative management method based on a cloud platform as claimed in claim 3, characterized in that: The prediction and optimization of procurement demand includes joint optimization based on demand forecast and inventory status, with the goal of minimizing total procurement costs, including procurement costs, inventory holding costs, out-of-stock costs, and emergency response costs. The demand-inventory cost optimization model is constructed as follows: Imposing demand constraints, inventory constraints, safety stock constraints, supplier availability constraints, and non-negativity constraints: Q t +I t-1 ≥D t -S t I t =I t-1 +Q t -D t I t ≥SS t Q t ≤Q max Q t ,I t ,S t ,E t ≥0 Among them, Z represents the total purchase cost, C p Represents the unit material procurement cost, C h represents the unit inventory holding cost, C s represents the unit shortage cost, C e represents the unit emergency purchase cost, Q t represents the purchase quantity at time t, I t represents the inventory at time t, D t represents the demand at time t, SS t represents the safety stock threshold at time t, Q max represents the maximum supply quantity of the supplier, (D t -Q t -I t ) + Out-of-stock quantities representing unmet demand; Output procurement plans, inventory analysis reports and abnormal warnings based on the demand-inventory cost optimization model; When the system detects that the inventory level is close to the safety threshold, it automatically generates a replenishment plan and performs supplier matching.

5. The enterprise procurement collaborative management method based on a cloud platform as claimed in claim 4, characterized in that: The prediction and optimization of procurement demand includes combining seasonal demand rules with market price fluctuations, establishing a dynamic adjustment model, and balancing procurement timing, procurement volume and cost, which can be expressed as: Imposing seasonal demand constraints, price volatility constraints, and risk tolerance constraints: Q t ≥D t (1+S index ) P t ≤P max η≤R threshold Among them, F t represents the seasonal demand influencing factor, P t Indicates the factors affecting market price fluctuations, R t represents the risk influencing factor of the emergency event, α, β, γ represent the weight parameters, η represents the adjustment factor of the purchase volume and inventory ratio, ξ represents the out-of-stock risk coefficient, S index represents the seasonal index, P max Represents the maximum market price threshold, R threshold Indicates risk tolerance; Output purchase timing suggestions, dynamic inventory strategies and risk warning reports based on the seasonality-price-risk dynamic adjustment model; When the supplier's market price drops, the system will prompt you to make bulk purchases in advance to reduce overall costs.

6. The enterprise procurement collaborative management method based on a cloud platform as claimed in claim 5, characterized in that: The executing procurement based on demand forecasting and optimization results includes automatically generating a purchase order based on demand forecasting and optimization results, including automatically extracting material procurement requirements, batches, and time nodes, and automatically generating a purchase order including an order number, material details, and delivery time; Recommendations are made based on supplier performance evaluation and historical cooperation data, and cloud platforms are used for process visualization and real-time tracking to adjust for unforeseen supply chain risks.

7. The enterprise procurement collaborative management method based on a cloud platform according to claim 6, characterized in that: The procurement execution based on demand forecasting and optimization results includes evaluating procurement performance, feeding back procurement execution results to the demand forecasting model and the optimization model, adjusting parameters, comparing forecast data with actual execution data, evaluating model prediction accuracy, and adaptively optimizing model parameters.

8. A system using the cloud platform-based enterprise procurement collaborative management method according to any one of claims 1 to 7, characterized in that: Including initialization module, procurement demand forecasting module, procurement execution module; The initialization module is used to collect multi-factor demand forecasting model data; The purchase demand forecasting module is used to construct a purchase demand forecasting model to perform purchase forecasting; The procurement execution module is used to execute procurement and process collaboration.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the cloud platform-based enterprise procurement collaborative management method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the cloud platform-based enterprise procurement collaborative management method described in any one of claims 1 to 7 are implemented.

Images