An internet-based supply chain digital construction system

Abstract

This invention relates to the field of supply chain management technology and discloses an internet-based digital supply chain construction system, comprising: a market demand assessment module, which outputs a demand heat coefficient based on social media popularity and the number of times items are added to cart or favorites on e-commerce platforms; a supply risk early warning module, which outputs a supply risk coefficient based on the factory quality inspection pass rate and the supplier's financial health; a resilience assessment module, which outputs a resilience coefficient based on the availability of substitutes and the response time of substitute warehouses; a two-way matching assessment module, which outputs a warehousing-product matching coefficient based on the supply risk coefficient, resilience coefficient, warehousing cost volatility, and product depreciation rate; and a dynamic inventory decision module, which outputs the optimal safety stock level based on the demand heat coefficient and the warehousing-product matching coefficient through an inventory decision model. Through multi-source data fusion and dynamic modeling, precise and intelligent management of supply chain inventory is achieved, improving the accuracy of inventory decisions and the supply chain's resilience.

Description

Technical Field

[0001] This invention belongs to the field of supply chain management technology, and in particular relates to an Internet-based digital supply chain construction system. Background Technology

[0002] Supply chain management is a core aspect of business operations, and one of its key challenges lies in scientifically setting safety stock levels to balance service levels and inventory costs. Traditional safety stock decision-making methods primarily rely on historical sales data within the company, employing statistical models based on averages and standard deviations for calculation. While these methods are effective in relatively stable market environments, their limitations have become increasingly apparent with the rapid development of the internet economy. For example, traditional methods suffer from market perception lag, failing to effectively integrate real-time internet data such as social media trends and e-commerce platform user behavior. They are slow to respond to sudden changes in market demand, making it difficult to predict "hot-selling" demand or demand decline triggered by online trends, leading to a disconnect between inventory strategies and actual market conditions.

[0003] Therefore, how to provide a dynamic collaborative decision-making scheme that can integrate multi-source data to improve system response speed is the technical problem that the present invention aims to solve. Summary of the Invention

[0004] The purpose of this invention is to provide an Internet-based digital supply chain construction system to solve the above-mentioned problems.

[0005] The present invention provides an Internet-based digital supply chain construction system, the system comprising: The market demand assessment module, based on social media popularity and the number of times items are added to cart or favorites on e-commerce platforms, outputs a demand popularity coefficient through a market demand model. The supply risk early warning module outputs a supply risk coefficient based on the supplier's factory quality inspection pass rate and the supplier's financial health through a supply risk model. The resilience assessment module outputs resilience coefficients based on the availability of alternatives and the response time of alternative warehouses through a supply chain resilience model. The two-way matching assessment module, under the current supply risk coefficient and elasticity coefficient, outputs the warehousing-product matching coefficient through the matching model based on the volatility of warehousing costs and the product depreciation rate. The dynamic inventory decision module outputs the optimal safety stock level based on the demand heat coefficient and the warehouse-product matching coefficient through the inventory decision model.

[0006] Furthermore, the market demand assessment module's functions include: The social media popularity index is obtained by comparing the difference between the current social media popularity and the historical minimum social media popularity with the difference between the historical maximum social media popularity and the historical minimum social media popularity. The difference between the current number of times a user adds items to their favorites and shopping cart on the e-commerce platform and the minimum number of times they add items to their favorites and shopping cart in history is compared with the difference between the maximum number of times they add items to their favorites and shopping cart in history and the minimum number of times they add items to their favorites and shopping cart in history to obtain the e-commerce platform's number of times it adds items to its favorites and shopping cart. Import social media popularity index and e-commerce platform favorites and add-to-cart frequency index into the formula Obtain the demand popularity coefficient Demand heat coefficient The larger the value, the higher the optimal safety stock level; the range of values ​​is... ,in, As a social media popularity index, The index of the number of times items are added to favorites and shopping carts on e-commerce platforms. This is the social media popularity weighting coefficient. Weighting coefficients for adding items to favorites and shopping carts on e-commerce platforms.

[0007] Furthermore, the operation of the supply risk early warning module includes: The supplier financial health index is obtained by comparing the difference between the current supplier financial health score and the lowest financial health score with the difference between the maximum financial health score and the lowest financial health score. Import supplier financial health and factory quality inspection pass rate into the formula. Obtain the supply risk coefficient value range ,in, The factory quality inspection pass rate, As a supplier's financial health index, This is the pass rate weighting coefficient.

[0008] Furthermore, the method for obtaining the supplier's financial health is as follows: The debt-to-asset ratio index is obtained by comparing the difference between the current debt-to-asset ratio and the minimum debt-to-asset ratio threshold with the difference between the maximum debt-to-asset ratio threshold and the minimum debt-to-asset ratio threshold. The current ratio index is obtained by comparing the difference between the current ratio and the minimum current ratio threshold with the ratio between the maximum current ratio threshold and the minimum current ratio threshold. The net profit margin index is obtained by comparing the difference between the net profit margin and the minimum threshold with the maximum threshold and the minimum threshold. Import the debt-to-equity ratio index, current ratio index, and net profit margin index into the formula. To obtain the supplier's financial health, the value range is... ,in, This is the debt-to-equity ratio index. The current ratio index, This refers to the net profit margin index. , and All are weighting coefficients.

[0009] Furthermore, the work of the resilience assessment module includes: The ratio of the difference between the current alternative warehouse response time and the optimal response time to the difference between the longest acceptable response time and the optimal response time is used to obtain the alternative warehouse response time index. Import the availability of alternatives and the response time index of alternative warehouses into the formula. To obtain the elastic coefficient elastic modulus The larger the value, the smaller the optimal safety stock level; the range of values ​​is... ,in, For the availability of alternatives, To replace the warehouse response time index, This is the response time weighting coefficient.

[0010] Furthermore, the work of the bidirectional matching evaluation module includes: The storage cost volatility index is obtained by comparing the difference between the current storage cost volatility and the minimum historical storage cost volatility with the difference between the maximum historical storage cost volatility and the minimum historical storage cost volatility. Importing warehousing cost volatility and product depreciation rate into the formula Obtain the warehouse-product matching coefficient value range ,in, For supply risk factor, The elastic coefficient, This is a warehousing cost volatility index. For product depreciation rate, For risk factor weighting coefficients, This represents the weighting coefficient for cost factors.

[0011] Furthermore, the inventory decision model in the dynamic inventory decision module is as follows: ,in, The optimal safety stock level has a range of values. , This is the demand heat coefficient. This is the warehouse-product matching coefficient. This is the weighting coefficient for demand popularity. These are the matching coefficients and weighting coefficients.

[0012] Furthermore, the dynamic inventory decision-making module also includes the following functions: Convert the optimal safety stock level into the actual safety stock quantity. ,in, The maximum safety stock calculated based on service level objectives. The minimum safety stock calculated based on economic order volume. This represents the optimal safety stock level.

[0013] Compared with the prior art, the beneficial effects of the present invention are: This invention achieves effective integration of multi-source data from the Internet. Through collaborative analysis of social media popularity and e-commerce behavior data, it can capture market demand trends in advance, solving the problem of lagging market perception in traditional methods and making inventory decision-making results more accurate. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention.

[0015] Figure 1 This invention provides a schematic diagram of the structure of an Internet-based digital supply chain construction system. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0017] In existing technologies, one of the core objectives of supply chain management is to optimize inventory costs while meeting customer demand. Traditional safety stock decision-making methods rely on historical order and sales data within the enterprise, using statistical methods to predict future demand and set fixed inventory levels. These methods have significant drawbacks in dynamic business environments: they cannot capture social media trends and e-commerce user behavior data in real time, leading to delayed market perception; supplier evaluation is limited to post-delivery performance, lacking real-time monitoring of quality risks and financial health; and inventory decisions, supply risk assessments, and warehousing cost management are isolated processes, unable to dynamically correlate and analyze multi-dimensional factors. An electronics manufacturer once failed to promptly detect trending products on social media platforms, resulting in insufficient inventory of popular models. Simultaneously, a supplier's sudden financial crisis caused supply disruptions, resulting in double losses. This reflects the shortcomings of traditional systems in terms of real-time performance, comprehensiveness, and coordination.

[0018] To address these issues, the inventors first observed that market demand signals have shifted from traditional sales data to public internet data, realizing that integrating social media trends and e-commerce add-to-cart behavior can help capture consumer trends in advance. They then discovered that supplier risks exist not only in the delivery phase but also require upfront assessment of quality pass rates and financial health to prevent disruptions. Furthermore, they recognized that inventory decisions must comprehensively consider supply chain resilience and dynamic changes in warehousing costs; for example, the response speed of alternative warehouses affects safety stock redundancy, and product depreciation rates determine the rationality of warehousing holding costs. By establishing a multi-dimensional data fusion model and a dynamic weight allocation mechanism, a collaborative evaluation framework was gradually formed, transforming fragmented decision-making factors into quantifiable, correlated parameters.

[0019] The specific implementation of the present invention will be described in detail below with reference to specific embodiments.

[0020] Figure 1 This invention provides a schematic diagram of the structure of an internet-based digital supply chain construction system. In one embodiment of the technical solution of this invention, an internet-based digital supply chain construction system 10 is provided, which includes: Market demand assessment module 11, based on social media popularity and the number of times items are added to cart and favorited on e-commerce platforms, outputs a demand popularity coefficient through a market demand model; The supply risk early warning module 12 outputs a supply risk coefficient based on the supplier's factory quality inspection pass rate and the supplier's financial health through a supply risk model. Resilience assessment module 13 outputs resilience coefficients based on the availability of alternatives and the response time of alternative warehouses through the supply chain resilience model; The two-way matching evaluation module 14, under the current supply risk coefficient and elasticity coefficient, outputs the warehousing-product matching coefficient through the matching model based on the volatility of warehousing costs and the product depreciation rate. The dynamic inventory decision module 15 outputs the optimal safety stock level based on the demand heat coefficient and the warehouse-product matching coefficient through the inventory decision model.

[0021] Among these, social media popularity refers to trend indicators formed by capturing data such as the volume of topic discussions and the frequency of keyword occurrences on social media platforms using natural language processing technology. Specifically, it can be implemented using sentiment analysis algorithms and popularity index calculation models to reflect fluctuations in potential market demand. E-commerce platform favorites and add-to-cart frequency refers to the frequency statistics of users adding items to their favorites or shopping carts on product detail pages. This can be obtained in real-time through e-commerce platform API interfaces to capture changing trends in consumer behavior. Factory quality inspection pass rate refers to the proportion of products in a supplier's production batch that pass quality inspection. This can be achieved by collecting production line inspection data using IoT devices to assess supplier quality risk. Supplier financial health is a quantitative score constructed based on indicators such as debt-to-equity ratio, current ratio, and net profit margin. This can be achieved through normalized processing and weighted calculation of financial statement data to provide early warning of supplier operational risks. Alternative availability refers to the proportion of production capacity that backup suppliers can provide for similar products when the primary supplier is unavailable. This can be achieved through supplier database retrieval and capacity assessment algorithms to measure supply chain substitution capabilities. Alternative warehouse response time refers to the time period from order placement to the completion of goods dispatch from the alternative warehouse. This can be achieved by obtaining historical fulfillment data from the logistics information system to assess the efficiency of supply chain emergency response. Warehousing cost volatility refers to the rate of change in warehousing rental and management costs per unit of time. It can be calculated using time series analysis to determine the standard deviation coefficient, reflecting the risk of warehousing cost fluctuations. Product depreciation rate refers to the rate at which the value of goods diminishes due to factors such as seasonality and technological iteration. It can be calculated using historical sales price curve fitting and residual value prediction models, used to assess inventory holding costs.

[0022] Specifically, the market demand assessment module 11 collects real-time social media topic data and e-commerce user behavior data. After normalization to eliminate dimensional differences, it uses weighted calculation to generate a demand heat coefficient, transforming public internet data into quantifiable market demand signals. The supply risk early warning module 12 simultaneously acquires supplier production line quality inspection data and financial statement data. It calculates the supply risk coefficient inversely using quality pass rate and financial health score, achieving a fusion assessment of quality risk and financial risk. The resilience assessment module 13, based on the supplier database and logistics information system, calculates the supply capacity of substitutes and the response efficiency of emergency warehouses, generating a resilience coefficient reflecting the supply chain's resilience. The two-way matching assessment module 14 receives real-time supply risk coefficients and resilience coefficients, combines warehousing cost fluctuation data and product residual value prediction results, and calculates the degree of fit between warehousing costs and product value through a multi-dimensional correlation model. The dynamic inventory decision module 15 inputs the demand heat coefficient and the warehousing-product matching coefficient into the inventory decision model, dynamically adjusts the contribution of parameters according to preset weights, and outputs the optimal safety stock level that changes in real time with market environment, supply status, and cost factors. In practical applications, it transforms social media interaction and e-commerce behavior data into quantifiable demand forecasting parameters, which can solve the problem of market perception lag. It establishes a dual assessment model covering quality risk and financial risk, improving the accuracy and timeliness of supply disruption early warning. It also constructs a dynamic matching mechanism between supply elasticity and warehousing costs, avoiding inventory redundancy or insufficient emergency reserves caused by isolated decisions. This enables enterprises to respond quickly to demand changes in complex market environments, accurately identify weak links in the supply chain, and optimize the efficiency of inventory resource allocation.

[0023] As a preferred embodiment of the technical solution of the present invention, the inventory decision model is as follows: in, The optimal safety stock level refers to the inventory decision result after normalization. Specifically, it can be achieved by dynamically combining the demand heat coefficient and the warehouse-product matching coefficient using a linear weighted model. This is used to solve the problem that traditional inventory decision-making cannot quantify the synergistic relationship between market demand and warehouse suitability. This is the demand heat coefficient. This is the warehouse-product matching coefficient. The demand heat weighting coefficient is a parameter that reflects the degree to which market demand affects inventory decisions. It can be dynamically adjusted using historical operating data of the enterprise or external market environment parameters to flexibly adjust the priority of demand factors according to market fluctuations. The matching coefficient and weighting coefficient are parameters that reflect the degree to which warehousing suitability affects inventory decisions. Specifically, they can be dynamically adjusted using supply chain cost constraints or warehousing resource availability parameters to optimize inventory allocation in response to changes in supply risk or warehousing costs. ,and and All are greater than or equal to 0 and less than or equal to 1.

[0024] Specifically, the inventory decision-making model integrates the demand heat coefficient and the warehousing-product matching coefficient using a linear weighting method to generate a normalized optimal safety stock level. The demand heat coefficient is derived from real-time data on social media popularity and e-commerce platform user behavior, while the warehousing-product matching coefficient integrates supply risk, supply chain resilience, and warehousing cost factors. By setting a constraint that the sum of the demand heat weight coefficient and the matching coefficient weight coefficient is 1, the decision weights for market demand and warehousing suitability are always balanced. For example, when market demand fluctuates drastically, the demand heat weight coefficient can be increased to 0.7 while the matching coefficient weight coefficient is decreased to 0.3, making inventory decisions more responsive to market changes; when warehousing cost pressures increase, the weight coefficients can be adjusted in the opposite direction to prioritize controlling inventory holding costs. The normalized range of the optimal safety stock level is [range to be filled in]. This facilitates the subsequent conversion into actual inventory levels through linear mapping.

[0025] The above solution addresses the disconnect between market demand and warehousing suitability. Based on real-time data-driven demand heat coefficients and multi-dimensional assessments of warehousing-product matching coefficients, it accurately quantifies the impact of market changes on inventory. Combined with warehousing costs and risk factors, it generates an optimal solution to balance supply and demand. For example, during e-commerce promotions, the system can quickly increase inventory to cope with surges in sales by increasing the demand heat weight coefficient; when suppliers face increased financial risks, it can reduce inventory dependence by adjusting the matching coefficient weight coefficient to avoid stockout losses due to supply disruptions.

[0026] In a preferred embodiment of the technical solution of the present invention, the optimal safety stock level is converted into the actual safety stock quantity. in, The maximum safety stock, calculated based on service level objectives, refers to the upper limit of inventory required to achieve a preset customer order fulfillment rate. Specifically, it can be calculated by analyzing historical order fluctuations using statistical methods or machine learning models and combining them with service level objectives. Its purpose is to ensure that the supply chain can still meet service commitments when supply fluctuates. The minimum safety stock calculated based on economic order quantity refers to the economically optimal inventory level that comprehensively considers procurement costs, warehousing costs, and capital occupation. Specifically, it can be calculated using the economic order quantity formula combined with the inventory holding cost model. Its purpose is to avoid the waste of funds caused by excessive inventory. The optimal safety stock level refers to the adjustment coefficient dynamically calculated from the demand heat coefficient and the warehouse-product matching coefficient. Specifically, it can be generated by integrating and analyzing real-time data through the inventory decision model. Its function is to dynamically adjust the inventory level between the maximum and minimum thresholds according to market changes.

[0027] Specifically, this method transforms the theoretically optimal safety stock level into an operational inventory level by constructing a dynamic mapping relationship. First, it calculates the maximum safety stock based on service level objectives, for example, by analyzing historical order data distribution to determine the upper limit of inventory to cover demand fluctuations, ensuring that preset customer satisfaction can be maintained even during supply disruptions. Second, it calculates the minimum safety stock based on economic order volume, for example, by balancing procurement and warehousing costs to determine the minimum inventory holding level. Finally, it uses the optimal safety stock level as a linear interpolation coefficient to dynamically determine the actual inventory level within the range defined by the maximum and minimum inventory levels. When market demand increases, the adjustment coefficient pushes the actual inventory level closer to the upper limit to cope with the surge in demand; when the warehousing matching coefficient decreases, the adjustment coefficient pulls the actual inventory level closer to the lower limit to control cost risks.

[0028] It is worth mentioning that after applying the above solution, when a surge in the number of times a product is added to favorites and shopping carts on an e-commerce platform is detected, the system automatically increases the actual inventory to near the maximum safety stock to avoid missing sales opportunities. When the volatility of warehousing costs exceeds the threshold, the system dynamically reduces the actual inventory to near the economic order quantity, effectively reducing inventory holding costs. On the one hand, this overcomes the defect of inventory adjustment lagging behind market changes in the traditional model, and on the other hand, it prevents the risk of excessive backlog or unexpected stockouts caused by single-dimensional decision-making.

[0029] As a preferred embodiment of the technical solution of the present invention, the step of outputting the demand popularity coefficient based on social media popularity and the number of times items are added to cart and favorited on e-commerce platforms through a market demand model is as follows: The social media popularity index is obtained by comparing the difference between the current social media popularity and the historical minimum social media popularity with the difference between the historical maximum social media popularity and the historical minimum social media popularity. The difference between the current number of times a user adds items to their favorites and shopping cart on the e-commerce platform and the minimum number of times they add items to their favorites and shopping cart in history is compared with the difference between the maximum number of times they add items to their favorites and shopping cart in history and the minimum number of times they add items to their favorites and shopping cart in history to obtain the e-commerce platform's number of times it adds items to its favorites and shopping cart. Import social media popularity index and e-commerce platform favorites and add-to-cart frequency index into the formula Obtain the demand popularity coefficient This refers to a comprehensive indicator that integrates the dissemination effects of social media and e-commerce user behavior data. Specifically, it can be calculated by using a weighted summation model to superimpose the two types of indices according to a preset ratio. The weighting coefficients can be dynamically adjusted based on product type or market stage to balance the impact of different data sources on demand forecasting. (Demand popularity coefficient) The larger the value, the higher the optimal safety stock level; the range of values ​​is... .

[0030] in, The social media popularity index refers to the transformation of real-time social media interaction data into a standardized indicator through the range normalization method. Specifically, it can be achieved by using the ratio of the total number of likes, reposts, and comments on social media platforms in the current period to the extreme values ​​of historical data. This is used to eliminate the differences in data dimensions between different periods and reflect the real-time trend of market attention. The e-commerce platform's collection and add-to-cart frequency index refers to mapping user behavior data to a unified dimension through linear transformation. Specifically, it can be achieved by processing the ratio of the sum of the number of collections and add-to-cart entries on the product details page within the current period to the extreme values ​​of historical data, which is used to quantify consumers' immediate purchase intentions. This is the social media popularity weighting coefficient. The weighting factor for adding items to favorites and shopping carts in e-commerce platforms can be automatically learned by combining historical data or optimization algorithms (such as gradient descent). ,and and All are greater than or equal to 0 and less than or equal to 1.

[0031] Specifically, the social media popularity index is calculated by comparing current data with historical extremes, effectively capturing data fluctuations caused by sudden trending events. For example, if a product's daily interaction volume surges to twice its historical peak due to influencer recommendations, the index will rise significantly. The e-commerce platform favorites and add-to-cart frequency index processes user behavior data using the same method. For instance, if a product's favorites volume reaches 80% of its historical peak during the pre-sale period, this index will objectively reflect the potential purchase conversion rate. After inputting the two indices into a weighted model, when the social media popularity weight coefficient is set to 0.6 and the e-commerce weight coefficient is 0.4, the system will pay more attention to the impact of market opinion on demand; if the weight coefficients are adjusted to 0.3 and 0.7, the focus will be on reflecting the actual transaction trends on e-commerce platforms. This dynamic weighting mechanism allows the demand heat coefficient to adapt to different marketing scenarios. For example, it emphasizes social media dissemination during the new product launch period and e-commerce behavior data during the mature product period. It is worth mentioning that existing solutions corresponding to the above approach rely solely on internal sales data for demand forecasting, and cannot promptly capture potential demand changes brought about by social media dissemination. For example, if a product generates heated discussions on social media but has not yet generated actual orders, traditional methods cannot identify this signal. In addition, the impact of historical data fluctuation range is not considered. For example, when the number of times a product is added to favorites increases from 100 to 200, if the historical extreme value is 50-300 times, traditional methods may underestimate the actual significance of this increase. In the above approach, through range normalization, the relative position of the data within the historical fluctuation range can be accurately reflected, avoiding misjudgments caused by differences in the absolute magnitude of the data.

[0032] Furthermore, the introduction of social media popularity indexes enables the timely identification of sudden market hotspots. For example, when a product experiences a surge in potential demand due to social media buzz, the system can increase safety stock in advance. In addition, the calculation of the e-commerce platform's collection and add-to-cart frequency index accurately reflects the changing trends of users' purchasing intentions. For instance, when the number of collections for a product continues to climb before a promotional event, the system can predict sales growth and adjust inventory strategies accordingly.

[0033] In summary, the above integrated solution effectively shortens the transmission chain of market demand signals, enabling inventory decisions to respond to market changes in advance and avoiding the risk of inventory backlog or shortage due to lagging demand forecasts.

[0034] As a preferred embodiment of the technical solution of the present invention, the step of outputting the warehousing-product matching coefficient based on the warehousing cost volatility and product depreciation rate using a matching model under the current supply risk coefficient and elasticity coefficient is as follows: The storage cost volatility index is obtained by comparing the difference between the current storage cost volatility and the minimum historical storage cost volatility with the difference between the maximum historical storage cost volatility and the minimum historical storage cost volatility. Importing warehousing cost volatility and product depreciation rate into the formula Obtain the warehouse-product matching coefficient value range .

[0035] in, The supply risk coefficient refers to the probability that a supplier's supply will be interrupted due to quality or financial issues. It is specifically calculated by combining the factory quality inspection pass rate and financial health indicators, and is used to characterize the constraint of supply chain stability on inventory demand. The resilience coefficient refers to the supply chain's ability to recover from unexpected events. It is specifically assessed through the availability of substitutes and the response time of alternative warehouses, and is used to measure the necessity of inventory redundancy requirements. The storage cost volatility index refers to the magnitude of changes in storage costs per unit of time. Specifically, it can be quantified by the ratio of the standard deviation to the mean in historical data, and is used to reflect the impact of dynamic changes in storage costs on inventory decisions. Product depreciation rate refers to the rate of loss of value per unit time due to a decline in the market value of a product. It can be calculated using market price monitoring data and product life cycle models to assess the risk of economic losses caused by inventory backlog. For risk factor weighting coefficients, These are the cost factor weighting coefficients, which can be automatically learned by combining historical data or optimization algorithms (such as gradient descent). and All are greater than or equal to 0 and less than or equal to 1.

[0036] Furthermore, the warehousing cost volatility index eliminates dimensional differences through range standardization, making warehousing cost fluctuations across different periods comparable. In the matching model, the weighted combination of the supply risk coefficient and the elasticity coefficient forms the risk elasticity factor, reflecting the potential pressure of maintaining inventory under the current supply chain environment; the weighted combination of the warehousing cost volatility index and the product depreciation rate forms the cost depletion factor, characterizing the direct economic cost of holding inventory. Through dynamic adjustment of the risk factor weight coefficient and the cost factor weight coefficient, the risk elasticity factor and the cost depletion factor are multiplied to achieve a dynamic balance between supply chain stability and economic efficiency. For example, when the supply risk coefficient increases, the risk elasticity factor decreases, the warehousing-product matching coefficient decreases accordingly, and the system automatically reduces the priority of the product's safety stock.

[0037] As a preferred embodiment of the technical solution of the present invention, the step of outputting the supply risk coefficient based on the supplier's factory quality inspection pass rate and the supplier's financial health through the supply risk model is as follows: The supplier financial health index is obtained by comparing the difference between the current supplier financial health score and the lowest financial health score with the difference between the maximum financial health score and the lowest financial health score. Import supplier financial health and factory quality inspection pass rate into the formula. Obtain the supply risk coefficient This refers to a quantitative indicator generated by weighted fusion of quality inspection pass rate and financial health index. Specifically, a reverse mapping relationship can be used to convert the weighted result into a risk level, which is used to dynamically reflect the probability of supply chain disruption. The value range is... .

[0038] in, The factory quality inspection pass rate refers to the proportion of supplier's products that pass quality inspection. It can be obtained by sampling inspection or full inspection and is used to quantify the supplier's quality risk. The Supplier Financial Health Index is a comprehensive score calculated based on the supplier's debt-to-equity ratio, current ratio, and net profit margin. Specifically, it can be achieved by standardizing each financial indicator with preset thresholds and then weighting and summing them to reflect the supplier's financial stability. This is the pass rate weighting coefficient. The weighting coefficient can be automatically learned by combining historical data or optimization algorithms (such as gradient descent). Greater than or equal to 0 and less than or equal to 1. Ratio processing refers to calculating and normalizing the difference between the original data and a preset threshold. This can be achieved through linear transformation or nonlinear mapping, and is used to eliminate the impact of differences in the dimensions of different indicators on the evaluation results.

[0039] The explanation for the above is as follows: Supplier financial health is achieved by standardizing the debt-to-equity ratio, current ratio, and net profit margin, transforming raw financial data into a comparable index to address assessment biases caused by differences in the dimensions of various financial indicators. The factory quality inspection pass rate and the financial health index are integrated through a weighted formula, where the pass rate weight coefficient adjusts the priority between quality risk and financial risk. This allows the model to capture both the risk of returns due to quality defects and the potential for supply chain disruptions caused by financial deterioration. The supply risk coefficient, through a reverse mapping relationship, transforms the weighted result into a risk level; a higher value indicates a higher probability of supply chain disruption, providing dynamic early warning signals for subsequent inventory decisions.

[0040] Through the above technical solution, this invention can monitor the quality risk and financial health status of suppliers in real time, dynamically adjust the supply risk coefficient, and avoid supply interruptions caused by insufficient assessment from a single dimension. For example, when the supplier's quality inspection pass rate drops sharply or the debt-to-equity ratio exceeds the threshold, the system automatically increases the supply risk coefficient, triggering the inventory decision module to increase safety stock or switch to a backup supplier, thereby reducing the risk of supply chain disruption.

[0041] As a preferred embodiment of the technical solution of the present invention, the method for obtaining the supplier's financial health is as follows: The debt-to-asset ratio index is obtained by comparing the difference between the current debt-to-asset ratio and the minimum debt-to-asset ratio threshold with the difference between the maximum debt-to-asset ratio threshold and the minimum debt-to-asset ratio threshold. The current ratio index is obtained by comparing the difference between the current ratio and the minimum current ratio threshold with the ratio between the maximum current ratio threshold and the minimum current ratio threshold. The net profit margin index is obtained by comparing the difference between the net profit margin and the minimum threshold with the maximum threshold and the minimum threshold. Import the debt-to-equity ratio index, current ratio index, and net profit margin index into the formula. To obtain the supplier's financial health, the value range is... .

[0042] in, The debt-to-asset ratio index is a quantitative indicator that is normalized by the relative position of the current debt-to-asset ratio and a preset threshold range. Specifically, the difference ratio method can be used to map the actual debt-to-asset ratio to a standardized range, thereby eliminating the differences in the dimensions of debt levels in different industries. The current ratio index is a quantitative indicator that is normalized by the relative position of the current ratio with respect to a preset threshold range. Specifically, it can use the same normalization method as the debt-to-equity ratio to measure the dynamic changes in short-term solvency. The net profit margin index is a quantitative indicator that is normalized by the relative position of the current net profit margin with respect to a preset threshold range. Specifically, a linear transformation method can be used to convert the absolute value into a relative value, which is used to compare the profitability of suppliers of different sizes. , and These are all weighting coefficients, which can be automatically learned by combining historical data or optimization algorithms (such as gradient descent). ,and , and All are greater than or equal to 0 and less than or equal to 1.

[0043] In one embodiment of the technical solution of this invention, the calculation process of supplier financial health is divided into two stages: indicator normalization and weighted fusion. In the indicator normalization stage, three types of financial indicators—debt-to-equity ratio, current ratio, and net profit margin—are compared with preset industry benchmark thresholds. Differences in dimensions are eliminated using the difference ratio method. For example, when calculating the debt-to-equity ratio index, if the supplier's actual debt-to-equity ratio exceeds the maximum threshold, the index automatically takes a value of 1 to warn of risk. In the weighted fusion stage, the inversely weighted debt-to-equity ratio index is linearly combined with the forward-weighted current ratio index and net profit margin index using configurable weighting coefficients. For example, the weighting coefficients can be dynamically adjusted according to supply chain management strategies; for the fast-moving consumer goods industry, the weight of net profit margin can be set higher than other indicators. This calculation method enables supplier financial health to dynamically reflect multi-dimensional financial risks, while achieving cross-industry comparability through preset thresholds.

[0044] Through the above technical solution, this invention achieves a multi-dimensional dynamic quantitative assessment of a supplier's financial health, resolving the risk of misjudgment caused by the reliance on a single indicator in traditional assessment methods. For example, in scenarios where a supplier's short-term solvency is normal but its long-term liabilities continue to rise, the inversely weighted debt-to-equity ratio index can provide early warning of a deteriorating financial structure, offering accurate data input for the supply risk warning module 12. Furthermore, the normalized indicators support cross-industry comparisons of suppliers; for instance, differentiated threshold configurations can be used in the electronics manufacturing and food processing industries to make the assessment results more aligned with industry characteristics.

[0045] As a preferred embodiment of the technical solution of the present invention, the step of outputting the elasticity coefficient based on the availability of alternatives and the response time of alternative warehouses through the supply chain elasticity model is as follows: The ratio of the difference between the current alternative warehouse response time and the optimal response time to the difference between the longest acceptable response time and the optimal response time is used to obtain the alternative warehouse response time index. Import the availability of alternatives and the response time index of alternative warehouses into the formula. To obtain the elastic coefficient This refers to a quantitative assessment value that comprehensively considers the availability of substitutes and the timeliness of alternative warehouse responses. Specifically, it can be generated using a weighted summation algorithm and is used to dynamically reflect the supply chain's resilience in the face of unforeseen events. (Resilience coefficient) The larger the value, the smaller the optimal safety stock level; the range of values ​​is... .

[0046] in, The availability of substitutes refers to the possibility of having alternative products when the main supplier experiences a supply disruption. This can be achieved by matching product parameters in the supplier database and is used to assess the availability of alternative resources when the supply chain is disrupted. The alternative warehouse response time index is an indicator that is standardized by comparing the actual response time with the preset optimal value and the maximum tolerance value. Specifically, it can be calculated using a linear normalization formula to eliminate the differences in time dimensions between different warehouses. The alternative warehouse response time refers to the time required for the alternative warehouse to complete the shipment of goods from receiving an order. Specifically, it can be statistically analyzed through historical transportation records in the logistics management system to measure the emergency response efficiency of the alternative warehouse. The response time weighting coefficient refers to the parameter that substitutes for the contribution of warehouse response time in resilience assessment. It can be determined through regression analysis of historical interruption event data and is used to adjust the intensity of the impact of response efficiency on resilience assessment. Greater than or equal to 0 and less than or equal to 1.

[0047] Regarding the practical significance of the above scheme, firstly, the actual response time data of the alternative warehouses is obtained and compared with the preset optimal response time and the longest acceptable response time for enterprises. A standardized index is generated by processing the difference ratio, making the response efficiency of warehouses of different sizes comparable. Secondly, the binary judgment of whether there are available resources for alternatives is transformed into a probabilistic indicator, which is then weighted and integrated with the response time index. Finally, by adjusting the response time weight coefficient, the impact of the existence and timeliness of alternative resources on the overall resilience is dynamically balanced.

[0048] When applied to real-world scenarios, when enterprises focus more on rapid replenishment capabilities, the weighting coefficient of response time can be increased, making the elasticity coefficient more sensitive to changes in warehouse logistics efficiency. The resulting elasticity coefficient is directly input into the inventory decision model. When the elasticity coefficient increases, the system automatically lowers the safety stock level to avoid increasing warehousing costs due to over-reliance on inventory buffers. The principle is that by introducing a response time index, time efficiency is incorporated into the elasticity assessment system, and dynamic adjustments are made in conjunction with the weighting coefficient, making the elasticity assessment more in line with the timeliness constraints in actual business scenarios.

[0049] Specifically, when alternatives are available but warehouse response time exceeds the tolerance threshold, the system will automatically reduce the elasticity coefficient, triggering a safety stock adjustment mechanism to avoid stockout risks caused by logistics delays. Simultaneously, when the response efficiency of alternative warehouses improves, even if the availability of alternatives temporarily decreases, the system can still maintain a reasonable inventory level through changes in the elasticity coefficient, preventing unnecessary cost waste.

[0050] The above are merely preferred embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made using the present invention specification, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. An Internet-based digital supply chain construction system, characterized in that, The system includes: The market demand assessment module, based on social media popularity and the number of times items are added to cart or favorites on e-commerce platforms, outputs a demand popularity coefficient through a market demand model. The supply risk early warning module outputs a supply risk coefficient based on the supplier's factory quality inspection pass rate and the supplier's financial health through a supply risk model. The resilience assessment module outputs resilience coefficients based on the availability of alternatives and the response time of alternative warehouses through a supply chain resilience model. The two-way matching assessment module, under the current supply risk coefficient and elasticity coefficient, outputs the warehousing-product matching coefficient through the matching model based on the volatility of warehousing costs and the product depreciation rate. The dynamic inventory decision module outputs the optimal safety stock level based on the demand heat coefficient and the warehouse-product matching coefficient through the inventory decision model.

2. The Internet-based supply chain digital construction system according to claim 1, characterized in that, The market demand assessment module includes the following functions: The social media popularity index is obtained by comparing the difference between the current social media popularity and the historical minimum social media popularity with the difference between the historical maximum social media popularity and the historical minimum social media popularity. The difference between the current number of times a user adds items to their favorites and shopping cart on the e-commerce platform and the minimum number of times they add items to their favorites and shopping cart in history is compared with the difference between the maximum number of times they add items to their favorites and shopping cart in history and the minimum number of times they add items to their favorites and shopping cart in history to obtain the e-commerce platform's number of times it adds items to its favorites and shopping cart. Import social media popularity index and e-commerce platform favorites and add-to-cart frequency index into the formula Obtain the demand popularity coefficient Demand heat coefficient The larger the value, the higher the optimal safety stock level; the range of values ​​is... ,in, As a social media popularity index, The index of the number of times items are added to favorites and shopping carts on e-commerce platforms. This is the social media popularity weighting coefficient. Weighting coefficients for adding items to favorites and shopping carts on e-commerce platforms.

3. The Internet-based supply chain digital construction system according to claim 1, characterized in that, The supply risk early warning module's functions include: The supplier financial health index is obtained by comparing the difference between the current supplier financial health score and the lowest financial health score with the difference between the maximum financial health score and the lowest financial health score. Import supplier financial health and factory quality inspection pass rate into the formula. Obtain the supply risk coefficient value range ,in, The factory quality inspection pass rate, As a supplier's financial health index, This is the pass rate weighting coefficient.

4. The Internet-based supply chain digital construction system according to claim 3, characterized in that, The method for obtaining the supplier's financial health status is as follows: The debt-to-asset ratio index is obtained by comparing the difference between the current debt-to-asset ratio and the minimum debt-to-asset ratio threshold with the difference between the maximum debt-to-asset ratio threshold and the minimum debt-to-asset ratio threshold. The current ratio index is obtained by comparing the difference between the current ratio and the minimum current ratio threshold with the ratio between the maximum current ratio threshold and the minimum current ratio threshold. The net profit margin index is obtained by comparing the difference between the net profit margin and the minimum threshold with the maximum threshold and the minimum threshold. Import the debt-to-equity ratio index, current ratio index, and net profit margin index into the formula. To obtain the supplier's financial health, the value range is... ,in, This is the debt-to-equity ratio index. The current ratio index, This refers to the net profit margin index. , and All are weighting coefficients.

5. The Internet-based supply chain digital construction system according to claim 1, characterized in that, The resilient assessment module's functions include: The ratio of the difference between the current alternative warehouse response time and the optimal response time to the difference between the longest acceptable response time and the optimal response time is used to obtain the alternative warehouse response time index. Import the availability of alternatives and the response time index of alternative warehouses into the formula. To obtain the elastic coefficient elastic modulus The larger the value, the smaller the optimal safety stock level; the range of values ​​is... ,in, For the availability of alternatives, To replace the warehouse response time index, This is the response time weighting coefficient.

6. The Internet-based supply chain digital construction system according to claim 1, characterized in that, The bidirectional matching evaluation module's functions include: The storage cost volatility index is obtained by comparing the difference between the current storage cost volatility and the minimum historical storage cost volatility with the difference between the maximum historical storage cost volatility and the minimum historical storage cost volatility. Importing warehousing cost volatility and product depreciation rate into the formula Obtain the warehouse-product matching coefficient value range ,in, For supply risk factor, The elastic coefficient, This is a warehousing cost volatility index. For product depreciation rate, For risk factor weighting coefficients, This represents the weighting coefficient for cost factors.

7. The Internet-based supply chain digital construction system according to claim 1, characterized in that, The inventory decision model in the dynamic inventory decision module is as follows: ,in, The optimal safety stock level has a range of values. , This is the demand heat coefficient. This is the warehouse-product matching coefficient. This is the weighting coefficient for demand popularity. These are the matching coefficients and weighting coefficients.

8. The Internet-based supply chain digital construction system according to claim 7, characterized in that, The dynamic inventory decision-making module also includes the following functions: Convert the optimal safety stock level into the actual safety stock quantity. ,in, The maximum safety stock calculated based on service level objectives. The minimum safety stock calculated based on economic order volume. This represents the optimal safety stock level.

Images