Supply chain management method and system based on intelligent manufacturing

Abstract

The present application relates to supply chain management method technical field, more specifically, it relates to supply chain management method and system based on intelligent manufacturing, method includes: obtaining the cost information, operation and maintenance information and inventory information of each stage in supply chain;Based on information, obtain the risk value of each stage through hierarchical weighted dynamic risk prediction algorithm;Combined with the risk value and the sales information of goods, the gross profit information of each stage is obtained by using superposition nonlinear gross profit optimization algorithm;According to the gross profit information and the risk value, the optimal shipment allocation of each stage is obtained by using adaptive allocation optimization algorithm;Based on the gross profit accumulation of each stage, the global gross profit optimization information is obtained by using multi-dimensional progressive gross profit accumulation optimization algorithm;Based on the global gross profit optimization information, the feedback adjustment information of supply chain system is formed by using overall feedback closed loop optimization algorithm, the multi-dimensional risk prediction is formed by dynamically obtaining the cost, operation and maintenance and inventory information of each stage in supply chain.

Description

Supply Chain Management Methods and Systems Based on Intelligent Manufacturing Technical Field

[0001] This invention relates to the field of supply chain management methods, and more specifically, to supply chain management methods and systems based on intelligent manufacturing. Background Technology

[0002] In the field of intelligent manufacturing supply chain management, with increasing market demand volatility and the growing complexity of supply chain networks, traditional supply chain management methods are increasingly unable to meet the demands for refined and real-time management. Current technologies typically rely on fixed cost, maintenance, and inventory control methods, generally employing simple linear analysis models or static forecasting methods based on average values, lacking agile responses to dynamic market changes. This traditional approach has significant limitations in supply chain optimization, especially in the face of real-time demand fluctuations, making it difficult to guarantee optimal profitability.

[0003] Most supply chain management systems on the market currently optimize through two main approaches: first, by improving the production efficiency of individual stages to reduce costs; and second, by using linear forecasting models to perform simple trend analysis of demand. However, these methods typically ignore the complex interrelationships and mutual influences between different stages, resulting in limited optimization capabilities for the overall supply chain. For example, a cost-based allocation model cannot dynamically account for the potential impact of risks at each stage, potentially leading to excessive inventory in some stages while other stages suffer from insufficient supply, impacting overall profitability. Furthermore, such models fail to adequately reflect the real-time nature of market fluctuations. When market demand fluctuates significantly, the system struggles to quickly adjust to mismatches between supply and demand, resulting in reduced profitability.

[0004] Furthermore, traditional supply chain management often uses a fixed percentage model for calculating gross profit, neglecting the potential optimization space for gross profit through risk forecasting and allocation strategies. This makes it difficult to find a balance between revenue and risk. For example, gross profit is usually set as the difference between sales revenue and fixed costs. While this fixed calculation method is convenient to operate, it is difficult to adapt to changes in demand at different stages and cannot fully consider the differences in risk under different market conditions. Therefore, traditional gross profit calculation lacks flexibility and optimization depth, making it impossible to fully utilize resources in the supply chain for flexible adjustments when market conditions fluctuate drastically.

[0005] Existing supply chain management systems also have limitations in their allocation strategies. Many systems employ a single allocation scheme or fixed rules in their allocation algorithms. This approach may be relatively effective when market demand is stable, but when demand fluctuates significantly, the allocation rules, lacking adaptive adjustment capabilities, can easily lead to inventory backlogs or shortages. For example, in traditional allocation methods, shipment volumes are usually set based on historical averages. This may meet demand when market demand is stable, but once demand increases or decreases, static allocation volumes can easily lead to uneven resource distribution.

[0006] Furthermore, existing supply chain systems generally lack a cumulative feedback mechanism for overall profitability. Traditional methods mostly calculate costs and gross profits independently at each stage, lacking global feedback optimization across all stages of the supply chain. Therefore, in this situation, feedback between different stages cannot form a closed-loop control, resulting in a lack of synergy between decisions at each stage of the supply chain and an inability to maximize overall profitability. Due to the lack of interaction within each link of the supply chain, profitability cannot be cumulatively optimized globally, thus failing to achieve synergistic effects. Summary of the Invention

[0007] Based on the shortcomings of the existing technologies, this invention proposes a supply chain management method based on intelligent manufacturing, which aims to solve the problems of lack of dynamism, real-time performance and collaboration in existing methods through a series of innovative algorithms.

[0008] This invention provides a supply chain management method for intelligent manufacturing, the method comprising:

[0009] Obtain cost, operation and maintenance, and inventory information at each stage of the supply chain;

[0010] Based on the information, the risk value at each stage is obtained through a hierarchical weighted dynamic risk prediction algorithm;

[0011] Combining the aforementioned risk value and product sales information, a superimposed nonlinear gross profit optimization algorithm is used to obtain gross profit information for each stage;

[0012] Based on the gross profit information and risk value, the optimal shipment allocation for each stage is obtained through an adaptive allocation optimization algorithm;

[0013] Based on the accumulation of gross profit at each stage, global gross profit optimization information is obtained through a multi-dimensional progressive gross profit accumulation optimization algorithm;

[0014] Based on the global gross profit optimization information, feedback adjustment information for the supply chain system is generated through an overall feedback closed-loop optimization algorithm.

[0015] Preferably, the hierarchical weighted dynamic risk prediction algorithm includes:

[0016] A multidimensional risk factor vector V is generated based on cost information, operation and maintenance information, and inventory information at each stage. i Using a weighted matrix W i The risk factor vector is weighted to obtain the risk value R. i The risk value R i The calculation formula is:

[0017]

[0018] Among them, R i W represents the risk value at the current stage. i V is a risk prediction weighted matrix. i Q is a vector of multidimensional risk factors within a given period. i Let α be the risk threshold vector. k β represents the weight of the impact of risk factors. k M is the risk adjustment coefficient. i For the actual gross profit of the stage, K i This represents the expected value of gross profit.

[0019] Preferably, the superimposed nonlinear gross profit optimization algorithm includes:

[0020] Based on the risk value R i Based on the cost and maintenance information of the goods, determine the gross profit (G) for the current stage. i The gross profit G i The calculation formula is:

[0021]

[0022] Among them, G i For stage gross profit, S i For stage sales, C i For stage costs, M i R represents the phased operation and maintenance cost, λ is the nonlinear adjustment factor, and R is the maintenance cost. i This is the risk value output for the previous layer, where θ is the risk equilibrium point.

[0023] Preferably, the adaptive allocation optimization algorithm includes:

[0024] According to the gross profit G i and risk value R i The shipment allocation quantity D is obtained through segmented adjustments. i+1 The formula for calculating the shipment allocation is as follows:

[0025]

[0026] Among them, Di+1 D represents the allocation amount for the (i+1)th stage. i γ is the basic allocation amount for stage i. i ζ is the risk allocation balance coefficient, δ is the risk threshold, and ζ is the adaptive allocation adjustment coefficient.

[0027] Preferably, the multidimensional progressive gross profit accumulation optimization algorithm includes:

[0028] Based on gross profit information at each stage, and combined with historical gross profit, a gradual cumulative optimization of gross profit is performed to obtain the global gross profit G. total The global gross profit G total The calculation formula is:

[0029]

[0030] Among them, G total To accumulate gross profit, G i For the gross profit in stage i, η i G is the cumulative optimization factor for the stage, ξ is the sensitivity coefficient to gross profit growth, and G is the cumulative optimization factor for the stage. i-1 This represents the gross profit from the previous stage.

[0031] Preferably, the overall feedback closed-loop optimization algorithm includes:

[0032] Based on the global gross profit, combined with the risk value and allocation information, a feedback optimization quantity F is formed. i The feedback optimization quantity F i The calculation formula is:

[0033]

[0034] Among them, F i For the stage feedback optimization quantity, G total To accumulate gross profit, R j Let ω be the risk value for stage j. j This is the feedback adjustment coefficient.

[0035] A smart manufacturing-based supply chain management system for implementing the method includes:

[0036] The information acquisition module is used to acquire cost information, operation and maintenance information, and inventory information at each stage.

[0037] The risk prediction module obtains risk values ​​for each stage based on a hierarchical weighted dynamic risk prediction algorithm.

[0038] The gross profit calculation module obtains gross profit information at each stage based on a superimposed nonlinear gross profit optimization algorithm.

[0039] The allocation optimization module obtains the shipment allocation amount for each stage based on an adaptive allocation optimization algorithm;

[0040] The gross profit accumulation module obtains global gross profit information based on a multi-dimensional progressive gross profit accumulation optimization algorithm.

[0041] The closed-loop feedback module obtains feedback optimization information based on the overall feedback closed-loop optimization algorithm and updates it to the initial stage of the system.

[0042] Preferably, the risk prediction module obtains the risk value for each stage based on the information obtained by the information acquisition module.

[0043] Preferably, the gross profit calculation module obtains the gross profit information for each stage based on the risk value obtained by the risk prediction module.

[0044] Preferably, the closed-loop feedback module generates feedback optimization information based on the global gross profit information obtained by the gross profit accumulation module and updates it to the information acquisition module.

[0045] The invention has the following beneficial effects:

[0046] The supply chain management method and system of the present invention are designed with algorithm modules such as hierarchical weighted dynamic risk prediction, superimposed nonlinear gross profit optimization, adaptive allocation optimization, multidimensional progressive gross profit accumulation and overall feedback closed-loop optimization, so as to realize dynamic prediction and optimization of each stage of the supply chain.

[0047] This invention dynamically acquires cost, operation, and inventory information at each stage of the supply chain to form a multi-dimensional risk prediction. Specifically, the hierarchical weighted dynamic risk prediction algorithm of this invention not only flexibly adapts to different market fluctuations but also establishes weights among various risk factors to achieve more accurate risk prediction. Based on this prediction result, a nonlinear gross profit optimization algorithm is superimposed to finely adjust gross profit, maximizing gross profit under controllable risk. An adaptive allocation optimization algorithm adjusts shipment volume in real time, ensuring that the supply chain maintains a reasonable allocation of resources even when demand fluctuates, avoiding the risks of inventory backlog and shortages. A multi-dimensional progressive gross profit accumulation optimization algorithm dynamically accumulates gross profit at each stage, achieving global optimization of revenue. Finally, through an overall feedback closed-loop optimization algorithm, the system can generate real-time feedback between each stage, continuously improving the overall efficiency of the supply chain.

[0048] Therefore, the technical problem this invention aims to solve is how to achieve real-time optimization of supply chain management in a smart manufacturing environment through accurate risk prediction, dynamic gross profit optimization, and adaptive allocation, and to achieve synergistic effects in global profit accumulation and feedback regulation. The steps in this invention's method form a coordinated and efficient overall solution through the complementary and synergistic effects of algorithms, effectively compensating for the shortcomings of existing technologies in dynamic regulation and real-time optimization, and ensuring the robustness and efficiency of the supply chain system under conditions of significant market demand fluctuations. Attached Figure Description

[0049] Figure 1 is a flowchart of the method of the present invention.

[0050] Figure 2 is a system structure logic block diagram of the present invention.

[0051] Figure 3 is a block diagram of the information flow and workflow judgment logic of the present invention. Detailed Implementation

[0052] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the specific implementation methods, structures, features, and effects are described in detail below with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0054] Please refer to Figures 1-3. This invention provides a supply chain management method and system based on intelligent manufacturing. It aims to achieve precise management of information such as cost, gross profit, and inventory at each stage of the supply chain through innovative algorithms with dynamic optimization, and to optimize allocation based on risk prediction and gross profit analysis, thereby improving the overall efficiency of the supply chain in an intelligent manufacturing environment.

[0055] The core of this invention lies in a supply chain management method based on intelligent manufacturing, the key of which is to first acquire cost information, operation and maintenance information, and inventory information at each stage of the supply chain. This information acquisition module can collect various types of information in real time from multiple data sources within the supply chain management system, such as cost data recorded in the financial system for each stage, equipment maintenance and operating costs in the operation and maintenance system, and inventory data from the warehouse management system. For specific numerical examples, cost information includes, but is not limited to, the unit cost of a single product during the production stage (e.g., 10 to 15 yuan per unit), operation and maintenance information includes the maintenance cost per piece of equipment (e.g., approximately 1 to 5 yuan per day), and inventory information represents the current inventory level; for example, the inventory at a certain stage may be between 200 and 500 units.

[0056] Next, by aggregating and standardizing the data from each stage, the system can obtain the overall operational status of each node in the supply chain. Preferably, through refined data stratification, this invention can more accurately obtain the cost composition of different stages, thereby providing basic data for subsequent gross profit calculation and risk control, and ensuring the overall optimization of supply chain management.

[0057] In a preferred embodiment of the present invention, based on information acquisition, a hierarchical weighted dynamic risk prediction algorithm is further proposed to obtain the risk values ​​at each stage. This algorithm uses a weighting matrix and a multidimensional risk factor vector for risk prediction, with the specific formula as follows:

[0058]

[0059] Among them, R i W represents the risk value at the current stage. i The risk prediction weighted matrix is ​​defined as an adjustable weight factor matrix that reflects the different impacts of each risk factor on the overall risk; V i This is a multidimensional risk factor vector within a stage, used to represent the risk parameter Q for each stage. i This is a risk threshold vector, used to represent the reasonable range of each risk factor; α k To determine the impact weights of risk factors, the weight ratio of each factor to the overall risk value is determined; β k This is a risk adjustment factor, typically adjusted based on historical data to optimize forecast accuracy; M i This represents the actual gross profit at the current stage, while K... i This represents the expected value of the gross profit forecast.

[0060] Preferably, in one embodiment of the present invention, the risk threshold can be set to 0.7. This is an empirical value, indicating that when the risk value exceeds 0.7, a certain stage of the supply chain is in a high-risk state and needs to enter the adjustment phase. Based on this prediction algorithm, the system can flexibly adjust the risk judgment based on real-time data, thereby significantly improving the supply chain's resilience and prediction accuracy.

[0061] Based on risk prediction, a nonlinear gross profit optimization algorithm is further applied to obtain gross profit information at each stage. This algorithm achieves optimal gross profit allocation under controllable risk by nonlinearly combining risk value and gross profit. The specific calculation formula is as follows:

[0062]

[0063] Among them, G i For the current stage of gross profit, Si This indicates the sales revenue for a given period, preferably set between 500,000 and 1,000,000 yuan when production and shipment volumes are large, in order to increase profits; C i The stage cost, referencing the raw material and production costs per unit of product, can be between 100,000 and 200,000 yuan; M i The operation and maintenance cost is typically around 50,000 yuan per phase; λ is a non-linear adjustment factor used to control the smoothness of the gross profit curve, and can usually be set to 0.5 to 1.5; R i The risk value is the output of the previous algorithm, and θ is the risk equilibrium point, which is usually taken as 0.7 to avoid gross profit being severely affected by excessive risk.

[0064] This algorithm is preferably designed to reduce gross profit fluctuations during high-risk phases. When the risk value reaches 0.7 or higher, the algorithm adjusts the ratio of sales revenue to costs to limit gross profit within a reasonable range, thereby reducing the volatility of system operation and maximizing the overall profitability of the supply chain.

[0065] In a preferred embodiment of the present invention, the optimal shipment allocation quantity for each stage is obtained through an adaptive allocation optimization algorithm based on the optimized gross profit information and risk value. This algorithm uses a piecewise function to dynamically adjust the allocation quantity for each stage according to the current risk and gross profit situation, ensuring optimal operation of the supply chain. The calculation formula is as follows:

[0066]

[0067] Among them, D i+1 D represents the shipment allocation for stage i+1. i This represents the basic allocation amount for the previous stage; γ i The risk allocation balancing coefficient can preferably be set in the range of 1.0 to 2.0 to balance the relationship between shipment volume and risk; δ is the risk threshold, which is recommended to be 0.5 to 0.7 to adapt to different risk allocation strategies; ζ is the adaptive allocation adjustment coefficient, which is preferably between 0.3 and 0.7 to ensure that the system can quickly adapt to changes in a higher risk environment.

[0068] This algorithm uses a segmented adjustment approach to enable the supply chain to automatically optimize shipment allocation under different risk levels. Preferably, when the risk value is below 0.5, the algorithm will maximize the allocation to meet market demand; when the risk exceeds 0.7, the algorithm will significantly reduce the allocation to reduce inventory backlog and cost waste, thereby improving the flexibility of the supply chain.

[0069] In a preferred embodiment of the present invention, based on the gross profit information of the aforementioned stages, a multi-dimensional progressive gross profit accumulation optimization algorithm is used to accumulate and optimize the gross profit at each stage, so as to achieve the optimal allocation of the overall gross profit of the supply chain. This algorithm combines historical gross profit with current stage data, and maximizes global benefits by dynamically updating the accumulated gross profit. The specific formula is as follows:

[0070]

[0071] Among them, G total Gross profit is accumulated across the entire supply chain, representing the overall profitability of the current supply chain; G i η represents the gross profit value for stage i; i The cumulative optimization factor for each stage is recommended to be in the range of 0.2 to 0.6 to correspond to different gross profit increments; ξ is the gross profit growth sensitivity coefficient, typically between 0.5 and 1.0, to adjust the sensitivity of gross profit growth; G i-1 This represents the gross profit from the previous stage.

[0072] Preferably, by gradually accumulating and adjusting the gross profit distribution, the optimal revenue distribution can be achieved in different stages of the supply chain, while avoiding instability caused by excessive differences in gross profit between stages. Furthermore, through incremental optimization, the algorithm ensures that the gross profit at each stage remains within a reasonable range, effectively improving the overall efficiency of the supply chain.

[0073] In a preferred embodiment of the present invention, based on the aforementioned cumulative gross profit optimization, the present invention further provides an overall feedback closed-loop optimization algorithm to adjust supply chain management strategies through real-time feedback, thereby optimizing the overall operation of the supply chain. This algorithm, based on gross profit and risk data at each stage, feeds back global gross profit information to the initial stage of the system, enabling subsequent stages to adjust parameters according to the feedback, thereby optimizing the overall efficiency and stability of the supply chain. The calculation formula of the algorithm is as follows:

[0074]

[0075] Among them, F i Let G be the feedback optimization amount for the current stage, representing the final optimization result of stage i, which will be directly fed back to the next stage; total Gross profit is accumulated and represents the overall profitability of the supply chain; R j ω represents the risk value for stage j, indicating the degree of impact of this stage on the overall return; j The feedback adjustment coefficient is preferably set between 0.8 and 1.2 to ensure the rationality and stability of the feedback data.

[0076] In one embodiment of the present invention, the feedback adjustment coefficient can be adapted according to the specific risk value. For example, a lower adjustment coefficient can be selected for low risk values ​​(such as below 0.3), while the coefficient can be increased for high risk values ​​(such as above 0.7), thereby achieving dynamic control under different risk conditions. Through this closed-loop feedback algorithm, the system can continuously optimize the relationship between gross profit and risk allocation, forming an adaptive adjustment mechanism and improving the overall responsiveness and profitability of the supply chain.

[0077] This invention also provides a supply chain management system based on intelligent manufacturing. This system includes an information acquisition module 1, a risk prediction module 2, a gross profit calculation module 3, an allocation optimization module 4, a gross profit accumulation module 5, and a closed-loop feedback module 6, to achieve dynamic monitoring and optimization of data at each stage. The information acquisition module 1 in this system is responsible for acquiring cost information, operational information, and inventory information from different data sources, ensuring the comprehensiveness and accuracy of the information.

[0078] Risk prediction module 2 uses a hierarchical weighted dynamic risk prediction algorithm to analyze risk factors at different stages and outputs the risk values ​​to gross profit calculation module 3. Gross profit calculation module 3 further employs a superimposed nonlinear gross profit optimization algorithm to calculate the gross profit information for each stage based on the comprehensive risk values. Allocation optimization module 4 uses an adaptive allocation optimization algorithm to adjust the allocation of gross profit results to achieve the optimal shipment allocation for each stage.

[0079] Furthermore, the gross profit accumulation module 5 combines multi-stage gross profit information and performs cumulative optimization through a multi-dimensional progressive gross profit accumulation optimization algorithm, outputting global gross profit information to the closed-loop feedback module 6. The closed-loop feedback module 6 then uses an overall feedback closed-loop optimization algorithm to provide the feedback results to the information acquisition module 1, thereby completing the closed-loop control of the entire system. Through data flow connections and collaborative operation, the various modules of the system form a highly automated supply chain optimization system.

[0080] In the intelligent manufacturing-based supply chain management system of this invention, the risk prediction module 2 specifically applies the aforementioned hierarchical weighted dynamic risk prediction algorithm. This algorithm dynamically predicts risk values ​​at each stage based on the data acquired by the information acquisition module 1. Its weighting matrix and risk factor vector can flexibly adapt to different risk types and influencing factors, thereby outputting accurate risk values.

[0081] In this process, the weighted matrix can be composed of different risk weight parameters to adapt to various market conditions. For example, in the event of severe market volatility, the system can increase the weight of the market volatility parameter to more accurately reflect the impact of market changes on the supply chain. The output of the risk prediction module 2 directly affects the optimization decision of the gross profit calculation module 3, enabling each stage of the supply chain to operate smoothly and obtain the best gross profit under the premise of controllable risk.

[0082] In the above system architecture, the gross profit calculation module 3 specifically employs a superimposed nonlinear gross profit optimization algorithm to obtain accurate gross profit information based on the output value of the risk prediction module 2. Preferably, this module compares historical data and real-time data to adjust the values ​​of λ and θ in a timely manner when the parameter uncertainty is large, so as to maintain the stability of the algorithm output.

[0083] For example, during peak market demand periods, sales figures may fluctuate significantly. In such cases, the gross profit calculation module 3 can appropriately adjust the risk equilibrium point (theta) to ensure the algorithm's adaptability to sales fluctuations. Through this nonlinear optimization, the gross profit calculation module 3 can more accurately allocate supply chain resources and maximize profits.

[0084] Furthermore, the closed-loop feedback module 6 of this invention, based on the overall feedback closed-loop optimization algorithm of claim 5, feeds back global gross profit and risk information to the information acquisition module 1. The core of the algorithm of the closed-loop feedback module 6 lies in optimizing the parameter settings of the information acquisition module 1 in real time according to the overall profit situation and risk level, so as to ensure that the supply chain can quickly respond and optimize resources in a constantly changing market environment.

[0085] In a preferred embodiment, the closed-loop feedback module 6 can be set with a feedback adjustment coefficient ω. j By maintaining a value between 0.8 and 1.2, resource input can be slightly reduced when risk is high, while resource allocation can be increased during low-risk phases to enhance the balance of the supply chain. In this way, the feedback module can maintain the dynamic stability of the system amidst fluctuations in demand and changes in risk levels, providing high-quality decision support for subsequent stages.

[0086] Through the above detailed description, the intelligent manufacturing-based supply chain management method and system of the present invention forms a complete logical closed loop in terms of information acquisition, risk prediction, gross profit calculation, shipment allocation, global gross profit accumulation and feedback adjustment. Through the synergistic effect of algorithms and the real-time flow of data between the modules, the system can accurately predict and control the risks and benefits of each stage of the supply chain, and ultimately optimize the overall efficiency of the supply chain.

[0087] The intelligent manufacturing-based supply chain management method and system of this invention achieves risk prediction, gross profit optimization, allocation adjustment, and feedback optimization at each stage of the supply chain through innovative algorithms, thereby improving the overall efficiency and profitability of the supply chain. To verify the superiority of this invention, experimental tests were conducted, comparing the method of this invention with existing traditional supply chain management methods using a professional supply chain dataset.

[0088] The dataset used in the test encompasses multidimensional data on typical supply chain processes, including costs, operational expenses, inventory information, sales revenue, and market fluctuations at each stage. Specifically, the data comes from the annual supply chain data of a smart manufacturing company, reflecting supply chain changes under different market conditions, such as demand fluctuations between peak and off-peak seasons. For comparison, the management method of this invention (example) and a traditional supply chain management method (comparative example) were implemented under the same market conditions, and a detailed analysis was conducted on the gross profit, risk, shipment allocation accuracy, and overall profitability at each stage.

[0089] This test uses the following four indicators to verify the superiority of the method of this invention in practical applications:

[0090] 1. Gross Profit Margin: Defined as the ratio of gross profit to sales revenue, used to verify the effectiveness of the gross profit optimization algorithm. The testing method involves comparing sales revenue and gross profit at each stage; a higher gross profit margin indicates better revenue optimization.

[0091] 2. Risk Control Level: This is quantified using a risk value. The risk threshold set in the test is 0.7; risks exceeding this threshold are considered higher risks. The risk value is measured using the output of a risk prediction algorithm. A higher risk control level indicates a stronger risk management capability of the method.

[0092] 3. Allocation Accuracy: This refers to the degree of matching between the allocated shipment quantity and the actual demand. Allocation accuracy is measured by calculating the ratio of actual shipments to predicted demand at each stage. Higher allocation accuracy indicates better adaptability and precision of the allocation algorithm.

[0093] 4. Overall Profit Improvement Rate: Defined as the percentage increase in profit of the management method of this invention compared to the traditional method. The calculation method is (overall profit of this invention - overall profit of the traditional method) / overall profit of the traditional method * 100%. This indicator is used to evaluate the improvement in overall efficiency of this invention.

[0094] In the embodiments, the method of the present invention performs real-time risk prediction, gross profit optimization, and dynamic allocation adjustment based on the information of each stage in the dataset; while the comparative method adopts the traditional average allocation and fixed gross profit calculation method, without considering factors such as risk control and feedback optimization. The experimental results are shown in Table 1.

[0095] Example of Indicator Comparison: Gross Profit Margin 45.6% 38.2% +7.4%; Risk Control 92% 75% +17%; Allocation Accuracy 96% 82% +14%; Overall Profit Improvement 12.5% ​​-- surface

[0096] The test results show that the method of this invention exhibits significant superiority in all indicators. Regarding gross profit margin, the method of this invention, by superimposing a nonlinear gross profit optimization algorithm and combining it with real-time risk prediction and control, achieves higher profit optimization, increasing the gross profit margin by 7.4 percentage points compared to the comparative method. This demonstrates that the method of this invention can utilize resources more effectively and maximize profits.

[0097] Regarding risk control, the embodiment demonstrates significantly enhanced risk management capabilities compared to the comparative method by combining a hierarchical weighted dynamic risk prediction algorithm with a holistic feedback closed-loop optimization algorithm. In the comparative method, the risk control rate was only 75%, while the embodiment achieved 92%, fully demonstrating the stability and resilience of the invention under complex market conditions.

[0098] Allocation accuracy is also a key advantage. Through an adaptive allocation optimization algorithm, the method of this invention achieves a high degree of matching between the shipment volume and actual demand at each stage, reaching an allocation accuracy of 96% in the embodiment, compared to only 82% in the comparative example. This demonstrates that the present invention can accurately allocate shipment volume even when actual demand fluctuates significantly, thereby reducing inventory costs and waste.

[0099] In terms of overall revenue improvement, the embodiment achieved a 12.5% ​​revenue increase compared to the comparative example, indicating that under the same market conditions, the method of the present invention can significantly improve overall efficiency through refined risk control and gross profit optimization, achieving a higher level of management and economic benefits.

[0100] In summary, the test results demonstrate the superiority of the intelligent manufacturing-based supply chain management method and system of this invention in improving gross profit margin, risk control, allocation accuracy, and overall profitability. The innovative algorithm of this invention outperforms traditional methods in all indicators, validating the practical application value of this invention in intelligent manufacturing supply chain scenarios.

[0101] It should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A supply chain management method based on intelligent manufacturing, characterized in that, The method includes: acquiring cost information, operation and maintenance information, and inventory information at each stage of the supply chain; and obtaining the risk value of each stage based on the cost information, operation and maintenance information, and inventory information using a hierarchical weighted dynamic risk prediction algorithm. The hierarchical weighted dynamic risk prediction algorithm includes: generating a multi-dimensional risk factor vector based on cost information, operation and maintenance information, and inventory information at each stage. Using a weighted matrix The risk factor vector is weighted to obtain the risk value. The risk value The calculation formula is: ;in, For the first Risk value of the stage For the first Risk prediction weighted matrix for each stage For the first Multidimensional risk factor vector within a phase, For the first Risk threshold vector for each stage For the first The impact weight of each risk factor For the first Risk adjustment coefficient for each risk factor For the first Actual gross profit at the stage For the first Expected gross profit for the stage; combined with the aforementioned risk value. Based on the sales information of the goods, the gross profit at each stage is obtained using a superimposed nonlinear gross profit optimization algorithm. According to the gross profit and risk value The shipment allocation amount for each stage is obtained through an adaptive allocation optimization algorithm. Gross profit at each stage The global cumulative gross profit is obtained through a multidimensional progressive gross profit accumulation optimization algorithm. Based on the aforementioned global cumulative gross profit The feedback optimization quantity of the supply chain system is formed through the overall feedback closed-loop optimization algorithm. and the feedback optimization amount Feedback is sent to the initial stage of the supply chain system for parameter updates.

2. The supply chain management method based on intelligent manufacturing as described in claim 1, characterized in that, The superimposed nonlinear gross profit optimization algorithm includes: based on the risk value Based on the cost and maintenance information of the goods, determine the first Gross profit per stage The gross profit The calculation formula is: ;in, For the first Gross profit at each stage For the first Sales volume in a given period For the first The cost of the stage For the first Phase-specific maintenance costs, It is a non-linear adjustment factor. Output the risk value for the previous layer. This is the risk balancing point.

3. The supply chain management method based on intelligent manufacturing as described in claim 2, characterized in that, The adaptive allocation optimization algorithm includes: based on the gross profit... and risk value The shipment allocation is obtained by adjusting the shipment in segments. The formula for calculating the shipment allocation is as follows: ;in, For the first The allocation amount for each stage, For the first The basic allocation amount for each stage To allocate a risk balancing coefficient, As a risk threshold, Adjustment coefficients are assigned adaptively.

4. The supply chain management method based on intelligent manufacturing as described in claim 3, characterized in that, The multidimensional progressive gross profit accumulation optimization algorithm includes: based on the gross profit at each stage By combining historical gross profit, incremental optimization of gross profit is performed to obtain global cumulative gross profit. The global cumulative gross profit The calculation formula is: ;in, To accumulate gross profit for the whole, For the first Gross profit at each stage For the first The cumulative optimization factor of the stage This is the sensitivity coefficient for gross profit growth. For the first Gross profit at each stage.

5. The supply chain management method based on intelligent manufacturing as described in claim 4, characterized in that, The overall feedback closed-loop optimization algorithm includes: based on the global cumulative gross profit By combining risk values ​​and allocation information, a feedback optimization quantity is formed. The feedback optimization amount The calculation formula is: ;in, For the first The amount of feedback optimization at each stage. To accumulate gross profit for the whole, For the first Risk value of the stage For the first The feedback adjustment coefficient for each stage.

6. A supply chain management system based on intelligent manufacturing that implements the method of any one of claims 1-5, characterized in that, include: The information acquisition module is used to acquire cost information, operation and maintenance information, and inventory information at each stage. The risk prediction module obtains risk values ​​for each stage based on a hierarchical weighted dynamic risk prediction algorithm. The gross profit calculation module uses a superimposed nonlinear gross profit optimization algorithm to obtain the gross profit at each stage. The allocation optimization module obtains the shipment allocation quantity for each stage based on an adaptive allocation optimization algorithm. The gross profit accumulation module obtains the global cumulative gross profit based on a multi-dimensional progressive gross profit accumulation optimization algorithm. The closed-loop feedback module obtains the feedback optimization amount based on the overall feedback closed-loop optimization algorithm. And update it to the information acquisition module.

7. The supply chain management system based on intelligent manufacturing as described in claim 6, characterized in that, The risk prediction module obtains the risk value for each stage based on the information acquired by the information acquisition module. 。 8. The supply chain management system based on intelligent manufacturing as described in claim 7, characterized in that, The gross profit calculation module is based on the risk value obtained by the risk prediction module. To obtain gross profit at each stage 。 9. The supply chain management system based on intelligent manufacturing as described in claim 8, characterized in that, The closed-loop feedback module is based on the global cumulative gross profit obtained by the gross profit accumulation module. Generate feedback optimization quantity And update it to the information acquisition module.

Images