Logistics supply chain management method and system

Abstract

The invention discloses a logistics supply chain management method and system, and relates to the technical field of logistics supply chain management, and the method comprises the following steps: 1, obtaining real-time data of each link of a supply chain based on a data collection unit, and carrying out the standardization processing and aggregation processing of the collected data; 2, predicting market demands based on the data of the data acquisition and preprocessing module, and generating a prediction optimization model of the demands; 3, constructing a multi-objective optimization model based on a demand prediction and preliminary optimization module to optimize the preliminary supply chain decision; 4, applying the optimized supply chain decision to the logistics supply chain, monitoring the state of the supply chain in real time, and dynamically adjusting the strategy based on the latest data and the optimization result; and 5, continuously monitoring and evaluating the operation effect of the supply chain based on a decision execution and dynamic adjustment module, and optimizing the multi-target optimization model based on historical data and a real-time monitoring result.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics supply chain management, and in particular to a logistics supply chain management method and system. Background Art

[0002] Logistics supply chain management refers to optimizing supply chain operations, from procurement to satisfying end customers at the lowest cost, with the core of logistics activities. It involves coordinating internal and external resources of the enterprise, including production, supply, sales and logistics, to achieve comprehensive management.

[0003] With the rapid development of the global economy and the diversification of market demands, modern logistics supply chains have become increasingly complex. Traditional supply chain management methods often have the following problems:

[0004] 1. High dependence on technology and strategy: The complex multi-objective optimization algorithm and dynamic adjustment strategy relied on by the present invention require high technical support and professional operational knowledge, which not only increases the difficulty of implementation and maintenance, but may also cause system instability or failure due to technical updates or improper operation.

[0005] 2. Limitations of market demand forecasting: Although the present invention can accurately predict market demand and optimize inventory, transportation and production strategies, market demand itself is uncertain and volatile. The accuracy of the forecasting model may be affected by a variety of external factors, such as emergencies, policy changes, etc., which may cause the forecast results to deviate from reality and thus affect the optimization effect of inventory levels and production plans.

[0006] 3. Customer dependence and satisfaction risk: The present invention ensures on-time delivery and order fulfillment rate by optimizing the algorithm to improve customer service experience. However, this method is highly dependent on the accuracy and real-time performance of the algorithm. If the algorithm fails or data is input incorrectly, it may lead to delayed order processing or untimely delivery, thereby affecting customer satisfaction and loyalty.

[0007] 4. Supply chain risks and adaptability challenges: Although the present invention has the ability to quickly respond to changes in market demand, in actual operation, the complexity and variability of the supply chain may exceed the system's processing capabilities. Although diversified supplier selection and risk management strategies can reduce some risks, they cannot completely eliminate all risks faced by the supply chain. In addition, as the market environment continues to change, the adaptability and effectiveness of the system may also face challenges.

[0008] Therefore, there is an urgent need for an intelligent supply chain management method and system that can dynamically adapt to market changes and optimize resource allocation to achieve efficient operation and sustainable development of the supply chain. Summary of the invention

[0009] The purpose of the present invention is to provide a logistics supply chain management method and system to solve the problems raised in the above background technology.

[0010] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0011] A logistics supply chain management method comprises the following steps:

[0012] Step 1, data collection and preprocessing module: the data collection and preprocessing module includes a data collection unit and a data preprocessing unit. The data collection unit acquires real-time data of each link of the supply chain by collecting multi-layer data. The data preprocessing unit performs standardization and aggregation processing based on the data collected by the data collection unit.

[0013] Step 2, demand forecasting and preliminary optimization module: forecast market demand based on the data from the data collection and preprocessing module, and generate a demand forecast optimization model. Based on the current supply chain status and predicted market demand, perform preliminary optimization calculations to determine preliminary supply chain decisions.

[0014] Step 3, multi-objective optimization calculation module: construct a multi-objective optimization model based on demand forecasting and preliminary optimization modules to optimize the preliminary supply chain decision;

[0015] Step 4, decision execution and dynamic adjustment: Apply the optimized supply chain decision to the logistics supply chain, monitor the status of the supply chain in real time, based on the latest data and optimization results;

[0016] Step 5, the feedback and continuous optimization: continuously monitor and evaluate the operational effect of the supply chain based on the decision execution and dynamic adjustment module, and optimize the multi-objective optimization model based on historical data and real-time monitoring results.

[0017] A further improvement of the technical solution of the present invention is that: the data acquisition unit acquires real-time data of each link of the supply chain by collecting multi-layer data, wherein x is set as a supply chain decision variable vector, including inventory level I, transportation status T, transportation speed V and purchase quantity Q;

[0018] The data preprocessing unit performs standardization processing and aggregation processing based on the data collected by the data collection unit as follows:

[0019] Standardization formula:

[0020]

[0021] Where D 标准 The original data set, even if it is inventory level I, transportation status T, transportation speed V and purchase quantity Q, D 原始is the standardized data set, μ is D 标准 The mean of 标准 The standard deviation of

[0022] The data set formed by the data preprocessing unit through multi-level data aggregation is specifically as follows:

[0023]

[0024] where ω i is the data weight at different levels, is the standardized data of the i-th level, D agg To form a multi-level data set, there are a total of n levels of data.

[0025] A further improvement of the technical solution of the present invention is that the multi-objective optimization model is specifically as follows:

[0026]

[0027] Among them, C(x), E(x), S(x), C(x), P(x), R(x), and A(x) represent the total cost function of the supply chain, the overall efficiency function of the supply chain, the customer service level function, the environmental impact function, the risk function of the supply chain, and the adaptability function of the supply chain under given production parameters, respectively. α, β, γ, δ, ∈ are weight coefficients, F(x) is the objective function, and x is the vector of supply chain decision variables.

[0028] A further improvement of the technical solution of the present invention is that the objective function includes the total cost function of the supply chain, the overall efficiency function of the supply chain, the customer service level function, the environmental impact function, the risk function of the supply chain and the adaptability function of the supply chain, which are respectively expressed as C(x), E(x), S(x), C(x), P(x), R(x), and A(x). The specific analysis is as follows:

[0029] The total cost function of the supply chain is: C(x) = C p (Q)+C s (I)+C t (T)+C h (V)

[0030] Among them C p (Q), C s (I) C t (T), C h (V) represents procurement cost, storage cost, transportation cost and labor cost respectively.

[0031] A further improvement of the technical solution of the present invention is that the overall efficiency function formula of the supply chain is further expressed as:

[0032]

[0033] Where E P 、E t are production efficiency and transportation efficiency respectively, λ is the penalty coefficient of transportation delay, and d(T) is the transportation delay time.

[0034] A further improvement of the technical solution of the present invention is that the customer service level function formula is further expressed as:

[0035] S(x)=ω d ·S d (T)+ω O ·S O (Q)

[0036] where ω d ,ω O are the weights of on-time delivery rate and order fulfillment rate, S d , S O They are on-time delivery rate and order fill rate respectively.

[0037] A further improvement of the technical solution of the present invention is that the environmental impact function formula is further expressed as:

[0038] P(x)=θ c ·P c (T)+θ e ·P e (V)

[0039] Where P c , P e They are expressed as carbon emissions and energy consumption respectively;

[0040] The risk function formula of the supply chain is further expressed as:

[0041] R(x)=κ i ·R i (Q)+κ m ·R m (D agg )

[0042] where κ i , κ m Expressed as the weight of each risk type, R i , R m They are respectively expressed as interruption risk and market volatility risk.

[0043] A further improvement of the technical solution of the present invention is that the adaptability function of the supply chain is further expressed as:

[0044]

[0045] Where η is the adjustment coefficient of response speed, M(t) is the market demand forecast function, dM(t) and dQ(x) represent the change rate of market demand and the change rate of production or supply capacity of the supply chain over time t, respectively.

[0046] A further improvement of the technical solution of the present invention is that in the process of supply chain optimization, the system optimization cycle steps are:

[0047] S1: Demand forecasting and preprocessing: Based on the multi-objective optimization model, the real-time data collected from each link of the supply chain is detected and processed to form a market demand forecasting function M(t), and the forecast results are preprocessed. Where M(t) is the prediction function, g(t-τ) is the response function or weight function, which indicates the attenuation of the influence on past data, X(τ) is the observation value at time τ, and M(t) mainly predicts any one of the values ​​of inventory level I, transportation status T, transportation speed V, and purchase volume Q;

[0048] S2: Based on the current supply chain status and demand forecast results, perform preliminary optimization calculations to obtain preliminary supply chain decisions;

[0049] S3: Based on the preliminary optimization results, a complex optimization engine is used to perform multi-objective optimization calculations to solve the optimal decision variable x so that the objective function F(X) reaches the minimum value;

[0050] S4: Based on the intelligent decision support module, the multi-objective optimization model is dynamically adjusted according to real-time monitoring data, and rapid re-optimization is performed according to changes in market and supply chain status.

[0051] A further improvement of the technical solution of the present invention is: a logistics supply chain management system, used to implement the logistics supply chain management method described above, characterized in that it includes a data acquisition and preprocessing module, a demand forecasting and preliminary optimization module, a multi-objective optimization calculation module, a decision execution and dynamic adjustment module, a feedback and continuous optimization module and an electrical connection.

[0052] Due to the adoption of the above technical solution, the present invention has the following technical advances compared with the prior art:

[0053] 1. The present invention provides an innovative logistics supply chain management method and system, which applies complex multi-objective optimization algorithms and dynamic adjustment strategies. This method not only comprehensively considers multiple key factors such as cost, time, and resource utilization, but can also make intelligent adjustments in a real-time changing market environment, thereby ensuring that the overall efficiency of the supply chain is significantly improved.

[0054] 2. The logistics supply chain management method and system provided by the present invention achieves a significant reduction in the total operating cost of the supply chain by finely optimizing inventory, transportation and production strategies. The method can accurately predict market demand, reasonably arrange production plans and inventory levels, and avoid cost waste caused by excessive inventory or out-of-stock. At the same time, by optimizing transportation routes and distribution methods, the logistics cost and transportation time are further reduced, so that the overall operating cost of the supply chain is effectively controlled, and the profitability and market competitiveness of the enterprise are significantly improved.

[0055] 3. The logistics supply chain management method and system provided by the present invention ensure on-time delivery and order fulfillment rate through advanced optimization algorithms, thereby significantly improving the customer service experience. The method can track the order status in real time, accurately predict the delivery time, and make rapid adjustments when necessary to ensure that the order can be delivered on time. At the same time, by optimizing production plans and inventory management, order delays and out-of-stock situations are reduced, and the order fulfillment rate is improved. The combined effect of these measures enables customers to enjoy more reliable and efficient services, enhancing customer satisfaction and loyalty.

[0056] 4. The logistics supply chain management method and system provided by the present invention can maintain the high adaptability and low risk level of the supply chain by quickly responding to changes in market demand. The method monitors market dynamics and customer needs in real time and adjusts the multi-objective optimization model in a timely manner to ensure that it can meet the ever-changing market demands. At the same time, through diversified supplier selection and risk management strategies, the risks faced by the supply chain are reduced and the stability and reliability of the supply chain are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0058] Figure 1 The present invention is a flow chart of a logistics supply chain management method and system. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] Embodiment 1, as Figure 1 As shown, the present invention provides a logistics supply chain management method, step 1, data collection and preprocessing module: the data collection and preprocessing module includes a data collection unit and a data preprocessing unit, the data collection unit obtains real-time data of each link of the supply chain by collecting multi-layer data, and the data preprocessing unit performs standardization and aggregation processing based on the data collected by the data collection unit;

[0061] Step 2, demand forecasting and preliminary optimization module: forecast market demand based on the data from the data collection and preprocessing module, and generate a demand forecast optimization model. Based on the current supply chain status and predicted market demand, perform preliminary optimization calculations to determine preliminary supply chain decisions.

[0062] Step 3, multi-objective optimization calculation module: construct a multi-objective optimization model based on demand forecasting and preliminary optimization modules to optimize the preliminary supply chain decision;

[0063] Step 4, decision execution and dynamic adjustment: Apply the optimized supply chain decision to the logistics supply chain, monitor the status of the supply chain in real time, based on the latest data and optimization results;

[0064] Step 5, Feedback and continuous optimization: Continuously monitor and evaluate the operational performance of the supply chain based on the decision execution and dynamic adjustment module, and optimize the multi-objective optimization model based on historical data and real-time monitoring results.

[0065] Demand forecasting and supply chain simulation can dynamically manage inventory levels to avoid cost waste caused by excessive or insufficient inventory. In terms of transportation strategy, the system can optimize transportation routes and methods based on real-time traffic data and historical transportation records, reduce transportation time and transportation costs. At the same time, in the optimization of production strategies, the system can flexibly adjust production plans based on real-time changes in market demand and production capacity, maximize the utilization efficiency of equipment and human resources, and avoid overproduction or shortages. Combining the above optimization measures, the system not only significantly reduces the operating costs of the supply chain, but also improves resource utilization and production efficiency, thereby bringing greater economic benefits to the enterprise.

[0066] The data acquisition unit acquires real-time data of each link of the supply chain through multi-layer data collection, where x is set as the supply chain decision variable vector, including inventory level I, transportation status T, transportation speed V and purchase quantity Q;

[0067] The data preprocessing unit performs standardization and aggregation processing based on the data collected by the data collection unit as follows:

[0068] Standardization formula:

[0069]

[0070] Where D 标准 The original data set, even if it is inventory level I, transportation status T, transportation speed V and purchase quantity Q, D 原始 is the standardized data set, μ is D 标准 The mean of 标准 The standard deviation of

[0071] The data sets formed by the data preprocessing unit through multi-level data aggregation are as follows:

[0072]

[0073] where ω i is the data weight at different levels, is the standardized data of the i-th level, D agg To form a multi-level data set, there are a total of n levels of data.

[0074] The multi-objective optimization model is as follows:

[0075]

[0076] Among them, C(x), E(x), S(x), C(x), P(x), R(x), and A(x) represent the total cost function of the supply chain, the overall efficiency function of the supply chain, the customer service level function, the environmental impact function, the risk function of the supply chain, and the adaptability function of the supply chain under given production parameters, respectively. α, β, γ, δ, ∈ are weight coefficients, F(x) is the objective function, and x is the vector of supply chain decision variables.

[0077] The objective function includes the total cost function of the supply chain, the overall efficiency function of the supply chain, the customer service level function, the environmental impact function, the risk function of the supply chain and the adaptability function of the supply chain, which are respectively expressed as C(x), E(x), S(x), C(x), P(x), R(x), and A(x). The specific analysis is as follows:

[0078] The total cost function of the supply chain is: C(x) = C p (Q)+C s (I)+C t (T)+C h (V)

[0079] Among them C p (Q), C s (I) C t (T), C h (V) represents procurement cost, storage cost, transportation cost and labor cost respectively.

[0080] The overall efficiency function formula of the supply chain is further expressed as:

[0081]

[0082] Where E P 、E t are production efficiency and transportation efficiency respectively, λ is the penalty coefficient of transportation delay, and d(T) is the transportation delay time.

[0083] The customer service level function formula is further expressed as:

[0084] S(x)=ω d ·S d (T)+ω O ·S O (Q)

[0085] where ω d ,ω O are the weights of on-time delivery rate and order fulfillment rate, S d , S O They are on-time delivery rate and order fill rate respectively.

[0086] The environmental impact function formula is further expressed as:

[0087] P(x)=θ c ·P c (T)+θ e ·P e (V)

[0088] Where P c , P e They are expressed as carbon emissions and energy consumption respectively;

[0089] The risk function formula of the supply chain is further expressed as:

[0090] R(x)=κ i ·R i (Q)+κ m ·R m (D agg )

[0091] where κ i , κ m Expressed as the weight of each risk type, R i , R m They are respectively expressed as interruption risk and market volatility risk.

[0092] The adaptability function of the supply chain is further expressed as:

[0093]

[0094] Where η is the adjustment coefficient of response speed, M(t) is the market demand forecast function, dM(t) and dQ(x) represent the change rate of market demand and the change rate of production or supply capacity of the supply chain over time t, respectively.

[0095] Based on the cyclic optimization steps, the real-time data collected from each link of the supply chain is detected and processed based on the multi-objective optimization model to form a market demand prediction function M(t), and the prediction results are preprocessed and dynamically adjusted to further optimize the logistics supply chain management system.

[0096] The multi-objective optimization algorithm combines multiple key factors in the supply chain, including the total cost function, the overall efficiency function of the supply chain, the customer service level function, the environmental impact function, the risk function of the supply chain, and the adaptability function of the supply chain. By optimizing these factors, the system can achieve optimal decisions under different operating conditions. The algorithm can balance multiple goals such as cost, efficiency, and service quality in different logistics scenarios to achieve overall optimization of the supply chain. Compared with traditional static planning methods, the dynamic adjustment strategy of the present invention can significantly reduce supply chain interruptions or delays caused by emergencies and improve overall operational efficiency.

[0097] In the process of supply chain optimization, the system optimization cycle steps are:

[0098] S1: Demand forecasting and preprocessing: Based on the multi-objective optimization model, the real-time data collected from each link of the supply chain is detected and processed to form a market demand forecasting function M(t), and the forecast results are preprocessed;

[0099]

[0100] Where M(t) is the prediction function, g(t-τ) is the response function or weight function, which indicates the attenuation of the influence on past data, X(τ) is the observation value at time τ, and M(t) mainly predicts any one of the values ​​of inventory level I, transportation status T, transportation speed V and purchase volume Q, thereby detecting the multi-objective optimization model.

[0101]

[0102] Whether it meets the standards of logistics supply chain management.

[0103] S2: Perform preliminary optimization calculations based on the current supply chain status and demand forecast results;

[0104] based on Determine the current supply chain status and demand forecast results, and further optimize the model, that is, update the initially collected data including inventory level I, transportation status T, transportation speed V, and purchase volume Q;

[0105] S3: Based on the preliminary optimization results, a complex optimization engine is used to perform multi-objective optimization calculations to solve the optimal decision variable x so that the objective function F(X) reaches the minimum value;

[0106] The decision variables x, even if they are inventory level I, transportation status T, transportation speed V and purchase quantity Q, the objective function F(X) is Minimize

[0107] Among them, C(x), E(x), S(x), C(x), P(x), R(x), and A(x) respectively represent the total cost function of the supply chain, the overall efficiency function of the supply chain, the customer service level function, the environmental impact function, the risk function of the supply chain, and the adaptability function of the supply chain under given production parameters. α, β, γ, δ, ∈ are weight coefficients, and F(x) is the objective function.

[0108] S4: Based on the intelligent decision support module, the multi-objective optimization model X0 is dynamically adjusted according to the real-time monitoring data, and it is quickly re-optimized according to the changes in the market and supply chain status.

[0109] The system of the present invention uses advanced optimization algorithms to track order status, transportation progress and production processes in real time to ensure that every link is within the plan. The system can also intelligently allocate resources and adjust transportation and production plans according to the priority and urgency of customer orders to ensure that orders are delivered on time. At the same time, the system has an automated exception handling mechanism. Once a potential delay risk is detected, it can immediately initiate an emergency plan, such as reallocating transportation resources or adjusting the production schedule, so as to avoid order delays to the greatest extent. In addition, by maintaining real-time information communication with customers, the system can inform them of possible delays or changes in advance, thereby enhancing customer trust and satisfaction.

[0110] A logistics supply chain management system is used to implement a logistics supply chain management method, characterized by: including a data acquisition and preprocessing module, a demand forecasting and preliminary optimization module, a multi-objective optimization calculation module, a decision execution and dynamic adjustment module, a feedback and continuous optimization module and an electrical connection.

[0111] Working principle: The staff uses the data acquisition unit in the data acquisition and preprocessing module to obtain real-time data from each link of the supply chain, that is, let x be the supply chain decision variable vector, including inventory level I, transportation status T, transportation speed V and purchase volume Q, and use the data preprocessing unit to perform standardization and aggregation processing based on the data collected by the data acquisition unit. The standardization and aggregation processing are as follows:

[0112] Standardization formula:

[0113]

[0114] Where D 标准 The original data set, even if it is inventory level I, transportation status T, transportation speed V and purchase quantity Q, D 原始 is the standardized data set, μ is D 标准 The mean of 标准 The standard deviation of

[0115] The data set formed by the data preprocessing unit through multi-level data aggregation is specifically as follows:

[0116]

[0117] where ω i is the data weight at different levels, is the standardized data of the i-th level, D agg To form a multi-level data set, which means there are a total of n levels of data,

[0118] Then, the market demand is predicted using the data from the data collection and preprocessing module, and a forecast optimization model for demand is generated. Based on the current supply chain status and the predicted market demand, a preliminary optimization calculation is performed to determine the preliminary supply chain decision. Then, a multi-objective optimization model is constructed based on the demand forecast and preliminary optimization module to optimize the preliminary supply chain decision. The multi-objective optimization model is as follows:

[0119]

[0120] Wherein C(x), E(x), S(x), C(x), P(x), R(x), and A(x) respectively represent the total cost function of the supply chain, the overall efficiency function of the supply chain, the customer service level function, the environmental impact function, the risk function of the supply chain, and the adaptability function of the supply chain under given production parameters, α, β, γ, δ, ∈ are weight coefficients, F(x) is the objective function, and x is the supply chain decision variable vector. Then, based on the optimized supply chain decision, it is applied to the logistics supply chain to monitor the status of the supply chain in real time. Based on the latest data and optimization results, the decision execution and dynamic adjustment module is used to continuously monitor and evaluate the operation effect of the supply chain, and based on historical data and real-time monitoring results, the multi-objective optimization model is optimized. The system of the present invention can quickly analyze market trends and demand changes and make corresponding adjustments by integrating advanced prediction models and flexible scheduling strategies. The system can not only adjust inventory levels and production plans in real time, but also optimize supplier selection and transportation arrangements to cope with sudden changes in the market. In addition, the risk management module of the system can monitor potential risks in the supply chain in real time, such as supplier supply capacity, natural disasters during transportation, etc., and formulate response strategies in advance to reduce the risk of supply chain interruption. Through these features, the system ensures high adaptability of the supply chain, enabling companies to maintain their advantages in a highly competitive market while minimizing operational risks.

[0121] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A logistics supply chain management method, characterized by: The following steps are involved: Step 1, data collection and preprocessing module: the data collection and preprocessing module includes a data collection unit and a data preprocessing unit. The data collection unit acquires real-time data of each link of the supply chain by collecting multi-layer data. The data preprocessing unit performs standardization and aggregation processing based on the data collected by the data collection unit. Step 2, demand forecasting and preliminary optimization module: forecast market demand based on the data from the data collection and preprocessing module, and generate a demand forecast optimization model. Based on the current supply chain status and predicted market demand, perform preliminary optimization calculations to determine preliminary supply chain decisions. Step 3, multi-objective optimization calculation module: construct a multi-objective optimization model based on demand forecasting and preliminary optimization modules to optimize the preliminary supply chain decision; Step 4, decision execution and dynamic adjustment: Apply the optimized supply chain decision to the logistics supply chain, monitor the status of the supply chain in real time, based on the latest data and optimization results; Step 5, the feedback and continuous optimization: continuously monitor and evaluate the operational effect of the supply chain based on the decision execution and dynamic adjustment module, and optimize the multi-objective optimization model based on historical data and real-time monitoring results.

2. A logistics supply chain management method according to claim 1, characterized in that: The data acquisition unit acquires real-time data of each link of the supply chain by collecting multi-layer data, where x is set as the supply chain decision variable vector, including inventory level I, transportation status T, transportation speed V and purchase quantity Q; The data preprocessing unit performs standardization processing and aggregation processing based on the data collected by the data collection unit as follows: Standardization formula: Where D 标准 The original data set, even if it is inventory level I, transportation status T, transportation speed V and purchase quantity Q, D 原始 is the standardized data set, μ is D 标准 The mean of 标准 The standard deviation of The data set formed by the data preprocessing unit through multi-level data aggregation is specifically as follows: where ω i is the data weight at different levels, is the standardized data of the i-th level, D agg To form a multi-level data set, there are a total of n levels of data.

3. A logistics supply chain management method according to claim 1, characterized in that: The multi-objective optimization model is specifically as follows: Among them, C(x), E(x), S(x), C(x), P(x), R(x), and A(x) represent the total cost function of the supply chain, the overall efficiency function of the supply chain, the customer service level function, the environmental impact function, the risk function of the supply chain, and the adaptability function of the supply chain under given production parameters, respectively. α, β, γ, δ, ∈ are weight coefficients, F(x) is the objective function, and x is the vector of supply chain decision variables.

4. A logistics supply chain management method according to claim 3, characterized in that: The objective function includes the total cost function of the supply chain, the overall efficiency function of the supply chain, the customer service level function, the environmental impact function, the risk function of the supply chain and the adaptability function of the supply chain, which are respectively expressed as C(x), E(x), S(x), C(x), P(x), R(x), and A(x). The specific analysis is as follows: The total cost function of the supply chain is: C(x) = C p (Q)+C s (I)+C t (T)+C h (V) Among them C p (Q), C s (I) C t (T), C h (V) represents procurement cost, storage cost, transportation cost and labor cost respectively.

5. A logistics supply chain management method according to claim 3, characterized in that: The overall efficiency function formula of the supply chain is further expressed as: Where E P 、E t are production efficiency and transportation efficiency respectively, λ is the penalty coefficient of transportation delay, and d(T) is the transportation delay time.

6. A logistics supply chain management method according to claim 3, characterized in that: The customer service level function formula is further expressed as: S(x)=ω d ·S d (T)+ω O ·S O (Q) where ω d ,ω O are the weights of on-time delivery rate and order fulfillment rate, S d , S O They are on-time delivery rate and order fill rate respectively.

7. A logistics supply chain management method according to claim 3, characterized in that: The environmental impact function formula is further expressed as: P(x)6θ c ·P c (T)+θ e ·P e (V) Where P c , P e They are expressed as carbon emissions and energy consumption respectively; The risk function formula of the supply chain is further expressed as: R(x)=k i ·R i (Q)+k m ·R m (D agg ) where κ i , κ m Expressed as the weight of each risk type, R i , R m They are respectively expressed as interruption risk and market volatility risk.

8. A logistics supply chain management method according to claim 3, characterized in that: The adaptability function of the supply chain is further expressed as: Where η is the adjustment coefficient of response speed, M(t) is the market demand forecast function, dM(t) and dQ(x) represent the change rate of market demand and the change rate of production or supply capacity of the supply chain over time t, respectively.

9. A logistics supply chain management method according to claim 1, characterized in that: In the process of supply chain optimization, the system optimization cycle steps are as follows: S1: Demand forecasting and preprocessing: Based on the multi-objective optimization model, the real-time data collected from each link of the supply chain is detected and processed to form a market demand forecasting function M(t), and the forecast results are preprocessed: Where M(t) is the prediction function, g(t-τ) is the response function or weight function, which indicates the attenuation of the influence on past data, X(τ) is the observation value at time τ, and M(t) mainly predicts any one of the values ​​of inventory level I, transportation status T, transportation speed V, and purchase volume Q; S2: Perform preliminary optimization calculations based on the current supply chain status and demand forecast results; S3: Based on the preliminary optimization results, a complex optimization engine is used to perform multi-objective optimization calculations to solve the optimal decision variable x so that the objective function F(X) reaches the minimum value; S4: Based on the intelligent decision support module, the multi-objective optimization model X0 is dynamically adjusted according to the real-time monitoring data, and it is quickly re-optimized according to the changes in the market and supply chain status.

10. A logistics supply chain management system, used to implement a logistics supply chain management method according to any one of claims 1 to 9, characterized in that: It includes data collection and preprocessing module, demand forecasting and preliminary optimization module, multi-objective optimization calculation module, decision execution and dynamic adjustment module, feedback and continuous optimization module and electrical connection.

Images