Cooperative processing method based on digital service supply chain

Abstract

The invention relates to the technical field of supply chain analysis, in particular to a supply chain cooperative processing method based on digital service, which comprises the following steps: a central processing unit analyzes demand fluctuation through a trend analysis algorithm to generate a demand fluctuation characteristic model; based on the demand fluctuation characteristic model, a fault-tolerant threshold value of each node is set, and the fault-tolerant threshold value comprises a resource redundancy range, logistics delay tolerance and inventory buffer capacity; on the basis of the demand fluctuation characteristic model and the fault-tolerant threshold value, predicting a future demand peak value and a future demand valley value of the supply chain in real time by using an AI algorithm, and dynamically adjusting resource configuration of each node through resource allocation; and an inter-node cooperative fault-tolerant mechanism is established, so that when a certain node exceeds a fault-tolerant threshold value, the demand pressure is relieved by allocating resources of other nodes. According to the invention, under the condition that the demand fluctuation is relatively large, the system can flexibly respond and rapidly adjust, so that the adaptability and the reaction speed of the supply chain are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of supply chain analysis, and in particular to a collaborative processing method based on a digital service supply chain. Background Art

[0002] Modern supply chains usually involve multiple nodes, including suppliers, manufacturers, warehousing facilities, distribution centers, and retailers. Each node has its own unique needs and resource allocation. However, factors such as demand fluctuations, resource shortages, and logistics delays often lead to instability and inefficiency in supply chain operations. Especially in a market environment with large demand fluctuations, how to ensure the coordination and stability of each link in the supply chain has become a technical problem that needs to be solved urgently.

[0003] In traditional supply chain management, many companies usually rely on historical data to predict demand and allocate resources accordingly. Demand forecasts often have great uncertainty, especially when market demand fluctuates greatly or emergencies occur. Traditional demand forecasting methods cannot respond to drastic fluctuations in demand in real time, leading to problems such as excess or shortage of inventory, waste of transportation resources, etc., thus affecting the overall efficiency of the supply chain and customer satisfaction.

[0004] Currently, the focus is on improving the accuracy of demand forecasting models and optimizing resource management of single nodes. The research on coordination and fault-tolerance mechanisms between nodes in the supply chain is relatively weak. Especially in the face of complex and dynamic demand fluctuations, how to achieve cross-node coordinated deployment through intelligent scheduling is still a technical bottleneck in the field of supply chain management. Summary of the invention

[0005] The present invention provides a collaborative processing method based on a digital service supply chain.

[0006] A collaborative processing method based on a digital service supply chain includes the following steps:

[0007] S1, demand fluctuation data collection and trend analysis: The data collection module monitors the demand changes of each node in the supply chain in real time, including order volume, inventory consumption rate and logistics demand rate, and aggregates the data to the central processing unit. The central processing unit analyzes the demand fluctuation through the trend analysis algorithm and generates a demand fluctuation feature model;

[0008] S2, dynamic setting of fault tolerance threshold: Based on the demand fluctuation characteristic model, the fault tolerance threshold of each node is set. The fault tolerance threshold includes resource redundancy range, logistics delay tolerance and inventory buffer, so as to ensure that the supply chain can flexibly allocate resources under demand fluctuations and avoid resource waste;

[0009] S3, flexible resource allocation and adaptive optimization: Based on the demand fluctuation characteristic model and fault tolerance threshold, AI algorithms are used to predict the future demand peaks and valleys of the supply chain in real time. Resource allocation is dynamically adjusted through resource allocation, including increasing or decreasing inventory and allocating spare transportation resources to ensure that each node meets demand during peak demand periods and avoids excessive redundancy during low demand periods.

[0010] S4, collaborative fault-tolerant mechanism between nodes: Establish a collaborative fault-tolerant mechanism between nodes, so that when a node exceeds the fault-tolerant threshold, the demand pressure can be alleviated by deploying resources from other nodes. The collaborative fault-tolerant mechanism between nodes is monitored and scheduled in real time by the central processing unit, including cross-node inventory sharing, logistics resource reallocation and flexible scheduling of human resources.

[0011] Optionally, the data acquisition module in S1 specifically includes:

[0012] The order volume data is obtained in real time through the order management system of each node, and the order generation, cancellation and change information is directly synchronized to the data acquisition module to provide the latest order volume change information. The order volume is expressed as O t , where t is the current time;

[0013] Extract inventory data from the inventory management system of each node and calculate the inventory consumption rate R t , the inventory consumption rate is generated based on the change of the initial inventory quantity and the real-time outbound data;

[0014] The logistics demand data is obtained through the logistics scheduling system, including the real-time status of the transportation task, the planned logistics volume and the actual delivery volume information, and the information is summarized in the data acquisition module to ensure the timeliness and accuracy of the logistics demand data, and then the logistics demand rate Q is calculated. t .

[0015] Optionally, the central processing unit in S1 analyzes the demand fluctuation by a trend analysis algorithm to generate a demand fluctuation characteristic model, specifically including:

[0016] S11, demand fluctuation feature extraction:

[0017] S111, fluctuation amplitude: The fluctuation amplitude is measured by calculating the standard deviation of order volume, inventory consumption rate and logistics demand rate to obtain the order volume fluctuation amplitude feature Amplitude O , inventory consumption rate fluctuation amplitude characteristics R , Logistics demand rate fluctuation amplitude characteristics Q ;

[0018] S112, Periodicity characteristics: Use wavelet transform to analyze the periodicity of order volume, inventory consumption rate and logistics demand rate, and identify the periodicity of demand fluctuations, including the periodicity characteristics of order volume O , Periodic characteristics of inventory consumption rate R , Periodic characteristics of logistics demand rate Q ;

[0019] S113, trend characteristics: use the moving average method to extract the long-term trend of the data. The trend characteristics of the order volume are T O , the inventory consumption rate trend characteristic is T R , the trend characteristic of logistics demand rate is T Q ;

[0020] S12, Construction of demand fluctuation characteristic model: Based on the fluctuation amplitude, periodicity and trend characteristics extracted above, a demand fluctuation characteristic model M is constructed. d , demand fluctuation characteristic model M d Including the key characteristics of supply chain demand in the process of fluctuation, demand fluctuation characteristic model M d Expressed as:

[0021] M d =

[0022] {Amplitude O ,Amplitude R ,Amplitude Q ,Period O ,Period R ,Period Q ,T O ,T R ,T Q}.

[0023] Optionally, the setting of the resource redundancy range includes: O and the periodic characteristics of inventory consumption rate R , and set a resource redundancy range to ensure that each node can provide sufficient redundant resources to meet demand when the fluctuation range is large or during periodic demand peaks; according to the order volume fluctuation range, set a redundancy coefficient to measure the intensity of demand fluctuations and the amount of redundant resources. The amount of redundant resources should be able to meet the scheduling capabilities of each supply chain node when the order volume surges. By analyzing the periodic characteristics of the inventory consumption rate, the peak and trough periods of inventory consumption can be identified, and redundant resource allocation can be increased during periodic peak periods to avoid supply interruptions due to insufficient inventory during peak demand periods.

[0024] Optionally, the setting of the logistics delay tolerance includes: based on the periodic characteristics of the logistics demand rate Period Q and logistics demand rate trend characteristics T Q , preset a delay tolerance range for the peak period of logistics demand. The logistics delay tolerance reflects the supply chain's tolerance for transportation delays, so as to provide buffer space for each node when the logistics demand surges, and reduce the impact of logistics delays on the operation of the supply chain; the logistics delay tolerance needs to take into account the fluctuations in logistics demand during periods of large demand fluctuations (such as promotional seasons or holidays). When logistics demand surges during periods of large demand fluctuations, sufficient time windows should be reserved to cope with transportation delays or other time bottlenecks in the supply chain. The tolerance is adjusted according to the intensity of demand fluctuations: during periods of surging demand, increase the delay tolerance to avoid supply chain disruptions due to logistics delays.

[0025] Optionally, the setting of the inventory buffer includes: R and the long-term trend characteristics of inventory consumption rate T R , set the inventory buffer of each node. The inventory buffer ensures that the node inventory is sufficient when the demand increases suddenly, so as to avoid the occurrence of inventory depletion or shortage, and ensure the smooth operation of the supply chain; the fluctuation range of inventory consumption rate reflects the range of changes in inventory consumption, and the long-term trend characteristics of inventory consumption rate indicate the overall change direction of inventory consumption. The purpose of setting the inventory buffer is to ensure that when the demand increases suddenly, each node has enough inventory to meet the demand, so as to avoid supply interruption or inventory shortage;

[0026] During peak demand periods (e.g., when orders surge or consumption increases), there should be enough buffer stock to cope with unexpected demand. During low demand periods (e.g., seasonal low demand periods), inventory redundancy should be reduced to avoid inventory backlogs.

[0027] Optionally, S3 includes establishing and training a demand forecasting model. By collecting historical data, the demand forecasting model combines order volume, inventory consumption rate and logistics demand factors, and uses a neural network to predict future demand fluctuations in the supply chain, including peak and valley values ​​of demand. After the demand forecasting model is trained, demand data of each node is collected in real time and input into the forecasting model to forecast demand for a period of time in the future, and predict the peak and valley values ​​of demand in the short term in the future.

[0028] Optionally, the input variables of the neural network-based demand forecasting model include: t , R t , Q t , the output variables include Forecast demand for the future time step t+k (1-3 days), focusing on the peak and valley values ​​of demand;

[0029] The structure of the neural network is divided into input layer, hidden layer and output layer, where:

[0030] Input layer: includes order quantity, inventory consumption rate and logistics demand rate at time step t as input features;

[0031] Hidden layer: multiple neurons, using ReLU activation function for nonlinear mapping;

[0032] Output layer: Output predicted demand A linear activation function is used to predict demand peaks and valleys.

[0033] Optionally, after the demand forecasting model is trained, the demand peak and demand valley are extracted:

[0034] Peak demand forecast: In the forecast results, select the forecast value The largest time point is the peak demand point: Represents the maximum demand that will occur during the forecast period of future demand;

[0035] Demand valley forecast: In the forecast results, select the forecast value The minimum time point is taken as the demand valley value: Represents the minimum demand that occurs within the forecast period of future demand.

[0036] Optionally, the S4 specifically includes:

[0037] S41, fault tolerance threshold monitoring and identification: real-time monitoring of the demand status of each node, including order volume, inventory consumption rate and logistics demand. When the demand of a node exceeds the set fault tolerance threshold (such as exceeding the set resource redundancy range or logistics delay tolerance), the central processing unit will automatically identify that the node has entered a high-load state and start the collaborative fault tolerance mechanism;

[0038] S42, resource allocation decision generation: The central processing unit generates a resource allocation decision based on the global demand fluctuation data and the resource status between nodes. The decision includes:

[0039] Inventory sharing: When the inventory of a node is lower than the preset fault tolerance threshold, the required inventory is transferred from other nodes with sufficient inventory through the cross-node inventory sharing mechanism;

[0040] Logistics resource reallocation: When the logistics demand at a certain node exceeds the tolerance range, the idle transportation resources of other nodes are allocated to nodes with high demand pressure through the cross-node logistics resource reallocation mechanism.

[0041] Beneficial effects of the present invention:

[0042] The present invention, by establishing a resource allocation mechanism based on a demand fluctuation characteristic model and AI prediction, realizes the dynamic response of the supply chain in the face of demand fluctuations, especially during peak and trough periods of demand, and can adjust the resource allocation of each node in real time to avoid the problem of excess or shortage of inventory. In this way, the overall operational efficiency of the supply chain is greatly improved, and resource utilization is optimized, ensuring that the system can respond flexibly and adjust quickly in the case of large fluctuations in demand, thereby improving the adaptability and response speed of the supply chain.

[0043] The present invention proposes a node-to-node collaborative fault-tolerance mechanism that monitors and dispatches resources in real time through a central processing unit. When a node exceeds the fault-tolerance threshold, it can automatically deploy resources from other nodes to alleviate demand pressure. This mechanism covers cross-node inventory sharing, logistics resource redistribution, and human resource scheduling, significantly enhancing the elasticity and stability of the supply chain. It combines resource allocation with demand fluctuation prediction, allowing the system to quickly fill resource gaps through the collaborative cooperation of other nodes when the node pressure is too high, ensuring the stable operation of the supply chain and avoiding the negative impact of a single node overload on the overall supply chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 A schematic diagram of a collaborative processing method according to an embodiment of the present invention;

[0046] Figure 2 Schematic diagram of the inter-node collaborative fault tolerance mechanism according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0048] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0049] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0050] like Figure 1-Figure 2 As shown, a collaborative processing method based on a digital service supply chain includes the following steps:

[0051] S1, demand fluctuation data collection and trend analysis: The data collection module monitors the demand changes of each node in the supply chain in real time, including order volume, inventory consumption rate and logistics demand rate, and aggregates the data to the central processing unit. The central processing unit analyzes the demand fluctuation through the trend analysis algorithm and generates a demand fluctuation feature model;

[0052] S2, dynamic setting of fault tolerance threshold: Based on the demand fluctuation characteristic model, the fault tolerance threshold of each node is set. The fault tolerance threshold includes resource redundancy range, logistics delay tolerance and inventory buffer to ensure that the supply chain can flexibly allocate resources under demand fluctuations while avoiding resource waste;

[0053] S3, flexible resource allocation and adaptive optimization: Based on the demand fluctuation characteristic model and fault tolerance threshold, AI algorithms are used to predict the future demand peaks and valleys of the supply chain in real time. Resource allocation is dynamically adjusted through resource allocation, including increasing or decreasing inventory and allocating spare transportation resources to ensure that each node meets demand during peak demand periods and avoids excessive redundancy during low demand periods.

[0054] S4, collaborative fault-tolerance mechanism between nodes: Establish a collaborative fault-tolerance mechanism between nodes so that when a node exceeds the fault-tolerance threshold, the demand pressure can be alleviated by deploying resources from other nodes. The collaborative fault-tolerance between nodes is monitored and scheduled in real time by the central processing unit, including cross-node inventory sharing, logistics resource redistribution, and flexible scheduling of human resources.

[0055] The data acquisition module in S1 specifically includes:

[0056] The order volume data is obtained in real time through the order management system of each node, and the order generation, cancellation and change information is directly synchronized to the data acquisition module to provide the latest order volume change information. The order volume is expressed as O t , where t is the current time;

[0057] Extract inventory data from the inventory management system of each node and calculate the inventory consumption rate R t The inventory consumption rate is generated based on the changes in the initial inventory quantity and the real-time outbound data to ensure accurate update of the inventory status. The inventory consumption rate R t It is expressed as: Among them, S0 is the initial inventory, S t is the real-time inventory at the current moment, indicating the percentage reduction of the initial inventory;

[0058] The logistics demand data is obtained through the logistics scheduling system, including the real-time status of the transportation task, the planned logistics volume and the actual delivery volume information, and the information is summarized in the data acquisition module to ensure the timeliness and accuracy of the logistics demand data, and then the logistics demand rate Q is calculated. t , expressed as:

[0059] Among them, D plan The current planned logistics demand is (the total amount of goods planned to be shipped), D actual is the actual shipment volume. This formula reflects the gap between planned demand and actual shipment. When the logistics demand satisfaction rate is lower than the threshold, the data collection module can issue an alarm to adjust the logistics resource allocation in time to avoid supply chain interruption.

[0060] The central processing unit in S1 analyzes the demand fluctuation through the trend analysis algorithm, and generates the demand fluctuation characteristic model, which specifically includes:

[0061] S11, demand fluctuation feature extraction:

[0062] S111, fluctuation amplitude: The fluctuation amplitude is measured by calculating the standard deviation of order volume, inventory consumption rate and logistics demand rate to obtain the order volume fluctuation amplitude feature Amplitude O , inventory consumption rate fluctuation amplitude characteristics R , Logistics demand rate fluctuation amplitude characteristics Q , for example, the fluctuation range of order volume can be expressed as: Among them, O i is the order quantity at each moment, is the average value of the order quantity. Similarly, the fluctuation range of the inventory consumption rate and the logistics demand rate can be calculated;

[0063] S112, Periodicity characteristics: Use wavelet transform to analyze the periodicity of order volume, inventory consumption rate and logistics demand rate, and identify the periodicity of demand fluctuations, including the periodicity characteristics of order volume O , Periodic characteristics of inventory consumption rate R , Periodic characteristics of logistics demand rate Q ;

[0064] Take the order volume cycle analysis as an example. For example, the wavelet transform is used to analyze the periodicity of the order volume. Through the wavelet transform, different frequency components in the order volume data can be identified, and then significant periodic patterns can be found. Suppose the order volume data is O t (t=1,2,...,N), the specific steps of wavelet transform are as follows:

[0065] 1. Select the mother wavelet: Use the Mor let wavelet function, which is defined as:

[0066] Where ω0 is the center frequency of the wavelet;

[0067] 2. Calculate the wavelet coefficients: For each scale s and position t, the wavelet transform coefficient W(s,t) can be obtained by t Convolution with the mother wavelet function yields:

[0068] Among them, s controls the scale (frequency component) of the wavelet, larger s values ​​correspond to low-frequency components, and smaller s values ​​correspond to high-frequency components.

[0069] 3. Identify periodicity: By drawing a wavelet energy diagram or wavelet power spectrum, observe the energy density at different scales s. If the energy is concentrated at a certain scale (i.e. frequency), the data corresponding to this scale has significant periodicity. Let the scale corresponding to the energy-intensive area be s * , then the corresponding period P is approximately: P = s * ·Δt, where Δt is the time step. The period P obtained by wavelet transform is the periodic feature of the order volume Period O .

[0070] Similarly, the cyclical characteristics of inventory consumption rates and logistics demand rates can be calculated.

[0071] S113, trend characteristics: use the moving average method to extract the long-term trend of the data. The trend characteristics of the order volume are T O , the inventory consumption rate trend characteristic is T R, the trend characteristic of logistics demand rate is T Q ;

[0072] Taking the order volume trend analysis as an example, the moving average method is used to extract the long-term trend of the order volume. Through moving average processing, the short-term fluctuations in the order volume are eliminated and the long-term trend characteristics are retained. The order volume data is O t (t=1,2,...,N), its long-term trend T t Obtained by:

[0073] 1. Select the window size: Set a window size w, and choose a larger w value (one week or one month) to filter out short-term fluctuations and retain only long-term trends;

[0074] 2. Calculate the moving average: For each time t, use the moving average formula with a window size of w to calculate the long-term trend T t : This formula represents the average value of the order volume in the window [t-w+1,t], that is, the long-term trend at the current time t, obtained by moving average processing. t Sequence, which is the long-term trend characteristic of order volume T O , the moving average can effectively remove short-term fluctuations, making the long-term growth or decline trend of order volume clearer, thereby more accurately reflecting the changing trend of supply chain demand.

[0075] Similarly, the trend characteristics of inventory consumption rate and logistics demand rate can be calculated.

[0076] S12, Construction of demand fluctuation characteristic model: Based on the fluctuation amplitude, periodicity and trend characteristics extracted above, a demand fluctuation characteristic model M is constructed. d , demand fluctuation characteristic model M d Including the key characteristics of supply chain demand in the process of fluctuation, demand fluctuation characteristic model M d Expressed as:

[0077] M d =

[0078] {Amplitude O ,Amplitude R ,Amplitude Q ,Period O ,Period R ,Period Q ,T O ,T R ,T Q}.

[0079] The setting of resource redundancy range includes: AmplitudeO and the periodic characteristics of inventory consumption rate R , and set a resource redundancy range to ensure that each node can provide sufficient redundant resources to meet demand when the fluctuation range is large or during periodic demand peaks; according to the order volume fluctuation range, set a redundancy coefficient to measure the intensity of demand fluctuations and the amount of redundant resources. The amount of redundant resources should be able to meet the scheduling capabilities of each supply chain node when the order volume surges. Therefore, the setting of redundant resources needs to reflect the range of demand fluctuations and ensure the continuity of the supply chain, so as not to cause resource shortages due to sudden increases in orders. In addition, by analyzing the periodic characteristics of inventory consumption rate, the peak and trough periods of inventory consumption are identified, and redundant resource allocation is increased during periodic peak periods to avoid supply interruptions due to insufficient inventory during peak demand periods.

[0080] The setting of logistics delay tolerance includes: Based on the periodic characteristics of logistics demand rate Q and logistics demand rate trend characteristics T Q , preset a delay tolerance range for the peak period of logistics demand. The logistics delay tolerance reflects the supply chain's tolerance for transportation delays, so as to provide buffer space for each node when the logistics demand surges, and reduce the impact of logistics delays on the operation of the supply chain; the logistics delay tolerance needs to take into account the fluctuations in logistics demand during periods of large demand fluctuations (such as promotional seasons or holidays). When logistics demand surges during periods of large demand fluctuations, sufficient time windows should be reserved to cope with transportation delays or other time bottlenecks in the supply chain. The tolerance is adjusted according to the intensity of demand fluctuations: during periods of surging demand, increase the delay tolerance to avoid supply chain disruptions due to logistics delays.

[0081] Through this approach, logistics tolerance not only takes into account short-term demand fluctuations, but also combines long-term logistics demand trends, so that the system can maintain a certain degree of flexibility in a changing environment and ensure the stable operation of the supply chain.

[0082] The setting of inventory buffer includes: Amplitude R and the long-term trend characteristics of inventory consumption rate T R , set the inventory buffer of each node. The inventory buffer ensures that the node inventory is sufficient when the demand increases suddenly, so as to avoid the occurrence of inventory depletion or shortage, and ensure the smooth operation of the supply chain; the fluctuation range of inventory consumption rate reflects the range of changes in inventory consumption, and the long-term trend characteristics of inventory consumption rate indicate the overall change direction of inventory consumption. The purpose of setting the inventory buffer is to ensure that when the demand increases suddenly, each node has enough inventory to meet the demand, so as to avoid supply interruption or inventory shortage;

[0083] During peak demand periods (e.g., when orders surge or consumption increases), there should be enough buffer stock to cope with unexpected demand. During low demand periods (e.g., seasonal low demand periods), inventory redundancy should be reduced to avoid inventory backlogs.

[0084] In addition, by analyzing the long-term trend of inventory consumption, we can identify long-term changing patterns in inventory demand, such as seasonal demand changes or long-term growth trends, and adjust the configuration of inventory buffers accordingly to ensure that in the event of future demand changes, each node in the supply chain can still meet the changing inventory demand.

[0085] S3 includes the establishment and training of demand forecasting models. Through the collection of historical data, the demand forecasting model combines order volume, inventory consumption rate and logistics demand factors, and uses neural networks to predict future demand fluctuations in the supply chain, including peak and valley values ​​of demand. After the demand forecasting model is trained, the demand data of each node is collected in real time and input into the forecasting model to forecast demand for a period of time in the future, and predict the peak and valley values ​​of demand in the short term in the future.

[0086] The input variables of the demand forecasting model based on neural network include: t , R t , Q t , the output variables include Forecast demand for the future time step t+k (1-3 days), focusing on the peak and valley values ​​of demand;

[0087] The structure of the neural network is divided into input layer, hidden layer and output layer, where:

[0088] Input layer: includes order quantity, inventory consumption rate and logistics demand rate at time step t as input features;

[0089] Hidden layer: multiple neurons, using ReLU activation function for nonlinear mapping;

[0090] Output layer: Output predicted demand A linear activation function is used to predict demand peaks and valleys.

[0091] The training process includes the following steps:

[0092] 1. Data preparation: Collect historical data, including order volume O t , Inventory consumption rate R t , logistics demand rate Q t , and standardize or normalize the data to ensure that the model performance is not affected by large scale differences during training.

[0093] The division of the training set and the validation set uses 80% of the time series data as the training set and the remaining 20% ​​as the validation set.

[0094] 2. Model training: Use back propagation to train the neural network, with the goal of minimizing the predicted value With real demand t+k The error between , the loss function is the mean square error (MSE): in, is the actual demand of the ith sample, It is the demand for neural network prediction.

[0095] 3.Adam optimizer is used to adjust the network weights to minimize the loss function.

[0096] 4. Tuning during training: Optimize the model by adjusting hyperparameters such as the number of network layers, the number of neurons in each layer, and the learning rate.

[0097] After the demand forecasting model is trained, the peak and valley values ​​of demand are extracted:

[0098] Peak demand forecast: In the forecast results, select the forecast value The largest time point is the peak demand point: Represents the maximum demand that will occur during the forecast period of future demand;

[0099] Demand valley forecast: In the forecast results, select the forecast value The minimum time point is taken as the demand valley value: Represents the minimum demand that occurs within the forecast period of future demand.

[0100] Once the peak and valley values ​​of demand are predicted, the resource configuration of each node can be dynamically adjusted based on these prediction results:

[0101] During peak demand:

[0102] Increase inventory: Based on predicted demand peaks, increase inventory levels to ensure demand is met.

[0103] Allocate backup transportation resources: Based on demand peak forecasts, increase the allocation of transportation resources to ensure timely delivery during high demand periods.

[0104] During demand valleys:

[0105] Reduce inventory: Reduce inventory levels to avoid excess inventory and reduce waste of resources.

[0106] Optimize transportation resources: reduce the allocation of spare transportation resources and avoid idle transportation resources.

[0107] S4 specifically includes:

[0108] S41, fault tolerance threshold monitoring and identification: real-time monitoring of the demand status of each node, including order volume, inventory consumption rate and logistics demand. When the demand of a node exceeds the set fault tolerance threshold (such as exceeding the set resource redundancy range or logistics delay tolerance), the central processing unit will automatically identify that the node has entered a high-load state and start the collaborative fault tolerance mechanism;

[0109] S42, resource allocation decision generation: The central processing unit generates a resource allocation decision based on the global demand fluctuation data and the resource status between nodes. The decision includes:

[0110] Inventory sharing: When the inventory of a node is lower than the preset fault tolerance threshold, the required inventory is transferred from other nodes with sufficient inventory through the cross-node inventory sharing mechanism;

[0111] Logistics resource reallocation: When the logistics demand of a certain node exceeds the tolerance range, the idle transportation resources of other nodes are allocated to the nodes with high demand pressure through the cross-node logistics resource reallocation mechanism;

[0112] The central processing unit monitors the status changes of each node in real time, including order processing status, inventory consumption rate, logistics resource usage and human resource allocation. Through dynamic scheduling, it executes resource allocation instructions in real time to ensure that cross-node resources can be flexibly allocated when node demand fluctuates, thereby ensuring the overall stability of the supply chain.

[0113] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0114] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A collaborative processing method based on a digital service supply chain, characterized in that: The following steps are involved: S1, demand fluctuation data collection and trend analysis: The data collection module monitors the demand changes of each node in the supply chain in real time, including order volume, inventory consumption rate and logistics demand rate, and aggregates the data to the central processing unit. The central processing unit analyzes the demand fluctuation through the trend analysis algorithm and generates a demand fluctuation feature model; S2, dynamic setting of fault tolerance threshold: based on the demand fluctuation characteristic model, set the fault tolerance threshold of each node, which includes resource redundancy range, logistics delay tolerance and inventory buffer; S3, flexible resource allocation and adaptive optimization: Based on the demand fluctuation characteristic model and fault tolerance threshold, AI algorithms are used to predict the future demand peaks and valleys of the supply chain in real time. Resource allocation is dynamically adjusted through resource allocation, including increasing or decreasing inventory and allocating spare transportation resources to ensure that each node meets demand during peak demand periods and avoids excessive redundancy during low demand periods. S4, collaborative fault-tolerant mechanism between nodes: Establish a collaborative fault-tolerant mechanism between nodes, so that when a node exceeds the fault-tolerant threshold, the demand pressure can be alleviated by deploying resources from other nodes. The collaborative fault-tolerant mechanism between nodes is monitored and scheduled in real time by the central processing unit, including cross-node inventory sharing, logistics resource reallocation and flexible scheduling of human resources.

2. A collaborative processing method based on a digital service supply chain according to claim 1, characterized in that: The data acquisition module in S1 specifically includes: The order volume data is obtained in real time through the order management system of each node, and the order generation, cancellation and change information is directly synchronized to the data acquisition module to provide the latest order volume change information. The order volume is expressed as O t , where t is the current time; Extract inventory data from the inventory management system of each node and calculate the inventory consumption rate R t , the inventory consumption rate is generated based on the change of the initial inventory quantity and the real-time outbound data; The logistics demand data is obtained through the logistics scheduling system, including the real-time status of the transportation task, the planned logistics volume and the actual delivery volume information, and then the logistics demand rate Q is calculated. t .

3. The collaborative processing method based on digital service supply chain according to claim 1 is characterized in that: The central processing unit in S1 analyzes the demand fluctuation by using a trend analysis algorithm to generate a demand fluctuation characteristic model, which specifically includes: S11, demand fluctuation feature extraction: S111, fluctuation amplitude: The fluctuation amplitude is measured by calculating the standard deviation of order volume, inventory consumption rate and logistics demand rate to obtain the order volume fluctuation amplitude feature Amplitude O , inventory consumption rate fluctuation amplitude characteristics R , Logistics demand rate fluctuation amplitude characteristics Q ; S112, Periodicity characteristics: Use wavelet transform to analyze the periodicity of order volume, inventory consumption rate and logistics demand rate, and identify the periodicity of demand fluctuations, including the periodicity characteristics of order volume O , Periodic characteristics of inventory consumption rate R , Periodic characteristics of logistics demand rate Q ; S113, trend characteristics: use the moving average method to extract the long-term trend of the data. The trend characteristics of the order volume are T O , the inventory consumption rate trend characteristic is T R , the trend characteristic of logistics demand rate is T Q ; S12, Construction of demand fluctuation characteristic model: Based on the fluctuation amplitude, periodicity and trend characteristics extracted above, a demand fluctuation characteristic model M is constructed. d , demand fluctuation characteristic model M d Including the key characteristics of supply chain demand in the process of fluctuation, demand fluctuation characteristic model M d Expressed as: M d ＝ {Amplitude O ,Amplitude R ,Amplitude Q ,Period O ,Period R ,Period Q ,T O ,T R ,T Q }。 4. A collaborative processing method based on a digital service supply chain according to claim 3, characterized in that: The setting of the resource redundancy range includes: O and the periodic characteristics of inventory consumption rate R , and set a resource redundancy range to ensure that each node can provide sufficient redundant resources to meet demand when the fluctuation range is large or during periodic demand peaks; according to the order volume fluctuation range, set a redundancy coefficient to measure the intensity of demand fluctuations and the amount of redundant resources. The amount of redundant resources should be able to meet the scheduling capabilities of each supply chain node when the order volume surges. By analyzing the periodic characteristics of the inventory consumption rate, the peak and trough periods of inventory consumption can be identified, and redundant resource allocation can be increased during periodic peak periods to avoid supply interruptions due to insufficient inventory during peak demand periods.

5. A collaborative processing method based on a digital service supply chain according to claim 4, characterized in that: The setting of the logistics delay tolerance includes: based on the periodic characteristics of the logistics demand rate Period Q and logistics demand rate trend characteristics T Q , preset a delay tolerance range for the peak period of logistics demand. The logistics delay tolerance reflects the supply chain's tolerance for transportation delays; the logistics delay tolerance needs to take into account the fluctuations in logistics demand during periods of large demand fluctuations. When logistics demand surges during periods of large demand fluctuations, sufficient time windows should be reserved to cope with transportation delays or other time bottlenecks in the supply chain. The tolerance is adjusted according to the intensity of demand fluctuations: during periods of surging demand, increase the delay tolerance to avoid supply chain disruptions due to logistics delays.

6. A collaborative processing method based on a digital service supply chain according to claim 5, characterized in that: The setting of the inventory buffer includes: R and the long-term trend characteristics of inventory consumption rate T R , set the inventory buffer of each node. The inventory buffer ensures that the node has sufficient inventory when the demand increases suddenly; the inventory consumption rate fluctuation amplitude characteristics reflect the range of changes in inventory consumption, and the long-term trend characteristics of the inventory consumption rate indicate the overall change direction of inventory consumption. The purpose of setting the inventory buffer is to ensure that when the demand increases suddenly, each node has sufficient inventory to meet the demand and avoid supply interruption or inventory shortage; During peak demand periods, there should be sufficient buffer stock to cope with unexpected demand, while during trough demand, inventory redundancy is reduced to avoid inventory backlogs.

7. The collaborative processing method based on digital service supply chain according to claim 2 is characterized in that: The S3 includes establishing and training a demand forecasting model. By collecting historical data, the demand forecasting model combines order volume, inventory consumption rate and logistics demand factors, and uses a neural network to predict future demand fluctuations in the supply chain, including peak and valley values ​​of demand. After the demand forecasting model is trained, the demand data of each node is collected in real time and input into the forecasting model to forecast demand for a period of time in the future, and predict the peak and valley values ​​of demand in the short term in the future.

8. The collaborative processing method based on digital service supply chain according to claim 7 is characterized in that: The input variables of the demand forecasting model based on neural network include: t , R t , Q t , the output variables include Forecast demand for the future time step t+k, paying attention to the peak and valley values ​​of demand; The structure of the neural network is divided into input layer, hidden layer and output layer, where: Input layer: includes order quantity, inventory consumption rate and logistics demand rate at time step t as input features; Hidden layer: multiple neurons, using ReLU activation function for nonlinear mapping; Output layer: Output predicted demand A linear activation function is used to predict demand peaks and valleys.

9. The collaborative processing method based on digital service supply chain according to claim 8 is characterized in that: After the demand forecasting model is trained, the peak and valley values ​​of demand are extracted: Peak demand forecast: In the forecast results, select the forecast value The largest time point is the peak demand point: Represents the maximum demand that will occur during the forecast period of future demand; Demand valley forecast: In the forecast results, select the forecast value The minimum time point is taken as the demand valley value: Represents the minimum demand that occurs within the forecast period of future demand.

10. The collaborative processing method based on digital service supply chain according to claim 1 is characterized in that: The S4 specifically includes: S41, fault tolerance threshold monitoring and identification: real-time monitoring of the demand status of each node, including order volume, inventory consumption rate and logistics demand. When the demand of a node exceeds the set fault tolerance threshold, the central processing unit will automatically identify that the node has entered a high-load state and start the collaborative fault tolerance mechanism; S42, resource allocation decision generation: The central processing unit generates a resource allocation decision based on the global demand fluctuation data and the resource status between nodes. The decision includes: Inventory sharing: When the inventory of a node is lower than the preset fault tolerance threshold, the required inventory is transferred from other nodes with sufficient inventory through the cross-node inventory sharing mechanism; Logistics resource reallocation: When the logistics demand at a certain node exceeds the tolerance range, the idle transportation resources of other nodes are allocated to nodes with high demand pressure through the cross-node logistics resource reallocation mechanism.

Images