Staggered period management method, system and device based on building material supply chain and storage medium

Abstract

The invention relates to a lag management method based on a building material supply chain, and the method comprises the steps: collecting real-time logistics data through an Internet of Things sensor disposed at a transportation tool and a storage node, and the real-time logistics data comprises the position coordinates of the transportation tool and the storage staying time of building materials; a delay risk map is constructed, nodes of the delay risk map represent logistics entity attributes of a supply chain link, and a side relation comprises a historical delay probability, a real-time congestion coefficient and an associated party responsibility relation; based on the lagging risk map, calculating lagging risk values of all links of building material supply through a time sequence prediction model; and when the risk value exceeds a preset threshold value, generating a multi-stage early warning signal, and sending a prompt to a user according to the multi-stage early warning signal.

Description

Technical Field

[0001] This application relates to the field of building materials supply chain management, and in particular to a method, system, equipment and storage medium for managing lag time based on the building materials supply chain. Background Technology

[0002] The building materials supply chain involves multiple stages such as transportation, warehousing, and loading / unloading. Delay risks often arise due to issues like traffic congestion, warehouse backlogs, and low efficiency in collaboration among responsible parties. Current technologies for delay management largely rely on manual experience or static data analysis, resulting in information lag. Logistics status depends on manual reporting, making it impossible to monitor the real-time location of transport vehicles and the extent of warehouse backlogs. Furthermore, the division of responsibilities is often ambiguous, and the responsibilities of related parties (carriers and warehouse operators) are not structured and modeled, leading to disputes over the apportionment of delay costs.

[0003] Therefore, it is necessary to provide a method, system, equipment, and storage medium for managing lag time based on the building materials supply chain. Summary of the Invention

[0004] This application provides a method, system, and storage medium for demurrage management based on the building materials supply chain, in order to solve the problems in the prior art where demurrage management relies heavily on manual experience or static data analysis, resulting in information lag, reliance on manual reporting of logistics status, inability to perceive the location of transportation vehicles and the degree of backlog in storage in real time, and unclear division of responsibilities, with unstructured modeling of the responsibilities of related parties (carriers and warehouses), leading to disputes over the apportionment of demurrage costs.

[0005] Firstly, this application provides a method for managing demurrage in the building materials supply chain, the method comprising:

[0006] Real-time logistics data is collected by IoT sensors deployed on transportation vehicles and warehousing nodes. The real-time logistics data includes the location coordinates of transportation vehicles and the dwell time of building materials in the warehouse.

[0007] Construct a delinquency risk map, wherein the nodes of the delinquency risk map represent the logistics entity attributes of the supply chain links, and the edge relationships include historical delinquency probability, real-time congestion coefficient and related party responsibility relationship;

[0008] Based on the aforementioned lag risk map, the lag risk value of each link in the building material supply is calculated using a time-series prediction model;

[0009] When the risk value exceeds a preset threshold, a multi-level warning signal is generated, and a prompt is issued to the user based on the multi-level warning signal.

[0010] In some embodiments, the method further includes:

[0011] Calculation of demurrage costs based on the multi-level early warning signals;

[0012] Based on the warning level of the multi-level early warning signal, obtain the billing rule corresponding to the warning level;

[0013] A cost-sharing scheme is generated based on the billing rules and the responsible party identification.

[0014] In some embodiments, the method further includes:

[0015] The map weights are updated based on the multi-level early warning signals;

[0016] Adjusting the transportation route of building materials based on dynamic path optimization algorithm;

[0017] Based on the adjusted building material transportation routes and adjusted warehousing allocation strategies, the edge relationships of the demurrage risk graph are updated.

[0018] In some embodiments, updating the edge relationships of the lag risk graph includes:

[0019] Based on the adjusted building material transportation routes, the historical demurrage frequency of each route is obtained;

[0020] Based on the adjusted warehousing allocation strategy, obtain the current backlog duration and current backlog amount of each warehouse building material;

[0021] The edge relationships of the lag risk graph are updated based on the historical standard processing time, the historical lag frequency, the current backlog duration, and the current backlog amount.

[0022] In some embodiments, updating the edge relationships of the lag risk graph based on historical standard processing time, historical lag frequency, current backlog duration, and current backlog amount includes:

[0023] The lag risk weight is determined by the following formula, and the weights of the edge relationships in the lag risk graph are updated based on the lag risk weight.

[0024]

[0025] Where i represents the starting node of the edge, j represents the ending node of the edge, and W ij (t) represents the lag risk weight from node i to node j, F represents the historical lag frequency, T is the industry standard processing time, Q1 represents the current backlog (tons), Q max t represents the maximum allowable capacity of the warehouse, α and β represent the current backlog duration, α and β are weighting coefficients used to balance the impact of historical data and real-time status, and γ is a time sensitivity coefficient used to represent the amplification effect of backlog time on risk.

[0026] In some embodiments, the dynamic path optimization algorithm employs a reinforcement learning algorithm, and its state space definition includes:

[0027] State variables include demurrage risk level, number of available alternative routes, and transport resource utilization rate;

[0028] Action set, including route switching, multimodal transport combination, and warehouse priority adjustment;

[0029] The reward function is shown in the following formula:

[0030] R = -(ω1·ΔT + ω2·ΔC)

[0031] Where R is the reward function value, ΔT is the expected shortening of the dwell time, ΔC is the change in action execution cost, and ω1 and ω2 are preset weight coefficients.

[0032] In some embodiments, calculating the lag risk values ​​for each stage of building material supply based on the lag risk map using a time-series forecasting model includes:

[0033] Based on the aforementioned delay risk map, the historical on-time rate of each transportation route and the storage capacity utilization curve of the aforementioned storage nodes are obtained;

[0034] Obtain real-time traffic flow forecast data;

[0035] The historical on-time rate, the warehouse capacity utilization curve of the storage node, and the traffic flow prediction data are input into the time series prediction model to determine the lag risk value of the building material supply in various environments.

[0036] Secondly, this application provides a demurrage management system based on the building materials supply chain, the system comprising:

[0037] The data acquisition module is used to collect real-time logistics data through IoT sensors deployed on transportation vehicles and warehousing nodes. The real-time logistics data includes the location coordinates of the transportation vehicles and the storage time of building materials.

[0038] The graph construction module is used to construct a delinquency risk graph, wherein the nodes of the delinquency risk graph represent the logistics entity attributes of the supply chain links, and the edge relationships include historical delinquency probability, real-time congestion coefficient and related party responsibility relationships.

[0039] The risk value calculation module is used to calculate the lag risk value of each link in the supply of building materials based on the lag risk map and through a time series prediction model.

[0040] The alert module is used to generate multi-level warning signals when the risk value exceeds a preset threshold, and to issue alerts to the user based on the multi-level warning signals.

[0041] Thirdly, an electronic device is provided, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0042] Memory, used to store computer programs;

[0043] When a processor executes a program stored in memory, it implements the steps of the method for managing lag time based on the building materials supply chain as described in any embodiment of the first aspect.

[0044] Fourthly, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the demurrage management method based on the building materials supply chain as described in any embodiment of the first aspect.

[0045] Compared with the prior art, the above-mentioned technical solutions provided in this application have the following advantages: (1) Traditional methods rely on offline data or human experience, which cannot capture changes in logistics status in real time (such as sudden congestion or warehouse backlog), resulting in a lag in risk assessment. This application embodiment collects data such as the location of transportation vehicles and the duration of warehouse stay in real time through IoT sensors, and dynamically quantifies risks by combining them with a demurrage risk map, which can realize data-driven dynamic demurrage risk monitoring; (2) The division of responsibilities relies on manual verification of contract terms, which is inefficient and prone to disputes; the cost calculation rules are static and cannot be adapted to dynamic scenarios. This application embodiment automatically matches billing rules based on multi-level early warning signals, and generates a cost sharing scheme by combining the responsible party identification, thus realizing automated demurrage responsibility determination and cost sharing. Attached Figure Description

[0046] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 A flowchart illustrating a method for managing demurrage based on the building materials supply chain, provided as an embodiment of this application;

[0049] Figure 2 This is a flowchart of a method for updating the edge relationships of a lag risk graph provided in an embodiment of this application;

[0050] Figure 3This is an exemplary flowchart provided in the embodiments of this application for calculating the lag risk value of each stage of building material supply using a time-series prediction model;

[0051] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0053] Figure 1 This is a flowchart illustrating a method for managing delays in the building materials supply chain, provided as an embodiment of this application. In some embodiments, Figure 1 The process shown can be performed by electronic devices, such as... Figure 1 As shown, the process may include the following operations:

[0054] Step 101: Collect real-time logistics data by deploying IoT sensors on transportation vehicles and warehousing nodes. The real-time logistics data includes the location coordinates of the transportation vehicles and the storage time of building materials.

[0055] Transportation vehicles are physical equipment used to transport building materials, including trucks, ships, and railway vehicles. Examples include cement trucks, sand and gravel ships, and mineral powder railway cars.

[0056] Storage nodes are the physical locations or facilities for storing building materials, such as warehouses, port yards, and temporary storage areas. For example, a finished product warehouse of a cement plant or a sand and gravel transshipment yard of a port.

[0057] Internet of Things (IoT) sensors are devices deployed in transportation vehicles and warehouse nodes to collect physical data in real time, including location sensors, temperature sensors, and weight sensors. Examples include GPS locators (collecting location data), RFID tags (recording warehouse dwell time), and pressure sensors (monitoring the stacking status of building materials).

[0058] Real-time logistics data is digital information that reflects the status of the logistics process, dynamically acquired through sensors. Examples include the current location of a truck (longitude 116.40°, latitude 39.90°) and the duration of cement's stay in a warehouse (72 hours).

[0059] The location coordinates of a transportation vehicle are the latitude and longitude data obtained through GPS or the BeiDou system. For example, the real-time location of truck A is (longitude 120.20°, latitude 30.27°).

[0060] The storage time for building materials refers to the length of time building materials spend in the storage facility from entry to exit. For example, a batch of mineral powder may have stayed in a port yard for 48 hours.

[0061] In some embodiments, GPS sensors can be installed on transport vehicles (such as trucks) to upload location coordinates to a cloud database in real time. RFID scanning devices can be deployed at warehouse nodes to record the entry and exit times of building materials and calculate their dwell time.

[0062] Step 102: Construct a delinquency risk map, wherein the nodes of the delinquency risk map represent the logistics entity attributes of the supply chain links, and the edge relationships include historical delinquency probability, real-time congestion coefficient, and related party responsibility relationships.

[0063] The demurrage risk map is a topological structure built on a graph database that reflects the demurrage risk at each stage of the supply chain. It includes nodes (logistics entities) and edges (relationships). For example, in the graph database, the node is "Port A" and the edge is "the transportation route from Port A to construction site B".

[0064] Nodes (logistics entity attributes) are physical entities (such as transportation vehicles, warehouses, and construction sites) and their attributes (such as capacity, location, and type) in the supply chain. For example, warehouse D has the attributes {capacity: 5000 tons, type: cement storage}.

[0065] Edge relationships are the connections and quantitative indicators between nodes, including historical lag probability, the frequency of lag on a certain route due to congestion or accidents in the past; real-time congestion coefficient, the degree of congestion calculated based on current traffic data (0-1 standardized value); and related party responsibility relationships, the division of responsibilities among various parties in the supply chain (such as transporters and warehouse providers).

[0066] In some embodiments, during the construction of a knowledge graph, for node construction, flow entity attributes can be extracted from an enterprise resource database (such as the "resource list" in a resource distribution map) and stored as graph database nodes. For edge relationships, the historical delay probability can be obtained by statistically analyzing the number of delays for a certain route over the past year divided by the total number of transport trips. Real-time congestion coefficients can be obtained by acquiring and normalizing traffic data through a traffic API (such as Gaode Maps). The liability relationships between related parties can be obtained by extracting liability clauses from a contract management system and mapping them to edge attributes.

[0067] Step 103: Based on the aforementioned lag risk map, calculate the lag risk value of each link in the building material supply through a time-series prediction model.

[0068] Time series forecasting models are algorithmic models that predict future trends based on time series data, such as LSTM and ARIMA models.

[0069] The demurrage risk value is a numerical value (e.g., 0-100 points) that quantifies the likelihood of demurrage in a supply chain segment, taking into account historical data, real-time status, and external factors (weather, policies).

[0070] In some embodiments, attributes of nodes and edges (such as historical lag probability and real-time congestion coefficient) can be extracted from the lag risk map, and a time series model can be trained using historical data. Input features include time series location data, warehouse dwell time, and weather data. The attribute data of nodes and edges extracted from the map are input into the model, and the lag risk score of each stage is output.

[0071] Step 104: When the risk value exceeds a preset threshold, a multi-level warning signal is generated, and a prompt is issued to the user based on the multi-level warning signal.

[0072] Multi-level warning signals are warning levels (such as low, medium, and high) based on risk values, each corresponding to a different handling strategy. For example, a risk value <50 is "green" (normal), 50-75 is "yellow" (attention), and >75 is "red" (emergency).

[0073] Preset thresholds are pre-defined risk thresholds used to trigger different levels of alerts. For example, the threshold for a yellow alert is 50, and the threshold for a red alert is 75.

[0074] In some embodiments, a risk threshold can be set according to business rules (such as a red alert threshold of 75). If the risk value exceeds the threshold, a corresponding warning signal and handling suggestions are generated (such as "Red alert: Route J is severely congested, it is recommended to switch to the alternative route K").

[0075] User notifications can be sent to relevant personnel via platform push notifications, SMS, or email.

[0076] In some embodiments, while generating multi-level early warning signals, related demurrage cost calculations can also be performed. For example, a cost-sharing scheme can be calculated using the method shown in the following embodiments.

[0077] S10, calculate the demurrage cost based on the multi-level early warning signal.

[0078] Demurrage charges are calculated based on the demurrage time and the responsible party, taking into account additional costs incurred due to logistics delays (such as warehousing overtime fees and transportation default fees). For example, if a batch of cement is detained at the port for 3 days, triggering a red alert, demurrage charges are calculated at 500 yuan per day.

[0079] In some embodiments, when the warning signal associated with a node or edge in the lag risk map is upgraded to a preset level (such as a red warning), the cost calculation process is automatically triggered.

[0080] S11, Based on the warning level of the multi-level warning signal, obtain the billing rule corresponding to the warning level.

[0081] Warning levels are a grading standard for multi-level early warning signals, used to distinguish the handling strategies under different risk scenarios. For example, red corresponds to "emergency handling", yellow corresponds to "monitoring and observation", and green corresponds to "no intervention required".

[0082] Billing rules are predefined fee calculation logics, including late payment rates, liability sharing ratios, and methods for calculating penalties. For example, a red alert costs 300 yuan per hour, with the responsible party bearing 80% of the cost; a yellow alert costs 150 yuan per hour, with the responsible party bearing 50% of the cost.

[0083] In some embodiments, a corresponding rule can be matched from the billing rule database based on the alert level (e.g., red).

[0084] S12, Generate a cost-sharing scheme based on the billing rules and the responsible party identifier.

[0085] The responsible party identifier is a unique code or label that identifies the responsible party in the supply chain and is used to determine who is responsible for cost sharing.

[0086] A cost-sharing scheme is a cost allocation plan generated based on billing rules and the division of responsibilities, clearly defining the amount each party needs to bear and the payment method. For example, the transportation company bears 70% of the demurrage costs (3,500 yuan), and the cargo owner bears 30% (1,500 yuan).

[0087] In some embodiments, the responsible party identifier (such as the carrier stipulated in the contract) can be extracted from the edge relationships of the demurrage risk graph. The cost to be borne by each responsible party is calculated according to the sharing ratio in the billing rules.

[0088] Figure 2 This is a flowchart illustrating a method for updating the edge relationships of a lag risk graph, as provided in an embodiment of this application. In some embodiments, Figure 2 The process shown can be performed by electronic devices, such as... Figure 2 As shown, the process may include the following operations:

[0089] Step 201: Trigger map weight update based on the multi-level early warning signal.

[0090] Graph weight updates adjust the weight parameters (such as historical lag probability and real-time congestion coefficient) of edge relationships in the lag risk graph to reflect the latest risk status. For example, if a traffic accident causes the real-time congestion coefficient of a certain road segment to rise from 0.5 to 0.9, a weight update is triggered.

[0091] In some embodiments, risk scenarios corresponding to multi-level warning signals can be analyzed (e.g., a red warning indicates severe congestion on a certain road segment). A weight update strategy is selected based on the warning level: for a red warning, the congestion coefficient weight is significantly increased (e.g., +0.3), and the historical lag probability weight is decreased (e.g., -10%); for a yellow warning, the weight is adjusted moderately (e.g., congestion coefficient +0.1); for a green warning, the weight remains unchanged.

[0092] Graph updates refer to modifying weight parameters in the edge relationships of the lag risk graph.

[0093] Step 202: Adjust the transportation route of building materials based on the dynamic path optimization algorithm.

[0094] Dynamic route optimization algorithms are algorithms that combine real-time data (such as road conditions and warehouse capacity) to calculate the optimal transportation route, such as Dijkstra's algorithm, genetic algorithms, or reinforcement learning models.

[0095] Building material transportation routes are the transportation routes planned from the starting point (such as a mine) to the destination (such as a construction site), including nodes along the way (such as transit warehouses and ports).

[0096] In some embodiments, real-time weight parameters (such as congestion coefficient), warehouse node capacity, and transportation vehicle status can be extracted from the demurrage risk map. Shortest path optimization is then performed, using the real-time congestion coefficient as the edge weight, to calculate the minimum time path. Multi-objective optimization is then performed by combining cost (freight charges), time (estimated arrival time), and risk (demurrage probability) scores, and the optimized route is output and synchronized to the logistics scheduling system.

[0097] In some embodiments, the dynamic path optimization algorithm employs a reinforcement learning algorithm, and its state space definition includes:

[0098] State variables include demurrage risk level, number of available alternative routes, and transportation resource utilization rate. The demurrage risk level is the current route risk level (e.g., high, medium, low) calculated based on the demurrage risk map. The number of available alternative routes is the number of switchable alternative routes in the current transportation scenario, derived from the results of dynamic route optimization in claim 3. The transportation resource utilization rate is the real-time resource utilization rate of transportation vehicles or warehousing nodes (e.g., truck occupancy rate, warehouse capacity utilization rate).

[0099] The action set includes route switching, multimodal transport combinations, and warehouse priority adjustments. The action set is a set of decision-making operations that an agent can choose to change the current logistics status to reduce demurrage risk. Route switching is switching from the current transport route to another available route (the alternative route generated in claim 3). Multimodal transport combinations are hybrid transport schemes that combine multiple modes of transport (such as road + rail + waterway). Warehouse priority adjustments dynamically modify the order of use or allocation ratio of warehouse nodes to optimize inventory turnover efficiency.

[0100] The reward function is shown in the following formula (1):

[0101] R=-(ω1·ΔT+ω2·ΔC)(1)

[0102] Where R is the reward function value, ΔT is the expected reduction in dwell time, ΔC is the change in action execution cost, and ω1 and ω2 are preset weighting coefficients. The expected reduction in dwell time is the anticipated reduction in dwell time (in hours) after executing the action, calculated based on path parameters from the dwell time risk map. The change in action execution cost is the increase or decrease in comprehensive costs (such as transportation fees, warehousing fees, and penalties) after executing the action. The preset weighting coefficients are parameters used to balance the impact of time and cost and can be set according to business needs.

[0103] Step 203: Update the edge relationships of the demurrage risk graph based on the adjusted building material transportation routes and the adjusted warehousing allocation strategy.

[0104] Warehouse allocation strategies are rules for dynamically allocating building material storage locations based on changes in transportation routes, such as prioritizing the use of low-risk warehouses and balancing inventory capacity.

[0105] In some embodiments, new paths and warehouse allocation results can be mapped to graph nodes (such as adding a transit warehouse F) and edges (such as "transit warehouse F → construction site G").

[0106] Edge relationship updates include adding edges and deleting / reducing the weight of edges. Adding edges: Adding edge relationships corresponding to new paths (e.g., "transfer warehouse F → construction site G"), and initializing the weight parameters (real-time congestion coefficient = 0.2). Deleting / reducing the weight of edges: Removing or reducing the weight of high-risk edges (e.g., marking the edge of the original path "port B → construction site C" as "disabled").

[0107] In some embodiments, updating the edge relationships of the lag risk graph may include the following operations.

[0108] S20, based on the adjusted building material transportation routes, obtain the historical demurrage frequency of each route.

[0109] The adjusted building material transportation routes are new transportation routes generated by a dynamic route optimization algorithm, used to replace high-risk routes.

[0110] Historical lag frequency is the number of times a path has experienced lag within a certain period in the past, and it is used to quantify the reliability of a path.

[0111] In some embodiments, a unique identifier (such as a route ID) for the adjusted route can be extracted from the logistics database, and the number of delays can be counted by route ID in the historical delay record database. The delay frequency can then be normalized into a probability (such as delay probability = number of delays / total number of transports).

[0112] S21, based on the adjusted warehousing allocation strategy, obtain the current backlog duration and current backlog amount of each warehousing building material.

[0113] The adjusted warehousing allocation strategy is a dynamically optimized building material storage plan designed to balance inventory and transportation efficiency. For example, sand and gravel originally planned to be stored at port B are instead allocated to transit warehouse D.

[0114] The current backlog duration refers to the length of time building materials remain in the warehouse beyond the planned storage time. For example, if a batch of cement was planned to stay for 24 hours but has actually stayed for 48 hours, the backlog duration is 24 hours.

[0115] Current backlog is the amount of building materials in a storage node that exceeds the planned inventory capacity. For example, transit warehouse D has a maximum capacity of 5,000 tons, currently stores 6,000 tons, and has a backlog of 1,000 tons.

[0116] In some embodiments, inventory data can be acquired in real time through a warehouse management system (WMS) or IoT sensors.

[0117] S22, based on the historical standard processing time, the historical lag frequency, the current backlog duration, and the current backlog amount, update the edge relationships of the lag risk graph.

[0118] Historical standard processing time is the average time for a warehouse node to process building material inbound and outbound operations under normal conditions. For example, the historical standard processing time for transit warehouse D is 2 hours per batch.

[0119] In some embodiments, the calculation and update can be performed according to a preset calculation method. For example, the new lag probability = original historical lag probability × (1 + backlog impact coefficient); the backlog impact coefficient = (backlog amount / planned inventory threshold) × (backlog duration / historical standard processing time); the congestion coefficient = original real-time congestion coefficient + (backlog amount / maximum capacity) × weight. Finally, the calculated parameters can be written into the edge attributes of the lag risk graph.

[0120] In some embodiments, updating the edge relationships of the lag risk graph based on historical standard processing time, historical lag frequency, current backlog duration and current backlog amount includes: determining the lag risk weight using the following formula (2), and updating the weights of the edge relationships of the lag risk graph based on the lag risk weight;

[0121]

[0122] Where i represents the starting node of the edge, j represents the ending node of the edge, and W ij (t) represents the lag risk weight from node i to node j, F represents the historical lag frequency, T is the industry standard processing time, Q1 represents the current backlog (tons), Q max t represents the maximum allowable capacity of the warehouse, α and β represent the current backlog duration, α and β are weighting coefficients used to balance the impact of historical data and real-time status, and γ is a time sensitivity coefficient used to represent the amplification effect of backlog time on risk.

[0123] Figure 3 This is an exemplary flowchart illustrating the calculation of lag risk values ​​at each stage of building material supply using a time-series forecasting model, as provided in embodiments of this application. In some embodiments, Figure 3 The process shown can be performed by electronic devices, such as... Figure 3 As shown, the process may include the following operations.

[0124] Step 301: Based on the demurrage risk map, obtain the historical on-time rate of each transportation route and the warehouse capacity utilization curve of the storage node.

[0125] Historical on-time rate is the probability that a transportation route will complete its transportation task on time within a historical period.

[0126] The warehouse capacity utilization curve reflects the change in inventory capacity at a storage node over time, with time (e.g., days / hours) on the horizontal axis and utilization rate on the vertical axis. For example, the warehouse capacity utilization curve of transit warehouse D shows that the peak utilization rate reaches 95% at 8:00 AM every day, and the lowest point at night is 60%.

[0127] In some embodiments, the "historical on-time rate" attribute of the transportation route can be extracted from the edge relationships of the lag risk graph, and the inventory time series can be extracted from the historical monitoring data of the storage nodes to generate the storage capacity utilization curve.

[0128] Step 302: Obtain real-time traffic flow prediction data.

[0129] Real-time traffic flow forecast data is obtained through traffic monitoring systems or third-party APIs and is used to predict road / waterway traffic flow in the future, including congestion index, average vehicle speed, etc.

[0130] In some embodiments, traffic data APIs (such as Amap and the Ministry of Transport's real-time traffic interface) can be called to obtain traffic flow predictions for the target transportation route.

[0131] Step 303: Input the historical on-time rate, the warehouse capacity utilization curve of the storage node, and the traffic flow prediction data into the time series prediction model to determine the lag risk value of each link in the building material supply.

[0132] In some embodiments, the historical on-time rate, the warehouse capacity utilization curve of the storage node, and the traffic flow prediction data can be directly input into the time series prediction model. Alternatively, the historical on-time rate, the warehouse capacity utilization curve of the storage node, and the traffic flow prediction data can be input into the time series prediction model for feature extraction, and then the extracted features can be input into the time series prediction model.

[0133] In this embodiment, a real-time data-driven intelligent management and control system for the building materials supply chain is constructed by integrating IoT sensors, demurrage risk maps, time-series prediction models, and reinforcement learning algorithms. This system can dynamically collect multi-dimensional logistics data such as the location of transport vehicles and the duration of storage stays. It accurately assesses demurrage risks by combining historical on-time rates, traffic flow predictions, and warehouse capacity utilization curves. Based on dynamic route optimization and multimodal transport combinations, it proactively avoids high-risk links and simultaneously realizes automatic determination of demurrage responsibility, intelligent cost allocation, and flexible allocation of warehousing resources. This significantly reduces the incidence of logistics demurrage, shortens transportation time, and optimizes overall costs. At the same time, it minimizes human intervention through fully automated decision-making across the entire chain, comprehensively improving the resilience and responsiveness of the supply chain.

[0134] Based on the same inventive concept, this application also provides a demurrage management system based on the building materials supply chain, the system comprising:

[0135] The data acquisition module is used to collect real-time logistics data through IoT sensors deployed on transportation vehicles and warehousing nodes. The real-time logistics data includes the location coordinates of the transportation vehicles and the storage time of building materials.

[0136] The graph construction module is used to construct a delinquency risk graph, wherein the nodes of the delinquency risk graph represent the logistics entity attributes of the supply chain links, and the edge relationships include historical delinquency probability, real-time congestion coefficient and related party responsibility relationships.

[0137] The risk value calculation module is used to calculate the lag risk value of each link in the supply of building materials based on the lag risk map and through a time series prediction model.

[0138] The alert module is used to generate multi-level warning signals when the risk value exceeds a preset threshold, and to issue alerts to the user based on the multi-level warning signals.

[0139] like Figure 4 As shown in the figure, this application provides an electronic device, including a processor 111, a communication interface 112, a memory 113, and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114.

[0140] Memory 113 is used to store computer programs;

[0141] In one embodiment of this application, when the processor 111 executes the program stored in the memory 113, it implements the method for managing the lag time based on the building materials supply chain provided in any of the foregoing method embodiments, including:

[0142] Real-time logistics data is collected by IoT sensors deployed on transportation vehicles and warehousing nodes. The real-time logistics data includes the location coordinates of transportation vehicles and the dwell time of building materials in the warehouse.

[0143] Construct a delinquency risk map, wherein the nodes of the delinquency risk map represent the logistics entity attributes of the supply chain links, and the edge relationships include historical delinquency probability, real-time congestion coefficient and related party responsibility relationship;

[0144] Based on the aforementioned lag risk map, the lag risk value of each link in the building material supply is calculated using a time-series prediction model;

[0145] When the risk value exceeds a preset threshold, a multi-level warning signal is generated, and a prompt is issued to the user based on the multi-level warning signal.

[0146] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the demurrage management method based on the building materials supply chain provided in any of the foregoing method embodiments.

[0147] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0148] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for managing lag time based on the building materials supply chain, characterized in that, The method includes: Real-time logistics data is collected by IoT sensors deployed on transportation vehicles and warehousing nodes. The real-time logistics data includes the location coordinates of transportation vehicles and the dwell time of building materials in the warehouse. Construct a delinquency risk map, wherein the nodes of the delinquency risk map represent the logistics entity attributes of the supply chain links, and the edge relationships include historical delinquency probability, real-time congestion coefficient and related party responsibility relationship; Based on the aforementioned lag risk map, the lag risk value of each link in the building material supply is calculated using a time-series prediction model; When the risk value exceeds a preset threshold, a multi-level warning signal is generated, and a prompt is issued to the user based on the multi-level warning signal.

2. The method according to claim 1, characterized in that, The method further includes: Calculation of demurrage costs based on the multi-level early warning signals; Based on the warning level of the multi-level early warning signal, obtain the billing rule corresponding to the warning level; A cost-sharing scheme is generated based on the billing rules and the responsible party identification.

3. The method according to claim 1, characterized in that, The method further includes: The map weights are updated based on the multi-level early warning signals; Adjusting the transportation route of building materials based on dynamic path optimization algorithm; Based on the adjusted building material transportation routes and adjusted warehousing allocation strategies, the edge relationships of the demurrage risk graph are updated.

4. The method according to claim 3, characterized in that, The updating of the edge relationships in the lag risk graph includes: Based on the adjusted building material transportation routes, the historical demurrage frequency of each route is obtained; Based on the adjusted warehousing allocation strategy, obtain the current backlog duration and current backlog amount of each warehouse building material; The edge relationships of the lag risk graph are updated based on the historical standard processing time, the historical lag frequency, the current backlog duration, and the current backlog amount.

5. The method according to claim 4, characterized in that, The step of updating the edge relationships of the lag risk graph based on historical standard processing time, historical lag frequency, current backlog duration, and current backlog amount includes: The lag risk weight is determined by the following formula, and the weights of the edge relationships in the lag risk graph are updated based on the lag risk weight. Where i represents the starting node of the edge, j represents the ending node of the edge, and W ij (t) represents the lag risk weight from node i to node j, F represents the historical lag frequency, T is the industry standard processing time, Q1 represents the current backlog (tons), Q max t represents the maximum allowable capacity of the warehouse, α and β represent the current backlog duration, α and β are weighting coefficients used to balance the impact of historical data and real-time status, and γ is a time sensitivity coefficient used to represent the amplification effect of backlog time on risk.

6. The method according to claim 3, characterized in that, The dynamic path optimization algorithm employs reinforcement learning, and its state space definition includes: State variables include demurrage risk level, number of available alternative routes, and transport resource utilization rate; Action set, including route switching, multimodal transport combination, and warehouse priority adjustment; The reward function is shown in the following formula: R = -(ω1·ΔT + ω2·ΔC) Where R is the reward function value, ΔT is the expected shortening of the dwell time, ΔC is the change in action execution cost, and ω1 and ω2 are preset weight coefficients.

7. The method according to claim 1, characterized in that, The calculation of lag risk values ​​for each stage of building material supply based on the lag risk map and using a time-series prediction model includes: Based on the aforementioned delay risk map, the historical on-time rate of each transportation route and the storage capacity utilization curve of the aforementioned storage nodes are obtained; Obtain real-time traffic flow forecast data; The historical on-time rate, the warehouse capacity utilization curve of the storage node, and the traffic flow prediction data are input into the time series prediction model to determine the lag risk value of the building material supply in various environments.

8. A demurrage management system based on the building materials supply chain, characterized in that, The system includes: The data acquisition module is used to collect real-time logistics data through IoT sensors deployed on transportation vehicles and warehousing nodes. The real-time logistics data includes the location coordinates of the transportation vehicles and the storage time of building materials. The graph construction module is used to construct a delinquency risk graph, wherein the nodes of the delinquency risk graph represent the logistics entity attributes of the supply chain links, and the edge relationships include historical delinquency probability, real-time congestion coefficient and related party responsibility relationships. The risk value calculation module is used to calculate the lag risk value of each link in the building material supply based on the lag risk map and through a time series prediction model. The alert module is used to generate multi-level warning signals when the risk value exceeds a preset threshold, and to issue alerts to the user based on the multi-level warning signals.

9. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; When a processor executes a program stored in memory, it implements the steps of the demurrage management method based on the building materials supply chain as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the demurrage management method based on the building materials supply chain as described in any one of claims 1-7.

Images