Cross-domain cooperative scheduling method, device and equipment of power grid material supply chain, storage medium and program product

Abstract

The invention relates to a cross-domain cooperative scheduling method, device and equipment of a power grid material supply chain, a storage medium and a program product, and relates to the technical field of logistics transportation. The material scheduling efficiency can be improved, and the resource scheduling deviation can be reduced. The method comprises the following steps: according to power grid material supply chain data, constructing a three-dimensional supply and demand state matrix model comprising a supply capability dimension, a transportation timeliness dimension and a demand intensity dimension; generating a supply-demand matching relation table according to the demand prediction data of the power grid enterprise, the productivity data of the supplier and the material allocation instruction of the logistics service provider; according to the supply and demand matching relation table and the parameters of each dimension in the three-dimensional supply and demand state matrix model, a material supply gap type is predicted through a gradient lifting decision tree model, and a cross-domain cooperative scheduling scheme is generated according to the material supply gap type; and feeding back the cross-domain cooperative scheduling scheme to the physical supply chain system, executing the cross-domain cooperative scheduling scheme to obtain a corresponding execution result, and updating the execution result to the three-dimensional supply and demand state matrix model.

Description

Technical Field

[0001] The present application relates to the field of logistics and transportation technology, and in particular to a cross-domain collaborative scheduling method, apparatus, computer equipment, computer-readable storage medium, and computer program product for a power grid material supply chain. Background Art

[0002] Currently, power grid material supply chain management mainly builds a dynamic warehouse monitoring system based on the Internet of Things perception layer, adopts RFID (Radio Frequency Identification) and sensor networks for inventory management; applies path optimization algorithms and GPS (Global Positioning System) positioning technology in the logistics link to improve distribution efficiency; and develops a material scheduling model based on BIM (Building Information Modeling) for construction scenarios to match project progress.

[0003] However, traditional management methods lack cross-organizational collaboration mechanisms. Key decisions such as demand forecasting, resource allocation, and exception handling remain primarily independent departmental operations. Blockchain technology is used solely for data storage and lacks intelligent rules for multi-party collaboration. This model is prone to supply and demand mismatches, delayed emergency response, and redundant resource allocation. This makes it difficult to optimize resources across the entire supply chain, especially when responding to sudden demand fluctuations in power grid projects, leading to significant deviations in resource scheduling. Summary of the Invention

[0004] Based on this, it is necessary to provide a cross-domain collaborative scheduling method, device, computer equipment, computer-readable storage medium and computer program product for the power grid material supply chain to address the above technical problems.

[0005] In a first aspect, the present application provides a cross-domain collaborative scheduling method for a power grid material supply chain, comprising:

[0006] Obtaining power grid material supply chain data, and constructing a three-dimensional supply and demand status matrix model based on the power grid material supply chain data, including supply capacity dimensions, transportation timeliness dimensions, and demand intensity dimensions; the power grid material supply chain data includes material inventory data, logistics trajectory data, and project progress data;

[0007] Obtaining demand forecast data from power grid companies, production capacity data from suppliers, and material allocation instructions from logistics service providers, and generating a supply and demand matching relationship table based on the demand forecast data, production capacity data, and material allocation instructions;

[0008] According to the supply-demand matching relationship table and the parameters of each dimension in the three-dimensional supply-demand status matrix model, the type of material supply gap is predicted by a gradient boosting decision tree model, and a cross-domain collaborative scheduling plan is generated according to the type of material supply gap;

[0009] The cross-domain collaborative scheduling solution is fed back to the physical supply chain system and executed to obtain corresponding execution results, and the execution results are synchronously updated to the three-dimensional supply and demand status matrix model.

[0010] In one embodiment, the material supply gap type is predicted by a gradient boosting decision tree model based on the supply and demand matching relationship table and the parameters of each dimension in the three-dimensional supply and demand status matrix model, including:

[0011] According to the supply and demand matching relationship table and the parameters of each dimension in the three-dimensional supply and demand status matrix model, time series features and spatial correlation features are constructed through feature engineering; the time series features and the spatial correlation features are input into the gradient boosting decision tree model, and the gradient boosting decision tree model is used to predict the supply capacity index, transportation reliability score and dynamic demand intensity value; if the supply capacity index is lower than the supply capacity threshold, the material supply gap type is determined to be a production gap; if the transportation reliability score is lower than the transportation timeliness threshold, the material supply gap type is determined to be a transportation gap; if the mutation rate of the dynamic demand intensity value exceeds the mutation rate threshold, the material supply gap type is determined to be a demand mutation gap.

[0012] In one embodiment, generating a cross-domain collaborative scheduling solution according to the material supply gap type includes:

[0013] According to the type of material supply gap, the corresponding objective function and constraint conditions are determined; the power grid material supply chain data, the objective function and the constraint conditions are input into the three-dimensional supply and demand state matrix model for solution to obtain the optimal solution; and the cross-domain collaborative scheduling plan is generated according to the optimal solution.

[0014] In one embodiment, determining the corresponding objective function and constraint conditions according to the type of material supply gap includes:

[0015] If the material supply gap type is the production gap, the objective function is determined based on maximizing capacity utilization and minimizing production switching costs, and the constraint conditions are determined based on capacity allocation constraints, demand coverage constraints, and production preparation time constraints; if the material supply gap type is the transportation gap, the objective function is determined based on minimizing transportation delay risks and balancing transportation loads, and the constraint conditions are determined based on path feasibility constraints, vehicle capacity constraints, and transit time window constraints; if the material supply gap type is the demand mutation gap, the objective function is determined based on maximizing arrival timeliness and minimizing emergency procurement premiums, and the constraint conditions are determined based on safety stock call constraints, emergency response time constraints, and supplier switching restrictions.

[0016] In one embodiment, generating a supply-demand matching relationship table based on the demand forecast data, the production capacity data, and the material allocation instructions includes:

[0017] The demand forecast data, the production capacity data, and the material allocation instructions are stored in a blockchain, and the authenticity of the demand forecast data, the production capacity data, and the material allocation instructions is verified in the blockchain through a smart contract; if the authenticity verification passes, the demand forecast data, the production capacity data, and the material allocation instructions are integrated and organized to obtain the supply and demand matching relationship table.

[0018] In one embodiment, the method further comprises:

[0019] When a deviation is detected between the actual execution data and the cross-domain collaborative scheduling plan, the correlation factors of the abnormal event are traced based on the three-dimensional supply and demand status matrix model; the cross-domain collaborative scheduling plan is optimized based on the correlation factors to obtain an optimized cross-domain collaborative scheduling plan;

[0020] Feeding back the cross-domain collaborative scheduling plan to the physical supply chain system and executing it to obtain the corresponding execution result includes: feeding back the optimized cross-domain collaborative scheduling plan to the physical supply chain system and executing it to obtain the corresponding execution result.

[0021] In a second aspect, the present application also provides a cross-domain collaborative scheduling device for a power grid material supply chain, including:

[0022] A model building module is used to obtain power grid material supply chain data and construct a three-dimensional supply and demand status matrix model based on the power grid material supply chain data, including supply capacity, transportation timeliness, and demand intensity dimensions; the power grid material supply chain data includes material inventory data, logistics trajectory data, and project progress data;

[0023] A table collating module is used to obtain the demand forecast data of the power grid enterprise, the production capacity data of the supplier, and the material allocation instructions of the logistics service provider, and generate a supply and demand matching relationship table based on the demand forecast data, the production capacity data, and the material allocation instructions;

[0024] A solution generation module is used to predict the type of material supply gap through a gradient boosting decision tree model based on the supply and demand matching relationship table and the parameters of each dimension in the three-dimensional supply and demand status matrix model, and generate a cross-domain collaborative scheduling solution based on the material supply gap type;

[0025] The result updating module is used to feed back the cross-domain collaborative scheduling solution to the physical supply chain system and execute it to obtain the corresponding execution result, and synchronously update the execution result to the three-dimensional supply and demand status matrix model.

[0026] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0027] Obtain power grid material supply chain data, and construct a three-dimensional supply and demand status matrix model including supply capacity dimension, transportation timeliness dimension and demand intensity dimension based on the power grid material supply chain data; the power grid material supply chain data includes material inventory data, logistics trajectory data and project progress data; obtain demand forecast data of power grid enterprises, production capacity data of suppliers and material allocation instructions of logistics service providers, and generate a supply and demand matching relationship table based on the demand forecast data, the production capacity data and the material allocation instructions; based on the supply and demand matching relationship table and the parameters of each dimension in the three-dimensional supply and demand status matrix model, predict the type of material supply gap through a gradient boosting decision tree model, and generate a cross-domain collaborative scheduling plan based on the type of material supply gap; feed back the cross-domain collaborative scheduling plan to the physical supply chain system and execute it to obtain the corresponding execution result, and synchronously update the execution result to the three-dimensional supply and demand status matrix model.

[0028] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0029] Obtain power grid material supply chain data, and construct a three-dimensional supply and demand status matrix model including supply capacity dimension, transportation timeliness dimension and demand intensity dimension based on the power grid material supply chain data; the power grid material supply chain data includes material inventory data, logistics trajectory data and project progress data; obtain demand forecast data of power grid enterprises, production capacity data of suppliers and material allocation instructions of logistics service providers, and generate a supply and demand matching relationship table based on the demand forecast data, the production capacity data and the material allocation instructions; based on the supply and demand matching relationship table and the parameters of each dimension in the three-dimensional supply and demand status matrix model, predict the type of material supply gap through a gradient boosting decision tree model, and generate a cross-domain collaborative scheduling plan based on the type of material supply gap; feed back the cross-domain collaborative scheduling plan to the physical supply chain system and execute it to obtain the corresponding execution result, and synchronously update the execution result to the three-dimensional supply and demand status matrix model.

[0030] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0031] Obtain power grid material supply chain data, and construct a three-dimensional supply and demand status matrix model including supply capacity dimension, transportation timeliness dimension and demand intensity dimension based on the power grid material supply chain data; the power grid material supply chain data includes material inventory data, logistics trajectory data and project progress data; obtain demand forecast data of power grid enterprises, production capacity data of suppliers and material allocation instructions of logistics service providers, and generate a supply and demand matching relationship table based on the demand forecast data, the production capacity data and the material allocation instructions; based on the supply and demand matching relationship table and the parameters of each dimension in the three-dimensional supply and demand status matrix model, predict the type of material supply gap through a gradient boosting decision tree model, and generate a cross-domain collaborative scheduling plan based on the type of material supply gap; feed back the cross-domain collaborative scheduling plan to the physical supply chain system and execute it to obtain the corresponding execution result, and synchronously update the execution result to the three-dimensional supply and demand status matrix model.

[0032] The above-mentioned cross-domain collaborative scheduling method, device, computer equipment, computer-readable storage medium and computer program product of the power grid material supply chain realizes the integration and mapping of data such as material inventory data, logistics trajectory data and project progress data by constructing a three-dimensional supply and demand status matrix model including the supply capacity dimension, transportation timeliness dimension and demand intensity dimension; generates a supply and demand matching relationship table based on demand forecast data, production capacity data and material allocation instructions to realize cross-domain data collaboration; predicts the type of material supply gap through the gradient boosting decision tree model and generates the corresponding type of cross-domain collaborative scheduling plan, effectively improving the emergency response speed and resource utilization; in addition, the cross-domain collaborative scheduling plan is fed back to the physical supply chain system and executed to obtain the corresponding execution result, and the execution result is synchronously updated to the three-dimensional supply and demand status matrix model, and finally generates a comprehensive and adaptively optimized power grid material supply chain management system, effectively improving the material scheduling efficiency and reducing the resource scheduling deviation, providing a timely and accurate data basis for subsequent project operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0034] Figure 1 This is an application environment diagram of a cross-domain collaborative scheduling method for a power grid material supply chain in one embodiment;

[0035] Figure 2 1 is a flow chart of a cross-domain collaborative scheduling method for a power grid material supply chain in one embodiment;

[0036] Figure 3 A schematic diagram of a flow chart of a material supply gap type prediction step in one embodiment;

[0037] Figure 4 A flowchart of a cross-domain collaborative scheduling method for a power grid material supply chain in a specific embodiment;

[0038] Figure 5 This is a structural block diagram of a cross-domain collaborative scheduling device for a power grid material supply chain in one embodiment;

[0039] Figure 6 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solutions and advantages of this application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0041] The cross-domain collaborative scheduling method for the power grid material supply chain provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown in Figure 1, the terminal can communicate with the server through the network. The blockchain can store the data that the server needs to process. The blockchain can be integrated on the server or placed on the cloud or other network servers. Figure 1 In the application environment shown, the terminal can be, but is not limited to, various personal computers, laptops, smart phones, and tablet computers. The server can be implemented as an independent server or a server cluster consisting of multiple servers.

[0042] In one embodiment, Figure 2 As shown in the figure, a cross-domain collaborative scheduling method for power grid material supply chain is provided, which can be applied to Figure 1 The terminal in the method may include the following steps:

[0043] Step S201: Obtain power grid material supply chain data, and construct a three-dimensional supply and demand status matrix model including supply capacity dimension, transportation timeliness dimension, and demand intensity dimension based on the power grid material supply chain data.

[0044] Specifically, the terminal responds to the cross-domain collaborative dispatching instructions of the power grid material supply chain, builds a digital twin of the power grid material supply chain, and collects material inventory data, logistics trajectory data and project progress data as power grid material supply chain data through IoT sensing devices deployed at storage nodes, logistics vehicles and construction sites. Based on the power grid material supply chain data, a three-dimensional supply and demand status matrix model is established, which includes the supply capacity dimension, transportation timeliness dimension and demand intensity dimension.

[0045] For example, at warehouse nodes, RFID (Radio Frequency Identification) tags, weight sensors, and temperature and humidity sensors are used to capture real-time raw material inventory data, including category codes, storage quantities, shelf locations, storage environment parameters (temperature, humidity, and safety status), and expiration dates. This data is then cleaned and standardized via an edge computing gateway. Logistics vehicles (including transport vehicles and drones) are equipped with GNSS (Global Navigation Satellite System) positioning modules, accelerometers, and fuel / power monitoring modules to record real-time raw logistics trajectory data, including material transport path coordinates, speed, vehicle status (vibration / tilt), energy consumption, and abnormal dwell time. This data is then used in conjunction with electronic fencing technology to demarcate safe transport zones. At construction sites, BIM model interfaces, project progress management software, and camera-based visual recognition systems are used to simultaneously capture raw project progress data, including actual material consumption rates, completion times for construction phase milestones, design change orders, estimates of remaining work quantities, and equipment installation quality inspection results. This data is then compared and analyzed against the planned schedule. The collected raw data (raw material inventory data, raw logistics trajectory data, and raw project progress data) is then structured and processed to generate three key data sets: material inventory data, logistics trajectory data, and project progress data. Material inventory data includes inventory levels, turnover rates, inventory age distribution, and environmental compliance indicators; logistics trajectory data includes transportation path topology, estimated arrival times, real-time position deviations, and vehicle health status scores; and project progress data includes the material demand list for the construction phase, actual quantities collected, project milestone completion rates, and remaining construction period pressure coefficients. Next, a three-dimensional supply and demand state matrix model is constructed based on the above data. Its mathematical expression is: ,in, Represents a dynamic and quantitative supply chain status matrix, supply capacity dimension It is composed of the real-time inventory of the storage node, the supplier's replenishment cycle and the amount of materials in transit. The dynamic supply capacity index of each node is calculated through linear weighting and mapped into the quantitative parameters of the supply dimension in the matrix; the transportation time dimension Based on the path congestion coefficient, average vehicle speed and historical transportation stability index in the logistics trajectory data, a time series prediction model is used to output the transportation reliability score as the dynamic weight of the timeliness dimension; the demand intensity dimension Based on the remaining work volume, critical construction path weights, and the frequency of sudden demand events in the project progress data, a demand urgency function is used to calculate dynamic demand intensity values. Finally, the three datasets are input into a three-dimensional supply and demand status matrix model through the digital twin's data bus. A GIS (Geographic Information System) system is used to establish the spatial topological relationships between warehousing, logistics routes, and construction sites, determining the supply and demand links between nodes in the matrix. A unified timestamp is used to align multi-source data to ensure that the matrix model reflects the real-time status of the supply chain. The supply chain simulation engine converts the raw data into standardized parameters in the matrix, and the matrix values ​​are dynamically updated.

[0046] Step S202: Obtain the demand forecast data of the power grid enterprise, the production capacity data of the supplier, and the material allocation instructions of the logistics service provider, and generate a supply and demand matching relationship table based on the demand forecast data, production capacity data, and material allocation instructions.

[0047] A supply-demand matching table is a table or data structure used to display the relationship between supply and demand. It is often used to help organizations or businesses systematically analyze and optimize the matching of supply and demand. Such a table can clearly display the connection between suppliers and demanders of resources, goods, and services, facilitating analysis of oversupply, undersupply, or mismatches.

[0048] Specifically, the terminal builds a cross-domain data sharing platform through the alliance blockchain and performs dynamic matching on the cross-domain data sharing platform, which includes the following steps: ① Input data: demand forecast data of power grid enterprises, production capacity data of suppliers, and material allocation instructions of logistics service providers; ② Smart contract verification: verify the authenticity of the above data; ③ Output results: generate a dynamic supply and demand matching relationship table, the fields in the table include: demander ID, matching supplier list, logistics service provider ID and matching score, etc.

[0049] In step S203, based on the supply and demand matching relationship table and the parameters of each dimension in the three-dimensional supply and demand status matrix model, the material supply gap type is predicted through the gradient boosting decision tree model, and a cross-domain collaborative scheduling plan is generated according to the material supply gap type.

[0050] Specifically, the terminal uses the gradient boosting decision tree model to predict material supply gaps based on the supply and demand matching relationship table and the parameters of each dimension in the three-dimensional supply and demand status matrix model, and generates a cross-domain collaborative scheduling plan across warehousing, logistics, and construction links.

[0051] In step S204, the cross-domain collaborative scheduling solution is fed back to the physical supply chain system and executed to obtain corresponding execution results, and the execution results are synchronously updated to the three-dimensional supply and demand status matrix model.

[0052] Specifically, the terminal parses the cross-domain collaborative scheduling plan into an executable instruction set for warehousing, logistics and construction systems through the virtual-reality interaction interface of the digital twin, and uses the adapted IoT protocol to control the warehousing robots, transport vehicles and construction equipment to perform operations; at the same time, it collects execution feedback data from the logistics system in real time, such as actual outbound volume, vehicle driving trajectory and construction material consumption rate. After time-space alignment and data cleaning, it updates the supply capacity dimension, transportation timeliness dimension and demand intensity dimension of the three-dimensional supply and demand status matrix model, and verifies the execution effect through quantitative comparison of KPI (Key Performance Indicator) and digital twin simulation. If the deviation exceeds the limit, it triggers model parameter self-learning and rule base iteration, ultimately achieving state synchronization and continuous optimization of all links in the supply chain.

[0053] Among them, the physical supply chain system can refer to the execution layer composed of physical hardware devices, which is used to receive scheduling instructions from the digital twin and feedback real-time data.

[0054] This embodiment realizes the integration and mapping of data such as material inventory data, logistics trajectory data, and project progress data by constructing a three-dimensional supply and demand status matrix model that includes the supply capacity dimension, transportation timeliness dimension, and demand intensity dimension; generates a supply and demand matching relationship table based on demand forecast data, production capacity data, and material allocation instructions to achieve cross-domain data collaboration; predicts the type of material supply gap through a gradient boosting decision tree model and generates a corresponding type of cross-domain collaborative scheduling plan, effectively improving the emergency response speed and resource utilization; in addition, the cross-domain collaborative scheduling plan is fed back to the physical supply chain system and executed to obtain the corresponding execution result, and the execution result is synchronously updated to the three-dimensional supply and demand status matrix model, ultimately generating a comprehensive and adaptively optimized power grid material supply chain management system, effectively improving material scheduling efficiency and reducing resource scheduling deviation, and providing a timely and accurate data foundation for subsequent project operations.

[0055] In one embodiment, Figure 3 As shown, in the above step S203, according to the supply-demand matching relationship table and the parameters of each dimension in the three-dimensional supply-demand state matrix model, the type of material supply gap is predicted by the gradient boosting decision tree model, which may include the following steps:

[0056] Step S301 : Based on the supply-demand matching relationship table and the parameters of each dimension in the three-dimensional supply-demand status matrix model, time series features and spatial correlation features are constructed through feature engineering.

[0057] In step S302, the temporal features and spatial correlation features are input into a gradient boosting decision tree model, and the gradient boosting decision tree model is used to predict the supply capacity index, the transportation reliability score, and the dynamic demand intensity value.

[0058] Step S303: If the supply capacity index is lower than the supply capacity threshold, the material supply gap type is determined to be a production gap; if the transportation reliability score is lower than the transportation time threshold, the material supply gap type is determined to be a transportation gap; if the mutation rate of the dynamic demand intensity value exceeds the mutation rate threshold, the material supply gap type is determined to be a demand mutation gap.

[0059] Specifically, the material supply gap prediction is achieved by collecting real-time material inventory data from storage nodes, logistics trajectory data from logistics vehicles, and project progress data from construction sites. Feature engineering is then used to construct temporal and spatial correlation features, such as inventory consumption rate, supplier capacity fluctuation rate, and the distance weight between the warehouse and the construction site. These features are then input into a gradient boosting decision tree model for training and prediction. The model outputs the material gap quantity and its probability distribution over a period of time. Multi-dimensional cross-validation is then performed based on the dynamic parameter thresholds of the supply capacity, transportation timeliness, and demand intensity dimensions in the three-dimensional supply and demand state matrix model. When the supply capacity index falls below the safety threshold and demand intensity surges, it is identified as a production gap. When the transportation reliability score continues to fall below the required timeliness for the project, it is classified as a transportation gap. If the demand intensity mutation rate exceeds the preset warning line and the inventory replenishment rate cannot match, it is identified as a demand mutation gap. Finally, the gap type is determined through the combined judgment of the classification model probability output and the business rule engine.

[0060] In one embodiment, generating a cross-domain collaborative scheduling solution based on the material supply gap type in step S203 may include the following steps:

[0061] According to the type of material supply gap, the corresponding objective function and constraints are determined; the power grid material supply chain data, objective function and constraints are input into the three-dimensional supply and demand state matrix model to solve and obtain the optimal solution; based on the optimal solution, a cross-domain collaborative scheduling plan is generated.

[0062] Specifically, the terminal invokes the corresponding objective function and constraints based on the type of material supply gap. The power grid material supply chain data, the objective function, and the constraints are then input into a three-dimensional supply-demand state matrix model to solve the optimal cross-domain collaborative scheduling solution. An improved branch-and-bound algorithm is used to solve the integer programming problem for production-related gaps, dynamic programming is used to optimize the path combination for transportation-related gaps, and a greedy algorithm is applied to generate a feasible solution for sudden demand gaps. It should be noted that the resulting scheduling solution must also satisfy the constraints of other links.

[0063] In one embodiment, determining the corresponding objective function and constraint conditions according to the type of material supply gap in the above embodiment may include the following steps:

[0064] If the material supply gap type is a production gap, the objective function is determined based on maximizing capacity utilization and minimizing production switching costs, and the constraints are determined based on capacity allocation constraints, demand coverage constraints, and production preparation time constraints; if the material supply gap type is a transportation gap, the objective function is determined based on minimizing transportation delay risks and balancing transportation loads, and the constraints are determined based on path feasibility constraints, vehicle capacity constraints, and transit time window constraints; if the material supply gap type is a demand mutation gap, the objective function is determined based on maximizing arrival timeliness and minimizing emergency procurement premiums, and the constraints are determined based on safety stock call constraints, emergency response time constraints, and supplier switching restrictions.

[0065] Specifically, the terminal determines the corresponding objective function and constraints based on the type of material supply gap predicted above:

[0066] (1) Production gap: The objective function includes maximizing capacity utilization and minimize production switching costs :

[0067]

[0068] in, For suppliers The actual output of For suppliers The maximum theoretical capacity, For suppliers Historical yield rate;

[0069]

[0070] in, For suppliers The unit cost of production line switching, is a binary variable.

[0071] Constraints include capacity allocation constraints: , Demand coverage constraints: And production preparation time constraints: ,in For suppliers Production line preparation time, For suppliers production rate, The final delivery time required by the demander.

[0072] (2) Transportation gap: The objective function includes minimizing the risk of transportation delay and balanced transport load ;

[0073]

[0074] in: For transport routes length, For path The average driving speed, For path The real-time congestion coefficient, For construction site Penalties per unit time due to delay;

[0075]

[0076] in: is the total number of vehicle sets, For vehicles The load factor, is the average load factor of all vehicles.

[0077] Constraints include path feasibility constraints , vehicle capacity constraints and transit time window constraints :in, For path The real-time congestion coefficient, represents the subset of transport paths assigned to vehicle v, For path The transport volume, For vehicles The maximum load, For transportation tasks The start time, For construction site The arrival time window cut-off time, is the length of path r, is the average travel speed of path r, is the deadline of the arrival time window required by construction site k.

[0078] (3) Sudden demand gap: The objective function includes maximizing the timeliness of arrival and minimizing the emergency purchase premium :

[0079]

[0080] in: For construction site Actual arrival quantity, For construction site The mutation demand;

[0081]

[0082] in: For emergency procurement channels The unit premium rate, To go through the channel Purchase volume.

[0083] Constraints include safety stock call constraints , Emergency Response Time Constraints and supplier switching restrictions ;in, For emergency procurement channels processing time, For channels transportation time, For construction site The latest tolerance time for urgent needs, is the set of emergency procurement channels available at construction site k, is the number of suppliers, To add a new supplier collection, is a binary variable (0 or 1), The maximum number of new suppliers allowed.

[0084] In one embodiment, generating a supply-demand matching relationship table based on demand forecast data, production capacity data, and material allocation instructions in step S203 may include the following steps:

[0085] The demand forecast data, production capacity data and material allocation instructions are stored in the blockchain, and the authenticity of the demand forecast data, production capacity data and material allocation instructions is verified through smart contracts in the blockchain; if the authenticity verification passes, the demand forecast data, production capacity data and material allocation instructions are integrated and organized to obtain a supply and demand matching relationship table.

[0086] Specifically, first, the end-user power grid enterprise encrypts and uploads a material demand forecast based on the project plan, including product categories, demand quantities, and time windows, to the blockchain. Data fields include project code, material classification code, demand date, and urgency tag. Suppliers upload capacity data files containing production line status, raw material inventory, and daily maximum output, and actual production data is automatically collected through IoT devices directly connected to the blockchain node. Logistics service providers submit transport task lists containing the transported material IDs (identifiers), origin and destination points, and planned shipping times, which are then linked to the vehicle's GPS trajectory data for verification. Second, the end-user utilizes smart contracts to verify authenticity. This includes comparing the supplier's historical capacity data with the fluctuation threshold of the current declared value; verifying the consistency between the origin and destination points in the logistics order and the vehicle's electronic fence range; and checking the logical correlation between the demand forecast and the demand intensity dimension in the three-dimensional matrix model. It should be noted that when a demander submits an urgent replenishment request, the inventory availability at the nearest storage node is automatically matched, triggering the logistics service provider to accept the order, lock in the corresponding vehicle capacity, and generate a blockchain electronic waybill. Finally, the terminal builds a dynamic supply and demand matching relationship table, where the fields of the table may include the demander ID, material code, demand time window, matching supplier list, logistics service provider ID, matching score, and last update timestamp, etc.

[0087] In one embodiment, the method of the present application further includes the following steps:

[0088] When deviations are detected between the actual execution data and the cross-domain collaborative scheduling plan, the correlation factors of the abnormal event are traced based on the three-dimensional supply and demand status matrix model; the cross-domain collaborative scheduling plan is optimized based on the correlation factors to obtain the optimized cross-domain collaborative scheduling plan;

[0089] Feedback of the cross-domain collaborative scheduling solution to the physical supply chain system and execution to obtain corresponding execution results in step S204 may include the following steps:

[0090] The optimized cross-domain collaborative scheduling plan is fed back to the physical supply chain system and executed to obtain the corresponding execution results.

[0091] Specifically, the terminal monitors collaborative scheduling execution data, calculating the transport schedule deviation rate, inventory consumption deviation, and construction schedule deviation in real time. This is then compared against preset thresholds to trigger anomaly warnings. These thresholds can be set based on actual monitoring conditions. When deviations are detected, a multi-dimensional traceability analysis is performed based on the three-dimensional supply-demand state matrix model. Inventory fluctuations and supplier performance data are tracked in the supply capacity dimension; path topology and vehicle sensor data are analyzed in the transport time dimension; and project plans are compared with actual progress in the demand intensity dimension. A causal propagation tree is constructed, and the contribution of each factor is quantified using a Bayesian network. Subsequently, an optimization plan is generated using a multi-constrained replanning model combined with a tabu search algorithm. The plan's feasibility is verified through digital twin simulations, and the blockchain platform pushes it to relevant stakeholders to determine vehicle availability, production capacity feasibility, and construction coordination. The final output includes an optimized solution that includes supplier reallocation, logistics route switching, and emergency resource scheduling. Finally, the optimized collaborative scheduling plan is fed back to the physical supply chain system via the digital twin for execution, and the execution results are synchronized and updated to the three-dimensional supply-demand state matrix model.

[0092] In one embodiment, Figure 4 As shown, a cross-domain collaborative scheduling method for a power grid material supply chain in a specific embodiment is provided, which specifically includes the following steps:

[0093] Step S401: Obtain power grid material supply chain data, and construct a three-dimensional supply and demand status matrix model including supply capacity dimension, transportation timeliness dimension, and demand intensity dimension based on the power grid material supply chain data.

[0094] Step S402: Obtain the demand forecast data of the power grid enterprise, the production capacity data of the supplier, and the material allocation instructions of the logistics service provider; store the demand forecast data, production capacity data, and material allocation instructions in the blockchain, and verify the authenticity of the demand forecast data, production capacity data, and material allocation instructions through smart contracts in the blockchain; if the authenticity verification passes, integrate and organize the demand forecast data, production capacity data, and material allocation instructions to obtain a supply and demand matching relationship table.

[0095] Step S403: Based on the supply and demand matching relationship table and the parameters of each dimension in the three-dimensional supply and demand status matrix model, time series features and spatial correlation features are constructed through feature engineering; the time series features and spatial correlation features are input into the gradient boosting decision tree model, and the gradient boosting decision tree model is used to predict the supply capacity index, transportation reliability score, and dynamic demand intensity value.

[0096] Step S404: If the supply capacity index is lower than the supply capacity threshold, the material supply gap type is determined to be a production gap; if the transportation reliability score is lower than the transportation time threshold, the material supply gap type is determined to be a transportation gap; if the mutation rate of the dynamic demand intensity value exceeds the mutation rate threshold, the material supply gap type is determined to be a demand mutation gap.

[0097] Step S405: Determine the corresponding objective function and constraints based on the type of material supply gap; input the power grid material supply chain data, objective function, and constraints into the three-dimensional supply and demand state matrix model to solve and obtain the optimal solution; generate a cross-domain collaborative scheduling plan based on the optimal solution.

[0098] Step S406: When it is monitored that the actual execution data deviates from the cross-domain collaborative scheduling plan, the correlation factors of the abnormal event are traced based on the three-dimensional supply and demand status matrix model; the cross-domain collaborative scheduling plan is optimized based on the correlation factors to obtain an optimized cross-domain collaborative scheduling plan; the optimized cross-domain collaborative scheduling plan is fed back to the physical supply chain system and executed to obtain the corresponding execution results, and the execution results are synchronously updated to the three-dimensional supply and demand status matrix model.

[0099] The beneficial effects brought about by the above embodiment are as follows:

[0100] This application constructs a three-dimensional supply and demand status matrix model based on digital twins to reflect the integration and mapping of warehousing, logistics, and construction data; combines blockchain technology to achieve cross-domain data collaboration, predicts the type of material gap based on machine learning models and generates multi-objective optimization scheduling plans, effectively improving emergency response speed and resource utilization; in addition, through intelligent tracing and dynamic closed-loop optimization of abnormal events, effectively reducing the risk of supply chain disruptions and operating costs, and ultimately generating a comprehensive and adaptively optimized power grid material supply chain management system, effectively improving material scheduling efficiency, and providing a timely and accurate data foundation for subsequent project operations.

[0101] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0102] Based on the same inventive concept, the embodiment of the present application also provides a cross-domain collaborative scheduling device for a power grid material supply chain for implementing the cross-domain collaborative scheduling method for a power grid material supply chain involved above. The implementation solution provided by the device is similar to the implementation solution described in the above method, so the specific limitations in the embodiments of one or more cross-domain collaborative scheduling devices for power grid material supply chains provided below can be found in the above limitations on the cross-domain collaborative scheduling method for power grid material supply chains, and will not be repeated here.

[0103] In an exemplary embodiment, Figure 5 As shown, a cross-domain collaborative scheduling device for a power grid material supply chain is provided, which may include:

[0104] Model building module 501 is used to obtain power grid material supply chain data and construct a three-dimensional supply and demand status matrix model based on the power grid material supply chain data, including supply capacity, transportation timeliness, and demand intensity dimensions; the power grid material supply chain data includes material inventory data, logistics trajectory data, and project progress data;

[0105] Table collating module 502 is used to obtain the demand forecast data of the power grid enterprise, the production capacity data of the supplier and the material allocation instructions of the logistics service provider, and generate a supply and demand matching relationship table based on the demand forecast data, production capacity data and material allocation instructions;

[0106] A plan generation module 503 is used to predict the type of material supply gap using a gradient boosting decision tree model based on the supply and demand matching relationship table and the parameters of each dimension in the three-dimensional supply and demand state matrix model, and to generate a cross-domain collaborative scheduling plan based on the material supply gap type;

[0107] The result updating module 504 is used to feed back the cross-domain collaborative scheduling solution to the physical supply chain system and execute it to obtain the corresponding execution results, and synchronously update the execution results to the three-dimensional supply and demand status matrix model.

[0108] In one embodiment, the solution generation module 503 is also used to construct time series features and spatial correlation features through feature engineering based on the supply and demand matching relationship table and the parameters of each dimension in the three-dimensional supply and demand status matrix model; according to the supply and demand matching relationship table and the three-dimensional supply and demand status matrix model, the time series features and spatial correlation features are input into the gradient boosting decision tree model, and the gradient boosting decision tree model predicts the supply capacity index, transportation reliability score and dynamic demand intensity value; if the supply capacity index is lower than the supply capacity threshold, the material supply gap type is determined to be a production gap; if the transportation reliability score is lower than the transportation timeliness threshold, the material supply gap type is determined to be a transportation gap; if the mutation rate of the dynamic demand intensity value exceeds the mutation rate threshold, the material supply gap type is determined to be a demand mutation gap.

[0109] In one embodiment, the solution generation module 503 is also used to determine the corresponding objective function and constraints based on the type of material supply gap; input the power grid material supply chain data, objective function and constraints into the three-dimensional supply and demand state matrix model for solution to obtain the optimal solution; and generate a cross-domain collaborative scheduling solution based on the optimal solution.

[0110] In one embodiment, the solution generation module 503 is also used to determine the objective function based on maximizing capacity utilization and minimizing production switching costs if the material supply gap type is a production gap, and determine the constraint conditions based on capacity allocation constraints, demand coverage constraints, and production preparation time constraints; if the material supply gap type is a transportation gap, then the objective function is determined based on minimizing transportation delay risks and balancing transportation loads, and determine the constraint conditions based on path feasibility constraints, vehicle capacity constraints, and transit time window constraints; if the material supply gap type is a demand mutation gap, then the objective function is determined based on maximizing arrival timeliness and minimizing emergency purchase premiums, and determine the constraint conditions based on safety stock call constraints, emergency response time constraints, and supplier switching restrictions.

[0111] In one embodiment, the table organization module 502 is also used to store the demand forecast data, production capacity data, and material allocation instructions in the blockchain, and verify the authenticity of the demand forecast data, production capacity data, and material allocation instructions through smart contracts in the blockchain; if the authenticity verification is passed, the demand forecast data, production capacity data, and material allocation instructions are integrated and organized to obtain a supply and demand matching relationship table.

[0112] In one embodiment, the device may also include: a plan adjustment module, which is used to trace the related factors of the abnormal event based on the three-dimensional supply and demand status matrix model when it is monitored that the actual execution data deviates from the cross-domain collaborative scheduling plan; optimize the cross-domain collaborative scheduling plan based on the related factors to obtain an optimized cross-domain collaborative scheduling plan; the result update module 504 is also used to feed back the optimized cross-domain collaborative scheduling plan to logistics and execute it to obtain the corresponding execution results.

[0113] Each module in the above-mentioned cross-domain coordinated scheduling device for the power grid material supply chain can be implemented in whole or in part through software, hardware, or a combination thereof. Each of the above modules can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in the computer device in software form, so that the processor can call and execute the corresponding operations of each of the above modules.

[0114] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 6As shown. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless means. The wireless means can be implemented via Wi-Fi, mobile cellular networks, near-field communication (NFC), or other technologies. When executed by the processor, the computer program implements a cross-domain collaborative scheduling method for a power grid material supply chain. The display unit of the computer device is used to produce a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0115] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0116] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0117] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0118] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0119] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0120] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0121] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0122] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A cross-domain collaborative scheduling method for power grid material supply chain, characterized in that: The method comprises: Obtaining power grid material supply chain data, and constructing a three-dimensional supply and demand status matrix model based on the power grid material supply chain data, including supply capacity dimensions, transportation timeliness dimensions, and demand intensity dimensions; the power grid material supply chain data includes material inventory data, logistics trajectory data, and project progress data; Obtaining demand forecast data from power grid companies, production capacity data from suppliers, and material allocation instructions from logistics service providers, and generating a supply and demand matching relationship table based on the demand forecast data, production capacity data, and material allocation instructions; According to the supply-demand matching relationship table and the parameters of each dimension in the three-dimensional supply-demand status matrix model, the type of material supply gap is predicted by a gradient boosting decision tree model, and a cross-domain collaborative scheduling plan is generated according to the type of material supply gap; The cross-domain collaborative scheduling solution is fed back to the physical supply chain system and executed to obtain corresponding execution results, and the execution results are synchronously updated to the three-dimensional supply and demand status matrix model.

2. The method according to claim 1, characterized in that The material supply gap type is predicted by the gradient boosting decision tree model based on the supply and demand matching relationship table and the parameters of each dimension in the three-dimensional supply and demand status matrix model, including: According to the supply-demand matching relationship table and the parameters of each dimension in the three-dimensional supply-demand status matrix model, constructing time series features and spatial correlation features through feature engineering; Inputting the time series features and the spatial correlation features into a gradient boosting decision tree model, and using the gradient boosting decision tree model to predict a supply capacity index, a transportation reliability score, and a dynamic demand intensity value; If the supply capacity index is lower than the supply capacity threshold, the material supply gap type is determined to be a production gap; if the transportation reliability score is lower than the transportation timeliness threshold, the material supply gap type is determined to be a transportation gap; if the mutation rate of the dynamic demand intensity value exceeds the mutation rate threshold, the material supply gap type is determined to be a demand mutation gap.

3. The method according to claim 2, characterized in that Generating a cross-domain collaborative scheduling plan according to the material supply gap type includes: Determine the corresponding objective function and constraint conditions according to the type of material supply gap; Inputting the power grid material supply chain data, the objective function, and the constraint conditions into the three-dimensional supply and demand state matrix model for solving to obtain an optimal solution; The cross-domain collaborative scheduling solution is generated according to the optimal solution.

4. The method according to claim 3, characterized in that Determining the corresponding objective function and constraint conditions according to the type of material supply gap includes: If the material supply gap type is the production gap, the objective function is determined based on maximizing capacity utilization and minimizing production switching costs, and the constraint conditions are determined based on capacity allocation constraints, demand coverage constraints, and production preparation time constraints; If the material supply gap type is the transportation gap, the objective function is determined based on minimizing the risk of transportation delay and balancing the transportation capacity load, and the constraint conditions are determined based on the path feasibility constraint, the vehicle capacity constraint, and the transit time window constraint; If the material supply gap type is the demand mutation gap, the objective function is determined based on maximizing arrival timeliness and minimizing emergency purchase premium, and the constraint conditions are determined based on safety stock call constraints, emergency response time constraints, and supplier switching restrictions.

5. The method according to claim 1, characterized in that Generating a supply-demand matching relationship table based on the demand forecast data, the production capacity data, and the material allocation instructions includes: Storing the demand forecast data, the production capacity data, and the material allocation instructions in a blockchain, and verifying the authenticity of the demand forecast data, the production capacity data, and the material allocation instructions through a smart contract in the blockchain; When the authenticity verification is passed, the demand forecast data, the production capacity data and the material allocation instructions are integrated and sorted to obtain the supply and demand matching relationship table.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: When it is monitored that the actual execution data deviates from the cross-domain collaborative scheduling plan, the associated factors of the abnormal event are traced based on the three-dimensional supply and demand status matrix model; Optimizing the cross-domain collaborative scheduling solution based on the correlation factors to obtain an optimized cross-domain collaborative scheduling solution; Feeding back the cross-domain collaborative scheduling solution to the physical supply chain system and executing it to obtain corresponding execution results includes: The optimized cross-domain collaborative scheduling solution is fed back to the physical supply chain system and executed to obtain corresponding execution results.

7. A cross-domain collaborative scheduling device for a power grid material supply chain, characterized in that: The device comprises: A model building module is used to obtain power grid material supply chain data and construct a three-dimensional supply and demand status matrix model based on the power grid material supply chain data, including supply capacity, transportation timeliness, and demand intensity dimensions; the power grid material supply chain data includes material inventory data, logistics trajectory data, and project progress data; A table collating module is used to obtain the demand forecast data of the power grid enterprise, the production capacity data of the supplier, and the material allocation instructions of the logistics service provider, and generate a supply and demand matching relationship table based on the demand forecast data, the production capacity data, and the material allocation instructions; A solution generation module is used to predict the type of material supply gap through a gradient boosting decision tree model based on the supply and demand matching relationship table and the parameters of each dimension in the three-dimensional supply and demand status matrix model, and generate a cross-domain collaborative scheduling solution based on the material supply gap type; The result updating module is used to feed back the cross-domain collaborative scheduling solution to the physical supply chain system and execute it to obtain the corresponding execution result, and synchronously update the execution result to the three-dimensional supply and demand status matrix model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images