Resource scheduling simulation method and device, equipment, storage medium and program product

Abstract

The application relates to a resource scheduling simulation method, device, equipment, storage medium and program product. The method comprises the following steps: firstly, monitoring the running state of each simulation node of a target industrial chain in a simulation running environment of the target industrial chain, determining a simulation risk event corresponding to the target industrial chain; then, constructing a target function according to a simulation risk parameter corresponding to the simulation risk event; next, solving the target function by using a preset optimization solver to obtain a global optimization strategy; and finally, generating a resource scheduling scheme of the target industrial chain based on the global optimization strategy. The method can improve the efficiency of industrial chain scheduling when facing a complex industrial chain environment.

Description

Technical Field

[0001] This application relates to the field of supply chain management technology, and in particular to a resource scheduling simulation method, apparatus, equipment, storage medium, and program product. Background Technology

[0002] With globalization, the complexity and dynamism of supply chains in the current market environment are increasing. They not only need to cope with immediate operational risks caused by supply shortages and demand fluctuations, but also with long-term structural changes driven by geopolitical and economic factors such as technological innovation and policy shifts. Therefore, supply chain scheduling simulation is of great significance for maintaining the stability and development of the supply chain.

[0003] Currently, in the field of supply chain scheduling, existing technologies typically employ enterprise resource planning systems, supply chain management systems, and manufacturing execution systems to execute and monitor daily operations. However, this approach is not very efficient in the face of complex and ever-changing supply chain environments. Summary of the Invention

[0004] Therefore, it is necessary to provide a resource scheduling simulation method, device, equipment, storage medium, and program product that can improve the scheduling efficiency of the industrial chain, addressing the aforementioned technical problems.

[0005] Firstly, this application provides a resource scheduling simulation method, the method comprising:

[0006] In the simulation environment of the target industry chain, monitor the operating status of each simulation node of the target industry chain and determine the simulated risk events corresponding to the target industry chain;

[0007] Construct an objective function based on the simulated risk parameters corresponding to the simulated risk events;

[0008] A preset optimization solver is used to solve the objective function to obtain a global optimization strategy;

[0009] Based on a global optimization strategy, a resource scheduling scheme for the target industry chain is generated.

[0010] In one embodiment, the method further includes:

[0011] Obtain simulated impact events that affect the target industry chain structure;

[0012] Determine the simulation impact parameters corresponding to the simulated impact events;

[0013] Based on the simulated risk parameters corresponding to the simulated risk events, construct the objective function, including:

[0014] Construct an objective function based on the simulated risk parameters and / or simulated impact parameters.

[0015] In one embodiment, an objective function is constructed based on simulated risk parameters and / or simulated impact parameters, including:

[0016] Determine the decision variables and constraints in the simulated risk parameters and / or simulated impact parameters;

[0017] Transform the constraints into reference coefficients;

[0018] Based on the decision variables and reference coefficients, an objective function is constructed.

[0019] In one embodiment, the objective function is:

[0020] ;

[0021] Where H(x) is the objective function; x is the decision variable vector, containing all decision variables to be optimized; x i Let q be the i-th decision variable; M is the total number of decision variables; i These are the linear coefficients, which are determined based on the reference coefficients; q ij These are quadratic coefficients, which are determined based on reference coefficients.

[0022] In one embodiment, the method further includes:

[0023] Identify the related events that affect the causal graph structure of the target industry chain, as well as the corresponding handling measures for these related events; related events include simulated risk events or simulated impact events;

[0024] In the simulation environment, if the handling measures are determined to be effective, they will be stored in the preset strategy library.

[0025] In one embodiment, the method further includes:

[0026] Identify the target entities within the target industry chain;

[0027] The global optimization strategy is sent to the terminal corresponding to the target entity, so that the terminal can generate a scheduling scheme for the target entity based on the global optimization strategy.

[0028] Secondly, this application also provides a resource scheduling simulation device, which includes:

[0029] The determination module is used to monitor the operating status of each simulation node in the target industry chain in the simulation operation environment and determine the simulated risk events corresponding to the target industry chain.

[0030] The module is used to construct the objective function based on the simulated risk parameters corresponding to the simulated risk events;

[0031] The decision module is used to solve the objective function using a preset optimization solver to obtain a global optimization strategy;

[0032] The generation module is used to generate resource scheduling schemes for the target industry chain based on a global optimization strategy.

[0033] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the resource scheduling simulation method described in any one of the first aspects.

[0034] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the resource scheduling simulation method described in any one of the first aspects above.

[0035] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the resource scheduling simulation method described in any one of the first aspects.

[0036] The aforementioned resource scheduling simulation method, apparatus, equipment, storage medium, and program product first monitor the operational status of each simulation node in the target industry chain within the simulation environment to identify the corresponding simulated risk events. Then, based on the simulated risk parameters corresponding to these events, an objective function is constructed. Next, a pre-set optimization solver is used to solve the objective function, yielding a global optimization strategy. Finally, based on the global optimization strategy, a resource scheduling scheme for the target industry chain is generated. In this way, simulated risk events in the target industry chain can be directly transformed into objective functions for solving, resulting in a global optimization strategy. Based on this strategy, a resource scheduling scheme is derived to address the scheduling problems associated with simulated risk events, thereby improving the efficiency of resource scheduling in complex industry chain environments. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a flowchart illustrating a resource scheduling simulation method in one embodiment;

[0039] Figure 2This is a flowchart illustrating the objective function construction steps in one embodiment;

[0040] Figure 3 This is a flowchart illustrating the resource scheduling simulation method in another embodiment;

[0041] Figure 4 This is a schematic diagram of the resource scheduling simulation system in another embodiment;

[0042] Figure 5 This is a schematic diagram of the resource scheduling simulation system in another embodiment;

[0043] Figure 6 This is a schematic diagram of the resource scheduling simulation system in another embodiment;

[0044] Figure 7 This is a schematic diagram of the resource scheduling simulation system in another embodiment;

[0045] Figure 8 This is a schematic diagram of the resource scheduling simulation system in another embodiment;

[0046] Figure 9 This is a structural block diagram of a resource scheduling simulation device in one embodiment;

[0047] Figure 10 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0049] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0050] Currently, in the field of supply chain scheduling, existing technologies typically employ Enterprise Resource Planning (ERP) systems, Supply Chain Management (SRM) systems, and Manufacturing Execution Systems (MES) to execute and monitor daily operations. Simultaneously, for forecasting and planning, existing technologies also utilize statistical models based on historical data, such as time series analysis or regression models, to predict future market demand or supply, or employ discrete event simulation methods to simulate and analyze specific production or logistics links. While existing technologies provide some support in improving operational efficiency and managing established processes, their efficiency remains low when facing complex and ever-changing supply chain environments.

[0051] In view of this, this application provides a resource scheduling simulation method, which directly transforms the simulated risk events of the target industrial chain into objective functions for solving, thereby obtaining a global optimization strategy. Based on the global optimization strategy, a resource scheduling scheme is obtained to solve the scheduling problem existing in the simulated risk events. When facing a complex industrial chain environment, it can improve the efficiency of industrial chain scheduling.

[0052] In one exemplary embodiment, such as Figure 1 As shown, a resource scheduling simulation method is provided. This embodiment illustrates the method by applying it to a terminal. It is understood that this method can also be applied to a server, and further to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0053] Step 101: In the simulation environment of the target industry chain, monitor the operating status of each simulation node of the target industry chain and determine the simulated risk events corresponding to the target industry chain.

[0054] The simulation environment can be constructed based on the inherent logical relationships between the various entities within the target industry chain. First, historical operational data of the target industry chain needs to be acquired. This is done through industrial IoT interfaces, database connectors, and application programming interfaces (APIs) to access real-time operational data from each entity within the target industry chain. This operational data includes, but is not limited to: order and inventory data from the Enterprise Resource Planning (ERP) system, production takt time and equipment status data from the Manufacturing Execution System (MES), and logistics and supplier delivery data from the Supply Chain Management (SCL) system. Then, the acquired historical operational data undergoes data cleaning to remove noise and outliers, followed by format conversion, time alignment, and standardization to ultimately form a unified-format multidimensional time-series dataset.

[0055] Next, a constraint-based causal discovery algorithm, such as the PC algorithm or FCI algorithm, is used to process the standardized historical operational data. By statistically testing the conditional independence of any two variables in the dataset under given subsets of other variables, the causal relationships between various entity units are inferred, and an initial causal graph structure is generated, consisting of nodes representing entity units and directed edges representing causal relationships. The initial causal graph structure is provided to domain experts for review through a human-computer interaction interface. Based on the experts' input, directed edges in the graph are added, deleted, and modified to revise the initial graph structure, forming a final industry chain causal graph that combines data-driven approaches with expert knowledge, containing a set of nodes V and a set of directed edges E.

[0056] Finally, for each node in the final causal graph of the industrial chain... This involves fitting a causal effect function to quantify the influence of a parent node's state on its own state. This function can be implemented using a nonlinear function approximator, such as a multilayer perceptron neural network. The function is based on the node... All parent nodes The state vector at time step t As input, output node The state vector at the next time step t+1 The causal effect function can be expressed as shown in the following equation.

[0057]

[0058] In the above formula, For nodes The state vector at time step; For nodes The set of state vectors of all parent nodes at time step t; It is a nonlinear mapping function; This represents a random disturbance term. Through the above steps, a complete causal graph of the industrial chain, G=(V,E,F), is output, which is the simulation environment of the target industrial chain.

[0059] The system monitors the operational status of each simulated node in the supply chain causal graph and predicts the next state of each node without considering random disturbances. The predicted state is then compared with the acquired real-time operational status, and the deviation between the two is calculated. It determines whether the deviation exceeds a preset risk threshold. If it does, it traces upstream along the causal path in the supply chain causal graph to locate the root cause of the deviation and generates a simulated risk event.

[0060] Specific steps may include, firstly, random perturbation terms. Set the value to zero, and use this to calculate the predicted state of each node in the next time step. Then, the predicted state will be... Corresponding real-time running status Compare the two and calculate the deviation norm between them, for example, by using Euclidean distance, as shown in the following formula.

[0061]

[0062] In the formula, For nodes The deviation value at time step t+1 is used to quantify the degree of difference between the predicted state and the real-time state. For the obtained nodes The real-time running state vector at time step t+1; The nodes calculated from the causal effect function The predicted state vector at time step t+1; It is the L2 norm, i.e., the Euclidean distance, used to calculate the straight-line distance between two state vectors in multidimensional space.

[0063] By continuously monitoring the deviation values ​​of each simulation node, when the deviation value exceeds a pre-set risk threshold, the simulation node where the deviation occurred is taken as the starting point, and a backtracking analysis is performed upstream along the directed edge of the causal graph of the industrial chain. Through this tracing process, the root cause node or path that caused the deviation is located, and finally a simulated risk event containing information on the risk source, scope of impact, and urgency is generated.

[0064] Step 102: Construct the objective function based on the simulated risk parameters corresponding to the simulated risk events.

[0065] Specifically, all discrete decision options in the scheduling or layout problem corresponding to the simulated risk event, such as whether to select a supplier or whether to activate a production line, as well as the constraints of the problem, such as the upper limit of resource usage and the order quantity that must be met, are mapped to simulated risk parameters. The objective function is obtained by fitting the simulated risk parameters, and the objective function is optimized to provide decision support for the efficient and scientific handling of simulated risk events.

[0066] Specifically, the optimization objective of the objective function needs to comprehensively consider multiple key indicators in the simulated risk event handling process, such as minimizing total cost, shortening total time, minimizing risk loss, maximizing processing efficiency, rationally controlling resource consumption, and further reducing potential risks. During the construction process, the simulated risk parameters can be transformed into quantifiable functional expressions through mathematical modeling.

[0067] Step 103: Use a preset optimization solver to solve the objective function and obtain the global optimization strategy.

[0068] The preset optimization solver can be a quantum annealing machine or a quantum heuristic solver such as simulated annealing or tabu search running on a traditional computing device. It can efficiently handle complex multivariate and multi-constraint optimization problems. The objective function is solved quickly through the preset optimization solver. During the solution process, the optimal solution is continuously approached through iterative calculation to obtain the decision vector that minimizes the objective function. This vector is the global optimization strategy.

[0069] Step 104: Generate a resource scheduling scheme for the target industry chain based on the global optimization strategy.

[0070] In this embodiment, each decision-making unit in the target industry chain can be abstracted as a computational entity with learning capabilities, i.e., defined as a cognitive agent. The global optimization strategy can serve as a top-level constraint or objective, which is then distributed to multiple cognitive agents in the target industry chain. Under the constraint of the global optimization strategy, each cognitive agent interacts with the simulation environment and learns through a multi-agent reinforcement learning algorithm based on a multi-objective reward function to generate the optimal joint action strategy, i.e., the final resource scheduling scheme.

[0071] In the above embodiments, firstly, in the simulation environment of the target industry chain, the operating status of each simulation node of the target industry chain is monitored to determine the simulated risk events corresponding to the target industry chain. Then, based on the simulated risk parameters corresponding to the simulated risk events, an objective function is constructed. Next, a preset optimization solver is used to solve the objective function to obtain a global optimization strategy. Finally, based on the global optimization strategy, a resource scheduling scheme for the target industry chain is generated. In this way, the simulated risk events of the target industry chain can be directly transformed into an objective function for solving to obtain a global optimization strategy. Based on the global optimization strategy, a resource scheduling scheme is obtained to solve the scheduling problems existing in the simulated risk events, thereby improving the efficiency of industry chain scheduling when facing complex industry chain environments.

[0072] In the embodiments of this application, in order to identify long-term and structural changes in the external environment of the target industrial chain, such as Figure 2 As shown, the method also includes:

[0073] Step 201: Obtain simulated impact events that affect the target industrial chain structure.

[0074] By leveraging network information collection technologies and subscription service interfaces, external data influencing the long-term structure of the target industry chain is acquired. This external data includes, but is not limited to: technical information from global patent and research paper databases, technology news and venture capital data, and geopolitical and macroeconomic analysis reports published by professional think tanks. Through natural language processing technology, unstructured text data can be deeply analyzed to identify events that impact the target industry chain. These events are quantified and transformed into potential structural modification schemes for the causal graph of the target industry chain, represented by adding nodes or adding / changing directed edges, and used to generate simulated impact events.

[0075] Step 202: Determine the simulation impact parameters corresponding to the simulated impact event.

[0076] In this process, all discrete decision options and constraints in the scheduling or layout problem corresponding to the simulated impact event can be mapped to simulated impact parameters.

[0077] Step 203: Construct the objective function based on the simulated risk parameters and / or simulated impact parameters.

[0078] Optionally, an objective function can be constructed based on the simulated risk parameters or simulated impact parameters. The objective function is used to solve the scheduling or layout problems corresponding to the simulated risk events or simulated impact events. Alternatively, an objective function can be constructed based on both the simulated risk parameters and simulated impact parameters. The objective function is used to solve the scheduling or layout problems corresponding to both the simulated risk events and simulated impact events simultaneously.

[0079] In the above embodiments, a target function is constructed by simulating risk events that reflect the operation of the target industrial chain and / or simulating impact events that reflect technological changes, policy changes, etc., to realize a resource scheduling simulation technology that can effectively cope with the above dual challenges and solve different resource scheduling problems of the target industrial chain.

[0080] In one embodiment, constructing an objective function based on simulated risk parameters and / or simulated impact parameters includes: determining decision variables and constraints in the simulated risk parameters and / or simulated impact parameters; converting constraints into reference coefficients; and constructing the objective function based on the decision variables and reference coefficients.

[0081] The scheduling or layout problem corresponding to the simulated risk parameters and / or simulated influence parameters to be solved is identified, including the decision variables, constraints, and optimization objectives, and transformed into a quadratic unconstrained bivariate optimization (QUBO) model. This model establishes an objective function, the goal of which is to minimize its value. The value of the objective function represents the total cost or total energy of a given decision combination, and is calculated by weighted summing of the independent costs or benefits generated by each individual decision variable, plus weighted summing of the interactive costs or benefits arising from synergistic or conflicting effects between all pairwise related decision variables. The model aims to find an optimal decision vector that minimizes the objective function.

[0082] In one embodiment, the objective function is:

[0083]

[0084] Where H(x) is the objective function of the quadratic unconstrained binary optimization model; x is the decision variable vector, containing all decision variables to be optimized; x i Let q be the i-th decision variable; M is the total number of decision variables; i These are the linear coefficients, which are determined based on the reference coefficients; q ij These are quadratic coefficients, which are determined based on reference coefficients.

[0085] Where x i =1 indicates that the decision is adopted, x i =0 indicates that the decision is not adopted. The linear coefficient represents the decision x to be adopted alone. i The resulting independent costs or benefits; x represents the quadratic coefficient representing the simultaneous adoption of the decision. i and decision x j The quantitative value of the synergistic or conflicting effects generated at that time. The linear and quadratic coefficients can be determined based on the reference coefficients transformed from the above constraints.

[0086] In the embodiments of this application, such as Figure 3 As shown, the method also includes:

[0087] Step 301: Identify the related events that affect the causal graph structure of the target industrial chain, and the corresponding handling measures for these related events.

[0088] The related events include simulated risk events or simulated impact events. Based on the steps described above, the corresponding handling measures for the related events are determined; that is, an objective function is constructed based on the simulated risk events or simulated impact events, and the resulting resource scheduling scheme is obtained after solving the function.

[0089] Step 302: In the simulation environment, if the treatment measure is determined to be an effective measure, the treatment measure is stored in the preset strategy library.

[0090] In the simulation environment, the resource scheduling scheme is verified to determine whether the measures are effective, i.e., whether they can solve the scheduling problem in the related events. The specific simulation process includes two methods.

[0091] The first approach involves simulating risk events as related events, evaluating the effectiveness of handling measures before implementing resource scheduling decisions. Specifically, a mathematical intervention (do-operator) is applied to the aforementioned industry chain causal graph, forcibly setting the state of one or more nodes in the graph to the values ​​required by the resource scheduling plan. For example, to evaluate the plan of activating a backup supplier, this unit forcibly sets the state of the node representing supplier selection to the backup supplier. Subsequently, the impact of this intervention is propagated forward using the causal effect function in the causal graph, calculating the expected state evolution of the system after the intervention, and outputting a quantitative evaluation result of the plan's effectiveness.

[0092] The second approach uses simulated impact events to assess the long-term impact of disruptive events on the supply chain. Specifically, it involves receiving potential structural modification proposals included in the simulated impact events. This is then merged with the existing industry chain causal graph G to generate a temporary virtual causal graph. Subsequently, in this virtual causal graph Long-term simulations were conducted to deduce the potential systemic impacts of this structural change, such as changes in market share and reshaping of cost structures.

[0093] After the aforementioned effective measures are parameterized, they are stored in a preset strategy library. When the target industry chain encounters a situation similar to that stored in the preset strategy library in the future, the corresponding strategy can be directly invoked from the preset strategy library to improve decision-making response speed.

[0094] In the embodiments of this application, the causal graph of the target industry chain can be periodically updated based on the latest operational data. The internal parameters of the causal effect function of the causal graph are retrained and calibrated to maintain the accuracy of the simulation environment's description of the current target industry chain. Simultaneously, when the aforementioned processing measures are verified as effective, potential structural modification schemes for the processing measures will be considered. Marked as pending confirmation. Upon receiving an external confirmation command, It is permanently merged into the main industry chain causal graph G.

[0095] In one embodiment, the method further includes: first, determining the target entity in the target industry chain; then, sending the global optimization strategy to the terminal corresponding to the target entity, so that the terminal generates a scheduling scheme corresponding to the target entity based on the global optimization strategy.

[0096] In this system, the target entity, i.e., the cognitive whole within the target industry chain, sends the global optimization strategy to the terminal corresponding to the target entity. The terminal receives the global optimization strategy and uses it as top-level guidance. Multiple cognitive agents generate specific tactical scheduling schemes through multi-agent reinforcement learning, and the learning process is guided by a multi-objective reward function. The multi-objective reward function is used to calculate the total reward value obtained by each cognitive agent at any time step. Its calculation method is as follows: the cost function value used to quantify operating costs, the efficiency function value used to quantify output efficiency, and the stability metric function value used to quantify disturbance resistance are weighted and summed according to preset weight coefficients.

[0097] Optionally, the multi-objective reward function can be expressed as follows:

[0098]

[0099] in, Let be the total reward value obtained by cognitive agent k at time step t; k is the unique index of the cognitive agent; t is the discrete time step. The cost function value of the cognitive agent k at time step t is used to quantify the operating cost or penalty term; The efficiency function value of the cognitive agent k at time step t is used to quantify performance indicators such as production efficiency or order fulfillment rate. This is a stability or resilience metric for a cognitive agent k at time step t, used to quantify its ability to resist external disturbances. , , These are preset normalized weighting coefficients for cost, efficiency, and stability, used to balance the priorities among different optimization objectives.

[0100] In one embodiment, a resource scheduling method is provided, comprising:

[0101] S1, in the simulation environment of the target industry chain, monitor the operating status of each simulation node of the target industry chain and determine the simulated risk events corresponding to the target industry chain.

[0102] S2, obtain simulated impact events that affect the target industry chain structure.

[0103] S3, determine the simulation impact parameters corresponding to the simulated impact event.

[0104] S4. Construct the objective function based on the simulated risk parameters and / or simulated impact parameters.

[0105] S5 uses a preset optimization solver to solve the objective function and obtain a global optimization strategy.

[0106] S6 generates a resource scheduling scheme for the target industry chain based on a global optimization strategy.

[0107] S7, identify the target entity in the target industry chain; send the global optimization strategy to the terminal corresponding to the target entity so that the terminal can generate the scheduling scheme corresponding to the target entity based on the global optimization strategy.

[0108] In one exemplary embodiment, the resource scheduling simulation method of this application can be applied to, for example... Figure 4 The resource scheduling simulation system shown may include: a supply chain causal twin construction module 10, a dynamic risk perception module 20, an influencing factor perception module 30, a global optimization decision module 40, a collaborative scheduling module 50, and a deduction and system self-evolution module 60.

[0109] The system comprises several modules: a supply chain causal twin construction module 10, which constructs a causal graph of the target supply chain and generates the basic model environment for system simulation and analysis; a dynamic risk perception module 20, connected to the supply chain causal twin construction module 10, which monitors the supply chain's operational status in real time based on the supply chain causal graph; and a global optimization decision module 40, which analyzes operational deviations to generate simulated risk events (e.g., operational-level risk events) and transmits them to the global optimization decision module 40; and an influencing factor perception module 30, which analyzes strategic data outside the supply chain to identify simulated impact events that could cause structural changes in the supply chain causal graph (e.g., strategic-level opportunities or threats) and transmits them to the global optimization decision module 40 and the deduction and system self-evolution module 60; and a global optimization decision module 40, which receives events from the dynamic risk perception module 20 or the influencing factor perception module 30. It transforms the corresponding scheduling or layout problem into a quadratic unconstrained binary optimization model, solves it to obtain a global optimization strategy, and transmits the global optimization strategy to the collaborative scheduling module 50. The collaborative scheduling module 50 receives global optimization strategies from the global optimization decision-making module 40, organizes cognitive agents in the industry chain, and, under the guidance of the global optimization strategies, collaborates through multi-agent reinforcement learning to generate specific and executable resource scheduling schemes. The deduction and system self-evolution module 60, connected to the industry chain causal twin construction module 10, the influencing factor perception module 30, and the collaborative scheduling module 50, stores effective measures in a preset strategy library and iteratively updates the industry chain causal graph and the strategies of the cognitive agents maintained by the industry chain causal twin construction module 10.

[0110] In the above embodiments, a simulation environment for the target industrial chain is constructed using an industrial chain causal graph. When an anomaly is detected in the simulation environment, the cause can be traced back according to the industrial chain causal graph, improving the accuracy of anomaly localization. Simultaneously, the parallel configuration of a dynamic risk perception module and a simulated impact perception module allows for the simultaneous resolution of different industrial chain scheduling problems, resulting in higher resource scheduling efficiency. Furthermore, a global optimization strategy is obtained through a quadratic unconstrained binary optimization model, leading to a resource scheduling scheme that further improves resource scheduling efficiency.

[0111] In one exemplary embodiment, such as Figure 5 The diagram shows the structure of the system modeling and data foundation subsystem of the resource scheduling simulation system described above. This subsystem can include a data standardization and preprocessing unit 13 and a supply chain causal twin construction module 10, providing a unified data foundation and causal model for the entire resource scheduling system. The data standardization and preprocessing unit 13 is used to acquire operational data of the target supply chain through the operational data access unit 11 and strategic data of the target supply chain through the strategic data access unit 12, and then output the data after standardization and preprocessing.

[0112] In one exemplary embodiment, such as Figure 6 The diagram shows the structure of the dual-modal perception and event triggering subsystem of the resource scheduling simulation system described above. This subsystem includes a dynamic risk perception module 20 and an influencing factor perception module 30. As the perception component of the resource scheduling simulation system, it perceives operational changes within the target industry chain and external strategic changes, generating corresponding simulated events. The dynamic risk perception module 20 generates simulated risk events, and the influencing factor perception module 30 generates simulated impact events. The dynamic risk perception module 20 may also include an operational status synchronization and deviation detection unit 21 and a causal attribution analysis unit 22. The operational status synchronization and deviation detection unit 21 detects the deviation norm between the predicted state and the real-time operational state of each node. The causal attribution analysis unit 22 monitors when the deviation exceeds a preset risk threshold, traces the deviation through an industry chain causal graph, and generates simulated risk events. The influencing factor perception module 30 may also include an information parsing unit 31 and a potential causal structure generation unit 32. The information parsing unit 31 receives strategic data, and the potential causal structure generation unit 32 generates simulated impact events based on events identified by the information parsing unit 31 that affect the target industry chain.

[0113] In one exemplary embodiment, such as Figure 7 The diagram shown is a structural block diagram of the hierarchical optimization decision subsystem in the resource scheduling simulation system described above. This hierarchical optimization decision subsystem, as the decision-making core of the resource scheduling system, is responsible for... Figure 6The events generated by the dual-modal perception and event-triggered subsystem are transformed into hierarchical, executable global optimization strategies and scheduling schemes. This hierarchical optimization decision-making subsystem includes a global optimization decision-making module 40 and a collaborative scheduling module 50. The global optimization decision-making module 40 is used to obtain the global optimization strategy, and the collaborative scheduling module 50, connected to the global optimization decision-making module 40, is used to decompose the global optimization strategy into executable resource scheduling schemes.

[0114] The global optimization decision-making module 40 receives simulated risk events or simulated impact events and executes the decision-making process through its internal quadratic unconstrained binary optimization modeling unit 41 and optimization solution unit 42. The collaborative scheduling module 50 generates resource scheduling schemes through its internal policy decomposition and distribution unit 51 and multi-agent collaborative learning unit 52.

[0115] In one exemplary embodiment, such as Figure 8 The diagram shown is a structural block diagram of the cognitive agent and self-evolving subsystem in the resource scheduling simulation system described above. This cognitive agent and self-evolving subsystem is responsible for defining the cognitive agents within the system and, through learning, driving the continuous iteration and evolution of the cognitive agent strategies and the overall system model. Optionally, this cognitive agent and self-evolving subsystem includes the function of cognitive agent modeling and the function of the deduction and system self-evolution module 60.

[0116] In this embodiment, cognitive agent modeling is used to abstract decision-making entities (e.g., factories, warehouses, logistics departments) in the target industry chain into computational entities with autonomous learning capabilities, i.e., cognitive agents. Each cognitive agent k is defined as its state space S. k Action Space A k and strategy π k The set of states. Wherein, the state space S k This refers to the local information that the cognitive agent can observe from the causal graph of the supply chain, and its action space A. k It is the set of operations that the agent can execute, policy π k It is its mapping function from state to action, which is optimized by the multi-agent reinforcement learning process in the cooperative scheduling module 50.

[0117] The simulation and system self-evolution module 60 includes a bimodal simulation unit 61 and a strategy and model evolution unit 62, realizing closed-loop iteration of the entire resource scheduling simulation system. The bimodal simulation unit 61 is used to execute the simulation simulation process described above to verify the resource scheduling scheme and determine the effectiveness of the handling measures. The strategy and model evolution unit 62 is used to continuously improve the system model based on the simulation results and the actual system operation results, such as adding handling measures to the preset strategy library and updating the industry chain causal graph.

[0118] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0119] Based on the same inventive concept, this application also provides a resource scheduling simulation apparatus for implementing the resource scheduling simulation method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more resource scheduling simulation apparatus embodiments provided below can be found in the limitations of the resource scheduling simulation method described above, and will not be repeated here.

[0120] In one exemplary embodiment, such as Figure 9 As shown, a resource scheduling simulation device is provided, comprising: a determination module, a construction module, a decision-making module, and a generation module, wherein:

[0121] The determination module is used to monitor the operating status of each simulation node in the target industry chain in the simulation operation environment and determine the simulated risk events corresponding to the target industry chain.

[0122] The module is used to construct the objective function based on the simulated risk parameters corresponding to the simulated risk events;

[0123] The decision module is used to solve the objective function using a preset optimization solver to obtain a global optimization strategy;

[0124] The generation module is used to generate resource scheduling schemes for the target industry chain based on a global optimization strategy.

[0125] In one embodiment, the device further includes an acquisition module for acquiring simulated impact events affecting the target industrial chain structure; determining simulated impact parameters corresponding to the simulated impact events; and the construction module is further used to construct an objective function based on the simulated risk parameters and / or simulated impact parameters.

[0126] In one embodiment, the construction module is specifically used to determine the decision variables and constraints in the simulated risk parameters and / or simulated impact parameters; convert the constraints into reference coefficients; and construct an objective function based on the decision variables and reference coefficients.

[0127] In one embodiment, the objective function is:

[0128] ;

[0129] Where H(x) is the objective function; x is the decision variable vector, containing all decision variables to be optimized; x i Let q be the i-th decision variable; M is the total number of decision variables; i These are the linear coefficients, which are determined based on the reference coefficients; q ij These are quadratic coefficients, which are determined based on reference coefficients.

[0130] In one embodiment, the device further includes a storage module for determining the associated events affecting the causal graph structure of the target industry chain, and the corresponding handling measures for the associated events; the associated events include simulated risk events or simulated impact events; in the simulation environment, if the handling measures are determined to be effective measures, the handling measures are stored in a preset strategy library.

[0131] In one embodiment, the device further includes a sending module for determining a target entity in the target industry chain; sending a global optimization strategy to the terminal corresponding to the target entity, so that the terminal generates a scheduling scheme corresponding to the target entity based on the global optimization strategy.

[0132] Each module in the aforementioned resource scheduling simulation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0133] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 10As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a resource scheduling simulation method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0134] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0135] In one exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: in a simulation environment of a target industry chain, monitoring the operating status of each simulation node of the target industry chain and determining the simulated risk events corresponding to the target industry chain; constructing an objective function based on the simulated risk parameters corresponding to the simulated risk events; solving the objective function using a preset optimization solver to obtain a global optimization strategy; and generating a resource scheduling scheme for the target industry chain based on the global optimization strategy.

[0136] In one embodiment, when the processor executes the computer program, it also performs the following steps: acquiring simulated impact events that affect the target industry chain structure; determining the simulated impact parameters corresponding to the simulated impact events; and constructing an objective function based on the simulated risk parameters and / or the simulated impact parameters.

[0137] In one embodiment, when the processor executes the computer program, it also performs the following steps: determining decision variables and constraints in the simulated risk parameters and / or simulated influence parameters; converting the constraints into reference coefficients; and constructing an objective function based on the decision variables and reference coefficients.

[0138] In one embodiment, the objective function is:

[0139] ;

[0140] Where H(x) is the objective function; x is the decision variable vector, containing all decision variables to be optimized; x i Let q be the i-th decision variable; M is the total number of decision variables; i These are the linear coefficients, which are determined based on the reference coefficients; q ij These are quadratic coefficients, which are determined based on reference coefficients.

[0141] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the associated events that affect the causal graph structure of the target industry chain, and the corresponding handling measures for the associated events; the associated events include simulated risk events or simulated impact events; and in the simulation environment, if the handling measures are determined to be effective measures, storing the handling measures in a preset strategy library.

[0142] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the target entity in the target industry chain; sending the global optimization strategy to the terminal corresponding to the target entity, so that the terminal generates a scheduling scheme corresponding to the target entity based on the global optimization strategy.

[0143] 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, it performs the following steps: in a simulation environment of the target industry chain, monitoring the operating status of each simulation node of the target industry chain and determining the simulated risk events corresponding to the target industry chain; constructing an objective function based on the simulated risk parameters corresponding to the simulated risk events; solving the objective function using a preset optimization solver to obtain a global optimization strategy; and generating a resource scheduling scheme for the target industry chain based on the global optimization strategy.

[0144] In one embodiment, when the computer program is executed by a processor, it performs the following steps: acquiring simulated impact events that affect the target industry chain structure; determining the simulated impact parameters corresponding to the simulated impact events; and constructing an objective function based on the simulated risk parameters and / or the simulated impact parameters.

[0145] In one embodiment, when the computer program is executed by a processor, it performs the following steps: determining decision variables and constraints in the simulated risk parameters and / or simulated influence parameters; converting the constraints into reference coefficients; and constructing an objective function based on the decision variables and reference coefficients.

[0146] In one embodiment, the objective function is:

[0147] ;

[0148] Where H(x) is the objective function; x is the decision variable vector, containing all decision variables to be optimized; x i Let q be the i-th decision variable; M is the total number of decision variables; i These are the linear coefficients, which are determined based on the reference coefficients; q ij These are quadratic coefficients, which are determined based on reference coefficients.

[0149] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the associated events affecting the causal graph structure of the target industry chain, and the corresponding handling measures for the associated events; the associated events include simulated risk events or simulated impact events; in the simulation environment, if the handling measures are determined to be effective measures, the handling measures are stored in a preset strategy library.

[0150] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the target entity in the target industry chain; sending the global optimization strategy to the terminal corresponding to the target entity, so that the terminal generates a scheduling scheme corresponding to the target entity based on the global optimization strategy.

[0151] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps: in a simulation environment of a target industry chain, monitoring the operating status of each simulation node of the target industry chain and determining the simulated risk events corresponding to the target industry chain; constructing an objective function based on the simulated risk parameters corresponding to the simulated risk events; solving the objective function using a preset optimization solver to obtain a global optimization strategy; and generating a resource scheduling scheme for the target industry chain based on the global optimization strategy.

[0152] In one embodiment, when the computer program is executed by a processor, it performs the following steps: acquiring simulated impact events that affect the target industry chain structure; determining the simulated impact parameters corresponding to the simulated impact events; and constructing an objective function based on the simulated risk parameters and / or the simulated impact parameters.

[0153] In one embodiment, when the computer program is executed by a processor, it performs the following steps: determining decision variables and constraints in the simulated risk parameters and / or simulated influence parameters; converting the constraints into reference coefficients; and constructing an objective function based on the decision variables and reference coefficients.

[0154] In one embodiment, the objective function is:

[0155] ;

[0156] Where H(x) is the objective function; x is the decision variable vector, containing all decision variables to be optimized; x i Let q be the i-th decision variable; M is the total number of decision variables; i These are the linear coefficients, which are determined based on the reference coefficients; q ij These are quadratic coefficients, which are determined based on reference coefficients.

[0157] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the associated events affecting the causal graph structure of the target industry chain, and the corresponding handling measures for the associated events; the associated events include simulated risk events or simulated impact events; in the simulation environment, if the handling measures are determined to be effective measures, the handling measures are stored in a preset strategy library.

[0158] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the target entity in the target industry chain; sending the global optimization strategy to the terminal corresponding to the target entity, so that the terminal generates a scheduling scheme corresponding to the target entity based on the global optimization strategy.

[0159] 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, data stored, data displayed, 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 the relevant data must comply with relevant regulations.

[0160] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, 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 many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0161] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0162] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A resource scheduling simulation method, characterized in that, The method includes: In the simulation environment of the target industry chain, monitor the operating status of each simulation node of the target industry chain and determine the simulated risk events corresponding to the target industry chain; Based on the simulated risk parameters corresponding to the simulated risk events, construct an objective function; A preset optimization solver is used to solve the objective function to obtain a global optimization strategy; Based on the global optimization strategy, a resource scheduling scheme for the target industry chain is generated.

2. The method according to claim 1, characterized in that, The method further includes: Obtain simulated impact events that affect the target industry chain structure; Determine the simulation impact parameters corresponding to the simulated impact event; The step of constructing an objective function based on the simulated risk parameters corresponding to the simulated risk event includes: The objective function is constructed based on the simulated risk parameters and / or the simulated impact parameters.

3. The method according to claim 2, characterized in that, The step of constructing the objective function based on the simulated risk parameters and / or the simulated impact parameters includes: Determine the decision variables and constraints in the simulated risk parameters and / or the simulated impact parameters; Transform the constraints into reference coefficients; The objective function is constructed based on the decision variables and the reference coefficients.

4. The method according to claim 3, characterized in that, The objective function is: ； Where H(x) is the objective function; x is the decision variable vector, containing all decision variables to be optimized; x i Let q be the i-th decision variable; M is the total number of decision variables; i The linear coefficients are determined based on the reference coefficients; q ij The coefficients are quadratic coefficients, which are determined based on the reference coefficients.

5. The method according to claim 3, characterized in that, The method further includes: Identify the related events that affect the causal graph structure of the target industrial chain, and the corresponding handling measures for the related events; the related events include the simulated risk events or simulated impact events; If the processing measure is determined to be effective in the simulation environment, the processing measure is stored in a preset strategy library.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Identify the target entities within the target industry chain; The global optimization strategy is sent to the terminal corresponding to the target entity, so that the terminal generates a scheduling scheme corresponding to the target entity based on the global optimization strategy.

7. A resource scheduling simulation device, characterized in that, The device includes: The determination module is used to monitor the operating status of each simulation node of the target industry chain in the simulation operation environment of the target industry chain and determine the simulated risk events corresponding to the target industry chain. The module is used to construct the objective function based on the simulated risk parameters corresponding to the simulated risk events; The decision module is used to solve the objective function using a preset optimization solver to obtain a global optimization strategy; The generation module is used to generate a resource scheduling scheme for the target industry chain based on the global optimization strategy.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

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

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

Images