154 results about "Directed graph" patented technology

The invention relates to a river network grading system and method based on a graph theory and confluence cumulant, and belongs to the technical field of water conservancy projects and geographic information. Comprising the following steps: acquiring original DEM data and water system data, and converting the water system data to a preset projection coordinate system; extracting a primary river network based on the DEM data, and screening the primary river network in combination with the length of the river network and the area of the drainage basin to obtain a simplified river network; river network flow calculation: carrying out flow assignment on each river network element in the simplified river network based on the confluence cumulant; graph theory modeling: abstracting the simplified river network into a directed graph model; and river network grading: reverse tracing is carried out by taking the water outlet as a starting point, and the hierarchical relationship between the trunk and the branch is determined by combining the in-degree / out-degree and the edge weight of the node, so that river network grading is realized. According to the method, river network grading is upgraded from morphological description to hydrological function description, and the method is suitable for high-precision river network refined analysis, intelligent water conservancy emergency management and other scenes.

The invention relates to a dynamic construction method and system for an integrated energy large model knowledge base. The method comprises the steps that a directed graph is constructed according to physical equipment or energy nodes on a target integrated energy system; performing knowledge association and filling on nodes and edges in the directed graph to form a node static knowledge set; accessing multi-source real-time data, and performing anomaly detection and state analysis on the multi-source real-time data to obtain a corresponding event; mapping the event into a directed graph, and updating the directed graph and the node static knowledge set to obtain an updated graph database and an updated vector knowledge base; and constructing an input prompt to the comprehensive energy field large model based on the query statement and the corresponding knowledge set to output an answer. According to the method, a dynamic knowledge base tightly coupling a physical world and an information world is constructed, the systematization degree, the cross-system analysis capability and the real-time performance of comprehensive energy system knowledge are remarkably improved, and powerful support is provided for deep application of a large model in scenes such as fault diagnosis and operation optimization.

The invention provides a power grid fault propagation path identification method and system based on a graph neural network, and relates to the technical field of power grid fault identification, and the method comprises the steps: obtaining a power grid topological structure and fault observation data, constructing a direction perception graph neural network, achieving the one-way message passing based on potential energy difference, and obtaining a node potential energy value and embedded representation; edges are screened to generate a directed graph, and candidate paths are generated in the potential energy gradient direction; and verifying the satisfaction degree of the graph neural network evaluation path to the physical constraint through an invariant, and finally selecting the path with the minimum topological entropy. According to the invention, the accuracy and reliability of fault propagation path identification are improved.

The invention relates to the technical field of process orchestration, and discloses an automatic orchestration system and implementation method based on event driving and context management, and the system comprises a model orchestration module which receives an external request through an OpenAPI, carries out the model packaging based on namespace attributes, and abstracts the workflow execution capability into a configurable model entity; the workflow engine module is used for providing a dynamic arrangement and execution mechanism based on a directed graph structure and carrying out unified context management; the parameter configuration module is used for constructing a global data constraint and management mechanism of a parameter-result double-layer model, and establishing a data mapping relation between an execution layer and a display layer of the process; and the data source management module uniformly manages and configures the external service capability units which can be called by the nodes in the workflow. According to the method, asynchronous, self-driven and distributed parallel execution of the workflow nodes can be realized, the operation efficiency in a high-concurrency scene is improved, and organic unification of performance, stability and expansibility is realized.

The invention discloses a power system carbon emission dynamic traceability and evaluation method, system and device based on life cycle and topological entropy fusion and a medium, and belongs to the technical field of power system low-carbon operation and carbon emission evaluation, and the method comprises the steps: collecting carbon emission data of different stages; establishing a stage set, calculating the emission of each stage, and solving a life cycle carbon entropy; abstracting a power system into a weighted directed graph, calculating a branch carbon flow rate based on the weighted directed graph, and calculating a graph theory carbon entropy based on node inflow; introducing a weight parameter, fusing the life cycle carbon entropy and the graph theory carbon entropy, and defining a fusion entropy; under a multi-period operation condition, calculating a time evolution sequence based on the fusion entropy, and defining a sensitivity coefficient; and generating a visual carbon flow map containing node carbon potential distribution, a branch carbon flow rate, a carbon entropy evolution curve and a responsibility allocation matrix. According to the method, dynamic conduction and node-level tracking of carbon emission along the electric power flow are realized, and the complexity and balance of carbon emission space distribution are quantified through an entropy theory.

The invention discloses a multi-type resource participation power grid frequency modulation method based on a consistency algorithm, and the method comprises the steps: firstly constructing an improved frequency response model fusing distributed optical storage equipment, hydrogen storage and energy storage equipment and a DC flexible load, identifying system parameters, solving a multi-resource comprehensive adjustment coefficient, constructing a directed graph model, employing a grouping consistency algorithm, and obtaining a multi-type resource participation power grid frequency modulation model; the optimal adjustment coefficient of each resource is solved through distributed optimization of an augmented Lagrange function and a consistency index, and primary frequency modulation of a multi-type resource collaborative response system is driven. According to the multi-type resource participation power grid frequency modulation method based on the consistency algorithm, by driving a multi-type resource collaborative response system to perform primary frequency modulation, collaborative regulation and control of light storage, hydrogen storage and flexible load are realized, economy and operation constraints are considered through distributed optimization, and communication complexity is reduced through a clustering iteration mechanism; and the frequency stability of the high-proportion new energy power grid is obviously improved.

The embodiment of the invention relates to the technical field of information processing, and discloses a reinforcement learning training method based on graphical user interface simulation, a system construction method, a system, equipment and a product, and the method comprises the steps: modeling a graphical user interface navigation graph into a directed graph, enabling nodes of the directed graph to represent the interface state of a graphical user interface, and enabling the nodes of the directed graph to represent the interface state of the graphical user interface; the edges of the directed graph are represented as state transition between the graphical user interfaces, and a navigation graph structure is generated by controlling topological parameters of the directed graph; rendering a graphical user interface according to the navigation map structure; driving the intelligent agent to perform graphical user interface operation by using the task target, and obtaining an operation action of the intelligent agent; evaluating the operation action and the task completion degree of the intelligent agent; and calculating a reward through the operation action and the task completion degree of the intelligent agent, and feeding back the reward to the intelligent agent. And an ideal experimental environment is provided for a methodology of constructing an intelligent agent based on a graphical user interface from zero.

The invention provides a fault root cause dynamic prediction method and system based on probability propagation reasoning, and relates to the technical field of fault positioning prediction, and the method comprises the steps: constructing a directed graph structure, associating each node with a dynamic fault probability, and constructing a fault state expression system; based on the fault state expression system, calculating and dynamically updating an edge weight, and constructing a dynamic propagation graph model; generating fault occurrence probabilities of the monitoring data, and fusing the fault occurrence probabilities to obtain aligned unified probability data; on the basis of a dynamic propagation graph model, on-graph probability propagation reasoning is carried out by using unified probability data, a final root cause is determined, and rapid fault positioning is realized; an intelligent self-healing and strategy optimization algorithm based on reinforcement learning is introduced, a repair strategy is automatically generated and executed, a decision is continuously optimized through online learning, and a self-evolution safety operation and maintenance system is formed. According to the invention, accurate and rapid prediction and positioning of system faults are realized.

The invention is suitable for the field of multi-modal data analysis and target identification, and provides a multi-modal time series data reasoning method based on a thinking chain, a three-layer reasoning state architecture is designed, hierarchical abstraction and time alignment of multi-modal data are realized through a gating circulation unit and a time modulation mechanism, and the multi-modal time series data reasoning efficiency is improved. Converting the multi-modal features into a unified time sequence semantic representation; designing a multi-step reasoning controller, and dynamically focusing key information and iteratively optimizing a reasoning state by adopting a modal exclusive attention mechanism and a gating circulation unit; in order to explicitly capture a cross-modal and cross-time complex dependency relationship, multi-modal time sequence dependent graph structure modeling is carried out, multi-modal time sequence data is modeled into a directed graph, and structured information transmission is realized through a graph neural network; according to the method, deep understanding and accurate prediction of military target behaviors are realized, the reasoning process can be visually explained through state evolution, attention weight, graph structure dependency and the like, and reliable technical support is provided for intelligent decision making in a complex scene.

Simulation and validation of neural network systems is provided. In various embodiments, a description of an artificial neural network is read. A directed graph is constructed comprising a plurality of edges and a plurality of nodes, each of the plurality of edges corresponding to a queue and each of the plurality of nodes corresponding to a computing function of the neural network system. A graph state is updated over a plurality of time steps according to the description of the neural network, the graph state being defined by the contents of each of the plurality of queues. Each of a plurality of assertions is tested at each of the plurality of time steps, each of the plurality of assertions being a function of a subset of the graph state. Invalidity of the neural network system is indicated for each violation of one of the plurality of assertions.

Embodiments of the present application provide a task scheduling method and device, a target directed graph to be detected is obtained; a change type of the target directed graph is matched based on task change information and a preset acyclic constraint condition, to obtain a first detection result; if the first detection result represents that the change type does not match the preset acyclic constraint condition, then the task nodes to be detected are detected based on the task change information and a preset cyclic detection method, to obtain a second detection result representing whether the target directed graph is a directed acyclic graph; in the directed graph detection process, first, whether the change type of the target directed graph conforms to the preset acyclic constraint condition is identified, if it conforms, then it can be directly determined that the target directed graph is a directed acyclic graph; if it does not conform, then part of the task nodes in the target directed graph are detected based on the preset cyclic detection method, to identify whether the target directed graph has a cycle, which can improve the detection efficiency of the directed graph, to ensure that the directed graph used in task scheduling is acyclic.

The invention relates to the crossing field of water management and artificial intelligence. The method disclosed by the invention solves the problems of difficulty in coordination of multi-subject benefit conflicts, insufficient utilization of a basin spatial topological structure, separation of physical constraints and decision-making processes, limitation of adaptive ability and the like in the prior art. The method is characterized by comprising the steps of abstracting a drainage basin into a directed graph structure; generating a node embedding vector by using a physically guided graph attention network, and explicitly introducing a physical constraint factor in an attention mechanism; configuring an intelligent agent for each sub-basin to perform distributed strategy learning; cooperative training is carried out by adopting a multi-agent depth deterministic strategy gradient algorithm, fair distribution is guided by a global reward function in a Nash product form, and physical constraints such as water balance and the like are ensured in combination with a local reward function containing a nonlinear physical penalty term. According to the method, distributed, physically consistent and self-adaptive optimal configuration of drainage basin water resources is realized, and the method is mainly used for improving fairness, efficiency and feasibility of water resource distribution.

The invention provides a circuit energy efficiency automatic optimization method. The method comprises the following steps: firstly, modeling a circuit gate-level netlist into a directed graph; extracting a key path by using a static time sequence analysis tool, and extracting a context sensing key sub-graph containing the path and a first-order neighborhood node of the path; thirdly, feature coding is conducted on the key sub-graphs through a graph neural network, and state vectors representing the local state of the circuit are generated; the state vector is input to a reinforcement learning policy network to decide a drive capability adjustment action for a particular standard cell. And the system modifies the netlist according to the action, calls the static time sequence analysis tool again to evaluate the modified performance, power consumption and area indexes, and generates a reward signal to iteratively optimize the strategy network. By constructing the closed-loop optimization process, the problems of low manual optimization efficiency and unbalanced power consumption and area balance are solved, automatic and intelligent collaborative optimization of circuit energy efficiency is realized, and the design quality and efficiency are remarkably improved.

A computing system including one or more processing devices configured to receive a computational workflow specification. The computational workflow specification includes a plurality of workflow stages. The plurality of workflow stages include one or more unfilled workflow stages that each include a respective workflow stage objective, a respective workflow stage exit criterion, and one or more fillable fields. The computational workflow specification further includes a directed graph structure in which the plurality of workflow stages are arranged. Based at least in part on the computational workflow specification, the one or more processing devices are further configured to compute a filled computational workflow including one or more filled workflow stages. Computing the filled computational workflow includes computing respective filled values of the one or more fillable fields at least in part at a generative language model. The one or more processing devices are further configured to execute the filled computational workflow.

The application discloses a kind of chart representation method and its application supporting observation transmission and computing resource joint scheduling, mainly solve the problem that the prior art uses observation and transmission independent scheduling, transmission and computing independent scheduling, leading to the long time delay of ground observation task completion.Its implementation scheme includes: given the satellite network directed graph including multiple satellite nodes and the connection edge between node.According to its construction observation subgraph and two communication subgraphs;Observation subgraph is connected through observation satellite node between first communication subgraph;First communication subgraph is connected through computing satellite node between second communication subgraph, constitute graph representation model, so that observation, transmission and computing can be characterized in the same graph, support multi-dimensional resource joint scheduling.The application can map observation, transmission and computing joint scheduling problem from complex mathematical programming problem to routing problem in graph, reduce the complexity of problem solving, guarantee low latency demand, can be used for satellite network ground observation task.

The embodiment of the invention provides a method, device and equipment for determining transaction risk assessment attributes of an object, and the method comprises the steps: obtaining transaction data of a transaction object, and constructing a directed graph; determining a first low-order feature according to a first edge weight corresponding to the node in the first sub-graph and a second edge weight corresponding to the node in the directed graph, and determining a second low-order feature according to the total number of closed loops and the number of sub closed loops; determining neighbor node aggregation features according to the directed graph and the basic features; determining a high-order feature based on the initial node feature, the neighbor node initial feature and the neighbor node aggregation feature; and inputting the first low-order feature, the second low-order feature, the high-order feature and the basic feature into a transaction risk assessment attribute determination model to determine a transaction risk assessment attribute. According to the technical scheme of the embodiment of the invention, the transaction risk assessment attribute of the transaction object is determined based on the constructed directed graph and the multi-dimensional features, the risk account is effectively identified and assessed, and the accuracy of transaction assessment is improved.

The invention discloses a file code similarity analysis method, which is based on a directed graph isomorphism theory and comprises the following steps of: A, extracting characteristics of an open source code file, namely a Call Graph (Call Graph for short), and establishing a file sample library; b, extracting a function call relation graph of the file to be analyzed; c, executing the standardization work of the graph, and preprocessing the graph according to the related definition of the tree structure; d, extracting the maximum common subgraph of the function call relation graph of the file to be analyzed and the sample library file; and E, calculating a relationship between the maximum common subgraph and the function call relationship graph to obtain a similar result, and completing file code similarity analysis. According to the method, the similarity of the file codes is analyzed by depending on the function call relation graph, the internal characteristics and higher-level logic characteristics of the file codes are considered, and higher accuracy and efficiency are achieved. The method is suitable for occasions such as source code plagiarism detection.

The embodiment of the invention provides a branch topology priority dynamic sorting and collaborative allocation method and device based on a graph neural network, node attributes and branch section connection relations are assembled into a branch topology directed graph through skeleton extraction and branch node geometric attribute calculation, and accurate expression of a tree space structure is achieved. And constructing a graph attention risk inference mechanism, fusing an intrusion distance, a growth rate and a trunk involved weight, carrying out weighted fusion to obtain a node risk score, and generating a priority ranking table according to a descending order. Double-constraint cluster task collaborative allocation is introduced, and a task allocation table is generated according to a nearest constraint and a load balancing constraint in combination with a cluster real-time position and a load state and is issued and executed, so that the defects of a traditional technology in aspects of branch topology modeling, multi-factor risk sorting, cluster collaborative scheduling and the like are effectively overcome; and a technical guarantee is provided for power transmission corridor tree barrier hidden danger disposal.

The invention relates to software quality verification, in particular to a software quality verification system and method for logic alignment of an execution path and a design blueprint, a design logic atlas construction module is used for converting extracted blueprint logic elements into a design logic atlas in a digraph form and providing a standardized design reference for logic alignment; the execution path atlas construction module is used for converting the collected key program execution track data into an execution path atlas consistent with the design logic atlas in structure; the logic alignment algorithm module is used for calculating map similarity based on a map editing distance, quantitatively evaluating logic consistency between a design logic map and an execution path map, and outputting a logic alignment score; the difference analysis engine is used for carrying out deep analysis on parts which are not successfully logically aligned, identifying logic difference types and carrying out risk level evaluation; according to the technical scheme provided by the invention, the defect that logic consistency verification is difficult to carry out on the program execution logic and the original design intention in the prior art can be effectively overcome.

The disclosure provides a fault root cause dynamic prediction method and system based on probability propagation reasoning, relates to the technical field of fault positioning prediction, and comprises the following steps: constructing a directed graph structure, associating a dynamic fault probability with each node, and constructing a fault state expression system; based on the fault state expression system, calculating and dynamically updating the edge weight to construct a dynamic propagation graph model; generating the fault occurrence probability of the monitoring data, and fusing the fault occurrence probability to obtain aligned unified probability data; based on the dynamic propagation graph model, performing graph probability propagation reasoning on the unified probability data to determine the final root cause, thereby realizing rapid fault positioning; introducing an intelligent self-healing and strategy optimization algorithm based on reinforcement learning to automatically generate and execute a repair strategy, and continuously optimizing the decision through online learning to form a self-evolving safe operation and maintenance system. The disclosure realizes accurate and rapid prediction and positioning of system faults.

The invention relates to an intelligent medical record generation method and system. The method comprises the following steps: extracting each piece of data in accessed multi-type data and constructing a time-based event; constructing a directed graph arrangement event; traversing the directed graph, and verifying whether an event conforms to a rule base or not by using the rule base containing causal logical reasoning in the traversing process; and traversing the directed graph based on the medical record generation condition, and sorting the traversing result based on the generation type to obtain a medical record document. According to the method, multi-source data are fused in the generation process, and cross-modal and cross-cycle long text integrated generation is achieved; performing real-time calling and verification on related knowledge based on the ternary knowledge base to realize dynamic enhancement; a time-event chain reasoning mechanism and fine-grained reference are realized based on a directed graph, so that the traceability of the time sequence, causal logic and information sources of disease course records is ensured, posterior verification and feedback after quality inspection are supported, and a high-quality medical record generation basis is provided.

The invention relates to the technical field of information security, in particular to a sequential cipher security analysis method for a composite structure, which comprises the following steps of: acquiring round function parameters of a target cipher algorithm, nonlinear component definition and a key scheduling rule, and generating a standardized configuration data set; dividing the complete algorithm into a plurality of independent low wheel structures along the boundary of the nonlinear component according to the wheel function parameters, and constructing a directed graph data model containing state transition constraints to compress a state space; calling a password component vulnerability feature library to quantify a sub-structure active S box distribution abnormal value and a linear diffusion layer vulnerability path, and generating a risk weight priority ranking list; and inputting the state sequence data into the target application environment simulation platform, and generating a reproducible vulnerability report when the output deviation exceeds a security threshold. Through hierarchical compression, risk guidance and multi-environment verification, the technical defect of insufficient path coverage of a high-round-number lightweight algorithm in a resource-limited scene is solved.

The invention discloses a road and bridge major concept-oriented teaching association semantic matching method and system, and the method comprises the following steps: obtaining a road and bridge major concept set and a road and bridge major teaching content set, and carrying out the preprocessing of the road and bridge major teaching content set; constructing an engineering cognitive object representation for each road and bridge professional concept; constructing a concept dependence directed relation set, and generating a road and bridge professional concept dependence directed graph; constructing a teaching evolution constraint mechanism; performing teaching stage labeling on the teaching content standardized text unit set; determining a stage reachable concept candidate set according to a teaching evolution constraint mechanism, and constructing a matching feature vector; based on the matching feature vector, asymmetric teaching semantic matching calculation is executed, and a directional matching result set is generated. According to the method, asymmetric semantic matching of road and bridge professional concepts and teaching contents is realized through engineering cognitive modeling and teaching evolution constraint, and the method has the advantages of accurate matching and high cognitive consistency.

The application relates to the field of pneumatic control and digital simulation technology, and discloses a digital simulation optimization method for a cylinder multi-working-condition direction control strategy, which comprises the following steps: building a working-condition transition directed graph and configuring local control parameters from multi-working-condition continuous sequence parameters; obtaining a steady-state node ideal boundary constraint vector according to an equation group; separating a preposed constraint and a residual feedforward to obtain an actual injection initial value vector and a virtual truncated residual vector; integrating the initial value to obtain a transient operation curve and a final state and updating the residual feedforward; converting the truncated residual into a penalty energy, combining the equivalent fluid mechanical impact dissipation energy to synthesize total hysteresis dissipation energy measurement to update the control parameters, and over-limit reconstructing the directed graph, which is sent to a bottom programmable logic controller after convergence. The application guarantees integral stability through residual separation and energy conversion, realizes multi-working-condition continuous transition optimization by combining physical dissipation limitation and topological dynamic reconstruction, and avoids calculation divergence and solutionless dead cycle.

The application provides a whole vehicle external flow field joint prediction method based on double-flow fusion and multi-head graph attention, and relates to the technical field of vehicle dynamics analysis. The steps of the method comprise receiving a three-dimensional discrete point set of the whole vehicle shape; constructing a residual feature enhancement network to obtain a geometric high-dimensional feature vector; constructing a coordinate embedding network to obtain a high-dimensional coordinate embedding feature; adaptively weighting and fusing the geometric high-dimensional feature vector and the high-dimensional coordinate embedding feature; constructing a directed graph based on a k-nearest neighbor algorithm, splicing the aggregated features output by the multi-head, and obtaining global coupling features; inputting the global coupling features into a parallel first prediction branch and a second prediction branch; the first prediction branch outputs a three-dimensional pressure coefficient distribution map of the vehicle body surface through point-by-point regression; the second prediction branch fuses the global coupling features and key section embedding features, obtains section flow field prediction values through point-by-point regression, and outputs a key section two-dimensional flow field map.

The invention discloses a control method of a double-layer reconfigurable battery system considering path optimization, which comprises the following steps: establishing a battery mathematical model based on a Thevenin equivalent circuit, designing a double-layer reconfigurable topological structure consisting of a battery cluster layer and a single battery layer, and simultaneously collecting SOC and fault states in real time; according to the battery mathematical model and the double-layer reconfigurable topological structure, constructing a weighted directed graph model based on a graph theory; the weighted directed graph model is solved by introducing an algorithm, an optimal path from a source node to a sink node is obtained, and high-SOC monomer preferential discharge, energy loss minimization and rapid isolation of a fault unit are realized. According to the method, the flexibility of a double-layer topological structure and the advantages of multi-dimensional weight optimization are combined, the capacity utilization rate of the battery pack can be effectively improved, the SOC consistency is improved, the safety and reliability of the system are remarkably enhanced, and the method has wide application prospects in electric vehicles, energy storage power stations and other scenes.

This invention relates to the field of curtain wall performance simulation and optimization technology, specifically disclosing a curtain wall performance simulation and optimization analysis system, including: a drainage path topology construction module, a construction interference parameter extraction module, a pseudo-effective drainage path identification module, a drainage correction and water retention backtracking module, and a drainage structure optimization verification module. This invention constructs a directed graph of drainage path topology and extracts the set of construction interference parameters for each graph edge. It calculates the path effectiveness coefficient to determine the drainage effectiveness of each graph edge, marks pseudo-effective drainage paths, corrects the nominal cross-sectional parameters, re-simulates and evaluates the drainage capacity, and backtracks to locate water retention risk areas. Finally, it generates an optimization scheme and performs closed-loop verification until all pseudo-effective drainage paths are eliminated. This invention solves the problem of existing methods that use geometric connectivity to equip drainage effectiveness but cannot identify pseudo-effective drainage paths, thus improving the accuracy of curtain wall drainage performance simulation and the reliability of optimization.

This invention relates to a river network classification system and method based on graph theory and confluence accumulation, belonging to the fields of water conservancy engineering and geographic information technology. The method includes the following steps: acquiring raw DEM data and river system data, and converting the river system data to a preset projected coordinate system; extracting a primary river network based on the DEM data, and filtering the primary river network by combining river network length and drainage area to obtain a simplified river network; calculating river network flow: assigning flow values ​​to each river network element in the simplified river network based on confluence accumulation; graph theory modeling: abstracting the simplified river network into a directed graph model; river network classification: tracing back from the outlet as the starting point, combining node in-degree / out-degree and edge weights to determine the hierarchical relationship between the main stream and tributaries, thus realizing river network classification. This invention upgrades river network classification from "morphological description" to "hydrological function characterization," and is suitable for high-precision refined analysis of river networks and smart water conservancy emergency management scenarios.

The invention discloses a fire-fighting equipment safety assessment optimization system and method based on big data, and belongs to the technical field of big data. Image features are collected through a contour detection algorithm, feature data of a fire hydrant interface and a water hose interface are compared, and adaptive solution is carried out; when the fire hydrant connector is matched with the water hose connector, the appearance state is monitored, a water pipe network digital twinborn model is constructed, and the abnormal position is marked; simulating a fire scene, and triggering a preset graded supply strategy in combination with the water pipe network distribution and the water source position; in combination with the abnormal position, abstracting the abnormal position into a vertex and an edge of a graph structure, and constructing a directed graph model with a weight; when it is judged that water flow of a certain section of water pipe is blocked, path searching is executed in the graph structure, and a standby water supply path is screened; and a reinforcement learning algorithm is used, a control instruction is sent to the intelligent valves on the standby water supply path, the corresponding valves are opened according to the path sequence, irrelevant branches are closed, and a closed water supply channel from the water source to the target fire hydrant is formed.

The application discloses a large-scale flexible job shop scheduling method and system, acquires job shop related information; creates job agents, machine agents and inventory agents according to the job shop related information based on a multi-agent ant colony algorithm, initializes multi-agent ant colony algorithm parameters and pheromone initial values; constructs a disjunctive graph in the form of a directed graph according to the job shop related information, sequentially traverses the disjunctive graph, and job agents, machine agents and inventory agents generate scheduling solutions according to an agent negotiation protocol and update pheromones; after multiple iterations, it is judged whether a new optimal solution is generated, if the iteration number exceeds the preset number of rounds, the current optimal solution is output, and the final job shop scheduling scheme is obtained. Advantage: the shortest completion time, machine utilization rate and calculation time required by the multi-agent ant colony algorithm have obvious advantages compared with the prior art, and are more suitable for large-scale job scheduling problems.