333 results about "Directed graph" patented technology

The invention discloses an ice storage air-conditioning system optimization control method based on a dynamic programming algorithm, which comprises the following steps: acquiring operation data of an ice storage air-conditioning system in real time, and constructing a directed graph model, directed graph nodes and interconnection weights among the nodes; transferring and converting a cold storage and release operation mode of the ice storage air-conditioning system in a preset optimization time domain into a shortest path for solving the directed graph model; based on a directed graph model, solving a shortest path by using a dynamic programming algorithm; and on the basis of the shortest path, an ice storage air conditioning system control strategy is generated and issued to a system execution layer, and the control strategy comprises but is not limited to a switching decision of a cold storage and release operation mode in each time period of the optimization time domain and an equipment start-stop state. The cold storage and release operation mode is controlled through the dynamic planning method, efficient matching of cold storage air conditioner loads is achieved, the system energy efficiency is improved, the operation cost is reduced, and operation and maintenance operation is simplified.

The invention discloses a method for realizing a logic breakpoint debugging function of an industrial configuration control system, which relates to the technical field of industrial automation control, and comprises the following steps of: constructing a fault prediction model, performing multi-scale time sequence modeling and spatial correlation analysis on spatial-temporal characteristic tensors, and generating a high-probability fault pile point set; constructing an equipment logic association graph, performing ontology reasoning to obtain an association diagnosis characteristic graph of high-risk logic nodes, and generating a directional monitoring instruction set in combination with the high-probability fault pile point set; and performing space-time scene reconstruction and root cause path analysis on the high-confidence breakpoint trigger signal and the five-dimensional section snapshot to generate an interactive fault diagnosis report. According to the method, the equipment-logic association graph is constructed, graph traversal and ontology reasoning are carried out, the dynamic association relationship between equipment physical data and control logic execution data is modeled into a weighted directed graph structure, node risk values are quantized by utilizing a graph diffusion algorithm, and visual tracking of a fault propagation path is realized.

The invention belongs to the field of medical information systems, and provides a medical institution full-process doctor-seeing path planning method and system based on artificial intelligence, and the method comprises the steps: modeling each doctor-seeing link in a medical institution into a directed graph; the node features and the edge weights of the directed graph serve as input, the node features are updated through a graph neural network, and the weight of each node is dynamically generated; a queuing theory model is adopted for modeling according to the queuing condition of each node, and the average waiting time of each node is calculated; designing a multi-objective optimization function, and taking balance of the shortest path and the minimum waiting time as an optimization objective to generate an optimal doctor-seeing path scheme; the resource state of each node is dynamically monitored based on a real-time feedback mechanism of the Internet of Things equipment and a hospital information system, and when it is monitored that the resource state or waiting time of the node is changed, the graph neural network and the queuing theory model are recalled to update node features and priority weights.

The invention discloses a dynamic identification system and method for fault nodes of a heat pump measurement and control network, and aims to solve the problems of one-sided weight distribution, lack of directional modeling and insufficient dynamic adaptability in the prior art. The system comprises an energy transfer topology network model building module which is used for respectively quantifying the physical connection strength and the directional energy transfer path of the heat pump system by building an undirected graph and directed graph bimodal model; the multi-dimensional weight distribution module adopts a subjective and objective fusion strategy and combines a complex network theory, an entropy weight method and an analytic hierarchy process to distribute comprehensive weights for nodes and explicit modeling directivity dependence; the dynamic robustness analysis module is used for simulating and positioning structural hub nodes through static attacks, simulating and tracking cascade failure and topology reconstruction processes through dynamic attacks, and comprehensively evaluating the robustness of the system; and the fault simulation verification module verifies weight rationality and method effectiveness from four dimensions of objectivity, center matching degree, interpretability and robustness based on a fuzzy comprehensive evaluation framework. According to the method, through fusion topology modeling, dynamic weight distribution and dynamic and static combination robustness analysis, key fault nodes are accurately recognized, the system vulnerability is revealed, a data driving basis is provided for redundancy design, intelligent operation and maintenance and reliability improvement of the heat pump system, and the operation and maintenance cost is remarkably reduced.

The invention discloses a water supply network global water quality prediction method based on a double flow-graph convolutional network, and belongs to the field of urban water supply. According to the method, a pipe network model of a directed graph is constructed, information flows in the upstream direction and the downstream direction are extracted respectively, feature learning is carried out through a parallel graph convolution module, a random mask mechanism is introduced during training to simulate sensor missing, and accurate prediction of the water quality concentration under the sparse monitoring condition is achieved. According to the double flow-graph convolution water quality prediction model provided by the invention, the practicability and coverage capability of the water quality prediction model under the condition of sparse monitoring data are remarkably improved; a double flow-graph convolution structure and a dynamic mask training mechanism are adopted, so that the robustness of the complexity of a pipe network is effectively enhanced; the constructed water quality prediction model has the characteristic of high response speed, can realize real-time prediction of water quality in combination with historical monitoring data and network structure information, is suitable for various scenes such as water quality monitoring, abnormal early warning and intelligent regulation and control, and is beneficial to improving the operation efficiency and management level of a water supply system.

The invention discloses a graph theory-based industrial internet identification system full-process tracing method, which realizes full-process tracing in a supply chain by introducing identifier fields into metadata and constructing a directed graph structure. The identifier fields include fields with similar representations for representing associations of the product upstream and downstream of the supply chain. The system queries across enterprises through a graph traversal algorithm (such as depth-first search (DFS) or breadth-first search (BFS)), and tracks the full life cycle of a product. The method supports attribute pointing code management, is used for tracing multi-attribute information (such as allocation weight, time and the like) of a product, solves cross-enterprise and cross-system coding differences through an alias mechanism, and simplifies a tracing process. The method has a flexible traceability path setting capability, can monitor the product circulation process in real time, gives out an early warning when an abnormality is found, and improves the transparency and safety of a supply chain.

The invention discloses a heterogeneous unmanned cluster collaborative hunting method, device and equipment and a storage medium, and relates to the technical field of agent automatic control, and the method comprises the steps: determining a heterogeneous unmanned cluster, environment information and constraint conditions of a multi-agent collaborative hunting system, and constructing a physical model of the multi-agent collaborative hunting system; at the beginning of each decision cycle, modeling a task allocation problem of multiple agents into a'maximum flow-minimum cost 'graph theory problem, constructing a task allocation directed graph, determining an individual capture target corresponding to each agent, and based on a PPO framework, taking the maximum return of the corresponding individual capture target completed by each agent as an individual target, and performing task allocation on each agent; and with the maximum return of all captured targets completed by the heterogeneous unmanned cluster as a global target, an intelligent agent is guided to learn an optimal hunting strategy. According to the method, the problem of obvious insufficiency in the aspect of processing heterogeneous capability constraints in the prior art is solved.

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 discloses a new energy multi-mode fault diagnosis method based on dynamic graph convolution and transfer learning. According to the method, multiple types of sensors are deployed to collect operation, environment and historical data of new energy equipment, and a multi-modal data set is generated through preprocessing; the method comprises the following steps: defining an equipment component as a graph node, constructing a directed graph containing a time-varying edge weight by utilizing dynamic time warping and an attention mechanism, and updating a graph structure on line; a dual-branch dynamic graph convolutional network is adopted to extract multi-modal data features, an adversarial transfer learning algorithm and a meta-learning algorithm are combined, distribution of a source domain and a target domain is aligned, and a special diagnosis model is generated by using small samples. And fault classification is carried out, a fault component is positioned in combination with a graph node attention weight, and a fault evolution index is constructed by fusing a fault prediction probability and an attention weight change rate. The method effectively fuses multi-modal data, adapts to complex working conditions, improves small sample diagnosis precision, realizes fault accurate positioning and evolution prediction, and has important significance for guaranteeing stable operation of new energy equipment.

A method includes determining a set of features associated with a set of vertices of a directed graph, obtaining a set of feature values associated with the set of vertices, where each respective vertex of set of vertices is associated with a respective subset of feature values. The method includes determining updatable features based on the set of features, selecting a first subset of features based on the set of updatable features. Selecting the first subset of features includes determining candidate subsets of features, determining feature subset scores associated with the candidate subsets of features based on a category label, and selecting the first subset of features based on the feature subset scores. The method includes performing a first operation to determine extracted feature values by determining feature extraction input values.

The invention provides a financial risk dynamic prediction method based on deep learning, and relates to the field of financial risk dynamic prediction. The financial risk dynamic prediction process provided by the invention comprises the steps of constructing a financial risk prediction data set, calculating a deviation absolute value sequence of a factor data time sequence, and fusing and mapping the time sequence and the deviation absolute value sequence into a high-dimensional embedded vector sequence through a weighted nonlinear function; constructing a finite span directed graph by taking each time step as a graph node; introducing a structure resonance factor; carrying out weighted coding and weighted fusion on a path to form an aggregation context vector; calculating a risk score; overall feature representation of factor data is extracted in combination with a bidirectional long-short-term memory network, and finally a financial risk prediction value is calculated by using a full-connection neural network. According to the method, local deviation and global time sequence information are fused, and the accuracy of financial risk prediction is improved.

The invention discloses a digraph-based power grid abnormal event identification method and device, terminal equipment and a storage medium, and the method comprises the steps: obtaining current power data and historical fault data in a to-be-detected region, and extracting entities, relationships and attributes from the current power data and historical fault data to construct an initial digraph; acquiring historical power data, and adjusting the weight of a directed edge in the initial directed graph to obtain an optimized directed graph and conditional probability distribution of each node; performing Monte Carlo random sampling on the optimized directed graph to generate a plurality of abnormal event sequences; and determining the actual node state of each node according to the current operation parameter, matching the node state feature of the actual node state with the event state feature of the abnormal event for each abnormal event sequence, determining a target abnormal event sequence, and further identifying the abnormal event occurring in the power grid. According to the invention, the abnormal event of the power grid can be identified.

The invention provides a power distribution control cabinet fault response method and device, and relates to the technical field of electrical automation control, and the key points of the technical scheme are that a weighted directed graph model representing the relation of internal components of a power distribution control cabinet is constructed in advance; mapping component fault information predicted by the digital twin system to attributes of corresponding nodes in the weighted directed graph model; identifying a fault path or a fault cluster satisfying a predetermined condition; for each identified fault path or fault cluster, calculating a composite risk index according to the prediction probability of the nodes included in the fault path or fault cluster, the weight of the connection edge and the severity of the influence on the system; and generating early warning information according to the composite risk index. According to the power distribution control cabinet fault response method and device provided by the invention, a potential fault propagation path or a fault aggregation area can be identified based on physical, electrical and influence relationships among components, and a composite risk formed by a plurality of potential fault combinations is quantified, so that a preventive maintenance decision is guided.

The invention provides a water supply network hydraulic state prediction method based on a gating chart neural network, and belongs to the field of urban water supply. The method for predicting the hydraulic state of the water supply pipe network comprises the following steps of: firstly, initializing data of other pipe network nodes without sensors by utilizing water head data monitored by sensor nodes; secondly, abstracting a topological structure of the water supply pipe network, and constructing a pipe network adjacency matrix of a directed graph; and finally, on the basis of the pipe network adjacent matrix and the initialized node water head information, constructing a GGNN-based water head prediction model, and predicting water heads of all nodes in the water supply pipe network. According to the method, the accuracy of water head prediction can be improved by combining an initialization strategy based on a sensor and physical constraints; the GGNN model shows the capability of effectively adapting to various water supply pipe networks with different configurations, and the adaptability is high; the water head prediction model provides a reliable and efficient solution for real-time monitoring and pipe network management decision, and the real-time monitoring and decision support capability can be improved.

The invention belongs to the technical field of flow instruments, and provides a dynamic compensation and error correction system of a high-precision flow instrument, which comprises a multi-dimensional data acquisition and preprocessing module, a module capable of being additionally provided with a sensor, a module for establishing a data stream with a timestamp and processing data, a module for fluid network modeling and priori knowledge construction, and a data processing module. A distributed collaborative optimization and parameter calibration module capable of constructing a directed graph model and generating initial compensation parameters; a network association reasoning and dynamic weight distribution module capable of adding a global penalty term to optimize parameters on the basis of a traditional error function; a working condition adaptation calibration and cross-domain parameter migration module capable of constructing an association graph, detecting abnormity and distributing weights; real-object-free calibration and parameter migration can be realized; according to the system, through multi-module cooperation, the problem that traditional single-table compensation is local and is not global is solved, and high precision and real-time performance of industrial-grade cooperative metering are supported.

The invention discloses a text generation method and device based on a large model, equipment and a storage medium, and relates to the technical field of natural language processing, and the method comprises the steps: carrying out the semantic analysis of a preset field related document based on an encoder of an initial large model, and generating a target concept set and a target embedding vector; constructing an initial weighted directed graph according to the target concept set and the target embedded vector, and expanding the initial weighted directed graph to obtain a target weighted directed graph; determining a target sub-graph meeting a preset optimal condition from the target weighted directed graph by utilizing a preset optimization algorithm, and obtaining a target structured text part set based on the target sub-graph; and performing fine tuning on the initial large model to obtain a fine-tuned large model, and converting the target structured text part set into a target text meeting a preset field text specification by using the fine-tuned large model. Content innovation can be realized while strict logic is ensured and requirements of professional fields are met.

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.

A process includes receiving a request via an API, determining a query based on a set of query parameters, and determining a target graph portion template based on the query, where the request includes a callback address. The process may include searching a set of directed graphs to determine a set of graph portions based on the query. Each respective directed graph of the set of directed graphs may include a set of vertices and a set of directed edges connecting respective pairs of vertices among the set of vertices, where each respective vertex of the set of vertices is associated with a respective category label of a set of mutually exclusive categories. The process may include selecting a set of event records and sending a value of the set of event records to the callback address.

In some embodiments, a computer-implemented method includes reading a multiple dependencies. Each dependency can be between a pair of features of multiple features, the multiple features including a target feature. The method can comprise reading training data correlating each pair. The training data can comprise loan application data for multiple loans. The method can include determining, from the training data, a conditional probability for each pair of features. Each pair of features can comprise a first feature and a second feature. The conditional probability can represent a probability of the first feature based on an occurrence of the second feature. The method can include constructing a directed graph comprising multiple nodes and multiple edges. Each node can correspond to one of the features. Nodes corresponding to a dependency can be connected by an edge. The method can further include assigning the conditional probability to each edge corresponding to that pair.

The invention belongs to the technical field of automatic testing, and particularly relates to a test task scheduling method and system of a control system based on a graph model and deep reinforcement learning. The method comprises the following steps: analyzing a test task demand, and then constructing a Single-rate DAG task scheduling model; according to a Single-rate DAG task scheduling model, generating a directed graph as the input of a GNN; establishing a heat map about the edge based on the directed graph and the GNN; generating a task scheduling sequence according to the heat map, and planning a scheduling scheme according to the task scheduling sequence; calculating a loss function, and updating the graph neural network according to the loss function; repeatedly establishing the heat map to calculate the loss function until a high-quality solution conforming to an expected target can be planned or a difference value between a mean value and a minimum value of the planned test scheme makespan is smaller than a certain threshold value, and ending iteration; and step 7, outputting an optimized solution. The method is used for solving the problem that a planning result of a high-correlation test task scheduling process is often high in randomness and is difficult to meet actual requirements.

The invention provides a network traffic prediction method and system, computer equipment and a storage medium. The method comprises the following steps: on the basis of a preset multi-scale time domain period, preprocessing to-be-processed network traffic time sequence data of a current prediction period obtained according to a preset sampling duration interval to obtain to-be-analyzed traffic time sequence data of a plurality of time scales and a graph Laplacian matrix; a directed graph adjacency matrix is generated based on a multi-scale fusion graph Laplacian matrix obtained by performing weighted fusion on graph Laplacian matrixes of different time scales by taking the total variation of a minimized graph as an optimization target, and then the flow time sequence data to be analyzed of a preset prediction time scale are analyzed according to the directed graph adjacency matrix and the flow time sequence data to be analyzed of the preset prediction time scale. And obtaining a network traffic prediction value of the current prediction period based on a preset traffic prediction model. According to the method, the real internal relevance of the traffic data can be adaptively learned in a complex dynamic environment based on the time domain periodicity of the traffic, so that the reliability and accuracy of real-time prediction of the network traffic are effectively improved.

The invention discloses an efficient software testing method and system based on a UML (Unified Modeling Language) activity diagram, and relates to the technical field of software testing. Feature extraction is performed on a to-be-modeled system testing demand to obtain system sub-demands; the method comprises the following steps: sequentially sorting based on system sub-requirements, generating corresponding activity elements to generate a system activity graph model, converting an activity graph into a directed graph through a conversion rule, traversing the directed graph by adopting a search algorithm of a graph theory to generate test paths, and finally optimizing each test path by adopting a genetic algorithm to generate a test path set. And testing the to-be-modeled system through the test path set. According to the invention, through feature extraction of the test demand and the sub-demand, the comprehensiveness and pertinence of the test are ensured, the risk of missing key functions or scenes is reduced, and the test efficiency is 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 belongs to the technical field of computers and electronics, and discloses a graph neural network hardware Trojan detection method and system fused with an attention mechanism, and the method comprises the steps: S1, mapping a netlist circuit code carrying a hardware Trojan into a directed graph; s2, performing graph embedding, graph segmentation and graph sampling on the directed graph; s3, extracting inherent characteristics of the nodes through an encoder; s4, extracting node local features through a graph neural network; s5, extracting global features of the nodes through an attention mechanism model; and S6, carrying out feature fusion on the data inherent features extracted by the auto-encoder, the local structure features extracted by the bidirectional GCN convergence model and the global structure features extracted by the self-attention mechanism, and obtaining an HT detection result through a classification model. According to the method, the Trojan horse detection accuracy and efficiency are greatly improved; compared with an existing method, the detection range or type is expanded, and the method can be applied to hardware Trojan horse detection of a large-scale integrated circuit actually.

The invention is suitable for the technical field of data analysis, and provides an intelligent decision graph construction method based on dynamic time sequence event data, which comprises the following steps: reading and cleaning original event data, processing fields, expanding nested information through a structured analysis and entity alignment technology, and generating cleaned structured data; the frequency of different field combinations is calculated, a frequency feature column is generated in combination with a timestamp and a weight factor, and a multi-dimensional relation is combined; screening event pairs based on a dynamic frequency threshold, constructing a directed graph data structure, taking unique identifiers of the events as nodes, establishing edges of a graph, setting edge weights, and optimizing a time sequence relationship between the events through time sequence matching and a dynamic weighting mechanism; and outputting a graph containing the node number, the edge number and the graph edge data screened based on the frequency. According to the method, the accurate, efficient and intelligent graph construction method is realized, the technical progress in the field of dynamic event data analysis is promoted, and the method can be applied to an actual scene in which dynamic event data needs to be processed and an associated graph needs to be constructed.

The invention relates to the technical field of guide vehicle distribution, in particular to a medical material automatic guide vehicle distribution path optimization system and method, which are used for investigating and analyzing hospital layout, and understanding and analyzing personnel, traffic flow, medical material characteristics and distribution requirements; selecting a proper AGV type and navigation mode according to an analysis result; minimization of distribution time is determined, and AGV energy consumption and equipment loss cost are reduced; the method comprises the following steps: establishing a mathematical model, abstracting a hospital environment into a directed graph, constructing a shortest path model or a multi-objective optimization model, and considering constraint conditions including a time window and a priority; an improved genetic algorithm is adopted to solve the model, the distribution path of the AGV is encoded into chromosome, fitness function design, selection, intersection and mutation operation are performed, the optimal distribution path is searched, the distribution path of the medical materials is optimized through model construction and algorithm improvement, the distribution time is shortened, and the distribution efficiency is improved.

The invention relates to a causal structure constraint and inference method and system based on a large language model, and the method comprises the steps: inputting a variable understanding text and a variable understanding cue word to LLMs to output an understanding variable text; inputting into LLMs based on the understanding variable text, and combining a causal inference cue word to output a directed graph network set A1; inputting the initial directed graph network set A1 and an error correction prompt word into LLMs to output a corrected directed graph network set A; and taking the directed graph network set A as an ancestor constraint, and incorporating the ancestor constraint A into a score-based causal structure learning algorithm to obtain an optimal causal structure. According to the scheme, more accurate and credible causal relationship inference can be provided when a complex data set is processed.

The invention belongs to the technical field of recommendation algorithms, and discloses a personalized learning path recommendation method based on knowledge relation mining and graph embedding driving, and the method comprises the following specific steps: 1, mining a knowledge point dependency relation, constructing a weighted directed graph, carrying out the data analysis on public data sets ASSISTments and Junyi, and carrying out the data analysis on the public data sets ASSISTments and Junyi; the implicit dependency relationship among knowledge points is mined through an improved Apriori algorithm, time dynamics and sequential dependency characteristics in the learning process are fully considered, and a weighted directed graph among the knowledge points is constructed according to the mined dependency relationship and the weight of the mined dependency relationship. According to the method, the implicit dependency relationship between the knowledge points is mined through an innovative method, the weighted directed graph is constructed, and a graph embedding technology is integrated into a recommendation model in combination with a unique self-defined embedding layer, so that compared with an existing recommendation method based on a simple association rule or a shallow network, the method has the advantages that the recommendation efficiency is improved; the mining and expression ability of the complex logic relation between the knowledge points is remarkably improved, and the recommendation omission rate of the sparse knowledge points can be effectively reduced.

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.