513 results about "Complex system" patented technology

The invention discloses a failure chain quantitative analysis and risk assessment method and system based on a multi-level security model, and aims to solve the defects that accident cause analysis of a complex social technology system is inaccurate, and a risk assessment result is lack of effective verification. According to the method, a multi-level causal model is systematically constructed, a multi-dimensional failure chain (MDFC) is extracted, multi-dimensional risk quantification is performed on the MDFC, a directed weighted failure propagation network is constructed based on the multi-dimensional risk quantification, and structural features of the directed weighted failure propagation network are analyzed to identify key risk factors. The core innovation of the method is that reverse accident reason tracing and forward risk propagation path analysis based on the weighted network are fused, mutual verification and iterative optimization are realized by comparing analysis results of the two paths, so that the understanding of an accident evolution mechanism is deepened, and the reliability of evaluation is improved. The system vulnerability can be revealed more comprehensively, powerful support is provided for formulating accurate risk control measures, and the overall safety level of a complex system is improved.

The invention discloses a drainage basin maintenance intelligent management system based on the Internet of Things and intelligent decision, and relates to the technical field of computers. Comprising a multi-source perception and edge access module which is used for realizing multi-protocol access, time and session alignment, data quality labeling, breakpoint resume and edge side anomaly preliminary screening of industrial data, low-power-consumption point location data and video and thermal image data. According to the invention, through the multi-source sensing and edge access module, various types of data such as industrial data, low-power-consumption point location data, video and thermal image data can be processed, the technical problems of multi-protocol access, time and session alignment, data quality labeling and breakpoint resume and the like are solved, the integrity and reliability of the data on the edge side are ensured, and the service life of the data is prolonged. The edge side anomaly preliminary screening function significantly improves the timeliness of early fault discovery, reduces the network bandwidth pressure, effectively solves the problems of anomaly cooperative detection and alarm flooding in a complex system, and improves the accuracy and timeliness of fault early warning.

The invention discloses a conversion method and system based on SysML and Modelica model semantic mapping. The method comprises the following steps that S1, a Modelica standard model library is imported into a SysML modeling tool; s2, completing the definition of behavior elements, and forming an SysML model instance; s3, exporting a Modelica model which can be executed by the Modelica simulator; s4, establishing a mapping relation table between SysML model elements and Modelica model elements; s5, when a change event occurs in the SysML model, updating the content of the corresponding Modelica model; s6, the Modelica model is imported into the SysML model, and a corresponding SysML model instance is generated; s7, simulation result mapping and behavior modeling generation are executed, a state transition diagram structure is formed, and structure updating of internal block diagrams in the system model is completed. According to the method, bidirectional conversion and joint simulation optimization between models are realized, and the method is suitable for cross-platform modeling, collaborative design and functional verification scenes of a complex system.

The invention relates to the technical field of power system data processing and network security, in particular to a system log data anomaly detection and management system and method. The system comprises an atlas establishment module, an anomaly identification module and a feedback adjustment module. According to the method, the global knowledge graph is constructed through the graph establishment module, the deviation degree is calculated in combination with historical baselines, direct association anomalies are judged, the potential influence degree between nodes is calculated based on a graph neural network propagation mechanism through the anomaly recognition module, and non-direct association anomalies are recognized through feature vector cosine similarity. A multi-dimensional feature matching rule base is combined to determine an anomaly type and execute response measures, a feedback adjustment module collects execution data through buried points, quantifies and evaluates effectiveness, optimizes a scheme through feature backtracking and root cause positioning and relies on digital twinborn simulation and gray scale landing to realize scheme iteration, and a feedback adjustment module performs feedback adjustment. The accuracy of anomaly detection and the dynamic adaptation capability of response measures are improved, and the method is suitable for log management and risk prevention and control of a complex system.

The invention discloses a multi-modal attack identification method fusing BMama and difference to guide trans-attention, which comprises the following steps: simulating a false data injection attack, a denial of service attack, an address resolution protocol spoofing attack and a domain name system spoofing attack, collecting physical layer sensor data and network layer flow data, and preprocessing multi-modal data; bMama is constructed to perform dynamic time modeling on multi-modal data, a graph neural network is combined to adversariate a variational auto-encoder, features of a power grid system topology and a communication topology structure are fused, and robustness of potential representation is enhanced through adversarial training; the method comprises the following steps of: guiding feature complementary fusion by using modal difference through a difference guide iteration cross-attention fusion mechanism, improving the capability of distinguishing complex attacks, finally carrying out attack detection and classification on fused modals, and executing end-to-end optimization according to a weighted combination of loss of each part. The method can effectively detect and classify the multi-modal attack in the smart power grid, and enhances the safety and reliability of a complex system.

Digital model platform that enables the streamlined creation and management of digital twins and physical twins by leveraging external feedback and artificial intelligence (AI) is disclosed. Methods and systems for a model collaboration platform that facilitate the integration of external feedback, whether from physical, virtual, or human sources, into the streamlined design, validation, verification, certification, assembly, operations, and maintenance processes of complex systems. Updated results are output to those external sources, including physical twins, other digital twins or models and simulations, and / or human users. External feedback includes feedback data from physical prototypes and their environment, virtual prototypes, simulations, and subject-matter experts. Embodiments are directed to integrating external feedback into the assembly and system-level assessment of digital twins, physical twins, digital threads, and the iterative design of constituting digital engineering models, including constructing, maintaining, and improving digital engineering models for the design, validation, verification, certification, operations, and maintenance of complex systems.

The invention discloses an unauthorized vulnerability detection method, device and equipment and a readable storage medium, and is applied to the field of security detection, and the method comprises the steps: carrying out the semantic recognition of real business flow data through a large language model, and determining a to-be-detected interface; performing semantic analysis on the parameters of the to-be-detected interface by using a large language model to determine target parameters; extracting a parameter value with an unauthorized vulnerability risk in the target parameter from the historical real service flow data; generating a test effective load of the to-be-detected interface based on the target parameter and the parameter value by utilizing a large language model and a preset rule base; and performing unauthorized vulnerability detection on the to-be-detected interface by using the test payload, and determining a detection result. According to the method, the natural language understanding capability of a large language model is utilized, the limitation of traditional regularization preprocessing and effective load generation is broken through, and the method is adaptive to diversified scenes of a complex system.

The various embodiments herein provide a system and method for networked digital twins with autonomous collaborative decision-making. The system comprises a Digital Twin Engine for real-time data acquisition, model synthesis, and simulation, an AI Module for advanced data analysis, an autonomous collaborative decision-making module for optimized decision-making, a communication layer for secure data exchange, and supporting modules for coordination, storage, security, and user interaction. The method for generating and deploying digital twins comprises data collection, transmission, preprocessing, model synthesis, simulation, validation, and deployment. The method for networking and collaboration comprises AI-based data processing, complex event processing, autonomous decision-making, task distribution, decision communication, real-time monitoring, and continuous improvement. This system enhances operational efficiency, scalability, and security, reducing the need for human intervention and providing a comprehensive management solution for complex systems.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as financial science and technology and medical health, and discloses a root cause analysis method and device based on a space-time dependency graph, equipment and a medium. Comprising the steps of constructing a space-time dependency graph, generating a diagnosis path blueprint, identifying a fault source and a root cause entity type, generating a graph query statement, executing query and performing cause and effect verification, and outputting a root cause analysis report. And the causal reasoning and root cause positioning of the system state change are realized by fusing the graph structure information and the natural language processing capability. Through cooperative processing of a language model and a graph data structure, fault symptom information and system structured state data are deeply fused, a path is generated in the graph structure, and a causal relationship is verified, so that the ability of understanding a complex system state evolution chain is improved, and accurate identification and diagnosis of root causes are realized. And the accuracy and the automation level of root cause analysis are obviously enhanced.

Disclosed in the present invention are a wind field correction method and system applied to a single-station remote sensing device. The method comprises the following specific steps: S1, acquiring wind field data by means of a data information acquisition apparatus, and obtaining radial wind speed information of a current acquisition point by means of a data processing module; S2, on the basis of the hypothesis of an uniform wind field, using a classical wind speed reconstruction algorithm for inversion to obtain a three-dimensional wind speed vector of the acquisition point; S3, establishing an error model; and S4, on the basis of an error factor β calculated by means of the error model, performing data correction on the three-dimensional wind speed vector of the acquisition point obtained by means of inversion in S2. Compared with the prior art, the present invention provides a high-precision correction method, which can be operated on low-end hardware, and can also be directly installed and operated on hardware of a measurement device, so that measurement results can be corrected in real time, no additional complexity can be brought to users, and costs are reduced; and the present invention is suitable for solving complex system problems when accurate boundary conditions cannot be obtained.

The invention discloses a metering equipment distribution decision simulation analysis method, and belongs to the technical field of computer data processing and simulation, and the method comprises the steps: fusing multi-source heterogeneous data to construct a space-time knowledge data set; performing causal inference based on the data set, and establishing a causal relationship graph; performing risk propagation deduction and causal link evolution simulation on the map to generate a risk situation set; generating an anti-fact intervention strategy for the risk situation; and performing quantitative analysis to output an optimal distribution strategy, and feeding back and updating the causal relationship graph by using an analysis result. According to the method, the data processing architecture of the dynamic knowledge graph is constructed by adopting causal inference, multi-step propagation inference and link evolution simulation can be carried out on risks in a complex system, and the accuracy and robustness of a data processing system for carrying out prospective decision making in an uncertain environment are remarkably improved.

The invention discloses an equipment anomaly tracing method and system based on a digital twinborn and graph neural network, and belongs to the technical field of industrial intelligent operation and maintenance and fault diagnosis. The invention provides an innovative solution integrating digital twin high-fidelity simulation and a graph structure deep learning algorithm, aiming at the technical bottlenecks that the generalization performance of an existing data driving method is insufficient under the conditions of fault sample scarcity and category imbalance and the traceability accuracy of unknown and composite faults is poor. The method comprises the following steps: constructing a high-fidelity digital twin integrating multi-dimensional physical attributes and a system topology structure; based on a fault mode, influence and harmfulness analysis method system, constructing a fault mode library comprising a plurality of single fault modes and composite fault modes, and generating an enhanced training data set with accurate labels through an automatic fault injection mechanism; training a graph neural network model with a multi-level attention mechanism by using the data set so as to learn a propagation rule of a fault in a complex system topology; and finally deploying the model to carry out abnormity traceability analysis on real-time industrial Internet of Things monitoring data. According to the method, the fault diagnosis generalization ability and the positioning precision under the sample imbalance condition are remarkably improved.

The invention relates to the technical field of Internet of Things, and discloses a remote diagnosis system and method for a complex system in an Internet of Things environment, and the system comprises a data collection module which is used for collecting the operation state information of the complex system; the data transmission module is used for transmitting the running state information to the cloud processing center; the cloud processing center is used for performing fault analysis according to the received operation state information based on a machine learning algorithm, generating a fault diagnosis result and a corresponding maintenance suggestion and transmitting the fault diagnosis result and the corresponding maintenance suggestion to the user terminal; and the user terminal is used for receiving the fault diagnosis result and the maintenance suggestion, remotely accessing the system state report of the complex system and remotely controlling the complex system. According to the invention, efficient remote monitoring, accurate fault diagnosis and real-time maintenance guidance of the complex system in the Internet of Things environment can be realized, the maintenance cost is reduced while the maintenance efficiency is improved, and thus the maintainability and safety of the complex system are enhanced.

The invention belongs to the technical field of root cause analysis in intelligent operation and maintenance, and discloses a method for mining fault propagation weight parameters, and the method comprises the following specific steps: S1, supervising data root cause probability initialization, S2, supervising data topology perception labeling, S4, unsupervised data space-time slicing, S5, multi-modal root cause reasoning, S6, parameter increment fusion and S7, online adaptive optimization. Precise modeling and dynamic adaptation are achieved through multi-stage collaborative optimization, and the root cause positioning capacity of a complex system is remarkably improved: a supervised and unsupervised data dual-drive strategy is adopted, a root cause probability baseline is constructed by utilizing work order history, and alarm streams are processed in combination with time-space slice standardization to form a structured knowledge base; the method comprises the following steps: quantifying a transition probability in a CMDB dependency relationship through topology perception annotation and a four-dimensional observation matrix, and constructing a feature matrix containing TP / FP counting to support accurate calculation of a probabilistic graph model;

The invention provides a simulation test key factor screening-oriented method and system and a computer program product. The method comprises the following steps: generating a structured configuration file; constructing a supervised learning data set based on the structured configuration file; based on the supervised learning data set, training a machine learning classification model to obtain a current key factor set; and repeating the steps, judging whether the current key factor set is converged or not, and if the current key factor set is converged, stopping simulation and outputting the current key factor set of the last round as a final key factor. According to the technical scheme of the invention, a high-dimensional, nonlinear and high-coupling complex system can be automatically processed; key factors are objectively recognized through machine learning, a small-batch iteration verification mechanism is adopted, and the screening accuracy and efficiency are improved while the number of times of simulation is remarkably reduced.

The invention discloses an intelligent group area coverage control-oriented multilayer game reinforcement learning method, which comprises the following steps of: mapping each agent in an intelligent group into a game player, and constructing an income evaluation mechanism in combination with a task target of the agent to form a group game model; constructing a perception model and a communication model based on physical capability constraints of the intelligent agent, designing evaluation indexes of coverage efficiency, operation safety, energy consumption efficiency and communication collaboration, and integrating the evaluation indexes into a vector revenue function of the intelligent agent; a TD3 model is adopted as a game player role of an intelligent agent, and association between reinforcement learning and group game is established; and constructing a multi-layer semi-distributed game reinforcement learning framework, carrying out environment interaction, and solving an intelligent group area coverage control strategy meeting Pareto-Nash equilibrium. According to the method, the balance of individual and collective benefits is realized, the calculation efficiency is improved through a semi-distributed iterative algorithm, and the method is suitable for solving requirements of a large-scale complex system.

The invention discloses a complex system data visualization modeling method based on GIS and topological graph fusion, and relates to the technical field of data visualization modeling, and the method comprises data fusion modeling, space-time anomaly reasoning, state propagation modeling and multi-dimensional visualization enhancement. The method comprises the following steps: performing unified access, cleaning and standardization processing on operation data, topological relation data, geographic space data, function configuration data and environment data of a complex system, and constructing a unified data model fusing geographic attributes and topological attributes; realizing abnormal root cause reasoning and spatial constraint propagation modeling of a system state by using a convolutional time sequence modeling method combined with a graph neural network; a dynamic evolution rule of a node state is described through a time gating mechanism, and interactive display is realized; according to the method, global visualization of the operation state of a complex system, dynamic backtracking of an abnormal propagation path and hierarchical analysis of key nodes can be realized, and the intelligent monitoring, situation awareness and decision support capabilities of the system are improved.

The invention discloses a cascade fault diagnosis method based on a root cause intensity power set belief rule base. According to the technical scheme, the method comprises the steps of 1, constructing a power set belief rule base; the conclusion hypothesis unit can clearly describe a single-point fault state, a composite fault state and a causal chain fault state. And 2, introducing a root cause strength parameter: introducing the root cause strength parameter into the conclusion hypothesis unit constructed in the step 1 for quantifying the causal influence capability of the fault state as the root cause. And step 3, reasoning fusion: calculating the matching degree and the activation degree of each rule, and applying an evidence theory-based reasoning fusion algorithm to an output result to obtain power set confidence distribution of each fault hypothesis. And step 4, fault diagnosis and fault root cause positioning are carried out, and a main fault root cause is output, and the main fault root cause is the root cause with the maximum root cause strength. The method is mainly used for realizing accurate diagnosis of cascade faults in a complex system by popularizing a traditional BRB model to power set reasoning and introducing a root cause strength concept.

This invention introduces a sophisticated system for deploying projects on cloud platforms, combining Unikernels, Cyber Security Mesh Architecture (CSMA), MQTT protocol with SHA256 encryption, an Unikernel Orchestration Rules Engine (UORE), generative AI, and an innovative caching mechanism. Unikernels offer a secure, isolated environment for applications, reducing overhead and boosting performance. CSMA provides extensive security through analytics, identity management, and policy enforcement. The MQTT protocol, secured with SHA256, ensures the integrity and confidentiality of communications. UORE automates deployment, integrating a TLS terminator and data management for streamlined operation. Generative AI proactively resolves deployment challenges, particularly for complex applications, while the caching mechanism enhances performance and efficiency by minimizing latency. This integrated approach automates and secures the deployment process, enabling scalable, efficient, and real-time project creation and deployment in the cloud, thereby addressing the key challenges of cloud application hosting.

The invention discloses an intelligent operation and maintenance and fault handling method based on an AI large model, and relates to the technical field of artificial intelligence and information, and the intelligent operation and maintenance method comprises the following steps: multi-source heterogeneous data fusion, cross-level fault analysis, handling strategy generation and verification, and resource optimization scheduling. The method has the advantages that multi-source heterogeneous data of the equipment layer, the software layer and the service layer are synchronously collected through the sensing layer, the space-time aligned feature matrix is constructed, the limitation that traditional operation and maintenance only depend on single-level data is solved, the time dependence and level incidence relation of the data can be mined at the same time in combination with a multi-mode AI large model of the analysis layer, and the data processing efficiency is improved. The fault root cause probability distribution and the influence hierarchy are accurately output, misjudgment or missed judgment caused by single hierarchy data deviation is avoided, and the accuracy of complex system fault positioning is remarkably improved.

The invention discloses a complex system comprehensive multi-view consistency detection method based on a large model, and relates to the technical field of information system architecture design. The method comprises the steps that N view models to be detected are determined, and a rule base is constructed and formed; forming a triple set; performing rule retrieval on the triple set to obtain a corresponding rule subset; and constructing a complete prompt statement according to the prompt template and the rule subset, and reasoning the prompt statement by the large language model to obtain a consistency detection result. Based on the MBSE method, the ability of understanding, reasoning and applying knowledge in the field of system architecture and system engineering is remarkably improved, the automation degree, accuracy and robustness of multi-view consistency detection are improved, and the correctness, completeness and consistency of complex information system architecture design are guaranteed.

The invention discloses an intelligent fault tree generation method and system based on joint simulation and dynamic causal reasoning, relates to the technical field of fault trees, and solves the problems that the manual construction efficiency of a complex system fault tree is low, the hidden failure path omission ratio is high, and a model and operation and maintenance data are disjointed. The method comprises the following steps: constructing a multi-physics field coupled system joint simulation model; capturing a propagation path of the fault among the functional units in real time, and generating a fault propagation map; constructing a minimum cut set based on Monte Carlo simulation and Bayesian network reasoning, and automatically adapting an AND / OR logic gate to generate a fault tree; and dynamically updating the knowledge graph in combination with an online learning technology. The method has a good application prospect in the field of health management of equipment with high safety requirements.

The invention discloses a nuclear accident emergency three-layer coupling network model and a construction method, and relates to the crossing field of nuclear accident emergency management and complex system risk simulation. The nuclear accident emergency three-layer coupling network model comprises an RMN layer which is used for simulating the dynamic diffusion process of radionuclides leaked by a nuclear accident in the atmosphere; the IN layer is used for constructing a spatial distribution and dependency relationship network of infrastructures; the EN layer is used for topologically defining a command or cooperation relationship of the emergency organization; according to the three-layer network coupling mechanism, when RDR of a middle grid is larger than or equal to RDRmax-1, IN-layer nodes in the middle grid at the same position are marked to be in a damaged state; and quantifying the bidirectional dependence density of the IN layer and the EN layer through the coupling strength epsilon. The method is used for predicting the direct risk of radioactive contamination in a nuclear accident and the secondary risk caused by emergency evacuation, revealing the risk evolution law, quantifying the risk diffusion scale, determining key influence factors, and providing a theoretical basis for formulating an emergency strategy.

The invention is suitable for the technical field of system fault monitoring, and provides a system fault monitoring method based on log real-time synchronization and active scanning, and the method comprises the steps: capturing a log increment in real time through a file system event monitoring trigger, analyzing a newly added log content, and synchronizing the log increment and the newly added log content to message middleware; a distributed active scanning unit is configured, the scanning period is dynamically adjusted, and node resources are expanded and shrunk based on the containerization technology; integrating the abnormal data of the user side, the interface state data of the server side and the log stream data, and constructing a multi-modal data set; a normalized error report increment is calculated based on a 30-minute sliding window, and a pre-processing instruction is generated in combination with a random forest algorithm and Bayesian optimization; executing corresponding operation according to the pre-processing instruction; according to the method, a traditional passive mode is broken through, the fault monitoring confidence coefficient is remarkably higher than that of an industry standard, sub-health perception and active blocking of a high-concurrency scene are supported, and a real-time and accurate intelligent operation and maintenance solution is provided for a complex system.

The invention relates to the technical field of program control, in particular to a reamer machining path intelligent optimization method and system based on artificial intelligence, and the method comprises the following steps: collecting a reamer main shaft load torque and a Z-axis feed current in the process that a reamer cuts into a workpiece, and generating a reaming contact area resistance characterization quantity; and mapping the resistance characterization quantity of the reaming contact area to generate a hardness distribution characteristic value of the workpiece material. According to the method, differential operation is carried out on a generated nonlinear track, the acceleration change rate of the nonlinear track is extracted, the dynamic complexity of a motion state is quantitatively evaluated, the dynamic complexity is combined with a contour error predicted by AI, a dynamically weighted feed-forward compensation amount is formed, and when a motion instruction is complex and the system following capability faces challenges, the compensation effect is enhanced; according to the predictive compensation mechanism, active suppression can be carried out before the servo error actually occurs, and the contour tracking precision of a complex nonlinear instruction is improved.

The invention relates to a superconducting power knowledge system construction method and system based on a lightweight large model. According to the method, multi-source data is utilized for unified representation, deep semantic information is obtained through a lightweight large model, knowledge extraction is achieved, and a basic knowledge graph is constructed; further forming a knowledge graph which can be dynamically updated through knowledge fusion; and in combination with real-time data, adaptive multi-hop reasoning is executed, and a diagnosis and decision result with a causal chain is generated. According to the method, the semantic understanding and reasoning ability of a lightweight large model is taken as a core, the structural expression advantage of a knowledge graph is combined, the limitation of updating lagging and fixed rule reasoning rigidness of a traditional static knowledge base is broken through, and precise cognition and causal chain inference of a complex system state are achieved. The method has universality and mobility, and is suitable for knowledge modeling and intelligent diagnosis of various electric power scenes and other complex industrial systems. The method is verified by taking a superconducting power system as an example, and the feasibility and effectiveness of the construction path are proved.

A platform for adaptive multi-agent simulation in a virtual world instantiates a set of agents with input traits and executes a simulation session, generating an output set. Upon detecting a change event in the virtual world, a trained model recommends an evolution operation, which is applied to the set of agents to generate an evolved set. The evolution operation includes mutation, selection, crossover, deletion of agents, or a combination thereof. The platform persists at least a portion of the initial output set and executes a second simulation operation using the evolved agents, generating a new output set and thereby enabling analysis and comparison of simulation results. The disclosed adaptive simulation approach with persisted context enables realistic and dynamic modeling of complex systems.

The invention discloses a supply chain risk dynamic early warning method and system based on time series data association analysis. The system comprises a sensing layer, an analysis layer and an application layer. The sensing layer comprises sensors applied to all links of the supply chain; the analysis layer comprises a time sequence data processing module, a dynamic dependency modeling module and a real-time risk calculation module; the application layer comprises an intelligent early warning module, and when the comprehensive risk score obtained by the real-time risk calculation module reaches a corresponding early warning threshold value, the intelligent early warning module is triggered, and early warning information is sent out in time by integrating different communication interfaces. According to the invention, an intelligent and closed-loop industrial monitoring and diagnosis system is formed through all frontier technologies, transition from passive response to active prediction, accurate positioning, rapid disposal and root cause treatment is realized, and powerful technical support is provided for guaranteeing safe, stable and efficient operation of a complex system.

The invention discloses a diagnosis scheme generation method and system based on multi-scale hypergraph and constraint optimization, and belongs to the technical field of industrial equipment health management. The method comprises the following steps: receiving fault diagnosis query information expressed by a natural language, and carrying out semantic analysis on the fault diagnosis query information to form semantic guide information; task nodes are extracted from the technical information set, and a multi-scale nested subgraph is constructed according to the relation between the task nodes; based on the multi-scale nested subgraph, dynamically reconstructing a task path, representing task nodes as hypergraph nodes, and constructing a multi-scale hypergraph; performing structure sensing regularization processing on the multi-scale hypergraph to obtain the multi-scale hypergraph; performing cross-scale attention processing on the multi-scale hypergraph to obtain a multi-scale fusion hypergraph; and generating fault diagnosis paths based on the multi-scale fusion hypergraph, sorting the fault diagnosis paths, and outputting a diagnosis scheme. According to the invention, the intelligent level and decision-making efficiency of complex system fault diagnosis can be significantly improved.

The invention relates to a knowledge graph and thinking chain reasoning-based complex system demand identification and management method. The method comprises the following steps of S1, constructing a system demand classification network model; s2, constructing a demand structured extraction model based on a thinking chain; and S3, constructing a general demand knowledge graph and a target graph, and complementing the target graph. Through fusion of the knowledge graph and the thinking chain reasoning technology, the problems that in the prior art, classification model precision is low, extraction model leak detection is high, and graph model universality is poor are solved, and the method is suitable for demand modeling in the fields of subways and high-end equipment.