195 results about "Structure mapping" patented technology

The invention discloses a road and bridge parameter anomaly detection method, and belongs to the technical field of civil engineering. Comprising the following steps: step 1, establishing space-time relevance and a data mapping relation between monitoring points; 2, self-adaptive updating of the judgment rule is achieved so as to adapt to state evolution of a bridge service stage; step 3, performing intelligent attribution analysis on abnormity in the monitoring data; step 4, carrying out joint identification and comprehensive evaluation on the sudden structural damage and the slow degeneration degradation process; and 5, carrying out quantitative analysis on the deviation degree of the bridge health state, and generating a standardized bridge health index. According to the method, the space-time correlation network and the environment-structure mapping function between the monitoring points are established, and a multi-dimensional feature extraction and dynamic weight distribution mechanism is combined, so that environment interference elimination, abnormal attribution intelligent analysis and joint identification of sudden damage and slow degeneration are realized, and finally, a standardized health index is quantified and generated.

The invention discloses a logistics traceability system and method based on a block chain technology, and relates to the technical field of logistics traceability, and the method comprises the steps: constructing an event graph structure containing a plurality of behavior event nodes, and calculating a structure closure signature value; judging whether the original data of the behavior event node is written into the block chain or not according to the responsibility structure weight value; constructing a verification path mapping graph based on the structure closure signature value and the responsibility structure weight value; when a traceability request is received, calling the verification path mapping graph, performing consistency verification on the original data of the target behavior event node and the structure mapping hash value, and generating a traceability verification result; according to the method, the credibility of the behavior event data structure is improved, meanwhile, the on-chain storage cost is effectively reduced, and the technical contradiction between full-uplink data and non-uplink data is solved.

The invention relates to the technical field of state monitoring, and discloses a tower inclination state monitoring method and system. The method comprises the following steps: performing multi-field digital coupling modeling on an electric power tower to obtain a digital twinborn model and calculating an electrical load-structure response sensitivity matrix; collecting a multi-modal sensing characteristic data set including tower inclination angle time sequence data, insulator chain offset, tower body micro-vibration spectrum and foundation settlement gradient; performing time-delay correlation analysis on the electrical event and the structure response to obtain an electrical-structure mapping matrix; tensor decomposition processing is carried out through a multi-mode inclination feature fusion network, and tower inclination mode fingerprints are obtained; and carrying out abnormal separation processing on the tower foundation area, the connection area and the upper structure area, and outputting structural inclination and non-structural inclination judgment results. According to the invention, the accurate mapping relation between the electrical load and the structure response is realized, the false alarm rate is effectively reduced, and the accuracy and timeliness of early warning are improved.

The invention discloses a bank loan business risk control system and method based on big data analysis, and relates to the technical field of financial risk control, and the method comprises the steps: collecting and preprocessing real-time behavior data, and obtaining a user behavior feature set; based on the user behavior feature set, calling a behavior map modeling engine to carry out structured mapping, matching with a risk anchor point rule base, identifying a potential risk mode and labeling an initial anchor point risk label; correcting the deviation between the initial risk anchor point tag and the actual default record by adopting a value function optimization method, and predicting the risk grade score of the current behavior of each user in combination with the historical behavior sample data and loan feedback data of the user; predicting probability distribution of migrating to a default state in the future through user risk grade scores and historical state evolution data; and in combination with the potential loss under each behavior path, evaluating the current loan business risk, and generating a risk control strategy through a risk level mapping rule and a strategy decision engine.

The invention discloses a multi-time-scale charging load and energy storage cooperation probability prediction method, and relates to the technical field of power systems and smart grids, and the method comprises the steps: obtaining historical multi-source data of a target system, and constructing factor sub-graphs of different time scales; coupling the cause sub-graphs into a time cause feedback atlas through a structure mapping function, wherein the atlas comprises explicit time scale control nodes; executing cross-time-scale causal effect calculation based on the time factor feedback atlas to generate a causal effect matrix; using the causal effect matrix to construct a joint probability prediction model, and outputting a first prediction result; and when it is monitored that the deviation of the first prediction result exceeds a dynamic threshold value, triggering a time scale switching mechanism to generate a second prediction result. According to the method, multi-scale causal modeling is realized by constructing the time cause feedback atlas containing the time scale control nodes, dynamic scale switching and a residual compensation mechanism are combined, the prediction precision and the scheduling adaptability are remarkably improved, and multi-time-scale collaborative optimization management is realized.

The invention discloses an H-bridge key equipment service life and system reliability evaluation method and system for a cascade network construction type energy storage system, and belongs to the technical field of power system automation. The method comprises the following steps: firstly, extracting task profile parameters under multiple time scales, and constructing a time sequence feature model; secondly, estimating a hot spot temperature sequence of the IGBT device and the capacitor based on a multilayer feedforward neural network; then, in combination with a continuous extreme point paired temperature cycle extraction method and a Miner linear cumulative damage criterion, the damage factor and the residual life of the device are evaluated; then, task profile samples are expanded based on a generative adversarial network with gradient penalty, and life distribution and reliability indexes of key devices under different profiles are calculated; and finally, based on H-bridge series structure mapping device level information, constructing a system level reliability model, obtaining system failure rate, average fault-free operation time and a reliability function, and realizing health state perception and reliability quantitative evaluation of the energy storage system.

The invention relates to the technical field of artificial intelligence, in particular to an art design style migration system based on deep learning, which comprises an image perception analysis module, a style constraint calculation module, a detail structure mapping module, a scale corresponding screening module and a region fusion regulation and control module. According to the method, the texture, the structure and the edge features of the image are accurately analyzed, key details and structure areas are identified, so that the flexibility of style migration is improved, style application is more accurate, the problem of excessive stylization or content imbalance is avoided, the spatial features of the content areas are effectively identified by analyzing the detail structure levels of the image, and the image quality is improved. The method comprises the following steps of: selecting and matching an optimal style domain according to a scale corresponding relation, enhancing multi-scale style adaptability, improving expressive force of an image under multi-style conversion, ensuring natural fusion of contents and styles, improving a visual effect and keeping harmony between the styles and original contents, and ensuring the accuracy of style mapping, screening and matching an optimal style domain according to a scale corresponding relation.

The invention relates to the technical field of safety monitoring of a nuclear reactor, and particularly discloses a multi-region pressure overrun leakage monitoring method for a reactor pressure vessel. The method comprises the steps of multi-region pressure data acquisition, real-time pressure field model construction, dynamic pressure field baseline modeling, pressure overrun anomaly detection, leakage source accurate positioning and evaluation based on spatial gradient analysis, topological structure mapping and multi-sensor data fusion, and graded early warning and response. By the adoption of the technical scheme, real-time and fine monitoring of pressure distribution in the reactor pressure vessel can be achieved, the rapid and accurate judgment and positioning capacity of leakage events is improved, the operation safety and reliability of nuclear power facilities are enhanced, and the reliability of the nuclear power facilities is improved. The defects of independent monitoring, local accurate positioning and complex working condition adaptability of multi-region pressure over-limit leakage in the prior art are overcome.

The invention relates to the technical field of power distribution networks, in particular to a low-voltage transformer area topology recognition method and system adopting a graph diffusion model, equipment and a medium, and the method mainly comprises the steps that a topology recognition model is established, target time sequence characteristics are input into the topology recognition model, and the target time sequence characteristics are input into the low-voltage transformer area topology recognition model. And implicitly identifying node pairs with synchronous fluctuation through a topology identification model, outputting node features fusing neighbor information, predicting a connection probability between nodes based on the node features, and outputting a new transformer area topology structure. Different from a traditional method which depends on a specific transformer area rule or needs a large amount of manual adjustment, the graph neural network trained by the scheme aims at learning a general electrical characteristic-topological structure mapping rule and denoising logic. The model is not limited to a specific structure of training data, can be effectively generalized and applied to new courts with large topological structure differences, and solves the problems that a traditional method is poor in adaptability and weak in expansibility.

The invention discloses a data filling automation system and method based on a large model, and relates to the field of electric digital data processing, and the method specifically comprises the steps: monitoring and collecting the input behaviors of a user in different platform forms in real time, constructing a semantic state vector, and carrying out the aggregation to form a semantic global vector; constructing a structural disturbance tensor model, modeling the stable position of each field, and obtaining a stable state representation vector of each target field under disturbance through a tensor projection mode; and constructing a path cost function according to a matching relationship between the semantic global vector and a structure mapping result, solving an optimal execution path for field filling and reporting, and driving a browser to perform automatic filling and reporting according to a path sequence, thereby realizing automatic operation of data filling and reporting under semantic reasoning and structure disturbance. Automatic and intelligent cross-platform data filling and reporting are achieved, filling and reporting efficiency is effectively improved, platform independence, semantic adaptability and structure fault-tolerant ability are achieved, and data consistency and stability of the filling and reporting process are ensured.

The invention discloses an operating system containerization kernel compatibility method based on shadow structure mapping, which comprises the following steps of: constructing a multi-dimensional mapping rule base by analyzing the difference of data structures between a container system and a standard system, and creating a shadow structure comprising a data area, a metadata area and an expansion area when the container system runs on a host system; the host system allocates a shadow memory space and a memory pool, establishes mapping between a shadow structure and a physical memory page and bidirectional mapping between the shadow structure and a host structure, intercepts system call of a container application, obtains a target structure and allocates a shadow structure and a host structure memory, and sends the shadow structure and the host structure memory to the host system; according to the method, conversion from the target structure to the host structure is completed according to the multi-dimensional mapping rule base, the host machine completes calling through the host structure, then the calling result is reversely converted into the target structure and returned to the container application, and seamless compatibility of the container system and the host system is achieved under the condition that a user mode program of the container system is not modified.

The invention discloses a spiking neural network deployment method and a deployment tool chain based on intermediate representation, and the method comprises the steps: carrying out the model analysis and structure mapping operation of a trained ANN-ONNX model, generating an SNN-ONNX model with a pulse characteristic, carrying out the optimization of a weight parameter through the combination of transfer learning and a precision fine tuning strategy, and carrying out the optimization of the weight parameter. Therefore, the expression ability and adaptability of the converted model are improved, and the reasoning execution performance of the SNN model on a target platform is improved by adopting an optimization means; meanwhile, an SNN-oriented modular operator component library is constructed, and the portability, maintainability and expandability of operators among different hardware platforms are enhanced by adopting an abstract interface and a design mode of specifically realizing decoupling. According to the method, efficient deployment of the SNN model on a target hardware platform is achieved, performance fidelity of the model under the function equivalent condition is ensured, and the method has wide engineering application prospects in the fields of edge calculation, low-power-consumption intelligent terminals, brain inspiration type artificial intelligence and the like.

The invention discloses a two-stage multi-agent cooperation strategy based on exploration reward molding, and belongs to the field of multi-agent reinforcement learning. Trajectory data (including environment states, rewards, rewards and actions) generated by interaction of the intelligent agent and the environment are stored in an experience buffer pool and are updated and maintained through increment. Subsequently, randomly sampling an environment state and a corresponding return from the experience pool, and constructing a conditional diffusion model by using the return as a condition to generate a high-return target state; thirdly, global environment states of different time steps in different trajectories are sampled, time structure mapping is learned, and states with similar time are mapped to hidden states with similar geometric space; according to the method, a double-end Q network is adopted, an exploration strategy is decoupled into a target exploration strategy and a behavior exploration strategy, reward functions corresponding to two stages respectively act on a decision-making network of an intelligent agent, and more effective exploration and collaboration are achieved.

The invention discloses an electric power production management system security situation awareness method based on a cryptographic algorithm. According to the invention, by deeply fusing SM2, SM3, SM4 and other national cryptographic algorithms and power system characteristics, a full-link autonomous and controllable security protection system is constructed. In a data acquisition stage, SM4 encryption transmission and SM3 hash evidence storage are adopted to ensure confidentiality and integrity of data from a source to processing, and eavesdropping and tampering risks in a transmission process are effectively resisted; in a core situation assessment link, point multiplication operation of SM2 elliptic curve cryptography is innovatively introduced into a node aggregation process of a graph neural network, and graph structure mapping of physical topology of a power system is combined, so that the model can accurately capture implicit association and cascade influence between equipment, and the situation assessment accuracy is improved. At the same time, the recognition capability of the hidden attack mode is enhanced by using the nonlinear transformation of SM4, and the perception depth and anti-attack toughness of the system to the complex threats in the power production scene are improved from the bottom layer of the algorithm.

The invention discloses a writing process analysis method based on computer vision, which relates to the technical field of handwritten character recognition, and comprises the following steps: carrying out perspective transformation on real-time writing data, obtaining a writing image frame sequence, carrying out motion blur correction and pen point coordinate positioning on the writing image frame sequence by adopting an RAFT (Reversible Addition Fragmentation Transform) optical flow algorithm, and forming a writing track data flow; and performing curvature segmentation on the writing trace data stream to obtain discrete stroke segments, and performing spatial topological correlation and geometric structure mapping on the discrete stroke segments to generate a writing stroke topological graph. Through the RAFT optical flow algorithm and the stroke semantic analysis model, the precision of stroke recognition is improved, and efficient and accurate analysis from dynamic visual input to structured character output is achieved.

The invention provides a nuclear power regulation human factor trap identification method and device based on a knowledge graph, and the method comprises the steps: determining a current nuclear power regulation according to a to-be-executed task, and extracting an operation target in the current nuclear power regulation; on the basis of a pre-constructed interface knowledge graph, according to the current nuclear power regulation, calculating all regulation paths from a task starting point node to a task end point node; the interface knowledge graph takes interaction elements related to operation in the interface of the nuclear power plant simulator as nodes and takes the relationship between the interaction elements as edges; the task end node is an operation target; and obtaining a human factor trap identification result of the current nuclear power regulation according to a path structure in the regulation path. According to the method, the interaction elements in the nuclear power plant simulator interface are subjected to structured mapping through the interface knowledge graph, automatic recognition of the structural human factor trap in the nuclear power regulation can be effectively achieved, data support and logic basis are provided for regulation optimization and interface design, and finally safety risks caused by human errors are reduced.

The invention relates to the technical field of power system automation, and discloses a power distribution network operation risk assessment regulation and control method based on a graph attention network and reinforcement learning, and the method comprises the steps: mapping a topological structure of a power distribution network into a graph structure; constructing a node feature matrix and an adjacent matrix based on the node features and the edge features; inputting the node characteristic matrix and the adjacent matrix into a short-circuit current prediction model based on a graph attention network (GAT), and outputting short-circuit current prediction values of a bus and a line in the power distribution network and corresponding short-circuit current prediction intervals after the distributed power supply is connected to the grid; constructing a reward function aiming at reducing the short-circuit current risk and guaranteeing the load power supply, and training a strategy network and a value function through a SoftActor-Critic algorithm so as to obtain a reinforcement learning model; and collecting the state of the power distribution network in real time in a preset scheduling period to realize dynamic regulation and control of the short-circuit current risk of the power distribution network. According to the method, topology and electrical association is accurately captured, and the prediction precision is improved.

The invention discloses a product image-text and document association identifier generation method fusing a PLM coding rule, relates to the technical field of product data management, and is used for solving the problem that an image-text and document association identifier is not clear. According to the method, document information vectors are constructed by fusing PLM coding rules and collecting document metadata of design drawings, process documents, quality management and bill-of-material systems, an image-text document structure mapping chain is generated through a structure mapping judgment model, a unique association identifier of the image-text document is generated in combination with a preset template, and the unique association identifier of the image-text document is obtained. And real-time updating is carried out during structure replacement, hierarchical reconstruction or configuration change, cross-system serial number semantic alignment is realized through a heterogeneous coding analysis rule base, heterogeneous naming conflicts are solved, identifiers are written into a product data management platform, an index relationship is established, hierarchical retrieval, version switching and historical backtracking are supported, and the product data management efficiency is improved. And the consistency and cooperation efficiency of product research and development and quality control are improved.

The invention relates to the technical field of industrial factory monitoring, in particular to a cloud-side collaborative factory digital twin monitoring modeling method and system. The method comprises the following steps: collecting communication link data and space coordinate data to construct a factory topological structure diagram and construct a factory digital twin monitoring model; based on the nested graph neural network, comparing existing and historical factory topology structure diagrams to obtain a factory topology difference structure diagram, and performing structure mapping consistency verification on the factory topology difference structure diagram by using a structure mapping residual function to generate an entity equipment structure change event set; obtaining a changed entity equipment operation state data set, and generating a factory performance offset index set; and the changed physical equipment and other physical equipment directly connected with the changed physical equipment in the factory are monitored. The invention provides a digital twin monitoring modeling method for a cloud-side collaborative factory, which integrates space structure information and communication link characteristics, has a dynamic self-adaptive capability, and realizes real-time state monitoring of the factory.

The invention discloses a power target damage propagation path modeling method based on an attack chain atlas, and the method comprises the steps: collecting multi-source heterogeneous data of a power system, and carrying out the standardized structure mapping and data quality optimization, thereby obtaining standardized behavior metadata; performing heterogeneous node extraction on the standardized behavior metadata, defining an association relationship between heterogeneous nodes to construct an initial atlas, optimizing the initial atlas in combination with manual verification and an automatic duplicate removal mechanism to obtain a heterogeneous atlas, and performing attack time sequence anchoring on attack behavior nodes in the heterogeneous atlas, the incidence relation of attack behaviors, system components and service logic in time and topology dimensions is mined, an attack path is reconstructed in a cross-layer mode, then a potential high-risk attack mode is identified, damage propagation prediction is carried out, and adaptive optimization is carried out on a damage propagation prediction result in combination with service priorities. The method has the effects of realizing structured restoration and damage propagation reasoning of the attack path and providing comprehensive technical support for safety protection of the power system.

The invention discloses a nursing information online management system based on multi-source data fusion, which belongs to the field of nursing and comprises modules of data acquisition, access, standardization, compatible processing, storage, privacy protection, intelligent fusion and the like. The system collects multi-protocol data through edge nodes, uniformly converts the multi-protocol data into an intermediate format and performs standardized processing, so that semantic consistency and structure unification are realized. A structure mapping and primary key synchronization mechanism is adopted, and a heterogeneous system data barrier is broken through. Nursing information storage is based on a column database, and performance and reliability are enhanced by combining cold and hot stratification and replica redundancy. The encryption module supports field-level encryption and auditing traceability, and data privacy is guaranteed. The fusion engine utilizes a graph neural network and time sequence modeling to aggregate multi-maintenance information and predict risks. Asynchronous communication and a Protobuf protocol are adopted among the modules, so that low-delay and high-throughput data flow is realized. The intelligent nursing management system has the beneficial effects that the intelligence, precision and safety of nursing management are remarkably improved.

The invention relates to the technical field of industrial digital twinning, and discloses a factory production monitoring method and system based on digital twinning, and the method comprises the steps: collecting the operation characteristic parameters of an entity production line and the simulation parameters of a digital twinning model, and constructing an entity-virtual mapping data set; calculating a structure coupling deviation rate and a time phase drift rate based on the time-structure mapping matrix; determining virtual-real mismatch types including a local lag type, a synchronous drift type and an energy reverse type according to the combination relation of the two types; performing regional response correction, time phase compensation or energy inversion correction for different types of mismatch; the correction result is fed back to the digital twin model to generate a corrected virtual operation curve, the stability index of the model is calculated, when the stability index does not reach a convergence interval, the deviation analysis and mismatch recognition steps are repeatedly executed, and dynamic coordination and high-precision production monitoring between the virtual model and the real model are achieved. According to the method, the dynamic coordination and high-precision production monitoring capability between virtual and real models is improved.

Provided is a quantum computing method for obtaining an optimal solution of a problem with multiple discrete variables, wherein the problem is represented by a cost function, the method comprising:—generating a graph structure from the cost function,—dividing the graph structure into at least two disjunct subgraph structures, wherein each subgraph structure comprises a subset of the multiple variables,—mapping each subgraph structure to a local cost function represented as local cost Hamiltonian,—determining, for each local cost Hamiltonian, all eigenstates corresponding to an energy below a predetermined cut off energy using a quantum processing device, wherein each variable of the subset of multiple variables is represented by a qubit of the quantum processing device,—recombining the determined eigenstates, and-approximating a ground state from the recombined eigenstates, wherein the ground state represents the optimal solution.

The invention discloses a three-dimensional anisotropic grid generation method based on a streamline tracking topological structure, and relates to the field of numerical simulation of fluid mechanics, and the method comprises the steps: S1, carrying out the tetrahedral subdivision processing of a computational domain of an aircraft through employing a triangulation algorithm Delaunay, and achieving the isotropic grid subdivision of the computational domain; s2, using isotropic grid point information generated in the isotropic topological structure to construct a corresponding sign distance SDF resolving model so as to obtain a scalar field satisfying a Laplace equation; s3, calculating the gradient of the scalar field by adopting an SDF gradient solving method based on local least square fitting to obtain a corresponding gradient field; s4, performing streamline tracking in the gradient field to obtain a corresponding grid topological structure; and S5, constructing a structured hexahedral mesh covering the whole computational domain according to the mesh topological structure and the corresponding surface mesh. According to the method, theoretical unification and engineering feasibility of two-dimensional to three-dimensional grid structure mapping are realized.

The invention provides an information visualization method and system, a medium, equipment and a program product, and relates to the technical field of information processing, and the method comprises the steps: obtaining heterogeneous input information; performing category detection on the heterogeneous input information by utilizing the classification model, and determining a category corresponding to the heterogeneous input information; calculating entity relevancy, information relevancy and information weight corresponding to the heterogeneous input information according to the category; inputting structured label information corresponding to the heterogeneous input information according to the entity relevancy, the information relevancy and the information weight; constructing an atlas data structure corresponding to the structured label information; and mapping the map data structure into visual elements to obtain visual information. According to the method, heterogeneous input information is converted into visual information, so that leap-type improvement from bottom-layer data quantification to top-layer cognitive perception is realized.

The present invention provides a method for constructing a data governance knowledge graph based on metadata, which includes defining the metamodel structure of each type of metadata and the relationship between metamodels, summarizing and abstracting all metamodel structures, and forming a unified metamodel structure after constructing corresponding relationships; dynamically adjusting the unified metamodel structure; constructing a dynamic ontology model, mapping the unified metamodel structure to the dynamic ontology model, and adjusting the dynamic ontology model according to the dynamic changes of the unified metamodel structure; processing the metadata in the metadata lake; mapping the structured data after data processing to the dynamic ontology model according to the corresponding mapping relationship between the unified metamodel structure and the dynamic ontology model, completing the construction of the initial knowledge graph; and detecting and preprocessing the real-time data stream to form the updated content of the knowledge graph. The present invention aims to achieve the effective integration and dynamic update of multi-source heterogeneous metadata knowledge in the data governance process.

The present invention provides a method and system for jointly predicting cement strength based on a cascade model, which relates to the field of cement strength prediction and includes: obtaining initial component information of cement to be predicted; inputting the initial component information into a trained cascade model to predict the final cement strength; wherein the cascade model includes a cascaded structure mapping model and a strength prediction model, first using the structure mapping model to map the structure information through a mapping relationship from initial component information to final structure information, and then using the strength prediction model to combine the initial component information with the mapped structure information to jointly predict the cement strength; the present invention simultaneously considers the influence of the initial cement component information and the final structure information on the cement strength, avoids the problem of insufficient prediction accuracy caused by a single type of information, and achieves high-performance cement strength prediction.

The invention discloses a jamming frame detection method and system for games, and relates to the technical field of computers, and the method comprises the following steps: fusing multi-modal features by using PyTorch, generating time sequence representation through TCN modeling based on the multi-modal features, mapping into jamming probability through a multilayer perceptron structure based on the time sequence representation, and optimizing the jamming probability by using a Focal Loss loss function. And a lagging detection result is generated. The frame difference threshold is dynamically optimized by adopting DQN reinforcement learning, so that the complexity of a game scene can be self-adapted, and the false alarm rate and the omission ratio are remarkably reduced; multi-modal features are fused through a multi-scale SE attention mechanism and PyTorch, and the feature expression ability and the model robustness are effectively improved; tCN time sequence modeling is used to accurately capture a lagging related time sequence mode, the detection precision under unbalanced data is optimized, and the accuracy and practicability of lagging detection in a high-dynamic game scene are enhanced.

The invention discloses a multi-modal large model-based multimedia file generation method, and relates to the technical field of education content generation. Task alignment and evidence readiness, question analysis and question solving trajectory diagram construction, compiling into a unified instruction of a split white board and a parastyle, controlled generation, co-optimization in generation, posterior judgment, traceable release and learning write-back are sequentially completed; according to the scheme, a problem solving track graph is used as a unique true source, a semantic structure which can do a problem is mapped into a shot, blackboard writing and oral playing, and a suitable age target and a cognitive load are synchronously constrained; in the generation stage, the fact and safety scores are calculated according to the shot, local regeneration is triggered, and rework of the whole section is reduced; source credentials are written before publishing, and learning conditions are written back in combination with watching and evaluation, so that a correct, right-age, traceable and self-evolutionary closed loop is formed. And unified numbering, continuous input processing and output are realized, fixed-point backspacing and sampling inspection are supported, uncertainty and cost are reduced, and convenience is brought to campus distribution and home check verification.

The invention relates to the field of artificial intelligence, and discloses a community epidemic risk assessment model construction method based on big data, and the method comprises the following steps: S1, collecting data to construct a heterogeneous space-time atlas; s2, performing node representation learning on the map by using a heterogeneous map attention mechanism in a map neural network, and extracting propagation association features between communities; s3, constructing a coupled cellular automaton model, and simulating a disease transmission process between communities; s4, performing structure mapping and adaptive optimization by adopting a structure transfer learning mechanism; and S5, in combination with a multi-agent reinforcement learning strategy, community-level prevention and control strategy recommendation and risk assessment output are carried out by taking the risk cost as an optimization target. The community propagation potential is modeled by combining population mobility, environmental meteorology and medical resource data, accurate description of a propagation chain in space and time dimensions is realized, the dynamic perception ability of a real propagation path is improved, and the problems of rough description of a propagation scene and large prediction deviation are solved.