6996 results about "Generative adversarial network" patented technology

The invention provides a news scene three-dimensional reconstruction and visualization method based on multi-source remote sensing data, and relates to the technical field of three-dimensional reconstruction, and the method comprises the steps: extracting multi-modal data feature points through employing a spatial position weighted iterative nearest point algorithm and a tensor projection algorithm; after bidirectional attention deep neural network processing and local geometric consistency constraint screening, registration multi-source remote sensing data is generated, data enhancement is carried out through a variational auto-encoder network and a generative adversarial network, the enhanced data is used for depth information generation and texture feature migration, an initial three-dimensional grid model is generated based on a Poisson reconstruction algorithm, and the initial three-dimensional grid model is constructed; and carrying out topological optimization by combining multi-view projection consistency constraint and a grid optimization algorithm to obtain an optimized three-dimensional scene model, setting a space division function, carrying out space division, constructing a grade model and a depth region, generating a scene semantic segmentation map, and updating a visual scene.

The invention relates to a business credit evaluation and supervision method based on a multi-modal coevolution algorithm, and the method comprises the steps: collecting and cleaning multi-modal data, guaranteeing the data quality, uniformly storing the multi-modal data as a structural database, extracting features through cross-modal comparative learning, and enabling the features to be embedded into a dynamic multi-modal knowledge graph, a modal sharing network is used to extract and fuse modal sharing and specific features, consistency of modal feature distribution is optimized through adversarial learning, a global co-evolution credit scoring model is initialized, a dynamic multi-objective algorithm is used to optimize accuracy, robustness and interpretability of the model, and a credit scoring result is obtained. A causal reasoning model is introduced to analyze driving factors of enterprise credit changes, a causal relationship is established, a closed-loop feedback system is designed, a credit evaluation model is updated, adaptability is enhanced, an interpretable credit evaluation report is generated based on a generative adversarial network, and transparency and credibility are enhanced. According to the method, the accuracy and adaptability of credit assessment are improved, and the robustness and interpretability of an assessment result are ensured.

The invention relates to the technical field of marine environment prediction, in particular to a marine environment multi-modal fusion prediction method and system based on digital twinning. The method comprises the following steps: capturing time-space correlation characteristics of multi-modal data of a marine environment based on a dynamic multi-modal graph neural network; performing multi-scale feature fusion on the space-time correlation features by using a multi-scale gating unit to obtain comprehensive feature representation; predicting the comprehensive feature representation by using a mixed time sequence prediction framework to obtain preliminary marine environment prediction data, including short-term dynamic modeling and long-term trend modeling; and performing noise fitting on the preliminary marine environment prediction data by using a generative adversarial network to generate final marine environment prediction data. According to the invention, through innovative combination of dynamic multi-modal data fusion, a mixed time sequence prediction framework and a multi-scale gating Tanh unit, the problems of insufficient data fusion, limited prediction precision and poor dynamic response capability in the traditional marine environment monitoring and prediction technology are effectively solved.

The invention discloses a concrete bridge crack detection method based on computer vision, and relates to bridge detection, and the method comprises the steps: collecting a crack image, GPS data and a depth image of a concrete bridge; according to the GPS data, establishing a mapping relation between the pixel coordinates and the fracture physical space coordinates; based on feature matching of ORB features and a registration optimization algorithm based on mutual information, obtaining alignment of the crack image and the depth image at a pixel level, and obtaining a color crack image and a depth crack image; a MaskR-CNN model is adopted to extract a pixel-level crack segmentation mask of the crack region; according to the crack segmentation mask and the registered depth crack image, depth information of a crack region is estimated through a depth completion algorithm based on a conditional generative adversarial network (CGAN), and a crack depth distribution map is obtained; according to the crack depth distribution map, geometric parameters of the crack are extracted through a morphological algorithm and a central axis transformation algorithm. Aiming at the low concrete bridge crack detection precision in the prior art, the detection precision is improved.

The invention relates to the field of bidding risk assessment, and discloses an AI technology-based intelligent bidding data analysis method and system and a storage medium, and the method comprises the following steps: obtaining bidding data, constructing a multi-dimensional space-time tensor, and extracting low-dimensional features through dynamic tensor decomposition; establishing a dynamic enterprise relationship graph, modeling an enterprise cooperation relationship by using a graph neural network, and capturing a bidding behavior mode between enterprises; a multi-target joint optimization model is constructed, and market trend prediction, enterprise credit assessment and risk early warning are synchronously realized; performing adversarial training by adopting a generative adversarial network, and dynamically adjusting task weights in combination with Pareto optimization to balance multi-task conflicts; and outputting a market prediction report, an enterprise credit portrait and a risk early warning list, and providing policy and regulation change influence analysis and a risk evidence chain. According to the method, bidding and tendering data are deeply mined through the AI technology, the market insight and the abnormal bidding behavior recognition capability are improved, and the method has wide application value.

The invention relates to the technical field of geological risk monitoring and early warning in tunnel construction, in particular to a karst tunnel risk intelligent early warning method, device and equipment based on deep learning, and the method comprises the steps: obtaining multi-source coupling data; performing high-dimensional fusion on the processed multi-source coupling data by using a generative adversarial network, and reconstructing a high-precision three-dimensional model of the detection area; performing geological risk grade classification on the detection area to generate a corresponding risk distribution map; generating a dynamic risk evaluation index, and triggering an early warning signal when the risk level exceeds a preset threshold value; the method comprises the steps of multi-source data acquisition, data preprocessing, high-precision three-dimensional model reconstruction, risk grade classification, dynamic risk monitoring and early warning and the like, and can solve the problems of single risk detection means, insufficient evaluation precision and poor real-time performance in existing karst tunnel construction.

The invention relates to the technical field of artificial intelligence and health management, in particular to a health management method and system based on multi-dimensional data analysis, and the method comprises the steps: collecting the physiological, behavior, environment and psychological data of a user, and carrying out the modeling through a recurrent neural network, and generating health state data; extracting a key causal relationship of the health risk based on a causal analysis model of a Bayesian network; comprehensively analyzing health changes through the short-term time sequence model and the long-term trend prediction model, and generating health risk data; a personalized health intervention scheme is designed by using a conditional generative adversarial network, and safe sharing and dynamic management of the scheme are realized through a block chain technology. According to the method, the health risk can be accurately identified, scientific intervention measures can be designed, the health management process is dynamically optimized, powerful technical support is provided for an intelligent old-age nursing scene, and the health management efficiency and effect are improved.

The invention discloses a real-time video quality optimization and enhancement method based on deep learning. The method comprises the following steps: S1, collecting a video stream and extracting continuous frames; s2, extracting motion area features by using an optical flow estimation algorithm, and generating a multi-modal feature matrix; s3, carrying out normalization processing; s4, outputting a de-noising optimization frame by using an adaptive multi-dimensional residual network and a frequency domain analysis technology; s5, generating a detail enhancement frame by using a progressive generative adversarial network; s6, constructing an inter-frame relation graph through locality sensitive hashing, correcting the frame by using a double-flow time sensing network, optimizing the frame sequence based on a dynamic time warping method, and outputting the corrected frame sequence; s7, inputting the corrected frame sequence into a dynamic feedback optimization module to generate an optimized frame sequence; and S8, recombining the optimized frame sequence into a continuous video, and transmitting the continuous video to a target platform. According to the method, the video definition and the time consistency are comprehensively optimized through methods of multi-modal feature fusion, dynamic optimization, progressive network generation and the like.

The invention discloses a multi-level information security policy generation method based on a knowledge graph, and the method comprises the following steps: S1, collecting multi-modal data of a plurality of security data sources, and generating a standardized data set; s2, constructing and dynamically updating a multi-level knowledge graph based on the standardized data set; s3, based on the multi-level knowledge graph, a graph neural network is adopted to identify security threats and generate an evaluation report; s4, analyzing time-space characteristics of the security event, and predicting a threat evolution trend; s5, optimizing a protection strategy based on the graph attention network, and adjusting in combination with a real-time feedback mechanism; s6, simulating an attack scene by using a generative adversarial network, and optimizing a security protection strategy generation process; and S7, based on the optimized protection strategy, further adjusting and optimizing by adopting a meta-learning algorithm. Through combination of meta learning, the graph neural network and the generative adversarial network, an intelligent and dynamically adjusted network security protection strategy generation and optimization scheme is provided.

The invention discloses an adapter life prediction system based on digital twinning and a dynamic early warning method. The system comprises a multi-source data acquisition module, a digital twinning model construction module, a data coordination module, a life prediction module and a calibration module. According to the method, the adapter full-life-cycle digital twins are constructed, the limitation of one-way static analysis of a traditional life prediction technology is broken through, and dynamic health assessment under multi-dimensional data driving is achieved; a cross-dimension feature fusion and closed-loop calibration mechanism is innovatively proposed, and the industrial problems that multi-source asynchronous data is weak in relevance and sudden abnormal response lags behind are effectively solved; through the synergistic effect of the generative adversarial network and the attention model, the stability and credibility of a prediction result are remarkably improved under a complex working condition; the technology can be adapted to a harsh use environment of an industrial adapter, and quantifiable and traceable decision support is provided for intelligent operation and maintenance of power electronic equipment.

A method is provided for enhanced data routing in neural networks using Self-Organizing Maps (SOM) integrated with Autoencoder-GAN. The method comprises training an autoencoder to encode input data into a latent space representation; applying a Self-Organizing Map (SOM) to organize the latent space representation into a topological map; refining the latent space representation using a Generative Adversarial Network (GAN), wherein the generator generates enhanced latent space representations and the discriminator evaluates their quality; using the refined latent space representations to update the SOM topology dynamically; generating routing coefficients based on the updated SOM topology to guide data routing in a capsule network; and dynamically adjusting routing within the capsule network using the generated routing coefficients to enhance performance based on the refined latent representations.

The invention relates to the technical field of artificial intelligence, in particular to an AI-driven multilingual intelligent document abstract and mind map generation system, which realizes unified representation of data such as multilingual texts, images and tables through a multi-modal semantic feature generation module, and constructs a dynamically optimized causal semantic map; generating a semantic flow path with clear logic based on a dynamic semantic flow modeling method, wherein the semantic flow path is used for multi-language abstract generation; the structure of the mind map is optimized by using the generative adversarial network, and the content of the map is further perfected through user interaction adjustment and logic consistency verification. The system supports a user to efficiently extract document core information, a logic structure is displayed in a visual mode, the accuracy, logicality and efficiency of document generation are remarkably improved, and the system is suitable for generation and decision support of complex multi-modal documents.

The invention discloses a multi-modal diagnosis and treatment data analysis and auxiliary diagnosis method for internet medical treatment, which comprises the following steps: S1, performing feature extraction and fusion on multi-modal diagnosis and treatment data through a nonlinear mapping algorithm based on quantum state optimization; s2, constructing a self-adaptive dynamic relation network, and capturing a complex interaction relation between cross-domain features in the diagnosis and treatment data; s3, fusing implicit features in the sparse medical data with semantic association; s4, optimizing the diagnosis and treatment decision process by applying a causal inference technology; s5, processing anomalies in the diagnosis and treatment data by using a fusion generative adversarial network and sparse tensor decomposition technology; s6, constructing a decentralized encrypted federated learning network to protect the privacy of the patient; s7, predicting a disease evolution path in real time to form dynamic decision support; and S8, performing accelerated analysis on the high-dimensional feature mode in the diagnosis and treatment data in combination with quantum calculation. The method has the advantages of high data fusion capability, high diagnosis precision and high real-time decision support capability.

The invention discloses a mechanical arm positioning and grabbing method based on machine vision, and relates to the technical field of machine vision and mechanical arm control, the method comprises the following steps: synchronously acquiring RGB-D images of a target scene through a multi-view camera array, and generating three-dimensional point cloud data through data fusion; an improved LSD algorithm and a PnP algorithm are adopted to calculate the initial pose of the target object, illumination distortion is eliminated in combination with the generative adversarial network, and three-dimensional coordinates are output; a mechanical arm motion error transfer model is constructed based on Monte Carlo simulation, and a candidate grabbing scheme set is generated through reinforcement learning; and an optimal grabbing scheme is screened through a preset priority evaluation rule, and a mechanical arm joint movement track and a control instruction set are generated. Through multi-modal data fusion and a nonlinear optimization algorithm, the technical problems of large target positioning deviation and sensitive illumination interference in a complex environment are solved, and the grabbing precision and robustness of the mechanical arm are improved.

The invention discloses an inspection method, device, equipment and medium based on a digital airspace system, and the method comprises the steps: carrying out the feature extraction and calibration of multi-source sensing monitoring data of a to-be-inspected region through a pre-trained neural network model; obtaining a structured semantic description and a time sequence measurement value to be combined with external meteorological spatial data to be input into a digital airspace expert model based on an MoE framework for multi-modal fusion; carrying out enhancement processing on the generated multi-modal fusion representation through a variational auto-encoder so as to input the multi-modal fusion representation into a multi-modal transformer decoder for decoding, and obtaining an entity triple set to construct a digital spatial domain knowledge graph; node characterization in the knowledge graph is enhanced by adopting an attention enhancement mechanism based on a graph neural network, the node characterization is input into a conditional generative adversarial network model for multi-task prediction, and an inspection decision suggestion is generated to be executed by the unmanned aerial vehicle, so that the utilization rate of multi-source sensing data is effectively improved, and the inspection efficiency of the unmanned aerial vehicle is improved.

The invention discloses a submarine cable risk dynamic assessment method and system based on multi-modal deep learning, and belongs to the field of marine infrastructure operation and maintenance. Aiming at the problems of incomplete data coverage, unreal generated scene, low evaluation reliability and the like in the prior art, the method comprises the following steps of: 1) constructing a multi-source heterogeneous data set containing six types of data including geology, ocean, ships, biology and the like, and realizing data alignment by adopting space-time grid coding; 2) designing a physical constraint generative adversarial network, and generating risk scene data conforming to a fluid mechanics law through a Navier-Stokes equation constraint; 3) creating a hierarchical space-time fusion network (HST-Transform), and combining CNN spatial feature extraction, a time sequence attention mechanism and a dynamic memory module to realize multi-modal fusion; according to the method, the detection rate of rare risk events is increased by 62%, the evaluation accuracy rate reaches 91.7%, the false alarm rate is reduced by 34% compared with a traditional method, and submarine cable breakage accidents can be effectively prevented.

The invention belongs to the technical field of intelligent navigation, and discloses a navigation obstacle avoidance method and system in a low-confidence and feature similar environment. The method comprises the following steps: acquiring multi-modal sensor data of obstacles in a detection area in a preset low-confidence environment by using a sensor; preprocessing the data of the multi-modal sensor; introducing a generative adversarial network to carry out image enhancement processing on the denoised image; performing cross-domain fusion on the data by using a converter architecture; obtaining an obstacle position, an obstacle type and a confidence degree distribution value based on a deep neural network, and constructing and obtaining an obstacle confidence degree map; dynamically planning an obstacle avoidance path by combining a deep reinforcement learning algorithm based on an obstacle confidence map obtained in real time, and performing auxiliary planning of the obstacle avoidance path based on an MPC model; the method can effectively cope with high challenge scenes such as tunnels and is widely applied to the fields of industrial automation, intelligent transportation and the like.

The invention discloses an artificial intelligence-based advertisement effect evaluation method and system, and the method comprises the steps: synchronously obtaining multi-source data containing a user behavior data flow and an advertisement putting index flow through a distributed collection engine, and generating a time-space synchronous multi-dimensional data cube; performing feature decoupling on the multi-dimensional data cube, and outputting a dynamic feature topology network with a weight; inputting the dynamic feature topology network into an adversarial training framework, and finally outputting an advertisement conversion probability space-time distribution diagram; based on the advertisement conversion probability space-time distribution map, deploying an attribution calculation unit for real-time feedback, and generating an incremental attribution map with a confidence interval; and inputting the incremental attribution atlas into a strategy generation adversarial network, and outputting an adversarial optimization advertisement putting strategy set meeting Pareto optimum. According to the embodiment of the invention, the accuracy and real-time performance of advertisement effect evaluation can be improved.

A generative adversarial multi-headed attention neural network self-learning method for aero-engine data reconstruction belongs to the field of end-to-end self-learning of aero-engine missing data. First, the samples are pre-processed, and the machine learning algorithm is used to pre-fill the normalized data first, and the pre-filled information is involved in the network training as part of the training information. Second, a generative adversarial multi-headed attention network model is constructed and the trained sample set is used to train the generative adversarial multi-headed attention network model. Finally, the samples are generated using the trained sample generator G. The method uses the generative adversarial network to better learn the distribution information of the data, and uses parallel convolution and multi-headed attention mechanism to fully exploit the spatial and temporal information among the aero-engine data.

The invention relates to the technical field of building model design, in particular to a building three-dimensional model lightweight design method and system based on artificial intelligence, and the method comprises the steps: extracting geometric-semantic features of a building model through a multi-scale curvature filtering and semantic segmentation network, constructing a fusion feature vector matrix, and obtaining a fusion feature vector matrix; by utilizing an integrated graph convolutional network and a self-adaptive neural simplification network of a double-branch attention mechanism, differential resampling is executed based on vertex importance weight, a simplified intermediate model is generated, a surface microstructure is recovered by means of a generative adversarial network, grid holes are corrected by combining Delou inner triangulation, and a surface microstructure is obtained. A non-uniform rational B-spline curved surface is adopted to reconstruct a key decoration component and output a lightweight model, so that the problems of insufficient geometric feature retention and semantic information splitting in the traditional technology are solved, intelligent, efficient and lightweight of a building three-dimensional model is realized, visual fidelity is ensured while data compression is performed, and the construction quality is improved. And the digital management requirement of the whole life cycle of the building is met.

The invention provides a vehicle mutual-aid claim settlement method and system based on multi-modal data fusion. Wherein vision and depth sensing data and maintenance records in a vehicle accident are integrated, part types and collision mechanical parameters are extracted, and surface microscopic deformation and internal hidden cracks are captured through dual-band scanning; and carrying out time-space association on the two to construct a comprehensive damage map. And generating a standard damage sequence by using the generative adversarial network based on a normal damage rule of the component, comparing the standard damage sequence with accident damage data layer by layer, extracting an abnormal region deviating from an evolution rule, and calculating a fraud risk index according to the spatial density of the abnormal region. And when the index exceeds a dynamic threshold value, triggering multi-source data to cooperatively verify feature consistency, and outputting a claim settlement result with a fraud mark. According to the technical scheme provided by the invention, accurate identification of maintenance fraud and collaborative optimization of claim settlement risk control efficiency are realized.

The invention relates to the technical field of project management and artificial intelligence, in particular to a project progress tracking and risk prediction system and method based on an improved knowledge graph and a multi-view graph neural network, and the system comprises a knowledge graph construction and dynamic updating module, an improved graph neural network analysis module, and an anomaly detection and risk prediction module. An intelligent early warning and visualization module; the method has the beneficial effects that anomaly detection is carried out through the GAN, possible delay and risk of a project are predicted, a risk early warning report is automatically generated, and optimization suggestions are provided for project managers. The system has the advantages of dynamically updating the knowledge graph in real time, improving risk prediction accuracy and enhancing project management perspectiveness and intelligent decision support, and is suitable for progress tracking and risk control in complex project management.

The invention discloses an intelligent vehicle extreme test scene generation method based on deep learning. The method comprises the following steps: building a hybrid generative adversarial network scene; collecting and preprocessing data; performing dynamic confrontation training; according to the extreme test simulation, an intelligent vehicle extreme test scene generation system based on deep learning comprises a hybrid generative adversarial network model, a data input module, a preprocessing module, an edge cloud module and an interaction module. A double-channel confrontation mechanism enables the risk controllability of a generated scene to be high, and dynamic confrontation training is carried out; a real multi-source data set is enhanced and labeled, the integrity of point cloud data is high through a point cloud missing region feature completion algorithm, and dynamic risk entry is effectively simulated by introducing a social force model into dynamic obstacle modeling; the multi-modal risk assessment network improves the assessment accuracy.

The invention relates to the technical field of unmanned aerial vehicle remote sensing and artificial intelligence crossing, in particular to an intelligent monitoring system and method based on multi-modal remote sensing data and deep learning, and the system comprises an unmanned aerial vehicle cluster networking subsystem, a mixed feature matching subsystem and a multi-modal fusion and continuous learning subsystem. The method comprises the following steps: constructing an unmanned aerial vehicle cluster carrying a multispectral sensor and a laser radar LiDAR, and carrying out wireless networking among a plurality of unmanned aerial vehicles to realize sharing of acquired images; feature point extraction is carried out on collected images of different time phases, the extracted feature points are input into the generative adversarial network, and the feature points are matched; and receiving the matched collected images, dynamically fusing data of visible light, infrared and other multi-modal images through a space-time attention mechanism, and realizing high-precision target recognition and dynamic environment self-adaption in a small sample scene. According to the method, unmanned aerial vehicle multi-source remote sensing data acquisition, feature fusion and deep reinforcement learning are combined, and the method is used for intelligently monitoring a dynamic environment.

An available transfer capability evaluation method and apparatus for a multi-region power system, belonging to the technical field of new energy grid connection. The method comprises the steps: in view of multi-dimensional uncertainty of new energy output and a load demand, on the basis of a conditional generative adversarial network method, determining a typical daily source-load scenario set; constructing an initial operation point set on the basis of the typical daily source-load scenario set, and determining a limit operation point of a multi-region power system; on the basis of the initial operation point set and the limit operation point, constructing an ATC evaluation model on the basis of safety indexes of multi-region power grid operation; and, on the basis of the ATC evaluation model and the typical daily source-load scenario set, determining available transfer capability probability distribution of the multi-region power system.

A system and method for cyber exploitation path analysis and response using federated networks to minimize network exposure and maximize network resilience, with the ability to simulate complex and large scale network traffic through the use of federated training networks, by gathering network entity information, establishing baseline behaviors for each entity, and monitoring each entity for behavioral anomalies that might indicate cybersecurity concerns. Further, the system and method involve incorporating network topology information into the analysis by generating a model of the network, annotating the model with risk and criticality information for each entity in the model and with a vulnerability level between entities, and using the model to evaluate cybersecurity risks to the network. Lastly, network attack path analysis and automated task planning for minimizing network exposure and maximizing resiliency is performed with machine learning, generative adversarial networks, hierarchical task networks, and Monte Carlo search trees.

The invention relates to the technical field of power system fault diagnosis, and discloses a power distribution network fault identification and positioning system based on a wide area measurement technology, and the system comprises a key measurement point optimization configuration module which determines the arrangement position of an optimal measurement point, and identifies a high-risk weak link in a power distribution network; the virtual-real fusion measurement network construction module adopts a generative adversarial network to generate blind area virtual measurement data conforming to a physical rule, and fuses actual measurement data and the virtual measurement data; the active fault excitation implementation module is used for implementing safe and controllable tiny disturbance injection and actively detecting response characteristics of weak links; the state estimation enhanced fault positioning module is used for constructing a health state evaluation model and calculating the deviation between a transfer function and a health baseline; the toughness fault positioning execution module is used for extracting key information dimensions and ensuring the reliability of fault positioning; through a virtual-real fusion measurement technology, efficient monitoring of the whole area of the power distribution network is realized on the basis of limited actual measurement equipment.

The invention discloses a hydraulic engineering operation and maintenance monitoring system based on digital twinning, and the system comprises the steps: S1, a data collection module which is used for obtaining multi-modal actual detection data from a plurality of monitoring points of a hydraulic engineering; s2, a data generation module which simulates and generates multi-dimensional virtual monitoring data and an abnormal sample library related to hydraulic engineering operation and maintenance; s3, a data fusion module which fuses the multi-dimensional virtual monitoring data and the multi-modal actual detection data; s4, a digital twinborn model construction module which dynamically constructs a multi-dimensional digital twinborn model of the water conservancy project based on the fused multi-modal data set; s5, an anomaly detection module which detects potential anomaly and sudden faults through an anomaly sample library generated by the generative adversarial network in combination with a multi-dimensional spatial-temporal trajectory clustering analysis method; and S6, an operation and maintenance monitoring module which is used for providing real-time operation and maintenance monitoring service for the multi-dimensional digital twin model. The method has the advantages of being high in dynamic adaptive capacity, high in monitoring accuracy and high in abnormal response speed.

The invention provides a financial data risk analysis method and system based on a large model, and relates to the technical field of intelligent risk control, and the method comprises the steps: obtaining financial data from a participant, carrying out the standardization and aggregation through a federated learning framework, generating a federated feature vector, constructing a bidirectional knowledge distillation model, receiving a vector, and carrying out the risk analysis of the financial data. A teacher model and a student model are deployed, a risk conduction map is constructed, a generative adversarial network is utilized to monitor changes of an enterprise association network, a risk conduction edge weight is adjusted, a financial report time sequence and a transaction event sequence are aligned through a space-time coupling encoder based on an LSTM and Transform architecture, and a multi-modal fusion feature vector is generated and input to a bidirectional knowledge distillation model; and a final risk score is obtained by combining the atlas, a grading early warning mechanism is triggered, and a risk disposal suggestion and a conduction path are generated, so that the data standardization and aggregation efficiency can be improved, and the dynamic coupling capability of a multi-modal fusion mechanism and the adaptability of a risk conduction model can be enhanced.

The invention relates to the technical field of traffic accident analysis, and discloses an intelligent analysis method for vehicle and pedestrian collision accident liability, and the method comprises the steps: firstly obtaining multi-source heterogeneous accident data, fusing a cross-platform data source through employing a federal learning framework when the data is insufficient, and reconstructing an accident scene three-dimensional coordinate system; and then, based on a multi-modal data fusion result, constructing a traffic participation entity relation topology model by using a graph neural network, and generating an accident dynamic evolution graph. Then, establishing a collision dynamics digital twin model by utilizing a physical engine, extracting a key collision feature vector, and constructing a responsibility probability distribution model based on a generative adversarial network; and optimizing a responsibility judgment strategy by adopting a double-layer reinforcement learning framework, verifying a physical simulation result through a hierarchical verification mechanism, analyzing a responsibility judgment logic chain, and finally outputting a responsibility analysis report with an interpretable label. The method can accurately and intelligently analyze the accident liability, and has good interpretability.