281 results about "Heterogeneous information" patented technology

The invention discloses an intention recognition method based on cross attention and multi-scale uncertainty. The intention recognition method comprises the following steps: preprocessing multi-modal data; parallel multi-modal feature coding oriented to intention recognition; the invention relates to multi-scale uncertainty perception decoding. According to the method, a parallelized multi-modal feature extraction path is constructed, and a hierarchical fusion mechanism based on cross attention is designed, so that deep semantic alignment and complementary enhancement of four types of heterogeneous information including the posture, the motion track, the global scene and the local vision of a rider are realized; the problems of incomplete feature representation and insufficient cross-modal correlation modeling caused by dependence on a single information source or adoption of a shallow fusion strategy in a traditional method are solved, so that the accuracy and robustness of intention recognition in a complex traffic scene are remarkably improved. According to the method, a multi-scale uncertainty perception decoding framework is introduced, risk early warning or context auxiliary verification is carried out on a low-confidence identification result, and the reliability of an automatic driving system in a safety critical scene is improved.

The invention provides an intelligent emergency decision support method and device based on multi-Agent cooperation. The method comprises a task planning module, an information acquisition module, a data fusion module and an execution monitoring module. The task planning module adopts a hierarchical decision-making mechanism, performs task decomposition in a plan making stage, generates a plurality of candidate execution paths by using thinking tree reasoning in a plan execution stage, and selects an optimal scheme. The information acquisition module acquires multi-source information such as network search, knowledge graph and geographic data through a plurality of professional Agents. And the data fusion module adopts a blackboard mode to manage heterogeneous information, and realizes intelligent abstract and correlation analysis through a large language model. And the execution monitoring module realizes dynamic optimization and fault self-recovery of the system through a multi-dimensional progress evaluation and cooperative monitoring mechanism. According to the invention, the problems of insufficient information processing capability, low decision-making efficiency and poor system stability of a traditional emergency decision-making system are solved. The information collection and processing efficiency is improved through large language model multi-Agent cooperation, the decision quality and accuracy are improved through a hierarchical decision mechanism, and long-term stable operation of the system is guaranteed through self-adaptive monitoring. The method is suitable for complex emergency decision-making scenes such as natural disasters, safety accidents and public health events.

The invention relates to an intelligent traffic flow prediction analysis method based on artificial intelligence, and the method comprises the steps: collecting and fusing traffic flow, environmental factors and event information according to traffic levels, and achieving the standardization and automatic clustering preprocessing of multi-level space-time attributes through regional factor labels; and then, expressing a multi-dimensional structure and a dynamic attribute of each node by using regional factor vectorization, dynamically modeling a spatial node heterogeneous adjacency relationship in combination with a self-organizing graph neural network, introducing a cross-level dynamic attention mechanism to perform weighted fusion on multiple spatial and temporal features, and outputting multi-granularity traffic prediction through a hierarchical fusion decoding network. And the model is combined with actual feedback to realize self-adaptive optimization of the area factors and model parameters. The method has the advantages that high-precision prediction of the traffic flow under multiple scales of roads, blocks, cities and the like is achieved, the self-learning and self-adaptive capacity for heterogeneous information, emergencies and spatial dynamic changes is improved, and hierarchical decision making and flow management are supported.

The embodiment of the invention provides a network security validity verification and quantitative evaluation method and system, and relates to the technical field of network security, and the method comprises the steps: obtaining global dynamic threat intelligence and a multi-dimensional global network security risk data source, and carrying out the preprocessing; constructing a global feature engineering system based on heterogeneous information network atlas and sequence analysis, forming a feature vector matrix, and mapping the feature vector matrix into an index state vector; inputting the feature vector matrix, the index state vector and the external environment information vector into an evaluation model, dynamically adjusting the weight of the feature vector matrix of each dimension, and outputting the validity score of each safety control point; based on the score, calculating a safety effectiveness index based on a time decay factor; identifying a weak link based on the index, and performing simulation verification to obtain a simulation attack actual measurement result; and an error vector is constructed based on the result and the validity score, and parameter adjustment and weight calibration are carried out. According to the scheme, the accuracy and the real-time performance of network security evaluation are improved.

The invention discloses a ship anti-collision early warning method based on multi-source heterogeneous information fusion, and the method comprises the steps: S1, obtaining the multi-source target information of a ship navigation radar, an AIS, and an infrared camera, and unifying the targets of all sensors to a same coordinate system; s2, preprocessing the radar and the AIS target; s3, performing information fusion on the preprocessed radar and AIS target; s4, performing information fusion on the target after radar and AIS fusion and the infrared image recognition target; and S5, based on the dynamic information of the final fusion target and the state of the ship, calculating the relative distance and orientation with the ship, and when the target is located in a preset fan-shaped area right in front of the ship and the relative distance is smaller than a dynamic danger threshold value, triggering a multi-stage acousto-optic character alarm. According to the invention, various sensor information can be integrated to detect and track the water surface target, and the robustness and the detection rate are improved, so that a more accurate early warning effect can be achieved on the water surface obstacle when the ship sails.

The invention relates to the technical field of fuel cells, in particular to a method and system for accurately controlling the hydrogen stoichiometric ratio of a fuel cell, and the method comprises the steps: firstly, obtaining a quantitative anode health state value through a fusion calculation model by collecting load current, anode inlet and outlet pressure, temperature, high-frequency resistance and other multi-source signals in real time; a feed-forward model based on a load current change rate predicts sudden change of hydrogen demand, and an optimal hydrogen flow instruction is jointly generated in combination with output of a PID controller which adaptively adjusts parameters according to a health state value. According to the method, the integrated diagnosis parameter, namely the anode health state value, is created, so that the internal state of the fuel cell can be accurately perceived and prospectively judged. Through deep fusion of multi-source heterogeneous information such as high-frequency resistance, anode pressure difference, current and temperature, a comprehensive index capable of comprehensively and quantitatively reflecting anode water content, gas concentration and runner smoothness is generated.

The invention discloses a multi-module collaborative navigation system for an intelligent robot, which relates to the field of robot navigation and comprises a multi-mode perception decision module, a semantic visual navigation module, a path memory fusion module and a rolling predictive control module which are electrically connected in sequence and work cooperatively. The multi-modal perception decision module performs weighted fusion on heterogeneous information, outputs scene representation and decision, and provides data support; the semantic visual navigation module analyzes the natural language instruction and combines visual data to complete path planning; the path memory fusion module carries out backtracking correction in an abnormal environment of semantic ambiguity and perception mismatch; and the rolling predictive control module realizes trajectory tracking and dynamic obstacle avoidance. According to the system, dependence on a prior map is reduced, instruction performability and dynamic obstacle avoidance capability are improved, collision risks are reduced, navigation real-time performance, stability and robustness are enhanced, and the system is compatible with multiple chassis and is suitable for complex dynamic scenes.

The invention belongs to the technical field of surveying and mapping and geographic information processing, and discloses a geographic entity intelligent identification and reconstruction system based on multi-source surveying and mapping data. The system is composed of a multi-source data acquisition and preprocessing module, a cross-modal feature coding and fusion module, a structural atlas construction and spatial logical reasoning module, a deformable neural modeling module and a physical prior guided collaborative prediction and closed-loop optimization module. According to the method, a cross-modal feature coding and fusion module is arranged, and a modal attention mechanism is introduced to dynamically weight multi-source data, so that heterogeneous information such as a laser point cloud, an inclined image and a multispectral image is fused into a unified coding vector in a high-dimensional space; compared with feature extraction performed by using a static deep network in a comparison file, the method of the invention adopts a minimum residual function to perform modal weight training, has an adaptive feature integration capability, and effectively improves the accuracy of geographic entity recognition and the robustness of boundary segmentation in different scenes.

The invention discloses a steel structure digital modeling method and system, and the method comprises the steps: obtaining high-precision point cloud data of a steel structure member through a laser scanning technology, carrying out the noise filtering and point cloud segmentation of the point cloud data, automatically recognizing the geometric features of the steel structure member through a geometric feature recognition technology, and distributing a unique identifier, the method comprises the following steps: collecting non-geometric attribute data of a steel structure component from a plurality of heterogeneous information sources, fusing the non-geometric attribute data through priority ranking and a conflict resolution mechanism, performing semantic reasoning completion based on component types, function positioning and engineering specifications, performing strict consistency verification on the completed non-geometric attribute information, and outputting the non-geometric attribute information in an industry general format; according to the method, comprehensive, efficient and accurate digital modeling of the existing steel structure component is realized, the core problems of data missing, information isolation, much manual intervention, low efficiency, error accumulation and the like in the prior art are effectively solved, and a solid and reliable digital foundation is provided for transformation, maintenance and management of steel structure engineering; and the method has remarkable engineering application value and economic benefit.

The invention relates to the technical field of train operation safety monitoring, and discloses a train obstacle detection method and system based on a four-eye sensor. The method comprises the following steps: constructing a three-dimensional sensing space fusing geometry, texture and temperature information by synchronously acquiring binocular visible light and binocular far infrared three-dimensional image data and carrying out cross validation and spatial association of heterogeneous visual information. And further combining orbit coordinate system constraints, dynamically generating and cutting a sensing space slice accurately corresponding to the rail-mounted area, and inputting the sensing space slice into the network to complete obstacle identification and positioning. And finally, calculating the threat degree based on the context, and generating an obstacle list. According to the method, multi-source heterogeneous information is fused, dynamic adaptation of a sensing space and a running orbit is realized, the robustness, the accuracy and the real-time performance of obstacle detection in a complex environment are improved, and false alarms and missing alarms are reduced.

The invention discloses a welding seam defect X-ray image intelligent diagnosis and credible traceability method based on multi-modal heterogeneous information collaboration, which is characterized in that a defect analysis network fusing multi-domain feature modeling and graph structure expression is constructed on the basis of bimodal data formed by a welding seam X-ray image and an industry detection standard text. In the image mode, dividing the weld seam image into a plurality of local area units through superpixel segmentation, taking the areas as image nodes, respectively extracting spatial domain, frequency domain, wavelet domain and edge domain features, and constructing a weighted graph structure by combining the spatial adjacency relation and the feature similarity relation between the areas; realizing overall modeling and correlation analysis of weld defect structure information by using a graph convolutional network; in a text mode, feature coding is carried out on an industry detection standard text, and the feature coding is used as an important prior constraint for defect judgment. Collaborative modeling of an image detection result and standard semantic information is achieved through a gating fusion mechanism, a mapping relation between a detection conclusion and a standard term is established, and interpretable expression and result credible traceability of the weld defect diagnosis process are achieved. And a welding seam X-ray film automatic digital acquisition and observation device is adopted in a matched manner, so that stable transmission, positioning observation and high-resolution digital imaging of the industrial ray film are realized, and reliable and consistent image data input is provided for the intelligent diagnosis method. The method is suitable for intelligent defect detection under complex welding seam structures and multi-working-condition imaging conditions, and has high engineering application value and popularization prospect.

The invention discloses a multi-source heterogeneous information extraction and structured processing method based on natural gas business data, and relates to the technical field of artificial intelligence application in the energy industry, and the method comprises the steps: analyzing a multi-modal document: carrying out the content analysis of natural gas sales documents in various formats, extracting key information, and obtaining the analyzed original data; data preprocessing: cleaning, recombining and standardizing the data to obtain preprocessed data; the mixed information extraction comprises key business index extraction, field rule base establishment, mixed extraction model establishment and context reasoning, and missing items in data are complemented by analyzing overall information and local content of a document, so that the integrity and accuracy of the information are improved; performing intelligent post-processing and constructing a relational database; according to the processing method, the natural gas service data can be accurately and efficiently extracted from the documents in various formats, and a basis is provided for subsequent data analysis and decision support.

The invention belongs to the technical field of Internet of Things. The invention provides a dynamic graph neural network link prediction method fusing multi-modal motifs. According to the embodiment of the invention, multi-source heterogeneous information such as structures, semantics, behaviors and the like is adaptively fused through a node-level modal attention mechanism, the problem that single-modal information is insufficient or unreliable is solved, and the discrimination ability of node representation is enhanced. And first-order adjacency, high-order adjacency and multiple motif modes are systematically fused, so that the model can simultaneously describe a local microcosmic mode and a global macroscopic topology, and the understanding of a complex network structure is more comprehensive. Spatio-temporal joint modeling is coordinated with time sequence attention through graph convolution, short-term mutation and long-term trend of network evolution are captured at the same time, and a dynamic link rule is accurately described. Through modal attention redistribution, time sequence consistency constraint and entropy regularization, modal missing and noise interference are effectively resisted, and prediction fluctuation is reduced.

The invention discloses a deep reinforcement learning multi-unmanned aerial vehicle cooperative path planning method of an HCA-MAPPO, and relates to multi-agent reinforcement learning and unmanned aerial vehicle cluster control. From a multi-unmanned aerial vehicle cluster collaborative path planning method, a simulation environment comprising a three-degree-of-freedom unmanned aerial vehicle kinematic model and a dual-coordinate system management system is established, and accurate simulation of a complex geographic scene is realized; a deep reinforcement learning method based on hierarchical cross attention HCA and multi-agent near-end strategy optimization MAPPO is provided; the method comprises the following steps: introducing an HCA executor network for performing priority processing on multi-source heterogeneous information; an internal curiosity module based on collaborative consistency gating is designed, so that the effective exploration efficiency in a sparse reward environment is improved; the invention provides a tangent guidance mixed reward shaping method based on conflict perception, and solves the problem of local optimum in path planning. And the situation awareness capability, the training convergence efficiency and the path planning success rate of the unmanned aerial vehicle cluster are obviously improved.

The invention relates to the technical field of network threat detection, in particular to a multi-modal analysis-fused network threat detection method and system, which are used for continuously acquiring network traffic, system call logs and cross-domain access records in a cloud computing environment in the power industry. Combining the obtained heterogeneous information into a uniform data stream according to a timestamp and an event identifier; aiming at the formed data stream, carrying out feature expansion on the hidden attack signal by utilizing a behavior pattern deconstruction method; recursive aggregation processing is carried out on the multi-source behavior units, causal chain constraints and role sensitive tags are introduced in the aggregation process, and candidate behavior chains capable of representing the attack evolution process are generated; mapping the candidate behavior chain to a virtual topological structure of a cloud computing environment, and predicting a potential penetration channel based on an attack path deduction algorithm; and triggering an adaptive protection strategy according to the predicted interaction result of the potential permeation channel and the candidate behavior chain. According to the invention, the network threat detection accuracy can be improved.

The invention discloses a chip IP interface information automatic analysis and connection modeling method, and relates to the technical field of integrated circuit verification, and the method comprises the steps: multi-source interface information collection: docking a design server through an FTP / SFTP protocol, automatically retrieving and capturing a target file, carrying out format preprocessing, and storing the collected original information through a database; heterogeneous information fusion analysis: extracting port physical attributes and generating machine executable rules by constructing a grammar analyzer and a semantic analyzer respectively, and automatically judging multi-source information contradictions by adopting a three-level judgment mechanism; structuring modeling of the connection relation: constructing a directed graph model of the IP nodes, the signal nodes and the constraint nodes, and automatically executing directed graph model verification; and through a standardized API interface docking verification tool, outputting a model file and a report file in standardized JSON-LD and DOT formats. Through cooperative work of cross-format acquisition, double-engine analysis, structured modeling and standardized output, full-automatic processing of IP interface information is realized.

The invention belongs to the technical field of computers, and particularly relates to a personalized recommendation method and system based on a dynamic heterogeneous graph and reinforcement learning. The method comprises the following steps: firstly, constructing a global heterogeneous information graph of multiple types of nodes offline, and learning static embedding of the nodes by using a graph neural network; secondly, dynamically constructing a session history into a session graph in a real-time interaction process of the user, and aggregating by adopting a graph convolutional network to generate a dynamic state vector of the user; inputting the dynamic state vector into an actor and commentator reinforcement learning framework; and finally, using a dominant function calculated by the commentator network as a stable learning signal, and performing end-to-end joint training on the whole model to optimize long-term cumulative return. According to the method, by introducing the session graph volume accumulation device, the accuracy of dynamic state representation is remarkably improved; and an actor commentator framework is adopted, so that the problem of high variance of a traditional strategy gradient method is effectively solved, and the training stability and efficiency are improved.

The invention provides a multi-agent cooperative medical treatment system and method based on dynamic weighted consensus. The method comprises the following steps: acquiring original medical data of a patient from a hospital heterogeneous information system; the dynamic weight of each specialized agent is calculated based on the domain correlation, the evidence authority level and the historical decision accuracy, and opinions are fused and processed and conflicts are processed through a weighted consensus algorithm; and recording the corresponding subsequent determination result of the final processing scheme, updating the historical decision accuracy of each specialized agent, and providing an efficient, accurate, comprehensive, personalized and explainable diagnosis and treatment scheme for each patient.

The invention provides a motor intelligent diagnosis method and system and a storage medium, and the method comprises the steps: obtaining the multi-source heterogeneous information and real-time working condition parameters of a motor, converting the multi-source heterogeneous information to a frequency domain to obtain a frequency spectrum tensor, mapping the real-time working condition parameters to a learnable spectrum attention mask, and obtaining a learnable spectrum attention mask; weighting the spectrum tensor by using the spectrum attention mask to obtain a mechanism weighted spectrum; processing the multi-source heterogeneous information and the real-time working condition parameters through physical simulation and a generative model to obtain targeted enhanced data; constructing a hybrid diagnosis network, taking a mechanism weighted frequency spectrum and targeted enhancement data as input, and taking a spectrum attention mask as a bias of a self-attention mechanism to extract global time sequence features; inputting the global time sequence features into a multi-task decoder based on the global time sequence features, outputting fault type probability, fault quantification parameters and a fault feature heat map, and obtaining a diagnosis result based on the fault type probability, the fault quantification parameters and the fault feature heat map. According to the invention, motor diagnosis can be realized more accurately.

The invention relates to the technical field of database security and anomaly detection, in particular to a database access anomaly detection method based on semantic vector and graph embedding, which is characterized by mainly comprising the following steps: preprocessing a data set, and extracting semantic units in the data set; a Word2Vec model is adopted to train the semantic unit, and a semantic vector of the SQL statement is generated; constructing a heterogeneous information graph taking a user, an operation type and a database table as nodes; establishing an undirected edge based on an entity association relationship, taking an association frequency as a weight, and taking a semantic vector as a node initial feature of the heterogeneous information graph; adopting a graph attention network GAT as a graph embedding algorithm to train the heterogeneous information graph, and generating a graph embedding feature corresponding to each database access statement; the graph embedding features are grouped according to a database table, and a sliding window is adopted to generate a corresponding time sequence; inputting the time sequence into the LSTM network, jointly optimizing graph embedding loss, time sequence modeling loss and regularization loss based on a designed total loss function to complete model training, and outputting time sequence features; and calculating the similarity between the output time sequence characteristics and the real image embedding characteristics, and judging whether the corresponding SQL operation is an abnormal operation or not according to a comparison result of the similarity and a threshold value. According to the method, SQL semantics, entity association and time sequence dependence multi-dimensional information can be fully fused, the accuracy and recall rate of anomaly detection are effectively improved, and reliable support is provided for database security protection.

The invention discloses a large model training method for generating corn growth guidance. The method belongs to the technical field of agricultural intelligent monitoring and prediction. The method solves the problem that when applied to a corn growth management scene, a large model method depends on multi-source heterogeneous information such as remote sensing images and meteorological data, although preliminary analysis and prediction based on the crop growth state can be achieved, the large model method still has limitation in the aspects of accuracy, interpretability and actual adaptability of decision suggestions. During data set construction, besides fusion of remote sensing data and multi-dimensional meteorological information, expert suggestions are added, more multivariate fusion features are constructed, and due to similarity between the expert suggestions and farmland management suggestions, correspondence between the features and tags is more accurate; according to the method, corn growth guidance based on a large model architecture can realize a technical span from'visible 'to'understandable' to'guidance ', and a scientific basis and decision support are provided for precise management of corn production.

The invention discloses a water area space land utilization function evaluation regulation and control method. The method comprises the following steps: collecting multi-source heterogeneous data of a water area space to construct a three-dimensional heterogeneous information network; inputting the three-dimensional heterogeneous information network into a pre-trained heterogeneous graph neural network to generate a node embedding vector; based on the node embedding vector, extracting a dynamic evolution characteristic tensor of a water area space land utilization function through a space-time diagram convolutional network; inputting the dynamic evolution characteristic tensor into an ecological system service value evaluation model, and outputting an ecological value matrix; and by taking the ecological value matrix as a constraint condition, calling a multi-objective optimization algorithm and performing collaborative optimization in combination with a multi-agent reinforcement learning framework, and generating a Pareto optimal solution set of water area space land utilization planning and a corresponding water area function partition configuration scheme. According to the method, scientificity, reasonability and sustainability of water area space land utilization planning are achieved, the land utilization rate is increased, and sustainable development of the water area space is promoted.

In order to solve the key problems of difficulty in multi-source information fusion, insufficient spatial topology modeling, attenuation of long-term prediction precision and the like in an existing aircraft ground taxiing trajectory prediction method, a parallel processing architecture of a historical trajectory encoder and a pavement path encoder is designed, and trajectory time sequence features are extracted by using a long-short-term memory network; modeling a spatial topological relation of a control path by adopting a graph attention network, and realizing effective integration of heterogeneous information through a feature fusion layer; a multi-component loss function fusing the position, the speed and the acceleration is provided, and the continuity and the smoothness of a prediction track are constrained; a lightweight data enhancement strategy and an adaptive residual connection mechanism are designed, the model generalization ability is improved, and long-term prediction error accumulation is relieved. According to the method, multi-source trajectory information can be effectively fused, and the accuracy and stability of aircraft ground taxiing trajectory prediction are remarkably improved.

The application provides a meta-learning-based responsive recommendation method, system and device, and the method comprises the following steps: constructing a meta-learning-based responsive recommendation model, wherein the meta-learning-based responsive recommendation model comprises a meta-learner and an ID embedding representation generator of a heterogeneous information network; training the meta-learning-based responsive recommendation model based on obtained data to obtain a trained meta-learning-based responsive recommendation model and model optimization parameters; obtaining user-goods historical scoring data of a user to be recommended, and obtaining target recommended goods based on the scoring data, the trained recommendation model and the model optimization parameters and recommending the target recommended goods to the user. The meta-learning-based responsive recommendation method is adopted, the meta-learning and the ID embedding representation generator are introduced, and therefore the responsiveness problem of the interest change of an old user and the initial response problem of a new user and a new good are solved from the root, and the problems of low recommendation accuracy and low user satisfaction are caused.

The application provides a motor intelligent diagnosis method and system and a storage medium, the method comprising: acquiring multi-source heterogeneous information and real-time working condition parameters of a motor, transforming the multi-source heterogeneous information to a frequency domain to obtain a frequency spectrum tensor, mapping the real-time working condition parameters to a learnable spectral attention mask, and weighting the frequency spectrum tensor with the spectral attention mask to obtain a mechanism weighted frequency spectrum; processing the multi-source heterogeneous information and the real-time working condition parameters through physical simulation and a generative model to obtain targeted enhanced data; constructing a hybrid diagnosis network, inputting the mechanism weighted frequency spectrum and the targeted enhanced data, and taking the spectral attention mask as a bias of a self-attention mechanism to extract global time sequence features; inputting the global time sequence features into a multi-task decoder to output a fault type probability, a fault quantitative parameter and a fault feature heat map, and obtaining a diagnosis result based on the fault type probability, the fault quantitative parameter and the fault feature heat map. The application can more accurately realize motor diagnosis.

The invention discloses an adversarial game intention prediction method and system based on game indexes and intention reasoning, and relates to the technical field of adversarial game decision making, and the method comprises the steps: receiving multi-source heterogeneous information and dynamic situation data of a game scene, the multi-source heterogeneous information comprising visual modal information, non-visual time sequence modal information and knowledge base modal information; the dynamic situation data of the game scene and a pre-constructed parameterized game index function library are subjected to relational mapping, a task completion evaluation result is obtained, and the pre-constructed parameterized game index function library comprises a plurality of task evaluation index functions associated with the specific confrontation game scene; the multi-source heterogeneous information is input into the pre-established game intention reasoning model, the intention recognition result is output and obtained, the task completion evaluation result is associated with the intention recognition result, prediction and evaluation of the confrontation game scene are achieved, and the recognition accuracy of the confrontation party cluster game intention is remarkably improved.

This invention belongs to the field of intelligent maritime surveillance technology, specifically a smart waterway monitoring and management system based on light beacons. It synchronously acquires multi-source heterogeneous information about vessels through integrated light beacon equipment, performs spatiotemporal registration and target association processing on this information, generates dynamic vessel trajectories, and extracts static attributes, motion behavior characteristics, visual activity characteristics, and environmental interaction characteristics. Utilizing a multi-evidence chain collaborative decision-making mechanism, it accurately identifies four fundamentally different vessel states: normal anchoring, illegal anchoring, active navigation, and uncontrolled dragging of anchor. This achieves a leap from state perception to behavioral cognition, significantly improving the accuracy of vessel anchoring identification and its robustness in complex scenarios. Based on the identification results, it triggers differentiated alarm strategies matching the state, generating handling instructions with reasons for the state determination, thereby greatly optimizing the allocation of surveillance resources and improving emergency response efficiency.

This invention relates to the field of intelligent early warning technology, and discloses a multi-level gradient early warning method and system for new energy equipment. The method includes: constructing a topological correlation matrix with measurement points within the new energy power station as nodes and electrical connections and information acquisition relationships as edges; extracting heterogeneous information from the measurement points based on the topological correlation matrix to obtain time-series data and a set of topological neighborhoods; performing joint entropy analysis on the time-series data and the time-series data of the neighborhood measurement points to obtain a neighborhood mutual information entropy vector; comparing the historical mutual information entropy vector under healthy operating conditions with the neighborhood mutual information entropy vector to obtain an abnormal entropy deviation value; constructing an entropy value topological heatmap based on the abnormal entropy deviation value and the topological location of the measurement points; identifying the boundary of the abnormal entropy deviation value diffusion field, locating the center location, marking the corresponding equipment as a hidden fault source, and generating a fault-level early warning signal.

The present application relates to the technical field of packaging box verification, and discloses a multi-source information verification system for product packaging boxes before storage. The system comprises a multi-source information acquisition module, which acquires packaging box stereo vision sequences, weight dynamic sampling and three-dimensional point cloud measurement data; a multi-modal feature learning module learns multi-scale space-time features from the vision data to generate vision space-time feature tensors; a dynamic weight analysis module decomposes the weight data in the frequency domain to generate weight frequency domain feature maps. A graph structure fusion module constructs a heterogeneous information graph from the two, generates a fusion verification graph feature through a graph neural network, an abnormal pattern recognition module generates an abnormal confidence distribution through a pre-trained variational autoencoder, an intelligent decision module outputs abnormal positioning and defect classification results accordingly, and an adaptive optimization module generates parameter adjustment strategies and transmits them to the storage system. The system realizes deep fusion of multi-source information, improves verification accuracy and intelligent level, and helps optimize the warehouse process.

The application discloses a social network link prediction method and device, the method comprises the following steps: decomposing a social heterogeneous network into a plurality of account association sub-views through a social network meta-path, using a graph convolution network to represent the accounts in each account association sub-view, fusing the features of the multiple views through an attention mechanism to generate an account feature vector, using the account feature vector to construct a social network link prediction model, and calculating a link score to realize link prediction. By using the social network meta-path to extract the multi-dimensional association relationship between the accounts, more heterogeneous information between the accounts is considered, and the attention mechanism fuses the features under the multiple account association sub-views to automatically calculate the contribution of various relationships to the link prediction effect, thereby solving the problem that the utilization rate of the social network heterogeneous association relationship is low in the prior art, and the link prediction accuracy is not high.