176 results about "Information aggregation" patented technology

The invention discloses an attention perception path reasoning method for a knowledge graph, and the method comprises the steps: firstly, generating an entity representation containing local semantics through employing a graph attention network coding entity and an adjacency relation, and synchronously obtaining an attention weight representing the association intensity between entities; secondly, innovatively providing a target-guided biased random walk path sampling strategy, and adaptively exploring a high-quality multi-hop semantic path related to a target task by taking the attention weight as a bias; then, information aggregation is carried out on the sampled semantic paths through a path encoder, and global path representation is obtained; and finally, carrying out deep fusion on the local entity representation and the global path representation, and jointly inputting the local entity representation and the global path representation into a prediction layer to carry out knowledge graph link prediction. According to the method, local structure perception and global path reasoning are cooperatively optimized through an attention mechanism, so that the link prediction precision and interpretability of the knowledge graph are remarkably improved.

The invention relates to the technical field of artificial intelligence and data processing, and discloses a multi-mode identity relation inference system based on a graph neural network. The system comprises a multi-modal feature extraction module, a cross-modal alignment module, a graph structure construction module, a dynamic relation reasoning module and a decision output module. According to the method, the cross-modal alignment module is introduced to project the image features and the text features to a unified public semantic space, so that the nonlinear distribution difference of heterogeneous modals in an embedding space is effectively eliminated, and cross-modal alignment errors are avoided from the source; by integrating the attention mechanism of modal perception in the graph neural network, the system can dynamically learn the semantic association strength between the nodes in different modals, adaptively adjust the weight distribution in the neighborhood information aggregation process, and significantly improve the accuracy of node characterization.

The invention relates to the field of machine learning, particularly discloses an artificial intelligence-based power system fault analysis and diagnosis method, and effectively solves the problem of information loss caused by neglecting a key waveform form in a transient signal in the prior art through a local feature extraction and serialization module. An original signal is converted into a local feature sequence with more characterization significance. Aiming at the averaging bottleneck of an existing model in an information aggregation stage, a traditional feature compression method is abandoned, and a sequence information aggregation and decision-making mechanism is provided. According to the mechanism, a context sensing sequence is regarded as a probability event, and modeling is carried out on the sequence from three orthogonal dimensions of a content center, time sequence dispersion and distribution uncertainty by calculating feature expectation, time sequence variance and information entropy of the context sensing sequence. The method can deeply insight and quantify the essential difference of different events in the time sequence dynamic evolution mode, thereby fundamentally solving the problem of misjudgment caused by feature confusion.

The invention relates to the field of underwater sound signal processing, in particular to an underwater DOA (direction of arrival) estimation method based on graph nerves and a convolutional neural network, which comprises the following steps: 1, establishing a linear array, and enabling narrow-band signals to simultaneously reach an underwater sound array; 2, performing signal preprocessing to obtain a signal covariance matrix, and performing normalization processing; 3, extracting correlation between array elements and spatial features of array signals, and performing data supplementation on sparse linear array information; 4, forming a double-branch structure, enhancing the information aggregation capability, and extracting features from a space path and a time domain path; and 5, constructing an adjacent matrix, filling node features of damaged array elements, adopting a double-branch structure, extracting spatial features and time domain features, carrying out feature integration, and outputting a DOA estimation result. The spatial correlation between array elements is extracted and the array sparsity problem is processed by using the graph neural network, and the time domain features of the signals are extracted in combination with the convolutional neural network, so that more accurate and more robust DOA estimation can be realized under the conditions of low signal-to-noise ratio and array sparsity.

The invention belongs to the field of geological disaster early warning, and provides a landslide danger prediction system and method, and the method comprises the steps: carrying out the fusion and normalization processing of multi-source disaster-inducing factors, obtaining an impact factor matrix, and carrying out the weighted correction of the impact factor matrix; determining spatial association strength and semantic association degree between the nodes according to the association edges; adopting feature mapping, association weight calculation and information aggregation adaptive learning to obtain association strength and association features of the nodes; according to the association strength and the association features of the nodes, learning by adopting an association graph model to obtain a global prediction model, and optimizing the global prediction model; and predicting the target landslide area through the optimized global prediction model to obtain a prediction result, and carrying out danger grade division on the prediction result according to a preset probability threshold. The beneficial effect of the invention is that the precision of landslide risk prediction is improved.

The invention belongs to the technical field of pipeline safety assessment, and discloses a multi-dimensional information interconnection and autonomous evolution collaborative pipeline full-state safety assessment method. And capturing a high-order relationship of data through double hypergraph reasoning of the instance-level hypergraph and the modal-level hypergraph to realize efficient interconnection. According to the method, mode-level and instance-level hypergraph information features are extracted through hypergraph information propagation, high-order correlation is mined through double-graph information aggregation, cross-mode and cross-instance consistency information and exclusive information are output after feature recombination, multi-dimensional data deep fusion is promoted, and high-quality data support is provided for follow-up pipeline full-state safety assessment. A two-stage autonomous evolution mechanism of intra-class progressive calibration and inter-class knowledge migration is respectively adapted to slight fluctuation and significant change scenes of the deep sea environment: precise adaptation of environment perturbation is realized through dual-branch feature extraction and dynamic weight adjustment in a domain; model parameter dynamic optimization is completed between domains through spatial-temporal feature clustering and cross-domain knowledge migration, and dynamic environment self-adaption can be achieved without manual intervention.

The invention provides a natural image matting method and system based on text and boundary information aggregation, and relates to the technical field of image processing. Splicing the original color image and the corresponding ternary image, extracting initial features, and obtaining enhanced fusion features through multi-scale Laplacian high-frequency extraction and cosine similarity weighted fusion; based on the enhanced fusion feature and the ternary image, generating a gated ternary fusion feature fused with priori knowledge through a trans-attention mechanism; global coding modeling is carried out on the gated three-value fusion features to obtain deep features; text prompt and multi-scale boundary information are introduced based on deep features, adaptive up-sampling is guided through a cross-attention mechanism, semantic difference consistency constraint is adopted between decoding layers, consistency constraint is implemented from pixel appearance, high-level semantics and color component dimensions, and finally a transparency image is output through a prediction header to obtain an image matting result. And the fidelity and the boundary accuracy of high-frequency details in a matting result are effectively improved.

The invention discloses a multi-working-condition industrial process soft measurement method based on multi-task learning and probability modeling, and aims to solve the problem of insufficient measurement precision caused by heterogeneous mixing of multi-working-condition process samples. The method comprises three core modules, namely a feature decoupling coding module, a hierarchical feature fusion module and a probability information aggregation module. Firstly, a spatial-temporal feature extractor is designed to explicitly decouple multi-working-condition data into working condition shared features and specific features, and hybrid feature expression and working condition recognition are achieved. Then, a hierarchical feature fusion module is constructed, deep fusion of information between working conditions is realized through a hierarchical expert gating network, and a complex interaction relationship between the working conditions is modeled; and finally, proposing a probability information aggregation strategy, inputting the fusion features into corresponding predictors, and weighting prediction results by using the working condition identification probability to generate final prediction output. According to the method, a classification task and a regression task are incorporated into a unified multi-task learning framework, and the good performance of multi-working-condition process performance index soft measurement is ensured.

The invention relates to the technical field of geological disaster early warning, in particular to a rainfall classification-based landslide disaster early warning method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining the characteristics of each grid node through collection and grid processing of multi-source data such as geology and rainfall; segmenting rainfall events and extracting morphological and statistical features; machine learning rainfall typing is carried out based on the features, and probability vectors of all rainfall types are obtained; then, constructing a graph structure fusing a space and a geological relationship, and fusing static and dynamic characteristics of grid nodes; inputting the spatio-temporal characteristic graph into a graph neural network, taking a probability vector as a condition signal, adjusting attention weight through learnable mapping, and realizing adaptive spatial information aggregation guided by rainfall typing; and calculating a landslide probability and generating an early warning based on the updated grid node representation, so as to deeply couple rainfall typing and a graph neural network, realize the crossing from a static threshold value to dynamic feature modulation, and improve the early warning accuracy, timeliness and spatial perception capability.

The invention discloses a radar quantitative rainfall estimation method based on a space-time attention model, and the method comprises the steps: carrying out the position coding, injecting position information into the embedded representation of sequence elements, explicitly representing the specific coordinates of the sequence elements in a sequence, dividing the codes into two types: fixed coding and learnable coding, and after the position coding is completed, carrying out the estimation of the radar quantitative rainfall. The method comprises the following steps of: calculating a mutual relationship between internal elements of an input sequence to realize a model architecture of information aggregation, establishing endogenous association between the elements of the sequence to realize feature interaction, synchronously calculating and integrating all position information of the sequence, and capturing space-time dependency in meteorological data through a position relationship between independent modeling time and space after calculation and integration; according to the invention, a position characterization mechanism based on three-dimensional space-time relative position coding is introduced, and space-time key features of radar echo data are effectively extracted through multiple attention modules; and designing a space-time position coding strategy capable of self-adaptive learning, and realizing joint feature representation of space-time dimensions.

The invention provides a diet scheme recommendation method and system, electronic equipment and a storage medium, and belongs to the technical field of artificial intelligence, and the method comprises the steps: determining a current portrait representation vector according to a user portrait of a target user; updating the historical user atlas according to the current portrait representation vector to obtain a fused user atlas; the historical user atlas is constructed based on historical portrait representation vectors of a target population, each historical portrait representation vector is an initial node in the historical user atlas, and the target population is composed of a plurality of users having similar characteristics with the target user; and generating a diet recommendation scheme of the target user according to the fused user map. According to the method, the dynamic user graph based on similar feature crowds is constructed, and the portrait representation vector of the target user is fused into the graph for information aggregation, so that a highly personalized diet recommendation scheme is generated by using group experience, and the pertinence and accuracy of generating the diet recommendation scheme are remarkably improved.

The invention discloses a road network traffic state generation method based on graph embedded coding, and belongs to the technical field of traffic road network traffic flow analysis and processing. Comprising the following steps: capturing road network spatial information features by using GraphSAGE, obtaining time sequence features through a self-attention mechanism, and constructing a road network embedded representation learning model based on spatio-temporal information aggregation; and constructing a road network traffic state generation model of graph embedded coding, obtaining a decoder based on Transform and GCN based on a road network embedded representation learning model of spatial-temporal information aggregation, and restoring to target output according to feature representation generated by STGE to complete a traffic flow prediction task and a data completion task. According to the method, fitting can be better carried out for the spatial-temporal characteristics of the road network, and a certain support is provided for establishing a unified traffic flow coding-decoding model.

AI system for collecting and structuring dialogue information to efficiently share it among members. [Solution] A dialogue information aggregation and structuring sharing AI system comprising: a dialogue unit that provides dialogue threads to terminals used by members belonging to a predetermined group, or that enables dialogue between members and between system members using a large-scale language model via information transmission and information acquisition means installed in the space where the members are present, and acquires dialogue information between the members and between the system members; an analysis unit that analyzes the dialogue information and generates structured knowledge from the dialogue information; and a storage unit that stores the knowledge, wherein the dialogue unit can read the knowledge from the storage unit and convey the content of the knowledge to the members during dialogue between the system members.

This invention belongs to the field of computer technology and discloses a financial information aggregation and recommendation method and system based on unsupervised cross-modal learning. It constructs a multi-channel data collection crawler engine to dynamically acquire heterogeneous data from cross-platform data sources; deploys a heterogeneous dual-engine architecture of semantic and numerical engines to perform semantic parsing and extract transaction features from the acquired heterogeneous data; constructs a cross-modal dynamic alignment matrix to generate a joint representation vector; acquires real-time search keywords and click behaviors to form short-term intent, analyzes historical cross-platform behavior trajectories to form long-term preferences, and constructs a two-layer intent recognition network based on short-term intent and long-term preferences; and outputs dynamic recommendation results integrating business objectives and user satisfaction indicators. This invention, based on unsupervised cross-modal learning technology, achieves cross-platform multi-channel financial information aggregation, deep user intent analysis, and personalized recommendation, thereby solving the problems existing in the prior art.

An object of a system according to an embodiment is to efficiently aggregate and utilize information posted by users at the time of a disaster.SOLUTION: A system according to an embodiment includes a post analysis unit, an information aggregation unit, and a portal integration unit. A contribution analysis part automatically analyzes the contribution contents of the user by using the generation AI. The information aggregation unit aggregates the information analyzed by the post analysis unit. The portal integration unit integrates the information aggregated by the information aggregation unit into the portal site.SELECTED DRAWING: Figure 1

The invention discloses a multi-modal emotion recognition method based on uncertainty entropy subtraction graph reconstruction, and the method comprises the steps: building and training a model, carrying out emotion prediction recognition based on the trained model, extracting multi-modal features through a pre-training encoder in a training stage, and mapping the multi-modal features to a unified space; a hybrid expert repair model based on uncertainty perception is constructed, missing modal features are generated according to historical contexts, and an information entropy of an expert selection weight is calculated to quantify a reliability factor of a current repair result; when a hypergraph used for emotion reasoning is constructed, the connection weight of hyperedges is dynamically adjusted by using a reliability factor, and unreliable nodes are inhibited from participating in information aggregation; and finally, optimizing the network through a dynamically weighted loss function, preferentially paying attention to feature reconstruction when the uncertainty is high, and paying attention to sentiment classification when the uncertainty is low. According to the scheme, the problem that noise data disturbs emotion reasoning due to the fact that the quality of repaired features cannot be quantified in the prior art is solved.

The application discloses a kind of based on semantic context's maintenance information aggregation search method and system, it is related to natural language processing technical field;After text analysis to search request, based on the maintenance semantic context extraction of preset static maintenance semantic label library obtains dynamic context;After the structured organization construction of dynamic context and search request, multiple semantic equivalent rewriting is carried out to obtain multiple rewritten search requests;Based on the scheme maintenance result search of preset multi-source maintenance knowledge base to all rewritten search requests obtains search result set;Based on dynamic context, search result set is sorted, and the first preset search result is obtained as final output.Analysis user natural language request, then rely on static maintenance semantic label library to complete dynamic context, then by structured fusion and multi semantic rewriting search, aggregate multi-source knowledge without omission, to quickly obtain the accurate scheme of adaptation, improve search accuracy while also greatly improve search efficiency.

The application belongs to the technical field of informatization and industrial data integration of nuclear power plants, and provides a maintenance procedure and information automatic association method and system based on equipment coding, the method comprising a receiving request step, a concurrent query step, a data aggregation step and an active push step, and the system comprising an equipment coding unified service module, a data interface adapter group module, an information aggregation and association engine and an active information service module, the application taking equipment coding as core master data, automatically aggregating maintenance related multi-source heterogeneous information through a service architecture and intelligent association technology, and actively pushing in a business context to form a method and system of an equipment holographic view.

The invention relates to the technical field of construction risk management of constructional engineering, in particular to a subway station deep foundation pit construction risk assessment method based on bilateral probability language, which comprises the following steps: step 1, constructing an evaluation set in a bilateral probability language term set form; 2, performing objective standardization processing on evaluation information; 3, determining a combination weight of subjective and objective combination; step 4, hierarchical information aggregation based on a weighted average operator; and step 5, risk quantification and grade determination. According to the method, a bilateral probability language term set (DPLTS) is introduced to completely describe expert group opinion distribution, and an LCM objective standardization method and a fuzzy entropy-cross entropy-BWM combined weighting model are combined to construct a risk assessment system which is complete in information, scientific in weight and robust in decision making; the defects of the prior art in the aspects of expressing complex uncertainty and fusing subjective and objective information are effectively overcome, and the reliability, the distinction degree and the practical value of a risk assessment result are remarkably improved.

The application discloses a multi-view graph Transformer cognitive assessment system and method fusing explicit features and a storage medium. The system comprises a feature embedding module, which is used for generating basic representations for three types of entities, namely learners, questions and knowledge concepts, and fusing difficulty coefficients of questions and knowledge concepts into their representations respectively; an intra-view information aggregation module, which is used for constructing three heterogeneous bipartite graphs, namely learner-question, learner-knowledge concept and question-knowledge concept, and updating node representations based on graph Transformer; a multi-view feature fusion module, which is used for fusing representations of each entity in different views to generate specialized representations; and a cognitive assessment module, which is used for mapping the specialized representations of learners to a vector space with the number of knowledge concepts as the dimension, and the obtained vector is the cognitive assessment result and is used for predicting the probability of answering any question correctly. The application fuses explicit difficulty, models multi-view graph structure and interacts with graph Transformer in depth, thereby significantly improving the accuracy and interpretability of cognitive assessment.

The application belongs to the technical field of oil well fault detection, and particularly relates to an oil well sensor spatial relationship modeling method based on centrality guided graph convolution, which comprises the following steps: firstly, valid nodes are reserved through node integrity maintenance, and state and trend features are extracted by using a double-view feature generation method; secondly, a weighted hybrid adjacency matrix is constructed by fusing prior physical connection and data-driven correlation; then, based on the weighted hybrid adjacency matrix and the node centrality score, a weight parameter for guiding spatial information aggregation is generated; finally, based on the weight parameter, centrality guided graph convolution operation is performed on a two-dimensional feature vector of the sensor node to update the node feature, and spatial relationship modeling is completed. The application introduces and optimizes a physical graph topology in oil well fault detection for the first time, effectively models the complex spatial dependence between sensors, significantly improves the interpretability, accuracy and robustness of a subsequent fault detection task, and is particularly suitable for identifying long-time evolving faults.

Embodiments of the present application are suitable for base frame operation and maintenance technical field, and provide an alarm information aggregation method and device, a monitoring system and a storage medium, wherein the alarm information aggregation method is applied to the monitoring system, and the method comprises the following steps: acquiring alarm information generated when a system abnormity occurs; the alarm information comprises attribute values corresponding to a plurality of alarm attributes respectively; the alarm information is decomposed step by step according to the plurality of alarm attributes to update an aggregation tree; the aggregation tree comprises a plurality of sub-nodes, and each sub-node corresponds to an attribute value; for any current end sub-node, if the current end sub-node and other end sub-nodes are sibling nodes, then the alarm information corresponding to the current end sub-node and the other end sub-nodes is aggregated to obtain aggregation information; and the aggregation information is sent to a user terminal of a staff. By using the above method, the sending cost of the monitoring system for sending alarm information can be reduced.

This invention belongs to the field of computer application technology. It discloses an information aggregation and retrieval system and method based on artificial intelligence, comprising: receiving user task objectives; combining associated resource sets and search preferences; calling a semantic model to generate semantic anchors; thereby generating a university-specific contextual blueprint to form a standardized information foundation within the university; parallel scheduling of various information interfaces within the university according to permissions; expanding query intents; filtering and sorting results to form a blueprint-bound retrieval result set; performing university-specific scenario analysis; generating dynamic aggregation summaries and difference comparison tables; grouping according to preset logic and performing visualization processing to form a structured presentation view; collecting user interaction data in the structured presentation view to generate a university user feedback dataset; and optimizing the university-specific contextual blueprint and university-specific knowledge unit network to form a closed-loop link.

A method, system, device and medium for defending against poisoning attacks in vertical federated learning, an active party and passive party interaction data integrity verification scheme is designed for the classic vertical federated learning algorithm Secureboost, the method is: key generation and distribution; the active party encrypts the Boost tree gradient information, and sends the encrypted result to the passive party, and sends the encrypted Boost tree gradient information to the trusted third party after homomorphic hash encryption; the passive party aggregates the received encrypted gradient information according to the feature dimension, and then performs homomorphic hash on the aggregation result and sends it to the trusted third party; the trusted third party aggregates all the information sent by the passive party, and then verifies whether the encrypted Boost tree gradient information sent by the active party and the aggregation result of the passive party information are consistent, if consistent, the integrity verification is passed, otherwise the verification is failed; the system, device and medium based on the above method defend against poisoning attacks, realize the safe aggregation of global model, and improve the defense reliability of poisoning attacks.

This application discloses an integrated, progressive, and efficient service system based on artificial intelligence, relating to the field of judicial service. The system includes: a pre-service processing module that queries the contact information of the parties in a case from a party information aggregation database module; then, an intelligent outbound calling module that initiates initial contact with the parties, inquiring about their preferred method of legal document service and guiding them to use electronic service; next, an intelligent flow decision module that determines the final service method based on the service scenario, pre-defined rules, and a priority mechanism; based on the final service method, the intelligent outbound calling module that confirms the corresponding service address, or guides the parties to register for a digital court account via SMS link; and finally, upon receiving the pushed legal documents, the system that invokes the service processing module to process the service according to the final service method corresponding to the parties in the case. This application can improve the efficiency of judicial service and save human and material resources.

The invention discloses a financial information prediction method based on AI, and the method comprises the following steps: S1, collecting financial information of a financial market, and carrying out the preprocessing of the financial information; s2, constructing a time sequence directed graph in the sliding time window according to an industry classification rule; s3, constructing a graph attention neural network, and generating a state representation sequence by adopting an information aggregation and time recursion propagation mechanism taking an edge weight as a weight; s4, establishing a reinforcement learning strategy optimization network, constructing a risk sensitive objective function based on the state representation sequence, and constraining a maximum retracement upper limit and a transaction handover upper limit; s5, iteratively updating the strategy parameters by using a risk sensitive objective function with constraints until convergence; s6, generating a predicted value and a confidence score of the latest timestamp, and executing risk calibration according to constraints; and S7, generating a directivity signal sequence based on the confidence score threshold, and outputting the predicted value subjected to risk calibration and the directivity signal sequence.

The invention relates to the technical field of intelligent processing of campus operation and maintenance work orders, and discloses an intelligent analysis and service optimization system for campus informatization maintenance work orders. According to the system, standardization processing of multi-source work order data is achieved through a work order information aggregation module; the intelligent priority evaluation module adopts a deep learning model to analyze fault text semantics, generates a dynamic priority coefficient and improves the accuracy of work order grading; the resource scheduling optimization module generates an optimal allocation scheme based on the priority and the personnel state; and the redundant communication management module constructs an active-active architecture by using a software defined network, so that load balancing and rapid fault switching of a data stream and a control signaling are realized, and the communication reliability of the system is effectively guaranteed. According to the invention, the problems of inaccurate priority judgment and insufficient communication guarantee of a traditional work order system are solved.

This application belongs to the field of interconnection network reliability and fault diagnosis technology, and discloses a method for intermittent fault diagnosis of low-bandwidth long interconnection networks based on graph attention mechanism. Targeting the hierarchical recursive structure and high connectivity of the network, under the PMC fault diagnosis model, a multi-round testing strategy is used to obtain test symptoms within the node's neighborhood. A feature vector is constructed for each node using local statistical feature extraction methods, and preprocessed using zero-padding and noise enhancement techniques. Finally, a graph attention network model is constructed, and the importance weights of neighboring node test results are dynamically learned using the attention mechanism to achieve accurate diagnosis of node fault states in the network. This application leverages the powerful local information aggregation capability of graph attention networks to overcome the diagnostic limitations of traditional algorithms, maintaining high diagnostic accuracy and robustness even with high fault rates, incomplete test symptoms, and large network sizes.

An object of the system according to the embodiment is to simplify information and processes in a company and to quickly guide an appropriate department or person in charge.SOLUTION: A system according to an embodiment includes an information aggregation unit, an analysis unit, a guidance unit, and a flow integration unit. The information aggregation unit aggregates information in a company. The analysis unit analyzes the information aggregated by the information aggregation unit. The guidance unit guides an appropriate department or person in charge based on the information analyzed by the analysis unit. The flow integration unit integrates and presents the procedure flows on the basis of the information analyzed by the analysis unit.SELECTED DRAWING: Figure 1