675 results about "Information representation" patented technology

The invention relates to the field of knowledge graph completion, provides a knowledge graph completion method based on multi-modal visual angle perception and a deep neural network, and aims to solve the problems of weak multi-modal information expression ability, rough fusion mode and insufficient structural reasoning ability in the prior art. According to the method, structure information, text description and visual image information of an entity in a knowledge graph are obtained, structure, text and image modal input is constructed respectively, and a graph neural network, a pre-training language model and a visual encoder are adopted for feature coding; weighted fusion and semantic enhancement of multi-modal features are realized through a visual angle fusion mechanism and hierarchical attention processing; cross-modal contrast learning is introduced to improve modal consistency; and carrying out triple reasoning by using a uniform Transform encoder, and verifying a completion result by scores. According to the method, multi-modal semantics are effectively integrated, the entity representation capability and the triple prediction accuracy are improved, the model robustness is enhanced, and the method is suitable for application scenes such as intelligent question answering and recommendation systems and has remarkable practical value and popularization prospects.

Systems, devices and automated processes are described for automated enhancement of metadata in a database of information about movies, television shows or other media programs. Gaps or errors in metadata describing the different programs in the database can be corrected using a digital architecture in which one or more sources are queried for missing information. Queries may be directed toward a large language model (LLM) or other artificial intelligence (AI) engine, if desired, that represents information about the media programs as embedded vectors that can be compared to query data to identify additional information about the media programs.

The invention discloses an industrial zero sample anomaly detection method and system based on cross-modal prompt learning, and relates to the technical field of computer vision and deep learning. The method comprises the following steps: acquiring RGB images and point cloud data containing product defects and normal states in an industrial scene, and preprocessing the point cloud data; constructing an anomaly detection model, preliminarily extracting information representation of the RGB image and the point cloud data by using the anomaly detection model, and performing further feature extraction and semantic alignment operation through prompt information; training the anomaly detection model based on a cross-modal collaborative mechanism, and testing the trained anomaly detection model by adopting a collaborative modulation strategy; and performing anomaly detection on a to-be-detected product by using the trained anomaly detection model. According to the method, the real-time defect detection precision and robustness can be remarkably improved in an industrial environment, especially under the conditions of data scarcity and complex modality.

The invention belongs to the technical field of image processing, and particularly relates to a sea temperature complementation method and system based on recursive double-flow Mama, and the method comprises the following steps: splicing a damaged SST image and a weekly average SST image as input, and outputting a predicted weekly average SST image and a predicted abnormal SST image through N times of recursive iteration of N same recursive hierarchical Mama blocks, and the two output images are added to obtain a final complemented SST image. According to the method, a recursive hierarchical Mama block for a sea surface temperature completion task is set, two parallel layers, namely a stable information representation module and an abnormal information representation module, are integrated in each block, features related to stability and features related to anomalies are extracted respectively, long-range dependency relationship modeling under large-area deficiency is achieved, and completion accuracy is improved.

The invention relates to a BOM table generation method based on full life cycle management, computer equipment and a computer readable storage medium, and the method comprises the following steps: S1, generating a client matrix according to a product design document and an engineering material, and obtaining information in the client matrix; the customer matrix is presented in the form of a two-dimensional table, column information in the two-dimensional table represents serial numbers of product parts and / or components of different assembly levels, and row information at least comprises names, numbers, specifications and models of the product parts and / or components and parent component identifiers; s2, generating an in-plant BOM matrix according to the material key information, the in-plant material number, the in-plant inventory status and the supply chain constraint condition, inputting the in-plant BOM matrix into a preset management system to generate an electronic drawing and document database, and establishing a structured D-BOM; s3, comparing the client matrix information obtained in the step S1 with the D-BOM established in the step S2; s4, carrying out adjustment and optimization on the D-BOM; and S5, importing the optimized D-BOM into a client matrix, and generating a final BOM.

The invention discloses a pediatric nursing knowledge question answering method and system based on multi-modal large model enhancement, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining multi-modal pediatric nursing related data, extracting knowledge entities, obtaining description text data of each knowledge entity, and forming text representation of the entities; establishing triple information according to the knowledge entities to generate a pediatric nursing knowledge basic database, and extracting triads to construct a knowledge graph; extracting multi-order graph data of each entity, and learning to generate knowledge graph representation of the entity; the text representation and the knowledge graph representation are fused, comprehensive knowledge information representation of the entity is obtained, the comprehensive knowledge information representation is used for finely adjusting a preset multi-modal large model, and pediatric nursing knowledge questions and answers are conducted through the finely-adjusted multi-modal large model. According to the method, more accurate, more reliable and more intelligent knowledge questions and answers are realized in a pediatric nursing scene through deep fusion of the structured constraint of the knowledge graph and the generalization ability of the multi-modal large model.

The invention provides a multi-modal data classification method and system, computer equipment and a storage medium, and the method comprises the steps: receiving multi-modal data through edge equipment, and carrying out the preprocessing of the multi-modal data; aligning to the same latitude through linear transformation or a projection layer; a comprehensive information representation vector is generated through fusion of an attention mechanism or a Transform architecture; quantifying the multi-modal large model, and deploying the multi-modal large model in edge equipment; sending the comprehensive information representation vector to a multi-modal large model for reasoning, and processing the comprehensive information representation vector through a multi-layer Transform architecture; and generating a classification result according to task requirements. According to the method, the real-time performance, the accuracy and the resource utilization efficiency of the system are improved through localized deployment on the edge equipment, sensitive data can be processed locally, data privacy and safety are guaranteed, cross-modal feature extraction and alignment are achieved, and the recognition capability in a complex scene is improved. Dependence on large-scale annotation data is reduced, and adaptability is improved.

The invention discloses a method and a device for enhancing scene trajectory prediction by fusing video monitoring and ADS-B, which can improve the precision and reliability of airport scene situation awareness, further accurately predict the moving trajectory of airplanes and other vehicles, and provide powerful technical support for airport scene management and flight safety. The method comprises the following steps: (1) synchronizing video monitoring data and ADSB data by using a timestamp, and realizing time-space alignment of different modal data through coordinate conversion; (2) determining a corresponding relation among different data sources through a data association technology, and constructing positive and negative sample pairs; (3) pre-training the multi-source heterogeneous data by using a comparative learning algorithm to extract and fuse key features, and constructing an efficient situation information representation model; and (4) adopting a pre-trained model as the basis of trajectory feature extraction, and inputting the basis to a long short-term memory (LSTM) network to predict the trajectory of the airport scene.

The invention provides a multi-view camera image and laser radar fused road perception method and system. The method comprises the steps of obtaining depth information features of a camera aerial view and depth information features of a laser radar aerial view based on a vehicle-mounted camera multi-view image and laser radar point cloud data; obtaining camera aerial view features with depth distribution based on the depth information features of the camera aerial view and the depth information features of the laser radar aerial view; performing feature alignment on the camera aerial view features with depth distribution and the camera aerial view features without depth distribution to obtain camera aerial view image features with depth information representation; and obtaining a prediction result based on the camera aerial view image features containing the depth information representation and the depth information features of the laser radar aerial view. According to the invention, the road condition of the current scene is inferred and predicted in real time through the image of the vehicle-mounted camera during vehicle driving, and the current driving road condition is sensed in real time under the unstructured road condition with limited visual field and severe environment.

The invention discloses a joint multi-modal entity relationship extraction method and system based on information representation and semantic alignment, and the method comprises the steps: obtaining sample data composed of an original image and a text, and obtaining the feature representation of visual information and text information based on the sample data; aligning the feature representation of the visual information and the feature representation of the text information by using a progressive modal semantic alignment strategy; by introducing a multi-layer correlation mapping mechanism guided by fine granularity, the correlation coefficient represented by the features of the aligned visual information and text information is judged, and features irrelevant to a task core are filtered; performing visual representation and text interaction by using a multi-modal interaction module to obtain multi-modal semantic features; carrying out weighted mapping on the multi-modal semantic features by utilizing a routing weighting function, and finally obtaining multi-modal feature representation; and sending the multi-modal feature representation into a word pair relation label extractor, and extracting an entity, an entity relation and an entity attribute quintuple.

The present disclosure provides a booklist cover generation method, apparatus, device, and storage medium, wherein the method includes: acquiring booklist information about a target booklist, wherein the target booklist indicates a book collection, and the booklist information represents introduction information for the target booklist; determining cover image description information for the target booklist that includes description information corresponding to at least one characteristic dimension of booklist attributes, based on the booklist information; generating a cover image for the target booklist based on the cover image description information.

A gear fault diagnosis method based on the joint weighted envelope anti-noise correlation of sub-signals. The method comprises: first, converting an original vibration signal sequence into envelope signals by means of a squaring-low pass filtering-square root calculation process of a signal sequence element by element; then, reconstructing the envelope signals on the basis of different time intervals, so as to obtain a series of sub-signals, and calculating a fault information representation metric of each sub-signal on the basis of L-moment theory indexes; next, assigning a weight to each sub-signal by combining the fault information representation metric and Sigmoid function transformation; then, on the basis of the envelope signals, and reconstructed sub-signals and corresponding weights thereof, calculating a joint weighted envelope anti-noise correlation function of an envelope signal sequence and the reconstructed sub-signals; and finally, determining a characteristic frequency on the basis of the reciprocal of a time interval value corresponding to a characteristic peak in a drawn graph showing the change of the joint weighted envelope anti-noise correlation function along with the time intervals, and finally recognizing a gear fault. By means of the method, a gear fault can be reliably recognized simply on the basis of time domain analysis when a signal length is limited and there is complex noise interference.

The invention belongs to the technical field of power load prediction, and relates to a power load prediction method based on interpretable multi-mode enhancement, which comprises the following steps: 1, constructing a text representation mode of an original load time sequence through a multi-mode enhancement module; 2, time sequence modal information and text representation information of the load are embedded into a high-dimensional vector space through a two-channel coding module; 3, receiving an embedded vector of a time sequence mode through a multi-mode prediction module, and taking a representation vector of a multi-mode text as input; 4, realizing an interpretable multi-mode alignment module; according to the method, the effects among the multi-modal information are divided into uniqueness, redundancy and collaboration; by constructing a negative sample pair for training, alignment of multi-modal information representation is enhanced, and then the prediction performance of the model is improved.

The embodiment of the invention discloses a data annotation method and device, equipment and a medium. According to the scheme, the method comprises the steps of obtaining to-be-annotated data; obtaining to-be-labeled labeling type information for the to-be-labeled data; the annotation type information represents the type of annotation information which can be annotated by the to-be-annotated data; determining an annotation processing module corresponding to the annotation type information according to the annotation type information; the annotation processing module has a data annotation function of annotating annotation information corresponding to the annotation type information; and carrying out annotation processing on the to-be-annotated data by utilizing the annotation processing module to obtain annotated data containing annotation information.

The invention discloses a video quality evaluation method with rich information representation, which comprises the steps of spatial domain feature extraction, motion feature extraction, time sequence modeling and quality prediction, and is characterized in that a fused feature vector is input into a time domain convolutional network for time sequence modeling, and the feature dimension is reduced to 128; and finally, directly mapping the 128-dimensional features into the quality score of the video through a full connection layer. According to the method, spatial domain feature extraction, motion feature extraction, time sequence modeling and quality prediction are set, the spatial domain feature extraction part of the model considers different features represented by video frames in RGB and YIQ color spaces so as to fully extract the features of the video frames in the spatial domain, and in addition, in order to fully understand the relation between adjacent frames, the feature extraction part of the model considers the different features represented by the video frames in the RGB and YIQ color spaces. Motion information on a time sequence is supplemented by extracting motion features of a video, so that the model has better performance, the accuracy of model prediction is improved, the overall model has better performance and accuracy in video quality evaluation, and the overall effect of the model is improved.

The invention discloses a millimeter wave electrocardiogram reconstruction system and method based on adaptive MODWT and CNN-BiLSTM-CA, and the method comprises the steps: collecting a tiny phase displacement signal of a target thoracic cavity region, and carrying out the multi-band decomposition and key component adaptive screening of an original signal through combining with a multi-scale stationary wavelet decomposition algorithm; and introducing a channel attention mechanism to enhance key information representation, inputting a reconstruction signal into a deep learning model combining a convolutional neural network and a bidirectional long-short term memory network, completing time sequence modeling and nonlinear mapping, and outputting a reconstruction waveform highly consistent with a standard electrocardiogram. According to the method, the signal reduction capacity under the complex interference condition is remarkably improved, high-precision and privacy-friendly remote physiological signal monitoring can be achieved under the condition of not depending on a lead electrode, and the method is superior to a traditional baseline model in the aspects of waveform reduction precision, signal time sequence consistency, model generalization capacity and the like; the method is suitable for various application scenes such as intelligent medical treatment.

The invention provides a point cloud weak supervision semantic segmentation method based on a dual self-attention mechanism, and the method comprises the steps: obtaining partially labeled three-dimensional point cloud data which comprises space coordinate information; local coordinate features of the point cloud data are coded through a GNE module, and discriminative local information representation is generated; a DLA module is adopted to calculate feature similarity between points in the point cloud data, attention weight is generated, and point feature expression is adjusted; performing weighted aggregation on the adjusted point features through an AFAP module to generate global feature representation; the DLA module and the AFAP module are connected in series and stacked to form a DARF module, and the modeling capability of complex geometrical shapes is improved; and performing semantic segmentation on the point cloud data based on a weak supervision training strategy, and outputting a segmentation result. According to the method, the dependence on the annotation data is remarkably reduced, and the segmentation performance is improved during limited annotation.

The invention discloses a battery fault diagnosis method based on a graph structure and an LSTM, and belongs to the field of battery fault diagnosis, and the method comprises the steps: converting battery blocks of a battery module and a connection relation thereof into a graph model based on a battery pack space connection information representation mode of the graph structure, so as to effectively capture the space dependence between the battery blocks; meanwhile, by combining the graph neural network and the long-short-term memory network, the spatial-temporal characteristics of the battery state can be accurately extracted, the processing capacity of time sequence data is enhanced, and therefore the accuracy and comprehensiveness of fault diagnosis are improved; besides, aiming at the problem of lack of a confidence evaluation mechanism in the prior art, an accurate confidence evaluation module is designed, and the reliability and transparency of the decision are effectively improved by calculating the confidence score of the diagnosis result.

A blockchain-based data processing method, performed by a consensus node on a second blockchain, includes: obtaining a cross-chain message submitted by a forwarding service device, and obtaining a blockchain identification carried in the cross-chain message associated with cross-chain transaction data stored in a first blockchain; obtaining, in a second blockchain corresponding to the blockchain identification, block Merkle information corresponding to the first blockchain, and obtaining, in a block Merkle tree represented by the block Merkle information, a Merkle proof set corresponding to the cross-chain message, the Merkle proof set including node information of one or more nodes in the block Merkle tree,; verifying validity of the cross-chain message according to the Merkle proof set and the block Merkle information; and obtaining a transaction execution result corresponding to the cross-chain message in response to verification succeeds, and storing the transaction execution result into the second blockchain.

The invention relates to the technical field of remote sensing images, in particular to a remote sensing image semantic change detection method based on multi-head adaptive attention and spatial feature enhancement, based on an MAA-SFENet model architecture, a multi-head adaptive attention (MAA) and attention driven feature association (ADFC) module is integrated, the MAA focuses on capturing fine local changes, and the ADFC module focuses on capturing fine local changes. And meanwhile, the global context is fused, and the ADFC focuses on processing large-scale high-dimensional data, so that the sensitivity to a spatial variation mode is enhanced. Besides, in order to further improve the adaptability to different environments, a spatial adaptive feature modulation (SAFM) module is introduced, and spatial information representation is dynamically adjusted, so that the detection precision under a complex background is improved. Experimental results on two SCD data sets show that the MAA-SFENet is superior to other advanced methods in qualitative and quantitative evaluation. The ablation experiment further verifies the important contribution of the three modules to performance improvement. Experimental results show that the MAA-SFENet has excellent performance and reliability in the remote sensing image SCD.

Embodiments of the present disclosure relate to systems and methods according to LLM-based agent groups for generating and enhancing engineering data funnel outputs. A method of obtaining a target structured information representation from one or more documents indicating the same process plant by using an interactive large language model (LLM)-based agent group in the context of an industrial plant is disclosed. The method includes obtaining at least one of the one or more documents at the LLM-based agent group. Each LLM agent from the group of LLM-based agents is given a task and a role, and is associated with one or more data processing tools from a set of predetermined data processing tools based on the given task and role. The method includes: selecting two or more LLM-based agents from a group of LLM-based agents for processing the document; processing the document by one of the selected two or more LLM agents, and outputting a structured information representation as a result of the processing; causing the selected two or more LLM agents to interact with the structured information representation based on a task and a role given to the selected two or more LLM agents; and obtaining a target structured information representation based on a result of the interaction.

The invention discloses a neuromorphic data classification method based on a gating space-time self-attention mechanism and a spiking neural network, and the method comprises the following steps: 1, selecting a public neuromorphic data set, carrying out the data preprocessing, and dividing the data into a training set, a verification set and a test set; 2, constructing a pulse neural network model to perform neuromorphic data classification, and introducing a gating space-time self-attention mechanism into the model to adaptively capture a global dependency relationship of space and time dimensions and enhance the space-time information representation capability of the model; and 3, training the constructed spiking neural network model by using the training set and the verification set, testing the trained model by using the samples in the preprocessed test set after training is completed, and outputting a prediction classification result of the samples by the model. According to the method, the representation capability of the spiking neural network in spatial-temporal feature modeling is remarkably enhanced through a gating spatial-temporal self-attention mechanism, and the precision of a neuromorphic data classification task is improved.

The embodiment of the invention relates to an information pushing method and device and electronic equipment, and the method comprises the steps: obtaining a natural language and a video generated through camera monitoring, and enabling the natural language to be used for determining a to-be-pushed video; determining feature data of the natural language to obtain first feature data; determining a first video based on a video generated by monitoring of the camera, and determining whether the first video is matched with the natural language based on at least two kinds of feature data of the first video and the first feature data; and under the condition that the first video is matched with the natural language, taking the first video as a to-be-pushed video, and pushing video information of the to-be-pushed video, the video information representing information of the to-be-pushed video. Therefore, the accuracy and / or timeliness of judging whether the concerned event occurs or not by the object such as the user can be improved.

The invention discloses a geographic space entity vectorization method and a geographic space entity vectorization system based on multi-modal fusion and metric learning, which are used for solving the problems that the traditional geographic information representation is single and multi-source data cannot be effectively fused. The method comprises the following steps: firstly, carrying out multi-modal feature extraction on text and coordinate information of a geographic space entity; then, through a neural network model with an independent coding stream and a deep fusion layer, intelligently fusing the multi-modal features and projecting the multi-modal features to a unified embedded vector space; and finally, optimizing the model by adopting a metric learning normal form through a hybrid triple sampling strategy combining semantic and spatial constraints. The invention also provides a system for realizing the method. The system comprises a feature engineering module, a training set generation module, a model training module and a reasoning application module. The system can automatically complete the whole process from data preprocessing, model training to vectorization reasoning. Compared with the prior art, the method has the advantages that the embedded vector with high semantic distinction degree and accurate spatial perception capability can be generated, and the computability and intelligence of geographic spatial data are effectively improved.

The application discloses a robot cognitive development method based on ontology semantics, and comprises the following steps: constructing a robot article identification professional knowledge base based on attribute function and ontology information representation of article definition; information determination based on attribute discrimination and semantic search; and robot cognitive development based on attribute information addition. The application simulates the process of human memory, learning and cognition of articles based on an ontology semantic knowledge base, and through machine learning and sensor attribute information, the robot can actively cognize, learn, expand and accumulate learned knowledge and experience according to information data; the robot can continuously develop its cognitive ability through learning, automatically construct a robot article identification professional knowledge base of unknown articles, and based on a semantic structure of triplets, share knowledge and exchange operation logic between man and machine, so that the cognitive level of the robot is improved and the operation experience of an operator is improved.

The invention is suitable for the field of power systems, and provides a power grid attack defense method, terminal equipment and a storage medium. The power grid attack defense method comprises the following steps: an edge node determines local abnormal information and a first response strategy according to local communication data, wherein the local abnormal information represents power grid attack information suffered by the edge node; determining local association information according to the local exception information and shared exception information of the adjacent nodes, wherein the local association information represents an association relationship between the edge node and the plurality of adjacent nodes; sending the local association information to the central node; obtaining traceability information obtained by the central node according to the local association information, wherein the traceability information represents attack source information and attack path information of the power grid attack; and determining a second response strategy according to the traceability information and the local abnormal information. Through the synergistic effect of the edge nodes and the center node, the full-chain identification and multi-point protection capabilities of the power system in a complex attack environment are improved.

Approaches presented herein provide for the generation of synthesized data from input noise using a denoising diffusion network. A higher order differential equation solver can be used for the denoising process, with one or more higher-order terms being distilled into one or more separate efficient neural networks. A separate, efficient neural network can be called together with a primary denoising model at inference time without significant loss in sampling efficiency. The separate neural network can provide information about the curvature (or other higher-order term) of the differential equation, representing a denoising trajectory, that can be used by the primary diffusion network to denoise the image using fewer denoising iterations.

A numerical control device (1) comprises a learning data acquisition unit that receives learning data including operation log information and operation state information, and a model generation unit that, using the learning data, generates a learned model for inferring screen display data for displaying a new operation screen from the operation log information and the operation state information. The operation log information represents a user's operation performed on an operation screen of the numerical control device (1) that controls a machine tool and represents information of the operation screen used in the operation. The operation state information represents a condition of the machine tool at a time when the operation shown in the operation log information is performed.The new operation screen includes information searched by the user and extracted from several existing operation screens.

The invention relates to an entity object traversal recognition detection method and device based on unmanned aerial vehicle equipment. The method comprises the following steps: acquiring cargo information acquired by unmanned aerial vehicle equipment in a cargo storage area, wherein the cargo information represents cargo storage related information acquired by the unmanned aerial vehicle equipment running according to a preset flight path and sequentially acquiring each storage position in the cargo storage area; according to the entity feature category in the cargo information, a cargo recognition algorithm matched with the cargo information is determined, cargo feature information corresponding to the cargo information is recognized based on the cargo recognition algorithm, and the cargo feature information comprises the product model, the storage number and the storage position of the corresponding cargo; and comparing the cargo feature information with inventory information in a preset database to obtain an inventory analysis result of the cargo storage area. By adopting the method, the systematic analysis of the cargo storage state can be realized, and the accuracy of inventory management and the real-time performance of information updating can be improved.