227 results about "Information embedding" patented technology

The invention belongs to the technical field of graph classification, discloses a graph classification method based on subgraph integration and position sensing, and relates to a graph classification method SIPA combining substructure embedding and node position sensing. The SIPA firstly extracts sub-graphs through two different strategies so as to capture multi-sample sub-structures in the graphs, the structural features of the sub-structures are coded by adopting a graph convolutional network, and information of different sub-graphs is effectively fused through an attention mechanism. Then, anchor nodes are introduced to calculate relative position information of nodes, and the information is embedded into node representation to better capture global position features. And finally, a graph information bottleneck mechanism is used for optimizing node representation and removing redundant information irrelevant to a classification task. The method not only effectively learns the local structure information, but also enhances the perception capability of the relative position information of the nodes. Experimental results show that SIPA is superior to an existing baseline model in five data sets, and the superiority of SIPA in a graph classification task is verified.

The invention discloses a policy service recommendation method and system based on a large language model, and relates to the field of policy information, and the method comprises the steps: analyzing a policy file, extracting policy terms with a numbering structure, building a unique identifier, and forming a term node set; identifying explicit or implicit reference behaviors in terms, constructing a reference path, and generating a reference directed graph; constructing a clause mapping tree based on the target clauses; mapping tree nodes are extracted to form structured prompt information, and the structured prompt information is embedded into large language model input; generating a policy report paragraph containing clause reference content; and outputting the structured policy text with clause reference chain closure and recommending the structured policy text to the user. According to the method, the clear reference context combined with the user information can be provided for the large language model, the large language model is guided to generate a text with a reasonable structure and complete terms for recommendation, and the problem of inaccurate generation when an existing model processes a complex reference structure is solved.

The invention belongs to the technical field of image analysis, and particularly relates to an electronic component defect detection method and system based on machine vision, and the method comprises the following steps: S1, obtaining visible light, X-ray and three-dimensional structured light images of an electronic component to be detected, and generating respective multi-scale feature pyramids through independent feature extraction networks; s2, generating a multi-modal fusion feature pyramid; s3, applying a candidate region generation network to propose a candidate defect region; s4, processing the spatial topological relation graph through a graph neural network, and embedding spatial context information into candidate defect region features; and S5, if the minimum distance between the candidate region features and all the pre-stored prototypes is greater than a set discrimination threshold, determining that the candidate region is a potential defect of an unknown type. According to the method, the detection range is widened, the robustness of feature expression is improved, the limitation of insufficient information of a single data source is overcome, and the accuracy, comprehensiveness and perspectiveness of detection are improved.

The invention provides an active-disturbance-rejection control method for an electromagnetic bearing two-level digital switching power amplifier embedded with model information. The method comprises the steps that an electromagnetic bearing two-level digital switching power amplifier mathematical model suitable for controller design is established based on the Fourier series theory and coil current characteristics; a direct current component in the mathematical model is defined as a modeling disturbance term, and feedforward compensation is directly carried out in the control law; parameter perturbation and an unmodeled part in the mathematical model are defined as unknown perturbation items, and real-time estimation is carried out through an extended state observer; a current item and a control input item in the mathematical model are used as known model information to be embedded into the design of the extended state observer; designing a feedback control law to carry out real-time compensation on the current item, the modeling disturbance item and the unknown disturbance item; a zero-order retainer and a current observer are adopted to carry out discretization processing on the controller, and the discretization processing is realized on a digital control platform based on a DSP (Digital Signal Processor). The method is high in current response speed and high in control precision.

The invention discloses a reversible information hiding method and system for enhancing image smoothness, and relates to the technical field of information security, and the system comprises a preprocessing module, an information embedding module and an optimization recovery module. According to the method, the Sobel operator is utilized to calculate the image gradient map, the region is divided based on the threshold T, the smooth region and the texture region can be accurately distinguished, an accurate basis is provided for differential processing of different regions, region characteristics are fitted, large-size blocks and sub-blocks of the smooth region are divided to facilitate subsequent refinement processing based on the gradient mean value, and the processing efficiency is improved. The small-size blocks of the texture area are beneficial to operation aiming at texture features, the rationality and effectiveness of overall processing are improved, meanwhile, the pixel mean value in the large-size blocks of the smooth area is calculated, the pixel and mean value difference value is recorded, reversible low-pass filtering is carried out, and the reversibility of the image in the whole information hiding and recovering process is ensured.

The embodiment of the invention provides an address data matching method and related equipment, and belongs to the technical field of geographic information services. The method comprises the following steps: constructing an address annotation corpus according to input address information data and a preset address database; the method comprises the following steps: generating a geographic information embedding vector according to a preset geographic information knowledge graph, performing address element analysis in combination with an address annotation corpus to obtain an address element sequence so as to construct a dictionary tree, and performing similarity screening through a spatial hierarchical matching algorithm to obtain a similar address set; generating an address embedding vector matrix through a preset word embedding vector model, and performing feature extraction through a preset semantic feature extraction model to obtain semantic-level similar features; according to input address information data, multi-dimensional character similarity matching is carried out to obtain character-level similar features, then weighted fusion is carried out in combination with semantic-level similar features, and target matching address data is determined according to a weighted fusion result. According to the embodiment of the invention, the address data matching accuracy and efficiency can be improved.

The invention discloses a generative image steganography method and device based on Stable Diffusion and discrete wavelet transform, and the method comprises the following steps: S1, sampling a potential representation of a to-be-generated image through employing a Stable Diffusion diffusion model, embedding secret information into a potential space of the diffusion model, processing the potential representation through employing discrete wavelet transform to carry out frequency domain information modulation, and carrying out the frequency domain information modulation; obtaining the potential representation after the secret information is embedded; s2, inputting the potential representation embedded with the secret information into a diffusion model, and generating a visual natural steganographic image through a diffusion inversion process; s3, inputting the received steganographic image into a diffusion model, and decrypting the received steganographic image without original model weight modification and empty prompt conditions to obtain embedded secret information; according to the method, the frequency domain embedding technology is combined with the potential diffusion model, so that high-fidelity, high-capacity and high-robustness image steganography is realized.

The invention discloses a heterogeneous network embedding method based on dynamic heterogeneous network decomposition and a hierarchical space-time attention mechanism. The method comprises the following steps: dynamic network decomposition: decomposing a heterogeneous network sequence into independent subgraph sets according to edge types; multi-order node attention aggregation: for each sub-graph, fusing information of nodes and different edge types; semantic level attention is embedded, wherein global semantic embedding is generated in combination with global relation type weight and meta-path long-short-term memory network coding; time dynamic modeling: respectively calculating a time attention weight and a Monte Carlo sampling approximate Horkes intensity, and then aggregating and splicing results of the time attention weight and the Monte Carlo sampling approximate Horkes intensity to obtain a final embedding result. According to the method, through cross-granularity semantic modeling and efficient time sequence dependence learning, an innovative solution is provided for node representation of the dynamic heterogeneous network.

The invention discloses a mapping knowledge domain embedding method fusing meta-information and logic rules, and relates to the technical field of computers. The method comprises the following steps: inputting a to-be-predicted knowledge graph into a knowledge graph embedding module; in the multi-granularity meta-information embedding module, for each entity to be predicted in the knowledge graph to be predicted, obtaining ontology information embedding and multi-hop neighbor relation embedding of the entity to be predicted; carrying out average pooling processing on each of the multi-hop neighbor relation embedding, and processing the neighbor relation embedding after the average pooling processing through a multi-layer perceptron and learnable parameters to obtain a hierarchical attention weight of each neighbor relation embedding; each multi-hop neighbor relation embedding comprises a plurality of neighbors; and performing weighted summation on the ontology information embedding and the multi-hop neighbor relation embedding based on the hierarchical attention weight to obtain meta-information embedding of a to-be-predicted entity in the to-be-predicted knowledge graph. According to the method, the determination precision of the meta-information embedding of the entity can be improved.

The present application belongs to the technical field of image analysis, and particularly relates to a kind of electronic component defect detection method and system based on machine vision, comprising the following steps: S1, the visible light, X-ray and three-dimensional structure light image of the electronic component to be measured are acquired, and respective multi-scale feature pyramids are generated through independent feature extraction network respectively;S2, multi-modal fusion feature pyramid is generated;S3, candidate region generation network is applied to propose candidate defect region;S4, spatial topological relation graph is processed through graph neural network, and spatial context information is embedded into candidate defect region feature;S5, if the minimum distance of candidate region feature and all pre-stored prototypes is greater than the set discrimination threshold, then it is determined that the candidate region is unknown type potential defect.The present application widens the detection range and improves the robustness of feature expression, overcomes the limitation of insufficient information of single data source, and improves the accuracy, comprehensiveness and foresight of detection.

The invention discloses a composite circuit substrate material parameter pixel gray scale coding method and device and a storage medium, and relates to the technical field of composite substrate material physical property modeling simulation. According to the method, the composite circuit substrate unit image is pixelated, the pixel gray value is used as a matrix material parameter coding space, and then matrix material parameter information is embedded into the substrate unit image, so that fusion coding of wiring pattern features and material mechanical parameters is realized when two or more materials exist in the same layer of substrate; and the accuracy of predicting the equivalent mechanical parameters of the substrate unit through the wiring image information of the substrate unit and the deep convolutional neural network is improved.

The embodiment of the invention provides an end-to-end image compression method and system based on window local attention and generalized chessboard space channel context, and belongs to the technical field of image processing. The method comprises the following steps: constructing a transformation network based on an attention module and a stacked residual block; the transformation network based on the attention module and the stacked residual block is used for executing adaptive transformation of contents through dynamic representation and neighborhood information embedding to obtain potential features; establishing a generalized chessboard space channel context model; the generalized chessboard space channel context model is used for carrying out entropy coding on the potential features; and obtaining image compression data according to the transformation network based on the attention module and the stacked residual block and the generalized chessboard space channel context model. According to the method, redundancy can be eliminated to the maximum extent, excellent rate distortion performance is achieved, and meanwhile high-throughput parallel computing efficiency is ensured.

The invention provides a coding method and system of a Transform class model for channel state information prediction. The coding method comprises the following steps: S1, acquiring and processing channel state time sequence data; s2, inputting the processed data into an encoder to extract features; s3, CFR data needing to be predicted are embedded, and position codes of the model are added; decoding the relevant parameters using a decoder; s4, processing the output of the decoder, and predicting channel state information; and S5, taking the CFR data and the CSI data obtained in the actual scene as the input of the model, and predicting channel frequency response information. According to the method, the time sequence characteristics of the channel state information are calculated and coded, and the time information is brought into the model, so that the relative stability time of the channel at the future moment is considered, the problem of weak time sequence information embedding capability in a Transform model is solved, and the accuracy of channel state prediction is improved.

The invention discloses an image watermarking method for a stable diffusion model, and the method comprises the steps: selecting one of all potential features in a reverse diffusion process of the stable diffusion model as a target potential feature, and constructing an image watermark generation recognition model which comprises a watermark information embedding module and a watermark extraction module; the watermark information embedding module is used for embedding user watermark information into the target potential features, and inputting the obtained watermark target potential features instead of the original target potential features into the remaining sub-models of the stable diffusion model to generate a watermark image; and the watermark information extraction module is used for extracting user watermark information from the watermark potential features obtained by carrying out DDIM inversion on the watermark image, and the user generating the watermark image can be identified according to the extracted user watermark information. According to the method, the user watermark information is embedded into the potential features of the stable diffusion model, so that the image traceability with high robustness and high concealment is realized on the premise of not damaging the quality of the generated image.

The invention discloses an academic community discovery and analysis method driven by a citation network, and the method comprises the steps: constructing the citation network, constructing an adjacent matrix A and a node attribute matrix X according to the citation network, and extracting a core sub-network information matrix S based on a k-core algorithm; constructing a dual-channel sparse graph attention auto-encoder, respectively taking (X, A) and (S, A) as input of the two channels to learn low-dimensional embedding of the two channels, and obtaining joint embedding Z through a dynamic weighted fusion strategy; reconstructing adjacent matrix information by adopting an inner product decoder, reconstructing node attribute characteristics and core sub-network information, and calculating reconstruction loss; and inputting the joint embedded Z into a self-supervised clustering module, performing joint optimization on the information embedding and reconstruction module and the self-supervised clustering module, and finally outputting a group division result of the papers / authors. According to the method, complementary fusion of attributes and a core structure is realized, robustness in noise and sparse scenes is enhanced, and discriminability and stability of group division are improved.

The invention discloses an emotion recognition method and system based on multi-modal data. The method comprises the steps that the multi-modal data in the task execution process of a target object is acquired; performing time dimension consistency processing on the audio data and the video data, and performing original feature extraction on the audio data and the video data which are consistent in time dimension to obtain multi-modal high-dimension original features; performing time sequence feature extraction on the multi-modal high-dimensional original features to obtain low-dimensional key time sequence features; performing cross-modal similarity calculation and adaptive fusion on the voice modal features and the visual modal features in sequence to obtain modal fusion features; performing dynamic gating adjustment and residual connection fusion on the modal fusion feature and the statistical information embedding feature of the target object in sequence to obtain a target fusion feature; and inputting the target fusion feature into an emotion recognition network for classification processing to obtain an abnormal emotion recognition result of the target object. According to the method, the accuracy of emotion recognition is improved.

The invention relates to a nuclear accident fault diagnosis method and equipment combining physical constraints and a large language model, and the method comprises the steps: constructing a mathematical model of fluid flow in a nuclear energy pipeline, and describing the behavior of fluid in the pipeline; converting related information of the nuclear energy pipeline fluid model established in the step into lexical elements tokens which can be understood by a large language model LLM; the physical constraint information is embedded into a large language model LLM; after the physical constraint information is embedded, performing fine tuning training on the large language model LLM to enable the large language model LLM to adapt to a nuclear energy pipeline fault diagnosis task; the large language model LLM after fine tuning training is used for carrying out fault category classification on the new nuclear energy pipeline operation data. According to the fault diagnosis text adaptation mechanism based on nuclear energy related lexical element embedding, nuclear energy operation parameter information presented in a numerical form in a work order is converted into language information containing rich nuclear energy operation features, and then the advantages of a large model in the aspect of feature extraction are fully played.

The invention relates to a node representation learning method fusing diffusion hypergraph modeling and a graph convolutional network, and belongs to the technical field of modeling and prediction of a complex diffusion process. The method comprises the following steps: extracting a static node structure representation of a social graph, and obtaining a social context feature representation of the static node structure representation; constructing a diffusion hypergraph according to the propagation diffusion sequence, and dividing the diffusion hypergraph into a plurality of sub diffusion hypergraphs; performing feature extraction and fusion on each sub-diffusion hypergraph to obtain user information features; obtaining time sequence feature information embedding based on the improved LSTM network and the user information features; and performing cross-dimension splicing on the social context feature representation and the time sequence feature information to obtain a splicing fusion feature, obtaining a propagation probability based on the splicing fusion feature, and completing model performance evaluation based on the propagation probability. The objective of the invention is to solve the technical problems that time sequence information is not deeply learned and global information is not integrated in the prior art.

The application discloses a kind of short video event detection method and device based on multi-modal representation learning, method includes: constructing latent sequence characteristic acquisition module, explores short video visual modal information and hearing modal information on the latent characteristics of short video before and after sequence;Construct a cyclic interaction information embedding module, construct a cyclic matrix for different modal, fully explore the relationship between multi-modal data and its coupling mode, mine the potential correlation between multi-modal feature elements;Local attention and global attention characteristic enhanced fusion feature representation are obtained by multi-modal attention fusion network;Event detection is realized using the short video multi-modal fusion features obtained by training.The application uses the visual and auditory modal information of short video, constructs short video feature representation learning network that fully mines the multi-modal information latent correlation characteristics and its attention enhancement, realizes the detection of short video event.Provides a new way of thinking for solving short video event detection problem.

The application discloses a neural network embedding method and device for power distribution network state estimation, electronic equipment and medium, wherein the method comprises: acquiring an input sequence; embedding time information and node type information into a vector through space-time prior information embedding to obtain a space-time embedding vector; sampling a node of interest according to a power flow direction of optimal power flow and fusing node information to obtain a node embedding vector; using a graph isomorphism neural network to capture the local of a graph and embedding it into a feature vector to obtain a structure embedding vector; fusing the input sequence and the three vectors and inputting them into a graph space-time prediction network to output a prediction result. Through the introduction of space-time prior information, graph node embedding based on the optimal power flow direction and graph structure embedding of the graph isomorphism neural network, the application realizes the modeling of the characteristics of the power distribution network, makes up for the deficiency of the prior art in the specific modeling of the power distribution network and improves the accuracy of the power distribution network state estimation.

This invention relates to a physical information neural network-based intelligent performance prediction method and system for automated multi-material fiber placement on complex curved surfaces in aircraft. The invention includes: collecting fiber placement process parameters; performing standardized preprocessing and physical constraint-enhanced sampling to obtain an enhanced training dataset; constructing a high-order nonlinear sparse regression candidate library based on the enhanced training dataset; jointly identifying piecewise smooth physical differential equation systems and their mode switching logic using sparse Bayesian regression and Hidden Markov Models to obtain an embeddable inverse mechanism model; constructing a Physical Information Embedded Generative Adversarial Network (PI-GAN); collaboratively optimizing the generator and discriminator through adversarial training to output surface defect indices and mechanical performance indices; and initiating incremental self-learning when introducing new process scenarios to achieve model self-evolution. This invention achieves end-to-end accurate prediction of multi-dimensional quality indices such as surface defects and mechanical performance.

The application discloses a system construction method for realizing CAD model security and data property right identification management, and realizes automatic identification management of UG / NX model security and data property right classification based on a PLM system.The technical scheme comprises the following steps: step 1: security classification label, that is, determining the security label of the model through a security review process node; step 2: intellectual property right classification label, that is, determining the intellectual property right label of the model through an intellectual property right review process node; step 3: specifying the corresponding label based on an improved document review process of product life cycle management of an enterprise; step 4: remotely transmitting the label information embedding program to a task queue server, that is, triggering the embedding program to remotely transmit the label information and related model information to the task queue server after the review is completed; and step 5: automatically writing the label into the server based on UG / NX secondary development technology, so as to write the label information into the UG / NX model.

The application discloses an image data hiding method for predicting pixels based on a voting strategy. The application divides a cover image into a gray area and a white area according to the pattern of an international chessboard, and uses the pixels of the white area to predict the pixels of the gray area. Here, the voting strategy is used for the prediction. Then, the application directly uses the predicted gray values to embed multi-bit secret data through a mapping table. When the secret data is recovered at the receiving end, the secret data embedded in the gray pixels can be inquired from the mapping table according to the difference between the received gray area pixel value and the predicted gray area value, so as to extract information. The scheme provided by the application combines the voting strategy with pixel prediction, can significantly improve the secret information embedding capacity, and enables the stego image to have a better visual effect when more information is embedded.

The invention relates to the technical field of data processing, and discloses a copper product full life cycle-oriented carbon footprint big data warehouse table design method, which comprises the following steps of: carrying out abnormal data filtering on an original carbon footprint data set of a copper product full life cycle to obtain standardized carbon footprint data; based on the standardized carbon footprint data, performing time series data storage optimization on the table structure of the big data warehouse to obtain a dynamic partition table structure; according to the standardized carbon footprint data, performing data mapping on the dynamic partition table structure to obtain an initial data table; traceability information embedding is carried out on the initial data table, and a carbon footprint big data warehouse table is obtained; performing storage structure reconstruction on the carbon footprint big data warehouse table to obtain an efficient storage data warehouse; carrying out life cycle carbon emission analysis on the efficient storage data warehouse to obtain a structured carbon footprint analysis report; according to the invention, the efficiency of carbon footprint data processing can be improved.

The supply chain firmware encryption method based on algorithm subpackaging and information embedding provided by the invention comprises the following steps: subpackaging a real supply chain firmware package based on a subpackaging algorithm to obtain a plurality of real sub-packages, and recording file characteristics of each real sub-package; generating a plurality of corresponding invalid packages based on the file features; mixing the invalid packets into a packet set containing the real sub-packets to obtain a mixed packet set; and generating names and sequences of the real sub-packages, and embedding the test information of the subpackaging algorithm and the names and sequences of the real sub-packages into firmware information. According to the method and the device, the firmware package of the supply chain is subpackaged, and the invalid package is mixed, so that the firmware package is difficult to crack, and the confidentiality of firmware is enhanced.

The application discloses a kind of environmental element information embedding heterogeneous network key node mining method, according to cross-layer rotation embedding, multi-modal environmental element embedding and reinforcement learning optimization strategy, the application not only can accurately model the cross-layer relationship of multilayer power network, improve the accuracy of edge prediction task, simultaneously can be combined with reinforcement learning to identify high-risk key nodes, provide scientific basis for disaster response, risk assessment and safety scheduling of smart grid, improve the security, resilience and intelligent level of power grid system.

The invention discloses a self-adaptive asymmetric image steganography method and system based on a diffusion model, and relates to the field of artificial intelligence and information security. According to the method, the corresponding cumulative distribution probability is calculated according to the noise to be embedded, then the secret information is embedded by slightly modifying the cumulative distribution probability, and the Gaussian noise after the information is embedded is obtained by using the inverse cumulative distribution function, so that the probability distribution of the embedded Gaussian noise is kept unchanged. Before actual embedding, simulation embedding is carried out in noise to be embedded, processes of simulation embedding + 1 and-1 are respectively completed to eliminate pixel points of which information cannot be correctly extracted, and modifications introduced by embedding + 1 and-1 to the noise are calculated. And then the asymmetric steganography embedding cost of each pixel point is obtained through calculation according to the modification amount, then secret information is embedded into cumulative distribution of Gaussian noise, and finally a reverse process is completed and a secret-carrying image is generated and obtained. The problem that an existing steganography method is insufficient in detection resistance and imperceptibility is solved.

A first node (e.g. an AP-MLD device) receives a Multi Access Point Co-ordination (MAPC) parameter set from at least another node in the network. Each MAPC parameter set data comprises MAPC capabilities information identifying one or more MAPC features supported by respective other nodes and details of supported functionality for each identified supported MAPC feature. An MAPC parameter set data for the first node is provided to the other network nodes. Information is exchange (e.g. direct or relayed messages) for establishing or modifying (e.g. updating or terminating) an MAPC group with at least one other node, said MAPC group is usable for defining a co-ordination between nodes of the MAPC group. The features, defined by management frames received from the other nodes, are then executed in accordance with the defined coordination. Apparatus, methods and computer program are defined for the above. Parameters may include: an element ID, length data, element ID extension data, and MAPC information of variable length – the MAPC information is thus embedded in the parameter set. The modification of coordination between nodes may involve MAPC management frames with MAPC headers instructing the removal of an identified node from the MAPC group.

The invention discloses a handwritten comment extraction method and device, equipment and a storage medium, and belongs to the technical field of handwritten comment extraction, and the method comprises the steps: extracting a comment image in a drawing image; extracting multi-scale text features and symbol features of the handwritten annotation information, identifying a text annotation according to the text features, identifying a non-text annotation according to the symbol features, and splicing the text annotation and the non-text annotation to obtain electronic annotation information; establishing a coordinate conversion relationship between the drawing image and the electronic drawing; position coordinates of the electronic annotation information on the electronic drawing are determined according to the coordinate conversion relation; and embedding the electronic annotation information into the electronic drawing according to the position coordinates to obtain the electronic drawing with the annotation information. According to the method, the electronic annotation information is recognized through the text features and the symbol features, the position coordinates are determined according to the dynamic mapping relation between the drawing photo with the annotation content and the electronic drawing, and the electronic annotation content is embedded into the electronic document according to the position coordinates.

The application relates to the field of information technology and provides a cross-modal document pre-training model implementation method and device.The purpose is to solve the problem that LayoutLMv3 cannot focus on a task, causing tasks to affect each other and leading to unsatisfactory performance of an ongoing task.The main scheme comprises the following steps: obtaining pre-training document image data;adding 2D text position embedding, 1D text position embedding and masked text information embedding, and taking the addition result as a to-be-fused text embedding vector;adding 2D image position embedding, 1D image position embedding and masked image information embedding, and taking the addition result as a to-be-fused image embedding vector;connecting the to-be-fused image embedding vector and the to-be-fused text embedding vector to obtain a multi-modal fusion embedding vector for pre-training model training; and through the pre-training model, different pre-training models are selected according to different task categories to perform fine-tuning training on different data sets, so that a model meeting a corresponding task is obtained.