173 results about "Multi layered perceptron" patented technology

The invention discloses a structure perception graph neural network physical field prediction method based on a geometric gating attention mechanism, and belongs to the technical field of artificial intelligence and computational physics crossing. The method comprises the following steps: extracting geometric features for standardization processing and organizing in a graph data structure; inputting the edge-level geometric features into a geometric gating function, generating a dynamic adjustment factor through a multi-layer perceptron, obtaining an attention weight after geometric modulation, and performing normalization processing to obtain output features of nodes; splicing the output features of the plurality of attention heads as final output features of the model; training the graph neural network model to obtain a physical field prediction model; and inputting the geometric features of the three-dimensional structure model to be predicted into the physical field prediction model. According to the method, the precision and physical consistency of complex physical field prediction are improved, and the problems of boundary blur, field intensity sudden change and the like caused by neglecting geometric dynamic change in a traditional static coding method are reduced.

The invention relates to the technical field of electronic detection, and discloses an electronic component dispensing detection method. The method comprises the following steps: acquiring dispensing image data of the surface of the electronic component, and generating a standardized dispensing data matrix containing glue position, thickness and uniformity characteristics through standardized preprocessing; constructing a dispensing correction matrix based on an adaptive window frame, and performing spatial reference dynamic correction on the standardized data matrix to obtain a spatial correction dispensing data matrix; inputting the data into a multi-layer sensor fusion network for feature fusion, and outputting a multi-source fusion dispensing data set; constructing a multi-dimensional abnormal feature incidence matrix based on the data set, and identifying abnormal dispensing data nodes by using a dynamic threshold detection algorithm; performing parameter optimization iteration on the multi-source fusion data set by using a gradient descent optimization algorithm to generate an optimized dispensing parameter set; and finally, constructing a three-dimensional visual dispensing quality model, and establishing a dynamic mapping relationship between model parameters and glue physical characteristics. The method can more comprehensively detect the glue quality.

The invention discloses a frequency domain-spatial domain multi-scale feature fusion complex marine environment ship fine-grained identification method, which comprises the following steps: acquiring a ship image to be identified and preprocessing the ship image to obtain a preprocessed ship image; constructing a frequency domain-spatial domain multi-scale feature fusion ship identification model; inputting the preprocessed ship image into a frequency domain-spatial domain multi-scale feature fusion ship identification model for processing, and outputting a ship fine-grained identification result; wherein the frequency domain-spatial domain multi-scale feature fusion ship identification model is obtained by extracting low-frequency features and high-frequency features of ship images through multistage wavelet transform, generating regional feature distribution and aggregation weights by using a learnable multilayer perceptron, optimizing extraction of ship fine-grained features, and training and verifying through a public data set. The public data set is ship image data and public data used for ship target fine granularity identification. According to the invention, the accuracy and robustness of ship identification are improved.

The invention relates to the technical field of kiln combustion control, and discloses a dynamic tar blending combustion proportion optimization control method and system. Comprising the following steps: collecting kiln system data to obtain a standardized working condition data set; inputting the multi-layer perceptron model to obtain a combustion stability score; when the score is lower than a stable threshold value, triggering risk assessment: extracting kiln load micro fluctuation characteristics from the data set, classifying shutdown risk levels by using a support vector machine algorithm model, and determining a high-risk early warning signal; based on the signal correlation current working condition, a historical optimal blending combustion proportion in a corresponding historical adjustment record is called, a deviation value is calculated in combination with the current blending combustion proportion, and a preliminary proportion adjustment suggestion value is obtained; and iterative correction is started, real-time fuel characteristic change and a combustion state prediction result are fused for step-by-step adjustment, a correction proportion is input into a multi-layer sensor to calculate a stability score, and an optimization control scheme is output after the stability score reaches the standard. According to the method, the tar blending combustion proportion is dynamically optimized, the combustion stability of the kiln is effectively improved, and the shutdown risk is reduced.

The invention discloses a forest point cloud branch and leaf separation method fusing double attention and edge perception, and relates to the field of forestry environment monitoring, the method is based on a forest point cloud branch and leaf separation network CLEANet, a classical encoder-decoder architecture is adopted, an encoder layer is composed of a down-sampling module and a channel-local point attention CLPA module, and the channel-local point attention CLPA module is composed of a down-sampling module and a channel-local point attention CLPA module. The decoder layer realizes feature recovery through combination of up-sampling, an edge perception module EAM and a multi-layer perceptron MLP, the CLPA module adaptively strengthens geometric detail and semantic feature expression through a double-attention mechanism and effectively captures wood and leaf component differences, the EAM module enhances perception of a network to a local geometric structure through a neighborhood feature propagation and fusion mechanism, and the local geometric structure is effectively captured. And characteristic mutation of the wood and the leaf at the boundary is captured. The method integrates a channel-local point attention mechanism and edge perception, has excellent robustness, good generalization ability and wide practical application potential, and provides powerful technical support for forest resource investigation and ecological environment monitoring.

The invention relates to a multi-modal 3D target detection method based on progressive deep fusion. Comprising the following steps: acquiring point cloud data and image information, and processing to obtain structured point cloud voxel features and standardized image information; dividing the point cloud into regular cylinder grids, extracting in-column point-level features by using a multi-layer sensor to generate column-level features, mapping the column-level features to a bird's-eye view feature map, generating a three-dimensional anchor frame through a region candidate network to predict a target position and attitude offset, and outputting a spatial ROI (Region of Interest); based on a YOL3D single-stage target detection method, multi-scale features are extracted by adopting a shared backbone and multi-scale fusion processing, multi-head collaborative regression target three-dimensional parameters of depth detection are utilized, and external parameter transformation is performed to generate a spatial 3D-ROI unified with laser radar coordinates; cross-modal geometric alignment is achieved through TAM, feature complementary fusion is completed through RAM, finally, feature cubes are fused, and categories, three-dimensional positions and postures of multiple targets are output. According to the invention, the detection precision of small targets, shielded targets and long-distance targets is improved.

The invention belongs to the technical field of hydropower engineering construction safety intelligent monitoring, and particularly provides a hydropower engineering construction potential safety hazard image-text multi-mode intelligent identification method, system and equipment, and the method comprises the steps: collecting hydropower engineering construction potential safety hazard text and image data, and building a corresponding relation between a potential hazard text and a potential hazard image; processing the hidden danger text by using a BERT model, extracting text features, processing hidden danger image data by using a Vision Transform model of a multi-head self-attention mechanism, and extracting image features; fusing the extracted text features and image features through Gate Net to obtain fused feature expression; a feature with a higher level is extracted from the fused features through a Transform model; and classifying the processed features by using a multi-layer sensor, and outputting results of various hidden dangers. According to the method, association between a construction potential safety hazard text and an image is fully considered, an image-text multi-modal joint characterization principle based on gating circulation fusion is provided, and a construction potential safety hazard multi-modal classification identification method is provided.

A method includes obtaining images of a scene and corresponding position data of a device that captures the images. The method also includes determining position data and direction data associated with camera rays passing through keyframes of the images. The method further includes using a position-dependent multilayer perceptron (MLP) and a direction-dependent MLP to create sparse feature vectors. The method also includes storing the sparse feature vectors in at least one data structure. The method further includes receiving a request to render the scene on an augmented reality (AR) device associated with a viewing direction. In addition, the method includes rendering the scene associated with the viewing direction using the sparse feature vectors in the at least one data structure.

The invention particularly relates to a false news detection method based on multi-modal information deviation perception fusion, and the method comprises the steps: employing a detection model fusing multi-modal information deviation features, enabling the model to respectively encode three types of modal features, fusing the text modal features and the image modal features through a full-connection network, and carrying out the detection of the multi-modal information deviation features; and in combination with a deviation score output by the multi-modal information deviation calculation module, modulating and guiding information among different modals, and respectively constructing a fine-grained cross-modal attention fusion path based on a pre-training language model and a pre-training image model and a semantic interaction fusion path based on a contrast language image model. At the same time, the model also uses a gating mechanism to fuse attention output, and jointly inputs each single-mode and multi-mode fusion result into a final classification network. And finally, taking the four paths of fusion features as input, and adopting a multi-layer perceptron for training and optimization to realize accurate discrimination of false news.

The invention discloses a vehicle dynamics multi-step prediction method, device and equipment and a storage medium, and relates to the technical field of automatic driving, and the method comprises the steps: obtaining vehicle data; generating a sequence sample based on the vehicle data using a sliding window; the sequence sample is input into a pre-constructed time sequence neural network, a prediction result is obtained, the time sequence neural network is composed of a gating circulation unit encoder and a multi-layer perceptron regression head, and the precision of complex working conditions can be improved.

The invention provides a method and a system for constructing an online rainfall forecasting model based on a space-time dynamic hypergraph neural network. The method comprises the following steps of: establishing a graph model of a hypergraph, an adjacent matrix of an original graph and an incidence matrix of the hypergraph; taking a hypergraph neural network mechanism as a core, and establishing an online rainfall forecasting model based on a space-time dynamic hypergraph neural network; splicing the time sequence and the space sequence of the rainfall data by adopting an encoder, inputting the spliced time sequence and space sequence into a multi-layer perceptron with a full-connection structure, and finally outputting a prediction sequence by adopting the multi-layer perceptron with the full-connection structure by a decoder; wherein the step of establishing the encoder comprises establishing a time embedding module for capturing meteorological elements and establishing a hypergraph attention network; wherein the step of establishing the decoder comprises the step of establishing a multi-layer sensor with a full-connection structure. And establishing an online learning mechanism, a seasonal sample storage pool and an online training mechanism based on mixed domain dynamic playback for correcting the output of the online rainfall forecasting model.

The invention discloses an intelligent design method for a dual-frequency wide-angle high-transmission metasurface, which comprises the following steps of: performing layered sampling on geometric structure parameters of a metasurface unit, performing equal-interval sampling on incident angles, performing full-wave electromagnetic simulation on a parameter sample group to obtain transmission electromagnetic response data, and constructing a database; a multi-layer perceptron neural network is used for learning a nonlinear mapping relation among geometric structure parameters, incident angles, frequencies and transmission coefficient amplitude values, and an independent test sample is used for evaluating the prediction precision and generalization ability of the trained multi-layer perceptron neural network under wide angles and dual frequency bands. A substitution model is constructed based on the trained multi-layer perceptron neural network, the substitution model is embedded into a global optimization process, structural parameters are iteratively optimized in combination with a heuristic search algorithm, an optimal design meeting a dual-band high-transmittance index is obtained, the precision and efficiency of metasurface design are remarkably improved, and the performance of the metasurface design is improved. While the wide-angle double-frequency high transmission performance is ensured, the design period is greatly shortened.

Apparatuses, systems, and techniques to select, from an elastic neural network, a sub-network that satisfies deployment constraints. In at least one embodiment, a sub-network is selected from an elastic neural network by using routers trained to select candidate sets of network architecture elements for each of a plurality of network architecture axes, including attention heads, MLP width, embedding dimension, and number of layers. In at least one embodiment, the elastic neural network is a large language model (LLM), and each transformer block of the LLM has a uniform architecture, thereby facilitating hardware acceleration during training and / or inference.

The present disclosure provides a method for implementing transformer models in analog compute-in-memory hardware. The method comprises training a target neural network using one or more operators on one or more graphics processing units, generating one or more datasets from full network traces to capture input-output relationships of non-vector-matrix multiplication operations, training one or more multi-layer perceptrons to approximate the non-vector-matrix multiplication operations using the one or more datasets, replacing the original non-vector-matrix multiplication operations with the trained one or more multi-layer perceptrons, and mapping the resulting multi-layer perceptron-only neural network to an analog compute-in-memory architecture. The non-vector-matrix multiplication operations comprise layer normalization operations, softmax operations, and GELU activation operations. The analog compute-in-memory architecture comprises crossbar arrays of memory elements that store weight values as analog quantities using conductance or capacitance properties.

This invention proposes a mechanism-aware synergistic anticancer drug combination prediction method and system, belonging to the field of biomedical technology. It includes: extracting node-level feature representations of the first and second drugs through a drug encoder, and extracting molecular representations of the cell line through a cell line encoder; generating an attention tensor based on a trilinear cross-modal synergistic strategy using a trilinear attention network to explicitly capture the synergistic dependencies of the drug combination in a specific cellular environment, and updating and enhancing the features through context fusion; finally, concatenating the enhanced features and outputting a synergistic score via a multilayer perceptron. This invention can directly model the joint interaction relationship between the first drug, the second drug, and the cell line, thereby accurately predicting the synergistic effect of the anticancer drug combination.

The application relates to the technical field of financial big data management, and discloses a financial big data management system based on a time sequence neural network, wherein the system comprises the following steps: each jurisdictional edge node generates a dynamic transaction directed graph based on a real-time transaction event stream, and extracts a local graph topology difference sequence containing a boundary node in-out degree change vector; a lightweight deep separable causal convolution encoder encodes the sequence, generates a local context-aware node representation through attention-weighted fusion; a boundary embedding vector is uploaded to a coordination node after being anonymized, cross-jurisdiction embedding space progressive unification is realized based on a federal-level contrast learning loss and Fisher information matrix weighted aggregation; asynchronous federal synchronization is triggered based on distribution drift detection; cross-jurisdiction candidate link logical splicing and distributed verification are completed through density clustering and cosine similarity matching; and finally, a multilayer perceptron classification network outputs a risk level and generates a cross-jurisdiction money laundering risk report.

The invention belongs to the technical field of airport meteorological monitoring, and relates to an airport dominant visibility measurement method and system based on multi-source data fusion, and the method comprises the steps: 1) employing the backscattering coefficient, PM2.5 concentration and relative humidity of a laser radar as feature vectors, and carrying out the weather classification through a support vector machine classifier; 2) under different weather types, using a laser radar to obtain echo signals of the whole airport area, and using a point-type visibility meter to obtain point-type visibility; 3) preprocessing the echo signal and obtaining laser visibility based on the echo signal; 4) performing dynamic weight iterative optimization on the point-mode visibility, the laser visibility and the near visibility under different weather types through a dynamic weight multilayer sensor to obtain final visibility; and 5) performing dominant visibility judgment based on the final visibility, and determining the dominant visibility. Through multi-source data fusion and an intelligent algorithm, the problems of insufficient precision, poor environmental adaptability and low automation degree in the prior art can be solved.

The invention discloses a multispectral multi-label classification method based on low confusion and spatial spectrum self-balancing, and belongs to the technical field of meteorological remote sensing image classification, a spectral convolutional network is used for efficiently extracting spectral features, in addition, the expression ability of label query is effectively improved through a proposed query generation module, and the classification efficiency is improved. Embedding the label into a query vector by utilizing a multilayer perceptron mapping label, and reducing the similarity between label queries by adopting cross correlation constraints; in order to fully excavate spatial and spectral characteristics, a three-branch network is designed and comprises a spatial branch, a spectral branch and a comprehensive branch; and each branch independently carries out feature learning, prediction results of each branch are fused through a branch balance voting mechanism, the training effect of weak branches is enhanced through interaction between the branches, and finally a more accurate classification result is obtained. According to the invention, in a meteorological multispectral image classification task, especially on identification of complex meteorological system categories, classification of weather systems, surface coverings and clouds can be accurately carried out.

This application discloses a method, apparatus, storage medium, and electronic device for predicting iron ore pixel-level grade, relating to the field of mineral resource prediction technology. The method includes: inputting hyperspectral data of the iron ore to be predicted into a convolutional autoencoder of a pixel-level grade prediction model; extracting low-dimensional features from the hyperspectral data using the convolutional autoencoder; inputting the low-dimensional features into a multilayer perceptron of the pixel-level grade prediction model; and mapping the low-dimensional features to a predicted iron ore grade value for each pixel in the iron ore to be predicted using the multilayer perceptron. This application can improve the accuracy of iron ore pixel-level grade prediction.

The invention belongs to the technical field of frequency spectrum prediction, and particularly relates to a frequency spectrum state prediction method based on a hybrid deep learning model, the hybrid deep learning model is fused with a long short-term memory (LSTM) network and a multi-layer perceptron (MLP), and through three-dimensional frequency spectrum data sensing, self-adaptive dual-threshold energy detection and hybrid model prediction, the frequency spectrum state is predicted. And the accuracy of idle channel spectrum prediction is further improved. According to the method, the secondary user (SU) in the cognitive radio system (CRS) can quickly select the channel with the highest idle probability for access, the repeated sensing frequency is reduced, the total sensing time is reduced by 30%, and the effective data transmission time is improved by 30%. Compared with the prior art, the method provided by the invention is higher in frequency spectrum state prediction precision in a low signal-to-noise ratio (SNR) scene, the throughput of the system is remarkably improved, and the energy consumption of the system is lower.

The invention provides a method for predicting intracardiac abnormal electrophysiological distribution based on an electrocardiogram. The method comprises the steps that body surface multi-lead electrocardiogram data are obtained and preprocessed, and high-quality data fragments are obtained; constructing a lead specific multi-expert network, and extracting lead specific spatio-temporal characteristics; designing a lead weight gating module, and dynamically calculating the attention weight of each lead by adopting a multi-layer perceptron to realize sample self-adaptive lead importance evaluation; performing weighted calibration on each lead feature by using the attention weight, and inputting the reweighted features into a feature fusion and semantic enhancement network to obtain a global feature vector; end-to-end training is completed, and predicted values of the intracardiac abnormal electrophysiology distribution in all the anatomical areas are output. Through lead specific modeling and cross-lead interaction fusion, intracardiac abnormal electrophysiological distribution prediction is achieved, and a noninvasive auxiliary tool is provided for preoperative evaluation and personalized treatment scheme formulation of cardiovascular diseases such as arrhythmia.

An isometric self-supervised line-of-sight estimation method and device, the method establishes a camera coordinate system and a world coordinate system, calibrates the camera, and estimates the extrinsic parameters of the world coordinate system; adjust the camera posture, rotate and scale the camera coordinate system; a virtual camera coordinate system is established, and after the head of the human body moves in three directions for two-dimensional projection, a homography matrix corresponding to the image transformation is obtained; the transformed picture is sent into the encoder for feature extraction, and after the features are extracted, they are projected to the vector space through the multilayer perceptron network, and the Barlow Twins loss is calculated through the hidden space feature mutual correlation matrix; the obtained encoder is connected with the multilayer perceptron network, and in the line-of-sight gaze data environment, the 3D line-of-sight direction is fitted by using transfer learning. The application can efficiently utilize unlabeled data for 3D line-of-sight estimation; it is invariant to appearance transformation and isometric to geometric transformation.

The application relates to the technical field of data processing, and provides a hybrid internal threat detection method based on a DACGAN-Transformer, which solves the problems of data imbalance and lack of fine-grained analysis in internal threat detection. A generative adversarial network (GAN) is used to generate samples similar to normal data distribution but having abnormal characteristics, data set is enhanced, and abnormalities are preliminarily judged. A Transformer model is used for hierarchical feature extraction of log data. Abnormality detection includes single-log abnormality detection and context abnormality detection, and the fine granularity and accuracy of detection are improved. Finally, the overall abnormality score of the GAN and the hierarchical abnormality score of the Transformer are combined, a multilayer perceptron is used for comprehensive evaluation, and whether a log entry is abnormal is determined. The application effectively improves the precision of internal threat detection and the security of a system.

The application discloses an Alzheimer's disease stage recognition method and system based on an interpretable multi-modal, and the method comprises the following steps: acquiring and preprocessing sMRI images of Alzheimer's disease patients and corresponding clinical texts to generate a clinical data set; constructing a multi-modal enhancement fusion model comprising an image feature extraction channel, a text feature extraction channel, a Mamba global sequence module embedding an image feature extraction channel and a feature fusion module based on a gating mechanism; extracting image features and text features of the clinical data set, and performing cross-modal interaction by using a multi-head attention mechanism to generate a feature fusion sequence; inputting the feature fusion sequence into a convolution-based multi-layer perceptron for feature enhancement, performing an Alzheimer's disease classification task and generating a classification result; and using a test set of the clinical data set and a ten-fold cross-validation method to quantitatively analyze the model performance on the Alzheimer's disease classification task, and integrating post-hoc interpretability technology to analyze the model classification result.

The application discloses a graph neural network training method based on flexible diffusion convolution and related equipment, and the method comprises the following steps: acquiring training graph data containing node labels; determining the local structure features of each node according to the node degree information of the training graph data; processing the local structure features by using a diffusion kernel function to obtain the smoothing features of each node; inputting the smoothing features into a multi-layer perceptron to obtain the preliminary label values of each node, and obtaining the predicted label values of each node after processing the preliminary label values through label smoothing; updating the parameters of the diffusion kernel function and the multi-layer perceptron based on the predicted label values and the node labels until convergence or a predetermined number of training rounds is reached. The application can optimize the prediction performance of the graph neural network model, improve the robustness and generalization, and improve the label prediction accuracy of complex graph data such as a recommendation system.

The invention discloses a circRNA (Ribonucleic Acid) and miRNA (Micro Ribonucleic Acid) interaction prediction system and a circRNA and miRNA interaction prediction method of a graph Fourier pulse neural network. The method comprises the following steps: on the basis of high-throughput sequencing omics data of complex diseases, constructing a heterogeneous biological information network containing drugs, diseases, proteins, circRNA, miRNA and lncRNA; converting the topological features of the entities into a unified feature space by using a graph convolutional network; designing a pulse graph neural network in combination with Fourier coding and a pulse neural network, and extracting a topological structure and high-order semantic features in the network; fusing sequences, topologies and semantic features of circRNA and miRNA through a gate multilayer perceptron to obtain embedding features of circRNA and miRNA; and finally, the interaction of circRNA and miRNA is predicted by adopting a Bayesian classifier. According to the method, heterogeneous biological information is modeled from the perspective of network science, Fourier coding, spiking neurons and graph embedding learning are utilized, the action mechanism of circRNA and miRNA in complex diseases can be disclosed, and the method has good practicability and application prospects in the fields of artificial intelligence, life science, clinical medicine and the like.

The invention relates to an e-commerce platform click conversion rate prediction method and system based on time perception, and belongs to the technical field of e-commerce recommendation systems. The invention aims to solve three technical problems in the prior art that the relationship between the user and the commodity is complicated and difficult to characterize, the dynamic evolution of the user interest is difficult to quantify and the periodic difference of the commodity sales is difficult to capture. According to the technical scheme, the method comprises the steps that a user time commodity tripartite graph is constructed, and effective embedding is conducted through representation learning; designing a multi-layer long-short-term memory network to extract long-short-term interests of the user; a time-weighted gating circulation unit is adopted to learn a commodity periodical mode; finally, multiple features are fused, and the click conversion rate is predicted through a multi-layer perceptron. According to the method, the prediction accuracy is effectively improved, and reliable support is provided for accurate recommendation and intelligent decision making of the e-commerce platform.

The invention discloses location coding for perceptual functionality in an automated driving system. A computer-implemented method includes generating 2D position information for image data. The 2D position information indicates a position of each of a plurality of pixels of the image in a 2D reference coordinate system of the image or a position of each of a plurality of blocks of the image in the 2D reference coordinate system of the image. The method further includes feeding input data including the generated 2D position information, extrinsic parameters of the in-vehicle camera, intrinsic parameters of the in-vehicle camera, and distortion parameters of the in-vehicle camera to a multi-layer perceptron configured to process the input data and output a 3D position code of the plurality of pixels or the plurality of blocks. The computer-implemented method further includes feeding the image data and the 3D position code to a transformer network configured to process the image data and the 3D position code and generate a predicted output of the vehicle in a 3D reference frame or a 2D reference frame.

This invention belongs to the field of multimedia analysis technology and discloses a multimodal media tampering detection method, system, device, and medium based on multi-view contrastive learning. The method includes: acquiring a training dataset, which includes training image-training text pairs and corresponding tampering category labels; introducing a cross-encoder based on a visual-language model, setting several multilayer perceptron head structures, and designing three contrastive learning methods: noise enhancement, prototype-based, and multi-label tampering classification, to obtain an initial multi-view contrastive learning framework; training the initial multi-view contrastive learning framework based on the training dataset to obtain a trained multi-view contrastive learning framework; and performing a tampering detection task on the image-text pair data to be detected based on the trained multi-view contrastive learning framework. The technical solution of this invention can improve the accuracy and robustness of multi-label classification.

The application discloses a space level semantic construction and equipment fault diagnosis method, relates to the technical field of industrial equipment fault diagnosis, and comprises the following steps: acquiring the characteristics of each equipment in a system to be diagnosed; the characteristics are vectors obtained by performing feature extraction on operation data and environment data; inputting the characteristics of each equipment in the system to be diagnosed into a fault diagnosis model to obtain a prediction value of a fault category in the system to be diagnosed; the fault diagnosis model is determined based on a fault seen category data set, a fault seen category space level semantic set, a sample feature generation model and a multilayer perceptron; a label is an actual value of the fault category, a space level semantic is a vector composed of description attribute values of the fault, and the space level semantic comprises k layers of semantics. The application improves the accuracy of equipment fault diagnosis.