13results about How to "Enhanced Semantic Information" patented technology

The invention discloses a multi-modal entity connection method based on data enhancement, which relates to the technical field of data processing, and comprises the following steps: enhancing entities by using a large language model, carrying out abstract processing on entity description through a design instruction, and extracting and optimizing key information; semantic information is enhanced by using a multi-modal large language model, enhanced information description is generated by fusing texts and visual features, and the enhanced information description comprises names, types, function and behavior features and physical or structural attributes of entities as well as spatial structures, appearances, color textures and other visual features extracted from the visual information; a candidate entity set is expanded and optimized through a retrieval technology, and retrieval enhancement is achieved; and performing decision selection by using a large language model, and selecting an optimal matching item from a candidate entity set obtained by retrieval enhancement. According to the method, through multi-level data enhancement and an accurate entity selection process, the accuracy and efficiency of multi-modal entity linking are remarkably improved.

The invention discloses a road defect detection method based on an improved YOLOv10 network, and belongs to the field of defect image processing. The core of the method is that a C2f-MCA module is introduced into a trunk part in the YOLOv10 network, modeling can be carried out on the attention of the width, the height and the channel at the same time, a multi-dimensional collaborative attention mechanism is established, and the accuracy and efficiency of a target recognition task are improved; a multi-level feature fusion module BDI is used to replace a traditional feature connection operation module, and semantic information and detail information in an image are enhanced by integrating multi-level feature fusion generated by an encoder; a loss function is optimized, and a SlideLoss loss function is designed, so that the model pays more attention to difficult samples, and bounding box regression is more accurate. Data training and test experiment results show that the average detection precision mAP (at) 0.5 of the new method can reach 86.6%, and the new method is superior to an existing road defect detection model.

The invention discloses a road and bridge deck disease identification method based on deep learning. The method comprises the following steps: acquiring a road and bridge deck disease image data set; constructing a road and bridge deck disease recognition model, and training the road and bridge deck disease recognition model based on the road and bridge deck disease image data set to obtain a trained road and bridge deck disease recognition model; the road and bridge floor disease identification model is constructed and obtained on the basis of a YOLOv9 network framework in combination with a CARAFE up-sampling module and a Triplet Attention mechanism; and obtaining a to-be-identified road and bridge surface image, and inputting the to-be-identified road and bridge surface image into the trained road and bridge surface disease identification model to obtain a disease identification result of the to-be-identified road and bridge surface image. According to the method provided by the invention, the problem of low recognition precision of an existing algorithm in different application scenes is effectively solved, and multiple disease types in road surface and bridge environments can be effectively and accurately recognized.

The invention discloses a method for lightweight prediction of PPI based on Node2vec, and the method comprises the following steps: a protein initial representation module: learning protein initial representation from a protein interaction network G = (V, E) in an unsupervised manner by using Node2vec; the multi-scale relation structure representation module is used for setting two GNNs with different scales to capture shallow layer and deep layer structure information in the protein interaction network, and the GNNs comprise an SGCN variant for the shallow layer structure information and a Mama module for the deep layer structure information; carrying out weighted sum summation on the protein feature representations obtained by SGCN and Mama learning to obtain final protein representation; in the prediction module, the deep protein representation and the shallow protein representation are subjected to element multiplication, semantic information of the features is enhanced, and then prediction is carried out. An unsupervised learning method Node2vec is introduced to carry out unsupervised learning on initial expression of protein, then graph nerve + attention is adopted to carry out supervised fine learning, and local features and global features in the initial expression of the protein are planned as a whole.

The invention provides a target detection method and system for a cervical cell image, and relates to the technical field of target detection, and the specific scheme comprises the steps: obtaining a to-be-detected cervical cell image; inputting the cervical cell image into a trained target detection model to obtain a candidate target area of the cervical cells; wherein the target detection model is used for fusing low-level feature information and high-level information based on enhanced semantic information and position information by adopting a multi-level connected feature pyramid network on the basis of YOLOv5, and generating candidate target areas through fused features; according to the method, the extraction capability of cell characteristics and the perception capability of the model are improved, so that better detection performance is obtained.

The invention discloses a DSE-YOLO v3-based fruit target identification method, and belongs to the technical field of artificial intelligence. The method comprises the following steps: step 1, constructing a data set of a fruit target; step 2, establishing a DSE-YOLO v3 network model; step 3, constructing a DSE-YOLO v3 network model; step 4, identifying fruit targets of large, medium and small scales; step 5, a DSE-YOLO v3 network model is trained; 6, determining an evaluation index of the fruit target recognition model; and step 7, testing effect verification. The DSE-YOLO v3 network disclosed by the invention compresses the network parameter calculation amount on the whole, pays more attention to different types of fruit target features in the process of generating the feature map, enhances the semantic information of the fruit features, effectively inhibits complex background information, and can solve the problem that the recognition precision is poor when the fruits are overlapped, shielded and densely distributed.

The invention discloses a drug adverse reaction detection method based on contrastive learning. For drug adverse reaction information obtained from social media data, a biomedical text mining method is used to mine valuable information therefrom to obtain structured data; a word vector is obtained as an initial value by pre-training words using a Word2Vector method with words as fine granularity, and external knowledge obtained from a medical dictionary is introduced into the word vector; the word vector is encoded using the most advanced BERT algorithm in deep learning to obtain a latent layer representation of the text; a hybrid contrastive learning method is used to optimize the fusion feature representation, and a new loss function is designed to train the model by combining the loss functions of unsupervised contrastive learning (UCL) and supervised contrastive learning (SCL) to improve the robustness of the model; finally, a Softmax function is used to predict the possibility of the existence of drug adverse reactions to achieve detection of drug adverse reactions.

This invention discloses a small target detection method and system based on improved YOLOv11 and fused attention, applicable to small target detection in unmanned aerial vehicles (UAVs). The method includes the following steps: constructing a backbone network using a custom module SFBCR; constructing a neck network using a custom module MFBCR to obtain a custom model; and designing a fused attention mechanism based on the SimAM attention module and PartialConv partial convolutional modules. The model parameters are determined by training on the public UAV small target dataset VisDrone. Compared with existing neural networks, the proposed detection method achieves an average accuracy improvement of 2.03% in UAV small target detection applications while maintaining detection speed. It can be used in smart city construction to improve urban traffic management.

The invention provides a structured annotation enhanced vulnerability detection method based on dynamic path selection, and belongs to the field of source code vulnerability detection. Comprising the steps that 1, each code snippet is analyzed into an abstract syntax tree, and a corresponding control flow graph is constructed; 2, evaluating the importance of paths in the control flow diagram, and dynamically selecting a plurality of paths; 3, the code snippets are provided for the large language model, corresponding row-level annotations are generated for each row of codes, and the annotations are inserted into a selected path according to a predefined annotation insertion rule; and step 4, coding the annotation paths into vectors, extracting a local dependency relationship between the paths, modeling a global dependency relationship between the paths, and finally performing vulnerability detection based on fusion features. According to the model provided by the invention, a code structure and a vulnerability situation can be comprehensively understood, and more efficient and more accurate vulnerability detection is realized.

The application discloses a kind of based on deep feature fusion's cable membrane structure digital twin model reconstruction method, including survey entity cable membrane space structure, arrangement acquisition station, acquisition cable membrane space structure three-dimensional point cloud data;The three-dimensional point cloud of cable membrane space structure is preprocessed and constructs dataset;RPMNet network architecture is improved, and spatial attention mechanism method is applied to the point cloud feature extraction layer of RPMNet network architecture;The three-dimensional point cloud of cable membrane space structure is finely registered;Based on the three-dimensional registration point cloud of cable membrane space structure, fine model reconstruction is carried out;Deviation analysis is carried out to the fine model reconstruction of cable membrane space structure and theoretical design model.The method realizes the accurate registration of three-dimensional point cloud data of cable membrane space structure, completes the high-fidelity digital twin model reconstruction of entity cable membrane structure space form, has the characteristics of high efficiency, low cost and wide coverage, has good applicability to cable membrane space structure, and can be widely applied to engineering practice.

The invention discloses a high-precision infrared target detection method based on YOLOv9 improvement, and the method comprises the steps: taking a disclosed hot data set as target detection image data, converting the target detection image data into a YOLO training format, and obtaining a training set; the method comprises the following steps: based on a YOLOv9 basic framework, introducing an SDI module, a DySample dynamic sampler and an MPDIOU loss function, and constructing an infrared target detection model; inputting the training set into the infrared target detection model, and performing optimization training on the model to obtain a trained infrared target detection model; and inputting an image to be detected into the trained infrared target detection model, and outputting an infrared target detection result. According to the invention, the target detection precision of the infrared image can be improved. The method can be widely applied to the technical field of image processing.

This invention provides an image-assisted 3D object detection method, comprising the following steps: Step 1, extracting features from a point cloud containing the 3D object to be detected and its corresponding image; Step 2, fusing the features of the point cloud and the image based on a block self-attention mechanism to obtain fused multimodal features; Step 3, generating a foreground point mask based on the fused multimodal features and using it to extract multi-scale features with a focus on the foreground, obtaining feature maps of the point cloud at different resolutions; Step 4, generating an object detection proposal, i.e., interpolating the feature maps at different resolutions based on the three nearest neighbor interpolation method, fusing the interpolated features with the multimodal features using a multilayer perceptron, and feeding them into a two-stage detection module to generate an object detection proposal, thereby completing the image-assisted 3D object detection.

The present invention discloses a multimodal entity connection method based on data enhancement, which relates to the field of data processing technology, including: using a large language model to enhance entities, summarizing entity descriptions through designing instructions, extracting key information and optimizing; using a multimodal large language model to enhance semantic information, generating enhanced information descriptions by fusing text and visual features, including entity names, types, functions and behavioral characteristics, physical or structural attributes, and visual features such as spatial structure, appearance morphology, color texture extracted from visual information; expanding and optimizing candidate entity sets through retrieval technology to achieve retrieval enhancement; using a large language model for decision-making selection, and selecting the best matching item from the candidate entity set obtained through retrieval enhancement. The present invention significantly improves the accuracy and efficiency of multimodal entity linking through multi-level data enhancement and precise entity selection process.