345results about How to "Improve recall" patented technology

The invention provides a document knowledge questioning and answering method, a document knowledge storage method and a document knowledge questioning and answering device, and relates to the technical field of intelligent questioning and answering. All layers of nodes of a knowledge tree are traversed according to a target retrieval mode on the basis of the query statement to obtain a query result, the knowledge tree comprises multiple layers of nodes, the multiple layers of nodes at least comprise first-layer nodes, second-layer nodes and third-layer nodes, semantics of the first-layer nodes are semantics of text contents of knowledge point levels in the document, and semantics of the third-layer nodes are semantics of text contents of knowledge point levels in the document; the semantics of the second-layer nodes are the semantics of the paragraph-level text content in the document, and the semantics of the third-layer nodes are the semantics of the full-text-level text content in the document; and outputting an answer text corresponding to the query statement based on the query result. The method provided by the invention not only improves the recall rate of knowledge and the correlation of answers, but also enhances the overall experience of the user, so that the user can obtain more comprehensive and accurate answers in complex queries.

The invention provides a test case generation method and system based on a large model and retrieval enhancement generation, and the method comprises the steps: obtaining a software description document, carrying out text fragment segmentation and vectorization, and constructing a software knowledge base; obtaining and vectorizing a demand document, and recalling a content optimization demand document in the reference software knowledge base based on the retrieval enhancement generation framework; constructing a first Prompt instruction, and splitting the optimized demand document into demand fragments of different test points by using a large language model; and finally, constructing a second Prompt instruction for the demand fragment of each test point, generating a test case by using a large language model, and establishing a mapping relationship between each test point and the test case for linkage output. According to the method, the understanding ability of the large model on the demand document is effectively enhanced; meanwhile, the requirements are decomposed into test points, mapping is carried out on the test points and related test cases, and completeness and accuracy of the requirements and the test cases can be conveniently sorted.

The invention discloses a lightweight track surface defect real-time detection method and device, relates to the technical field of image data processing, and improves the detection precision and detection efficiency of track defect detection by optimizing a model structure and a training strategy. The method comprises the following steps: pre-training a T-YOLOv8 teacher model by using a data set of a track image; the T-YOLOv8 teacher model is obtained by taking an original YOLOv8 model as a basis, introducing an NEW-IAT module into a backbone network and replacing a neck network with a CBAM-C2f module; carrying out distillation training on the lightweight S-YOLOv8 student model by using the trained T-YOLOv8 teacher model, and carrying out optimization and verification on the trained lightweight S-YOLOv8 student model; the lightweight S-YOLOv8 student model is based on an original YOLOv8 model, an SPPF layer is reserved, the rest part of a backbone network is replaced by a lightweight new backbone network, and the lightweight new backbone network comprises three modules of HGStem, LightHGBlock and DWConv; and the optimized lightweight S-YOLOv8 student model is used to carry out real-time detection on track surface defects to obtain track defect information.

The invention discloses an operation site safety management and control method and system based on a multi-modal large model, and the method comprises the steps: collecting site violation data, and carrying out the preprocessing, and obtaining multi-modal data; constructing a multi-modal large model; carrying out training and optimization on the multi-modal large model by utilizing the preprocessed multi-modal data; and using the optimized multi-modal large model to realize operation site safety management and control. According to the invention, a visible light image, a safety violation knowledge base and other modal data are fused, and a comprehensive safety monitoring and management platform is constructed by using a large model and a big data processing technology, so that real-time monitoring, early warning and intelligent response of potential safety hazards of a complex operation site are realized, and the safety management level of the operation site is improved.

The invention relates to an aluminum alloy handle surface defect detection method, device and equipment and a storage medium. The method comprises the following steps: respectively acquiring standard illumination original images and low illumination original images of a plurality of angles of the surface of the aluminum alloy handle, and preprocessing to obtain a preprocessed image pair of each angle; processing is carried out through three parallel convolution branches and residual connection, and an enhanced feature map of each angle is obtained; performing illumination compensation processing to obtain an illumination equalization image of each angle; performing optimization to obtain a de-noised image of each angle; and splicing and reconstructing the de-noised image of each angle to obtain a reconstructed surface image, and carrying out multi-scale feature fusion and surface defect detection on the reconstructed surface image to obtain a surface defect detection result. According to the method, the precision and recall rate of defect positioning on the surface of the aluminum alloy handle are improved.

The invention provides an abnormal network traffic identification method based on small sample data enhancement, and the method comprises the steps: S1, converting one-dimensional traffic data into a two-dimensional gray-scale map, and employing a twin network combined with a dynamic attention mechanism to analyze the differences between various types of traffic data pair by pair; parameters of an attention mechanism in the twinborn attention network are analyzed, and inter-class difference features are identified; s2, selecting a training domain by using the inter-class feature difference matrix, introducing a comparative learning method to judge the difference between real data and generated data, and generating an enhanced data set for each class of traffic; s3, after the enhanced data set issued by the central server is received, each edge server uses the enhanced data set and local sample data to train the twinborn attention network in the step S1; due to different local sample data sets, each edge server is trained to obtain a personalized abnormal traffic identification and classification model suitable for local data distribution, and abnormal traffic is effectively classified.

The invention belongs to the technical field of computer vision and artificial intelligence, and discloses a lightweight wisdom classroom learning behavior detection method and system, and the method comprises the steps: extracting student behavior features in a classroom image, and obtaining preliminary multi-scale features; designing a deep convolutional neural network to perform deep spatial-temporal feature representation on the extracted features, and introducing a focusing modulation module to enhance the features; designing a dynamic detection head to fuse and process features of different scales; and calculating the difference between a prediction result and a real label by using the optimized classification loss function and bounding box loss function, optimizing model parameters, and outputting a final student behavior detection result through the model. And finally, the system performs detailed analysis on the detected student behaviors and generates a visual classroom behavior report. According to the method, more accurate student behavior detection in a classroom scene is realized, a complex classroom environment and diversified student behavior modes can be effectively processed, and the method has relatively high practicability.

The invention discloses an improved YOLOv8 chip surface defect detection model construction method and application, and the method comprises the steps: constructing a network structure of an improved YOLOv8 target detection model, which comprises a Backbone module, a Neck module and a Head module; the Backbone module comprises a multi-layer DCNv3 network, a C2f network and an SPPF network, and outputs a first effective feature layer, a second effective feature layer and a third effective feature layer after performing multi-layer convolution processing on the picture; the Neck module adopts a BiFPN bidirectional feature pyramid feature fusion structure, inputs three effective feature layers output by the Backbone module into a ConcatBiFPN network for bidirectional adaptive fusion, and then outputs the three effective feature layers through a CBAM attention mechanism network; the Head module comprises a Deect network structure, and the Deect network structure is connected with a CBAM attention mechanism network and outputs a target detection result; the improved YOLOv8 target detection model structure is used for accurately recognizing the surface defects of the chip, and the adaptability to different types of defects is improved.

The invention discloses a PET waste plastic intelligent sorting method and system based on multi-feature fusion, and the method comprises the following steps: collecting an RGB-HSI original data set of PET waste plastic, carrying out the dimension reduction processing of the HSI data set based on a genetic algorithm to generate MSI data, and forming a feature fusion data set with RGB data; constructing a feature fusion network based on a YOLACT model, and training by adopting a feature fusion data set; the feature fusion network comprises an RGB branch, an MSI branch and a fusion prediction module, RGB is used for extracting features of RGB data, the MSI branch is used for extracting features of MSI data, and the fusion prediction module is used for combining output of the RGB branch and output of the MSI branch to make comprehensive prediction; and installing the trained feature fusion network to an industrial personal computer to realize intelligent sorting of the PET waste plastics. Compared with a traditional recognition algorithm, the method can improve the recognition precision.

The invention belongs to the technical field of machine vision and deep learning, and discloses an engineering structure crack detection and measurement method based on machine vision, and the method comprises the steps: collecting original image data of an engineering structure, discretizing the original image data into image blocks, carrying out the preprocessing, building a crack classification model through a Resnet-50 neural network, and carrying out the training, the method comprises the following steps of: firstly, constructing an image block, identifying a crack image in the image block, then constructing a SegFormer segmentation model based on a Transformer framework to segment the crack image to obtain a crack mask graph, evaluating the performance of the two models, then analyzing the two models by adopting an orthogonal skeleton line method, obtaining a contour line and a skeleton line of a crack, and calculating the length of the crack. According to the method, the ResNet-50 image classification model and the SegFormer segmentation model are combined to realize high-precision crack identification and segmentation of the building structure crack, the contour line and the skeleton line of the crack are obtained and the length of the crack is measured by means of the orthogonal skeleton line method, and the crack of an engineering structure is well detected and subjected to risk assessment.

The invention provides an unsupervised domain adaptive target detection method and system based on a double-path structure, and the method comprises the steps: carrying out the target detection of an unmarked target domain data set through an unsupervised domain adaptive target detection model of the double-path structure, performing label filtering fusion on the invariant feature detection result set and the feature detection result set obtained by detection to obtain a target false label of the target domain data set; training a model by using the source domain data set, the target domain data set and the target pseudo-tag, and updating the target pseudo-tag once when a new target pseudo-tag obtained based on target detection is trained once; and inputting the to-be-detected target domain image into the trained model for detection to obtain a target detection result, performing label filtering fusion on the result obtained by dual-path detection to obtain a pseudo label with high confidence, and performing training fine tuning on the model by using the data set with the pseudo label. The recall ratio and precision ratio of model detection can be improved, and then the detection precision is improved.

The invention relates to the technical field of software security, in particular to a decentralized financial platform loan intelligent contract vulnerability detection method and system based on a graph neural network, and the method comprises the steps: collecting intelligent contract source code data, and carrying out the vulnerability marking of the intelligent contract source code data according to whether there is a vulnerability in the data; compiling intelligent contract source code data into an abstract syntax tree, and constructing a contract code heterogeneous graph; constructing a graph neural network model, and performing vulnerability prediction training on the graph neural network model by using the contract code heterogeneous graph to obtain an intelligent contract vulnerability detection model, the graph neural network model captures structural features of a contract code heterogeneous graph layer by layer by using a hierarchical attention enhancement mechanism and predicts and identifies vulnerabilities in contract codes based on the structural features; and converting the to-be-detected smart contract source code into a target contract code heterogeneous graph to perform vulnerability prediction on the target contract code heterogeneous graph. According to the method, the semantics and data flow characteristics of the contract can be accurately captured, and efficient and accurate detection of the intelligent contract vulnerability is realized.

The invention discloses an explicit-implicit relationship collaborative extraction method and device based on a large model and a pre-training model, and the method comprises the steps: 1, obtaining a word vector of a text through a pre-training language model, building a word-level table labeling frame based on the word vector of the text, and building a table labeling frame based on the word level; obtaining an explicit entity relationship triple in the text; wherein the pre-training language model is BERT; 2, acquiring implicit knowledge in the text from the GPT model as an external knowledge source; 3, performing instruction fine tuning by fusing the open source large language model with implicit knowledge and prompts, and performing reasoning through texts and implicit knowledge to obtain an implicit entity relationship triple; and 4, systematically integrating the explicit and implicit entity relationship triples obtained from the text by the open source large language model fused with implicit information fine adjustment and the pre-training language model, and finally obtaining a combined triad.

The invention relates to an electric power marketing business abnormity real-time detection method and system based on stream-oriented computation, and belongs to the technical field of electric power system optimizing.The method comprises the steps that data snapshots are extracted from an electric power marketing business system, difference comparison is conducted on the data snapshots and historical snapshots of an intermediate library, and standardized increment events are generated and stored; capturing an incremental event in real time through a data change capturing tool and pushing the incremental event to a message queue; a streaming computation engine consumes the event stream, sequentially performs data cleaning, association with a static dimension table and sliding window statistical feature calculation, and constructs a feature vector; and performing parallel analysis and weighted fusion on the feature vectors based on a business rule base and an online machine learning model to generate a comprehensive risk score, and outputting an abnormal event when the score exceeds a threshold value. According to the method, the problems of exception identification lagging and complex work order process in a traditional batch processing mode are solved, the crossing of the business risk from hour-level detection to minute-level real-time perception is realized, and the timeliness and accuracy of power marketing risk management and control are improved.

The invention discloses a low-overlapping-rate point cloud registration method based on topology-metric decoupling, and belongs to the technical field of computer vision and three-dimensional reconstruction, and the method comprises the steps: scanning an object through a three-dimensional laser scanning collection terminal, collecting point clouds at two different angles as a source point cloud and a target point cloud, and achieving high-robustness registration in a difficult scene with an extremely low overlapping rate; according to the method, through the asymmetric association strategy, the zero solution problem under the low overlapping rate is solved through the one-way matching union set, and the recall rate is remarkably increased; meanwhile, through a DGTG geometric pruning and probability manifold optimization mechanism, a voxel quantization error is eliminated by using anisotropic covariance and Lie algebra iteration, a translation error and a rotation error are greatly reduced, and a precision bottleneck caused by voxelization is effectively broken through. According to the method, the existence of a solution can be ensured under the condition that the overlapping rate is extremely low, voxel quantization errors can be eliminated through manifold optimization based on covariance, and high-precision and high-efficiency registration of low-overlapping-rate point clouds is achieved.

The invention discloses a scientific and technological novelty retrieval method, device and equipment based on semantic elements and a medium, relates to the technical field of text retrieval, combines novelty retrieval semantic vectors and semantic retrieval formulas, captures deep semantics of target novelty retrieval points, ensures that literatures highly related to the target novelty retrieval points are screened out, and meanwhile, through the semantic analysis and retrieval technology, the target novelty retrieval points are obtained. The operation difficulty and the time cost are reduced. The method comprises the steps that when a novelty search application form is received, a comprehensive novelty search point is generated according to content to be subjected to novelty search and retrieval indicated by the novelty search application form, and a novelty search semantic vector of the comprehensive novelty search point is obtained; based on the novelty search application form and the comprehensive novelty search points, extracting target semantic elements; expanding the target semantic elements to obtain a semantic set corresponding to the target semantic elements, and constructing a semantic retrieval formula by utilizing the semantic set; and based on the novelty search semantic vector and the semantic retrieval formula, executing novelty search operation to obtain a plurality of target literatures, sorting the plurality of target literatures, and outputting the sorted target literatures.

The invention discloses a traffic sign detection method and device based on YOLOv5 and a medium, belongs to the technical field of traffic sign detection, and aims to solve the technical problem of how to improve the small target detection precision, reduce the omission ratio and further improve the detection performance of traffic signs. According to the technical scheme, a prior anchor point frame is optimized by using a genetic algorithm and a K-means algorithm, and the detection accuracy of a small target is enhanced; a Bi-FPN structure is introduced to realize feature fusion of semantic and position information, and the representation capability of the network is improved; by integrating an attention mechanism GAM, the anti-interference performance and the feature extraction capability of the network in a complex environment are enhanced; sIOUloss is adopted as a frame regression loss function, so that the positioning accuracy is improved.

The invention discloses an organelle combination phenotype high-throughput drug screening method based on machine learning, and relates to the technical field of drug research and development biology. The method comprises the following steps of: 1, analyzing a cell image by ComOrganNet; step 2, performance evaluation of the ComOrganNet model is carried out; 3, the performance of ComOrganNet in the data set is expanded; step 4, comparing the ComOrganNet with a conventional cell parameter extraction method; 5, verifying the practicability of the ComOrganNet classification model; 6, establishing a natural product library and obtaining an active component screening result; according to the method, cell image analysis and preprocessing are carried out in combination with ComOrganNet, deep learning classification is carried out in combination with OfficientNet V2, higher classification accuracy can be achieved in high-throughput drug screening, particularly, when multi-channel image input is used, the accuracy of a model in a verification set reaches 80%, and the result is remarkably superior to that of single-channel image training.

The invention discloses a road surface disaster detection method and system, electronic equipment and a storage medium, and relates to the technical field of intelligent traffic management and computer vision, and the method comprises the steps: collecting image data containing a plurality of road surface disaster types, carrying out the data marking in each image data, and carrying out the data marking; a data sample is constructed through each piece of image data subjected to data annotation; training the improved YOLOv10 model by using the data sample until a loss function of the improved model reaches a preset end condition, and determining the improved model of which the loss function reaches the preset end condition as a disaster detection model; acquiring a to-be-detected image of a to-be-detected road surface, and inputting the to-be-detected image into the disaster detection model for processing to obtain a disaster detection result of the to-be-detected road surface, the disaster detection result including a disaster type and a disaster position; by combining the deep learning technology and optimization algorithm design, the problem that the existing method is insufficient in detection precision, robustness and applicability is solved.

The invention relates to a sensitive information detection method and device, computer equipment and a computer readable storage medium. The method comprises the following steps: acquiring to-be-retrieved data; preprocessing the to-be-retrieved data to obtain target data; converting the target data into a target vector; performing rule matching on the target vector; if the rule matching is successful, performing similarity retrieval in a preset vector database according to the target vector; a plurality of sensitive information vectors are stored in the preset vector database; if the sensitive information vector meeting the similarity requirement is retrieved from the preset vector database, inputting the target vector into a preset classification model; and determining a sensitive information detection result of the to-be-retrieved data according to a classification result of the preset classification model. By adopting the method, missing report and false report can be avoided, and the accuracy of sensitive information detection is improved.

The invention relates to the technical field of data processing, and discloses a medicine flow data transmission safety early warning method and system based on big data. Firstly, an improved neighbor sorting algorithm and an improved clustering algorithm are used for carrying out similar repeated data cleaning and missing data filling on an original medicine flow direction data set, and a processed medicine flow direction data set is obtained; secondly, dimension reduction processing is carried out on the processed medicine flow direction data set, and a final medicine flow direction data set is obtained; a kernel parameter and a penalty factor in the support vector machine are optimized by using a parrot optimization algorithm, and Cauchy variation improvement is introduced to obtain a support vector machine early warning model; and finally, establishing a medicine flow direction data transmission safety early warning model, checking the final medicine flow direction data set to obtain an early warning result, and completing safety early warning. By processing and analyzing the medicine flow direction data, the purpose of medicine flow direction data transmission safety early warning is achieved, and the method is accurate and objective.

The invention provides a data retrieval method and device, electronic equipment and a medium. The method comprises the following steps: analyzing whether a target problem text can be split or not by utilizing a large language model; under the condition that it is determined that the target question text cannot be split, rewriting the target question text into an abstraction question by means of a large language model; retrieving the knowledge base according to the abstraction problem to obtain a first retrieval result; generating hypothetical answers for the target question text by using a large language model; retrieving the knowledge base according to the hypothetical answer to obtain a second retrieval result; according to the target question text, retrieving the knowledge base to obtain a third retrieval result; and determining a target retrieval result according to the first retrieval result, the second retrieval result and the third retrieval result.

The invention discloses an adversarial sample detection method and system and electronic equipment, and the method comprises the steps: inputting to-be-detected target images into a classifier, and obtaining classification labels corresponding to the to-be-detected target images; inputting the target images to be detected and the classification labels corresponding to the target images to be detected into a trained sequence condition variation auto-encoder to obtain reconstructed images of the target images to be detected output by the sequence condition variation auto-encoder; and determining whether the to-be-detected target image is an adversarial sample or not according to the reconstructed image. According to the method provided by the embodiment of the invention, the classification label and the to-be-detected target image are synchronously input into the trained sequence condition variation auto-encoder to improve the difference between the adversarial sample and the original sample, so that the adversarial sample can be detected more accurately, the accuracy rate, the precision rate and the recall rate of detection are improved, and the method has wide applicability.

The invention relates to an iteration-based undersampling cost-sensitive ensemble classification method, belongs to the technical field of medical data analysis, and is particularly suitable for processing a disease prediction model in an unbalanced data set. According to the method, the sampling probability of the majority class samples is dynamically adjusted through an iterative undersampling strategy, it is ensured that the features of the minority class samples are focused on in the training process, and meanwhile important information of the majority class samples is prevented from being lost. In combination with cost-sensitive learning and ensemble learning, the invention provides a classification method capable of remarkably improving the minority class sample prediction performance while keeping the overall accuracy of a classifier. The method has good adaptability, is suitable for various unbalanced data set scenes, and shows an excellent application effect in medical data analysis and disease early warning.

The invention discloses an intelligent position recommendation method based on BERT. The method specifically comprises the following steps: performing data screening, data filling, feature analysis, data sampling and data conversion processing on employment data of original students; personalized information of students is converted into a natural language text form, and corresponding labels are marked according to original employment data, so that the data can be used for training a text classification model; dividing the processed data into a training set and a test set according to a proportion of 8: 2, and carrying out training, testing and verification by utilizing a pre-trained bert-based-history model; the mapping relation between the employer industry and the position is preset, and the corresponding position is recommended according to the output of the model; the effectiveness of the method is proved by comparing experimental results of other models under the same data. The method has the advantages that the recall rate and accuracy of recommendation results are improved, interview pertinence is enhanced, and the success rate is increased.

The invention relates to the technical field of natural language processing, and discloses an emotion analysis method and system based on multi-modal feature fusion and SVM classification, and the method comprises the steps: constructing a data preprocessing module, a feature extraction module and a classification module; the data preprocessing module is used for preprocessing a to-be-tested text to obtain model input data meeting input requirements; the feature extraction module performs feature extraction and fusion on model input data by adopting multiple methods to obtain multi-modal fusion features; training a support vector machine model by using the multi-modal fusion features to perform an emotion classification task to obtain a classification module; an emotion analysis model is constructed based on the data preprocessing module, the feature extraction module and the classification module, and emotion analysis of the to-be-tested text is achieved. According to the method, a plurality of feature extraction methods are fused, so that all-around representation of text emotion is realized; and the SVM is adopted as a classifier, so that the classification precision of sentiment analysis is effectively improved, and the performance is excellent when large-scale and multi-category data is processed.

The invention discloses an object group identification method and related equipment. The method comprises the following steps: acquiring operation content information of a plurality of content publishing objects in at least one dimension; according to the operation content information, aggregating the content publishing objects to obtain a primary object group; for each primary object group, mining social relation data corresponding to each content publishing object in the primary object group so as to mine a target social association object having an influence on the primary object group; and combining the primary object groups according to the target social association object and the abnormity degree of the content publishing objects in the primary object groups to obtain a potential abnormal target object group. The method can be better suitable for an organized team discovering anomaly detection scene, the discovery efficiency of the abnormal object and the recall rate of the abnormal object are improved, and therefore the detection range of the abnormal object is widened.

The invention provides a multi-source security knowledge fusion driven security risk management large model construction method and application. The method comprises the following steps: constructing a campus security knowledge graph and a semantic vector database based on multi-modal campus security data; performing approximate nearest neighbor search in the semantic vector database based on user query to obtain context evidence related to the user query, splicing the context evidence with the user query to obtain a retrieval enhancement prompt, the user query being campus security risk information of any mode; and training based on the campus security knowledge graph to obtain a security risk management large model, and inputting the retrieval enhancement prompt into the security risk management large model to obtain a risk solution. According to the scheme, the attention confidence, the feed-forward network confidence and the knowledge alignment confidence of all levels are aggregated in the reasoning process to generate the comprehensive confidence score, so that the illusion problem caused by no data reference in the model reasoning process is effectively avoided.

The invention discloses a personal data retrieval method and device based on a deep neural network, and relates to the technical field of data retrieval. The personal data retrieval method and device based on the deep neural network specifically comprise the following steps: S1, data preprocessing and index construction; s2, designing a deep neural network model; s3, performing strategy retrieval and fragmentation processing; s4, displaying a retrieval result; s5, performing feedback and optimization; the semantic relation between the file names is learned through the deep neural network, the intelligent retrieval capacity exceeding traditional keyword matching is achieved, the intention of a user can be accurately understood, and even if the file names are not completely matched, related files can be found; after complete file name retrieval fails, a fragmentation processing strategy is adopted, deep neural network similarity calculation is combined, the retrieval range is effectively expanded, the retrieval recall rate and accuracy are improved, and meanwhile the input burden of a user is reduced.

The invention relates to the technical field of digital archive management and information retrieval, and discloses a digital archive multi-modal data semantic enhancement fusion retrieval method and system.The method comprises the steps that a policy cycle time axis and a policy term evolution graph are constructed, tense logical reasoning is conducted on archive seals, and permission effectiveness evolution is derived; the temporal permission feature vector and the content semantic vector are fused to generate a multi-modal representation vector, and cross-policy-cycle semantic enhancement retrieval is realized by combining query expansion and temporal permission filtering, so that the problems of missing detection and misjudgment of policy and regulation archives in seal permission historical evolution and term cross-cycle retrieval are solved.