822 results about "Binary classification" patented technology

The invention discloses an industrial equipment fault detection method fusing a complex relation and space-time dependence, and belongs to the technical field of industrial anomaly detection, and the method comprises the steps: constructing a plurality of adjacent matrixes, carrying out the weighted fusion to form an enhanced adjacent matrix, and comprehensively and accurately describing the complex multi-dimensional relation between industrial equipment; designing a spatial-temporal feature extraction module, extracting spatial features in parallel by using a graph convolutional neural network and a random graph attention network, extracting time features through time convolution and a multi-head attention mechanism, and dynamically fusing the spatial-temporal features by means of a gating mechanism to generate graph-level features; a state judgment layer composed of a plurality of node-level binary classifiers and a voting mechanism are adopted to comprehensively judge classification results of all nodes, so that the stability and reliability of judgment of the overall state of the industrial control system are enhanced, and the risk of misjudgment is reduced; the problems of equipment relation modeling and multi-dimensional information fusion are effectively solved, features are extracted and fused more accurately, and the accuracy and adaptability of anomaly detection are improved.

The invention relates to a crop drought degree prediction method based on unmanned aerial vehicle remote sensing monitoring. The method comprises the following steps: S1, data collection: collecting a multispectral image and a thermal infrared image of a farmland in real time through a remote sensing sensor; s2, image preprocessing: carrying out preprocessing operation on the collected multispectral image and thermal infrared image; s3, class specific feature selection: dividing the farmland into different classes according to the types, growth stages and expected drought degree grades of the crops, decomposing a multi-class classification problem into a plurality of dichotomy problems, and constructing a deep learning model for feature learning and importance evaluation for each dichotomy problem to obtain a class specific feature selection result; a class specific feature set for each class is formed, and class specific features for different classes are fused to form a comprehensive feature set; s4, model construction and training: constructing a drought degree prediction model according to the comprehensive feature set; and S5, drought degree prediction: realizing real-time monitoring and prediction of drought according to the real-time data and the prediction model.

The invention discloses a pipeline robot pipe network defect detection method and system based on deep learning, and relates to the technical field of image processing, and the method comprises the steps: collecting and preprocessing a pipeline inner wall image in real time, and constructing a high-quality pipeline inner wall image sample; constructing a shallow classification model to perform binary classification on the high-quality pipeline inner wall image samples, and marking the inner wall image samples containing defects as defect image samples; extracting local features and global features of defect image samples, fusing to obtain fine-grained features, obtaining weights of defects belonging to different defect labels, constructing label characterization, enabling the graph convolutional network to construct a multi-label classification model, adaptively modeling correlation information between the labels, and obtaining a defect label prediction result. According to the method, correlation information between the labels is modeled in a self-adaptive mode through the graph convolutional network, classification of various pipe network defect types is achieved, the efficiency and accuracy of pipe network defect detection are improved, and the actual application requirement is better met.

A GNSS positioning slowly-varying fault detection method based on residual-SVR regression comprises the steps that an observation information sequence is acquired based on a Kalman filter, and a covariance matrix of the observation information sequence is calculated; accumulating multi-step information through a sliding window, and constructing chi-square statistics; based on the fault-free data, constructing a training set by taking an innovation sequence as input and chi-square statistics as output, and generating an innovation-statistics mapping function; and fitting a normal slope threshold value based on an SVR predicted value, carrying out least square fitting on an observation statistic curve by sliding a window in real time, and judging whether to start a slow change fault alarm or not. According to the method, the residual error sequence is directly used as model input, and the dynamic chi-square statistical magnitude is used for replacing a traditional dichotomy label, so that the detection delay is reduced; an SVR detection model based on grid search and cross validation collaborative optimization is utilized, and an optimal parameter combination of a minimum mean square error (MSE) is screened through logarithm uniform sampling, interval linear sampling and five-fold cross validation, so that the average absolute error of slowly varying fault detection is reduced.

The invention discloses an emotion recognition method and system based on cross-modal alignment and matching enhancement. According to the method, firstly, feature extraction is carried out on text, audio and video modalities in a data set, and then a text and audio cross-modal emotion alignment module and a text and video cross-modal emotion alignment module are constructed respectively, so that cross-modal semantic alignment is realized. Constructing an emotion label matching module based on an alignment result, generating modal pairs with similar emotions but different labels by using a difficult negative sample mining strategy, and paying attention to cross-modal emotion consistency through a dichotomy task guide model; performing modal feature fusion on the three modals through a six-layer attention crossing mechanism, finally splicing feature vectors, inputting the spliced feature vectors into a long-sequence context fusion modeling module for deep modal fusion, and capturing cross-modal interaction information; and the fused features are sent to an emotion classification module, and a final emotion category recognition result is output.

The invention discloses a data collaborative directory management method and system, and relates to the technical field of government affair informatization, and the method comprises the steps: generating a directory snapshot containing a global hash value; calculating a directory node hash value of each edge directory node based on the directory snapshot identifier; eliminating clock drift interference through time sequence alignment and dynamic tolerance filtering; inputting the Hash difference time sequence into an isolated forest model to judge a substantial change node; based on the difference entry number and the historical calling weight, combining a dual-threshold rule and an online dichotomy model to hierarchically synchronize requirements; according to a grading result, matching an incremental push mode or a full pull mode, and constructing a synchronous transaction context containing an exponential backoff retry mechanism; synchronous operation is executed through the two-stage state model, and compensation rollback is triggered when the synchronous operation fails; and calculating a health index of the substantially changed node, dynamically selecting a self-healing action and optimizing system parameters. The problem of misjudgment caused by time sequence drift is effectively solved, the synchronization efficiency is improved, and the consistency of directory versions is guaranteed.

The present invention discloses a radar automatic recognition method and device for low-altitude small targets. The method first performs radar data preprocessing; then uses a deep neural network to extract the features of the processed data, and then respectively uses supervised learning and unsupervised learning to perform binary classification and anomaly detection; finally, determines whether it is a drone, a bird or other low-altitude floating objects according to the results of binary classification and anomaly detection. This method solves the problem of identifying low-altitude floating objects, has a very wide range of applications, strong generalization ability, less computation, lower cost, and higher recognition accuracy.

The invention discloses a time-space pixel feature progressive fusion remote sensing change detection method based on ViT, and the method comprises the steps: employing a pre-trained Vision Transform (ViT) as a backbone network, carrying out the fine adjustment of a model parameter through introducing a low-rank matrix, and extracting the features of a dual-time-phase remote sensing image through the fine-adjusted model; global-local feature interaction of the dual-temporal remote sensing image is enhanced through a global context branch and a time sequence dependent branch, and three-stage fusion (shallow layer, middle layer and high layer) is performed on features of the front and rear temporal remote sensing images by combining a multi-level progressive fusion mechanism to obtain enhanced features of the dual-temporal remote sensing image; after the features of the dual-time-phase remote sensing image are connected according to channels, convolution fusion is carried out, and a dichotomy prediction change image is generated through up-sampling, nonlinear feature transformation and convolution. According to the method, the target boundary definition and detection precision in a complex scene can be remarkably improved, the model generalization ability is effectively enhanced, and information loss is reduced.

A disease and pest recognition and prediction algorithm based on deep learning, the algorithm comprising the following steps: step 1, selecting a material; step 2, constructing a disease and pest species data set; step 3, constructing a disease and pest recognition model; step 4, establishing a binary classification model; step 5, extracting image features from a multi-classification deep learning model, i.e., constructing a feature library; step 6, building an automatic disease and pest recognition system; step 7, constructing a disease and pest occurrence rule data set; step 8, constructing a disease and pest prediction model; step 9, correcting and updating a model; step 10, constructing a disease and pest recognition and prediction system; and step 11, constructing a disease and pest early-warning model.

The subject invention pertains to deep learning (DL) systems and methods for the binary classification of Alzheimer's Disease. Optical coherence tomography (OCT) generated reports were used, and the images were grouped into 3 different inputs: (1) an optic nerve head (ONH) model including a retinal nerve fiber layer (RNFL) thickness map, a RNFL deviation map, and an ONH-centered en face image; (2) a Macula model including a ganglion cell inner plexiform layer (GCIPL) thickness map, a GCIPL deviation map, a macular thickness map, and a macula-centered en face image; and (3) a General model including all images of (1) and (2). A fusion network is provided to analyze the plurality of images from a single eye for classification. The fusion network includes Feature Extraction, Feature Fusion, and Feature Reconstruction. Ensemble learning is provided to advantageously combine several baseline models to build a single but more powerful model.

The invention provides a multi-receptive-field network abnormal flow detection method and system based on endogenous security attributes, and relates to the technical field of network security and abnormal flow intelligent detection. The method comprises the following steps: firstly, performing multi-scale flow representation, preprocessing and data enhancement on network flow data to obtain enhanced input flow data; local features are extracted through basic convolution, and local and global fusion features are obtained based on a double-branch network comprising a multi-receptive field convolution branch and a Mama-self-attention branch; deep fusion representation is formed through multi-round feature extraction and tensor fusion, and finally binary classification and fine-grained classification results are output through global pooling and a linear classification layer. According to the method, high-precision, high-robustness and high-real-time detection of the abnormal traffic of the complex network is realized under low calculation overhead.

The invention relates to the technical field of fault prediction and computer big data processing, in particular to a generalized zero sample composite fault diagnosis method, device and system based on anti-fact reasoning. According to the generalized zero sample composite fault diagnosis method based on the anti-fact reasoning, a two-stage generalized zero sample composite fault diagnosis model based on the anti-fact reasoning is constructed. According to the model, internal causal components of fault data are pointed out from the angle of causal theory, and then a structural causal model is constructed to describe decoupling and generation of fault features under the guidance of anti-factual reasoning. On the basis, a generative model is improved through a reinforced discriminator in the first stage so as to realize binary classification of a single fault and a composite fault. In the second stage, a single fault category is predicted through supervised training of a classifier, and meanwhile, a traditional zero sample learning method is designed to classify composite faults. According to the method, the diagnosis precision of the model is greatly improved, and the problem of deviation of model diagnosis on visible classes and invisible classes is solved.

The invention provides a user credit scoring method and system based on multi-source behavior data, and the method comprises the steps: obtaining user behavior data, so as to construct a standardized multi-module behavior event record; taking a user as a unit, using the behavior event record as a node to construct a behavior graph, and constructing a directed edge according to a timestamp of event occurrence; based on the behavior map, constructing a user behavior path by using a constrained maximum edge weight path search algorithm; performing structure matching on the high-credit user behavior path template set and each user behavior path, calculating a path deviation degree of each user behavior path, and obtaining a minimum deviation score; and in combination with the minimum deviation score and the matched optimal matching path, predicting a risk tag of the user through a credit scoring model based on dichotomy learning, and outputting a customer credit score.

The invention relates to the technical field of voice recognition, in particular to a training method of an audio understanding model, an audio understanding method and device, a storage medium and a program product. The method comprises the following steps: obtaining a speech recognition model and a large language model; the speech recognition model comprises a coding module, a prediction module and a first fusion module; according to the coding module, the large language model main body, the first fusion module and the binary classification layer, constructing an audio text classification model; the first fusion module and the binary classification layer obtain a modal prediction result according to the acoustic features output by the coding module or the semantic features output by the large language model main body; determining a reverse gradient value of the first fusion module according to the real mode and updating parameters of the first fusion module; in response to the fact that the preset condition is met, an audio understanding model is constructed and trained according to the coding module, the large language model body and a second fusion module, and the second fusion module comprises the first fusion module. The accuracy of audio understanding can be improved.

The invention relates to the technical field of image detection, in particular to a satellite and unmanned aerial vehicle cooperative remote sensing image change detection system and method, and the method comprises the steps: obtaining a dual-time-phase satellite remote sensing image and an unmanned aerial vehicle remote sensing image of the same geographic region; the satellite branches are subjected to four-stage convolution-pooling operation, multi-stage wide-area features are output, and the unmanned aerial vehicle branches output high-resolution local features aligned with the satellite branches in space through the backbone network; performing channel interaction operation on each stage of double-time-phase features, and generating a spatial weight map to strengthen a change region; aligning adjacent level resolutions through transposition convolution, dynamically integrating multi-scale features, and outputting optimized fusion features in combination with residual connection; and performing convolution dichotomy on the fused features to generate a change detection result graph. According to the method, the problem of signal attenuation caused by heterogeneous data feature mismatch is effectively solved, the false alarm rate caused by environmental interference is remarkably reduced, and the complete detection capability of a micro-to-macro full-scale dynamic target is synchronously improved.

The invention discloses an alarm analysis method, device and equipment, and the method comprises the steps: determining a target DAG matched with a target alarm analysis scene from a preset directed acyclic graph DAG; the DAG comprises a plurality of rule judgment nodes; the rule judgment nodes comprise at least one natural language rule judgment node, and each natural language rule judgment node is used for calling a large language model based on a preset prompt text to perform binary classification judgment on the input alarm data; inputting the alarm data into the target DAG, and generating a node hit track of the alarm data; the node hit track is used for recording a rule judgment node triggered by the alarm data and a corresponding judgment result; and obtaining an alarm analysis result based on the node hit trajectory. According to the invention, the automatic, interpretable and traceable research and judgment process of the alarm can be realized, and the accuracy, interpretability and maintenance convenience of alarm analysis are improved.

The invention discloses an alternating current arc detection method based on current and harmonic wave fluctuation and a related device, and the method comprises the steps: collecting first electrical signal data at a preset position in a target power grid, extracting harmonic wave features in the first electrical signal data, collecting second electrical signal data at the preset position, and extracting current waveform features in the second electrical signal data; determining a dichotomy feature data set and a fluctuation feature data set according to the harmonic features and the current waveform features; training a preset model based on the dichotomy feature data set and the fluctuation feature data set to obtain a dichotomy model and a fluctuation model; and performing arc fault detection on the electrical signal of the preset second time period at the preset position through a dichotomy model and a fluctuation model to determine a target arc fault detection result at the preset position. According to the invention, the arc fault detection is carried out through the combination of the binary classification model and the fluctuation model, and the detection accuracy of the fault arc can be improved.

To provide a method for predicting a strain distribution map and determining damage based on deep learning.SOLUTION: The present invention comprises: a step S1 of establishing an image dataset of finite element analysis results for strain distribution map prediction; a step S2 of building a deep learning model for strain distribution map prediction based on a DeepLabv3+ network and performing learning and validation; a step S3 of establishing a dataset for damage determination of a structural analysis model and performing preliminary processing and data enhancement operations; a step S4 of building a binary classification deep learning model for damage determination based on a convolutional neural network and performing learning and validation for transition learning; and a step S5 of performing an interpretability analysis on the learned binary classification structural analysis model and outputting a region in an image that more contributes to classification.SELECTED DRAWING: Figure 1

The invention discloses a text classification method, electronic equipment and a storage medium, and relates to the technical field of data processing, which comprises the steps of improving the input quality through noise filtering and standardization processing in a word segmentation stage, realizing accurate numerical mapping of semantics by means of an embedded matrix in a vector conversion stage, and improving the input quality. The semantic association between word segmentation units is analyzed and quantified into a weight matrix through interactive operation and normalization processing of query vectors and key vectors, value vectors are subjected to weighted fusion through the weight matrix, comprehensive features containing global contexts are obtained, and a result is output through pooling compression and a dichotomy model. By optimizing matrix operation logic and reducing redundant information processing, the technical problems of high calculation complexity, insufficient expandability and insufficient real-time performance caused by dense matrix operation in a large-scale text classification task are solved, and the purposes of improving the semantic comprehension accuracy and improving the text classification efficiency are achieved while the semantic comprehension accuracy is guaranteed. The text classification efficiency is obviously improved, and the applicability of the model in a large-scale scene is enhanced.

The invention belongs to the technical field of biological prediction, and discloses an enzyme-reaction relationship prediction method based on representation learning, which comprises the following steps: acquiring and preprocessing related data of an enzyme-reaction relationship, and constructing an enzyme-reaction relationship database; a multi-modal fusion framework is adopted, a protein language model based on a sequence and a structure and a biochemical reaction language model improved based on functional groups are integrated, and an enzyme-reaction relation prediction model is constructed in combination with an interpretable mechanism; and outputting a binary classification prediction result corresponding to the simplified molecular linear input standard expression of the protein enzyme sequence and the biochemical reaction based on the enzyme-reaction relationship prediction model. According to the method, time consumption and cost in the prediction process can be effectively reduced, function inference on certain novel or unique protein sequences can be realized, in addition, the prediction accuracy can be effectively improved, and researchers are helped to understand the enzymatic reaction mechanism after prediction.

The invention relates to the technical field of GNSS deception jamming detection, in particular to a GNSS deception jamming detection method and system based on a random forest, a GNSS software receiver is adopted to process deception data sets of different scenes, parameters of different processing stages are extracted to serve as sample features, sample tags are added according to the deception occurrence moments of the scenes, and the deception jamming detection method and system based on the random forest are obtained. The parameter characteristics of different processing stages comprise signal processing stage characteristics, original observed quantity characteristics and PVT calculation result characteristics; gNSS deception jamming detection is used as a dichotomy problem of signals not subjected to deception jamming and signals mixed with deception jamming, a random forest classifier is constructed by utilizing extracted sample training, and whether the deception jamming signals exist in GNSS signals to be detected or not is judged by utilizing the classifier. According to the method, the GNSS deception jamming is detected by selecting the parameters of different processing stages as the features and constructing the random forest classifier, the importance of each feature in deception detection is deeply analyzed, and a reference is provided for deeply understanding deception behaviors and reasonably formulating an anti-deception strategy.

The invention provides a document level event extraction method and device based on heterogeneous graph interactive learning and public context sensing fusion. The method comprises the following steps: acquiring a to-be-detected document; inputting a to-be-detected document into the trained event extraction model to generate an extraction result; comprising the steps that sentences in an input document and entity mentions extracted from the sentences are coded, and initial representation vectors of the sentences and the entity mentions are generated; constructing a heterogeneous graph of the input document, performing information interaction on nodes in the heterogeneous graph according to the initial representation vectors of the nodes, and generating global representation vectors mentioned by sentences and entities; performing binary classification on each predefined event type according to the global representation vector of the sentence and predicting the occurrence probability of each predefined event type; extracting a public context between any two entities according to the global representation vectors mentioned by all the entities so as to predict an adjacent matrix between any two entities, and extracting an entity combination; and combining and pairing the predicted event type and the extracted entity to generate an event record.

The invention discloses a rolling bearing depth universal domain self-adaptive cross-working-condition fault diagnosis method and device and a medium, and can be applied to the technical field of rolling bearing intelligent fault diagnosis. According to the method, the fault diagnosis model comprising the feature extractor, the binary classification network and the adversarial domain discriminator is trained through the source domain data containing the fault type label and the target domain data not containing the fault type label, and the loss function in the training process is calculated; adjusting model parameters of the fault diagnosis model according to the total loss function and a preset model parameter optimization algorithm so as to realize shared class feature distribution alignment between the source domain training set and the target domain training set, and identifying a private fault type of the target domain data set according to a confidence coefficient threshold; and when the number of training iterations of the fault diagnosis model is greater than or equal to the maximum number of iterations, the trained fault diagnosis model is tested through the target domain test set, so that the fault diagnosis accuracy of the fault diagnosis model can be improved.

The invention relates to the technical field of message recovery, and discloses an AI-based iOS device message recovery method and system, and the method comprises the steps: connecting an iOS device, positioning a database file of a message application, and obtaining a database file path list; reading an equipment storage sector, creating a physical mirror image, and analyzing a free block position mark in an APFS container super block; binary classification identification is carried out through an AI data block classification model, an SQLite page type label and a page mapping relation are obtained, deleted messages of a recombined database and a device end are determined, differential comparison is carried out on all historical backup snapshot records of an iCloud account, and cloud end deleted messages are obtained; according to the method and the system, the reorganization success rate of the database and the extraction integrity of the deleted messages are improved, and a technical solution is provided for comprehensive, accurate and efficient recovery of the iOS device messages.

The invention discloses a high-precision perimeter security and protection method and system for intelligent diagnosis, which can accurately mark a physical boundary and perform reasonable partitioning by accurately acquiring a security and protection perimeter contour diagram, thereby facilitating more effective deployment of intrusion detection equipment, improving the overall security of a target area, and improving the security and protection efficiency of the target area. Real intrusion and false alarm are distinguished by adopting a predefined rule to set a threshold value and training a dichotomy model, the false alarm rate can be remarkably reduced through manual recheck of suspected intrusion events, it is ensured that safety response is more accurate and effective, low-level, middle-level and high-level alarm mechanisms are introduced, and the safety and reliability of the system are improved. The abnormal condition can be properly responded according to the risk level, so that the processing efficiency is improved, and corresponding emergency plans can be adopted for threats of different levels.

A system and method for facilitating training of large language model based recommender systems are provided. The system may utilize one or more LLMs to create probability distributions for binary classification tasks associated with specific user-item pairs. The probabilities may be utilized to rank one or more tasks directly. The training of the one or more LLMs may involve the use of Knowledge Distillation methods and may be based on incorporating a dual-label system such as, for example, hard labels and soft labels. The one or more LLMs training data may consist of user-item pairs and their corresponding features. The labels used in the training process may include binary classification labels and their respective probabilities. The system may further implement the trained one or more LLMs to determine rankings or recommendations associated with user engagement of one or more content items.

Disclosed in the present application is a generative adversarial network (GAN)-based test data automatic generation method, which comprises the following steps: step 1, for a required test task, acquiring training data conforming to an actual test; step 2, preprocessing the training data, wherein, in order to ensure more balanced and comprehensive learning of a GAN during a training process, triplet partitioning is used to preprocess the training data; and step 3, designing and building a GAN model, wherein the GAN comprises a generator network and a discriminator network, the generator network being used for capturing and learning the distribution of the training data, and the discriminator network being used for determining the realness of sample data, namely determining the probability of the sample data being from real training data. The present application constructs the generator network in the form of encoder-decoder, and then constructs the discriminator network in the form of processing a binary classification task, the generator network and the discriminator network jointly forming the whole architecture of the GAN.

The invention discloses a model training method and device, a storage medium and a computer program product, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining a weight positive sample training set and a weight negative sample training set, the weight positive sample training set and the weight negative sample training set are obtained by labeling and screening a preset unlabeled sample set; based on a preset unbiased positive sample and unmarked sample learning algorithm, according to the weight positive sample training set and the weight negative sample training set, training to obtain a dichotomy model; iterating the dichotomy model through a loss function and a regular function corresponding to the dichotomy model based on a preset expectation maximization algorithm until the dichotomy model converges, and obtaining a converged dichotomy model; and taking the converged dichotomy model as a prediction model. The problems that an existing method is poor in universality and generalization and needs to label samples manually are solved, and the universality and generalization of model training are improved.

The invention belongs to the technical field of medical image intelligent diagnosis, and provides a breast cancer focus benign and malignant discrimination method based on a gated multi-expert mechanism. The method comprises the following steps: firstly, carrying out standardization and semantic preprocessing on a mammary gland X-ray image, a BI-RADS imaging report and structured clinical data, embedding age, mammary gland density and focus position information into a text template in a natural language form, and realizing unified expression of multi-modal input; secondly, extracting image features by utilizing a ResNet network and a simplified CLIP model, obtaining a text semantic vector by adopting a Bio-ClinicalBERT model, and establishing two sub-paths of a lump expert and a calcification expert in a Transform structure; further, an expert weight is dynamically generated through a gating routing mechanism, and soft routing fusion is executed; and finally, outputting benign and malignant results of the breast cancer focus by the binary classification module. According to the method, deep fusion and dynamic collaboration of the mammary gland X-ray image, the BI-RADS text and the clinical information are realized, and the accuracy and interpretability of breast cancer discrimination can be remarkably improved.

The invention belongs to the technical field of artificial intelligence, and relates to a mail batch processing method, system and device based on a large model and a storage medium, and the method comprises the steps: 1) collecting mails needing batch processing, and carrying out the preprocessing; 2) performing supervision fine tuning and evaluation on the general basic large model by using the constructed mail fine tuning data set to obtain a mail large model; 3) utilizing the mail large model and a trained numerical entity identification dichotomy model to carry out association analysis on mails needing batch processing so as to obtain an associated mail cluster; and 4) by taking the associated mail cluster as a unit, carrying out batch abstract summarization on mails which need to be processed in batches by utilizing the general basic large model. Email processing efficiency and quality can be improved so as to adapt to high-speed development and complex requirements of the information era.