468 results about "Manual annotation" patented technology

The invention discloses a semi-supervised identification method and system for a small target of a container, and belongs to the technical field of artificial intelligence and computer vision, and the method comprises the steps: carrying out the target detection of a container image through a pre-trained target detection model, intercepting a sub-image, and inputting the sub-image into an initial classification model, and obtaining a classification confidence coefficient; the uncertainty of the model on a sample classification result is quantified through a Monte Carlo Dropout method; a feature space distance filtering and dynamic threshold adjusting mechanism is combined, and samples with high confidence, low uncertainty and consistent feature space are screened out to serve as pseudo label data; pseudo label data and initial synthesis data are mixed, and the generalization ability of the model is gradually improved through semi-supervised iterative training. According to the method, the dependence on manual annotation can be remarkably reduced, meanwhile, the distribution difference between synthetic data and real scene data is gradually reduced, and finally, high-precision recognition and strong generalization ability of a classification model in a real scene are achieved.

The invention provides an intelligent detection system for forging defects of a forge piece product, and relates to the technical field of industrial intelligent detection.The intelligent detection system comprises the steps that multi-angle images of a to-be-detected workpiece are collected and then spliced, and a complete surface expansion view of the product is generated; obtaining defect types of the defect candidate regions through region coordinates and region sizes of the defect candidates; obtaining a confidence value of a corresponding defect type judgment result; a lightweight deep network recognition model is called for secondary judgment, new sample data are generated in a manner of supporting manual annotation, and an equipment end is connected with a programmable controller for intelligent defect detection of the workpiece to be detected. According to the invention, the problems of incomplete defect coverage, failure to realize high-precision automatic identification of multiple types of defects and influence on the detection accuracy and the production efficiency caused by diversified and complex forging surface defects and limited image acquisition angles in the prior art can be solved, comprehensive acquisition and splicing of multi-angle images are realized, and the detection accuracy and the production efficiency are improved. The technical effect of improving the defect detection accuracy of the forge piece product is achieved.

The invention discloses a multi-granularity visual reasoning model construction method and device based on reinforcement learning. The method comprises the following steps: constructing an'image-reasoning query-bounding box 'triple as a training data set; designing a composite reward function including positioning precision, target counting precision and format reward; training the multi-modal large language model by adopting a GRPO algorithm; the trained model can output a region-level bounding box, and a pixel-level mask is generated and a contour-level result is extracted in combination with the segmentation model. According to the method, the problems that in the prior art, a reasoning path depends on manual annotation, multi-granularity tasks cannot be expanded, and generalization is insufficient are solved, and the autonomous decision-making ability, task expansibility and generalization in a distribution offset scene of the model are improved.

The invention discloses a special disease queue data capturing method and system based on an intelligent medical knowledge graph, and relates to the technical field of medical information, and the method comprises the following steps: S1, constructing a special disease intelligent medical knowledge graph which comprises a bidirectional mapping relation between standard terms of a single disease category and clinical actual corpora, clinical text data is accumulated in a mode of combining manual annotation and machine learning, and a domain exclusive knowledge base containing symptoms, diagnosis and examination indexes is formed. According to the special disease queue data capturing method and system provided by the invention, by constructing the special disease intelligent medical knowledge graph, bidirectional mapping of single disease specification terms and clinical actual corpora is realized, and the problem of insufficient semantic understanding when non-standardized clinical corpora are processed by a traditional method is effectively solved; the entity information in the unstructured medical data can be accurately extracted by utilizing a natural language processing model and an inference engine.

The invention relates to the technical field of power grid intellectualization, in particular to a digital power grid asset classification and evolution monitoring method, system and device based on self-supervised comparative learning and a storage medium. The method comprises the following steps: acquiring network flow data in a digital power grid, extracting multi-dimensional features such as a time interval, a direction, a data packet length, a protocol type and an address port, and constructing an asset behavior feature matrix; then constructing a self-supervised contrast learning model, taking the communication behavior sequences of the same asset in different time periods as a positive sample pair, taking the communication behavior sequences of different assets as a negative sample pair, and training an asset embedding model through an InfoNCE contrast loss function; then, asset communication behaviors are mapped to a semantic embedding space, and asset classification and identification are carried out based on embedded vectors; and finally, carrying out evolution monitoring on the assets by adopting a sliding time window mechanism, generating an asset evolution trajectory sequence, and carrying out abnormity perception early warning. Autonomous learning without manual annotation, high-precision asset identification and real-time state evolution monitoring are realized.

The invention relates to a meteorological data set automatic construction method and system based on modal bridging, and aims to meet the multi-modal large model training requirement in the meteorological field, and the method and system realize automatic conversion from an original meteorological image to a structured expert reasoning text through deep fusion of image and text information. The method comprises five stages of data preprocessing, image-text semantic modeling, causal reasoning generation, consistency screening and parallel processing, key meteorological elements are extracted by using a multi-modal model, a chained thinking process is constructed through a language model with meteorological knowledge, chained reasoning annotation is realized, cross-modal semantic alignment and a multi-round reasoning mechanism are introduced, and a multi-modal semantic model is established. The method is advantaged in that high-quality samples are screened in combination with rules and models, automation, high consistency and good expansibility are realized, manual annotation cost is substantially reduced, and the method is suitable for large-scale meteorological reasoning multi-modal data set construction.

The invention provides a distributed optical fiber temperature sensing logging data blind denoising method and system based on physical self-supervised learning. The method comprises the following steps: acquiring original noisy distributed temperature sensing (DTS) logging data, and generating a self-supervised training sample through a space-time alternating downsampling strategy by using the space-time coherence of the original noisy distributed temperature sensing (DTS) logging data; constructing a physical self-supervised blind denoising network model by using a simplified structure, and inputting a self-supervised training sample for training; in the training process, a multi-physical constraint loss function optimization model is introduced until a loss function converges, and a denoising model is obtained; and inputting to-be-processed complete DTS logging data into the denoising model to obtain denoised DTS logging data. According to the method, manual labeling and large-scale labeling of the data set are not needed, the inherent physical characteristics and structural information of the DTS data can be fully utilized, efficient and accurate blind denoising of the DTS logging data is achieved, and the problem that an existing deep learning denoising method needs to depend on a large amount of labeled data is solved.

The invention provides a model fine tuning method and system based on feedback and reinforcement, and relates to the technical field of natural language processing, and the method comprises the steps: obtaining an output text generated by a language model, and carrying out the embedded coding; identifying a structural semantic unit in the text, and generating structural mark information; constructing a low-layer capsule set based on the structure marking information, and executing dynamic routing to generate a high-layer semantic capsule set; constructing a structure expression matrix according to the mapping relation between the high-level semantic capsule set and the structure mark; and inputting the matrix into a reward scoring model to generate a reinforcement learning return value, and updating language model parameters according to the reinforcement learning return value. According to the method, closed-loop linkage of the language model structure perception capability and the strategy optimization path is realized, and the text generation structure and semantic consistency can be improved under the condition that manual annotation is not needed.

The invention provides a non-autoregressive end-to-end dialect recognition method for a power supply service telephone system. The method comprises the following steps of dual-track telephone recording corpus preprocessing, automatic pre-labeling and context construction, manual labeling and dialect word library construction, dialect sub-area division and classification modeling, and dialect recognition model training and optimization. Based on the ffmpeg audio processing tool, the standardization and automation level of voice data processing in a telephone system scene is improved, and the manual annotation efficiency is greatly improved. And meanwhile, aiming at the problems that dialects are various in type, significant in difference and the like, a unified dialect labeling rule system is constructed, a model training process is optimized in combination with a transfer learning strategy, and the robustness and generalization ability of the model in a complex telephone voice environment are enhanced while high accuracy is ensured.

The invention provides a clinical data intelligent labeling and quality control method and system, and relates to the technical field of data processing, and the method comprises the steps: constructing a medical knowledge graph, carrying out the vectorization expression of nodes, extracting the context correlation features of a clinical text through a multi-head attention mechanism, and calculating the semantic similarity to form a hierarchical semantic link network; knowledge reasoning is carried out based on reinforcement learning to obtain an implicit association path, and the implicit association path is converted into a labeling rule and optimized. According to the method, efficient and intelligent labeling of the clinical data is realized, the labeling accuracy and consistency are improved, and the manual labeling cost is reduced.

The invention discloses an abnormal data monitoring method and device based on artificial intelligence, and the method comprises the steps: 1, dividing an original data stream through a sliding window, extracting statistics, time sequence and change rate features, and dynamically screening features adaptive to data distribution based on an SHAP value; 2, constructing a double-flow model, capturing a global isolated mode by adopting an improved isolated forest in a static flow, capturing time sequence dependence on the basis of LSTM-AE in a dynamic flow, and fusing two-flow scores through performance-driven dynamic weight distribution; 3, combining a density peak value algorithm with historical density attenuation weighting, and dynamically adjusting an abnormal threshold value; 4, realizing low-delay incremental learning through a double-trigger mechanism and experience playback; 5, multi-granularity interpretation is generated, manual annotation feedback is supported, feature engineering and model training are integrated, and a'detection-interpretation-feedback-optimization 'closed loop is formed; high-adaptability anomaly monitoring is realized through dynamic feature screening, double-flow fusion detection, threshold value self-adaption and man-machine collaborative optimization.

The invention belongs to the technical field of artificial intelligence, and particularly relates to an artificial intelligence data annotation and cue word automatic construction engine system, which comprises a data annotation module for firstly carrying out preliminary annotation on data based on a pre-training model, then automatically annotating a data sample through an active learning algorithm, and meanwhile, monitoring the quality of annotated data in real time; and the cue word automatic construction module generates cue words based on task analysis, optimizes the cue words by using a reinforcement learning technology, and performs classified storage and management on the generated cue words. By adopting the semi-automatic labeling and active learning labeling functions, not only can the workload be greatly reduced, but also the unnecessary labeling work can be reduced, so that the labeling efficiency is remarkably improved, the labeling time is shortened, the large-scale data labeling requirement is met, and the problem of efficiency bottleneck caused by slow manual labeling is solved.

The invention discloses a coevolution driver cognitive load personalized quantification method, which relates to the technical field of traffic safety, and comprises the following steps: collecting a multi-modal physiological signal and processing the multi-modal physiological signal into structured feature data; constructing a labeled sample set D1 and an unlabeled sample set Du based on the structured feature data to perform semi-supervised collaborative pseudo labeling training, generating pseudo labels for unlabeled samples, and forming a self-labeled data set S; and constructing a training set and an enhanced training set by using S and D1, carrying out supervised contrast learning feature extraction, and carrying out model tuning in combination with an MAML algorithm. And finally, inputting any sample into the optimized model to generate continuous cognitive load value prediction. Wherein only a small amount of manual labeling is needed, the label quality can be improved, and the personalized quantification efficiency of the cognitive load can be improved; multi-modal information is fused, so that the robustness and the accuracy are improved; a continuous and fine-grained quantification mode is provided, and the accurate automatic driving decision-making requirement is met.

The invention discloses an Alzheimer's disease early warning method based on white matter lesion omics characteristics, and relates to the field of wisdom medicines.The method comprises the steps that magnetic resonance imaging data of a historical subject in the period from the mild cognitive impairment period to the period before diagnosis of Alzheimer's disease are obtained, and manual labeling of white matter and white matter lesion areas is carried out; a manual annotation data set is obtained; training a deep learning model for white matter lesion recognition based on the manual annotation data set; inputting to-be-identified magnetic resonance imaging data into the deep learning model, and extracting lesion features of the white matter; performing standardization and feature alignment on the extracted lesion features, and inputting the lesion features into a deep clustering model to form clustering results for different white matter lesion feature types; and an early risk assessment model is constructed based on the clustering result and the Alzheimer's disease transformation risk tag corresponding to the clustering result, and the Alzheimer's disease transformation risk level of the subject is output, so that the problems that multiple lesion features are difficult to quantify and details are difficult to identify are solved.

The invention relates to the technical field of code development, and provides an AI code effective proportion statistical method and device, a medium and equipment. The method comprises the steps of obtaining related information of codes submitted by a user; according to a user name in the related information, searching log information of an AI code generated by a corresponding user through adoption of a code generation tool; under the condition that the file name of the code submitted by the user is matched with the file name in the log information, searching a corresponding submitted code segment from the code submitted by the user according to the mark information in the log information; and calculating the similarity between the AI code and the submitted code segment, and counting the effective proportion corresponding to the AI code according to the similarity. Therefore, the calculation of the effective proportion considers the quality of the AI code, so that the effective proportion can accurately reflect the real contribution of the AI code, and the calculation process is automatically realized, thereby avoiding the tedious, time-consuming and labor-consuming conditions of manual labeling.

The invention provides a multi-modal fusion road topology reasoning method and system, and the method comprises the steps: converting an extracted lane mask into a semantic seed point in a historical point cloud, and carrying out the pseudo-label setting based on the semantic seed point. And performing model training based on the historical image with the pseudo tag and the historical point cloud to obtain a lane detection model. Obtaining lane line information from the real-time image and the real-time point cloud by using a lane detection model, mapping the lane line information to a bird's-eye view feature map, calculating a topological relation between lane lines based on the lane line information in the bird's-eye view feature map, obtaining a topological reasoning matrix, and obtaining a topological reasoning result; and obtaining a corresponding road topology reasoning result based on the graph neural network according to the topology reasoning matrix. According to the scheme, on the basis of a pseudo label generation mechanism, dependence on manual marking is reduced, data preparation cost is reduced, effective fusion of a lane line representation method based on bird's-eye view space unified mapping and lane topology reasoning is introduced, and a lane topology reasoning result with high precision and good topology consistency can be obtained.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a target data sample set construction and screening method, device, equipment and medium, and the method comprises the steps: obtaining a target type description, carrying out semantic extension to generate an extension description, generating a reference image sample based on an image generation model, real data units are screened through feature extraction and similarity comparison, and a target data sample set is constructed in combination with knowledge base verification. According to the method, by introducing semantic extension, reference image generation, cross-domain feature comparison and knowledge base consistency verification, real samples highly fitting target type semantics are automatically screened from massive original data, so that the manual annotation dependence is reduced, the illegal sample construction efficiency is improved, and the manual annotation time is shortened. And the training quality and the expansion capability of a subsequent detection model are enhanced.

One or more embodiments of the invention provide a multi-modal large model training method, apparatus and device, and a storage medium, and the multi-modal large model comprises a visual coding layer used for generating image features corresponding to an image, and a large language model used for generating a reply text based on the image features and a query text; the method comprises the following steps: aiming at aligning an image feature space of a visual coding layer and a text representation space of a large language model, adjusting a multi-modal large model to obtain an aligned multi-modal large model; based on pre-training samples which are constructed in a data synthesis mode and correspond to various tasks in the at least one task in the medical scene, pre-training the aligned multi-modal large model to obtain a pre-trained multi-modal large model; and performing fine tuning on the pre-trained multi-modal large model based on a fine tuning sample which is obtained through a manual labeling mode and corresponds to the target task in the medical scene to obtain the multi-modal large model used for executing the target task.

The invention discloses a semi-supervised text data multi-label classification method, system and device and a storage medium. According to the method, a double-branch model of a shared feature processing network is constructed, a pseudo label generator is utilized to automatically generate a pseudo label for an unlabeled sample on the basis of limited labeled data, and the pseudo label generator and a classifier are jointly trained to realize collaborative learning of labeled data and unlabeled data; by introducing an adaptive threshold mechanism and an improved loss function design, the recognition precision of minority class labels is effectively improved. Compared with a traditional full supervision model, the method has the advantages that the dependence on large-scale manual annotation is reduced, the data preparation cost is remarkably reduced, and the application performance of the classification model in multi-label scenes such as medical text analysis, public opinion monitoring and personalized recommendation is improved. The system, the device and the storage medium provided by the invention can realize the method, and have good expandability and engineering application value.

The invention relates to the technical field of database development, in particular to an SQL generation method and device based on a large model and an ER graph. The method comprises the following steps: analyzing a user query statement to obtain a database candidate table set; querying table field information of each table related to the user query statement from a database candidate table set; according to the table field information of each table, querying an association relationship among the tables in the database candidate table set from a preset ER map, and determining intermediate table information, the intermediate table being used for associating candidate tables without direct association; and generating an SQL query statement according to the intermediate table information and the database candidate table set. Through combination of candidate set generation and SQL optimization, logic errors of the generative large model are reduced, and execution efficiency is improved. The method does not depend on manual annotation of training data of a query language and an SQL template, the labor cost is greatly reduced, and good mobility is achieved.

The invention discloses a patent evaluation method based on a feature-efficacy matrix and a large language model, which performs feature-efficacy matrix analysis and construction on a patent text set to be processed by using text generalization and downstream task potential of the large language model, and does not need to adopt manual annotation, thereby reducing the cost. Wherein at least one feature-efficacy matrix and a patent summary contained in a patent text to be processed are obtained in the analysis and construction step of the large language model. According to the method, a vector and efficacy interval mixed retrieval mode is constructed based on the feature-efficacy matrix, and complex query requirements of patents are accurately matched. Meanwhile, a multi-dimensional patent quality evaluation mode based on a feature-efficacy matrix is a comprehensive evaluation mode from the dimensions of novelty, efficacy, popularity and the like and is applied to patent retrieval, and the analysis effect of related patents is further improved.

This invention relates to a system and method for non-invasive detection of gravesites and archaeological features using multimodal remote sensing and machine learning. Remotely sensed datasets, including RGB, multispectral, hyperspectral, LiDAR, and thermal imagery, are orthorectified, mosaicked, and subdivided into tiled image segments. Features are labeled through manual annotation of visible markers and environmental signatures and expanded via iterative augmentation. A supervised pipeline trains computer vision models, such as YOLO-based detectors, in parallel with tabular models derived from spectral indices (NDVI, NDRE), LiDAR elevation derivatives, and thermal anomalies. Inference outputs are cross-validated against thresholded evidence layers to reject false positives and upgraded when spectral, spatial, and thermal evidence align. Validated detections are exported as GIS-compatible layers with confidence scores and metadata. The system provides a scalable, replicable tool supporting archaeologists, Indigenous communities, and planners in cemetery investigations, cultural resource management, and humanitarian searches for unmarked or clandestine graves.

The invention discloses an encrypted traffic adaptive update classification method and system oriented to an open network environment. The method comprises the following steps: firstly, extracting endogenous semantic features and exogenous environment features based on a causal decoupling mechanism, and stripping an environment confusion factor through anti-fact disturbance and invariance constraint to obtain invariant semantic representation; constructing a macroscopic drift state vector representing a network situation, and inputting a trained meta-learning super-network intelligent decision adaptive control hyper-parameter; performing cross-modal element calibration by utilizing large language model thinking chain reasoning, and calculating the subspace direction consistency of an instantaneous gradient vector of a candidate sample and a category optimization trajectory prototype so as to screen credible samples; and in combination with the capacity-limited playback queue, gradient orthogonal projection constraints are introduced to update low-rank adaptation layer parameters. According to the method, the concept drift problem is solved through causal decoupling and meta-learning decision, forgetting prevention is achieved through orthogonal projection updating, and the online adaptability and robustness of the model in the open environment can be improved without additional manual annotation.

The embodiment of the invention provides a remote sensing target segmentation method, electronic equipment, a storage medium and a program product. The method comprises the following steps: acquiring a to-be-segmented remote sensing image and a sample library; calculating the feature similarity between the to-be-segmented target semantic tag and each sample, and screening out a target sample of which the feature similarity meets a preset requirement from the sample library; generating a target reference mask based on the target sample; and converting the target reference mask into a visual prompt, and inputting the visual prompt and the to-be-segmented target semantic tag into a segmentation model to obtain a segmentation result. Through combination of sample library assistance and visual prompt guidance, accurate segmentation of a specific target in a remote sensing image is realized, and dependence on dense manual annotation is eliminated. Meanwhile, the generalization ability of the model to the same kind of targets in different scenes is enhanced through double constraints of semantic tags and visual features.

The invention discloses a method for automatically constructing a pathological image data set and training cell nucleus detection and classification based on a space transcriptome technology, and belongs to the field of image processing and artificial intelligence auxiliary pathological diagnosis. According to the method, a spatial transcriptome public data set is obtained, and a data set containing image blocks, weak supervision / semi-supervision labels and cell nucleus boundary information is automatically constructed through preprocessing, deconvolution cell type annotation and cell nucleus instance segmentation, so that the dependence on manual annotation is reduced. Furthermore, a detection and classification model is designed, a multi-scale deformable attention encoder and a decoupled detection and classification decoder are adopted, a limited deformable cross attention mechanism is introduced into the classification decoder, KL divergence classification loss is combined, and instance-level cell nucleus categories are learned from region-level proportion labels. According to the method, end-to-end automation is realized, the cell nucleus detection and classification precision and efficiency are improved, and a high-quality pre-training model basis is provided for downstream pathological analysis.

The invention discloses a capsule network sentiment analysis method for teaching evaluation. Firstly, teaching evaluation texts are collected, aspect items are extracted through data preprocessing, an aspect category-emotion two-tuple is generated through manual annotation, and a teaching evaluation data set is constructed. Secondly, splicing each evaluation text and all aspect categories, and inputting the spliced evaluation text and all aspect categories into a pre-training language model for encoding to obtain high-dimensional context vector representation; thirdly, text features highly related to a specific aspect are extracted through a cross attention mechanism, and modeling and classification of category sentiment polarity of all aspects are achieved through a capsule network and a dynamic routing mechanism; and finally, judging the existence of aspect categories and the sentiment polarity of the aspect categories through a multi-task classifier, and outputting a plurality of aspect-sentiment two-tuples contained in the sentences. The sentiment analysis accuracy and interpretability in a multi-aspect and multi-sentiment polarity coexistence scene in a teaching evaluation text are effectively improved, and the method is suitable for intelligent analysis of large-scale education evaluation data.

The invention discloses a semi-supervised image annotation method based on a limited label data set, and the method comprises the steps: taking a FixMatch frame as a basis, and integrating a learnable batch normalization module, a dual-scale parallel convolution module, a content and style separation dual-branch module and a dynamic residual gating module in a ResNet backbone network, the stability of feature extraction and the adaptive capacity to enhanced disturbance are improved. For a label-free sample, a multi-level pseudo-label fusion mechanism is provided, prediction distribution of weak, medium and strong enhanced views is synthesized, and high-confidence pseudo-labels are generated through confidence weighted fusion of multi-level enhanced views and comparison and screening with a category threshold. On the basis, a joint loss function composed of label supervision loss and pseudo label consistency loss is constructed, and a plurality of key control parameters in FixMatch + + are adjusted and optimized in a pre-experiment and grid search combined mode to obtain a group of optimal parameters of the model. Finally, a user inputs a label-free image into the trained FixMatch + + model, and the model can automatically generate a high-confidence pseudo label, so that the number of labeled samples in a limited labeled image set is increased, and the classification precision is improved. By implementing the method, the manual annotation cost can be reduced, and efficient and reliable support is provided for image analysis and recognition tasks.

The embodiment of the invention provides a model training method and device, electronic equipment and a storage medium, and relates to the technical field of deep learning, and the method comprises the steps: carrying out the word segmentation of a theme document, and obtaining a word segmentation list; a sliding window for the word segmentation list is obtained, word frequency statistics is conducted on the word segmentation list according to the sliding window, and a global word frequency list corresponding to the word segmentation list is obtained; performing feature statistics on the global word frequency table to obtain corresponding sparse features; performing feature fusion on the sparse features according to the global word frequency table to obtain a dense matrix; obtaining a domain dictionary corresponding to the subject document, and performing weighting processing on the dense matrix according to the domain dictionary to obtain a corresponding mixed feature matrix; and training the initial classifier to be trained according to the mixed feature matrix to obtain a trained target classifier, thereby effectively reducing dependence on manual annotation, forming an end-to-end cold start solution, reducing noise interference in a model training process, and shortening a training period.

The invention discloses a scene intelligent extraction method based on L4-level automatic driving minibus road test data, and the method comprises the steps: collecting environment data and vehicle dynamic data, and carrying out the preprocessing, and obtaining time series data; constructing a DSFEM network, inputting time sequence data for training, and constructing a self-supervised loss function to update parameters of the DSFEM network to obtain time sequence features; clustering the time sequence features through a K-means clustering algorithm to obtain clustered scene features; constructing a manual annotation scene library, and calculating the similarity between the scene features to be stored and the behavior features of the existing scenes in the manual annotation scene library; an existing scene with the highest similarity is matched for the scene features, and manual annotation information corresponding to the existing scene is mapped into the scene features, so that scene automatic extraction and manual annotation scene library updating are realized; according to the method, the efficiency is remarkably improved in the aspect of scene generation, the reasonability and the coverage range of a scene library are ensured, and reliable support is provided for testing and evaluation of an automatic driving minibus.