306results about How to "Reduce labeling costs" patented technology

The invention discloses an image self-supervised learning method and system fusing contrast learning and feature mask modeling. An original image which is low in cost and does not need to be labeled is used as training data, a double-branch self-supervised learning network is constructed, one branch is a comparison learning branch based on a SimCLR framework, the other branch is a mask self-encoder branch based on a mask feature model, and the whole network comprises an image preprocessing module, an image feature extraction module and a shared weight encoder. And carrying out self-supervised training by combining the two branches with a loss function specially designed for the two branches, and finally obtaining a pre-training model capable of fully extracting image features. According to the method, the advantages of comparative learning and feature mask modeling are combined, information is effectively extracted from unlabeled image data, and image understanding is enhanced. The method has the main advantages that the robustness is high, the method is particularly suitable for limited data sets in the remote sensing and medical fields, the model precision is improved, and the data requirement and labeling cost are reduced.

The invention discloses a domain-adaptive retrieval enhancement generation method and system, and the method comprises the steps: carrying out the document analysis and semantic partitioning of a document through a semantic understanding model and a document rule, and storing document fragments; on the basis of the large language model and a preset question library, generating a question and disassembling the question; performing correlation evaluation and sorting on the initial retrieval results in combination with a retrieval technology; candidate content most matched with the cue words is screened out through a large language model, and question-retrieval fragments are scored and marked; performing fusion on the initial retrieval result and the scoring and labeling result to construct positive and negative samples, and constructing a supervised data set; and based on a preset loss function, utilizing the supervised data set to carry out supervised training on the knowledge semantic search model, replacing the RAG mixed search module, and carrying out continuous iteration. By means of the technical scheme, new domain knowledge and operation feedback data can be flexibly applied, and domain self-adaptive retrieval enhancement generation is achieved.

The invention provides a multi-mode intelligent robot control method and device, and the method comprises the steps: obtaining a current mode instruction which at least comprises one of a video instruction, a text instruction, a picture instruction and an audio instruction; on the basis of a pre-trained multi-modal large model, according to the current modal instruction, obtaining post-collapse characterization; on the basis of a pre-trained robot imitation learning network, according to the representation after collapse and current environment observation, predicting an output target action; the multi-mode intelligent robot with the body is controlled to operate according to the target action; wherein the robot imitation learning network is obtained by performing training optimization according to a training sample set formed by single-modal data samples, corresponding environment observation data and real actions of the robot. According to the method, the post-collapse representation is obtained by pre-training the multi-modal large model, and the post-collapse representation is utilized to predict the target action, so that the requirement on multi-modal manual annotation data when a training robot simulates a learning network is avoided in the process, the effect of multi-modal reasoning can be achieved only according to single-modal data training, and the efficiency of multi-modal reasoning is improved. Not only is data collection and labeling cost reduced, but also the reasoning ability of the model is improved.

The invention relates to the technical field of data annotation, and particularly discloses an intelligent annotation method and system for large model data, and the method comprises the steps: carrying out the confidence evaluation of each piece of unannotated text data in an unannotated text data set through employing a natural language processing technology based on deep learning; according to the method, text data corresponding to the minimum confidence coefficient is selected as representative sample data, corpus expansion is performed on the representative sample data, and then semantic feature extraction and compensation type interactive fusion are performed on the representative sample data and the representative sample data after corpus expansion, so that common information and unique information between the representative sample data and the representative sample data after corpus expansion are fully utilized; therefore, comprehensive semantic understanding and intelligent labeling of the representative sample data are realized. In this way, the efficiency and accuracy of data annotation can be remarkably improved, meanwhile, the requirement for manual intervention is greatly reduced, and the annotation cost is reduced.

The invention belongs to the technical field of data processing, and discloses an enterprise multi-type data labeling method and system based on feature engineering, and the method comprises the steps: collecting initial data of an enterprise internal information system, and dividing the initial data to obtain a text data set, a table data set and an image data set; feature vectors of different types of data are fused after features are extracted and screened, and a multi-dimensional feature space is constructed; constructing an annotation model according to the feature information of the feature space, constructing similar sample pairs as positive sample pairs and irrelevant sample pairs as negative sample pairs for unannotated new data, and comparing, learning and optimizing the similarity between the similar sample pairs; and carrying out label inference based on the feature vectors obtained by comparative learning, and generating a labeling result. According to the method, efficient and automatic labeling of various types of data can be achieved, the method is suitable for various heterogeneous data such as texts, tables and images, and high labeling precision and expansibility are achieved.

The invention discloses a low-cost cell segmentation method, system and device based on active learning. The method comprises the following steps: selecting an initial cell image for preprocessing and bounding box labeling; forming a training set and constructing a target detection model for training so as to predict a bounding box of pictures of the verification set; taking the bounding box as a prompt for segmenting a cut model (SAM), and outputting a corresponding cell mask; adopting a Monte Carlo discarding method to predict the uncertainty of the unlabeled pictures, and selecting the pictures with higher uncertainty to be labeled by experts; adding the marked image data into the training set of the last round for updating, and repeating the training and sample selection of the model; and outputting a model weight and an index record after the required performance is achieved. According to the method, the data annotation cost of a cell segmentation algorithm is greatly reduced on the premise of ensuring the model performance.

The invention discloses a multi-modal federation active learning-based network anomaly detection method, which comprises the following steps of: fusing data of a plurality of modals through multi-modal feature aggregation to generate uniform feature representation; an active learning mechanism is introduced into the federated learning framework, and distributed nodes are allowed to autonomously select learning strategies according to characteristics and distribution conditions of own data; the node isomerism in the distributed environment is dealt with through an adaptive learning optimization strategy; the communication efficiency is optimized and the global synchronization frequency is reduced through a progressive federated synchronization mechanism; according to the method, multi-modal data fusion and federated active learning are combined, so that the precision and efficiency of network anomaly detection are improved on the premise of protecting data privacy.

The invention discloses a self-adaptive resource optimization and model generalization method in an end-side cloud collaborative intelligent system, and the method comprises the following steps: end equipment collects corresponding environment data and equipment operation parameters, and carries out the training of a preset local model based on the collected data; the method comprises the following steps: constructing a digital twinborn model, calculating a statistical distance between a real-time data stream monitored in real time and a preset data distribution model based on the real-time data stream monitored in real time by the digital twinborn model, and if the statistical distance is greater than a preset value, starting an active sample selection mechanism to optimize and update a local model. The optimized and updated local model is sent to the edge node; a local model sent by the end equipment and the edge node is compressed by adopting a bidirectional knowledge distillation mechanism, a lightweight model is obtained, and global optimization and fusion are carried out through a cloud server. According to the method, resource allocation can be optimized, and the model generalization ability is improved, so that the data processing efficiency of the system, the fairness of resource allocation and the accuracy of intelligent decision making are improved.

The invention provides an automatic driving obstacle recognition method and system based on deep learning, and relates to the technical field of automatic driving, and the method comprises the steps: collecting sample image data and sample point cloud data; performing feature extraction on the marked point cloud and the marked image by using a 3DCNN network, and performing training according to an extraction result to obtain a classifier and a prediction head; enhancing the unmarked image and the unmarked point cloud; performing feature extraction on the enhanced image and the enhanced point cloud to obtain a multi-scale image feature and a multi-scale point cloud feature; dynamically adjusting the weights of the multi-scale image features and the multi-scale point cloud features based on a feature fusion method of an attention mechanism to obtain fusion features; and inputting the fused features into the trained classifier and the prediction head to obtain an obstacle recognition result. According to the method, the accuracy, robustness and generalization ability of obstacle recognition are remarkably improved, the marking cost is reduced, and the high requirements of an automatic driving scene for real-time performance and reliability are met.

The invention discloses an encrypted traffic detection method based on LLM enhanced semi-supervised learning. The method comprises the following steps: firstly, training a traffic detection model for detecting encrypted traffic under an LESS framework; and detecting the encrypted traffic by using the trained traffic detection model. Components of the LESS framework include a Prompt orchestrator, an NSSN, and an LLM optimizer. The components work cooperatively, a detection model is trained by using a labeled training set and a label-free training set, and each piece of data in a data set is formed by arranging length values of data packets in a network flow in sequence; the Prompt composer guides the LLM to generate label-free enhanced data in different scenes; the NSSN automatically sets a pseudo label for the enhanced label-free traffic data, and learns traffic detection knowledge accordingly; under the guidance of the SSL loss, the LLM optimizer adjusts the enhancement strategy of the LLM to align the semi-supervised training requirements of the detection model. The training steps of the detection model include LLM pre-fine tuning; marking the LLM enhanced data; and continuous demand alignment can be realized.

The invention relates to a maritime activity knowledge extraction method and device based on a large language model. The maritime activity knowledge extraction method and device are used for maritime knowledge extraction. The method comprises the steps that an initial cue word is preset, a cue word optimization strategy is set to optimize the initial cue word, the optimized cue word is used for guiding a large language model to conduct statement transcription on reconstructed data, and a preliminary extraction result is obtained; labeling the preliminary extraction result according to a preset extraction error label system, taking a labeled text as a similar error text, carrying out statement structure analysis on the similar error text, generating a simulation text question and answer pair, carrying out feedback modification on the optimized prompt word, and obtaining a simulation result; and utilizing the modified cue word to guide a large language model to perform knowledge extraction on the marine activity data to obtain marine knowledge. By adopting the method, offshore knowledge extraction can be realized.

The invention discloses an intelligent diagnosis method for large model knowledge annotation, and the method comprises the steps: carrying out the knowledge injection of a large model, and obtaining the formatted semantic knowledge of each fault type; constructing a self-supervised pre-training network by using all fault data to train an encoder to extract class-independent features; constructing and training a health feature comparison and semantic knowledge prediction network; using the trained encoder and the health feature comparison and semantic knowledge prediction network to obtain semantic knowledge of a fault sample without category, adjusting the predicted semantic knowledge based on a double-view dynamic semantic knowledge learning strategy, dividing test data into a high-probability sample and a low-probability sample, the semantic knowledge of the low-probability samples is adjusted by using the spatial distribution of the high-probability samples, and the fault is diagnosed cooperatively. According to the method, semantic knowledge labeling can be carried out by using professional documents under the condition that fault data is limited, spatial distribution of semantic knowledge is adjusted, and the accuracy and credibility of fault diagnosis are improved.

The invention relates to an insect pest semi-supervised target detection method combining active learning and multi-scale view learning. The method comprises the following steps: constructing a semi-supervised target detection data set; performing data enhancement on the semi-supervised target detection data set; constructing a semi-supervised model and generating a pseudo label; performing multi-scale view learning through the student model to obtain a multi-scale view prediction result; performing semi-supervised training; performing active learning, and updating the semi-supervised target detection data set; and inputting a to-be-detected field corn image into the finally trained teacher model to obtain a final pest detection result. According to the method, active learning is combined to select some data which is beneficial to the model and can effectively improve the performance for labeling, and the labeling cost is utilized to the maximum extent; adding a multi-scale view learning structure, and capturing effective information; and finally, under the condition of limited 20% annotation data, the detection precision of more than 80% annotation data can be realized, and the annotation cost is greatly saved.

The invention discloses a hole making process parameter recommendation method based on a knowledge graph, which uses an optimized seven-step method, and provides an ontology evaluation system and an ontology updating method, so that a hole making process ontology can be updated and iterated according to different processing requirements; according to the method, the fine-tuning UIE model is adopted to perform knowledge extraction on the hole-making process text data, good extraction accuracy can be obtained only by performing fine-tuning on the UIE model by using small sample data, the marking cost of knowledge extraction of the hole-making process text data is reduced, and the extraction efficiency is improved; according to the method, an entity alignment algorithm and a processing case filtering algorithm based on text similarity and word list mapping are designed, so that the repetition rate of knowledge in the knowledge graph is reduced, and the retrieval efficiency is improved.

The invention relates to a fault detection method based on a multi-modal attention mechanism. The method comprises the following steps: performing data fusion on multiple data sources in an IT system; wherein the multiple data sources comprise log data, monitoring data and user behavior data; inputting the fused data into a fault detection model to obtain a fault detection result; wherein the fault detection model is constructed based on a GRU neural network and a multi-head attention mechanism. According to the invention, by introducing the large language model, the GRU neural network, the multi-head attention mechanism and the multi-modal data fusion technology, the accuracy and reliability of system fault detection can be effectively improved.

The invention belongs to the technical field of natural language processing, and discloses a text data labeling method and system based on weak supervised learning. The method comprises the following steps: performing pseudo label generation on a plurality of historical text data by using a weak supervised learning algorithm to obtain a plurality of source domain data provided with real labels and a plurality of target domain data provided with pseudo labels; constructing a text data labeling model by using a deep learning and adversarial training algorithm, and adjusting the text data labeling model by using a continuous learning algorithm; and labeling the real-time text data by using the adjusted text data labeling model to obtain labeled real-time text data, and updating the adjusted text data labeling model by using a continuous learning algorithm. The problems that in the prior art, manual labeling cost is high, labeling quality is uneven, and dependence on label data is high are solved.

The invention discloses a facial action unit identification method based on CLIP and multi-mode mask prompt learning. The method comprises the following steps: 1, carrying out facial action unit identification on the basis of the CLIP and the multi-mode mask prompt learning; the method comprises the steps that 1, a multi-modal shared AU prompt (AU-prompt) and an attention mask are designed based on an AU prior position, the AU-prompt comprises a plurality of learnable tokens, the attention mask is designed according to prior positions of different AU facial muscle changes, and a specific AU attention mask is obtained; 2, in a multi-mode prompt learning process, introducing an attention mask of a specific AU into different layers of a CLIP model text and an image encoder for prompt learning, and learning local detail features of the AU and global association features among different AUs to obtain local features and global features; and step 3, fusing the local features and the global features, calculating loss with the text features, and finally realizing AU identification. According to the method, the facial action unit can be effectively recognized under the condition that the labeled data is limited.

The invention provides an end-to-end automatic driving system and method. The system comprises an environment sensing module, a feature extraction module, a data fusion module, a decision generation model module and a decision analysis module. The environment sensing module comprises a plurality of types of sensors, and each sensor collects environment information data of different modes. The feature extraction module extracts features of each modal environment information data. And the data fusion module fuses the features of the modal environment information data to obtain fused features. The decision generation model module determines a driving decision by using a trained decision generation model based on the fusion features. And the decision analysis module converts the driving decision output by the decision generation model module into a specific vehicle control instruction. The method has higher adaptability to complex and dynamic driving scenes, reduces the cost of data annotation during training, and improves the generalization ability of the model in various driving scenes.

The invention discloses a 3D target detection method and system based on binocular vision and open vocabularies, and relates to the technical field of target detection. The method comprises the following steps: calculating pixel features of each image by adopting an open vocabulary 2D detection model; pixel features of the left view and the right view are aggregated to each three-dimensional point; obtaining a parallax estimation map based on the pixel features of the left and right views; introducing a time aggregation guide parallax consistency constraint to obtain a depth parallax estimation map; converting the depth parallax estimation map into a 3D point cloud, and extracting features to obtain 3D features; and carrying out correlation integration on the text features, the 2D fusion feature vectors and the 3D features by utilizing object-level image guide detection loss, object-level cross comparison alignment and object-level self-comparison learning to obtain a three-dimensional target detection model, realizing three-dimensional target detection and distinguishing different target objects. According to the invention, accurate detection and distinguishing of the target can be realized, so that the flexibility and universality of 3D target identification are improved.

The invention belongs to the technical field of unit fault diagnosis, and discloses a fault diagnosis method and system for a fault large-scale unit based on sharing and specific representation learning. The method not only can be applied to multi-measuring-point fault diagnosis of a large-scale unit, but also has wide applicability. In other multi-sensor systems or complex equipment, the fault detection effect can also be improved through multi-view representation learning. The invention provides a weighted sharing-specific multi-view depth representation learning fault diagnosis method for fault diagnosis of multi-measuring-point data of a large-scale unit. The method consists of two parts, namely sharing and specifically representing a learning network and weighted multiple similarity loss and orthogonal loss. A multi-measuring-point data fault diagnosis problem of a large-scale unit is solved by sharing a specific representation learning network, and weighted multiple similarity loss and orthogonal loss are used to further improve the feature extraction capability of the network and reduce redundancy.

The invention provides a video saliency target detection method based on image annotation. The method comprises the following steps: S1, establishing a training set and a test set; s2, constructing a progressive saliency target detection network; s3, training the progressive saliency target detection network by using the training set, and identifying video frames in the test set by using the coarse positioning network to generate a first space-time positioning tag; s4, acquiring adjacent frames of the video frame, and identifying the adjacent frames based on an adjacent frame difference method to generate a second space-time positioning tag; step S5, inputting the first space-time positioning tag and the second space-time positioning tag into a double-flow positioning network for positioning the video salient object; and S6, the attention sampler and the fine segmentation network are used to identify and segment the images corresponding to the video frames in sequence to obtain corresponding salient object positioning maps. The method has the beneficial effects that the marking cost of the video saliency target detection data set can be reduced, and adaptation to rich scenes is realized.

The invention discloses an automatic driving algorithm training data generation system based on a diffusion model. In the invention, a driving environment-oriented controllable data sample generation scheme is provided, the scheme takes a diffusion model as a reference methodology, brand new data is generated and training samples of related perception tasks are expanded based on collected data samples and prior labels, so that the problems of uneven quality of existing training data samples, less difficult data and the like are solved; by generating the cue word, the sample acquisition cost and acquisition difficulty of the difficult case are reduced, the generalization effect of the model in the actual business is improved, and the algorithm is pushed to serve more businesses. Meanwhile, by combining the input of various forms of control conditions, the controllability of the data generation process is improved, and the generation result better conforms to the expectation. And finally, screening out generation results which do not meet requirements through a verification mechanism, and ensuring the generation quality.

The invention provides a phytoplankton chromatography sequence identification method and a phytoplankton chromatography sequence model building method, and belongs to the technical field of image enhancement identification. The method comprises the following steps: firstly, acquiring microscopic chromatography sequence data of phytoplankton, performing view field extraction and serialization recombination, and constructing a three-dimensional data set; then, constructing a three-dimensional recognition model containing physical perception and a sequence aggregation mechanism, extracting single-frame semantic features by the model by adopting a parameter-shared twin network, and introducing a physical definition prior module to calculate a space-frequency domain quality score of a slice; secondly, designing a deep perception sequence aggregation module, and adaptively aggregating key features of a high signal-to-noise ratio by taking definition scores as gating signals and combining spatial context information between slices; and finally, training and optimizing the model based on the image-level weak supervision label to obtain an optimal model. According to the method, the problems of information truncation and out-of-focus noise interference caused by extremely shallow depth of field of high-power microscopic imaging are solved, and full-depth-of-field stereoscopic perception can be realized under the condition that frame-by-frame fine labeling is not needed.

The invention relates to the technical field of image classification, in particular to an image classification method and system based on potential domains and category diversity. The method comprises the following steps: acquiring image data, including acquiring image data of a source domain and a target domain; preprocessing the image data of the source domain and the target domain; constructing a domain adaptive image classification model; performing model training on the constructed domain adaptive image classification model; and carrying out image classification by using the trained domain adaptive image classification model. According to the method, the distribution difference of the source domain and the target domain is gradually aligned by generating the potential domain, and the source domain, the potential domain and the target domain are consistent in feature distribution by adopting a class-level and domain-level multi-level alignment strategy, so that the precision of the model in a cross-domain classification task is remarkably improved.

The invention discloses a multi-modal data enhancement method and system based on an AI training platform, and belongs to the technical field of multi-modal data processing.The method comprises the steps that firstly, a multi-modal data fusion pipeline is developed on the AI training platform, and data of different modals are collected through a data collection module for preprocessing; in the preprocessing stage, a multi-modal data fusion pipeline is used for carrying out feature extraction on data from different modals, and joint modeling is carried out at a specific level; then, automatically generating high-quality synthetic data by adopting a data enhancement pipeline; and finally, developing a multi-modal deep learning pipeline to fully learn and understand deep features of different modal data. According to the method, the problem of model learning bias caused by single-modal data in the prior art is solved, the generalization ability and the data processing efficiency of the model are improved, meanwhile, the processing difficulty of a multi-modal data task is simplified for an AI training platform user, and the method has important application value.

The present invention belongs to the field of computer vision and machine learning, and discloses a method for counting live pigs based on instance segmentation. It makes up for the shortcomings of the existing algorithms, such as high labeling cost, low precision and poor robustness. The technology first uses an image segmentation network to obtain the category prediction result of each pixel in the image, and then calculates the image segmentation loss, instance splitting loss, positioning loss and regression loss respectively, and finally weightedly fuses each loss and trains the network as supervision information. The technology of the present invention only needs to mark the center point of the pig, and can output a roughly segmented area for each pig instance, and then obtain the accurate location and quantity information of the pig instance, solving the problem of counting and positioning live pigs in complex environments.

The invention provides a public service equipment disease identification method and device. The public service equipment disease identification method comprises the steps of obtaining a to-be-identified public service equipment image; inputting the to-be-recognized public work equipment image into a trained equipment recognition model to obtain a public work equipment recognition result corresponding to the to-be-recognized public work equipment image; based on the public service equipment identification result, determining a first disease identification model corresponding to the equipment type in the public service equipment identification result from a disease identification model group, and inputting the to-be-identified public work equipment image into the trained first disease identification model to obtain an equipment disease identification result corresponding to the to-be-identified public work equipment image. The disease identification method can automatically identify the diseases of different types of public work equipment, and improves the model generalization ability and the disease identification efficiency.

The invention discloses a multi-modal representation supported learner element cognitive ability evaluation method and system, and belongs to the field of model evaluation and prediction. The method comprises the following steps: firstly, constructing a learner meta-cognitive ability evaluation model consisting of a feature extraction module, an enhanced representation module, a multi-modal fusion module and a prediction module; and then, in combination with a fusion auxiliary task of multi-level cross-modal comparison predictive coding, training the learner meta-cognitive ability evaluation model according to a framework of combining semi-supervised learning and active learning, and performing learner meta-cognitive ability evaluation by using the trained learner meta-cognitive ability evaluation model. According to the method, multi-modal unified meta-cognitive quantitative representation can be effectively utilized, the dynamic dependence and long-term incidence relation among multiple modals can be accurately captured based on a cavity cross-modal attention mechanism, the model training efficiency is improved through a framework combining semi-supervised learning and active learning, and meta-cognitive ability evaluation is achieved.

The invention provides a ship name intelligent identification method. The method comprises the following steps: acquiring a ship image, a ship name identification sample set in multiple languages and a ship name identification sample set in multiple languages; performing feature extraction in the final data set, designing a self-supervised learning model, and performing comparative learning pre-training on the self-supervised learning model by using the extracted features; a hybrid model based on the deep convolutional neural network and Transform is constructed; designing tasks, and then constructing a multi-task sharing model according to feature vectors output by the hybrid model; constructing a graph neural network by using ship name region features and character feature vectors; and taking the feature representation output by the graph neural network as the input of a lightweight detection model, and identifying the ship name. According to the method, the problems of identification precision, adaptability and real-time performance in ship name identification are solved, and the robustness and accuracy of the system under the complex environment and multi-language support are remarkably improved.

The invention belongs to the technical field of artificial intelligence, and relates to a training method of a few-sample relation classification model and related equipment, and the method comprises the steps: constructing a business knowledge graph according to cleaning business data; performing data set division on the business knowledge graph to obtain an initial training set, a verification set and a test set; training the original language model according to the initial training set to obtain a pre-trained language model; constructing a seed relationship r and a seed sentence set Sr according to the verification set and the test set, and inputting the seed relationship r and the seed sentence set Sr into a sentence generator to obtain an optimal candidate sentence; expanding the seed sentence set Sr according to the optimal candidate sentence to obtain an expanded training set; and performing model training on the prototype network model according to the extended training set to obtain a target network model. According to the method, relation classification is effectively carried out under the situation of few samples and zero samples, the accuracy and generalization ability of the model are improved, the data annotation cost is reduced, and the method is suitable for knowledge graph construction and information extraction tasks in the field of electric power design.