212 results about "Sample selection" patented technology

Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for receiving a query relating to a data item that includes multiple data item samples and processing the query and the data item to generate a response to the query. In particular, the described techniques include adaptively selecting a subset of the data item samples using a selection neural network conditioned on features of the data item samples and the query. Then processing the subset and query using a downstream task neural network to generate a response to the query. By adaptively selecting the subset of data item samples according to the query, the described techniques generate responses to queries that are more accurate and require less computation resources than would be the case using other techniques.

The invention discloses a single-point supervised directional target detection method based on adaptive sample allocation and a global-local context enhancement module, which comprises the following steps: inputting an original remote sensing image into a backbone network, extracting to obtain a multi-scale feature map set, inputting a feature map with the highest resolution into a global-local context module to obtain an enhanced feature, and extracting the enhanced feature from the global-local context module; inputting the enhanced features into a projection layer to generate a category probability graph; based on the category probability graph, training and optimizing the category probability graph to obtain a probability histogram set by adopting a sample distribution and optimization strategy combining adaptive positive sample selection, online difficult case mining and a focus loss dynamic weighting mechanism based on prediction confidence; and based on the full training set category probability histogram set, carrying out adaptive pseudo tag threshold calculation, and finally, realizing end-to-end joint training of pseudo tags and enhanced features through a prediction quality guide weighting strategy. According to the method, the target contour precision and the detection robustness are remarkably improved, and high-performance remote sensing image directional target detection is realized under a weak supervision condition.

The invention discloses a remote sensing image sample intelligent acquisition method based on image classification, and relates to the technical field of image acquisition, and the method comprises the following steps: carrying out the feature extraction of a remote sensing image, and obtaining an initial feature; performing classification uncertainty evaluation according to the initial features to obtain uncertainty indexes; performing sample representativeness calculation according to the uncertainty index to obtain a representative index; performing sample diversity analysis according to the representative indexes to obtain diversity indexes; performing comprehensive sample scoring according to the diversity indexes to obtain sample scoring data; and performing sample selection according to the sample scoring data to obtain a final collection sample. According to the method, uncertainty weighted items are introduced, representativeness is calculated in combination with similarity, global distribution and local feature differences are considered, reliability of representativeness calculation is improved, balance of samples on ground feature type distribution is improved, and stability and scientificity of sample screening are improved.

A long-term continuous learning method based on task core memory management and consolidation aims to enable a model to sequentially learn from a large number of task sequences, new knowledge is obtained, information of previous learning is reserved, and the method is similar to a human learning mode. The method comprises the following steps: 1) task input and instruction fine tuning; 2) performing difference analysis on the model parameters of the current task and the previous task, identifying a task core memory unit, calculating an adaptive weight based on task prototype similarity, and dynamically updating the memory unit; 3) constructing an experience playback buffer area through a difficult sample selection strategy and a difference sample selection strategy; and 4) utilizing the joint loss function training model to keep the memory of the historical tasks while learning the new tasks. According to the method, the problem of disastrous forgetting in long-term continuous learning is mainly solved, and the performance of the model in a long-term sequence task is remarkably improved.

The invention discloses a multi-component catalyst active site prediction system and method fused with quantum embedding, and relates to the technical field of catalysis and material informatics, and the system comprises a structure and site enumeration module which generates candidate sites; the adaptive quantum embedding calculation module obtains key reaction microcosmic parameters; the unified site fingerprint and feature engineering module constructs and fuses standard site fingerprints; the physical consistency machine learning module predicts adsorption energy and other parameters and uncertainty thereof; the active learning and sample selection module selects a high-value sample optimization model; the microdynamics evaluation module calculates index values such as activity; and the multi-objective optimization and sorting module generates an optimization sorting list. According to the method, the unification of calculation precision and efficiency is realized, the problem of non-unification of locus characterization is solved, the model interpretability and extrapolation reliability are improved, and the comprehensive evaluation and optimization sorting of multi-target performance are completed.

The invention provides a fine-grained image clustering method and system based on FG-CLIP and language enhancement, and belongs to the field of image clustering. A pre-training text generation model is utilized to generate diversified coarse-grained text descriptions, then a text fine-grained module and a text screening module are utilized to perform fine processing on a text, and two enhanced views are fused to form consistent text representation, so that the comprehensiveness of text information is enhanced. Then, a neighbor set is constructed according to the feature similarity through a random neighbor sample selection module, attention to samples in the same cluster is improved, and the selection range of positive samples is expanded; and finally, inputting the image features, the text features and neighbor samples thereof into each modal cluster-level mapping head for dimension mapping, and realizing alignment and joint training of the two modal features through random neighbor contrast loss. Under the assistance of the text information, the fine-grained clustering targets can be accurately distinguished, so that the accuracy and robustness of fine-grained image clustering are effectively improved.

The invention discloses a target detection online learning dynamic sample selection method and system, computer equipment and a storage medium. The method comprises the steps that classification uncertainty and positioning uncertainty of samples to be screened are obtained through Monte Carlo Dropout sampling; constructing multi-dimensional feature vectors including classification uncertainty, positioning uncertainty, knowledge gap matching degree and the like; constructing a dynamic weight learning network based on an attention mechanism, and calculating the weight of each feature in combination with a model verification set performance index; and performing multi-dimensional value scoring on the samples according to the feature weights, and screening out an optimal sample subset in combination with calculation power limitation so as to complete online updating of the model. According to the method, the sample value is comprehensively evaluated through multi-dimensional feature fusion, different scene requirements are adapted by utilizing dynamic weights, and resource consumption and updating effects are balanced in combination with computing power perception sampling, so that the adaptability and detection precision of the model in a dynamic scene are effectively improved, and meanwhile, the dependence on manual annotation is reduced.

The invention relates to the technical field of artificial intelligence, and discloses a self-supervised learning-based electrocardiosignal anomaly detection system, which comprises an electrocardiosignal acquisition module, a data preprocessing module, a feature coding module, a self-supervised comparative learning module, an anomaly score calculation module and an anomaly judgment module which are in communication connection, the electrocardiosignal acquisition module is used for acquiring an original electrocardiosignal and transmitting the original electrocardiosignal to the data preprocessing module; the data preprocessing module is used for conducting denoising, baseline drift correction and standardization processing on original electrocardiosignals and transmitting the processed signals to the feature coding module. According to the invention, through a dynamic negative sample selection unit in the self-supervised contrast learning module, depending on technologies such as feature queue maintenance, feature distance calculation, clustering analysis and the like, samples which have significant difference from positive sample feature distribution and are different in category are screened as negative samples, so that the model can accurately learn real similarity between similar electrocardiosignal samples; and feature learning confusion is avoided.

The invention discloses an electric power field training set dynamic construction method and system based on BERT and reinforcement learning. The method comprises the following steps: S1, constructing a terminology library and a knowledge graph in the power field; s2, performing power field adaptation on the BERT model by using a terminology library and a knowledge graph to obtain a field adaptation model; s3, designing a strategy network based on reinforcement learning so as to dynamically select unlabeled samples and generate pseudo labels; and S4, based on the domain adaptation model and the strategy network, dynamically constructing and optimizing a training set through an iteration process. According to the method, the training set quality and the model performance are jointly improved, manual labeling is avoided, sample selection can be adaptively adjusted, the labeling cost is low, and the model accuracy is high. According to the method, the pseudo labels are automatically generated through the reinforcement learning strategy network, manual labeling requirements are reduced, labeling efficiency and model performance are improved, the quality of a training set can be optimized, and adaptability is enhanced.

The invention discloses a children voice expression error recognition and correction method based on comparative learning, and the method comprises the steps: carrying out the preprocessing of an inputted children voice signal, obtaining a logarithmic Mel spectrum feature sequence, and converting the logarithmic Mel spectrum feature sequence into voice semantic coding features through an improved Transform encoder; on the basis of an age-adaptive positive and negative sample selection mechanism, voice features are optimized by using a comparative learning method, and an enhanced voice representation vector is obtained; constructing a multi-modal fusion network, combining an enhanced voice vector and BERT language model features, realizing adaptive fusion through multi-head cross attention and a gating mechanism, adopting a bidirectional LSTM to design an error positioning module to recognize the position and the type of a pronunciation error, and using a joint loss function to execute end-to-end training; standard correction audio is generated according to the error type, and correction guidance is provided for children. According to the invention, high-precision recognition, positioning and correction of children's speech expression errors are realized, and technical support is provided for children's language development.

The invention discloses a multi-modal cross-domain small sample facial expression recognition method based on relational distillation self-paced learning, and relates to a computer vision technology. Constructing a multi-modal semantic enhancement module, generating semantic descriptions of expressions by using a large language model, performing CLIP coding, and performing alignment and fusion with image visual features in the multi-modal semantic enhancement module to construct a multi-modal prototype; a self-paced learning mechanism based on relational distillation is designed, visual and semantic structural errors are calculated, and progressive training from easy to difficult is realized through a soft and hard mixed sample selection strategy and a mixed sample selection mechanism regulated and controlled by a dynamic threshold value. And cross-domain migration of emotional knowledge from basic expressions to fine-grained composite expressions can be effectively realized. And under the condition that only a small number of labeled samples are provided, rapid adaptation and accurate recognition of new expressions can be realized. The method is remarkably superior to a traditional supervised learning method, has higher practicability and expansibility, and can better meet the requirement for efficient recognition of new expressions in practical application.

The invention discloses a class increment target detection method combining sample playback and an attention mechanism, and belongs to the field of target detection, and the method comprises the steps of dynamic sample selection playback, DETR model construction based on attention enhancement, and hybrid playback training. At the end of each incremental learning stage, dynamically replaying the samples, screening representative samples from the current task through a K-Center-Greedy algorithm, and storing the representative samples into a memory bank with fixed capacity; according to the DETR model based on attention enhancement, a channel attention module (SE module) is embedded in a target detection network DETR, and key feature expression is enhanced through feature channel re-calibration; the hybrid replay training is mainly characterized in that during new task training, a historical sample is extracted from a memory bank and mixed with a current sample to serve as a training set to be input, and cross-task knowledge fusion is achieved by jointly optimizing a detection loss function and an attention weight.

The invention discloses a performance self-improving large model recommendation system and method, and the system comprises an initialization module which is used for pre-training a large language model through supervision and fine tuning, and generating an initial recommendation model; the self-optimization module comprises three iteratively executed sub-modules; the sample selection sub-module is used for screening historical data samples of which the information amount is higher than a threshold value on the basis of comparison between the model prediction probability and the preset threshold value; the response fusion sub-module is used for generating K candidate responses for a selected sample and generating a preference data set based on model evaluation; and the DPO optimization sub-module is used for updating model parameters by utilizing the improved DPO loss function and generating an optimized recommendation model. According to the method, the dependence on static preference data in the prior art is broken, the recommendation quality and robustness are improved, and adaptive optimization is realized.

The invention discloses a power system power flow self-adaptive regulation and control method based on deep transfer learning, and the method comprises the steps: 1, constructing a power system source domain power flow analysis model, and constructing a loss function for a power flow error in combination with the power flow data characteristics of a source domain and a target domain; step 2, designing a network parameter initialization method suitable for power flow analysis, realizing transferable representation from source domain data to a target domain, and constructing an initialized target domain power flow analysis model; 3, introducing a sample selection and incremental learning mechanism, and carrying out dynamic screening and retraining on key power flow samples in a target domain; and 4, carrying out load flow calculation and optimization control on the target power system by adopting the trained target domain load flow analysis model, and realizing self-adaptive optimization of the system operation state through iterative correction and parameter updating. According to the method, rapid calculation and dynamic optimization of the power flow of the power system are realized, and the intelligent level, stability and calculation reliability of power grid operation analysis are remarkably improved.

The invention provides a landslide susceptibility evaluation method based on a deep neural network and considering time sequence InSAR and time sequence rainfall, belongs to the technical field of geological disasters and geographic information, and particularly relates to a landslide susceptibility prediction method based on the deep neural network. The method comprises the following steps: establishing a buffer area through landslide points, selecting a research area to randomly generate non-landslide points, screening related static characteristic factors by using a Pearson's correlation coefficient matrix and a VIF method, obtaining GCP points by using PS-InSAR, introducing the generated points as SBAS-InSAR processing parameters, generating dynamic characteristic factors of surface deformation, and calculating the deformation of the surface deformation. The time sequence average rainfall of the region is obtained through spatial interpolation, the rainfall before earth surface deformation is obtained through data processing codes to serve as another dynamic characteristic factor, finally evaluation is conducted through the constructed ResNetconvLSTMUnet, and the susceptibility index is divided into five grades; according to the method, the dual-time-sequence dynamic factors are creatively fused, the spatial-temporal feature extraction capability is enhanced, the data redundancy is reduced, the sample selection is reasonable, the evaluation precision is high, and scientific support can be provided for landslide disaster prevention and reduction.

The invention provides a sample data processing and data auditing method and device, equipment and a storage medium, which can be applied to various scenes such as sample selection. The method comprises the following steps: acquiring N candidate samples; for each candidate sample in the N candidate samples, reasoning the candidate sample through the target model to obtain first feature information of the candidate sample extracted by a middle layer of the target model; encoding the first feature information of the candidate sample to a high-dimensional space to obtain second feature information of the candidate sample; and selecting K difficult samples from the N candidate samples based on the second feature information of each candidate sample. According to the method, the first feature information of the candidate samples is extracted from the middle layer of the target model, the first feature information is coded into the high-dimensional sparse second feature information, then the K difficult samples are accurately selected from the N candidate samples based on the second feature information, and the selection accuracy of the difficult samples is improved.

This invention relates to the field of agricultural intelligent equipment and machine vision technology, and discloses a method for weed detection and growth point localization based on shared features. The method constructs a collaborative dataset containing weed detection labels and growth point labels, utilizes a shared feature extraction network to extract multi-scale features, and sets detection task branches and growth point localization branches in a unified feature space to achieve joint modeling of weed detection and growth point localization. Then, adaptive positive sample selection is performed based on the joint cost between candidate sample points and labeled growth points, and joint training is conducted using detection loss, growth point localization classification loss, and growth point localization regression loss. During the inference stage, the method outputs weed detection results and growth point localization results, and generates target point information. This method can reduce redundant calculations and error cascading in the multi-stage processing, and improve the accuracy of growth point localization and the stability of target point output in complex farmland scenarios.

The application belongs to the field of shell structure design, and particularly discloses a shell stability prediction method and system based on combined proxy model sequence sampling, which comprises the following steps: obtaining initial samples and corresponding shell critical pressures, and putting them into a database; obtaining training samples from the database, and establishing a temporary combined proxy model based on the training samples; randomly obtaining candidate samples, calculating the prediction uncertainty and sparsity degree of the candidate samples based on the temporary combined proxy model and the sample distribution in the database, and then selecting part of the samples in the candidate samples to add to the database; repeating the sampling until a preset termination condition is reached, and ending the sampling process; and using the samples in the database and the corresponding shell critical pressures to establish a final combined proxy model, so as to realize shell structure stability prediction. The application uses the information provided by the model and data to guide sample selection, can reduce the number of samples required for establishing a shell structure proxy model, and improves the design efficiency.

This invention provides a method and system for predicting the state of power equipment based on online testing adaptation, comprising: collecting power equipment state data in real time through sensors and forming test samples; filtering a set of adapted historical samples from a historical sample memory bank that meet preset conditions in terms of similarity to the test samples in the latent space through a transferable historical sample selection module, wherein the historical sample memory bank stores historical power equipment state data; performing time-frequency domain hybrid data augmentation on the test samples and the adapted historical sample set through a transferable online augmentation module to generate an augmented sample set; inputting the augmented sample set into a pre-trained power equipment state prediction model for batch training, dynamically adjusting the model parameters to adapt to the distribution shift; and fusing the output of the dual-stream predictor of the power equipment state prediction model to generate the power equipment state prediction result for the next time period. This invention can perform power equipment state prediction.

To provide a computer system and a learning data generation method for generating learning data for efficiently learning a model that outputs a feature quantity vector of data to which a numerical value is given as a label.SOLUTION: A computer system that holds information of a model that calculates a feature amount vector of data to which a label that is a numerical value representing a feature of the data is assigned, calculates the feature amount vector by inputting the data to the model, and executes a process of selecting a negative example and a positive example using the feature amount vector a plurality of times, the computer system comprising: For each candidate data, an index representing the difference between the query and the label of the candidate data is calculated, the candidate data having a large index is selected as a negative example, and the candidate data having a small index is selected as a positive example.SELECTED DRAWING: Figure 5

The present application relates to the technical field of shield muck treatment, and discloses a method and system for predicting the resource utilization of shield muck, which comprises collecting samples and pretreating, measuring quality and particle size distribution, obtaining initial parameters through initial pressure compression testing, obtaining parameters under different pressures through step-by-step pressure testing, inputting data into a prediction model to determine the availability and determine the optimal utilization mode, and generating a report for storage. The system comprises sample selection and pretreatment, fixation and measurement, initial parameter collection, test parameter collection, and resource utilization prediction modules. The method and system can accurately predict the resource utilization potential of shield muck, determine the optimal utilization mode, improve the resource utilization efficiency, and have good economic and environmental benefits.

The application discloses a cross-working condition control equipment fault detection system based on causal correction and full-space modeling. The system comprises a control equipment detection instrument, a control equipment fault database, a data processing module, a full-space fault modeling module, a causal correction module and a control equipment fault display and control module. The full-space modeling module and the causal correction module respectively solve the problems of data sparsity and sample selection bias existing in traditional methods, and are intended to realize unbiased estimation of fault probability under multiple working conditions.

The application discloses a wireless federated learning method for large-scale Internet of Things cooperative intelligence, aiming at the problem of heterogeneous device computing capability in a large-scale Internet of Things scene, and integrating centralized learning and federated learning to form a unified architecture, so that devices with weak computing capability can participate in global model training. On the one hand, the application determines the data sample selection strategy by the data importance of the centralized learning user, which can reduce the communication overhead and transmission time of data uploading; on the other hand, the application prunes the model of the federated learning user, which can effectively reduce the local computing time under the premise of ensuring the learning performance. The federated learning method provided by the application can realize data sample selection, model pruning and user scheduling of different types of users, which is helpful to improve the utilization rate of wireless network resources and alleviate the problem of limited resources of the Internet of Things.

The invention relates to the technical field of computer security, in particular to a feature space backdoor attack method, system and device based on fusion data transaction model parameter constraint and a storage medium. Obtaining an original training data set, constructing a data transaction model, calculating malicious sample loss values, and screening samples with smaller loss values as target samples; poisoning features are randomly extracted from the original data set, discrete noise is generated through a noise generator to form a trigger, the trigger is added to a target sample, a label is turned over, and an attack data set is formed; original training data are sampled, and a toll-snow information matrix of each layer is calculated; using the original model parameters to initialize the backdoor model, adding the L1 norm of the parameter disturbance difference value and the parameter difference constraint term based on the Feisnow information matrix into a loss function, and training the backdoor model; performance fluctuation caused by random sample selection is avoided through sample screening based on loss values, so that the backdoor model maintains the classification capability of clean samples while learning trigger features.

The application discloses a wetland feature set optimization method fusing improved filtering and packaging strategies, and steps of the method comprise the following: according to the actual situation of a research area, sample selection and a classification system are completed; multi-source remote sensing data are selected, and corresponding pretreatment is carried out on each data; feature extraction is carried out on the pretreated data, and an original feature set is constructed; three single-criterion filtering algorithms, i.e., LS, DC and JM distance, are fused to obtain an MCF-LDJ algorithm, the original feature set is preliminarily selected based on the MCF-LDJ, and a preliminary selected feature set is obtained; the preliminary selected feature set obtained in step 4 is further optimized by using a packaging algorithm, and a final optimized feature subset is obtained; the application proposes a multi-criterion fusion filtering algorithm, so that the importance of calculated features is more reasonable. The complementarity of the filtering algorithm and the packaging algorithm is utilized to improve the operation speed and evaluation accuracy of the feature selection algorithm.

The invention relates to a micro-service architecture root cause positioning method based on heterogeneous graph modeling and active learning, and the method comprises the following steps: 1, carrying out the feature extraction and topological structure of indexes, logs, call chains and deployment information, and forming unified heterogeneous graph modeling; and step 2, clustering, label diffusion and boundary sample selection are carried out on the heterogeneous graph model constructed in the step 1, semi-supervised training driven by active learning is used to continuously optimize a root cause positioning model, and the model is deployed in a production environment online to realize real-time fault detection and positioning. According to the method, the structural characteristics of the micro-service system can be fully utilized, and the root cause positioning method with low labeling requirements is provided, so that the balance between the task performance and the labeling overhead is realized, and a better solution is provided for efficient root cause positioning of the micro-service system.

The embodiment of the application provides a sample selection method for fluid inclusion micro-thermodynamic test. The method comprises the following steps: scanning a fluid inclusion slice to obtain a scanning image; placing the fluid inclusion slice under an optical microscope, observing and determining the fluid inclusions to be tested and their positions in the fluid inclusion slice through the optical microscope according to a research target; marking image positions corresponding to the positions of the fluid inclusions to be tested on the scanning image; determining final target fluid inclusions for the fluid inclusion micro-thermodynamic test according to comprehensive sample selection criteria based on all the fluid inclusions to be tested found; placing the fluid inclusion slice under the optical microscope again, determining the positions of the final target fluid inclusions in the fluid inclusion slice based on the image positions marked on the scanning image, and circumscribing the positions corresponding to the final target fluid inclusions on the fluid inclusion slice.

Data samples are selected for power consumption management. This comprises receiving samples associated with respective times, distributed in a sliding time window as current samples (23) and in a past period as past samples (25). Selected past samples are determined by keeping a first share (26) of the past samples, consisting in most recent ones, and a second share (29) through eliminating among the past samples deprived from the first share, called a complementary share (27), part of the past samples in function of at least some of the current samples and of elimination conditions (32) depending on similarity criteria (31) applied to at least the first and complementary shares. The selected past samples are provided with the current samples for power consumption management. Applications to power failure detection and power consumption dynamic adaptation.

This invention discloses a dual-constraint incremental axial piston pump fault diagnosis method based on sample selection and playback, belonging to the field of fluid pressure and electrical digital data processing. The method includes: acquiring fault signals at the current moment and labeling them to obtain fault samples, constructing a fault diagnosis model; merging the fault samples at the current moment with old fault samples to form an incremental dataset, where the selection of old fault samples is based on improved sample profile coefficients and thresholds; inputting the incremental dataset into the fault diagnosis models at the current and previous moments respectively, further calculating the total incremental loss function composed of cross-entropy loss, cosine contrast loss, and surrogate loss, updating the model parameters through backpropagation until convergence, obtaining the fault diagnosis model trained at the current moment. This invention overcomes the catastrophic forgetting problem of learned fault knowledge in existing fault diagnosis models, and improves the continuous learning capability of the axial piston pump fault diagnosis model through incremental learning.

The application discloses a remote sensing image shadow index performance evaluation method based on multiple scenes and multiple criteria, so as to evaluate the performance of different shadow indexes in urban and mountain scenes. The method comprises the following steps: data preparation, shadow extraction, sample selection, multiple criteria evaluation and comprehensive scoring. In the multiple criteria evaluation process, the shadow extraction accuracy evaluation is for the urban and mountain scenes; the separability of the shadow and the easily confused ground objects is for the urban scene, and is quantitatively evaluated by a 1.5 interquartile range (1.5IQR) separation ratio; the sensitivity of the shadow to the light intensity is for the mountain scene, and is quantitatively evaluated by the correlation between the shadow index and the cosine value of the solar incident angle (cosi). The method disclosed by the application can avoid the problems of single scene and single criterion in the traditional evaluation method, the evaluation result is intuitive and reliable, and the method has important scientific significance for objectively analyzing and evaluating the performance of the shadow index.