76 results about "Hybrid data" patented technology

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.

A system for decentralized database management includes a graphical user interface (GUI) layer configured to receive user actions for database operations. The GUI layer includes an input mapping module to translate user actions into backend commands, a real-time monitoring module to display metrics related to node status, database health, and blockchain transactions, and an error handling module to categorize errors for troubleshooting. The system includes a hybrid database system integrated within a decentralized blockchain network supporting both relational and non-relational data models, with value contracts defining database schemas and rules, and an indexing mechanism for optimizing data retrieval. A Self-Delegated Proof of Equal Stake (SDPoES) consensus mechanism is provided to validate and synchronize database operations across nodes, including a dynamic scheduling engine to coordinate block production among master nodes and a stake validation system to manage master node qualification through memory staking requirements.

This invention provides a method, system, and electronic device for protecting the operational mode of model inference, relating to the field of artificial intelligence security technology. The method includes: generating a public sample set based on the original model; randomly selecting sensitive samples and copying the query sample to be inferred multiple times, mixing them, and then randomly shuffling them; encrypting the mixed dataset using a homomorphic encryption algorithm and sending it to a remote system for encrypted inference; finally, decrypting and reconstructing the returned encrypted inference result locally, and using double verification to determine whether the operational mode of the remote system is complete. This invention, by generating highly sensitive samples and combining sample copying, random shuffling, and homomorphic encryption algorithms, achieves efficient and reliable detection of tampering with the operational mode of the remote model's inference process, while simultaneously ensuring data privacy.

This invention discloses an intelligent analysis and early warning cloud database system for big data in water conservancy project operation and maintenance, specifically relating to the field of water conservancy project operation and maintenance technology. The system is based on a cloud-native architecture and includes an intelligent data lake warehouse, a time-series graph fusion storage engine, an embedded model computation module, a collaborative early warning and analysis module, and a self-learning optimization module. The intelligent data lake warehouse performs semantic annotation preprocessing on multi-source heterogeneous operation and maintenance data; the time-series graph fusion storage engine deeply integrates domain knowledge graphs with semantically annotated time-series data sequences, logically binding the time-series data sequences to graph nodes through globally unique identifiers to form a time-series-graph hybrid data model; the embedded model computation module deploys dedicated analysis models; the collaborative early warning and analysis module aggregates multimodal evidence chains, schedules model collaborative computation, and performs fusion analysis to generate early warnings; the self-learning optimization module optimizes the model online based on feedback. This invention achieves data fusion storage and intelligent early warning, improving operation and maintenance efficiency and reliability.

This application relates to an adaptive learning-based robotic arm control method, apparatus, device, and storage medium. The method includes: jointly training a first initial model and a second initial model based on an offline dataset until a first preset condition is met, obtaining a first reference model and a second reference model; obtaining an online dataset corresponding to the robotic arm based on the first and second reference models; determining a hybrid dataset based on the offline and online datasets; jointly training the first and second reference models based on the hybrid dataset until a second preset condition is met, obtaining a first target model and a second target model; determining an adaptive control model based on the first and second target models; the adaptive control model is used to generate and filter optimal parameter pairs for the robotic arm in real time to achieve adaptive control of the robotic arm. Using this application can improve the adaptive capability of robotic arm control.

This invention discloses a photovoltaic power prediction simulation platform based on fitting correction and digital twins, comprising modules such as a hybrid data source, scheme configuration and comparison, a digital twin simulation engine, scenario scripts, and robustness testing. The method of this invention constructs a forward simulation path through triple fitting correction (meteorological data correction, power conversion correction, and scheduling standard evaluation); and utilizes the results of the third evaluation correction to form a feedback signal, dynamically adjusting the feature weighting and power calibration parameters in the forward path to form a closed-loop simulation; the digital twin engine integrates long-cycle factors such as component aging and a sudden event injection mechanism to simulate a high-fidelity dynamic environment. This invention enables dynamic evaluation of the adaptive learning capability of prediction schemes, robustness and resilience testing under extreme conditions, and provides a fair comparison environment and refined error attribution analysis, significantly improving the efficiency and depth of photovoltaic power prediction system research and development and verification.

The application relates to an OpenGL multi-class object uniform drawing method based on VBO internal coding, which comprises the following steps: constructing a mixed data structure containing vertex coordinates, color components, texture coordinates and object type marks, and storing the mixed data structure in the memory of a VBO in an interlaced arrangement; defining a uniform vertex shader and a fragment shader; judging whether texture mapping is needed according to the object type marks during a rendering process; and deleting the VBO object and the shader program after the rendering is completed, and releasing the display memory and the memory resources. The application links map elements with different rendering logics, realizes the uniform drawing of heterogeneous objects under a single pipeline, fully utilizes the parallel processing capacity of a GPU, avoids frequent switching of the shader, effectively saves the communication bandwidth between a CPU and the GPU, simplifies the development difficulty of multi-map element mixed rendering in a complex scene, and facilitates the horizontal expansion of a system in large-scale geographic information visualization.

The application discloses a pseudo-label model training method and device, a storage medium and electronic equipment. The method comprises the following steps: obtaining a plurality of sample communication relationship data with added sample labels; using a first classification model to analyze the sample communication relationship data, and generating a first classification label, wherein the first classification model is trained using clean label data; using a second classification model to analyze the sample communication relationship data, and generating a second classification label, wherein the second classification model is trained using mixed data, and the mixed data comprises clean label data, noise label data and unlabeled data; determining that the difference between the sample label and the second classification label is a first difference, and the difference between the first classification label and the second classification label is a second difference; and using a preset loss function model to analyze the first difference and the second difference, and determining a pseudo-label model. The application solves the technical problem that unlabeled data cannot be used for model training.

The invention discloses a wind turbine generator gearbox state monitoring and fault early warning method and system. The method comprises the following steps: defining a key part of a gearbox of a wind turbine generator as a flexible body, and constructing a multi-body dynamic model based on the flexible body; the multi-body dynamics model receives input multi-source time sequence data, then performs feature extraction and multi-index fault early warning algorithm processing, and outputs signal abnormal information for the current multi-source time sequence data; the signal abnormal information is gearbox fault data; constructing a mixed data set guided by a physical mechanism and performing data enhancement; and inputting a spatial-temporal feature coding fault diagnosis model based on the enhanced mixed data set, and then outputting a health index. According to the intelligent early warning system for the wind turbine generator gearbox, through the technical innovation of making up for data missing through modeling simulation, improving diagnosis precision through an intelligent algorithm and guaranteeing real-time early warning through edge calculation, a set of intelligent early warning system for the wind turbine generator gearbox which is high in precision, low in time delay and strong in generalization is successfully constructed.

This invention discloses a method and system for fine-tuning gradient correction of synthetic data in asymmetric machine translation, relating to the field of neural machine translation technology. The method includes the following steps: constructing a hybrid training dataset; initializing the neural machine translation model and training parameters; calculating the gradients of real data and synthetic data respectively; performing unidirectional judgment based on the real data gradient to detect gradient conflict states; performing asymmetric gradient correction based on the gradient conflict state detection results; updating the parameters and verifying the convergence of the neural machine translation model; constructing a hybrid dataset and calculating the real data gradients of real parallel data and synthetic data respectively; when gradient conflict is detected, unidirectionally projecting the synthetic data gradient to the orthogonal direction of the real data gradient, preserving the semantic anchoring effect of the real data, avoiding semantic drift introduced by the synthetic data, improving translation quality and robustness, increasing computational efficiency, and exhibiting good adaptability and economy in low-resource scenarios.

This invention discloses a method and system for massive data sharding and aggregation query based on a hybrid database architecture, belonging to the field of data query technology. Upon receiving an aggregation query request, a consistency cross-section identifier is generated. Under the constraint of the consistency cross-section identifier, the target data is ordered sharded, and a two-sided compensation shard is constructed to cover the shard boundary data. Candidate shards are extracted in parallel and shard fingerprint information is generated to establish a mapping relationship between the basic shards and the two-sided compensation shards. An aggregation closure unit is constructed based on the grouping field summary. The target shard set is determined and deduplication rules are generated. Duplicate contributions are removed and boundary truncation compensation is performed on the local aggregation results to obtain a corrected result set. Finally, global aggregation is performed, and the query results corresponding to the consistency cross-section identifier are output. This invention can effectively solve the statistical bias problem caused by shard boundaries and data inconsistency during massive data sharding and aggregation, improving the accuracy and stability of the query results.

The embodiments described herein provide a hybrid data center cooling system. In at least one embodiment, a data center cooling system includes one or more air-to-liquid heat exchangers to utilize one or more first coolant flows to transfer heat from one or more heated air flows and one or more heated second coolant flows that are returned from one or more compute hardware components.

A system for decentralized database management includes a graphical user interface (GUI) layer configured to receive user actions for database operations. The GUI layer includes an input mapping module to translate user actions into backend commands, a real-time monitoring module to display metrics related to node status, database health, and blockchain transactions, and an error handling module to categorize errors for troubleshooting. The system includes a hybrid database system integrated within a decentralized blockchain network supporting both relational and non-relational data models, with value contracts defining database schemas and rules, and an indexing mechanism for optimizing data retrieval. A Self-Delegated Proof of Equal Stake (SDPoES) consensus mechanism is provided to validate and synchronize database operations across nodes, including a dynamic scheduling engine to coordinate block production among master nodes and a stake validation system to manage master node qualification through memory staking requirements.

The present application relates to the technical field of electric digital data processing, and discloses a data processing method of multi-source error fusion, comprising: acquiring geometric static error, non-uniform temperature field distribution and strain load mixed data containing thermal stress characteristics of a large controlled system; thermal elastic compensation modeling is used to calculate thermal deformation compensation and map thermal induced pseudo-tension component; the component is used to decouple and separate strain load mixed data, and extract net mechanical load component; according to the dynamic distribution weight of each data compensation component observation variance, a multi-dimensional matrix fusion is used to generate a comprehensive error state vector; a physical logic threshold is compared, and a space deviation control instruction is outputted; the present application decouples thermal induced interference at the level of electric digital signal, cuts off the coupling parasitic link between temperature characteristics and strain characteristics, avoids data space collinearity interference, suppresses control instruction oscillation, and improves the deviation hedging stability and real-time processing efficiency of a large controlled system.

One embodiment of the present invention provides an apparatus and method for accurately segmenting a tooth image using artificial intelligence technology in a tooth diagnostic device. An apparatus according to one embodiment of the present invention includes: a database storing a hybrid data set comprising a plurality of disclosed tooth images and a plurality of undisclosed tooth images; and a control unit that generates a tooth segmentation image by segmenting at least one tooth in one tooth image included in the hybrid data set through a Seg-CSAB segmentation model, and generates a tooth analysis image by marking the location of the missing tooth on the tooth segmentation image through a missing tooth location prediction module.

The application provides a residual neuromorphic processing architecture, which comprises 16 neuromorphic cores and an on-chip network communication, and introduces two mechanisms of double packet time division multiplexing and distributed pipeline synchronization on the basis of a traditional on-chip network router circuit, so that a high-throughput pipeline parallel inference without deadlock can be realized in a 16-core system with a 4*4 grid scale only by adding a small amount of state machine and a multiplexer circuit. The deadlock problem is solved by a double packet time division multiplexing control strategy, so that the MS and the pulse packet are alternately transmitted in time, and the routing deadlock caused by the mixed data flow is fundamentally avoided. The application improves the calculation accuracy, reduces the resource consumption and improves the throughput. Compared with the scheme without adopting the DP-TDM, the application is shortened by 29.37%. The system reaches a high throughput of 817.9K time steps / second, and the comprehensive performance is better than that of the existing scheme.

This invention discloses a method for predicting the characteristics of amorphous oxide semiconductor devices based on a hybrid dataset. The method involves constructing a hybrid dataset of drain-source currents for amorphous oxide semiconductor devices and using it to train an artificial neural network model. Device size parameters and voltage parameters are input into the trained artificial neural network model, which outputs predicted drain-source current values. Based on the device's voltage parameters and the corresponding predicted drain-source current values, the electrical characteristics of the amorphous oxide semiconductor device under different device size parameters are predicted. This invention rationally integrates data from different sources within a unified framework, fundamentally resolving the contradiction between insufficient measured data and significant deviations in simulation data in traditional modeling methods. It achieves a data fusion approach of "measured data as the primary source, supplemented by simulation data," making it easier for the neural network to learn electrical laws consistent with real devices, thereby further improving the stability, accuracy, and physical consistency of the prediction model.

A system for decentralized database management includes a graphical user interface (GUI) layer configured to receive user actions for database operations. The GUI layer includes an input mapping module to translate user actions into backend commands, a real-time monitoring module to display metrics related to node status, database health, and blockchain transactions, and an error handling module to categorize errors for troubleshooting. The system includes a hybrid database system integrated within a decentralized blockchain network supporting both relational and non-relational data models, with value contracts defining database schemas and rules, and an indexing mechanism for optimizing data retrieval. A Self-Delegated Proof of Equal Stake (SDPoES) consensus mechanism is provided to validate and synchronize database operations across nodes, including a dynamic scheduling engine to coordinate block production among master nodes and a stake validation system to manage master node qualification through memory staking requirements.

Embodiments described herein provide a hybrid data center cooling system. In at least one embodiment, a data center cooling system includes one or more air-and-liquid heat exchangers to use one or more first coolant flows to transfer heat from one or more heated air flows and one or more heated second coolant flows returned from one or more computing hardware.

This invention provides an intelligent shale lithology identification method based on machine learning and data augmentation. The method includes: S1, acquiring raw well logging data and preprocessing it to output a test set and a training set; S2, defining a multi-stage feature optimization strategy to perform feature optimization on the training set; S3, employing a denoising-augmentation-equilibrium hybrid data sampling strategy to perform hybrid data sampling on the training set; S4, constructing a random forest model based on KNN weighting and Optuna optimization, and training the random forest model; S5, inputting the test set into the random forest model for evaluation. By combining the hybrid data sampling strategy with the sample weighting mechanism, the model's identification performance for all lithologies, especially a few lithology types, is significantly improved. It can systematically address data imbalance and achieve efficient automated lithology identification.

This invention discloses a two-stage scheduling method for coordinated distribution network ancillary services for electric vehicles based on deep reinforcement learning. The method includes: establishing a scheduling strategy model based on a distribution network model, an electric vehicle battery dynamic characteristic model, a charging price incentive model, and a discharging price incentive model; training the scheduling strategy model using a two-stage training method based on a Gaussian mixture model; during scheduling, using a K-means clustering method based on electric vehicle energy availability criteria to select electric vehicles for distribution network ancillary services; and establishing a data simulator, performing pre-training using a mixture of real and simulated data in the offline stage, and training using real-time data in the online stage. The scheduling method proposed in this invention can effectively improve training speed and model robustness, and reduce accumulated voltage errors and the proportion of illegally charged electric vehicles during online startup, thereby solving the problems of real-time peak shaving and voltage regulation.

The present invention relates to a method for identifying pipeline failures that enables the detection of specific failures in critical events, since it presents an optimized search space for obtaining a precise and adaptable trained model, based on the use of a hybrid database comprising operational data and simulated data, and feedback from performance metrics combining variable data in an optimizer, generating machine learning models with greater specialization capacity and consequently allowing an increased capacity for classifying critical events.

This application relates to a method and system for optimizing a ruthenium-catalyzed selective hydrogenation process for benzene based on interpretable machine learning. The method includes: acquiring the original experimental dataset of the ruthenium-catalyzed selective hydrogenation reaction for benzene; generating synthetic data through conditional variational autoencoder training and data augmentation; merging the synthetic datasets to obtain a mixed dataset; inputting the mixed dataset into an automated machine learning platform to complete model training and selection, obtaining a predictive model for output performance variables; and quantifying the contribution of features through model interpretability analysis to reveal the nonlinear relationship between features and output performance. This invention effectively solves the problems of scarce catalytic experimental data and poor model interpretability, achieving accurate prediction of reaction performance and mining of the influence patterns of key process parameters, providing an efficient data-driven solution for process optimization and catalyst design.

A method, performed in an environment where data transmission is vulnerable to quantum computers, for comparing a first dataset and a second dataset, in particular with a view for determining whether these two datasets are identical. The method not requiring the presence of these two datasets in the apparatus, and including the following steps of: a) mixing a number, called the mixer number, with the first dataset, using a mixing function, in order to obtain mixed data, b) hashing the mixed data using a hash function, wherein the a length of the mixer number is longer than a length of the hash and c) comparing the hash thus obtained in step b) with a third dataset assumed to be the hash of the second dataset mixed with the same mixer number as that used in step a) and with the same mixing function.

The application provides a large language model training and reasoning method based on mixed field entropy dynamic alignment. The training method comprises the following steps: acquiring a general field data set and a target field data set; generating multiple reasoning tracks corresponding to each general field sample in the general field data set and calculating corresponding reasoning uncertainty and exploration diversity; obtaining a comprehensive value score of each general field sample according to the reasoning uncertainty and the exploration diversity, and selecting the top k general field samples with the highest scores to obtain a selected general field data set; in each iteration training, a batch of data is sampled from the mixed data set for track generation and entropy dynamic extraction to obtain an entropy dynamic set of the target field sample and an entropy dynamic set of the general field sample, and an entropy dynamic alignment reward is calculated to update the parameters of the strategy model until the preset training condition is met to obtain a trained large language model; and the accuracy of the reasoning result is improved.

The application discloses a kind of based on multi-modal data fusion's family broadband construction dynamic early warning scheduling method, it is related to communication network operation and maintenance technical field.For the defects existing in the prior art family broadband construction management, the scheme includes: obtaining specified data, generating standardized multi-modal data set after preprocessing;For the space-time data in data set, text-time-value mixed data parallel modeling, through feature extraction and fusion, the output space-time risk feature map and cross-modal abnormal feature vector are completed after prior modeling, and the construction risk fusion feature set is obtained through the feature level fusion strategy, and the construction abnormal feature information is extracted;Build intelligent early warning model, the model is trained and optimized by historical data, and the output early warning result is evaluated;Based on early warning result, dynamic optimization scheduling of construction resources is carried out;The foregoing data is visualized and displayed, and the model parameters and scheduling strategy are iteratively optimized relying on feedback data.The application is used for optimizing the efficiency of family broadband construction.

This invention discloses an image target detection model training method, apparatus, device, and storage medium, applied in the field of target detection. The method includes: acquiring raw data; acquiring generated data where the occlusion area reaches a preset occlusion threshold to obtain generated training data; continuously using a basic target detection model to perform inner loop training on the generated training data and raw data; acquiring mixed data to perform iterative outer loop training on the basic detection model; stopping the inner and outer loop iterative training when the Loss3 value during training with mixed data does not change within a preset number of consecutive iterations, thus obtaining the image target detection model. This invention generates a large amount of generated data using computer technology and uses a basic model to perform inner and outer loop training on the acquired raw data, generated data, and mixed data, greatly reducing data collection time costs. Furthermore, due to the inner and outer loop iterations, the obtained image target detection training model can more accurately identify target objects.

This invention provides a method, system, equipment, and medium for detecting pests and diseases throughout the entire growth period of cereal crops, belonging to the interdisciplinary field of smart agriculture and computer vision technology. The invention first collects field images covering the seedling stage to the grain-filling stage and different stages of pests and diseases, and annotates them with fine granularity. Then, it decouples foreground and background through a targeted hierarchical data augmentation strategy and expands the samples through generative fusion to construct a hybrid dataset. Based on a lightweight YOLOv11n, a multi-scale dilated attention module is embedded in the detection head, and a meta-learning feature adaptation module is set between the backbone and neck networks. The model is trained using an adaptive threshold focus loss function. During training, common features of pests and diseases across the growth period are extracted, full-scale pest and disease features are captured, and sample weights are balanced, ultimately resulting in an integrated detection model that can output pest and disease categories, confidence levels, and bounding box positions. This method effectively solves the problem of imbalanced sample distribution and improves detection accuracy and model generalization ability.