1926 results about "Synthetic data" patented technology

The invention belongs to the technical field of earthquake disaster scene recognition, and discloses an earthquake disaster scene recognition method based on deep learning. The method comprises the following specific steps: S1, data acquisition and preprocessing; S1.1, multi-source heterogeneous data acquisition and establishment of a comprehensive database containing seismic waveform data, surface deformation data, building structure data, geographic information data and historical disaster record data; through fusion of a 3D convolutional network, a graph attention mechanism, a space-time LSTM and an adaptive cross-modal attention fusion technology, combined modeling of a seismic waveform space-time evolution law, an earth surface deformation space distribution characteristic, a building group topology vulnerability and disaster chain time sequence association is realized, the characterization capability of a complex nonlinear disaster mode is effectively improved, and the method has the advantages of high adaptability and high reliability. And disaster assessment response time is shortened to a sub-second level through mixed precision quantification and edge computing deployment, and high recognition accuracy is still kept in a scene with strong noise and data missing in combination with a multi-task classifier and a physical constraint verification mechanism.

Multi-modal models learn a joint latent space for relating data points across different modalities. To more effectively learn multi-modal models with reduced training requirements and greater benefit from limited multi-modal training data, a multi-modal model may be trained with fixed or pre-trained unimodal encoders that generate data representations in respective latent spaces. The multi-modal model is trained to learn a shared latent space while fixing the unimodal encoders, enabling training without storing the unimodal encoders in memory. Limited multi-modal data may also be augmented by generating synthetic data between commonly-labeled pairs in the respective modality's latent spaces. The effect of data diversity can also be determined by generating a diverse data set with respect to the data points in latent space, enabling measurement of performance of the multi-modal model on limited training data.

Multi-modal models learn a joint latent space for relating data points across different modalities. To more effectively learn multi-modal models with reduced training requirements and greater benefit from limited multi-modal training data, a multi-modal model may be trained with fixed or pre-trained unimodal encoders that generate data representations in respective latent spaces. The multi-modal model is trained to learn a shared latent space while fixing the unimodal encoders, enabling training without storing the unimodal encoders in memory. Limited multi-modal data may also be augmented by generating synthetic data between commonly-labeled pairs in the respective modality's latent spaces. The effect of data diversity can also be determined by generating a diverse data set with respect to the data points in latent space, enabling measurement of performance of the multi-modal model on limited training data.

The invention discloses a method and a system for collecting decision data by an intelligent agent driven by a multi-modal large model. The method comprises the following steps: collecting original data of a predetermined sensor, calculating information entropy and a normalized mass score, and generating a fusion feature vector through self-adaptive multi-modal information fusion; time sequence sensitive multi-mode alignment processing is carried out on the image, and time sequence alignment features are obtained by combining timestamp embedding and a self-attention mechanism; based on this, decision distribution is generated by using a Bayesian neural network, uncertainty is evaluated, and a final decision and index set is generated; evaluating a task score in combination with task description, and making an execution plan according to a resource state; initializing the model, generating synthetic data, optimizing the model and storing experience. According to the invention, the efficient decision-making process of the intelligent trolley is realized, and the execution capability and task completion precision of the intelligent trolley are improved.

Multi-modal models learn a joint latent space for relating data points across different modalities. To more effectively learn multi-modal models with reduced training requirements and greater benefit from limited multi-modal training data, a multi-modal model may be trained with fixed or pre-trained unimodal encoders that generate data representations in respective latent spaces. The multi-modal model is trained to learn a shared latent space while fixing the unimodal encoders, enabling training without storing the unimodal encoders in memory. Limited multi-modal data may also be augmented by generating synthetic data between commonly-labeled pairs in the respective modality's latent spaces. The effect of data diversity can also be determined by generating a diverse data set with respect to the data points in latent space, enabling measurement of performance of the multi-modal model on limited training data.

The invention discloses a mountainous area high pier cast-in-place safety detection method based on multi-source data fusion, and relates to the technical field of intelligent building safety monitoring, and the method comprises the steps: deploying a sensor network, a multi-angle holder video monitor and an unmanned aerial vehicle, covering a mountainous area high pier for comprehensive monitoring, and collecting multi-source data; transmitting the multi-source data to an edge computing node in real time through a wireless network, and preprocessing the multi-source data to form a standardized multi-source data set; applying a spatio-temporal data fusion method, combining historical data and a comprehensive data model to predict a security risk, and generating a risk factor; threshold and rule abnormity identification is carried out on the risk factors, the safety condition is evaluated in real time, early warning is triggered in real time, and disposal suggestions are provided. According to the method, the safety detection efficiency and accuracy in the mountainous area high pier cast-in-place process are remarkably improved through multi-source data fusion and a quantum enhancement multi-modal algorithm, the triggering speed of safety early warning is effectively increased, and the safety guarantee of a construction site is remarkably enhanced.

Embodiments of the disclosure relate to unsupervised learning with synthetic data and attention masks. According to example embodiments of the disclosure, a plurality of sample images are generated by providing a plurality of text prompts into a trained generative model, respectively. For a sample image of the plurality of sample images, at least one attention map is obtained from a generative model, the at least one attention map being determined by the generative model for generating the sample image, an attention map indicating visual elements of an object within the sample image. Training of a target model is performed according to unsupervised learning at least based on the plurality of sample images and attention maps for the plurality of sample images, the target model being configured to perform an image processing task.

The invention relates to the technical field of computer storage, in particular to a multi-level cache management method, system and equipment for solid-state storage equipment and a medium. The method comprises the following steps that multiple layers of caches are configured in the solid-state storage device and comprise a high-speed cache layer, a medium-speed cache layer and a low-speed cache layer, and each layer of cache has different access speeds and capacities and is used for storing data blocks with different priorities and access frequencies; dynamically scheduling the data blocks to a proper cache layer through a cache allocation algorithm according to the real-time access frequency, size, life cycle and importance of the data blocks; establishing a comprehensive data block priority evaluation model, and calculating a priority score of each data block; according to the multi-level cache management method, by configuring the multi-layer cache, the priority evaluation model and the multi-path scheduling mechanism, dynamic scheduling and load balancing of the data blocks among different cache layers are achieved, and the overall efficiency of data access is improved.

A system and method for comprehensive data utilization and tracking comprising an ontological engine which in some embodiments is configured to create and curate various industry-specific ontologies which can be used to provide deeper context to an enterprise's network traffic and data transmission. The system and method further comprise a tagging and tracking engine configured to inspect network packets, apply a first tag associated with an authentication object, apply a second tag associated with an identified ontology, and track the tagged packets as they traverse the enterprise network, generating data utilization tracking information as the packets move through the network. A scoring engine may leverage the data utilization tracking information in combination with user entity and behavior data to compute a risk score associated with data utilization on the enterprise network.

An agentic workflow system and method generate question and answer pairs and prompts that may be used to aligns generative artificial intelligence (a large language model (LLM) or a large multimodal model (LMM)) with the principles of a specific domain so that the generative artificial intelligence is better able to respond to a user query in the specific domain. The system and method may also generate aligning processes that may be used to post-train an already trained generative artificial intelligence system or fine tune the training of the generative artificial intelligence system to align that generative artificial intelligence system with the principles of the specific domain. The system and method may be used to align the generative artificial intelligence system to a plurality of different domains.

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

Apparatuses, system, and techniques use one or more first neural networks to generate one or more synthetic data to train one or more second neural networks based, at least in part, on one or more performance metrics of one or more second neural networks.

In hemodynamic determination in medical imaging, the classifier is trained from synthetic data rather than relying on training data from other patients. A computer model (in silico) may be perturbed in many different ways to generate many different examples. The flow is calculated for each resulting example. A bench model (in vitro) may similarly be altered in many different ways. The flow is measured for each resulting example. The machine-learnt classifier uses features from medical scan data for a particular patient to estimate the blood flow based on mapping of features to flow learned from the synthetic data. Perturbations or alterations may account for therapy so that the machine-trained classifier may estimate the results of therapeutically altering a patient-specific input feature. Uncertainty may be handled by training the classifier to predict a distribution of possibilities given uncertain input distribution. Combinations of one or more of uncertainty, use of synthetic training data, and therapy prediction may be provided.

A method for training and using a field machine learning (ML) model to classify emission data is presented. The method includes generating synthetic data by a large language model (LLM) by prompting the LLM with emission classes and few shot examples. The synthetic data includes multiple synthetic data instances and corresponding instance labels. A training dataset is obtained from the synthetic data. The method further includes training the field ML model with training instances which are synthetic data instances from the training dataset and corresponding training labels. The field ML model generates a predicted probability distribution of a training output class corresponding to a training instance. The method further includes adjusting a model parameter weight of the field ML model to minimize a categorical cross-entropy loss function calculated based on the generated predicted probability distribution. The trained field ML model is used to classify emission data.

The invention relates to the technical field of data management, in particular to a data management method and system for an industrial energy storage system. The method comprises the following steps: carrying out real-time energy storage data acquisition on an industrial energy storage unit, and generating corrected energy storage monitoring data; carrying out distributed redundancy transmission on the corrected energy storage monitoring data, and carrying out uploading data difference analysis to obtain monitoring uploading difference data; performing difference conflict processing on the redundant monitoring and uploading data through the monitoring and uploading difference data to generate monitoring fragment feature data; performing dynamic cache synchronization processing according to the monitoring fragment feature data to obtain monitoring cache state data; and performing management state comprehensive analysis on the monitored fragment feature data by monitoring the cache state data to generate a comprehensive data management index. According to the method, efficient, reliable and safe uploading management optimization of mass industrial energy storage monitoring data is realized through distributed intelligent caching, and the problems of inconsistent data uploading and even data loss are effectively solved.

The invention relates to the technical field of power equipment operation and maintenance management, in particular to a power equipment asset health management and predictive maintenance service system which comprises a data acquisition and integration module, a feature engineering module, a health assessment and prediction engine maintenance decision and early warning module and a service interface module. The data acquisition and integration module acquires equipment operation parameters through multiple types of sensors, and associates pre-stored equipment asset information to generate an equipment comprehensive data stream; the feature engineering module cleans and standardizes the equipment comprehensive data stream, and constructs a space-time correlation feature matrix; the health assessment and prediction engine comprises a health state assessment unit and a fault prediction unit, the health state assessment unit outputs a health index HI by using a gradient boosting decision tree, and the fault prediction unit outputs a fault probability and a remaining service life RUL in a future preset time period; and the maintenance decision and early warning module generates a grading early warning signal and a maintenance strategy scheme. The intelligent level of operation and maintenance of power equipment is improved, reliable operation of the equipment is guaranteed, and the operation and maintenance cost is reduced.

The invention discloses a rendering method and system for generating a monitoring event queue of an air conditioner host. The method comprises the steps of obtaining operation data and monitoring data of air conditioner equipment, constructing an equipment connection diagram, extracting spatio-temporal characteristic data and constructing a comprehensive data model. Constructing a multi-level event processing queue, and generating an event scheduling strategy scheme; constructing a dependency graph of the rendering process, and generating a resource allocation scheme; constructing a rendering strategy scheme in combination with pre-stored historical rendering data, and generating a time series data set; generating a version chain table in combination with the historical data version information; performing data consistency check, and outputting a synchronous rendering data set; executing the rendering task sequence to obtain a rendering result; meanwhile, the execution state of the rendering process is monitored, and a rendering execution report and a rendering state report are generated. According to the method, the average response time of the system is prolonged, the accuracy of data processing is guaranteed, the stability of the system is improved, and powerful technical support is provided for stable operation of the air conditioner host monitoring system.

The invention relates to the technical field of coal mine disaster monitoring, in particular to a gas coal mine goaf coupling disaster monitoring method, an electronic device and a storage medium, and the gas coal mine goaf coupling disaster monitoring method comprises the following steps: obtaining comprehensive data of a goaf through a sensor network, and carrying out data preprocessing to obtain standardized data; constructing a digital twinborn model through a 3D modeling and geographic information system technology; performing data synchronization and model correction processing on the digital twinborn model, and optimizing parameters and states of the digital twinborn model; constructing a fluid-solid-heat multi-field coupling model through a computational fluid mechanics and finite element analysis method; constructing a risk assessment model through an analytic hierarchy process and a fuzzy comprehensive evaluation method; training a disaster early warning model by using a machine learning algorithm based on the standardized data and the risk assessment model; a digital twinborn model, standardized data, a risk assessment model and a disaster early warning model are integrated, and a visual interaction platform is constructed. According to the monitoring method, multiple disaster elements can be coupled and dynamically evolved, and the disaster prediction accuracy and timeliness are greatly improved.

The invention discloses a P4 switch processor core-oriented multi-service traffic packet scheduling method, which mainly comprises the following steps of: proposing a feature extraction method based on a statistical interval and Sketch, integrating data packet time correlation and traffic dynamic change, optimizing a Bloom filter conflict detection mechanism, and improving the adaptability and accuracy of an algorithm in a limited resource environment; a decision tree model is combined with scheduling, a decision tree is reconstructed to adapt to an operation mode and a data processing requirement of a P4 switch, and high-precision service flow classification under linear speed operation is ensured; a packet scheduling method AD-PIFO is designed based on a variable priority, the forwarding priority of a data packet is dynamically adjusted, the QoS requirements of different services are met, and the overall performance and efficiency of the switch are improved. The method is outstanding in high-priority traffic throughput and low-delay performance, is superior to similar algorithms in medium-low priority traffic throughput, is stable and effective under different load conditions, is reasonable in extra time overhead of data packet transmission, and is widely applied to SDN network optimization data packet scheduling scenes.

Systems and methods for Data Loss Protection (DLP) utilizing distilled models include receiving a plurality of general data predictions from a teacher model; determining one or more strengths of the teacher model based on the received general data predictions; generating a synthetic dataset based on the one or more strengths of the teacher model; providing the synthetic dataset to the teacher model and receiving a plurality of synthetic data predictions from the teacher model based thereon; and performing knowledge distillation on a student model based on the synthetic data predictions received from the teacher model to produce a distilled model. The distilled model is then used in production for classifying inputs to a DLP system.

The invention discloses a project execution risk assessment system and method based on data mining, and relates to the technical field of project execution risk assessment, and the method specifically comprises the following steps: obtaining comprehensive data information related to project execution, and storing the comprehensive data information after obtaining; analyzing the stored comprehensive data information, evaluating an accumulated risk of dependency of each task chain in a project execution process, classifying each task chain in the project according to an evaluation result, identifying high-risk, medium-risk and low-risk task chains, and generating a corresponding risk evaluation report; according to the risk assessment report, advising a manager to take corresponding risk mitigation measures for task chains of different risk levels; and updating comprehensive data information in real time, periodically recalculating an accumulated risk assessment coefficient, and dynamically adjusting a risk assessment result. According to the method, the problem of accumulative risk assessment of a complex dependent task chain is solved, and the effects of accurate classification management and dynamic risk adjustment are achieved.

The invention provides a sewage treatment operation cloud platform based on Internet of Things and GIS, and the platform is characterized in that a data collection layer is used for obtaining user water consumption data and sewage pipe network data, and distributing all the data to each edge calculation node; the data storage layer is used for temporarily storing the data preprocessed by the edge computing node into a high-frequency storage chain, aggregating to obtain sewage pipe network comprehensive data, and permanently storing the sewage pipe network comprehensive data into a low-frequency storage chain; the data analysis layer is used for extracting sewage pipe network comprehensive data in the low-frequency storage chain, constructing a multi-dimensional dynamic GIS model by utilizing a GIS system, analyzing and predicting the multi-dimensional dynamic GIS model through a sewage treatment rectification analysis model, and generating a sewage treatment rectification plan of the sewage pipe network according to an analysis and prediction result; and the application service layer is used for acquiring all the sewage treatment and rectification plans and distributing all the sewage treatment and rectification plans to a management client held by a sewage pipe network manager. The sewage treatment device has the effect of efficiently and intelligently realizing sewage treatment.

The invention discloses a lithium ion battery health state estimation method and system, a medium and equipment, and the method comprises the steps: enabling each client of a battery mechanism participating in collaborative modeling to extract a health factor based on the original data of local battery monitoring, constructing and training a deep convolution generative adversarial network, and obtaining local synthetic data; each client uploads the local synthetic data to a central server, and the central server aggregates the local synthetic data of each client to form global synthetic data and distributes the global synthetic data to each client; each client carries out federated transfer learning training based on local data and the global synthesis data, uploads a local model to a central server after local training is finished, carries out dynamic weighted aggregation to form a global model and issues the global model, and the local training and federated aggregation are continuously and iteratively executed until the whole training process is finished; and each client carries out personalized fine tuning on the global model based on local data to realize estimation of the health state of the battery.

The invention discloses a computer memory bank fault prediction method and system based on deep learning, and relates to the technical field of computer hardware fault diagnosis, and the system comprises a multi-source time sequence data collection module which is used for obtaining memory bank operation state data in real time; the dynamic feature enhancement module is based on a composite architecture of a generative adversarial network and transfer learning, comprises a fault mode generator, and generates synthetic data consistent with real fault distribution by using an LSTM network; aligning feature spaces of different hardware platforms through a maximum mean difference loss function; the multi-modal fusion deep learning model comprises a space-time convolutional network, a graph attention network and an adaptive weight adjustment mechanism; and the fault early warning analysis module is used for analyzing a fault probability predicted value, an interpretable thermodynamic diagram and a maintenance suggestion. According to the invention, passive maintenance is changed into active prevention and control, and preposition and precision of fault management are realized through dual mechanisms of long-term trend prediction and short-term risk early warning.

Systems and methods are for mitigating hindsight bias related to designing and using artificial intelligence models for outlier events. More specifically, systems and methods for the use of synthetic data in the training and / or validation of model predictions in order to prevent overfitting and generate predictions that attempt to predict the unpredictable.

The present application relates to the field of behavior recognition technology, and discloses a behavior recognition method, device, equipment, storage medium and computer program product, including: obtaining multi-source heterogeneous data collected by a multimodal sensor network, and performing spatiotemporal synchronization and fusion processing on the multi-source heterogeneous data based on a spatiotemporal synchronization algorithm to obtain target comprehensive data; extracting low-dimensional feature vectors from the target comprehensive data, and combining the attention mechanism to perform time series modeling on the low-dimensional feature vectors to construct a behavior dynamic model; performing behavior recognition on the real-time collected operation process information according to the behavior dynamic model, and outputting the personnel behavior category. By integrating multi-source heterogeneous data in the complex environment of the power plant, and accurately extracting key features, and capturing the dynamic change laws of behavior and state, the model can accurately distinguish various types of personnel behaviors under normal operating procedures or complex and changeable working conditions, and realizes real-time and accurate recognition of violations and abnormal behaviors in power plant operations.

Techniques for determining a presence of an object, especially an object such as animal or debris, in a path of a vehicle, are discussed herein. For example, sensors of various modalities, which may include multispectral sensors, may capture data representing an environment the vehicle is traversing. In examples, one or more trained machine learned (ML) models, operating on a vehicle computing system, may detect and / or classify objects in the environment, based on input data of one or more modalities or spectral bands. The ML models may be pre-trained using training data including real sensor data, synthetic data, and / or augmented data, along with auto-generated annotations. In some examples, hyperspectral data may be used to identify materials associated with detected objects. A confidence score associated with the detection of the object may also be computed. The vehicle may be controlled based on detection of the object and its classification.

The invention provides a multi-data fusion fire-fighting early warning method and platform, and relates to the technical field of fire fighting, and the method comprises the steps: collecting a multi-dimensional environment data set of a target region; performing noise filtering on the multi-dimensional environment data set to obtain a multi-dimensional environment de-noised data set; comprehensively analyzing the plurality of data sources based on the multi-dimensional environment de-noised data set to generate fire-fighting comprehensive data, and fusing the multi-dimensional environment de-noised data set to obtain a multi-dimensional environment fused data set; building a fire risk model according to the fire-fighting comprehensive data, synchronizing the multi-dimensional environment fusion data set to the fire risk model for evaluation according to a plurality of data sources, and obtaining a fire risk level of the target area; and generating a fire-fighting early warning instruction based on the fire risk level, and sending the instruction to the remote control terminal. According to the method, the technical problem that a traditional fire early warning method is single in monitoring means and is easily interfered by environmental factors to cause false alarm or missing alarm is solved, and the accuracy and response speed of fire early warning are remarkably improved.

The invention relates to the technical field of wind field simulation, and provides a wind field numerical simulation method based on multiple meteorological data sources. The objective of the invention is to solve the problems of large simulation error, rough terrain boundary processing and poor turbulence model parameter adaptability caused by non-uniform coverage of a single data source, insufficient precision and unscientific multi-source fusion. The method is characterized by comprising the following steps: step 1, constructing a CFD three-dimensional grid based on a geometric model of a target area; 2, collecting original data of a ground station, satellite remote sensing, numerical forecasting and the like; 3, performing standardized preprocessing (abnormal value elimination, missing interpolation, radiation / geometric correction and resampling), determining a multi-source fusion weight by combining historical data analysis, and generating comprehensive meteorological data by adopting a weighted average method; and 4, inputting the comprehensive data into a CFD-RANS model, dynamically adjusting turbulence parameters, accurately setting terrain boundary conditions, and obtaining a wind field space-time distribution result through numerical solution. According to the invention, through combination of multi-source data fusion and CFD simulation, the wind field simulation precision and stability are improved.

The invention relates to a power system scheduling method and device based on multi-modal data fusion. The method comprises the following steps: acquiring multi-modal data of a power system, wherein the multi-modal data comprises power grid topology data, meter information, wind and light energy output prediction data, maintenance plan text data and energy comprehensive data; performing feature extraction, space-time alignment processing and hierarchical attention learning on each modal data to obtain a fusion feature vector; training the scheduling model by using the fusion feature vector until a total loss function meets a preset condition, the total loss function comprising a power flow equation constraint term; the method comprises the following steps: acquiring real-time multi-modal data of a power system, and obtaining a real-time fusion feature vector through feature extraction, space-time alignment processing and hierarchical attention learning; and inputting the real-time fusion feature vector into the trained scheduling model to obtain a real-time scheduling decision, and scheduling the power system according to the real-time scheduling decision. The method can improve the dispatching precision of the power system.