25 results about "Extensive data" patented technology

The invention belongs to the field of artificial intelligence, and particularly relates to a disaster risk early warning algorithm based on multi-modal fusion and a space-time propagation model, which comprises a multi-modal data management module, a cross-modal semantic alignment module, a space-time propagation graph modeling module, a propagation constraint deduction module, a graded early warning generation module and an online closed-loop calibration module. Depth alignment of multi-modal data on a semantic level, dynamic deduction of a disaster propagation process under constraint of a physical mechanism and operable conversion of an early warning result in a business scene are realized, and the whole system takes a unified space-time framework as a base, takes a propagation graph as a link and takes closed-loop calibration as a guarantee, so that the accuracy of the system is improved. The structural defects of extensive data splicing, propagation modeling deficiency and decision chain fracture in a traditional early warning method are fundamentally overcome.

This invention belongs to the field of equipment life prediction technology, and discloses a method and related apparatus for predicting the remaining life of a photovoltaic inverter. The method includes: acquiring junction temperature data of the IGBT modules in the photovoltaic inverter under test; determining the number of junction temperature thermal cycles of the IGBT modules in the photovoltaic inverter under test based on the junction temperature data; calculating the cumulative damage of the IGBT modules in the photovoltaic inverter under test based on the number of junction temperature thermal cycles; and calculating the remaining life prediction result of the photovoltaic inverter under test based on the cumulative damage of the IGBT modules. This invention can more accurately predict the remaining life of the IGBT modules, and thus more accurately predict the overall remaining life of the photovoltaic inverter. The prediction process does not require extensive data collection and training of the prediction model, effectively reducing the difficulty of life prediction and improving prediction efficiency.

Systems and methods ingest extensive data regarding parties and contextual data to determine correlation between a variety of data types, parameters related thereto, and member service representative (MSR) contact events and corresponding staffing levels. The appropriate level of staffing, based on real-time and historical context to meet demand for calls, emails, messages, and other contact or servicing can be calculated without overstaffing.

This invention discloses a deep learning-based orthodontic image classification model determination system, relating to the field of image data technology. The system includes a construction module for building an orthodontic data annotation library, comprising multiple tooth overlay models and multiple maxillary / mandibular overlay models, and for annotating orthodontic sample images according to the library. A training module, connected to the construction module, determines the feature information of the annotated orthodontic sample images, selects a deep learning model based on the feature information, and trains the selected deep learning model using the annotated orthodontic sample images to obtain a trained deep learning model. This invention enables data integration and annotation of numerous dental problems through the orthodontic data annotation library, achieving extensive data coverage and ensuring the accuracy and consistency of image annotation. It also enables rapid annotation of oral cavity-related images, improving the efficiency of orthodontic analysis.

This invention discloses an image-based method for detecting and reconstructing irregular strip-shaped objects, comprising the following steps: S1: image acquisition; S2: image preprocessing; S3: optimizing the network model; S4: setting network model parameters; S5: inputting the training set into the optimized network model for training, saving the trained weight file, and using the test set to test the model's segmentation effect on the target; S6: reconstructing branch segments. This method can effectively detect and segment branches with similar background colors, overlaps, and occlusions, without requiring extensive data statistics, and achieves high reconstruction accuracy.

The invention relates to the technical field of vocational education, in particular to a vocational education demand prediction system based on LSTM time sequence prediction and a dynamic adjustment method, and the system comprises a multi-source data collection module, a knowledge graph construction module, an intelligent data processing module, an LSTM-reinforcement learning prediction module, a dynamic adjustment module and an execution feedback module. According to the scheme, firstly, three types of data of industrial economy, post requirements and education and learning are integrated, a knowledge graph containing semantic and quantitative information is constructed, abnormal value recognition and missing value filling are optimized, and data suitability is improved; secondly, capturing time sequence dependence through bidirectional LSTM, optimizing model parameters in combination with knowledge attention and reinforcement learning, and achieving demand prediction; and finally, constructing a resource dynamic coefficient matrix, converting constraints into mathematical conditions to solve an optimal adjustment amount, and feeding back an optimization model and a map in real time, thereby effectively solving the problems of extensive data, prediction deviation and experience-dependent adjustment in the prior art, and realizing efficient matching of vocational education resources and demands.

The system provides real-time safety scores for motor carriers, accurately predicts future safety scores, and allows users to simulate various safety scenarios. Users can input data and perform complex calculations, ensuring accurate and timely updates of safety scores. The system's efficiency lies in accumulating and analyzing extensive data, leading to more precise predictions of future safety scores. The calculated, predicted, or simulated safety scores are presented on diverse devices such as desktop computers, mobile phones, or other compatible devices.

This invention discloses a fault-constrained Dal-UNet stratigraphic surface reconstruction method, applicable to the fields of information processing and oil and gas exploration. Existing deep learning reconstruction algorithms, based on supervised learning, require extensive data and manually labeled training data for pre-training, resulting in high economic and time costs. Data quality directly impacts algorithm performance, and in geological studies with relatively scarce data, supervised deep learning algorithms are prone to overfitting, making them even more difficult to apply directly to stratigraphic surface reconstruction tasks involving complex geological structures with faults. This invention utilizes the Dal-UNet network to capture hidden features from limited and sparse stratigraphic surface data and combines it with a fault-constrained algorithm to reconstruct complex stratigraphic surfaces containing faults, effectively restoring the true topography.

A method for achieving super-resolution in localizing electrical fields measured at the head surface with electroencephalography through a generative model of the cerebral cortex that has a very high resolution of cortical surface dipoles constructed from the known properties of human cerebral cortex and adapted to optimize the Bayesian explanation the individual's cortical surface electrical fields. The iterative optimization of the prior (generative) with the posterior (observed) fields with extensive data from extended recordings provides a probabilistic estimation of the individual's functional brain activity that can be used to train artificial neural network approximations of the individual's mental activity.

The invention discloses a power system data acquisition system which comprises a data acquisition module, a data storage module, a data processing module, a data transmission module, a data analysis module and a data application module. The power system data acquisition system based on the big data has the characteristics of high efficiency, accuracy, real-time performance, stability, safety and the like, can provide powerful support for intelligent upgrading and optimization of a power system, is expansion and upgrading of a traditional data acquisition system, can process wider data sources, and has wide application prospects. And data values are mined by using a big data analysis technology, so that more powerful decision support is provided for safe, economic and efficient operation of a power system.

The invention belongs to the technical field of laser precision machining and intelligent manufacturing, and particularly relates to a laser machining parameter transfer learning method, system and equipment and a medium, and the method comprises the following steps: S1, specifying a machining requirement, and inputting known physical characteristics and an initial laser parameter range of a to-be-machined material; s2, establishing a basic model library containing a multi-physics field coupling model, and constructing a laser parameter-electronic dynamics-processing result mapping database based on historical experimental data and model simulation results; and S3, based on the physical model library and the mapping database, training a machine learning or deep learning model as a prediction model. According to the method, a multi-physics field coupling model and a data driving model can be fused, the interpretability of the model is ensured by utilizing a physical mechanism, and the prediction precision is improved through mass data training; and the three-stage feedback mechanism realizes real-time adaptive adjustment in the machining process, so that the key index deviation of the machining result can be within an effective control range.

The invention provides a feature mixed cross view image matching method based on MambaVision. The images from the unmanned aerial vehicle platform and the satellite platform are matched, and the geographic position information carried by the images of the satellite platform is used as the current geographic position information of the unmanned aerial vehicle, so that the pure vision geographic positioning task of the unmanned aerial vehicle is realized. And inputting the unmanned aerial vehicle platform image and the satellite platform image into the same feature extraction network, and respectively extracting image features: regarding an image matching process as an image retrieval process, and calculating cosine similarity between the current unmanned aerial vehicle image and the satellite image library image through features to obtain a matching result. According to the method, a University-1652 data set is used for training and testing, and the data set is the most widely used data set in the field at present. Compared with other unmanned aerial vehicle cross-view geographic positioning methods based on deep learning, the method has the advantages of high precision, strong generalization and network lightweight.

This invention relates to the field of electrically excited synchronous motor technology, specifically to a method for rapidly estimating the initial position of a main motor based on estimated rotor current characteristic values, comprising: acquiring the three-phase rotor current of the exciter; acquiring the target rotor current of the exciter; acquiring the excitation current of the main motor; and acquiring the stator current. α shaft and β The invention obtains the variance of the excitation current of the main motor corresponding to the stator shaft; obtains the angle compensation value of the main motor rotor; and obtains the estimated initial position value of the main motor rotor. This invention accurately estimates the excitation current of the main motor and quickly estimates the initial position of the main motor rotor even when the initial position of the exciter is unknown, without requiring extensive data processing, thus simplifying the complexity of the initial position identification process for the main motor rotor.

The present invention provides a guided visual diagnostic system and method for use with medical devices. [Solution] When a technician discovers and reports a device malfunction, the diagnostic system automatically generates a diagnostic plan detailing the necessary parts, areas of interest, and actions to be taken. The perceptual module analyzes the technician's actions and recommends the next steps, guiding the technician using augmented reality (AR) indicators. The planning component creates the diagnostic plan using a knowledge graph (KG) and a large-scale language model (LLM), eliminating the need for extensive data labeling or model training. The tracking component enhances 3D detection using perceptual sensors and a 2D nested object detection model. The guiding component simplifies the process for novice technicians by integrating 2D models and AR interactions to ensure efficient and accurate diagnosis.

This invention discloses a wind speed prediction method and system based on Kalman filtering and LSTM, belonging to the field of wind power generation and wind energy prediction technology. The method includes: acquiring data from the wind turbine's SCADA system, including historical wind speed, wind direction, humidity, and temperature; preprocessing the acquired data, including data denoising and normalization, and using mutual information to filter out the required data; dividing the filtered input data into training and testing sets, and inputting them into an LSTM network for training, obtaining the optimal hyperparameters based on extensive data training and a Bayesian optimization algorithm; inputting the LSTM prediction results into the Kalman filter KF update equation, leveraging the optimal state estimation characteristics of the dynamic system using the KF update equation to correct instantaneous meteorological disturbances and inherent model biases in real time, and finally outputting the wind speed prediction result. This invention achieves high-precision wind speed prediction, facilitates real-time wind speed monitoring, and enables optimal control of wind turbine units.

The present application relates to a kind of internet big data extraction method, device, equipment and storage medium, comprising the following steps, to the distributed crawler collection of internet data source, obtain original network data, and it is converted into structured data matrix.Matrix is analyzed by multi-level semantics, construct semantic feature map, and carry out theme segmentation and classification, form theme domain knowledge tree.Further dig the association rules in knowledge tree, construct implicit knowledge network.Based on the network, query condition is carried out semantic decomposition and extension, generate extended query data, and with knowledge network similarity matching, obtain candidate data set.Finally, candidate data is sorted and extracted by multiple factors, output target data, solve the technical problem that existing system has large deviation when carrying out price prediction and maintenance cost analysis in second-hand car market due to extensive data source and semantic ambiguity.

The invention discloses a data acquisition optimization method, system and equipment, and belongs to the technical field of data processing. The method comprises the following steps: predicting expected utility of unacquired data based on analysis of acquired data; and dynamically distributing and collecting resources according to the utility. The analysis is based only on intrinsic characteristics of the data. The system correspondingly comprises a utility prediction device and a resource allocation device. According to the method, passive collection is changed into active screening through a core normal form of value pre-judgment driving dynamic scheduling, and resources can be preferentially allocated to high-value data in a prospective manner, so that resource waste is remarkably reduced, and the overall collection efficiency and the data quality are improved. The scheme does not depend on a specific implementation mode, is generally suitable for wide data acquisition scenes such as artificial intelligence and the Internet of Things, and is widely applied to scenes in which high-value data needs to be efficiently acquired from massive and heterogeneous data sources.

This invention proposes a tunnel blasting construction method, a fully computerized rock drilling rig, electronic equipment, and storage medium. The method includes: acquiring construction photos during actual construction, the photos containing the rock area; analyzing the construction photos based on a pre-built prediction model to output a borehole distribution map and charge information; and performing tunnel blasting construction according to the borehole distribution map and the charge information, ensuring that the over-excavation and under-excavation profiles after blasting are kept within a preset range. This invention obtains a prediction model based on extensive data training, and performs intelligent borehole layout and intelligent charge calculation based on rock information acquired before drilling. This enables blasting to achieve optimal blasting advance and over-excavation / under-excavation control effects with lower explosive costs and shorter drilling times, reducing reliance on operator experience, improving the control level of over-excavation and under-excavation, and reducing construction time and waste of subsequent wet spraying materials.

The application discloses a kind of filing file writing and reading method, device, terminal equipment and storage medium.The filing file writing method includes: receiving data file to be written;Index information corresponding to data file to be written is used to update the index file written in the tail of the archive file to obtain target index file;Target index file is written in the tail of the archive file, and data file to be written is appended to the data area of the archive file, when continuously adding data file, only data file is appended in the tail of the archive file, and the index file in the tail of the archive file is updated, without needing to modify the entire archive file, solve the problem that the mode of file archiving using ASAR archive file is not suitable for appending content in the archive file, provide a kind of support continuously appending write file archiving method, satisfy more extensive data archiving demand.

The invention discloses an implementation method of a self-attention residual attention mechanism applied to table data, the table data is one of data structures which are most widely applied at present, and a traditional processing method is mainly based on a tree model; and the migration ability of the deep learning can improve the model training efficiency, and training from the beginning is not needed. Therefore, the method is improved on the basis of a Transform model, the information content of original data is reserved through a residual attention mechanism, meanwhile, a simplified output header is adopted to reduce time consumption of model training and reasoning, and therefore performance and efficiency are remarkably improved. The method provides a new thought for modeling for reserving original information during deep learning processing of table data, and is expected to be widely applied to actual scenes.

Once a technician detects and reports an equipment failure, diagnostic systems and methods herein automatically generate a diagnostic plan, detailing necessary parts, areas of interest, and actions to be taken. Using augmented reality (AR) indicators, a system guides the technician while a perception module analyzes their actions to recommend next steps. A planning component uses knowledge graph (KG) and LLM to create the diagnostic plan, without requiring extensive data labeling or model training. A tracking component enhances 3D detections by employing perception sensors and a 2D nested object detection model. A guiding component simplified processed for novice technicians by integrating 2D models and AR interactions to ensure efficient and accurate diagnostics.

The invention relates to the technical field of data acquisition, in particular to a coal mine data acquisition method and system based on a script language. Based on the wide data source access capability of the data source layer, the universal problem of multi-source heterogeneous data acquisition is solved, and unified access of various data sources such as databases, industrial equipment, files, Web and message queues is realized; by means of a standardized template of a script library layer and a multi-language execution environment of a script engine layer, customization and iteration of collection logic are achieved, the problem that a traditional method is insufficient in flexibility and expandability is solved, and protocol changes can be adapted without compiling and publishing; through a unified task management and resource isolation mechanism of a scheduling layer and data circulation and quality enhancement of a unified data bus, high reliability and data quality of the system are ensured, and stable and efficient management and control of large-scale acquisition tasks are realized; the method breaks through the rigid limitation of technology type selection, and improves the efficiency, flexibility and controllability of coal mine data collection.

The application relates to a LWIP protocol stack expansion and multi-network card implementation method for spatial real-time network communication, and introduces a LWIP protocol stack and a LWIP_vlan protocol stack, wherein the LWIP_vlan protocol stack is obtained by adding a suffix vlan to all symbols in the source code of the LWIP protocol stack, modifying the LWIP protocol stack into the LWIP_vlan protocol stack, and then expanding the function of the LWIP_vlan protocol stack to support a VLAN label and a spatial real-time network function; the LWIP protocol stack and the LWIP_vlan protocol stack are integrated into the same software engineering, tasks are created, network card interfaces are added, threads for receiving and processing network data packets are created, and socket threads for providing network programming interfaces are created under the two protocol stack modes; for the LWIP_vlan protocol stack, a spatial real-time network function module is initialized, and the function of a low_level_output_vlan function is expanded, so that the two protocol stacks are simultaneously supported by the multi-network card. The application supports flexible switching modes, protocols and standards of the multi-network card, ensures accurate data transmission and reception, simultaneously supports various network cards and device types, and realizes more extensive data exchange and integration.

The invention discloses a low-stimulation anti-falling upper anterior tooth fixed parallel guide CAD / CAM customization method, which comprises the following steps of: obtaining upper anterior tooth lingual side local scanning data and occlusion records, and constructing a virtual tooth jaw model; designing a guide plate body completely attached to the tooth surface and a positioning cap and a connecting rod integrated with the guide plate body on the model; the integrated component is subjected to 3D printing through light-cured resin; the connecting rod and the positioning cap are removed by grinding after the connecting rod is directly placed in place and adhered to a dental surface clinically; according to the method, only the upper anterior tooth lingual key local morphology data and the occlusion height information need to be acquired through limitation, and the step of acquiring and processing complete three-dimensional data of the whole tooth in a traditional digital scheme is abandoned, so that the data acquisition and preprocessing process is greatly simplified, the data storage and calculation load is reduced, and the data processing efficiency is improved. Therefore, the starting point of the whole customization process is more efficient, and the problem of process complexity caused by wide data requirements is solved.

Embodiments of a system for determining a data gravity index score and implementing a wide range of data center architectures are disclosed. In some embodiments, the system can calculate a data gravity index score based on the amount of data stored at a given location, the amount of data in motion at the given location, a bandwidth index associated with the given location, and a latency index associated with the given location. Based on the data gravity index score, in some embodiments, the system can localize traffic to improve network performance, improve security operations, and create software-defined network overlays.