1152 results about "Data selection" patented technology

An adapter layer may be used to customize a machine learning component by transforming data flowing into, out of, and / or within the machine learning component. The adapter layer may include a number of neural network components, or “adapters,” configured to perform a transformation on input data. Neural network components may be configured into adapter groups. A router component can, based on the input data, select one or more neural network components for transforming the input data. The input layer may combine the results of any such transformations to yield adapted data. Different adapter groups can include adapters of different complexity (e.g., involving different amounts of computation and / or latency). Thus, the amount of computation or latency added by an adapter layer can be reduced for simpler transformations of the input data.

Systems, methods, and computer-readable media for autonomous agents are disclosed. The autonomous agent can include one or more processing circuits configured to receive or identify a dynamic data structure comprising one or more functions or one or more frameworks for performing a plurality of cyber resilience operations. The processing circuits can register the autonomous agent with a decentralized network, centralized network, or data source (DNCNDS). The processing circuits can receive or identify, from at least one computing system external or internal to the DNCNDS, cyber resilience data. The processing circuits can perform, in real-time, the at least one cyber resilience operation of the plurality of cyber resilience operations based at least on selecting at least one function of the one or more functions of the dynamic data structure based at least on the cyber resilience data.

The invention relates to the technical field of three-dimensional imaging, and discloses a high-precision underwater structured light three-dimensional point cloud imaging method and system, and the method comprises the following steps: deploying a plurality of sensor nodes, monitoring the temperature, salinity and turbidity key parameters of a water body in real time, selecting proper light source wavelength and power according to the collected data, and carrying out the three-dimensional point cloud imaging of the underwater structured light. It is ensured that the optimal signal-to-noise ratio is obtained under the current condition, and meanwhile the exposure time and gain setting of the camera are initialized. According to the method, the optimal signal-to-noise ratio is obtained by monitoring water body conditions in real time and dynamically adjusting light source characteristics, the optimal structured light pattern is predicted by using a machine learning model, scattering noise is removed, advanced registration and fusion algorithms and an accurate phase unwrapping method are applied, and a high-quality comprehensive structured light pattern is generated. Point cloud gaps are filled through a geometric correction algorithm and an interpolation / filtering algorithm, so that a reconstruction model is closer to the surface of a real object.

The invention relates to the technical field of medical data analysis and processing, in particular to a medical scientific research auxiliary method and system based on a large model, a terminal and a medium, and the method comprises the steps: extracting theme meanings based on a natural language processing technology, sending retrieval requests to a plurality of medical literature databases based on the theme meanings, and returning retrieved related literatures; performing feature extraction on the related literatures, classifying the related literatures, and generating a literature review; determining an experiment type based on related literatures and medical knowledge maps in combination with the research problem and an expected target, determining an experiment process and an input demand, obtaining a precise search condition in combination with the input demand, and obtaining corresponding research data based on the precise search condition; a corresponding analysis method is selected for analysis processing, and an analysis result is obtained; and generating a preliminary framework of the thesis based on research data, analysis results and literature review in combination with a standard structure template. The efficiency and quality of medical scientific research are effectively improved, the cost is reduced, and the intelligence and systematicness of scientific research are enhanced.

The invention relates to the technical field of industrial automatic detection and computer vision, in particular to a complex workpiece high-precision defect detection method based on a dynamic light source and multi-dimensional detection, which comprises the following steps: performing multi-dimensional data acquisition on a complex workpiece by using high-precision laser scanning equipment; working parameters of the workpiece are adjusted according to characteristics of the workpiece and environmental changes, and the image acquisition process is optimized; performing data preprocessing on three-dimensional coordinate data obtained by laser scanning and texture information obtained by structured light projection; respectively extracting geometric features, texture features and depth defect features of the workpiece from the preprocessed data; acquiring sample data from the database, selecting and optimizing a proper deep learning model, training the model by using the sample data, and constructing a defect detection model; and inputting the data subjected to preprocessing and feature extraction into a defect detection model, and detecting the defect degree of the workpiece.

The invention discloses an engine residual service life prediction method and system based on space-time state selection, and belongs to the field of equipment residual service life prediction. According to the method, multiple technologies such as a time sequence-space double-branch coding and hierarchical fusion mechanism, a selective state space model, a cross-layer residual jump connection and parameter sharing mechanism and an efficient self-attention mechanism are integrated, and an STSSFormer network model is constructed to predict the residual service life of the aero-engine; the system mainly comprises a data selection and preprocessing module, an input sample construction module, a model training module and a residual service life prediction module. According to the method, the feature expression and fusion capability is comprehensively enhanced, and the method has remarkable advantages in the aspects of prediction accuracy of the remaining service life, model robustness and engineering practicability.

The invention provides a teacher teaching ability analysis method and system based on multi-modal data fusion. The method comprises the following steps: acquiring multi-modal data in a teaching process of a teacher, wherein the multi-modal data comprises video, audio and text data; and after preprocessing the data, selecting a matched AI model for analysis according to the data, and generating an evaluation result of the teaching ability of the teacher. Evaluation is based on a plurality of first-level indexes, and comprises lesson mark and teaching material interpretation, teaching design implementation, teaching reflection evaluation, technology fusion teaching and teaching effect evaluation. The system integrates and analyzes multi-modal data by using a cross-modal attention mechanism, and maps teaching behavior characteristics to a multi-dimensional evaluation index. And providing personalized improvement suggestions according to the evaluation result, and regularly collecting and updating data to realize dynamic optimization of the teaching scheme. Through big data analysis and multi-modal fusion, teacher teaching ability evaluation is automatically generated, a teaching improvement scheme with high adaptability is provided, and the teacher teaching effect is effectively improved.

The systems and methods disclosed herein generate responses using data retrieved by validating vector embeddings using hash signatures. An output generation request is received via a computing device and includes an input that includes a content set and a command set. The content set includes data chunks, which refers to text, audio, image, and / or video data. A subset of the data chunks that fail to associate with existing hash signatures are selected. Each selected data chunk is validated against predefined constraints that define the operative boundaries of a guideline set and subsequently assigned a unique hash signature to indicate a degree of satisfaction of the data chunk with the guidelines. Using an artificial intelligence (AI) model, a response to the output generation request is generated in accordance with the data chunks, where each data chunk is associated with a corresponding unique hash signature.

The invention discloses an automatic leveling method for intelligently controlling an underwater leveling machine. The method comprises the following steps: acquiring real-time attitude data and working surface flatness requirements of a plurality of execution mechanisms of the underwater leveling machine, and constructing state and operation action information characteristics; an execution mechanism is mapped into an agent with a body, information is shared through an underwater acoustic communication network, and each agent selects and executes a leveling action based on self and neighborhood interaction data; after execution, obtaining a reward value, storing the reward value in an experience pool, sampling and updating the state-action function, and performing iterative training to obtain a multi-body agent reinforcement learning optimization model; continuously monitoring the state of a mechanism when the model runs, dynamically updating the features of an affected area when a fault or hydrodynamic abnormality is identified, and recalculating a leveling strategy to obtain a dynamic re-planning scheme; the scheme is combined with model output to generate a real-time leveling instruction sequence, and the real-time leveling instruction sequence is decomposed and then issued to each execution mechanism, so that self-adaptive accurate leveling control of the underwater leveling machine is realized, and the working efficiency and reliability of a complex underwater environment are effectively improved.

Implementations relate to generating a plurality of training instances to train a generative model in performing tasks using external tool(s) / service(s) accessible via corresponding API(s). The plurality of training instances each includes a synthetic natural language user instruction and execution step(s) to perform a task (e.g., a single-API task or a multi-API task) specified in the synthetic natural language user instruction. The synthetic natural language user instructions selected for the synthetic training data can be generated based on processing textual prompt(s) using a first LLM, where the textual prompt(s) can each include a list of APIs and associated API documents, one or more seed examples, and a request to synthesize a natural language user instruction. The one or more execution steps for a corresponding synthetic natural language user instruction can be generated based on parsing the corresponding synthetic natural language user instruction using the first LLM or a second LLM.

The invention relates to a seabed sand wave and pipeline interaction numerical simulation method and system and a readable medium. The method comprises the following steps: selecting a sub-model under an environment dynamic simulation model according to environment data; selecting a sub-model under the sediment transportation simulation model according to the seabed sediment data; whether a fatigue stability simulation model needs to be carried out is selected according to the pipeline type, if the pipeline is a rigid pipeline, the fatigue stability simulation model is not started, and otherwise, the fatigue stability simulation model is started; starting a sub-model of the protection and treatment simulation model; determining a computational domain of a numerical simulation model, adjusting grid boundary conditions through an environment dynamic simulation model, and combining all selected models to form a final numerical simulation model; and inputting to-be-tested material parameters and environmental parameters into the final numerical simulation model to obtain a seabed sand wave and pipeline interaction numerical simulation result. According to the method, a numerical simulation result which better conforms to the dynamic change process of the sand waves in a real environment can be obtained, and the dynamic change of the seabed sand waves can be better understood and predicted.

A method for selecting training data for training a deep learning model is provided. The method includes steps of: (a) obtaining one or more individual attributes each of which corresponds to each of a plurality of training data included in total training data, and generating a bipartite graph by matching each of the plurality of training data included in the total training data with the individual attributes; and (b) selecting n training data among the total training data, by referring to the bipartite graph, wherein the n is a target number of the training data to be used for training the deep learning model, and wherein the training data selecting device selects the n training data to be used for training the deep learning model such that each cardinal number of each of the individual attributes matched with the n training data is within a predetermined deviation threshold.

The invention discloses an interactive English teaching method, which comprises the following steps: S1, constructing a virtual learning environment by using a virtual reality technology, S2, comprehensively evaluating the English levels of students through an artificial intelligence algorithm, and generating a personalized learning path for each student according to an evaluation result; s3, constructing interactive learning activities and feeding back the interactive learning activities in real time, S4, collecting and analyzing interactive learning activity data of students, selecting and establishing online communities, and issuing cooperative learning tasks in the communities; s5, collecting learning data of the students in all the learning paths, and analyzing the learning data; and S6, according to a learning data analysis result, a teaching strategy is adjusted in time. The virtual reality technology and the artificial intelligence technology are combined, brand-new, personalized and immersive English learning experience is provided for students, and the English teaching quality and the learning effect of the students are expected to be remarkably improved.

The invention relates to the technical field of computers, in particular to a multi-path routing system and system based on traffic prediction, and the system comprises a traffic prediction module which is used for obtaining historical data of network traffic; predicting the network flow in a period of time in the future based on the historical data; the route selection module is in communication connection with the traffic prediction module and receives predicted traffic data sent by the traffic prediction module; a plurality of paths meeting the bandwidth requirement are selected for data transmission; the data transmission module is in communication connection with the route selection module and executes data transmission according to the multiple paths selected by the route selection module; the network monitoring module is in communication connection with the data transmission module and monitors data traffic in a network in real time; sending the real-time flow data to a routing selection module; the route adjustment module is in communication connection with the route selection module and the network monitoring module and is used for receiving the real-time flow data sent by the network monitoring module; and dynamically adjusting the path selected by the routing module based on the real-time flow data.

A video editing system leverages a generative artificial intelligence (AI) model to identify songs to overlay on a video. The video editing system extracts a set of key frames from the video and prompts the generative AI model to generate a video narrative for the video. A video narrative is a text description of the plot, theme, feel, or other characteristics of the video. The video editing system uses the video narrative to prompt the generative AI model again to generate a set of descriptor tags for the video based on the video narrative. Descriptor tags are strings that represent themes, features, or characteristics of the song. The video editing system uses an audio tagging system to score a set of songs based on the set of descriptor tags and presents a selected subset of the set of songs based on the scores of the songs.

The invention relates to the technical field of large language models, and provides a user preference oriented instruction tuning data selection method, which comprises the following steps of: performing supervision and fine tuning on a pre-trained large language model to obtain a supervision and fine tuning large language model; constructing a preheating preference data set optimization supervision fine tuning large language model; generating a basic candidate response of the verification instruction through a basic candidate model, and generating a preference candidate response of the verification instruction through a preference candidate model; performing evaluation according to the evaluation model, and constructing a preference pair set according to an evaluation result; calculating a preference gradient by using a preference loss function to obtain a bidirectional user preference gradient; and scoring the training data, selecting a training data set according to the score, and performing fine tuning on the direct preference large language model to obtain an optimized large language model. According to the method, the matching degree of the selected data and the target task can be remarkably improved, and the generalization ability of the instruction fine tuning model on the target task is improved.

The invention relates to a remote sensing data coverage screening method based on a profit value, relates to the technical field of remote sensing image data processing, and solves the technical problems of insufficient region coverage optimization, serious computing resource waste, lack of flexible screening strategies and the like in the prior art. The method comprises the following steps: step 1, preparing a data set; 2, checking attributes of the data set; and step 3, performing a region coverage algorithm. According to the remote sensing data coverage screening method based on the profit value, by designing a coverage algorithm and introducing an image quality control and consistency guarantee mechanism, the efficiency and accuracy of remote sensing image data selection are remarkably improved. According to the method, the storage and calculation burden of redundant images can be reduced, the efficiency of image coverage is maximized, and the accuracy and consistency of global earth surface coverage are ensured.

The invention relates to the technical field of image processing, and particularly discloses a high-quality video reconstruction method based on electroencephalogram signals, which comprises the following steps: preprocessing electroencephalogram data, down-sampling video frames, and segmenting the electroencephalogram data by using a sliding window technology; selecting a channel with high correlation with video reconstruction; electroencephalogram time features are extracted; electroencephalogram space-time features are extracted; electroencephalogram time-frequency features are extracted; the electroencephalogram time-space-frequency features are fused; extracting the category and semantic information of the electroencephalogram; adopting a comparative learning method to align electroencephalogram-text-picture features; generating a reference video frame by using a stable diffusion model; and generating a high-quality video by using the video diffusion model. According to the method, the information of electroencephalogram features is further deeply extracted, the semantic content of the video is remarkably enhanced, meanwhile, the introduced video diffusion model gradually constructs a clear and natural picture through a step-by-step denoising process, the consistency between video frames is remarkably improved, and therefore the high-quality video rich in details is generated.

The invention relates to a monitoring method and system for the full life cycle of a transformer substation project, and the method comprises the following steps: deploying an unmanned plane automatic airport to collect environment data, and selecting a transformer substation project construction site according to the actual construction demands and the environment data; modeling the power generation and transformation project based on the monitoring data of the power generation and transformation project construction site, and constructing a hidden danger sample library; constructing an intelligent monitoring system which comprises a hidden danger recognition module, an expert rechecking module and a decision generation module; wherein the hidden danger identification module performs hidden danger identification by using an improved YOLOv8n network to obtain a hidden danger target; the improved YOLOv8n network is specifically characterized in that a convolution attention module and an adaptive feature fusion module are embedded in a backbone network; the hidden danger target passing through the expert rechecking module is input into a decision generation module, and a hidden danger decision is generated and issued to an unmanned aerial vehicle automatic airport; the unmanned aerial vehicle automatic airport receives and controls the unmanned aerial vehicle to execute the hidden danger decision.

The invention relates to the technical field of language model integration, in particular to a large language model integration method supporting semantic correction. The method comprises the following steps: S1, selecting several large language models, and sorting and preprocessing text data for training and testing; s2, training each source model and an optimization model by using an intelligent fusion language model technology; s3, fusing parameters of each source model by using an intelligent fusion language model technology, selecting model parameters for fusion according to the text data, and adjusting the fused model; s4, evaluating the semantic correction capability of the fused model, and adjusting a fusion strategy and regularization parameters according to an evaluation result; and S5, integrating the trained model into a target system. According to the large language model integration method supporting semantic correction, through an intelligent fusion language model technology, a context sensing and hybrid regularization technology is utilized to train and optimize a model and enhance adaptability, and a FuseLLM fusion technology is adopted to merge all source model parameters.

The invention discloses a personalized acupuncture treatment scheme recommendation method and system based on data analysis, and relates to the technical field of acupuncture. The method comprises the following steps: constructing a feature vector matrix according to multi-dimensional feature data of a target patient; taking the matrix as a constraint, retrieving similar historical cases in a pre-constructed acupuncture case database, and obtaining a sample case set and a similarity set; configuring a data selection strategy based on the similarity set, constructing a sample training set, and training to generate an acupuncture parameter evaluation plug-in; and defining an acupuncture parameter optimization space based on the sample case set, performing iterative optimization in the space by using the evaluation plug-in, and finally outputting an acupuncture treatment parameter scheme adaptive to the target patient. According to the method, the whole-process personalized recommendation of the acupuncture treatment scheme from case screening, model evaluation to parameter optimization is realized, and the accuracy, objectivity and clinical operability of treatment are improved.

The embodiment of the invention provides a snow depth inversion method and system based on a random forest. The snow depth detection method is applied to the technical field of snow depth detection, and comprises the following steps: selecting an acquisition area, acquiring snow depth data in a predetermined acquisition area, and preprocessing to obtain processed data; selecting a prediction variable and a target variable, training the random forest model to obtain a trained random forest model, and performing precision verification; and inputting snow depth data acquired in real time into the trained random forest model, performing snow depth prediction, and outputting to obtain a prediction result. In this way, active microwave high-resolution snow depth data and passive microwave inversion of the mountain snow depth are combined, and Sentinel-1 inversion snow depth data are taken as a training target, so that the inversion precision of the mountain snow depth is improved.

The invention discloses a server cluster load balancing cooperative processing system and method and electronic equipment, and relates to the technical field of servers, and the method comprises the steps: receiving node operation data sent by each edge node in a region; carrying out load prediction in the region according to the node operation data and a pre-trained neural network model to obtain a prediction result; determining a dynamic scheduling weight; solving calculation is carried out according to the multiple pre-stored node mapping schemes, preset solving parameters and a pre-established target function, and a multi-target Pareto solution set is obtained; performing preferential processing according to the Pareto solution set and the dynamic scheduling weight to obtain a target node mapping scheme; and according to the target node mapping scheme, controlling each edge node in the region to execute load balancing cooperative operation. The problem that the load balancing performance of the server cluster is poor is solved, and the server load balancing performance of the server cluster is improved by selecting a proper target node mapping scheme based on the node operation data collected by each edge node of the edge layer.

The invention relates to the technical field of data backup, and discloses an iOS device data backup and recovery method and system, and the method comprises the steps: carrying out the SSL certificate verification and EscrowBag key authentication of an iOS device, and obtaining a data path list; according to the data path list, parallel scanning of APFS file system B-Tree traversal, NAND flash memory page reading and SQLite WAL log analysis is carried out on the iOS device storage partition, and an original data set is obtained; performing integrity evaluation based on the original data set to obtain an effective data set and constructing a virtual file index; the data selection list of the user is confirmed based on the virtual file index, safety recovery is executed, and a data recovery result is returned. The SQLite page Cell reconstruction and fragment file signature matching technology is combined, intelligent repair and quality prediction can be conducted on damaged data, the user experience and operation efficiency are improved, and the user experience is improved. And the security and the reliability in the data recovery process are ensured.

A system may include a robotic control circuit configured to control one or more robotic functions of a robot. A system may include a plurality of sensors configured to collect data. A system may include a governance analysis circuit configured to analyze the data and select one or more governance frameworks based on the analyzed data. A system may include a governance model circuit configured to generate a model that applies the one or more governance frameworks to determine one or more governance actions, wherein the robotic control circuit is configured to control the one or more robotic functions in accordance with the one or more governance actions, wherein the robotic control circuit, the governance analysis circuit, and the governance model circuit are integrated on a single substrate.

The invention is suitable for the technical field of computers, and provides an SATD identification method based on a query strategy combining representativeness and uncertainty, and the method comprises the following steps: data preprocessing and representation; constructing an initial training set; data selection based on a query strategy; stopping training; and analyzing a result. According to the method, the SATD recognition model trained on the basis of the BERT model is superior to an original method in F1 score index; a representative and uncertainty combined query strategy and an active learning method are adopted, a model with excellent performance can be obtained only by training part of data rich in information amount, and the manpower labeling cost is greatly reduced; the specific value of the number of all marked SATD annotations to the number of SATDs in all training sets serves as a stop threshold value, and flexible strategies are provided for different application scenes so as to obtain different SATD recognition models. According to the method, the SATD in the code annotation can be accurately and efficiently identified under the condition of using less data and label cost.

The invention discloses a self-adaptive time sequence control circuit and method applied to an SRAM (Static Random Access Memory), relates to the technical field of integrated circuits, and aims to solve the problem that the traditional SRAM time sequence control circuit easily causes unstable performance of the SRAM under different temperature conditions. The adaptive time sequence control circuit comprises a temperature compensation code generation circuit and a time sequence compensation circuit. The time sequence compensation circuit at least comprises a delay chain circuit, a first AND gate and a second AND gate; the output end of the first AND gate is connected with the data input end of the delay chain circuit and the first input end of the second AND gate, the data selection end of the delay chain circuit is connected with the output end of the temperature compensation code generation circuit, the output end of the delay chain circuit is connected with the second input end of the second AND gate, and the output end of the second AND gate is connected with the SRAM. The self-adaptive time sequence control circuit applied to the SRAM is used for improving the performance stability of the SRAM under different working temperature conditions.

The invention discloses an adjusting and optimizing filtering method and system for a petroleum filtering device, and relates to the technical field of petroleum filtering, and the method comprises the following steps: initially checking and establishing a petroleum feature set; and inputting the petroleum feature set into a filter screen setting model to generate a filter screen configuration result. And key adjustment parameters of the petroleum filtering device are established. Big data is called through a petroleum feature set, a fitness function is constructed, data selection is performed based on the big data and in-plant control data, and a solution space and an initial solution set are established. And evaluating the initial solution set based on a fitness function, performing iterative screening, and establishing an optimal solution identifier and an inferior solution identifier. And performing initial solution set reproduction and solution space variation through optimal solution and inferior solution identification, and executing initial solution set iteration. And generating an optimization result according to the iteration result, and performing tuning filtering treatment according to the filter screen configuration result and the optimization result. Therefore, the technical effects of improving the adaptability of the petroleum filtering device and improving the filtering efficiency are achieved.

The invention relates to a turbine blade cooling optimization method and device based on non-Newtonian fluid. Comprising the following steps: step 1, carrying out grid division and simulation processing on a three-dimensional geometric model of the micro-channel of the turbine blade containing a shear groove to obtain a simulation grid model; 2, on the basis of the simulation grid model, determining a non-Newtonian fluid constitutive model suitable for the simulation grid model, and associating the non-Newtonian fluid constitutive model to the simulation grid model to obtain a fluid characteristic grid model; step 3, calculating index data based on the fluid characteristic grid model and the target equation; 4, adjusting the structure parameters of the shearing grooves in the simulation grid model, repeatedly executing the step 1 to the step 3 according to the adjusted structure parameters of the shearing grooves, and recording index data corresponding to the structure parameters of each group of shearing grooves to obtain a candidate data set; and 5, selecting the structure parameter of the shear groove with the comprehensive optimal resistance performance and heat transfer performance from the candidate data set according to the index data, and taking the structure parameter as an optimized target shear groove parameter.

The invention discloses a multi-modal document automatic proofreading method and system based on artificial intelligence, and relates to the technical field of data processing, and the method comprises the steps: receiving an original document, and converting the original document into structured data composed of a plurality of data of different formats and types; according to the data of each format type, selecting a corresponding check model to check the structured data to obtain a difference item corresponding to the data of each format type; determining a risk level corresponding to each difference item through a preset quality grader; and correcting each difference item according to each risk level. According to the method and the device, the corresponding verification models are selected to verify the structured data through the data of different formats and types in the structured data, the risk level of the difference item obtained through verification is determined through the preset quality classifier, and the difference item is corrected based on the risk level, so that automatic correction of the structured data is realized; and compared with a manual proofreading mode, the proofreading efficiency is effectively improved.