681 results about "Model selection" patented technology

An AI-enhanced distributed system for neural network-based data compression leverages reinforcement learning optimization and privacy-preserving computation across edge and central computing devices to autonomously optimize efficiency and quality. The system includes a lightweight compression subsystem at edge devices that applies privacy-preserving preprocessing and partially compresses input data before securely transmitting it to central computing devices. A reinforcement learning agent continuously monitors system performance and automatically optimizes compression parameters, model selection, and task allocation based on multi-objective rewards. The central compression subsystem processes data using AI-optimized parameters and temporal modeling components. The system incorporates hardware detection capabilities that automatically select optimal compression models based on available processing resources and implements homomorphic encryption for computation on encrypted data while coordinating federated learning across distributed devices. This AI-enhanced distributed approach improves bandwidth efficiency, energy consumption, and adaptability while ensuring data privacy and security.

The invention relates to the technical field of power station operation and maintenance, and discloses a power generation equipment intelligent operation and maintenance method and system based on model autonomous selection, and the method comprises the steps: obtaining the multi-mode operation and maintenance data of a photovoltaic power station, and generating a multi-mode operation and maintenance data set; inputting each modal data of the multi-modal operation and maintenance data set into a corresponding module for feature extraction; inputting the extracted feature vectors into a contrast learning network for cross-modal alignment, and outputting an executable decision result by combining a retrieval enhancement generation technology with a knowledge graph; and constructing a privacy protection training framework through federated learning, inputting an executable decision result into a digital twin system for strategy verification, and generating a trained multi-modal large model for the photovoltaic power station to select a corresponding module in the trained multi-modal large model based on the feature data for real-time monitoring. According to the invention, the problems of poor accuracy and untimely reaction in the traditional operation and maintenance process of the photovoltaic power station are solved, and the operation and maintenance of the power station can be carried out timely and accurately.

The invention discloses an anomaly detection model selection method and system based on index portraits, and relates to the technical field of intelligent operation and maintenance of power systems. The method comprises the following steps: collecting historical data of a target monitoring index, extracting multi-dimensional features to construct an index portrait, and classifying the index portrait; screening candidate anomaly detection models from the matching rule base, performing adaptation degree scoring in combination with a model compatibility evaluation mechanism, determining an optimal anomaly detection model to perform anomaly detection, and outputting an anomaly judgment result; when a plurality of models exist, generating a final abnormal result through a confidence-driven arbitration mechanism; for multi-index abnormity, causal reasoning is carried out in combination with an electric power knowledge graph, main alarm indexes are determined, and secondary indexes are processed according to a delay strategy; meanwhile, incremental updating of index portrait features, adaptive adjustment of model parameters and dynamic optimization of matching rules are supported, and a whole-process closed-loop mechanism covering'portrait construction-model matching-result fusion-alarm decision-feedback updating 'is constructed.

A system and method for optimizing automated textual prompts in artificial intelligence (AI) conversational systems is disclosed. The system comprises a network interface, processors, and memory-storing instructions for performing operations to optimize prompts. These operations include receiving and preprocessing input data, tokenizing the data, verifying data authenticity, performing temporal analysis, calculating prompt complexity scores, and selectively expanding or refining prompts based on complexity thresholds. The system further incorporates context-aware optimization, multi-faceted prompt refinement, variation generation, and evaluation using machine learning models. Additional features include a technological hub with advanced processing capabilities, sensor-augmented input apparatus, device-specific prompt optimization, AI model selection, multimodal context integration, and an AI-driven creativity booster. The system provides interactive prompt visualization, certification, and uniqueness verification modules. This comprehensive approach ensures the generation of optimized, contextually relevant, and creative prompts for various AI applications while maintaining data integrity and user engagement.

The invention relates to the technical field of natural language processing, and discloses a power generation industry data intelligent treatment method, device and equipment based on a large model, and the method comprises the steps: constructing a multi-source heterogeneous task data set covering structured and unstructured information, completing the fine tuning training of a plurality of industry sub-fields based on a language model, forming a large language model set with specific scene adaptability; constructing a multi-view semantic representation structure for actual input data, integrating modeling task intention, application scene and model adaptability, predicting an optimal target model and a Top-K candidate model, and generating a unified semantic embedding vector; and realizing accurate matching of the structured knowledge fragments through the graph neural network. The problems that an existing model is insufficient in semantic understanding, inflexible in model selection and inaccurate in knowledge calling in the data management process are solved, the requirements of diversified tasks for accuracy and specialty are met, and then management of data assets is facilitated.

The systems and methods disclosed herein enable dynamic selection of a routing model for generation of an output in response to a provided input (e.g., a prompt for a large-language model). Based on the selected routing model, the data generation platform can evaluate the input and / or other suitable system parameters (e.g., system resource usage) to determine a suitable model for processing the provided input. For example, the routing model can determine a technical application associated with the input and dynamically determine to modify the input prior to generation of the output based on system resource measurement values and / or other suitable information, thereby conferring efficiency, security, and accuracy benefits while preserving system resilience.

The invention provides an adaptive welding seam detection and three-dimensional reconstruction method based on deep learning and binocular vision. The adaptive welding seam detection and three-dimensional reconstruction method comprises the steps of S1, collecting samples and making a training data set; s2, the picture of the sample to be welded is processed, a feature region is recognized, the image quality of the region to be welded is analyzed and evaluated through wavelet transform and local variance, and the noise level and the contrast ratio are calculated; s3, dynamically generating edge detection parameters and model fitting parameters according to the image quality; s4, using an edge detection algorithm to extract edge point cloud of the welding seam area; s5, performing RANSAC linear fitting, weighted least square fitting and polynomial curve fitting on the edge point cloud in parallel; s6, selecting an optimal fitting result based on an image quality adaptive dynamic scoring model; and S7, carrying out three-dimensional coordinate conversion in combination with the three-dimensional matching model IGEV-Stereo, and outputting a final welding seam three-dimensional coordinate. According to the invention, automatic detection of the position and size of the welding seam can be efficiently and accurately realized.

The invention discloses a resume analysis method and system based on multiple large language models, and belongs to the technical field of large language models.The resume analysis method and system based on the multiple large language models.The resume analysis method and system based on the multiple large language models comprise the following specific steps that firstly, model parallel analysis is conducted, simultaneously inputting the data into at least two heterogeneous large language models through an application program interface; and each large language model independently performs information extraction and analysis according to the model structure and the training data of the large language model, and outputs a structured data result containing a plurality of preset fields. Through the multi-model parallel analysis and conflict re-judgment mechanism, the misjudgment risk of a single model is effectively reduced, the robustness of the whole system is improved, the resume analysis accuracy is remarkably improved, the model pool is automatically optimized and updated through the dynamic scoring mechanism, and the problem that the model is difficult to select and update is solved.

The invention discloses a commercial customer service system based on large model emotion recognition labeling and correction, and belongs to the technical field of natural language processing and deep learning. In order to solve the problems that an existing emotion recognition system depends on large-scale manual labeling, label quality is unstable and small sample performance is poor, a multi-model collaborative labeling and iterative optimization mechanism is adopted, and fusion labels are generated through automatic basic model selection, small sample LoRA fine adjustment, double-model divergence detection and large model arbitration. And a refining training set is constructed for iterative fine tuning to form a closed-loop optimization system. The method can effectively reduce the labeling cost, improves the label consistency and the emotion recognition precision under complex semantics, and is suitable for business information, financial public opinions and intelligent customer service scenes.

A computing device may perform training of a set of machine learning models on a first data set associated with a first domain. In some examples, the training may include, for each machine learning model of the set of machine learning models, inputting, as values for a set of parameters of the respective sets of parameters and for an iteration of a set of iterations, a moving average of the set of parameters calculated over a threshold number of previous iterations. The computing device may select a set of model states that are generated during the training of the plurality of machine learning models based on a validation performance of the set of model states performed during the training. The computing device may then generate an ensembled machine learning model by aggregating the set of machine learning models corresponding to the set of selected model states.

The invention relates to a backlight module LED model selection method and device, electronic equipment and a storage medium, and the method comprises the steps: responding to a data configuration operation in a graphical interface, and obtaining a configured reference spectrum data source, a diaphragm penetration rate frequency spectrum and a liquid crystal panel penetration rate frequency spectrum; performing spectrum modulation simulation processing on the reference spectrum data source, the diaphragm penetration rate spectrum and the liquid crystal panel penetration rate spectrum according to an optical structure hierarchical relationship of a simulation backlight module to obtain colorimetric parameters of the simulation backlight module; and determining a backlight module LED model selection result according to the colorimetric parameters. In this way, the actual assembling and measuring process of the backlight module is converted into mathematical operation, the backlight scheme of the simulated backlight module can be evaluated under the condition that the backlight module is not actually assembled, then the optimal LED model selection result of the simulated backlight module is determined, the development efficiency of the newly-assembled screen backlight module is improved, and the development cost is reduced.

The present disclosure is related to machine learning model swap (MLMS) framework for that selects and interchanges machine learning (ML) models in an energy and communication efficient way while adapting the ML models to real time changes in system constraints. The MLMS framework includes an ML model search strategy that can flexibly adapt ML models for a wide variety of compute system and / or environmental changes. Energy and communication efficiency is achieved by using a similarity-based ML model selection process, which selects a replacement ML model that has the most overlap in pre-trained parameters from a currently deployed ML model to minimize memory write operation overhead. Other embodiments may be described and / or claimed.

An apparatus comprising an interface and a processor. The interface may be configured to receive sensor data from a plurality of sensors. The processor may be configured to detect an intruder in response to an analysis of the sensor data, activate an AI model in response to detecting the intruder and generate a countermeasure signal in response to a countermeasure selection by the AI model. The AI model may be configured to analyze the sensor data, compare the sensor data of the intruder to a database of pests to perform a classification of the intruder, determine the countermeasure selection in response to the classification of the intruder as a selected pest, monitor the sensor data for an outcome of the countermeasure selection, and generate a text description of the classification of the selected pest, the countermeasure selection and the countermeasure outcome.

The invention relates to the technical field of research and development management, can be applied to business scenes of financial science and technology, medical health and the like, and discloses an anomaly analysis method, device, equipment and medium based on a variation test. Generating a test case through the semantic perception model; selecting a variation strategy by using a state-driven model according to the service state, and generating a variation test case based on the access control strategy; executing the variation test case in a distributed environment, and collecting system resource index data and request execution monitoring data; and inputting the collected data into the abnormal prediction model, and outputting an abnormal behavior prediction result. Through combination of semantic perception generation, state-driven selection and anomaly prediction, coverage of a test case on protocol dependence and a service state is improved, and the accuracy of anomaly detection of the object storage system is remarkably improved.

The invention belongs to the technical field of sound source processing, and provides a sound source positioning and detecting method and device. The method comprises the following steps: acquiring delay estimation of microphones I and II and delay estimation of microphones I and III based on a three-path linear uniform microphone array; based on the delay estimation sum, respectively carrying out positioning calculation under near-field and far-field conditions; according to the sound source distance under the near-field condition, comparing the sound source distance with a distance judgment threshold value, and determining a far-field / near-field output sound source position; and carrying out feature extraction on the signals of any microphone array, and carrying out event classification based on a pre-trained convolutional neural network. According to the method, far / near field model selection is carried out according to the distance judgment threshold, large deviation generated by a single model in a critical region is avoided, continuous and stable positioning from short distance to long distance is achieved, time classification can be achieved while position calculation is carried out, and integrated output is achieved.

The embodiment of the invention discloses a visible light-infrared bimodal fusion target detection system and method and a medium, and the system comprises the steps: a bimodal fusion target detection model carries out the weighted summation of deep features of visible light and infrared images and a feature weight map, and obtains a first fusion feature image for target detection; the visible light or infrared light single-mode target detection model carries out two times of down-sampling on the image and then carries out standard convolution to obtain an initial feature image, after four times of convolution output splicing, multi-scale feature fusion is carried out, and a second fusion feature image is obtained for detection; the model selection module selects an optimal sub-model from candidate models (bimodal fusion, visible light or infrared single-modal model) for detection according to the probability distribution of the six-channel spliced image. According to the system, through feature level and decision level fusion, the target detection accuracy and stability in a complex scene are improved.

Aspects of the present disclosure provide systems, methods, and computer-readable storage media that support intelligent model selection for style-specific digital content generation. For example, a system that provides a digital content generation service may include a trained style detection model may receive reference digital content items from a user and extract a user style embedding that represents a style preference of the user. In some implementations, the reference digital content items may include text documents or images provided or selected by the user. The system may compare the user style embedding to a plurality of model style embeddings that each correspond to a respective generative artificial intelligence (AI) model to generate a ranked list of generative AI models. The system may access one or more highest ranked generative AI models from the ranked list to generate novel digital content based on a prompt from the user.

A system includes one or more processors to store a first explanatory model (e.g., a SHAP model or a LIME model) and a second explanatory model; execute the machine learning model (e.g., a neural network) using a first set of data to generate a first classification data point; generate a first plurality of explanatory evaluation metrics for the first explanatory model by applying the first explanatory model to the first classification data point; and responsive to the first plurality of explanatory evaluation metrics satisfying an explanatory model selection policy, apply the first explanatory model and the second explanatory model to a second classification data point output by the machine learning model based on a second set of transaction data.

Methods and systems are described for AI and / or ML model selection in a telecommunications network. One example embodiment includes obtaining a first set of one or more criteria for selecting between at least two AI / ML models; performing at least one measurement procedure to obtain one or more measurements; and using the obtained one or more measurements and the first set of one or more criteria to select between the at least two AI / ML models. A measurement procedure can comprise e.g. CSI, radio link procedure (RLP), positioning measurement, measurement related to cell change procedure etc. Certain described embodiments enhance measurement performance of the measurement (e.g., CQI) and correspondingly improve the outcome / performance of the procedure (e.g., data scheduling) using the measurement. This in turn reduces the overall processing in the UE, frees up at least part of the memory resources and reduces the UE power consumption.

The invention provides a method for automatically deploying artificial intelligence models, which simplifies a model building process through systematic data preprocessing, model selection, parameter optimization and performance monitoring mechanisms, and dynamically updates or switches models in an application environment to maintain overall prediction performance at the best state while improving the performance of the model in multiple application environments.

The invention relates to the technical field of communication and electronics, and discloses a low-altitude unmanned system data processing method and gateway based on edge computing, and the edge computing gateway executes the following steps: obtaining sensor data collected by a low-altitude unmanned system in real time, continuously monitoring the network connection quality between the edge computing gateway and the cloud server; in response to the change of the network connection quality, dynamically selecting one adaptive mode from three preset data processing modes; processing the sensor data by adopting the selected data processing mode to obtain an analysis result; and based on the analysis result, locally generating a control instruction for controlling the low-altitude unmanned system at the edge computing gateway. By analyzing the preset task profile file and combining the utility evaluation and the model selection strategy, the computing resources and the AI model of the unmanned system are subjected to prospective pre-configuration.

The invention discloses an expandable category guide anomaly detection method and device for multiple categories of targets, and relates to the field of computer vision. The method comprises the following steps: carrying out abnormal region guided adaptive enhancement preprocessing on an industrial image to obtain a target image; judging the category of the target image according to a pre-constructed lightweight neural network classifier; activating at least one anomaly detection model according to the category of the target image; and performing anomaly prediction on the target image by using the activated anomaly detection model, and fusing with the confidence corresponding to the anomaly detection model to realize adaptive anomaly discrimination of the industrial image. According to the method, the sample category is quickly judged through the lightweight classifier, the pre-screening and path guidance of the anomaly detection model are realized, the category guidance weight is generated by using a confidence coefficient mechanism, the subsequent model fusion strategy is endowed with higher adaptability, and the structural clarity, the model selection accuracy and the overall calculation efficiency of the system are effectively improved.

Certain aspects of the disclosure pertain to machine learning evaluation and selection in a streaming environment. A machine learning model can generate inferences based on real time streaming data. A plurality of machine learning models can be available for a particular domain or task. Performance of the plurality of machine learning models can be continuously evaluated. Based on evaluation results, at least one of the plurality of machine learning models can be selected to provide output. For example, the streaming data can be routed to a selected machine learning model. Further, a poor-performing model, as determined based on evaluation results, can be fine-tuned based on real time data to improve performance.

The invention discloses a dynamic simulation modeling method for a compressed air energy storage system based on AMESIM and application, and belongs to the technical field of compressed air energy storage.The method comprises the steps that firstly, system indexes are determined, based on the system indexes, a system technological process diagram is designed, main equipment and auxiliary equipment are selected, and design point parameters of the main equipment and the auxiliary equipment in the energy storage and release stage are determined; then, according to the equipment model selection result, sub-models of all elements in the air circulation loop and the heat storage and exchange loop are selected in the AMESIM; thirdly, calibrating and verifying each main equipment sub-model by utilizing main equipment characteristics and model selection parameters, and building a steady-state simulation model of the compressed air energy storage system; and then, constructing a dynamic simulation model based on the steady-state model, and carrying out dynamic simulation verification and evaluation. According to the method, the co-simulation model integrating thermodynamics, fluid mechanics, control theory and mechanical dynamics can be quickly built, and the method has the advantages of being high in model modeling precision, high in multidisciplinary coupling calculation capacity, high in simulation efficiency and the like.

To provide a learning model evaluation support device and a learning model evaluation support program which allow for easily evaluating a characteristic of a learning model.SOLUTION: A learning model evaluation support device 100 includes a model information display unit 110, a model selection unit 120, and an output display unit 150. The model information display unit 110 selectively displays a plurality of learning models which are stored in a prescribed storage area and share an interface, on a display device 260. The model selection unit 120 selects at least one of the plurality of learning models displayed on the display device 260. The output display unit 150 displays an output result from at least one learning model on the display device 260.SELECTED DRAWING: Figure 17

The invention relates to the technical field of new energy power generation prediction, and particularly provides an ultra-short-term solar irradiance prediction method and device based on a satellite cloud atlas, and the method comprises the steps: obtaining the prediction time period of a prediction result and an error evaluation index of a parameter type relative to each pre-trained multi-layer perceptron model; selecting a pre-trained multi-layer perceptron model with the minimum error evaluation index to predict the prediction result; wherein the parameter types comprise global level irradiance, direct normal irradiance and diffusion level irradiance. According to the technical scheme provided by the invention, model optimization selection is carried out for different irradiance types, and the adaptability and accuracy of prediction are greatly improved.

The present application relates to a method, apparatus, and device for analyzing a lithography process window based on stepwise regression. The method comprises: obtaining photoresist pattern image data and determining the constraints required for the lithography process window; determining a lithography process model that satisfies the relationship between the photoresist pattern features, exposure energy, and focal length, and a stepwise regression direction for the lithography process model; performing stepwise regression on the lithography process model based on the photoresist pattern image data in the direction indicated by the stepwise regression direction to obtain multiple candidate lithography process models and model selection index values ​​for each candidate lithography process model; determining a target lithography process model from the multiple candidate lithography process models based on the model selection index values; and determining the lithography process window based on the constraints and the target lithography process model. This method can improve the accuracy of the analysis results of focal length energy matrix data.

The invention provides a service deployment and model selection system and method for inference precision perception in an edge environment. The system comprises a user side and an edge server side. The user side comprises terminal equipment and a reasoning request module; the edge server side comprises a service type selection module and a model selection module; the system runs based on multiple time slots; in each time slot, the reasoning task of the user is recorded as a quintuple, and the quintuple represents the task size, the service type, the calculation density under different configurations, the reasoning precision under different configurations and the task priority; the calculation density and the reasoning precision of the tasks change along with different resource configurations; the system model provided by the technical scheme comprehensively considers a plurality of factors such as reasoning delay, reasoning precision and memory limitation, and aims to improve the utilization efficiency of edge resources while considering the user service quality.

The invention discloses an aggregate random distribution concrete PFC (Power Factor Correction) simulation method, which comprises the following steps: a model selection step: determining a parallel bonding model as a mechanical model for concrete material simulation; a cement mortar matrix generation step of generating a cement mortar matrix by using particles in a set size range in a set space range based on the model, and setting pore density, particle density and contact model parameters; a coarse aggregate random distribution simulation step: randomly covering and grouping original particles in the matrix in a grouping and range mode; a concrete numerical model construction step: determining particle classification so as to distinguish cement mortar and coarse aggregate; and a model reliability verification step: comparing indoor test results through a uniaxial compression test. According to the method, the simulation accuracy is improved, the randomness of aggregate is reduced, the model reliability is ensured, the matrix simulation refinement degree is improved, and a method is provided for concrete modeling and performance research.

The invention discloses a lithium battery health state and service life prediction method based on HA-BiLSTM, and belongs to the technical field of new energy, and the method comprises the following steps: S1, data preprocessing and loading; s2, calculating the SOH (state of health) of the battery and extracting features; s3, constructing a mixed attention bidirectional LSTM model; s4, generating time sequence data; s5, multiple times of training and optimal model selection are carried out; step S6, predicting a future SOH sequence; according to the method, the physical characteristics of the battery and the advantages of a deep learning algorithm can be effectively fused, an intelligent prediction model with the dynamic feature screening capability is constructed, high-precision prediction of SOH and RUL is achieved, and meanwhile technical support is provided for intelligent operation and maintenance of a new energy automobile battery management system BMS and an energy storage system.