Systems and methods for solving problems including combinatorial optimization problems are disclosed. A set of solutions to a combinatorial optimization problem are obtained from a quantum computing system such as a quantum annealer. A pattern mining operation is performed on a set of solutions output by a quantum annealing. The patterns are input to a solver to generate a solution to the initial problem.

A generative artificial intelligence-based system and method for providing an improved end-to-end data analytics tool is provided. Data from input unit(s) associated with multiple data sources located at disparate locations is collected. A data quality assessment is performed based on one or more pre-determined criteria. Transformed version of the collected data is processed for analyzing one or more data parameters associated with the transformed data to determine relationships and patterns within the transformed data. Prompts are generated related to operational issues associated with the specific domain. The prompts are provided to Large Language Models (LLMs) as input for generating diagnostic data and insights related to the operational issues. An optimized value of one or more modifiable prompt parameters associated with the generated prompts is determined for customizing the LLMs. Domain specific recommendations are provided by LLM based on the generated diagnostic data and insights for resolving the operational issues.

A generative artificial intelligence-based system and method for providing an improved end-to-end data analytics tool is provided. Data from input unit(s) associated with multiple data sources located at disparate locations is collected. A data quality assessment is performed based on one or more pre-determined criteria. Transformed version of the collected data is processed for analyzing one or more data parameters associated with the transformed data to determine relationships and patterns within the transformed data. Prompts are generated related to operational issues associated with the specific domain. The prompts are provided to Large Language Models (LLMs) as input for generating diagnostic data and insights related to the operational issues. An optimized value of one or more modifiable prompt parameters associated with the generated prompts is determined for customizing the LLMs. Domain specific recommendations are provided by LLM based on the generated diagnostic data and insights for resolving the operational issues.

An image processing method includes: detecting repetition numbers of each image frame of an input image frame sequence, wherein the input image frame sequence includes sequentially inputted at least one first image frame and at least one second image frame, and image data of each first image frame is different from image data of each second image frame; determining a first lookup table according to a first repetition numbers of the at least one first image frame, wherein the first lookup table indicates a plurality of sets of compensation calculations; and using a first set of compensation calculations in the sets of compensation calculations to process the at least one first image frame according to a second repetition numbers of the at least one second image frame.

According to an embodiment, an image processing device includes one or more processors. The one or more processors are configured to: acquire an image; detect a first repeated pattern from the image; detect an object included in the first repeated pattern; and output the object as a second repeated pattern.

The disclosed computer-implemented method for updating a machine-learning-based prediction model with preserved privacy may include receiving a plurality of training data sets for training a machine-learning-based global prediction model for predicting future incidents of a computing event. Each data set may include incidents of the computing event. The method may include creating, by training the global prediction model using the plurality of training data sets, an intermediate prediction model of the global prediction model. The intermediate prediction model may be a precursor state to a fully trained global prediction model. The method may further include providing the intermediate prediction model to a computing node to enable the computing node to fully train a local prediction model using both the intermediate prediction model and a local training data set. Various other methods, systems, and computer-readable media are also disclosed.

The disclosed computer-implemented method for updating a machine-learning-based prediction model with preserved privacy may include receiving a plurality of training data sets for training a machine-learning-based global prediction model for predicting future incidents of a computing event. Each data set may include incidents of the computing event. The method may include creating, by training the global prediction model using the plurality of training data sets, an intermediate prediction model of the global prediction model. The intermediate prediction model may be a precursor state to a fully trained global prediction model. The method may further include providing the intermediate prediction model to a computing node to enable the computing node to fully train a local prediction model using both the intermediate prediction model and a local training data set. Various other methods, systems, and computer-readable media are also disclosed.

Disclosed is a method for siting heat wave monitoring stations based on risk evaluation, including: acquiring historical meteorological data of a target region, and preprocessing the historical meteorological data to generate a gridded associated meteorological data set; identifying historical high-temperature heat wave events based on the associated meteorological data set, and calculating parameters and summary indexes of heat wave feature of grids; evaluating station building priority of the grids based on spatial distribution features of the summary indexes; acquiring multi-source data, and evaluating a heat wave risk to generate a heat wave risk map; performing iterative computation using an optimization algorithm based on current station building information, temporal-spatial distribution features of meteorological factors and the heat wave risk map to determine alternative station building positions; and acquiring on-site survey information of each alternative station building position, and determining a position where a station is to be built.

Disclosed is a method for siting heat wave monitoring stations based on risk evaluation, including: acquiring historical meteorological data of a target region, and preprocessing the historical meteorological data to generate a gridded associated meteorological data set; identifying historical high-temperature heat wave events based on the associated meteorological data set, and calculating parameters and summary indexes of heat wave feature of grids; evaluating station building priority of the grids based on spatial distribution features of the summary indexes; acquiring multi-source data, and evaluating a heat wave risk to generate a heat wave risk map; performing iterative computation using an optimization algorithm based on current station building information, temporal-spatial distribution features of meteorological factors and the heat wave risk map to determine alternative station building positions; and acquiring on-site survey information of each alternative station building position, and determining a position where a station is to be built.

Herein are timeseries preprocessing, model selection, and hyperparameter tuning techniques for forecasting development based on temporal statistics of a timeseries and a single feed-forward pass through a machine learning (ML) pipeline. In an embodiment, a computer hosts and operates the ML pipeline that automatically measures temporal statistic(s) of a timeseries. ML algorithm selection, cross validation, and hyperparameters tuning is based on the temporal statistics of the timeseries. The result from the ML pipeline is a rigorously trained and production ready ML model that is validated to have increased accuracy for multiple prediction horizons. Based on the temporal statistics, efficiency is achieved by asymmetry of investment of computer resources in the tuning and training of the most promising ML algorithm(s). Compared to other approaches, this ML pipeline produces a more accurate ML model for a given amount of computer resources and consumes fewer computer resources to achieve a given accuracy.