Abstract: A system and a process for provisioning a job through a trained machine-learning dynamic provisioning agent is provided herein. An input vector representing the job having one or more job components may be received. One or more additional data vectors representing additional job data may be obtained. For the one or more job components respectively, one or more action values corresponding to one or more provisioning options may be calculated based on the one or more additional data vectors. For the one or more job components respectively, one or more provisioning options for the respective one or more job components may be selected based on the corresponding one or more action values. The one or more selected provisioning options corresponding to the respective one or more job components may be aggregated. The aggregated selected provisioning options may be provided.

Abstract: A method for automatically calibrating a first simulation parameter of a simulation model to compute a performance parameter of an electrical device by a large-language-model-LLM-based agent system, comprising: collecting first data; configurating the simulation model; calibrating the simulation model based on the first data to approximate the real behavior of the electrical device; running the calibrated simulation model on second data that describe a target application scenario of the electrical device simulated by the calibrated simulation model; using the calibrated simulation model with the second simulation parameter for a realistic simulation; and optimizing the second simulation parameter.

Abstract: A method for automating error diagnosis of an industrial drive product includes obtaining, by a generative artificial intelligence (AI) agent, a notification that is associated with an error occurred; retrieving pieces of information from one or more data sources that are associated with the industrial drive product; determining a relevance in relation to the error; for pieces of information of the plurality of pieces of information that are determined to have a relevance above a predetermined relevance threshold, augmenting, by the generative AI agent, the pieces of information; and generating, by the generative AI agent, a proposal for handling the error based on the augmented pieces of information.

Abstract: A method for aggregating outputs of multiple language models determines calibration information of each of the multiple LMs using at least one calibration question; obtains, from each of the multiple LMs, an original answer based on an original question; obtains, from each of the multiple LMs, an estimation answer based on an estimation question using the determined calibration information, wherein the estimation question asks for a most popular answer to the original question among the multiple LMs; and determines a predicted answer to the original question by aggregating sets of same original answers and same estimation answers.

Abstract: A method for configuring an electric drive that is connectable to at least one electric motor, and/or the electric motor, the method comprising providing a request for configuring the electric drive and/or electric motor to at least one agent software component; decomposing, by the at least one agent software component, the task of configuring the electric drive and/or electric motor into a sequence of sub-actions; and causing, by the at least one agent software component, the performing of each sub-action so that completing all sub-actions results in the electric drive and/or electric motor being at least partially configured.

Abstract: A system and a process for provisioning a job through a trained machine-learning dynamic provisioning agent is provided herein. An input vector representing the job having one or more job components may be received. One or more additional data vectors representing additional job data may be obtained. For the one or more job components respectively, one or more action values corresponding to one or more provisioning options may be calculated based on the one or more additional data vectors. For the one or more job components respectively, one or more provisioning options for the respective one or more job components may be selected based on the corresponding one or more action values. The one or more selected provisioning options corresponding to the respective one or more job components may be aggregated. The aggregated selected provisioning options may be provided.

Abstract: A system and a process for provisioning a job through a trained machine-learning dynamic provisioning agent is provided herein. An input vector representing the job having one or more job components may be received. One or more additional data vectors representing additional job data may be obtained. For the one or more job components respectively, one or more action values corresponding to one or more provisioning options may be calculated based on the one or more additional data vectors. For the one or more job components respectively, one or more provisioning options for the respective one or more job components may be selected based on the corresponding one or more action values. The one or more selected provisioning options corresponding to the respective one or more job components may be aggregated. The aggregated selected provisioning options may be provided.

Abstract: A system and a process for provisioning a job through a trained machine-learning dynamic provisioning agent is provided herein. An input vector representing the job having one or more job components may be received. One or more additional data vectors representing additional job data may be obtained. For the one or more job components respectively, one or more action values corresponding to one or more provisioning options may be calculated based on the one or more additional data vectors. For the one or more job components respectively, one or more provisioning options for the respective one or more job components may be selected based on the corresponding one or more action values. The one or more selected provisioning options corresponding to the respective one or more job components may be aggregated. The aggregated selected provisioning options may be provided.

Abstract: A system and process for artificially generating training data for machine-learning is provided herein. One or more input vectors for a machine-learning system may be identified. One or more parameters for the training data based on a domain of the machine-learning system may be retrieved. One or more functions for generating the training data corresponding to the one or more input vectors may be retrieved. One or more data sources may be accessed to retrieve one or more sets of data for building a data foundation for generating the training data. Training data corresponding to the one or more input vectors may be generated based on the one or more parameters and the one or more data foundations. The machine-learning system may be trained via the generated training data obtained from the database.

Abstract: A foot and leg warmer or foot covering configured for wearing by a user, the foot and leg warmer having a sole portion, front portion, rear portion, upper front portion, and an adjustable attachment configured for allowing the user to fit the foot and leg warmer to the user's body. The foot covering configured for attaching above a wearer's calf muscle, thereby using the warmth of the wearer's calf muscle to heat air trapped within the foot covering and thereby heats the wearer's lower extremities.

Abstract: A foot and leg warmer or foot covering configured for wearing by a user, the foot and leg warmer having a sole portion, front portion, rear portion, upper front portion, and an adjustable attachment configured for allowing the user to fit the foot and leg warmer to the user's body. The foot covering configured for attaching above a wearer's calf muscle, thereby using the warmth of the wearer's calf muscle to heat air trapped within the foot covering and thereby heats the wearer's lower extremities.