Abstract: In some examples, one or more processors configured by executable instructions may receive an audio signal and data to embed in the audio signal. For example, the data may be received dynamically from one or more data sources. The one or more processors may embed the received data in real time into the audio signal as embedded data based at least in part on controlling a phase angle of a selected frequency component of the audio signal. For instance, the embedded data may include at least one of text, a bar code, a quick response code, an image, a uniform resource locator (URL), or multimedia content. Additionally, the one or more processors may send the audio signal with the embedded data over a network to a plurality of electronic devices that include respective decoders for extracting the embedded data from the audio signal.

Abstract: A system and a computer-implemented method for validating label data includes receiving the label data and segmenting it into one or more parts using a first machine learning model. Further, from the segmented label data a first plurality of attributes, including text and images, are extracted. The method further includes receiving ground truth data associated with the label data and extracting a second plurality of attributes from the ground truth data. The first and second plurality of attributes are then compared using a second machine learning model and the result of comparison are displayed on a three pane user interface. Further, the label data is validated based on the displayed results.

Abstract: A system for managing one or more robots is provided. The system is configured to resolve the one or more issues or faults that lead to failure of execution of one or more automation processes executed by the one or more robots. The system is configured to receive information of an issue associated with at least one robot of the one or more robots and further configured to obtain job log data, associated with the at least one robot, for the issue. The system is further configured to determine, using a trained machine learning model, a corrective action, and its associated confidence score for resolving the received issue, based on the job log data and an analysis performed by the trained machine learning model. Further, system performs the corrective action based on the confidence score and the analysis, for managing the one or more robots.

Abstract: A system and a computer-implemented method for validating label data includes receiving the label data and segmenting it into one or more parts using a first machine learning model. Further, from the segmented label data a first plurality of attributes, including text and images, are extracted. The method further includes receiving ground truth data associated with the label data and extracting a second plurality of attributes from the ground truth data. The first and second plurality of attributes are then compared using a second machine learning model and the result of comparison are displayed on a three pane user interface. Further, the label data is validated based on the displayed results.

Abstract: A system and a computer-implemented method for analyzing workflow of test automation associated with a robotic process automation (RPA) application are disclosed herein. The computer-implemented method includes receiving the workflow of the test automation associated with the RPA application and analyzing, via an Artificial Intelligence (AI) model associated with a workflow analyzer module, the workflow of the test automation based on a set of pre-defined test automation rules. The computer-implemented method further includes determining one or more metrics associated with the analyzed workflow of the test automation and generating, via the AI model, corrective activity data based on the determined one or more metrics.

Abstract: A system for managing one or more robots is provided. The system is configured to resolve the one or more issues or faults that lead to failure of execution of one or more automation processes executed by the one or more robots. The system is configured to receive information of an issue associated with at least one robot of the one or more robots and further configured to obtain job log data, associated with the at least one robot, for the issue. The system is further configured to determine, using a trained machine learning model, a corrective action, and its associated confidence score for resolving the received issue, based on the job log data and an analysis performed by the trained machine learning model. Further, system performs the corrective action based on the confidence score and the analysis, for managing the one or more robots.

Abstract: A system and a computer-implemented method for validating label data includes receiving the label data and segmenting it into one or more parts using a first machine learning model. Further, from the segmented label data a first plurality of attributes, including text and images, are extracted. The method further includes receiving ground truth data associated with the label data and extracting a second plurality of attributes from the ground truth data. The first and second plurality of attributes are then compared using a second machine learning model and the result of comparison are displayed on a three pane user interface. Further, the label data is validated based on the displayed results.

Abstract: A system and a computer-implemented method for validating label data includes receiving the label data and segmenting it into one or more parts using a first machine learning model. Further, from the segmented label data a first plurality of attributes, including text and images, are extracted. The method further includes receiving ground truth data associated with the label data and extracting a second plurality of attributes from the ground truth data. The first and second plurality of attributes are then compared using a second machine learning model and the result of comparison are displayed on a three pane user interface. Further, the label data is validated based on the displayed results.

Abstract: A robotic process automation (RPA) workflow may be automatically created from text, an image, and/or a media file. A workflow sequence may be converted into a digital format using optical character recognition (OCR), and this information may then be analyzed by an artificial intelligence (AI) model and converted into a predicted RPA workflow. The predicted RPA workflow may be presented to a developer for approval, denial, or modification. Information pertaining to the selection by the developer may then be used for subsequent retraining of the AI model to improve prediction accuracy.

Abstract: Training and using artificial intelligence (AI)/machine learning (ML) models to automatically supplement and/or complete code of RPA workflows is disclosed. A trained AI/ML model may intelligently and automatically predict and complete the next series of activities in RPA workflows (e.g., one, a few, many, the remainder of the workflow, etc.). Actions users take while creating workflows over a time period may be captured and stored. The AI/ML model may then be trained and used to match the stored actions with stored workflow sequences of actions in order to predict and complete the workflow. As more and more workflow sequences are captured and stored over time, the AI/ML model may be retrained to predict a larger number of sequences and/or to more accurately make predictions. Auto-completion may occur in real-time in some embodiments to save time and effort by the user.

Abstract: Automatic completion of robotic process automation (RPA) workflows using machine learning (ML) is disclosed. A trained ML model may intelligently and automatically predict and complete the next series of activities in RPA workflows (e.g., one, a few, many, the remainder of the workflow, etc.). Actions users take while creating workflows over a time period may be captured and stored. The ML model may then be trained and used to match the stored actions with stored workflow sequences of actions in order to predict and complete the workflow. As more and more workflow sequences are captured and stored over time, the ML model may be retrained to predict a larger number of sequences and/or to more accurately make predictions. Auto-completion may occur in real-time in some embodiments to save time and effort by the user.

Abstract: A system and a computer-implemented method for analyzing a robotic process automation (RPA) workflow are disclosed herein. The computer-implemented method may include obtaining the RPA workflow and analyzing the obtained RPA workflow to provide an analyzed RPA workflow. The computer-implemented method may further include determining one or metrics associated with the analyzed RPA workflow and performing one or more corrective activities for the analyzed RPA workflow based on the determined one or more metrics.

Abstract: A system and a computer-implemented method for analyzing workflow of test automation associated with a robotic process automation (RPA) application are disclosed herein. The computer-implemented method includes receiving the workflow of the test automation associated with the RPA application and analyzing, via an Artificial Intelligence (AI) model associated with a workflow analyzer module, the workflow of the test automation based on a set of pre-defined test automation rules. The computer-implemented method further includes determining one or more metrics associated with the analyzed workflow of the test automation and generating, via the AI model, corrective activity data based on the determined one or more metrics.

Abstract: An intelligent workflow design solution is provided that assists a user (e.g., developer of RPA workflows) by automatically and intelligently recommending suggested activities for use in building sequences of activities in an RPA workflow. The solution utilizes a predictive learning model to customize and personalize the workflow design process for a user, thereby shortening design cycle time and improving efficiency. A system and method for developing an RPA workflow includes monitoring one or more activities that are selected by a user and identifying one or more recommended activities as candidate next activities in a sequence based on a predictive learning model. The candidate next activities are generated for selection by the user and the predictive learning model is trained based on an actual selection by the user of a next activity for the sequence.

Abstract: An electric device comprises a core having a center section and two outer sections, a high current winding, and a low current winding. The high current winding includes a plurality of half-turn coils connected in parallel between a first high current terminal and a second high current terminal. Each of the plurality of half-turn coils is wound around a fraction of the center section and forms a loop around one of the two outer sections along with the first and second high current terminals. The low current winding includes a plurality of full-turn coils connected in series between a first low current terminal and a second low current terminal, each of the plurality of full-turn coils wound around the center section of the core substantially fully. The plurality of half-turn coils of the high current winding are interleaved with the plurality of full-turn coils of the low current winding.

Abstract: Automatic completion of robotic process automation (RPA) workflows using machine learning (ML) is disclosed. A trained ML model may intelligently and automatically predict and complete the next series of activities in RPA workflows (e.g., one, a few, many, the remainder of the workflow, etc.). Actions users take while creating workflows over a time period may be captured and stored. The ML model may then be trained and used to match the stored actions with stored workflow sequences of actions in order to predict and complete the workflow. As more and more workflow sequences are captured and stored over time, the ML model may be retrained to predict a larger number of sequences and/or to more accurately make predictions. Auto-completion may occur in real-time in some embodiments to save time and effort by the user.

Abstract: A robotic process automation (RPA) workflow may be automatically created from text, an image, and/or a media file. A workflow sequence may be converted into a digital format using optical character recognition (OCR), and this information may then be analyzed by an artificial intelligence (AI) model and converted into a predicted RPA workflow. The predicted RPA workflow may be presented to a developer for approval, denial, or modification. Information pertaining to the selection by the developer may then be used for subsequent retraining of the AI model to improve prediction accuracy.

Abstract: An electric device comprises a core having a center section and two outer sections, a high current winding, and a low current winding. The high current winding includes a plurality of half-turn coils connected in parallel between a first high current terminal and a second high current terminal. Each of the plurality of half-turn coils is wound around a fraction of the center section and forms a loop around one of the two outer sections along with the first and second high current terminals. The low current winding includes a plurality of full-turn coils connected in series between a first low current terminal and a second low current terminal, each of the plurality of full-turn coils wound around the center section of the core substantially fully. The plurality of half-turn coils of the high current winding are interleaved with the plurality of full-turn coils of the low current winding.

Abstract: A converter for an LED driver for an LED light source. The converter has a flyback transformer. The primary receives a rectified AC voltage. A switching transistor is coupled in series with the primary. A controller controls the switching transistor on and off to generate a bus voltage across the secondary and a center tap voltage at a center tap of the secondary. The controller is powered by a first low-voltage DC voltage. A first power supply receives the center tap voltage and generates a second low-voltage DC voltage when the center tap voltage is above a cutover voltage. A second power supply has an output coupled to the first power supply output. The second power supply receives the bus voltage and generates the second DC voltage when the center tap voltage is below the cutover voltage.

Abstract: A light-emitting diode (LED) driver is adapted to control either the magnitude of the current conducted through a LED light source or the magnitude of a voltage generated across the LED light source. The LED driver comprises a power converter circuit for generating a DC bus voltage, and an LED drive circuit for receiving the bus voltage and adjusting the magnitude of the current conducted through the LED light source. The LED driver is operable to dim the LED light source using either a pulse-width modulation technique or a constant current reduction technique. The LED drive circuit may comprise a controllable-impedance circuit, such as a linear regulator. The LED driver may be operable to control the magnitude of the bus voltage to optimize the efficiency and reduce the power dissipation in the LED drive circuit, as well ensuring that the load voltage and current do not have any ripple.