Abstract: Systems and methods for analyzing, prioritizing, and potentially automatically generating robots implementing processes and/or process flows for robotic process automation (RPA) are disclosed. Artificial intelligence (AI) may be used to analyze business processes and/or process flows and look for possible candidates for automation or improvement of existing automations. Listeners (e.g., robots, separate software applications, operating system extensions, etc.) may be employed to listen in the background on user computing systems to mine data pertaining to workflow effectiveness and/or to identify new processes and/or process flows that may improve return on investment (ROI) for RPA.

Abstract: Human-in-the-loop robot training using artificial intelligence (AI) for robotic process automation (RPA) is disclosed. This may be accomplished by a listener robot watching interactions of a user or another robot with a computing system. Based on the interactions by the user or robot with the computing system, the robot may be improved and/or personalized for the user or a group of users.

Abstract: Reinforcement learning may be used to train machine learning (ML) models for robotic process automation (RPA) that are implemented by robots. A policy network may be employed, which learns to achieve a definite output by providing a particular input. In other words, the policy network informs the system whether it is getting closer to the winning state. The policy network may be refined by the robots automatically or with the periodic assistance of a human in order to reach the winning state, or to achieve a more optimal winning state. Robots may also create other robots that utilize reinforcement learning.

Abstract: Probabilistic models may be used in a deterministic workflow for robotic process automation (RPA). Machine learning (ML) introduces a probabilistic framework where the outcome is not deterministic, and therefore, the steps are not deterministic. Deterministic workflows may be mixed with probabilistic workflows, or probabilistic activities may be inserted into deterministic workflows, in order to create more dynamic workflows. A supervisor system may be used to monitor an ML model and raise an alarm, disable an RPA robot, bypass an RPA robot, or roll back to a previous version of the ML model when an error is detected by a data drift detector, a concept drift detector, or both.

Abstract: Using artificial intelligence (AI) to select and/or chain robotic process automation (RPA) models a given problem is disclosed. A model of models (e.g., an RPA robot or an ML model) may serve as an additional layer on an existing system that makes the existing models more effective. This model of models may incorporate AI that learns an improved or best set of rules or an order from existing models, potentially taking certain activities from a model, feeding input from one model into another, and/or chaining models in some embodiments.

Abstract: Artificial intelligence (AI)-based process identification, extraction, and automation for robotic process automation (RPA) is disclosed. Listeners may be deployed to user computing systems to collect data pertaining to user actions. The data collected by the listeners may then be sent to one or more servers and be stored in a database. This data may be analyzed by AI layers to recognize patterns of user behavioral processes therein. These recognized processes may then be distilled into respective RPA workflows and deployed to automate the processes.

Abstract: Artificial intelligence (AI) layer-based process extraction for robotic process automation (RPA) is disclosed. Data collected by RPA robots and/or other sources may be analyzed to identify patterns that can be used to suggest or automatically generate RPA workflows. These AI layers may be used to recognize patterns of user or business system processes contained therein. Each AI layer may “sense” different characteristics in the data and be used individually or in concert with other AI layers to suggest RPA workflows.

Abstract: Process evolution for robotic process automation (RPA) and RPA workflow micro-optimization are disclosed. Initially, an RPA implementation may be scientifically planned, potentially using artificial intelligence (AI). Embedded analytics may be used to measure, report, and align RPA operations with strategic business outcomes. RPA may then be implemented by deploying AI skills (e.g., in the form of machine learning (ML) models) through an AI fabric that seamlessly applies, scales, manages AI for RPA workflows of robots. This cycle of planning, measuring, and reporting may be repeated, potentially guided by more and more AI, to iteratively improve the effectiveness of RPA for a business. RPA implementations may also be identified and implemented based on their estimated return on investment (ROI).

Abstract: Automatic activation and configuration of robotic process automation (RPA) workflows using machine learning (ML) is disclosed. One or more parts of an RPA workflow may be turned on or off based on one or more probabilistic ML models. RPA robots may be configured to modify parameters, determine how much of a certain resource to provide, determine more optimal thresholds, etc. Such RPA workflows implementing ML may thus be hybrids of both deterministic and probabilistic logic, and may learn and improve over time by retraining the ML models, adjusting the confidence thresholds, using local/global confidence thresholds, providing or adjusting modifiers for the local confidence thresholds, implement a supervisor system that monitors ML model performance, etc.

Abstract: Using artificial intelligence (AI) to select and/or chain robotic process automation (RPA) models a given problem is disclosed. A model of models (e.g., an RPA robot or an ML model) may serve as an additional layer on an existing system that makes the existing models more effective. This model of models may incorporate AI that learns an improved or best set of rules or an order from existing models, potentially taking certain activities from a model, feeding input from one model into another, and/or chaining models in some embodiments.

Abstract: Described herein are various technologies pertaining to performing an operation relative to tabular data based upon voice input. An ASR system includes a language model that is customized based upon content of the tabular data. The ASR system receives a voice signal that is representative of speech of a user. The ASR system creates a transcription of the voice signal based upon the ASR being customized with the content of the tabular data. The operation relative to the tabular data is performed based upon the transcription of the voice signal.

Abstract: Generally discussed herein are devices, systems, and methods for scheduling tasks to be completed by resources. A method can include identifying features of the task, the features including a time-dependent feature and a time-independent feature, the time-dependent feature indicating a time the task is more likely to be successfully completed by the resource, converting the features to feature values based on a predefined mapping of features to feature values in a first memory device, determining, by a gradient boost tree model and based on a first current time and the feature values, a likelihood the resource will successfully complete the task, and scheduling the task to be performed by the resource based on the determined likelihood.

Abstract: Generally discussed herein are devices, systems, and methods for task routing. A method can include receiving, from a resource, a request for a task, in response to receiving the request, determining whether to retrieve a new task of new tasks stored in a first queue or a backlog task of backlog tasks stored in a second queue based on a combined amount of backlog tasks and new tasks relative to a capacity of the resource or the resources, retrieving the new task or the backlog task from the determined first queue or second queue, respectively, based on the determination, and providing the retrieved task to the resource.

Abstract: Generally discussed herein are devices, systems, and methods for scheduling tasks to be completed by resources. A method can include identifying features of the task, the features including a time-dependent feature and a time-independent feature, the time-dependent feature indicating a time the task is more likely to be successfully completed by the resource, converting the features to feature values based on a predefined mapping of features to feature values in a first memory device, determining, by a gradient boost tree model and based on a first current time and the feature values, a likelihood the resource will successfully complete the task, and scheduling the task to be performed by the resource based on the determined likelihood.

Abstract: A processing unit can acquire datasets from respective data sources, each having a respective unique data domain. The processing unit can determine values of a plurality of features based on the plurality of datasets. The processing unit can modify input-specific parameters or history parameters of a computational model based on the values of the features. In some examples, the processing unit can determine an estimated value of a target feature based at least in part on the modified computational model and values of one or more reference features. In some examples, the computational model can include neural networks for several input sets. An output layer of at least one of the neural networks can be connected to the respective hidden layer(s) of one or more other(s) of the neural networks. In some examples, the neural networks can be operated to provide transformed feature value(s) for respective times.

Abstract: Generally discussed herein are devices, systems, and methods for task routing. A method can include receiving, from a resource, a request for a task, in response to receiving the request, determining whether to retrieve a new task of new tasks stored in a first queue or a backlog task of backlog tasks stored in a second queue based on a combined amount of backlog tasks and new tasks relative to a capacity of the resource or the resources, retrieving the new task or the backlog task from the determined first queue or second queue, respectively, based on the determination, and providing the retrieved task to the resource.

Abstract: Generally discussed herein are devices, systems, and methods for scheduling tasks to be completed by resources. A method can include identifying features of the task, the features including a time-dependent feature and a time-independent feature, the time-dependent feature indicating a time the task is more likely to be successfully completed by the resource, converting the features to feature values based on a predefined mapping of features to feature values in a first memory device, determining, by a gradient boost tree model and based on a first current time and the feature values, a likelihood the resource will successfully complete the task, and scheduling the task to be performed by the resource based on the determined likelihood.

Abstract: A system that analyses content of electronic communications may automatically extract requests or commitments from the electronic communications. In one example process, a processing component may analyze the content to determine one or more meanings of the content; query content of one or more data sources that is related to the electronic communications; and based, at least in part, on (i) the one or more meanings of the content and (ii) the content of the one or more data sources, automatically identify and extract a request or commitment from the content. Multiple actions may follow from initial recognition and extraction, including confirmation and refinement of the description of the request or commitment, and actions that assist one or more of the senders, recipients, or others to track and address the request or commitment, including the creation of additional messages, reminders, appointments, or to-do lists.

Abstract: A deep learning network is trained to automatically analyze enterprise data. Raw data from one or more global data sources is received, and a specific training dataset that includes data exemplary of the enterprise data is also received. The raw data from the global data sources is used to pre-train the deep learning network to predict the results of a specific enterprise outcome scenario. The specific training dataset is then used to further train the deep learning network to predict the results of a specific enterprise outcome scenario. Alternately, the raw data from the global data sources may be automatically mined to identify semantic relationships there-within, and the identified semantic relationships may be used to pre-train the deep learning network to predict the results of a specific enterprise outcome scenario.

Abstract: Methods, systems, and computer programs are presented for evaluating the accuracy of predictive systems and quantifiable measures of incremental value. One method provides a scientific solution to test and evaluate predictive systems in a transparent, rigorous, and verifiable way to allow decision-makers to better decide whether to adopt a new predictive system. In one example, objects to be evaluated are assigned to a control group or an experiment group. The testing provides an equal or better distribution of scores in the control group for the scores obtained with the first predictor, but the method aims at maximizing the scores of objects obtained with the second predictor in the experiment group. Since the first scores are evenly distributed in both groups, any result improvements may be attributed to the better accuracy of the second predictor when the results of the experiment group are better than the results of the control group.