Sri International

Melinda Gervasio

Karen L Myers

Bart Peintner

Neil Yorke-Smith

Thomas J Lee

Chih-Hung Yeh

Adam John Cheyer

Patrick Denis Lincoln

Kenneth C Nitz

Thierry Donneau-Golencer

Grit Denker

Rukman Senanayake

John James Byrnes

Dayne B Freitag

Steven Mark Eker

Hung H Bui

Mei Marker

Daniel Sanchez

Stephen L Hardt

Eric Yeh

Leslie Pound

Daniel Elenius

Robert Sasseen

David Morley

Janet Murdock

Shahin Saadati

Matthew Crossley

Boone Adkins

Rodrigo De Salvo Braz

Pauline M Berry

In general, the disclosure describes techniques for identifying sequences of user actions from event data and logs of user actions for at least one user of a computing system. In one example, a system includes a sequence mining unit that processes event data and logs of user actions for at least one user of a computing system to obtain a set of one or more candidate action sequences each comprising a sequence of one or more user actions. A sequence filtering unit of the system applies, to the set of one or more candidate action sequences, one or more filters informed by a model of user actions for an application domain to obtain a set of one or more filtered action sequences to improve a quality of action sequences identified by the system. An output device of the system outputs an indication of the set of one or more filtered action sequences usable for generating at least one automated workflow or information usable for improving a workflow.

User action sequence recognition using action models

In general, the disclosure describes various aspects of techniques for evaluating decisions determined by autonomous devices. A device comprising a memory and a processor may be configured to perform the techniques. The memory may store first state data representative of a first observational state detected by an autonomous device, and first action data representative of one or more first actions the autonomous device performs responsive to detecting the first observational state. The processor may execute a computation engine configured to identify, based on the first action data, a first inflection point representative of changing behavior of the autonomous device. The computation engine may further be configured to determine, based on the first inflection point, first explanatory data representative of portions of the first state data on which the autonomous device relied that explain the changing behavior of the autonomous device, and output the first explanatory data.

Explaining behavior by autonomous devices

Techniques are disclosed for training a machine learning model to perform actions within an environment. In one example, an input device receives a declarative statement. A computation engine selects, based on the declarative statement, a template that includes a template action performable within the environment. The computation engine generates, based on the template, synthetic training episodes. The computation engine further generates experiential training episodes, each experiential training episode collected by a machine learning model from past actions performed by the machine learning model. Each synthetic training episode and experiential training episode comprises an action and a reward. A machine learning system trains, with the synthetic training episodes and the experiential training episodes, the machine learning model to perform the actions within the environment.

Synthetic training examples from advice for training autonomous agents

Mathematical technologies for recommending content to a user based on a user's preferences are disclosed. Embodiments of these technologies can generate a probabilistic representation of a data set, and then adjust the probabilistic representation to reflect a user-specific weighting scheme. The user preference-adjusted representation of the data set can be used to recommend content to the user.

Similarity metric relativized to a user's preferences

The present invention relates to an electronic assistant. In one embodiment, a system for processing data on a computing device includes at least one extractor for extracting data from an email to produce extracted data, a user model for generating a high-level model of an email environment on the computing device, based on the extracted data, and at least one predictor for generating a prediction related to the email, based on the extracted data and on the high-level model. In another embodiment, a system for scheduling an event includes an extractor for extracting constraints from a request for the event, a user model for receiving and storing scheduling preferences from a user, and a predictor coupled to the extractor and to the user model, for generating a candidate schedule for the event in accordance with the constraints and the scheduling preferences.

Electronic assistant for making predictions based on user messages

A device, method and system for monitoring, predicting, and accelerating interactions with a computing device includes determining a current interaction context at a computing device based on interactions occurring at the computing device, predicting a number of potential subsequent interactions, speculatively executing at least some of the potential subsequent interactions, and presenting interactive representations of the speculatively-executed interactions at the computing device.

Device, method and system for monitoring, predicting, and accelerating interactions with a computing device

The present invention relates to a method and apparatus for assisting with automated task management. In one embodiment, an apparatus for assisting a user in the execution of a task, where the task includes one or more workflows required to accomplish a goal defined by the user, includes a task learner for creating new workflows from user demonstrations, a workflow tracker for identifying and tracking the progress of a current workflow executing on a machine used by the user, a task assistance processor coupled to the workflow tracker, for generating a suggestion based on the progress of the current workflow, and a task executor coupled to the task assistance processor, for manipulating an application on the machine used by the user to carry out the suggestion.

Method and apparatus for automated assistance with task management

Growing community of inventors

Mountain View, CA, United States of America

Melinda Gervasio