Microsoft Technology Licensing, LLC

Dan Bohus

Eric J Horvitz

Dinei A Florencio

Douglas Guimarães Macharet

Semiha Ece Kamar Eden

Stephanie Rosenthal Pomerantz

Alejandro Acero

Xiao Li

Geoffrey G Zweig

Douglas Guimaraes Macharet

The subject disclosure is directed towards processing evidence, which may include high-dimensional streaming evidence, into a future belief state. The existing evidence is used to project a belief about a future state. The future belief state may be used to determine whether to wait for additional evidence, or to act now without waiting for additional evidence, e.g., based on a cost of the delay. For example, an autonomous assistant may decide based upon the belief whether to engage a person or not, or to wait for more information before the engagement decision is made.

Value of information with streaming evidence based on a prediction of a future belief at a future time

Technologies pertaining to human-robot interaction are described herein. The robot includes a computer-readable memory that comprises a model that, with respect to successful completions of a task, is fit to observed data, where at least some of such observed data pertains to a condition that is controllable by the robot, such as position of the robot or distance between the robot and a human. A task that is desirably performed by the robot is to cause the human to engage with the robot. The model is updated while the robot is online, such that behavior of the robot adapts over time to increase the likelihood that the robot will successfully complete the task.

Adapting robot behavior based upon human-robot interaction

Described is a technology by which a structured model of repetition is used to determine the words spoken by a user, and/or a corresponding database entry, based in part on a prior utterance. For a repeated utterance, a joint probability analysis is performed on (at least some of) the corresponding word sequences as recognized by one or more recognizers) and associated acoustic data. For example, a generative probabilistic model, or a maximum entropy model may be used in the analysis. The second utterance may be a repetition of the first utterance using the exact words, or another structural transformation thereof relative to the first utterance, such as an extension that adds one or more words, a truncation that removes one or more words, or a whole or partial spelling of one or more words.

Structured models of repetition for speech recognition

Individuals may interact with automated services as one or more parties, where such individuals may have collective (as well as individual) intents. Moreover, parties may concurrently communicate with the interface, and the interface may have to manage several concurrent interactions with different parties. Single-individual interfaces may be unable to react robustly to such dynamic and complex real-world scenarios. Instead, multi-party interfaces to service components may be devised that identify individuals within a scene, associate the individuals with parties, track a set of interactions of the parties with the service component, and direct the service component in interacting with the parties. A multi-party interface may also detect and politely handle interruptions, and may identify information items about individuals and parties based on context and history, prioritize the intents of the individuals and parties, and triage interactions accordingly.

Growing community of inventors

Kirkland, WA, United States of America

Dan Bohus