Microsoft Technology Licensing, LLC

Andres Monroy-Hernandez

Todd D Newman

Michael Brian Palmer

Pamela Bhattacharya

Justin Brooks Cranshaw

Mayerber Loureiro De Carvalho Neto

Benjamin Gene Cheung

Charles Yin-che Lee

William L Portnoy

Lars Hasso Liden

Daniel James Driscoll

Emad Mohamed Hamdy Elwany

A software agent, that is used to assist in providing a service, receives communications from a set of users that are attempting to use the software agent. The communications include communications that are interacting with the software agent, and communications that are not interacting with the software agent. The software agent performs natural language processing on all communications to identify such things as user sentiment, user concerns or other items in the content of the messages, and also to identify actions taken by the users in order to obtain a measure of user satisfaction with the software agent. One or more action signals are then generated based upon the identified user satisfaction with the software agent.

Signal analysis in a conversational scheduling assistant computing system

A set of nodes are organized into a graph to represent a workflow to enable the dynamic and directed management of that workflow in a decentralized system. Each node maintains a value necessary for execution of the workflow, and includes code to populate that value. A workflow agent manages the population of the values according to an identified dependency structure for the nodes relative to the workflow. As changes are made to the workflow, the workflow agent ensures that values and dependencies of the nodes stay up-to-date. Each node retains historic values, which enables the workflow agent to query several states of the workflow throughout time as changes are made thereto. The dynamic management of the nodes improves the responsiveness of the system to changes, thereby improving computational efficiency.

Dynamic directed graph workflows

In order to complete user instructions beyond the scope of services that are provided on the user's own computing device, a framework an interaction framework for executing user instructions with online services is provided. The framework includes an instruction processing agent that interacts with a user agent on a computer user's computing device to execute instructions provided to the user agent. The instruction processing agent maintains a list of domain agents, each domain agent corresponding to a domain. Upon receiving a user instruction (from a user agent), the instruction processing agent identifies a suitable domain and corresponding domain agent for completing the user instruction and provides the instruction to the domain agent. The domain agent identifies an online service suitable for completing the user instruction and interfaces with the online service via a proxy for the online service to carry out the user instruction.

Interaction framework for executing user instructions with online services

An outsourcing environment is described herein by which an outsourcing entity may delegate document-transformation tasks to at least one worker entity, while preventing the worker entity from gaining knowledge of sensitive items that may be contained within a non-obfuscated original document (NOD). In one example, the environment may transform the NOD into an obfuscated original document (OOD) by removing sensitive items from the NOD. The worker entity may perform formatting and/or other document-transformation tasks on the OOD, without gaining knowledge of the sensitive items in the NOD, to produce an obfuscated transformed document (OTD). The environment may then allow for the outsourcing entity to view a content-restored version of the OTD.

Outsourcing document-transformation tasks while protecting sensitive information

Growing community of inventors

Seattle, WA, United States of America

Andres Monroy-Hernandez