Techniques to respond to user requests using natural-language machine learning based on branching example conversations

US10866978B2 · kind B2 · utility

Assignee

• FACEBOOK, INC. · US

Inventors

• Martin Jean Raison · San Francisco, US
• Willy Blandin · San Francisco, US
• Andreea-Loredana Crisan · San Francisco, US
• Stepan Parunashvili · Boiceville, US
• Kemal El Moujahid · Mountain View, US
• Laurent Nicolas Landowski · Menlo Park, US

Key dates

• Filing date: Dec 27, 2016
• Grant date: Dec 15, 2020
• Expiry date: Jun 3, 2039

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N3/006
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Techniques to response to respond to user requests using natural-language machine learning based on branching example conversations are described. In one embodiment, an apparatus may comprise a bot application interface component operative to receive an example-interaction repository, the example-interaction repository comprising a plurality of example user-to-bot interactions, including one or more branching example user-to-bot interactions; and an interaction processing component operative to generate a linearized example-interaction repository by replacing the one or more branching example user-to-bot interactions with the plurality of linearized example user-to-bot interactions; submit the example-interaction repository to a natural-language machine learning component; and receive a sequence model from the natural-language machine learning component in response to submitting the example-interaction repository; and a client communication component operative to perform a user-to-bot conversation based on the sequence model. Other embodiments are described and claimed.