US Patent Application 17836456. AUTOMATIC CONTENT GENERATION simplified abstract

AUTOMATIC CONTENT GENERATION

Organization Name

Microsoft Technology Licensing, LLC==Inventor(s)==

[[Category:Weixin Cai of Bothell WA (US)]]

[[Category:Si-Qing Chen of Bellevue WA (US)]]

[[Category:Michel Galley of Seattle WA (US)]]

[[Category:William Brennan Dolan of Kirkland WA (US)]]

[[Category:Christopher J. Brockett of Kirkland WA (US)]]

[[Category:Zhang Li of Bellevue WA (US)]]

[[Category:Warren A. Aldred of Redmond WA (US)]]

[[Category:Xinyu He of Lynnwood WA (US)]]

[[Category:Jesse Alexander Freitas of Seattle WA (US)]]

[[Category:Kaushik Ramaiah Narayanan of Bellevue WA (US)]]

AUTOMATIC CONTENT GENERATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 17836456 titled 'AUTOMATIC CONTENT GENERATION

Simplified Explanation

The patent application describes a system and method for generating contextually relevant content in a user's writing style.

• The system receives logical inputs in bullet point format regarding a specific topic.
• A content generator uses machine learning models to generate draft content.
• The user's writing style is identified by applying the logical inputs to a machine learning model.
• The system determines the context and direction for the draft content using another machine learning model.
• Based on the logical inputs, identified writing style, context, and direction, at least one paragraph of draft content is generated in the user's writing style.
• The draft content follows an outline associated with the bullet point format and has the same context and direction as the logical inputs.
• The generated draft content is presented on a client device.

Original Abstract Submitted

Systems and methods are directed to generating content that is contextually relevant in a writing style of a user. In example embodiments, a plurality of logical inputs regarding a topic is received in bullet point format. A content generator generates draft content using machine learning (ML) models. The generating comprises identifying a writing style of the user by applying the plurality of logical inputs to a first ML model, determining a context and direction for the draft content using a second ML model, and based on the plurality of logical inputs, the identified writing style, and the context and direction, generating at least one paragraph of draft content in the writing style of the user that follows an outline associated with the bullet point format and comprises a same context and direction as the plurality of logical inputs. The draft content is then presented at a client device.