US 12,105,747 B2
Automatic content generation
Weixin Cai, Bothell, WA (US); Si-Qing Chen, Bellevue, WA (US); Michel Galley, Seattle, WA (US); William Brennan Dolan, Kirkland, WA (US); Christopher J. Brockett, Kirkland, WA (US); Zhang Li, Bellevue, WA (US); Warren A. Aldred, Redmond, WA (US); Xinyu He, Lynnwood, WA (US); Jesse Alexander Freitas, Seattle, WA (US); and Kaushik Ramaiah Narayanan, Bellevue, WA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Jun. 9, 2022, as Appl. No. 17/836,456.
Claims priority of provisional application 63/347,004, filed on May 30, 2022.
Prior Publication US 2023/0385320 A1, Nov. 30, 2023
Int. Cl. G06F 16/338 (2019.01); G06F 16/332 (2019.01); G06F 16/335 (2019.01); G06F 18/22 (2023.01); G06F 40/253 (2020.01); G06F 40/30 (2020.01); G06N 20/00 (2019.01)
CPC G06F 16/338 (2019.01) [G06F 16/3326 (2019.01); G06F 16/335 (2019.01); G06F 18/22 (2023.01); G06F 40/253 (2020.01); G06F 40/30 (2020.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by an editor system via an editor user interface component displayed on a client device of a user, a signal containing a plurality of logical inputs regarding a topic and an indication of one or more customization selections for customizing draft content that will be generated based on the plurality of logical inputs, the signal generated based on entry of the plurality of logical inputs in a bullet point format in an input portion of the editor user interface component and based on one or more selections made via customization fields, or options displayed relative to the input portion on the editor user interface component;
in response to receiving the signal containing the plurality of logical inputs and the indication of the one or more customization selections, triggering a content generator of the editor system to generate the draft content using one or more machine learning (ML) models, the generating comprising:
applying the plurality of logical inputs to a first ML model of the one or more ML models to identify a writing style of the user from a plurality of machine-learned writing styles;
applying the plurality of logical inputs to a second ML model of the one or more ML models to determine a context and direction for the draft content; and
based on the plurality of logical inputs, the indication of the one or more customization selections, the identified writing style, and the context and direction, generating, by the content generator, 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; and
causing presentation of the draft content in the editor user interface component.