Alan C Ross

US Patent:

20220245322, Aug 4, 2022

Filed:

Jan 29, 2021

Appl. No.:

17/163162

Inventors:

- San Francisco CA, US
Owen Winne Schoppe - Orinda CA, US
Xing Han - Austin TX, US
Michael Reynolds Sollami - Cambridge MA, US
Brian J. Lonsdorf - Moss Beach CA, US
Alan Martin Ross - San Francisco CA, US
David J. Woodward - Bozeman MT, US
Sonke Rohde - San Francisco CA, US

International Classification:

G06F 40/103
G06F 40/284
G06T 11/60
G06N 3/04

Abstract:

An online system generates a set of content item variations for a reference content item that include different styles of text for the content item. The different styles of text are generated by applying machine-learned style transfer models, for example, neural network based models to reference text of the reference content item. The text variations retain the textual content of the reference text but are synthesized with different styles. The online system can provide the content item variations to users on an online experimental platform to collect user interaction information that may indicate how users respond to different styles of text. The online system or the content providers can effectively target users with content items that include the style of text the users respond to based on the collected information.

US Patent:

20220222046, Jul 14, 2022

Filed:

Jun 22, 2021

Appl. No.:

17/354439

Inventors:

- San Francisco CA, US
Sönke Rohde - San Francisco CA, US
Brian J. Lonsdorf - Moss Beach CA, US
Jessica Lundin - Seattle WA, US
David J. Woodward - Bozeman MT, US
Alan Martin Ross - San Francisco CA, US
Michael Sollami - Cambridge MA, US

International Classification:

G06F 8/20
G06N 20/00
G06F 9/451
G06F 8/38

Abstract:

Techniques are disclosed relating to automatically synthesizing user interface (UI) component instances. In disclosed techniques a computer system receives a set of existing UI elements and a set of design rules for the set of existing elements, where design rules in the set of design rules indicate one or more allowed states for respective UI elements in the set of existing UI elements. The one or more allowed states may correspond to one or more visual characteristics. Using the set of existing UI elements, the computer system may then automatically generate a plurality of UI component instances based on the set of design rules, where a respective UI component instance includes a first UI element in a first allowed state. The computer system may then train, using the plurality of UI component instances, a machine learning model operable to automatically generate UI designs.

US Patent:

20230129240, Apr 27, 2023

Filed:

Jan 26, 2022

Appl. No.:

17/649045

Inventors:

- San Francisco CA, US
Sönke Rohde - San Francisco CA, US
Alan Martin Ross - San Francisco CA, US
David James Woodward - Bozeman MT, US
Jessica Lundin - Seattle WA, US
Owen Winne Schoppe - Orinda CA, US
Brian J. Lonsdorf - Soquel CA, US
Aashish Jain - Cambridge MA, US

International Classification:

G06F 9/451
G06F 9/54
G06N 3/08
G06N 3/04

Abstract:

Techniques are disclosed for automatically converting a layout image to a text-based representation. In the disclosed techniques, a server computer system receives a layout image that includes a plurality of portions representing a plurality of user interface (UI) elements included in a UI design. The server computer system transforms, via executed of a trained residual neural network (ResNet), the layout image to a text-based representation of the layout image that specifies coordinates of bounding regions of the plurality of UI elements included in the UI design, where the text-based representation is usable to generate program code executable to render the UI design. The disclosed techniques may advantageously automate one or more portions of a UI design process and, as a result save time and computing resources via the execution of an image to text-based conversion ResNet machine learning model.

US Patent:

20230129431, Apr 27, 2023

Filed:

Jan 26, 2022

Appl. No.:

17/649016

Inventors:

- San Francisco CA, US
Sönke Rohde - San Francisco CA, US
Alan Martin Ross - San Francisco CA, US
David James Woodward - Bozeman MT, US
Jessica Lundin - Seattle WA, US
Owen Winne Schoppe - Orinda CA, US
Brian J. Lonsdorf - Soquel CA, US
Aashish Jain - Cambridge MA, US

International Classification:

G06F 3/04845
G06N 3/04
G06V 10/771
G06V 10/762
G06V 10/82

Abstract:

Techniques are disclosed for automatically generating new content using a trained 1-to-N generative adversarial network (GAN) model. In disclosed techniques, a computer system receives, from a computing device, a request for newly-generated content, where the request includes current content. The computer system automatically generates, using the trained 1-to-N GAN model, N different versions of new content, where a given version of new content is automatically generated based on the current content and one of N different style codes, where the value of N is at least two. After generating the N different versions of new content, the computer system transmits them to the computing device. The disclosed techniques may advantageously automate a content generation process, thereby saving time and computing resources via execution of the 1-to-N GAN machine learning model.

US Patent:

20210334666, Oct 28, 2021

Filed:

Apr 22, 2020

Appl. No.:

16/854913

Inventors:

- San Francisco CA, US
Owen Winne Schoppe - Orinda CA, US
Alan Martin Ross - San Francisco CA, US
Brian J. Lonsdorf - Belmont CA, US
David James Woodward - Westfield IN, US
Sönke Rohde - San Francisco CA, US
Michael Reynolds Sollami - Cambridge MA, US
Chetan Ramaiah - Palo Alto CA, US

International Classification:

G06N 5/02
G06N 20/00
G06F 40/109
G06F 17/16

Abstract:

A textual properties model is used to infer values for certain font properties of interest given certain text-related data, such as rendered text images. The model may be used for numerous purposes, such as aiding with document layout, identifying font families that are similar to a given font families, and generating new font families with specific desired properties. In some embodiments, the model is trained from a combination of synthetic data that is labeled with values for the font properties of interest, and partially-labeled data from existing “real-world” documents.

US Patent:

20210240318, Aug 5, 2021

Filed:

Jan 31, 2020

Appl. No.:

16/778936

Inventors:

- San Francisco CA, US
Brian J. Lonsdorf - Belmont CA, US
Sönke Rohde - San Francisco CA, US
Alan Martin Ross - San Francisco CA, US
David James Woodward - Westfield IN, US
Jessica Lundin - Seattle WA, US

International Classification:

G06F 3/0484

Abstract:

Techniques are disclosed relating to generating a user interface (UI) migration plan, including intermediate UIs, for migrating from a current UI to a new UI. A computer system may receive information specifying a current UI and a new UI, and identify one or more differences between the current and the new UIs. Based on the differences, the computer system may generate information specifying one or more candidate intermediate UIs. The computer system may score the candidate intermediate UIs relative to a specified set of design criteria. The computer system may determine a UI migration plan that specifies a set of the one or more candidate intermediate UIs that are displayable in order to migrate from the current UI to the new UI, where the set of one or more intermediate UIs is selected based on the scoring. Use of the UI migration plan may advantageously reduce user interaction issues.

US Patent:

20210240319, Aug 5, 2021

Filed:

Jan 31, 2020

Appl. No.:

16/779290

Inventors:

- San Francisco CA, US
Sönke Rohde - San Francisco CA, US
Brian J. Lonsdorf - Belmont CA, US
Jessica Lundin - Seattle WA, US
David James Woodward - Westfield IN, US
Alan Martin Ross - San Francisco CA, US

International Classification:

G06F 3/0484

Abstract:

Techniques are disclosed relating to measuring presentation aspects of portions of a user interface (UI) that have been identified to be presented neutrally and automatically generating a new UI that reduces differences in the presentation aspects of the identified portions. Portions of the UI identified to be presented neutrally may include elements or content in the UI identified to be presented neutrally. Portions for neutral presentation may include portions of UI that, for example, portions that present legal decisions, portions with survey data, forms or information displays, or portions where a user is requested to make a choice between alternative options. Presentation aspects that may be measured include, for example, visual aspects, clarity aspects, or tonal aspects. Reducing the differences in the presentation aspects may present the elements or content with more neutrality to reduce influence in decisions due to visual, clarity, or tonal aspects between the elements or content.

US Patent:

20210240451, Aug 5, 2021

Filed:

Jan 31, 2020

Appl. No.:

16/779177

Inventors:

- San Francisco CA, US
Brian J. Lonsdorf - Belmont CA, US
Alan Martin Ross - San Francisco CA, US
Sönke Rohde - San Francisco CA, US
David James Woodward - Westfield IN, US
Jessica Lundin - Seattle CA, US

International Classification:

G06F 8/38
G06F 8/36
G06N 20/00
G06F 40/30

Abstract:

Techniques are disclosed relating to determining a similarity of components of a current user interface (UI) to new UI components for use in automatically generating a new UI. A computer system may receive information specifying a current UI including a particular current UI component and information specifying a plurality of new UI components for a new UI. The computer system may then identify characteristics of the particular current UI component. Based on these identified characteristics, the computer system may score ones of the plurality of new UI components, where the scoring is performed to determine a similarity to the particular current UI component. The computer system may then select, based on the scores, a particular new UI component from the plurality of new UI components for use, in the new UI, for the particular current UI component. Such techniques may advantageously improve user experience by automatically providing up-to-date user interfaces.

Address:

802 N Mechanic St, Monroe, IA 50170

Phone:

6415213464

VIN:

3FAHP0JA5BR201276

Make:

FORD

Model:

FUSION

Year:

2011