US 11,989,488 B2
Automatically and intelligently exploring design spaces
David Allan White, San Jose, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Jul. 30, 2020, as Appl. No. 16/943,126.
Claims priority of provisional application 63/010,438, filed on Apr. 15, 2020.
Prior Publication US 2021/0326494 A1, Oct. 21, 2021
Int. Cl. G06F 30/12 (2020.01); G06F 30/27 (2020.01); G06N 20/00 (2019.01)
CPC G06F 30/12 (2020.01) [G06F 30/27 (2020.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method for generating new product designs comprising:
receiving, from a user device of a user, a request for a digital component for presentation at the user device;
receiving a data set of user-provided information regarding a particular product design;
generating, based on the data set of user-provided information, a visual representation mapping design factors that represent subjective characteristics of the particular product design to a continuous shape representing potential product design geometries;
segmenting the visual representation into a plurality of segments based on values of the design factors;
selecting a segment of the visual representation that contains less than a threshold amount of data points from the data set;
selecting a digital component that solicits information from the user;
dynamically altering, based on the selected segment of the visual representation, a presentation of the digital component such that the dynamically-altered digital component solicits information from the user about the segment of the visual representation that contains less than the threshold amount of data points;
distributing, for presentation at the user device, the dynamically-altered digital component;
obtaining, from the user device and by way of a feedback mechanism, feedback information regarding the segment of the visual representation that contains less than the threshold amount of data points; and
modifying a value of a given design factor of the particular product design based, at least in part, on the feedback information obtained from the user to create a modified product design.