US 12,333,558 B2
Techniques for generating analytics reports
Matthew Thompson Walter, Ladera Ranch, CA (US); Michael Joseph Valenty, Carlsbad, CA (US); Sundardas Samuel Dorai-Raj, Campbell, CA (US); Moshe Lichman, Costa Mesa, CA (US); Manish Agrawal, Sunnyvale, CA (US); Joseph Kelly, Brooklyn, NY (US); Michael Andrew Wallace, San Francisco, CA (US); and Stephen Paul Ganem, Huntington Beach, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Appl. No. 17/925,486
Filed by Google LLC, Mountain View, CA (US)
PCT Filed Jun. 17, 2022, PCT No. PCT/US2022/034017
§ 371(c)(1), (2) Date Nov. 15, 2022,
PCT Pub. No. WO2023/244244, PCT Pub. Date Dec. 21, 2023.
Prior Publication US 2024/0232913 A1, Jul. 11, 2024
Int. Cl. G06Q 10/00 (2023.01); G06Q 30/0201 (2023.01); G06Q 30/0601 (2023.01)
CPC G06Q 30/0201 (2013.01) [G06Q 30/0633 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A computer-implemented method, the method comprising:
accessing, by one or more computing devices, a plurality of unidentified events, the plurality of unidentified events having a total number of unidentified events, and wherein each event in the plurality of unidentified events being associated with one or more properties;
calculating, using a machine-learned prediction model, a number of pseudo users associated with the plurality of unidentified events based on an event-to-user-ratio and the total number of unidentified events, calculating, using the machine-learned prediction model, a number of sessions associated with the plurality of unidentified events based on an event-to-session-ratio and the total number of unidentified events, wherein the machine-learned prediction model determines the event-to-session-ratio based on data derived from a plurality of identified events associated with identified users of the website that have accepted identifiers when browsing the website;
assigning, using the machine-learned prediction model, a first event from the plurality of unidentified events to a first pseudo user based on the one or more properties of the first event;
generating an analytics report for a website, the analytics report includes information derived from the number of pseudo users, the number of sessions, and the first event being assigned to the first pseudo user; and
adjusting a parameter of the machine-learned prediction model based data derived from the analytics report, the data derived from the analytics report includes the number of pseudo users or the number of sessions.