US 12,457,268 B2
Fast estimation of downloads for apps at launch
Paul Ernest Stolorz, Los Altos, CA (US); Tadaishi Yatabe Rodriguez, Uppsala (SE); and Abbie Marin Popa, Oakland, CA (US)
Assigned to Data.ai Inc., San Francisco, CA (US)
Filed by DATA.AI INC., San Francisco, CA (US)
Filed on Mar. 21, 2022, as Appl. No. 17/700,179.
Claims priority of provisional application 63/165,674, filed on Mar. 24, 2021.
Prior Publication US 2022/0311834 A1, Sep. 29, 2022
Int. Cl. H04L 67/50 (2022.01)
CPC H04L 67/535 (2022.05) 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
installing, by one or more processors, a first instance of a tracking application on a first client device including:
enabling automated data collection by the first instance of the tracking application from a memory of the first client device, the tracking application generating engagement data based on automatically accessing an application install flag in the memory of the first client device;
determining, by the one or more processors, a plurality of client devices that have downloaded the tracking application, each instance of the tracking application tracking engagement with one or more software applications based on an application install flag on a corresponding client device, the plurality of client devices including the first client device;
receiving, by the one or more processors, the engagement data from the tracking application installed on each client device of a set of client devices among the plurality of client devices, the set of client devices being fewer in quantity than the plurality of client devices, the engagement data indicating the engagement with the one or more software applications executed on the set of client devices during a first time interval;
detecting, by the one or more processors, a software application of the one or more software applications was launched as available for download within the first time interval from a network-based server providing software application publication based on the engagement data;
based on detecting, from the engagement data, that the software application was launched as available for download, determining, by the one or more processors, a preliminary install base for the software application for the first time interval based on a quantity of installs in the plurality of client devices based on the quantity of the set of client devices reporting the engagement data for the first time interval and a historical rate of client devices reporting engagement data for other software applications;
determining, by the one or more processors, based on the preliminary install base for the software application for the first time interval, whether an engagement for the software application is greater than a threshold engagement value; and
responsive to determining that the engagement for the software application is greater than the threshold engagement value, determining, by the one or more processors, based on the preliminary install base for the software application for the first time interval, an estimated number of downloads for the software application during the first time interval.