US 12,327,150 B2
On-device privatization of multi-party attribution data
Ryan M. Rogers, Los Gatos, CA (US); Man Chun D. Leung, Daly City, CA (US); David Pardoe, Mountain View, CA (US); Bing Liu, San Jose, CA (US); Shawn F. Ren, Knoxville, TN (US); Rahul Tandra, Santa Clara, CA (US); Parvez Ahammad, San Jose, CA (US); Jing Wang, Los Altos, CA (US); Ryan T. Tecco, Philadelphia, PA (US); and Yajun Wang, Sunnyvale, CA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Nov. 1, 2022, as Appl. No. 17/978,933.
Prior Publication US 2024/0143416 A1, May 2, 2024
Int. Cl. G06F 3/00 (2006.01); G06F 9/54 (2006.01); G06F 21/64 (2013.01)
CPC G06F 9/54 (2013.01) [G06F 21/645 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
at a first computing device associated with a user, (i) receiving and storing on the first computing device, first event data associated with a login to a first party application, (ii) receiving and storing on the first computing device, second event data representing a click, in the first party application, on a link to a third party application, (iii) receiving and storing on the first computing device, third event data from the third party application, (iv) converting the third event data to a label selected from a set of available labels that are each represented by a compressed format comprising at least one bit, (v) mapping the compressed format of the labeled third event data to the first event data and the second event data to create an instance of multi-party attribution data, (vi) grouping multiple instances of the multi-party attribution data into a batch, (vii) adding noise to the compressed format of the labeled third event data in the batch using a differentially private algorithm, and (viii) sending the noisy batch of multi-party attribution data to a second computing device;
applying a debiasing algorithm to the noisy batch of multi-party attribution data; and
at a second computing device, using the debiased noisy batch of multi-party attribution data to train at least one machine learning model to produce output that can be used to control a content distribution.