US 12,260,433 B2
Systems and methods for automatically generating remarketing lists
Bharath Pattabiraman, Santa Clara, CA (US); and Ardian Poernomo, San Jose, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by GOOGLE LLC, Mountain View, CA (US)
Filed on Jan. 4, 2022, as Appl. No. 17/568,713.
Application 17/568,713 is a continuation of application No. 16/787,779, filed on Feb. 11, 2020, granted, now 11,216,852.
Application 16/787,779 is a continuation of application No. 14/984,341, filed on Dec. 30, 2015, granted, now 10,565,627.
Prior Publication US 2022/0129953 A1, Apr. 28, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 30/0241 (2023.01); G06Q 30/0207 (2023.01); G06Q 30/0251 (2023.01); G06Q 30/0601 (2023.01)
CPC G06Q 30/0277 (2013.01) [G06Q 30/0222 (2013.01); G06Q 30/0253 (2013.01); G06Q 30/0641 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A system for automatically generating remarketing lists based on sessions, comprising: one or more processors and a memory, the one or more processors configured to: receive reporting data associated with client device visits to information resources, the reporting data being generated via execution of online reporting scripts embedded in the information resources;
identify, based on the received reporting data, one or more client sessions, each client session of the one or more client sessions corresponding to a client device visiting one or more information resources;
determine, from each client session of the one or more client sessions and based on the received reporting data, a plurality of information resource pairs, each information resource pair of the plurality of information resource pairs including a destination information resource and a referrer information resource from which the client device visited the destination information resource;
construct, using the one or more client sessions, a graph including the plurality of information resource pairs and a respective plurality of edges between the destination information resources and corresponding referrer information resources of the plurality of information resource pairs, wherein each edge of the plurality of edges represents an interaction metric based on a number of client devices that visited the destination information resource of the respective information resource pair from the corresponding referrer information resource of the respective information resource pair, and wherein at least one pair of the plurality of information resource pairs includes a conversion information resource;
implement a graph clustering module to select, from the plurality of information resource pairs and based on (i) the interaction metrics represented by the corresponding edges and (ii) a number of edges between at least some information resources in the plurality of information resource pairs and the conversion information resource, a subset of information resource pairs, wherein the interaction metrics include weights of click-through rates between the referrer information resource and the destination information resource of the plurality of information resource pairs; and
generate a client identifier list including one or more client device identifiers each associated with a respective client session of the one or more client sessions that visited a corresponding referrer information resource of at least one information resource pair of the subset of information resource pairs.