US 11,816,272 B2
Identifying touchpoint contribution utilizing a touchpoint attribution attention neural network
Zhenyu Yan, Cupertino, CA (US); Fnu Arava Venkata Kesava Sai Kumar, Cupertino, CA (US); Chen Dong, San Matteo, CA (US); Abhishek Pani, Sunnyvale, CA (US); and Ning Li, Seattle, WA (US)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Mar. 28, 2022, as Appl. No. 17/656,782.
Application 17/656,782 is a continuation of application No. 15/917,052, filed on Mar. 9, 2018, granted, now 11,287,894.
Prior Publication US 2022/0221939 A1, Jul. 14, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 30/00 (2023.01); G06F 3/01 (2006.01); G06N 3/08 (2023.01); G06F 3/0484 (2022.01); G06F 3/0481 (2022.01); H04L 67/50 (2022.01)
CPC G06F 3/017 (2013.01) [G06F 3/0481 (2013.01); G06F 3/0484 (2013.01); G06N 3/08 (2013.01); H04L 67/535 (2022.05)] 19 Claims
OG exemplary drawing
 
1. A method comprising:
generating a digital target touchpoint path of a target user, the digital target touchpoint path comprising a digital target touchpoint sequence of digital touchpoints;
generating an encoded touchpoint vector encoding the digital target touchpoint path via an encoding layer of a touchpoint attribution neural network;
determining a hidden state vector via the touchpoint attribution neural network from the encoded touchpoint vector, wherein the hidden state vector comprises historical contextual information of the digital target touchpoint path; and
generating target attention weights from the hidden state vector via a touchpoint attention layer of the touchpoint attribution neural network, wherein the target attention weights comprise attention coefficient values that indicate attribution levels for the digital touchpoints in the digital target touchpoint path.