公开(公告)号：US20200211057A1

公开(公告)日：2020-07-02

申请号：US16236180

申请日：2018-12-28

Applicant: Oath Inc.

Inventor： Deguang Kong ,  Jian Yang

IPC: G06Q30/02

Abstract: Advertisement budgets are often apportioned over an advertisement period, such as apportioning fixed increments of the budget over subperiods of the advertisement period. Each allocation of the budget may be used for auctions of advertisement opportunities during the subperiod. However, fixed apportioning may not be responsive to the actual user response, and manual adjustment of the budget may provide an efficient allocation in view of an advertiser's response target, resulting in overspending, underspending (wherein resulting user response fails to meet a response target), and/or inefficient allocation of the budget. Instead, a server may measure the user response during a first advertisement subperiod, extrapolate the user response over the advertisement period, and compare the extrapolated user response to the response target. Based on the comparison, budget allocation during a second advertisement subperiod may be adjusted by an allocation offset that adapts the allocation of the advertisement budget to the response target.

公开(公告)号：US10672025B2

公开(公告)日：2020-06-02

申请号：US15064310

申请日：2016-03-08

Applicant: Oath Inc.

Inventor： Suleyman Cetintas ,  Pengyuan Wang ,  Jian Yang ,  Puneet Mohan Sangal

IPC: G06Q30/02

Abstract: Systems, devices, and methods are disclosed for determining the quality of traffic received from different web page publishers, and setting a pricing structure for the different traffic based on the determined quality of traffic. Accurately determining the quality of traffic and/or clicks from different publishers allows the network system described herein to offer a fair marketplace with just return on investments (ROI) for advertisers, and offer a robust and accurate traffic quality based pricing model for publishers. Internet based technology, and in particular deep learning techniques available through a neural network, are utilized to determine the pricing structure based on click and/or web page traffic quality measurements generated through the deep learning techniques.