公开(公告)号：US20210264297A1

公开(公告)日：2021-08-26

申请号：US16800504

申请日：2020-02-25

Applicant: Oath Inc.

Inventor： Alexander Shtof ,  Yair Koren ,  Yohay Kaplan

IPC: G06N5/04 ,  G06N20/00 ,  G06N5/02 ,  G06F16/23 ,  G06F16/2457

Abstract: One or more computing devices, systems, and/or methods for content recommendation based upon continuity and grouping information of attributes are provided herein. User interaction data specifying whether users interacted with content items, user attributes of the users, and content attributes of the content items is obtained. A data structure is populated with the user interaction data. The data structure is modified by inserting a set of sub-fields into the data structure for a user attribute. A sub-field is populated with a value representing an option of the user attribute. The set of sub-fields are an encoding of continuity information and grouping information representing options for the user attribute. The data structure is processed using machine learning functionality to generate a model. The model is utilized to generate a prediction as to whether a user will interact with a content item.

公开(公告)号：US20200273095A1

公开(公告)日：2020-08-27

申请号：US16286812

申请日：2019-02-27

Applicant: Oath Inc.

Inventor： Yair Koren ,  Michal Aharon ,  Abraham Shahar ,  Assaf Keret ,  Tal Cohen ,  Yohay Kaplan

IPC: G06Q30/08

Abstract: One or more computing devices, systems, and/or methods for generating bid values are provided. A content item and/or a budget associated with the content item may be identified. A target spend data structure associated with the content item may comprise a plurality of target spend values associated with a plurality of sub-periods of time within a first instance of a period of time. A first update target spend value, associated with a second instance of a first sub-period of time, may be generated based upon a first budget factor calculation associated with the first instance of the first sub-period of time and a second budget factor calculation associated with the first instance of the period of time. A first bid value for presenting the first content item at the second instance of the first sub-period of time may be generated based upon the first update target spend value.