公开(公告)号：US20170177337A1

公开(公告)日：2017-06-22

申请号：US14979085

申请日：2015-12-22

Applicant: Yahoo! Inc.

Inventor： Shahar Golan ,  Oren Shlomo Somekh ,  Michal Aharon

IPC: G06F9/30 ,  G06Q30/02 ,  G06F17/30

CPC classification number: G06Q30/0277 ,  G06F16/2237 ,  G06F16/2455 ,  G06F16/248

Abstract: Briefly, embodiments disclosed herein may relate to digital content selection, and more particularly to weighted pseudo-random digital content selection for use in and/or with online digital content delivery, such as online advertising, for example.

公开(公告)号：US20160110646A1

公开(公告)日：2016-04-21

申请号：US14519273

申请日：2014-10-21

Applicant: Yahoo! Inc.

Inventor： Oren Shlomo Somekh ,  Shahar Golan ,  Nadav Golbandi ,  Zohar Karnin ,  Oleg Rokhlenko ,  Oren Anava ,  Ronny Lempel

IPC: G06N5/04 ,  G06Q30/06

Abstract: Method, system, and programs for estimating interests of a plurality of users with respect to a new piece of information are disclosed. In one example, historical interests of the plurality of users are obtained with respect to one or more existing pieces of information. One or more users are selected from the plurality of users. Historical interests of the one or more users can minimize an objective function over the plurality of users. Interests of the one or more users are obtained with respect to the new piece of information. Estimated interests of the plurality of users are generated with respect to the new piece of information based on the obtained interests of the one or more users.

Abstract translation: 公开了用于估计关于新信息的多个用户的兴趣的方法，系统和程序。 在一个示例中，针对一个或多个现有的信息获得多个用户的历史兴趣。 从多个用户中选择一个或多个用户。 一个或多个用户的历史兴趣可以使多个用户的目标功能最小化。 获得关于新的信息的一个或多个用户的兴趣。 基于获得的一个或多个用户的兴趣，针对新的信息片段生成多个用户的估计兴趣。

公开(公告)号：US20170083522A1

公开(公告)日：2017-03-23

申请号：US14857258

申请日：2015-09-17

Applicant: Yahoo! Inc.

Inventor： Oren Shlomo Somekh ,  Michal Aharon ,  Shahar Golan ,  Noa Avigdor-Elgrabli ,  Dana Drachsler Cohen

IPC: G06F17/30 ,  G06F3/0484 ,  G06N99/00

CPC classification number: G06F17/3053 ,  G06F3/04842 ,  G06F17/30324 ,  G06F17/30867 ,  G06N99/005

Abstract: Systems and methods for building a latent item vector and item bias for a new item in a collaborative filtering system are disclosed. The method includes dividing incoming users into intervals with each interval having a learning phase and a selection phase. The learning phase scores each incoming user according to a best estimate latent vector and bias and saves the highest score. In the selection each incoming user is scored and a user exceeding the highest score is selected. The best estimate latent vector and bias is then updated based on the user's vector and bias, and the user's interaction with the item. The updated best estimate latent vector is then used in further intervals for learning and selecting users.