公开(公告)号：US20190188740A1

公开(公告)日：2019-06-20

申请号：US15849364

申请日：2017-12-20

Applicant: Facebook, Inc.

Inventor： Hongzheng Xiong ,  Pravin Paratey ,  Brian Rosenthal ,  Abhishek Agarwal ,  Daniel Kristopher Harvey ,  Damien Lefortier

IPC: G06Q30/02 ,  H04L29/08 ,  G06F15/18

CPC classification number: G06Q30/0203 ,  G06N20/00 ,  G06Q30/0201 ,  G06Q30/0254 ,  H04L67/306

Abstract: An online system displays a first set of content items to a user of a test group and displays a second set of content items to a user of a control group. The online system presents a poll to each user to evaluate the user's recall of the content item associated with the poll. The online system receives a poll response from each user, which is input, along with a set of features associated each user, into a prediction model. The prediction model enables the online system to determine a poll response prediction of a third user based on a set of features associated with the third user. The poll response prediction enables the online system to determine if it would be effective to present the content item to the third user.

公开(公告)号：US10452701B2

公开(公告)日：2019-10-22

申请号：US15808168

申请日：2017-11-09

Applicant: Facebook, Inc.

Inventor： Hongzheng Xiong

IPC: G06F16/35 ,  G06Q30/02 ,  G06N20/00

Abstract: An online system generates a hierarchical taxonomy including multiple levels arranged in order of increasing specificity, in which each level includes one or more topics with which a content item maintained in the online system may be associated. Based on information associated with presentations of content items to online system users, which may indicate the users' familiarity with the content items, the online system predicts a likelihood that a particular user is familiar with information associated with one or more content items associated with a topic. Based at least in part on the predicted likelihood, the online system generates a connection between the user and the topic, in which the connection corresponds to a predicted level of knowledge that the user has about the topic. The online system may later retrieve the user's predicted level of knowledge about the topic (e.g., to select content for presentation to the user).

公开(公告)号：US20190138651A1

公开(公告)日：2019-05-09

申请号：US15808168

申请日：2017-11-09

Applicant: Facebook, Inc.

Inventor： Hongzheng Xiong

IPC: G06F17/30 ,  G06Q30/02

CPC classification number: G06F16/353 ,  G06N20/00 ,  G06Q30/0277

Abstract: An online system generates a hierarchical taxonomy including multiple levels arranged in order of increasing specificity, in which each level includes one or more topics with which a content item maintained in the online system may be associated. Based on information associated with presentations of content items to online system users, which may indicate the users' familiarity with the content items, the online system predicts a likelihood that a particular user is familiar with information associated with one or more content items associated with a topic. Based at least in part on the predicted likelihood, the online system generates a connection between the user and the topic, in which the connection corresponds to a predicted level of knowledge that the user has about the topic. The online system may later retrieve the user's predicted level of knowledge about the topic (e.g., to select content for presentation to the user).