公开(公告)号：US20170161276A1

公开(公告)日：2017-06-08

申请号：US14960172

申请日：2015-12-04

Applicant: Facebook, Inc.

Inventor： Max Christian Eulenstein ,  Lauren Elizabeth Scissors ,  Alexander Peysakhovich ,  Lars Seren Backstrom ,  Lu Wang

IPC: G06F17/30

CPC classification number: G06F17/30867 ,  G06F17/3053 ,  G06Q50/01

Abstract: A social networking system builds a quality controlled and desired population-representative pool of human raters to provide ratings on content items to improve a feed ranking model used for providing its users with more relevant content. The system identifies a pool of candidate human raters for providing ratings on a feed of content items. For each candidate human rater of the pool of candidate human raters, the system presents a feed of content items based on a feed ranking model, obtains ratings on the feed of content items, and determines a score representing the consistency of the obtained ratings, the representativeness of the pool of human raters, or the relevance of the content provided by the ranking model. The system uses the computed scores to modify the ranking model used to present content to its users for improving the relevance of the presented content.

公开(公告)号：US20170161667A1

公开(公告)日：2017-06-08

申请号：US14960179

申请日：2015-12-04

Applicant: Facebook, Inc.

Inventor： Max Christian Eulenstein ,  Lauren Elizabeth Scissors ,  Alexander Peysakhovich ,  Lars Seren Backstrom ,  Lu Wang

IPC: G06Q10/06 ,  G06Q50/00 ,  G06F17/30

CPC classification number: G06Q10/06398 ,  G06Q50/01

Abstract: A social networking system builds a quality controlled and desired population-representative pool of human raters to provide ratings on content items to improve a feed ranking model used for providing its users with more relevant content. The system identifies a pool of candidate human raters for providing ratings on a feed of content items. For each candidate human rater of the pool of candidate human raters, the system presents a feed of content items based on a feed ranking model, obtains ratings on the feed of content items, and determines a score representing the consistency of the obtained ratings, the representativeness of the pool of human raters, or the relevance of the content provided by the ranking model. The system uses the computed scores to modify the ranking model used to present content to its users for improving the relevance of the presented content.

公开(公告)号：US10540627B2

公开(公告)日：2020-01-21

申请号：US14960179

申请日：2015-12-04

Applicant: Facebook, Inc.

Inventor： Max Christian Eulenstein ,  Lauren Elizabeth Scissors ,  Alexander Peysakhovich ,  Lars Seren Backstrom ,  Lu Wang

IPC: G06Q10/06 ,  G06Q50/00

Abstract: A social networking system builds a quality controlled and desired population-representative pool of human raters to provide ratings on content items to improve a feed ranking model used for providing its users with more relevant content. The system identifies a pool of candidate human raters for providing ratings on a feed of content items. For each candidate human rater of the pool of candidate human raters, the system presents a feed of content items based on a feed ranking model, obtains ratings on the feed of content items, and determines a score representing the consistency of the obtained ratings, the representativeness of the pool of human raters, or the relevance of the content provided by the ranking model. The system uses the computed scores to modify the ranking model used to present content to its users for improving the relevance of the presented content.

公开(公告)号：US10120945B2

公开(公告)日：2018-11-06

申请号：US14960172

申请日：2015-12-04

Applicant: Facebook, Inc.

Inventor： Max Christian Eulenstein ,  Lauren Elizabeth Scissors ,  Alexander Peysakhovich ,  Lars Seren Backstrom ,  Lu Wang

IPC: G06F17/30 ,  G06Q50/00

Abstract: A social networking system builds a quality controlled and desired population-representative pool of human raters to provide ratings on content items to improve a feed ranking model used for providing its users with more relevant content. The system identifies a pool of candidate human raters for providing ratings on a feed of content items. For each candidate human rater of the pool of candidate human raters, the system presents a feed of content items based on a feed ranking model, obtains ratings on the feed of content items, and determines a score representing the consistency of the obtained ratings, the representativeness of the pool of human raters, or the relevance of the content provided by the ranking model. The system uses the computed scores to modify the ranking model used to present content to its users for improving the relevance of the presented content.

公开(公告)号：US20170161277A1

公开(公告)日：2017-06-08

申请号：US14960181

申请日：2015-12-04

Applicant: Facebook, Inc.

Inventor： Max Christian Eulenstein ,  Lauren Elizabeth Scissors ,  Alexander Peysakhovich ,  Lars Seren Backstrom ,  Lu Wang ,  Virot Chiraphadhanakul

IPC: G06F17/30

CPC classification number: G06F16/9535 ,  G06Q30/0282 ,  G06Q50/01

Abstract: A social networking system builds a quality controlled and desired population-representative pool of human raters to provide ratings on content items to improve a feed ranking model used for providing its users with more relevant content. The system identifies a pool of candidate human raters for providing ratings on a feed of content items. For each candidate human rater of the pool of candidate human raters, the system presents a feed of content items based on a feed ranking model, obtains ratings on the feed of content items, and determines a score representing the consistency of the obtained ratings, the representativeness of the pool of human raters, or the relevance of the content provided by the ranking model. The system uses the computed scores to modify the ranking model used to present content to its users for improving the relevance of the presented content.