公开(公告)号：US20190163808A1

公开(公告)日：2019-05-30

申请号：US15826644

申请日：2017-11-29

Applicant: Microsoft Technology Licensing, LLC

Inventor： Charu Jangid ,  Wei Wang ,  Aayush Gopal Dawra ,  Mahesh Vishwanath ,  Qiang Wu ,  Kirill Talanine ,  Robert Gibson ,  Monica Cai ,  Warren Bartolome ,  James Michael Fell

IPC: G06F17/30

Abstract: Techniques for reducing electronic resource consumption using search data are disclosed herein. In some embodiments, a computer-implemented method comprises: identifying a cohort of profiles from profiles based on a determination that at least one attribute is shared among the profile data of the cohort; receiving corresponding search appearance data including an impression count for the cohort of profiles; selecting reference profiles from the cohort based on the impression counts of the reference profiles; selecting a target profile from the cohort based on the impression count of the target profile; identifying a trend corresponding to at least one feature among the reference profiles; and causing an indication of the feature(s) to be displayed on a computing device of the user of the target profile based on the identifying of the trend.

公开(公告)号：US10733210B2

公开(公告)日：2020-08-04

申请号：US15826644

申请日：2017-11-29

Applicant: Microsoft Technology Licensing, LLC

Inventor： Charu Jangid ,  Wei Wang ,  Aayush Gopal Dawra ,  Mahesh Vishwanath ,  Qiang Wu ,  Kirill Talanine ,  Robert Gibson ,  Monica Cai ,  Warren Bartolome ,  James Michael Fell

IPC: G06F16/00 ,  G06F16/28 ,  G06F16/248 ,  G06F16/2457 ,  G06F16/958

Abstract: Techniques for reducing electronic resource consumption using search data are disclosed herein. In some embodiments, a computer-implemented method comprises: identifying a cohort of profiles from profiles based on a determination that at least one attribute is shared among the profile data of the cohort; receiving corresponding search appearance data including an impression count for the cohort of profiles; selecting reference profiles from the cohort based on the impression counts of the reference profiles; selecting a target profile from the cohort based on the impression count of the target profile; identifying a trend corresponding to at least one feature among the reference profiles; and causing an indication of the feature(s) to be displayed on a computing device of the user of the target profile based on the identifying of the trend.

公开(公告)号：US20190108209A1

公开(公告)日：2019-04-11

申请号：US15825657

申请日：2017-11-29

Applicant: Microsoft Technology Licensing, LLC

Inventor： Karan Ashok Ahuja ,  Befekadu Ayenew Ejigou ,  Ningfeng Liang ,  Lokesh P. Bajaj ,  Wei Wang ,  Paul Fletcher ,  Wei Lu ,  Shaunak Chatterjee ,  Souvik Ghosh ,  Yang Li ,  Wei Deng ,  Qiang Wu

IPC: G06F17/24 ,  G06F15/18 ,  G06Q50/00 ,  H04L29/08

Abstract: In an example, first and second machine learned models corresponding to a particular context of a social networking service are obtained, the first machine learned model trained via a first machine learning algorithm to output an indication of importance of a social networking profile field to obtaining results in the particular context, and the second machine learned model trained via a second machine learning algorithm to output a propensity of the user to edit a social networking profile field if requested. One or more missing fields in a social networking profile for the user are identified. For each of one or more of the one or more missing fields, the field and an identification of the user are passed through the first and second machine learned models, and outputs of the first and second machine learned models are combined to identify one or more top missing profile fields.

公开(公告)号：US10678997B2

公开(公告)日：2020-06-09

申请号：US15825657

申请日：2017-11-29

Applicant: Microsoft Technology Licensing, LLC

Inventor： Karan Ashok Ahuja ,  Befekadu Ayenew Ejigou ,  Ningfeng Liang ,  Lokesh P. Bajaj ,  Wei Wang ,  Paul Fletcher ,  Wei Lu ,  Shaunak Chatterjee ,  Souvik Ghosh ,  Yang Li ,  Wei Deng ,  Qiang Wu

IPC: G06F17/00 ,  G06F40/174 ,  G06Q50/00 ,  G06N20/00 ,  H04L29/08

Abstract: In an example, first and second machine learned models corresponding to a particular context of a social networking service are obtained, the first machine learned model trained via a first machine learning algorithm to output an indication of importance of a social networking profile field to obtaining results in the particular context, and the second machine learned model trained via a second machine learning algorithm to output a propensity of the user to edit a social networking profile field if requested. One or more missing fields in a social networking profile for the user are identified. For each of one or more of the one or more missing fields, the field and an identification of the user are passed through the first and second machine learned models, and outputs of the first and second machine learned models are combined to identify one or more top missing profile fields.