公开(公告)号：US11580099B2

公开(公告)日：2023-02-14

申请号：US17038395

申请日：2020-09-30

Applicant: Microsoft Technology Licensing, LLC

Inventor： Wenxiang Chen ,  William Tang ,  Runfang Zhou ,  Tanvi Sudarshan Motwani ,  Jeremy Lwanga ,  Sara Smoot Gerrard ,  Daniel Sairom Krishnan Hewlett ,  Alexandre Patry ,  Songtao Guo ,  Sai Krishna Bollam

IPC: G06F16/00 ,  G06F16/242 ,  G06K9/62 ,  G06F16/9032 ,  G06F16/9035

Abstract: Methods are presented for providing dynamic search filter suggestions that are updated and ranked based on the user filter selections. One method includes detecting a query received in a user interface (UI), calculating, by a search-candidate model, first search results, and calculating, by a suggestions model, first filter suggestions for filter categories to filter responses to the query. The suggestions model is obtained by training a machine-learning algorithm utilizing pairwise learning-to-rank modeling. The first search results and the first filter suggestions are presented in the UI. When a selection in the UI of a filter suggestion is detected, the search-candidate model calculates second search results for the filter categories based on the query and the selected filter suggestion, and the suggestions model calculates second first filter suggestions based on the query and the selected filter suggestion. The second search results and the second filter suggestions are presented in the UI.

公开(公告)号：US20220100746A1

公开(公告)日：2022-03-31

申请号：US17038395

申请日：2020-09-30

Applicant: Microsoft Technology Licensing, LLC

Inventor： Wenxiang Chen ,  William Tang ,  Runfang Zhou ,  Tanvi Sudarshan Motwani ,  Jeremy Lwanga ,  Sara Smoot Gerrard ,  Daniel Sairom Krishnan Hewlett ,  Alexandre Patry ,  Songtao Guo ,  Sai Krishna Bollam

IPC: G06F16/242 ,  G06F16/9035 ,  G06F16/9032 ,  G06K9/62

Abstract: Methods are presented for providing dynamic search filter suggestions that are updated and ranked based on the user filter selections. One method includes detecting a query received in a user interface (UI), calculating, by a search-candidate model, first search results, and calculating, by a suggestions model, first filter suggestions for filter categories to filter responses to the query. The suggestions model is obtained by training a machine-learning algorithm utilizing pairwise learning-to-rank modeling. The first search results and the first filter suggestions are presented in the UI. When a selection in the UI of a filter suggestion is detected, the search-candidate model calculates second search results for the filter categories based on the query and the selected filter suggestion, and the suggestions model calculates second first filter suggestions based on the query and the selected filter suggestion. The second search results and the second filter suggestions are presented in the UI.

公开(公告)号：US10733243B2

公开(公告)日：2020-08-04

申请号：US15691623

申请日：2017-08-30

Applicant: Microsoft Technology Licensing, LLC

Inventor： Runfang Zhou ,  Ajit Paul Singh ,  Anish Ramdas Nair ,  Sen Zhou ,  Vladislav Tcheprasov ,  Sachin Hosmani ,  Da Teng

IPC: G06F16/00 ,  G06F16/951 ,  G06Q50/00

Abstract: A system, a machine-readable storage medium storing instructions, and a computer-implemented method described herein are directed to a Similar Profiles Engine. The Similar Profiles Engine generates an inverted index query based on one or more portions of profile data of a target member account of a social network service. The Similar Profiles Engine identifies respective profile data, of one or more candidate member accounts in the social network service, that maps to at least one inverted index filter, the at least one inverted index filter matching at least a portion of the inverted index query. The Similar Profiles Engine calculates a similarity score between each respective candidate member account and the target member account, and causes a display of identifiers of one or more candidate member accounts in a user interface of a client device based on respective similarity scores.