Personalized search result rankings

Patent metadata

Field	Value
Publication number	US-2020192951-A1
Application number	US-201816219791-A
Country	US
Kind code	A1
Filing date	Dec 13, 2018
Priority date	Dec 13, 2018
Publication date	Jun 18, 2020
Grant date	—

Abstract

The present concepts relate to an improved personalized search engine that can generate personalized rankings of search results in view of individual user's personal preferences and interests. Information about a segment of online content is collected. Certain activities by a user are tracked, including search queries submitted by the user, search results clicked on by the user, and/or web pages browsed by the user. From these activities, the user's preferences relating the segment are inferred using the collected segment information. When the user conducts a search directed to the segment, certain search results that the user is more likely to be interested in, based on the user's preferences, are ranked higher to generate the personalized rankings.

First claim

1 . A system, comprising:
one or more databases storing:
segment information associated with a segment, the segment information including information about entities relating to the segment; and
user preference information associated with a user, the user preference information including tags that correspond to the entities in the segment information, the tags having confidence values as measurements of the user's preferences with respect to the corresponding entities;
one or more hardware processors; and at least one computer-readable storage medium storing computer-readable instructions which, when executed by the one or more hardware processors, cause the one or more hardware processors to:
receive activity history of the user;
generate the user preference information based at least on the activity history and the segment information;
receive a search query from the user;
generate search results responsive to the search query;
determine that the search query is directed to the segment based at least on the search query or the search results;
inferring a user preference for a particular search result by determining that the particular search result relates to a particular entity in the segment information for which a corresponding tag exists in the user preference information;
rank the search results by promoting a ranking of the particular search result based at least on a particular confidence value associated with the corresponding tag to generate personalized rankings of the search results reflecting the promoted ranking of the particular search result; and
provide the personalized rankings of the search results to the user.

2 . The system of claim 1 , wherein the segment relates to one of:
showtimes, retail shopping, sports, or flights.

3 . The system of claim 1 , wherein the information about the entities are stored in one or more entity graphs.

4 . The system of claim 1 , wherein the entities in the segment information have entity identifiers and the corresponding tags in the user preference information have matching entity identifiers.

5 . The system of claim 1 , wherein the activity history comprises at least one of: a query history, a click history, or a browse history.

6 . The system of claim 5 , wherein:
the click history comprises satisfactory clicks and excludes dissatisfactory clicks; and the satisfactory clicks are distinguished from the dissatisfactory clicks based at least on dwell times.

7 . The system of claim 1 , wherein the activity history falls within a specified time period.

8 . The system of claim 1 , wherein the user preference information is stored in a user graph.

9 . The system of claim 1 , wherein a degree to which the ranking of the particular search result is promoted is based at least on the particular confidence value.

10 . A method, comprising:
receiving segment information containing information about entities related to a segment; receiving activity history of a user; generating tags and associated confidence values based at least on the activity history and the segment information, the tags corresponding to the entities in the segment information; storing the tags and the associated confidence values in user preference information; receiving a search query from the user; obtaining search results based at least on the search query; determining that the search query is directed to the segment based at least on the search query or the search results; inferring a user preference for a particular search result by determining that the particular search result relates to a particular entity in the segment information for which there is a corresponding tag in the user preference information; promoting a ranking of the particular search result based at least on a particular confidence value associated with the corresponding tag to generate personalized rankings of the search results; and sending the personalized rankings of the search results to the user.

11 . The method of claim 10 , wherein generating the tags and the associated confidence values comprises:
determining that the activity history relates to the entities in the segment information.

12 . The method of claim 10 , wherein receiving the activity history comprises:
receiving at least one of a query history, a click history, or a browse history.

13 . The method of claim 12 , wherein generating the tags and the associated confidence values comprises:
analyzing a web page associated with the click history or the browse history to determine that the web page relates to one or more of the entities in the segment information, wherein the tags correspond to the one or more of the entities.

14 . The method of claim 10 , wherein generating the confidence values comprises:
using a machine-learning model to calculate the confidence values as a measure of the user's preferences for the associated tags that correspond to the entities in the segment information.

15 . The method of claim 10 , further comprising:
receiving updated activity history of the user; and updating the user preference information based at least on the updated activity history.

16 . The method of claim 10 , wherein determining that the particular search result relates to the particular entity comprises:
parsing and analyzing contents of a web page associated with the particular search result.

17 . The method of claim 10 , wherein promoting the ranking of the particular search result comprises:
using a machine-learning model to increase the ranking of the particular search result, wherein an amount of the increase is based at least on the particular confidence value.

18 . A computer-readable storage medium comprising instructions which, when executed by one or more hardware processors, cause the one or more hardware processors to perform a process, comprising:
storing segment information associated with a segment, the segment information including information about entities relating to the segment, the entities having entity identifiers; receiving activity history of a user; generating user preference information associated with the user based at least on the activity history and the segment information, the user preference information including tags having entity identifiers that match the entity identifiers in the segment information, the tags being associated with confidence values that measure the degrees to which the user prefers the corresponding entities in the segment information; receiving a search query from the user; obtaining search results responsive to the search query; classifying the search query as being directed to the segment based at least on the search query or the search results; analyzing a web page associated with a particular search result to identify a particular entity in the segment information that relates to the particular search result; finding a particular tag in the user preference that corresponds to the particular entity based at least on a particular entity identifier associated with the particular entity; increasing a ranking of the particular search result based at least on a particular confidence value associated with the particular tag; generating personalized rankings of the search results based at least on the increased ranking of the particular search result; and sending the personalized rankings of the search results to the user.

19 . The computer-readable storage medium of claim 18 , wherein the instructions further cause the one or more hardware

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Singhal Aman
• De Barros Marcelo
• Srinivasan Prithvishankar

Classifications

• G06F16/9024

  Graphs; Linked lists (G06F16/9027 takes precedence) · CPC title

• G06F16/9538

  Presentation of query results · CPC title

• G06F16/908

  using metadata automatically derived from the content · CPC title

• G06N20/00

  Machine learning · CPC title

• G06N5/04

  Inference or reasoning models · CPC title