Music recommendations from trending queries

Patent metadata

Field	Value
Publication number	US-10846331-B2
Application number	US-201715719512-A
Country	US
Kind code	B2
Filing date	Sep 28, 2017
Priority date	Dec 29, 2016
Publication date	Nov 24, 2020
Grant date	Nov 24, 2020

Abstract

A plurality of entities relating to popular search queries are identified. A set of entities representing musical artists or events is selected from the plurality of entities. Based on a history of online actions of a user, a subset of the selected set of entities that is relevant to the user is determined, and personalized music recommendations are created for the user, where the personalized music recommendations comprise music content associated with the determined subset of entities that each represent a musical artist or event relating to the popular search queries. The personalized music recommendations are provided for presentation to the user.

First claim

What is claimed is:

1. A method for providing personalized music recommendations to a user, the method comprising:
identifying, by a processing device of a content sharing platform, a plurality of entities relating to popular search queries submitted via one or more search engine platforms, wherein
the content sharing platform enables sharing of music content between users, and
the plurality of entities include musical artists and other entities distinct from the musical artists;

selecting, by the processing device and from the identified plurality of entities, a set of entities that each represents a distinct musical artist relating the popular search queries;
obtaining, by the processing device, a history of online actions of the user on the content sharing platform;
determining, by the processing device, a subset of the selected set of entities based on the obtained history of online actions of the user, wherein each entity in the determined subset of entities is a distinct musical artist that is relevant to the user;
creating and storing on the content sharing platform, by the processing device, the personalized music recommendations for the user, the personalized music recommendations comprising music content associated with each of the determined subset of entities; and
providing, by the processing device, the personalized music recommendations over a network for presentation to the user, wherein at least one of the presented personalized music recommendations is to be selected by the user for consumption.

2. The method of claim 1 , wherein the popular search queries are search queries submitted by at least a threshold number of users via the one or more search engine platforms over a predefined time period, the one or more search engine platforms comprising at least one search engine platform that is external to the content sharing platform.

3. The method of claim 1 , wherein the distinct musical artist comprises one of a singer, a musician, a composer, a music video director, a music video producer, or a band.

4. The method of claim 1 , wherein the online actions of the user comprise one or more of submitting a search query, accessing a media item, or consuming a media item, wherein the consuming the media item comprises watching or listening to the media item.

5. The method of claim 1 , wherein the determining, based on the history of online actions of the user, the subset of the selected set of entities comprises;
identifying musical artists associated with the online actions of the user; and
determining whether any of the identified musical artists matches any of the selected set of entities relating to the popular search queries.

6. The method of claim 1 , wherein the creating the personalized music recommendations for the user comprises:
assigning a score to each of the determined subset of entities based on popularity of respective search queries and relevancy to the user.

7. The method of claim 6 , wherein the creating the personalized music recommendations for the user further comprises:
identifying music recommendation candidates that are ranked based on a plurality of factors; and
improving a rank of any of the identified music recommendation candidates that matches one of the determined subset of entities based on a score assigned to a respective entity of the determined subset of entities.

8. The method of claim 1 , further comprising:
identifying a reference to an artist profile associated with a respective entity in the determined subset of entities; and
providing the reference for presentation to the user together with the personalized music recommendations.

9. The method of claim 1 , further comprising:
identifying an online document indicating why a respective entity in the determined subset of entities is popular; and
providing a reference to the online document for presentation to the user together with the personalized music recommendations.

10. The method of claim 1 , further comprising:
creating a summary indicating why a respective entity in the determined subset of entities is popular; and
providing the summary for presentation to the user together with the personalized music recommendations.

11. The method of claim 1 , wherein the music content of the personalized music recommendations is at least one of a playlist or a channel.

12. A system for providing personalized music recommendations to a user, the system comprising:
a memory; and
a processing device of a content sharing platform, operatively coupled to the memory, the processing device is configured to:
identify a plurality of entities relating to popular search queries submitted via one or more search engine platforms, wherein
the content sharing platform enables sharing of music content between users, and
the plurality of entities include musical artists and other entities distinct from the musical artists;

select, from the identified plurality of entities, a set of entities that each represents a distinct musical artist relating the popular search queries;
obtain a history of online actions of the user on the content sharing platform;
determine a subset of the selected set of entities based on the retrieved history of online actions of the user, wherein each entity in the determined subset of entities is a distinct musical artist that is relevant to the user;
create and store, on the content sharing platform, the personalized music recommendations for the user, the personalized music recommendations comprising music content associated with each of the determined subset of entities;
provide the personalized music recommendations over a network for presentation to the user, wherein at least one of the personalized music recommendations is to be selected by the user for consumption.

13. The system of claim 12 , wherein to create the personalized music recommendations for the user, the processing device is configured to:
assign a score to each of the determined subset of entities based on popularity of respective search queries and relevancy to the user.

14. The system of claim 13 , wherein to create the personalized music recommendations for the user, the processing device is further configured to:
identify music recommendation candidates that are ranked based on a plurality of factors; and
improve a rank of any of the identified music recommendation candidates that matches one of the determined subset of entities based on the corresponding score assigned to a respective entity of the determined subset of entities.

Assignees

• Google Inc
• Google Llc

Inventors

• Ip Lawrence
• Marney Sean
• Jiang Shengwei
• Sharma Vivek
• Ranganathan Srivaths
• Wang Yuh-Jiun

Classifications

• G06F16/635 Primary

  Filtering based on additional data, e.g. user or group profiles · CPC title

• G06F16/686

  using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings · CPC title

• G06F16/639 Primary

  using playlists · CPC title

• G06F16/24578

  using ranking · CPC title

• G06F16/9535

  Search customisation based on user profiles and personalisation · CPC title