Automatically generating music marketplace editorial content

• US 9,442,987 B2
• Filed: 08/18/2014
• Issued: 09/13/2016
• Est. Priority Date: 06/19/2012
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Nogues, Paul, Leang, Sebastien, Aroux, Damien, Millot, Manuel
• Primary Examiner(s): Luu, Le H
• Application Number:
  US14/462,071
• Publication Number:
  US 20140379732A1
• Time in Patent Office: 757 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/435 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/437 Administration of user profiles, e.g. generation, initialisation, adaptation, distribution
• CPC Class Codes: G06F 16/4393 Multimedia presentations, e.g. slide shows, multimedia albums
• CPC Class Codes: G06F 16/60 of audio data
• CPC Class Codes: G06F 16/638 Presentation of query results
• CPC Class Codes: G06F 16/68 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/7834 using audio features
• CPC Class Codes: H04N 21/252 Processing of multiple end-users' preferences to derive collaborative data
• CPC Class Codes: H04N 21/25883 being end-user demographical data, e.g. age, family status or address arrangements for identifying locations of users in broadcast systems H04H60/52
• CPC Class Codes: H04N 21/25891 being end-user preferences retrieval of video data in a video database based on user preferences G06F16/739; arrangements for recognizing users' preferences H04H60/46; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/8113 comprising music, e.g. song in MP3 format

Abstract

Example apparatus and methods concern automatically creating editorial content for albums that are to be recommended in a computerized music marketplace. An album may be selected for recommendation after analyzing consumption data (e.g., sales, downloads, samples), and popularity data (e.g., chart rankings, critical reviews). The popularity data may also include data mined from sources including search engines and social media sites. An overall recommendation score may be a weighted function of consumption data and popularity data. A customized recommendation score may be a weighted function of the overall recommendation score influenced by regional considerations, demographic considerations, and other considerations. The editorial content may include art and text and may be customized based on regional considerations, demographic considerations, and based on other art or text that will appear at the same time as the editorial content.

Claims

1. A method, comprising:

controlling an automated album scoring process to acquire static information for a set of albums and to acquire dynamic information for the set of albums;

controlling the automated album scoring process to select a genre for which an album recommendation is to be made, to select a region for which the album recommendation is to be made, and to select a demographic for which the album recommendation is to be made;

controlling the automated album scoring process to produce a raw score for a member of the set of albums as a function of the static information, the dynamic information, the genre, the region, and the demographic;

controlling an automated recommendation process to acquire a set of thresholds associated with recommendations in the music marketplace, and to acquire a set of time constraints associated with recommendations in the music marketplace, where the set of ratios, set of thresholds, and set of time constraints control, at least in part, whether an album will be recommended in the music marketplace;

controlling the automated recommendation process to acquire a set of weights that control, at least in part, the relative importance to a recommendation score of the genre, the region, the demographic, members of the set of thresholds, or members of the set of time constraints;

controlling the automated recommendation process to produce the recommendation score for the member of the set of albums as a function of the raw score, the set of thresholds, the set of time constraints, and the set of weights;

selecting the member of the set of albums as a recommended album based, at least in part, on the recommendation score, and

automatically generating editorial content for the music marketplace for the recommended album.

2. The method of claim 1, where the static information includes an artist name for an album, a genre for an album, a release date for an album, a length of an album, a language for the lyrics on an album, cover art for an album, or artist art for an album.

3. The method of claim 1, where the dynamic information includes a consumption data for an album, a review for an album, a ranking for an album, a search-based popularity indicia for an album, a web-site traffic-based popularity indicia for an album, a social media-based popularity indicia for an album, a previous popularity score for an album, or information provided by a distributor of an album.

4. The method of claim 3, comprising controlling the automated recommendation process to produce the recommendation score as a function of a previous recommendation score.

5. The method of claim 4, comprising controlling the automated recommendation process to produce the recommendation score as a function of a change in consumption or a change in popularity attributed to a previous recommendation score.

6. The method of claim 1, where the genre partitions the music marketplace by music type, where the region geographically partitions the music marketplace, where the classification partitions the music marketplace by release date, and where the demographic partitions purchasers by identifiable criteria including age, sex, or location.

7. The method of claim 1, where the set of thresholds limit recommendations based on the number of times the album has been recommended previously, the number of consecutive times the album has been recommended, or the number of albums by an artist that are currently recommended.

8. The method of claim 1, where the set of time constraints limit recommendations based, at least in part, on a release date associated with an album.

9. The method of claim 1, where the set of weights control the relative importance of the genre, the region, the classification, the demographic, the set of ratios, the set of thresholds, or the set of time constraints.

10. The method of claim 1, where the editorial content comprises cover art, artist art, and customized text, and where the customized text is customized as a function of the static information, the dynamic information, the genre, the region, the classification, or the demographic.

11. The method of claim 1, comprising:

controlling the automated scoring process and the automated recommendation process to reside on a server, and

making the editorial content available to a client.

12. The method of claim 1, where the set of weights are user configurable.

13. An apparatus, comprising:

a processor;

a memory;

a set of logics that facilitate automated production of editorial content for an album to be recommended to a music marketplace; and

an interface that connects the processor, the memory, and the set of logics,

the set of logics comprising;

a first logic that analyzes consumption data for the album, the consumption data including data describing a number of sales, data describing a number of downloads, data describing a number of samples, data describing a number of streams, or data describing a number of plays;

a second logic that analyzes popularity data for the album, the popularity data including data describing search engine relevance, and data describing social media relevance;

a third logic that produces an overall recommendation score for the album as a function of the consumption data;

a fourth logic that produces a customized recommendation score for the album; and

a fifth logic that selectively provides editorial content for the album to a music marketplace, where the editorial content includes art and text,

where the fourth logic produces the customized recommendation score as a function of the overall recommendation score as influenced by a demographic consideration and the popularity data.

14. An apparatus, comprising:

a processor;

a memory;

a set of logics that facilitate automated production of editorial content for an album to be recommended to a music marketplace; and

an interface that connects the processor, the memory, and the set of logics,

the set of logics comprising;

a first logic that analyzes consumption data for the album, the consumption data including data describing a number of sales, data describing a number of downloads, data describing a number of samples, data describing a number of streams, or data describing a number of plays;

a second logic that analyzes popularity data for the album, the popularity data including data describing search engine relevance, and data describing social media relevance;

a third logic that produces an overall recommendation score for the album as a function of the consumption data;

a fourth logic that produces a customized recommendation score for the album; and

a fifth logic that selectively provides editorial content for the album to a music marketplace, where the editorial content includes art and text,

where the fourth logic produces the customized recommendation score as a function of the overall recommendation score as influenced by a demographic consideration and the popularity score; and

where the fifth logic provides the editorial content to a music marketplace in a customized form, where the customized form depends, at least in part, on the regional consideration, the demographic consideration, and the membership in a set of recommended albums.