Methods and systems for utilizing contextual feedback to generate and modify playlists

• US 7,962,482 B2
• Filed: 04/27/2006
• Issued: 06/14/2011
• Est. Priority Date: 05/16/2001
• Status: Expired due to Term

• Current Assignee: Pandora Media LLC (Liberty Media Corporation)
• Original Assignee: Pandora Media Incorporated (Liberty Media Corporation)
• Inventors: Conrad, Thomas J., Kennedy, Joseph J., Handman, Etienne F., Westergren, Timothy B.
• Primary Examiner(s): Trujillo; James
• Assistant Examiner(s): Black; Linh
• Application Number:
  US11/380,563
• Publication Number:
  US 20060212444A1
• Time in Patent Office: 1,874 Days
• Field of Search: 707/100, 707/102, 707/758, 707/784
• US Class Current: 707/733
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/40 of multimedia data, e.g. slideshows comprising image and additional audio data retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70
• CPC Class Codes: G06F 16/634 Query by example, e.g. query by humming
• CPC Class Codes: G06F 16/639 using playlists
• CPC Class Codes: G06F 16/64 Browsing; Visualisation therefor generation of a list or set of audio data G06F16/638
• 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 16/686 using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
• CPC Class Codes: G06F 16/687 using geographical or spatial information, e.g. location
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G11B 27/034 on discs G11B27/036, G11B27/038 take precedence
• CPC Class Codes: G11B 27/10 Indexing; Addressing; Timing or synchronising; Measuring tape travel
• CPC Class Codes: G11B 27/105 of operating discs
• CPC Class Codes: G11B 27/11 by using information not detectable on the record carrier

Abstract

Systems and methods of generating and modifying a playlist using contextual information are disclosed. For example, a user may provide an input seed such as a song name or artist name. The input seed is compared to database items and a playlist is generated as a result. In some examples, the contextual information is used to enhance the comparison and to select better content objects for a user'"'"'s playlist. Meanwhile, in some examples the content objects in the playlist may be arranged in an enhanced order using ranking and/or contextual information.

Claims

1. A tangible computer-readable medium having computer-executable instructions that causes one or more processors to perform a method comprising:

storing, in an electronic memory, feedback from a plurality of users about a first content object, wherein the first content object is stored in an electronic content server;

storing, in the electronic memory, contextual information relating to context in which the feedback about the first content object was provided, where the contextual information is independent of characteristics of the first content object;

calculating a suitability quotient of the first content object based on the contextual information, wherein the suitability quotient is;

a sum of feedback provided about the first content object based on the contextual information where the feedback is positive,

less a sum of feedback provided about the first content object based on the contextual information where the feedback is negative,

divided by a total number of times the first content object was transmitted to a user terminal;

storing, in the electronic memory, the suitability quotient;

utilizing the feedback, the contextual information, and the suitability quotient to generate a playlist of content objects; and

transmitting from the electronic content server each of the contents objects to a user terminal, wherein the transmitting is in response to the user terminal requesting content.

2. The computer-readable medium of claim 1 wherein the feedback comprises positive, negative, and neutral feedback, and the threshold amount is one thousand.

3. The computer-readable medium of claim 1 wherein the contextual information comprises information relating to the first content object in the context of at least one of the following:

particular artist, particular album, and particular station.

4. The computer-readable medium of claim 1 wherein the contextual information comprises information relating to the first content object in the context of characteristics of a second content object.

5. The computer-readable medium of claim 1 wherein the contextual information comprises information relating to the first content object in the context of an extrinsic factor, wherein the extrinsic factor comprises at least one of the following:

temporal factor, geographic factor, and demographic factor.

6. The computer-readable medium of claim 1 wherein the contextual information comprises at least one of the following:

station on which the first content object was playing when the feedback was provided, name of a second content object played immediately prior to the first content object when the feedback was provided, artist of the second content object played immediately prior to the first content object when the feedback was provided, and a musicological characteristic of the second content object played immediately prior to the first content object when the feedback was provided, location of a user when the feedback was provided, age of the user when the feedback was provided, gender of the user when the feedback was provided, a time of day when the feedback was provided, and a day of week when the feedback was provided.

7. A computer-implemented method of generating a playlist at an electronic playlist server, comprising:

comparing, using a processor, an input seed, which is sent from a user terminal, to a first database item stored in the electronic playlist server, wherein the first database item corresponds to a first content object stored in an electronic content server;

retrieving from the electronic playlist server feedback that is associated with contextual information related to the first content object, wherein the feedback includes feedback provided about a plurality of content objects;

retrieving values indicating suitability of each of the plurality of content objects in the context of the first content object, wherein the value indicating suitability is;

a sum of feedback provided about the particular content object in the context of the first content object where the feedback is positive,

less a sum of feedback provided about the particular content object in the context of the first content object where the feedback is negative,

divided by a sum of the sum of feedback where the feedback is positive and the sum of feedback where the feedback is negative;

selecting more than one content objects from the plurality of content objects for the playlist based on at least the values indicating suitability, wherein sequence of playback of the more than one content objects of the playlist is determined using at least the values indicating suitability of each of the more than one content objects of the playlist; and

transmitting from the electronic content server a first of the more than one content objects of the playlist to a player at the user terminal in accordance with the sequence of playback.

8. The method of claim 7 wherein the contextual information comprises information relating to the at least one of the following:

particular artist, and particular album of the first content object.

9. The method of claim 7 wherein the contextual information comprises information relating to the first content object in the context of a second content object.

10. The method of claim 7 wherein the contextual information comprises information relating to the first content object in the context of characteristics of a second content object.

11. The method of claim 7 wherein the contextual information comprises information relating to the first content object in the context of at least one extrinsic factor, where the at least one extrinsic factor comprises at least one of the following:

temporal, geographic, and demographic factors.

12. A method comprising:

storing, in a first computer memory, feedback about a first content object from at least one user;

storing, in a second computer memory, contextual information relating to context in which the feedback about the first content object was provided, where the contextual information is independent of characteristics of the first content object and the at least one user providing the feedback;

retrieving, using a processor in an electronic playlist server, the feedback in the first computer memory and contextual information in the second computer memory;

generating, using the processor in the electronic playlist server, a playlist of a plurality of content objects using at least the feedback, wherein order of playback of the first content object of the plurality of content objects in the playlist is determined using at least the contextual information;

transmitting from an electronic content server using a content engine each of the plurality of content objects to a player in accordance with the order of playback;

storing a suitability quotient of the first content object based on at least the feedback and contextual information relating to a particular context in which the feedback was provided, wherein the suitability quotient is;

a sum of all feedback provided about the first content object while in the particular context where all the feedback is positive,

less a sum of all feedback provided about the first content object while in the particular context-where all the feedback is negative,

divided by a total number of times the first content object was transmitted to a user terminal; and

retrieving the suitability quotient;

wherein the generating a playlist of content objects further includes using the suitability quotient.

13. A computerized apparatus, comprising:

a computer memory configured to store feedback from a plurality of users about a first content object and contextual information relating to a context in which the feedback about the first content object was provided;

an electronic playlist component comprising a processor configured to;

calculate and store a suitability quotient of the first content object based on the contextual information, wherein the suitability quotient is;

a sum of feedback provided about the first content object based on the contextual information where the feedback is positive,

less a sum of feedback provided about the first content object based on the contextual information where the feedback is negative,

divided by a sum of the sum of feedback where the feedback is positive and the sum of feedback where the feedback is negative;

retrieve the feedback, the contextual information, and the suitability quotient for use in generating a playlist, if the sum of positive feedback plus the sum of negative feedback exceeds a threshold amount; and

generate an playlist of content objects; and

an electronic content component comprising a content engine configured to transmit each of the content objects of the playlist of content objects to a media player.

14. The computerized apparatus of claim 13, wherein the first content object of the playlist of content objects is transmitted in accordance with an order of playback determined using at least the contextual information.