# US 2012/0254806 A1 · System and method for dynamic, feature-based playlist generation

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2012/0254806 A1
- Document ID: US20120254806A1
- Status: Published application
- Kind: A1
- Application number: 13/076,223
- Filed: 2011-03-30
- Published: 2012-10-04
- Earliest claimed: 2011-03-30
- Assignees: Google Inc.
- Inventors: Rich GOSSWEILER; Douglas Eck; Hrishikesh ARADHYE; Tomas IZO
- Web page: https://patentgrep.com/patent/US20120254806A1

## CPC

- G11B 27/105: {of operating discs}
- G06F 16/4387: {by the use of playlists}
- G06F 16/639: {using playlists}
- G06F 16/68: Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G10H 2240/081: Genre classification, i.e. descriptive metadata for classification or selection of musical pieces according to style
- G10H 2240/121: Musical libraries, i.e. musical databases indexed by musical parameters, wavetables, indexing schemes using musical parameters, musical rule bases or knowledge bases, e.g. for automatic composing methods
- G11B 27/034: on discs (G11B27/036, G11B27/038 take precedence)
- G11B: INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER (recording measured values in a way that does not require playback through a transducer G01D9/00; recording or playback apparatus using mechanically marked tape, e.g. punched paper tape, or using unit records, e.g. punched or magnetically marked cards G06K; transferring data from one type of record carrier to another G06K1/18; circuits for coupling output of reproducer to radio receiver H04B1/20; gramophone pick-ups or like acoustic electromechanical transducers or circuits therefor H04R)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G10H: ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE

## Abstract

Methods and systems for generating playlists of media items with audio data are disclosed. Based on two received feature sets, media items corresponding to each feature set are identified. Transition characteristics are also received. Based on the identified media items and transition characteristics, a dynamic playlist is generated that transitions from media items having characteristics of the first feature set to media items having characteristics of the second feature set. Each time the playlist is generated, it may include a different set of media items.

## Claims

### Claim at position 1

1-27. (canceled)

### Claim 28

A computer implemented method for generating a playlist of media items with audio or video data, comprising:
creating a first feature set to be associated with one or more media items;
creating a second feature set to be associated with one or more media items;
receiving data indicating desired transition characteristics;
identifying, using a clustering technique implemented by one or more processing devices, a set of media items, each media item corresponding to one or more characteristics of at least one of the first feature set and second feature set; and
generating, by one or more processing devices, a playlist of media items from the identified set of media items which transitions from media items corresponding to characteristics of the first feature set to media items corresponding to characteristics of the second feature set according to the desired transition characteristics.

### Claim 29 (depends on 28)

The method of claim 28, wherein the playlist of media items is a first playlist of media items, and further comprising:
generating, by one or more processing devices, a second playlist of media items from the identified set of media items which transitions from media items corresponding to characteristics of the first feature set to media items corresponding to characteristics of the second feature set according to the desired transition characteristics, wherein the first and second playlists of media items do not contain any duplicated media items.

### Claim 30 (depends on 28)

The method of claim 28, wherein the first feature set is associated with a first feature set vector.

### Claim 31 (depends on 28)

The method of claim 28, wherein the second feature set is associated with a second feature set vector.

### Claim 32 (depends on 28)

The method of claim 28, wherein each media item is associated with a media item vector.

### Claim 33 (depends on 28)

The method of claim 28, further comprising:
detecting context data; and
generating, by a processing device, each feature set based on one or more elements of detected context data.

### Claim 34 (depends on 33)

The method of claim 33, wherein the context data includes one or more of a time of day, a weather condition, or an ambient light level.

### Claim 35

A computer implemented method for generating a playlist of media items with audio or video data, comprising:
detecting context data to be associated with one or more media items;
creating a first feature set to be associated with one or more media items;
creating a second feature set to be associated with one or more media items;
identifying, using a clustering technique implemented by one or more processing devices, a set of media items, each media item corresponding to one or more characteristics of at least one of the first feature set and second feature set; and
generating, by one or more processing devices, a playlist of media items based on the detected context data and which transitions from media items corresponding to characteristics of the first feature set to media items corresponding to characteristics of the second feature set.

### Claim 36 (depends on 35)

The method of claim 35, wherein the playlist of media items is a first playlist of media items, and further comprising:
generating, by one or more processing devices, a second playlist of media items based on the detected context data which transitions from media items corresponding to characteristics of the first feature set to media items corresponding to characteristics of the second feature set, wherein the first and second playlists of media items do not contain any duplicated media items.

### Claim 37 (depends on 35)

The method of claim 35, wherein the first feature set is associated with a first feature set vector.

### Claim 38 (depends on 35)

The method of claim 35, wherein the second feature set is associated with a second feature set vector.

### Claim 39 (depends on 35)

The method of claim 35, wherein each media item is associated with a media item vector.

### Claim 40 (depends on 35)

The method of claim 35, wherein the context data includes one or more of a time of day, a weather condition, or an ambient light level.

### Claim 41

A system for generating a playlist of media items with audio or video data, comprising:
a receiver configured to receive a first feature set to be associated with one or more media items, a second feature set to be associated with one or more media items, and data indicating desired transition characteristics;
a media item identifier configured to identify media items in a library using a clustering technique, each media item corresponding to characteristics of at least one of the first or second feature sets;
a playlist generator configured to generate a playlist of media items which transitions from media items identified as corresponding to characteristics of the first feature set to media items identified as corresponding to characteristics of the second feature set according to the received transition characteristics.

### Claim 42 (depends on 41)

The system of claim 41, further comprising a feature set generator to generate a feature set based on at least one of a user selected media item, user selected genre, or user selected element of metadata.

### Claim 43 (depends on 41)

The system of claim 41, wherein the playlist of media items is a first playlist of media items, and wherein the playlist generator is further configured to:
generate a second playlist of media items from the identified set of media items which transitions from media items corresponding to characteristics of the first feature set to media items corresponding to characteristics of the second feature set according to the received transition characteristics, wherein the first and second playlists of media items do not contain any duplicated media items.

### Claim 44 (depends on 41)

The system of claim 41, wherein the first feature set is associated with a first feature set vector.

### Claim 45 (depends on 41)

The system of claim 41, wherein the second feature set is associated with a second feature set vector.

### Claim 46 (depends on 41)

The method of claim 41, wherein each media item is associated with a media item vector.

### Claim 47 (depends on 41)

The system of claim 41, further comprising:
a context data detector configured to detect one or more elements of context data; and
a feature set generator configured to generate each feature set based on the one or more elements of detected context data.

### Claim 48 (depends on 47)

The system of claim 47, wherein the context data includes one or more of a time of day, a weather condition, or an ambient light level.

### Claim 49

A computer-implemented method of generating a playlist of media items with audio or video data, comprising:
creating a first feature set to be associated with one or more media items;
creating a second feature set to be associated with one or more media items;
receiving a desired playlist length; and
dynamically selecting media items for a playlist using a clustering technique, each media item corresponding characteristics of at least one of the first or second feature sets based on a current position of the playlist as compared to the desired playlist length.

### Claim 50 (depends on 49)

The method of claim 49, wherein the playlist is a first playlist, and further comprising:
determining that the first playlist has terminated;
dynamically selecting media items for a second playlist using the clustering technique, each media item corresponding to characteristics of at least one of the first or second feature sets based on a current position of the second playlist as compared to the desired playlist length.
