Human-machine interfaces for utterance-based playlist selection

Patent metadata

Field	Value
Publication number	US-11755283-B2
Application number	US-202217720486-A
Country	US
Kind code	B2
Filing date	Apr 14, 2022
Priority date	Jul 18, 2018
Publication date	Sep 12, 2023
Grant date	Sep 12, 2023

Abstract

Systems, methods, and devices for human-machine interfaces for utterance-based playlist selection are disclosed. In one method, a list of playlists is traversed and a portion of each is audibly output until a playlist command is received. Based on the playlist command, the traversing is stopped and a playlist is selected for playback. In examples, the list of playlists is modified based on a modification input.

First claim

What is claimed is:

1. A method comprising:
receiving, by a human-machine interface of a device, first input data including first utterance data;
determining the first utterance data includes a request to provide a list of playlists;
receiving the list of playlists, the list of playlists being associated with the first utterance data;
predicting an activity of a user of the device;
determining, for each playlist of the list of playlists, a similarity value describing how related the respective playlist is to the predicted activity;
reordering the list of playlists based on the similarity value, thereby generating a reordered list of playlists;
traversing the list of playlists according to the reordered list of playlists;
audibly outputting an introduction corresponding to descriptor data of the playlist, and
audibly outputting a predetermined portion of each playlist in the reordered list of playlists, the predetermined portion including a playlist trailer generated from a subset of one or more media content items of the playlist.

2. The method of claim 1 , further including:
while traversing the list of playlists, receiving second input data;
determining that the second input data is associated with a playlist command; and
based on the playlist command:
stopping the traversing;
selecting a selected playlist based on the playlist command; and
initiating playback of the selected playlist.

3. The method of claim 1 , wherein the predicting the activity of the user of the device is performed based on data from one or more sensors coupled to the device.

4. The method of claim 1 , wherein the predicting the activity of the user of the device is performed by asking the user to describe a current activity and processing a response to the question.

5. The method of claim 1 , wherein the similarity value is determined based on a vector space representation of the activity and the respective playlist.

6. The method of claim 1 , wherein the similarity value is determined based on a title, description, or tag of the playlist.

7. The method of claim 1 ,
wherein the list of playlists is modified based on the descriptor data.

8. A non-transitory computer-readable medium having stored thereon sequences of instructions, the sequences of instructions including instructions that when executed by a computer system causes the computer system to perform:
receiving, by a human-machine interface of a device, first input data including first utterance data;
determining the first utterance data includes a request to provide a list of playlists;
receiving the list of playlists, the list of playlists being associated with the first utterance data;
predicting an activity of a user of the device;
determining, for each playlist of the list of playlists, a similarity value describing how related the respective playlist is to the predicted activity;
reordering the list of playlists based on the similarity value, thereby generating a reordered list of playlists;
traversing the list of playlists according to the reordered list of playlists; and
audibly outputting an introduction corresponding to descriptor data of the playlist; and
audibly outputting a predetermined portion of each playlist in the reordered list of playlists, the predetermined portion including a playlist trailer generated from a subset of one or more media content items of the playlist.

9. The non-transitory computer-readable medium of claim 8 , further having stored thereon a sequence of instructions for causing the computer system to perform:
while traversing the list of playlists, receiving second input data;
determining that the second input data is associated with a playlist command; and
based on the playlist command:
stopping the traversing;
selecting a selected playlist based on the playlist command; and
initiating playback of the selected playlist.

10. The non-transitory computer-readable medium of claim 8 , wherein the predicting the activity of the user of the device is performed based on data from one or more sensors coupled to the device.

11. The non-transitory computer-readable medium of claim 8 , wherein the predicting the activity of the user of the device is performed by asking the user to describe a current activity and processing a response to the question.

12. The non-transitory computer-readable medium of claim 8 , wherein the similarity value is determined based on a vector space representation of the activity and the respective playlist.

13. The non-transitory computer-readable medium of claim 8 , wherein the similarity value is determined based on a title, description, or tag of the playlist.

14. The non-transitory computer-readable medium of claim 8 ,
wherein the list of playlists is modified based on the descriptor data.

15. A system, comprising:
a remote server having a playlist data store; and
a device being configured to:
receive, by a human-machine interface of the device, first input data including first utterance data;
determine the first utterance data includes a request to provide a list of playlists;
receive the list of playlists, the list of playlists being associated with the first utterance data;
predict an activity of a user of the device;
determine, for each playlist of the list of playlists, a similarity value describing how related the respective playlist is to the predicted activity;
reorder the list of playlists based on the similarity value, thereby generating a reordered list of playlists;
traverse the list of playlists according to the reordered list of playlists;
audibly output an introduction corresponding to descriptor data of the playlist; and
audibly output a predetermined portion of each playlist in the reordered list of playlists, the predetermined portion including a playlist trailer generated from a subset of one or more media content items of the playlist.

16. The system of claim 15 , wherein the device is further configured to:
while traversing the list of playlists, receive second input data;
determine that the second input data is associated with a playlist command; and
based on the playlist command:
stop the traversing;
select a selected playlist based on the playlist command; and
initiate playback of the selected playlist.

17. The system of claim 15 , wherein the device predicts the activity of the user of the device based on data from one or more sensors coupled to the device.

18. The system of claim 15 , wherein the similarity value is determined based on a vector space representation of the activity and the respective playlist.

19. The system of claim 15 , wherein the similarity value is determined based on a title, description, or tag of the playlist.

20. The system of claim 15 ,
wherein the list of playlists is modified based on the descriptor data.

21. The method according to claim 1 , wherein the subset contains fewer media content items than a full set of media content items of the playlist.

22. The non-transitory computer-readable medium of claim 8 , wherein the subset contains fewer media content items than a full set of media content items of the playlist.

23. The system according to claim 15 , wherein the subset contains fewer media content items than a full set of media content items of the playlist.

Assignees

• Spotify Ab

Inventors

• Bromand Daniel
• Mitic Richard
• Jurcut Horia-Dragos
• Cramer Henriette Susanne Martine
• Brillman Ruth

Classifications

• G06F16/639

  using playlists · CPC title

• G06F3/167 Primary

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L15/26

  Speech to text systems (G10L15/08 takes precedence) · CPC title