US 12,190,015 B2
Cognitive aid for audio books
Brant Candelore, Poway, CA (US)
Assigned to Sony Group Corporation, Tokyo (JP)
Filed by Sony Group Corporation, Tokyo (JP)
Filed on Feb. 15, 2023, as Appl. No. 18/169,429.
Prior Publication US 2024/0272867 A1, Aug. 15, 2024
Int. Cl. G06F 3/16 (2006.01); G06F 16/68 (2019.01); G10L 15/18 (2013.01); G10L 15/22 (2006.01)
CPC G06F 3/165 (2013.01) [G06F 3/167 (2013.01); G06F 16/686 (2019.01); G10L 15/1815 (2013.01); G10L 15/22 (2013.01); G10L 2015/223 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A method, comprising:
identifying an audible request for information pertaining to some but not all of an audio book;
responsive to identification of the audible request, accessing data associated with the audio book, the data comprising metadata indicating different plot summary elements of an overall plot summary for the audio book, the different plot summary elements associated with different respective audio book playback position ranges;
determining a current playback position of the audio book;
executing naturallanguage processing to determine a type of information being requested pursuant to the audible request;
using the metadata and the current playback position to identify an answer related to the audible request; and
based on the identification of the answer, dynamically generating a summary that conforms to the type of information being requested and that summarizes one or more events up to the current playback position but not events associated with playback positions subsequent to the current playback position; and
presenting a first output on a display, the first output comprising the dynamically-generated summary that conforms to the type of information being requested and that summarizes the one or more events up to the current playback position but not events associated with playback positions subsequent to the current playback position, the first output further comprising a first selector, the first selector comprising a first word from the dynamically-generated summary on the face of the first selector, the first selector being selectable to provide a command to a device to present a second output different from the first output, the second output related to the first word on the face of the first selector;
wherein the first output further comprises a second selector, the second selector comprising a second word from the dynamically-generated summary on the face of the second selector, the second word being different from the first word, the second selector being selectable to provide a command to the device to present a third output different from the first and second outputs, the third output related to the second word on the face of the second selector:
wherein the first selector is presented, as part of the first output, in-line with other portions of the dynamically-generated summary, the other portions of the dynamically-generated summary not being selectable to provide commands to present other outputs related to the other portions of the dynamically-generated summary; and
wherein the second selector is concurrently presented, as part of the first output, in-line with the first selector and with the other portions of the dynamically-generated summary that are not selectable to provide commands to present other outputs related to the other portions of the dynamically-generated summary.