US 12,436,994 B1
Generating description pages for media entities
Christian Garcia Siagian, Los Angeles, CA (US); Vedant Ulhas Shete, Milpitas, CA (US); Timothy William Stephani, Emeryville, CA (US); Jobel Kyle Petallana Vecino, Los Angeles, CA (US); and Gordon Zheng, North Hollywood, CA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on May 31, 2024, as Appl. No. 18/680,925.
Application 18/680,925 is a continuation of application No. 17/690,931, filed on Mar. 9, 2022, granted, now 12,026,199.
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/683 (2019.01); G06F 16/34 (2025.01); G06F 16/68 (2019.01); G06F 40/284 (2020.01); G06F 40/295 (2020.01)
CPC G06F 16/685 (2019.01) [G06F 16/345 (2019.01); G06F 16/686 (2019.01); G06F 40/284 (2020.01); G06F 40/295 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A first computer system comprising at least one data store and at least one computer processor,
wherein the first computer system is connected to one or more networks, and
wherein the at least one data store has one or more sets of instructions stored thereon that, when executed by the at least one computer processor, cause the first computer system to perform a method comprising:
generating a transcript of audio data representing at least a portion of a podcast, wherein the transcript comprises a set of words;
dividing the transcript into a plurality of sections, wherein each one of the plurality of sections comprises a subset of the set of words of the transcript;
generating, for each one of the sections, a sentence based at least in part on the subset of the set of words of the one of the sections;
identifying, for each one of the sections, a phrase representative of the one of the sections, wherein each one of the phrases comprises at least some of the subset of the set of words of the one of the sections;
generating a summary of the portion of the podcast based at least in part on the sentences generated for each one of the sections;
identifying at least one phrase representative of the portion of the podcast based at least in part on the phrases representative of each one of the sections;
generating a page of information regarding at least one of the podcast or the portion of the podcast, wherein the page comprises:
a title of at least one of the at least one of the podcast or the portion of the podcast;
the summary of the portion of the podcast; and
the at least one phrase representative of the portion of the podcast; and
transmitting data for causing a display of the page to a second computer system.