Computing device and corresponding method for generating data representing text

Patent metadata

Field	Value
Publication number	US-10977424-B2
Application number	US-201916517033-A
Country	US
Kind code	B2
Filing date	Jul 19, 2019
Priority date	Jul 2, 2014
Publication date	Apr 13, 2021
Grant date	Apr 13, 2021

Abstract

An example method involves (i) accessing first data defining multiple portions of a content item, wherein at least a plurality of the portions represent text; (ii) selecting, from the plurality of portions representing text, a subset of the portions representing text, wherein the selecting is based on each portion of the selected subset having a particular characteristic; (iii) based on the text represented by the portions of the selected subset, generating second data that represents a concatenation of the text represented by the portions of the selected subset; and (iv) providing output based on the generated second data.

First claim

The invention claimed is:

1. A method comprising:
determining, by a server, a set of attributes of a user of a client device;
based on the determined set of attributes, generating, by the server, a sequence of content items, wherein at least one content item in the sequence comprises multiple portions, and wherein at least one of the multiple portions represents text;
preparing the at least one content item, wherein the preparing comprises:
(i) extracting, from the at least one content item of the sequence, at least one of the multiple portions that represents text;
(ii) making a determination that the extracted at least one of the multiple portions representing text has a particular characteristic; and
(iii) based on the determination, modifying the extracted at least one of the multiple portions representing text;

generating data representing a concatenation of (i) the prepared at least one content item of the sequence and (ii) at least one other content item of the sequence; and
providing output based on the generated data.

2. The method of claim 1 , wherein the content item comprises a news article.

3. The method of claim 1 , wherein the at least one content item in the sequence comprises a news article, and wherein extracting the at least one of the multiple portions that represents text is based on the at least one of the multiple portions that represents text representing content from at least one section from a predefined set of sections of the news article.

4. The method of claim 1 , wherein modifying the extracted at least one of the multiple portions that represents text comprises editing a length of the extracted at least one of the multiple portions that represents text.

5. The method of claim 1 , wherein the particular characteristic of the extracted at least one of the multiple portions that represents text is a number of text characters.

6. The method of claim 1 , wherein the extracted at least one of the multiple portions that represents text defines at least two positions representing a particular type of grammatical break, and wherein modifying the extracted at least one of the multiple portions that represents text comprises:
(i) identifying, from among the at least two positions, a position that is closest to a target position within the text; and
(ii) based on the identified position within the text, removing a particular portion of text that follows the identified position within the text.

7. The method of claim 1 , wherein modifying the extracted at least one of the multiple portions that represents text comprises:
(i) identifying a term within the represented text;
(ii) using the identified term as a basis to select a text-editing rule from among a set of text-editing rules; and
(iii) applying the selected text-editing rule to the extracted at least one of the multiple portions that represents text.

8. The method of claim 1 , further comprising:
providing the generated data to a text-to-speech system; and
generating, by the text-to-speech system, an audible version of the generated data.

9. The method of claim 1 , further comprising:
transmitting, by the server, the sequence of content items to the client device; and
selecting, by the client device via input from a user, the at least one content item in the sequence.

10. The method of claim 1 , wherein the set of attributes of the user comprises at least one selected category of news stories.

11. The method of claim 10 , wherein the at least one selected category includes at least one of a sports category, a politics category, or an entertainment category.

12. The method of claim 1 , wherein the client device is configured to provide the user with a personalized news program via an audio output mechanism.

13. The method of claim 1 , wherein the sequence of content items comprises a playlist.

14. A non-transitory computer-readable medium having stored thereon program instructions that when executed by a processor cause performance of a set of acts, the set of acts comprising:
determining a set of attributes of a user;
based on the determined set of attributes, generating a sequence of content items, wherein at least one content item in the sequence comprises multiple portions, and wherein at least one of the multiple portions represents text;
preparing the at least one content item, wherein the preparing comprises:
(i) extracting, from the at least one content item of the sequence, at least one of the multiple portions that represents text;
(ii) making a determination that the extracted at least one of the multiple portions representing text has a particular characteristic; and
(iii) based on the determination, modifying the extracted at least one of the multiple portions representing text;

generating data representing a concatenation of (i) the prepared at least one content item of the sequence and (ii) at least one other content item of the sequence; and
providing output based on the generated data.

15. The computer-readable medium of claim 14 , wherein the at least one content item in the sequence comprises a news article, and wherein extracting the at least one of the multiple portions that represents text is based on the at least one of the multiple portions that represents text representing content from at least one section from a predefined set of sections of the news article.

16. The computer-readable medium of claim 14 , wherein modifying the extracted at least one of the multiple portions that represents text comprises editing a length of the extracted at least one of the multiple portions that represents text.

17. The computer-readable medium of claim 14 , wherein the set of attributes of the user comprises at least one selected category of news stories.

18. A computing device comprising:
a communication interface;
a processor; and
a non-transitory computer-readable medium having stored thereon program instructions that when executed by the processor cause the computing device to perform a set of acts, the set of acts comprising:
determining a set of attributes of a user;
based on the determined set of attributes, generating a sequence of content items, wherein at least one content item in the sequence comprises multiple portions, and wherein at least one of the multiple portions represents text;
preparing the at least one content item, wherein the preparing comprises:
(i) extracting, from the at least one content item of the sequence, at least one of the multiple portions that represents text;
(ii) making a determination that the extracted at least one of the multiple portions representing text has a particular characteristic; and
(iii) based on the determination, modifying the extracted at least one of the multiple portions representing text;

generating data representing a concatenation of (i) the prepared at least one content item of the sequence and (ii) at least one other content item of the sequence; and
providing output based on the generated data.

19. The computing device of claim 18 , wherein the at least one content item in the sequence comprises a news article, and wherein extracting the at least one of the multiple portions that represents text is based on the at least one of the multiple portions that represents text representing content from at least one section from a predefined set of sections of the news article.

20. The computing device of claim 18 , wherein modifying the extracted at least one of the multiple portions that represents text comprises editing a le

Assignees

• Gracenote Digital Ventures Llc

Inventors

• Panguluri Venkatarama Anilkumar
• Defouw Gregory P

Classifications

• G06F16/345 Primary

  Summarisation for human users · CPC title

• G06Q30/02

  Marketing; Price estimation or determination; Fundraising · CPC title

• G06F40/151

  Transformation · CPC title

• G06F40/253

  Grammatical analysis; Style critique · CPC title

• G06F3/0488

  using a touch-screen or digitiser, e.g. input of commands through traced gestures · CPC title