System and method for automatic content aggregation generation

Patent metadata

Field	Value
Publication number	US-11651239-B2
Application number	US-201916410848-A
Country	US
Kind code	B2
Filing date	May 13, 2019
Priority date	Apr 8, 2016
Publication date	May 16, 2023
Grant date	May 16, 2023

Abstract

Systems and methods for content aggregation creation are disclosed herein. The system can include memory having a content database and an aggregation database. The system can include a user device having a first network interface and a first I/O subsystem. The system can include a server that can: provide content to the user device via a first electrical signal; receive a selection of a portion of the provided content from the user device via a second electrical signal; automatically extract sentences from the selected portion of the provided content via a natural language processor; automatically generate a parse tree for one of the automatically extracted sentences; identify noun phrases from the part of speech tags within the parse tree; place content associated with one of the noun phrase in a content aggregation; and output the content aggregation to the user device.

First claim

What is claimed is:

1. A system comprising a server, including at least one computing device coupled to a network and including at least one processor executing instructions within a memory which, when executed, cause the system to:
transmit a content, stored within a content database and, through the network to a first user device for display;
receive a selection, by a user operating the first user device, of a portion of the content;
parse the portion of the content into at least one sentence using a natural language processor;
generate a parse tree for the at least one sentence, wherein each branch of the parse tree is associated with a corresponding part of speech tag;
algorithmically select, from the parse tree, according to predefined heuristics, a word or phrase within the at least one sentence, wherein the word or phrase is selected from the parse tree based on a part of speech tag associated with a branch of the parse tree that includes the word or phrase;
generate a prompt replacing the word or phrase with a placeholder;
store the word or phrase in a database coupled to the network in association with the prompt;
generate a display comprising the prompt; and
transmit the prompt to a second user device for display, wherein a response comprising the word or phrase is identified as a correct response.

2. The system of claim 1 , wherein the content comprises at least one text, image, video, or audio file provided by a recommendation software engine, identified as relevant to a common subject.

3. The system of claim 1 , wherein the selection is received by the user highlighting the portion of the content.

4. The system of claim 1 , wherein the at least one sentence is:
parsed by the natural language processor identifying, within a portion of the content, a capital letter, a period, or a blank space; or
identified using non-parsing methods.

5. The system of claim 1 , wherein the associated part of speech tag identifies a noun, a verb, an adjective, an adverb, or a cardinal number.

6. The system of claim 1 , wherein the associated part of speech tag is associated with at least one topic or skill, identified in the database as being associated with the content.

7. The system of claim 6 , wherein the at least one topic or skill is associated with the content based on a semantic analysis of the word or phrase in the at least one sentence, compared to a syllabus or a schedule for tasks, topics, skills or skill levels associated with the word or phrase.

8. The system of claim 1 , wherein the placeholder is an underlining in place of the word or phrase.

9. A method, comprising:
transmitting, by a server including at least one computing device coupled to a network and including at least one processor executing instructions within a memory, a content, stored within a content database and, through the network to a first user device for display;
receiving, by the server, a selection, by a user operating the first user device, of a portion of the content;
parsing, by the server, the portion of the content into at least one sentence using a natural language processor;
generating, by the server, a parse tree for the at least one sentence, wherein each branch of the parse tree is associated with a corresponding part of speech tag;
algorithmically selecting, by the server, from the parse tree, according to predefined heuristics, a word or phrase within the at least one sentence, wherein the word or phrase is selected from the parse tree based on a part of speech tag associated with a branch of the parse tree that includes the word or phrase;
generating, by the server, a prompt replacing the word or phrase with a placeholder;
storing, by the server, the word or phrase in a database coupled to the network in association with the prompt;
generating, by the server, a display comprising the prompt; and
transmitting, by the server, the prompt to a second user device for display, wherein a response comprising the word or phrase is identified as a correct response.

10. The method of claim 9 , wherein the content comprises at least one text, image, video, or audio file provided by a recommendation software engine, identified as relevant to a common subject.

11. The method of claim 9 , wherein the selection is received by the user highlighting the portion of the content.

12. The method of claim 9 , wherein the at least one sentence is:
parsed by the natural language processor identifying, within a portion of the content, a capital letter, a period, or a blank space; or
identified using non-parsing methods.

13. The method of claim 9 , wherein the associated part of speech tag identifies a noun, a verb, an adjective, an adverb, or a cardinal number.

14. The method of claim 9 , wherein the associated part of speech tag is associated with at least one topic or skill, identified in the database as being associated with the content.

15. The method of claim 14 , wherein the at least one topic or skill is associated with the content based on a semantic analysis of the word or phrase in the at least one sentence, compared to a syllabus or a schedule for tasks, topics, skills or skill levels associated with the word or phrase.

16. The method of claim 9 , wherein the placeholder is an underlining in place of the word or phrase.

17. The method of claim 9 , wherein parsing the portion of the content into the at least one sentence includes filtering of the portion of the content to remove one or more unwanted artifacts in the portion of the content.

18. The method of claim 9 , wherein filtering of the portion of the content includes performing double quote normalization, hyphenated word joining, removal of footnote references, or removal of extra white space.

19. The method of claim 9 , further comprising:
evaluating, by the server, the parse tree to validate that the parse tree was created for a sentence; and
in response to the parse tree not being validated, discarding the parse tree.

20. The method of claim 9 , further comprising:
identifying, based on a word count, a subset of rational phrases associated with the portion of content of the at least one sentence.

Assignees

• Pearson Education Inc

Inventors

• York Sean
• Stewart Tim
• Strong David
• Hellman Scott
• Murray William

Classifications

• H04L47/10

  Flow control; Congestion control · CPC title

• G06N5/022 Primary

  Knowledge engineering; Knowledge acquisition · CPC title

• G06Q50/20

  Education · CPC title

• H04L12/4641 Primary

  Virtual LANs, VLANs, e.g. virtual private networks [VPN] (LAN interconnection over a bridge based backbone H04L12/462; encapsulation techniques H04L12/4633; routing of packets H04L45/00; packet switches H04L49/00; virtual private networks for security H04L63/0272) · CPC title

• G06N5/04

  Inference or reasoning models · CPC title