Personalized automatic content aggregation generation

• US 10,642,848 B2
• Filed: 05/26/2017
• Issued: 05/05/2020
• Est. Priority Date: 04/08/2016
• Status: Active Grant

• Current Assignee: Pearson Education Incorporated (Pearson plc)
• Original Assignee: Pearson Education Incorporated (Pearson plc)
• Inventors: Oros, Luis Manuel, Sadauskas, Jr., John Paul, Sabitini, Peter Alexander, Noble, Jacob Smith, Paris, Kelly Lynn, Strong, David William
• Primary Examiner(s): Spieler, William
• Application Number:
  US15/606,832
• Publication Number:
  US 20170293693A1
• Time in Patent Office: 1,075 Days
• CPC Class Codes: G06F 16/24556 Aggregation; Duplicate elimination
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/2465 Query processing support for facilitating data mining operations in structured databases
• CPC Class Codes: G09B 7/02 of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student
• CPC Class Codes: G09B 7/06 of the multiple-choice answer-type, i.e. where a given question is provided with a series of answers and a choice has to be made from the answers
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04W 4/18 Information format or content conversion, e.g. adaptation by the network of the transmitted or received information for the purpose of wireless delivery to users or terminals
• CPC Class Codes: H04W 4/21 for social networking applications

Abstract

Generating personalized aggregated content is disclosed herein. The system can include a memory include an aggregated content database. The system can include a user device having a first network interface and a first I/O subsystem. The system can include one or more servers that can include a packet selection system and a presentation system. These one or more servers can: receive content files from the user device. A server can create independent clauses from the content files and further extract words to create incomplete clauses. The incomplete clauses are transmitted to the user device such that a user can view and respond to the incomplete clauses.

Claims

1. A processor-based system for automatically generating personalized aggregated content, the processor-based system comprising:

a communication network;

a memory comprising at least a user profile data base;

a server, comprising one or more processors, performing actions of;

receiving, from a user device, a one or more content files via a first electrical signal communicated via the communication network;

processing each content file of the one or more content files by automatically extracting;

a one or more independent clauses, from a content file, wherein each independent clause of the one or more independent clauses contains at least four words, and at least one of the at least four words comprises a noun, and at least one of the at least four words comprises a verb; and

at least one word of the at least four words from the independent clause of the one or more independent clauses to form an incomplete clause of a one or more incomplete clauses and an extraction of a one or more extractions;

generating a content aggregation by placing, for each content file of the one or more content files, the one or more incomplete clauses and the one or more extractions in an aggregation file, wherein each incomplete clause is associated with one extraction of the one or more extractions;

associating the aggregation file with a user of the user device;

storing the aggregation file in a user profile database; and

transmitting, to the user device, an alert via a second electrical signal communicated via the communication network.

2. The processor-based system for automatically generating personalized aggregated content of claim 1, the server further performing further actions of:

processing each independent clause of the one or more independent clauses by;

identifying a noun phrase of a one or more noun phrases in an independent clause as the at least one word;

associating the noun phrase with a content file;

storing the noun phrase in an aggregation database;

further extracting the noun phrase from the independent clause to form an incomplete clause of the one or more incomplete clauses;

associating the noun phrase with the incomplete clause;

associating the incomplete clause with the content file;

storing the incomplete clause in the aggregations database;

creating a one or more test phrases by selecting a corresponding noun phrase of the one or more noun phrases from the aggregation database, wherein the one or more noun phrases are associated with the content file; and

associating the one or more test phrases with the incomplete clause.

3. The processor-based system for automatically generating personalized aggregated content of claim 2, the server further performing additional actions of:

receiving, by the server and from the user device, in response to the alert, a request to view one incomplete clause of the one or more incomplete clauses, via a third electrical signal communicated via the communication network;

transmitting, by the server and to the user device, via a fourth electrical signal communicated via the communication network;

the one incomplete clause of the one or more incomplete clauses;

the one or more test phrases, and/or the associated noun phrase; and

receiving, by the server and from the user device, a response to the one incomplete clause of the one or more incomplete clauses, via a fifth electrical signal communicated via the communication network.

4. The processor-based system for automatically generating personalized aggregated content of claim 3, the server further performing subsequent actions of:

determining, by the server, the response is desirable; and

transmitting, by the server and to the user device, a second notification that the response is desirable via a sixth electrical signal communicated via the communication network.

5. The processor-based system for automatically generating personalized aggregated content of claim 1, wherein the user, and/or an instructor, created the one or more content files.

6. The processor-based system for automatically generating personalized aggregated content of claim 5, wherein the one or more content files comprise text documents, scanned documents, word processor generated documents, PDF generated documents, and/or presentation processing created documents.

7. The processor-based system for automatically generating personalized aggregated content of claim 1, wherein the alert is a first notification that the aggregation file is available.

8. A method for automatically generating personalized aggregated content, the method comprising:

receiving, at a server and from a user device, a one or more content files via a first electrical signal communicated via a communication network;

processing each content file of the one or more content files by automatically extracting;

a one or more independent clauses, from a content file, wherein each independent clause of the one or more independent clauses contains at least four words, and at least one of the at least four words comprises a noun, and at least one of the at least four words comprises a verb; and

at least one word of the at least four words from an independent clause of the one or more independent clauses to form an incomplete clause of a one or more incomplete clauses and an extraction of a one or more extractions;

generating a content aggregation by placing, for each content file of the one of the one or more content files, the one or more incomplete clauses and the one or more extractions in an aggregation file, wherein each incomplete clause is associated with one extraction of the one or more extractions;

associating the aggregation file with a user of the user device;

storing the aggregation file in a user profile database; and

transmitting, to the user device, an alert via a second electrical signal communicated via the communication network.

9. The method for automatically generating personalized aggregated content of claim 8, further comprising:

further processing each independent clause of the one or more independent clauses by;

identifying a noun phrase of a one or more noun phrases in an independent clause as the at least one word;

associating the noun phrase with a content file;

storing the noun phrase in an aggregation database;

further extracting the noun phrase from the independent clause to form an incomplete clause of the one or more incomplete clauses;

associating the noun phrase with the incomplete clause;

associating the incomplete clause with the content file;

storing the incomplete clause in the aggregations database;

generating one or more test phrases by randomly selecting a corresponding noun phrase of the one or more noun phrases from the aggregation database, wherein the one or more noun phrases are associated with the content file; and

associating the one or more test phrases with the incomplete clause and the content file.

10. The method for automatically generating personalized aggregated content of claim 9, further comprising:

receiving, by the server and from the user device, in response to the alert, a request to view one incomplete clause of the one or more incomplete clauses, via a third electrical signal communicated via the communication network;

transmitting, by the server and to the user device, via a fourth electrical signal communicated via the communication network;

the one incomplete clause of the one or more incomplete clauses;

the one or more test phrases, and/or the associated noun phrase; and

receiving, by the server and from the user device, a response to the one incomplete clause of the one or more incomplete clauses, via a fifth electrical signal communicated via the communication network.

11. The method for automatically generating personalized aggregated content of claim 10, further comprising:

determining, by the server, the response is desirable; and

transmitting, by the server and to the user device, a second notification that the response is desirable via a sixth electrical signal communicated via the communication network.

12. The method for automatically generating personalized aggregated content of claim 11, wherein the user, and/or an instructor, created the one or more content files.

13. The method for automatically generating personalized aggregated content of claim 8, wherein the alert is a first notification that the aggregation file is available.

14. The method for automatically generating personalized aggregated content of claim 8, wherein the one or more content files comprise text documents, scanned documents, word processor generated documents, PDF generated documents, and/or presentation processing created documents.

15. A method for creation of a content aggregation comprising:

transmitting a content to a user device, via a first electrical signal communicated via a communication network;

receiving a selection of the content, from the user device, via a second electrical signal communicated via the communication network;

automatically extracting sentences from the content via Natural Language Processing, a resulting extraction including;

a one or more independent clauses, from a content file within one or more content files, wherein each independent clause of the one or more independent clauses contains at least four words, and at least one of the at least four words comprises a noun, and at least one of the at least four words comprises a verb; and

at least one word of the at least four words from the independent clause of the one or more independent clauses to form an incomplete clause of a one or more incomplete clauses and an extraction of a one or more extractions;

automatically generating a parse tree for one of the automatically extracted sentences, wherein each of a plurality of branches of the parse tree are associated with a part of speech tag;

identifying one or more noun phrases from the part of speech tag within the parse tree;

placing content associated with a noun phrase of the one or more noun phrases in a content aggregation, the content aggregation comprising placing, for each content file of the one or more content files, the one or more incomplete clauses and the one or more extractions in an aggregation file, wherein each incomplete clause is associated with one extraction of the one or more extractions; and

outputting the content aggregation to the user device via a third electrical signal communicated via the communication network.

16. The method of claim 15, wherein the content is provided to the user device from a content database comprising content relevant to a common subject.

17. The method of claim 15, wherein the user device comprises:

a first network interface configured to exchange data via a communication network; and

a first I/O subsystem configured to convert electrical signals to user interpretable outputs via a user interface.

18. The method of claim 15, further comprising identifying a subset of the noun phrases, wherein the subset of the noun phrases comprises at least one attribute identified as improving a quality of the content aggregation.

19. The method of claim 18, wherein identifying the at least one attribute that improves the quality of the content aggregation comprises:

automatically determining a number of words in the noun phrase;

retrieving a size threshold;

comparing the number of words in the noun phrase to the size threshold; and

associating a first Boolean value with the noun phrase when the number of words is less than the size threshold and associating a second Boolean value with the noun phrase when the number of words is greater than a noun threshold.

20. The method of claim 19, wherein identifying noun phrases from the part of speech tag within the parse tree comprises:

(a) identifying a root of the parse tree;

(b) progressing from the root to a one of the plurality of branches of the parse tree;

(c) retrieving the part of speech tag associated with the one of the plurality of branches of the parse tree; and

identifying the part of speech tag associated with the one of the plurality of branches of the parse tree.