IP Library Granted Patent US 9,721,207
Granted Patent B2
US 9,721,207 · App. 14/287,432 · Granted Aug 1, 2017

Generating written content from knowledge management systems

Inventors: Karl J. Cama (Coppell, TX); Norbert Herman (Denver, CO); Daniel T. Lambert (New York, NY)
Assignee: International Business Machines Corporation
G06N5/022G06F17/30011G06F17/30719
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,721,207
App. No.
14/287,432
Filed
May 27, 2014
Granted
Aug 1, 2017
Kind
B2
Art Unit
2144
USPC
715/234
Abstract

The disclosure is directed to written content generation. A method for generating written content in an application in accordance with an embodiment includes: receiving a query from a user; importing data from at least one data source in response to the query; ranking the imported data based on a plurality of ranking factors to determine a relevance of the imported data; automatically generating written content using at least a portion of the imported data based on the determined relevance of the imported data; and automatically customizing the written content based on a file format of the application.

Claims (36)

1. A method for generating written content in an application, comprising:

importing data from a plurality of data sources in response to a user query, wherein the plurality of data sources include at least one website determined to be a reliable source of information by a community of users, at least one internal knowledge management system, and at least one external knowledge management system;

ranking the plurality of data sources based on a plurality of ranking factors, wherein the plurality of ranking factors include: total page views for each website, expertise of at least one author of data presented on each website, comments regarding the data presented on each website, crowd-sourced ratings of each website, a number of times the data presented on each website has been shared, and a reputation of an entity associated with the website;

ranking the imported data imported from the plurality of data sources based on the ranking of the plurality of data sources to determine a relevance of the imported data;

displaying, on a user interface, the imported data having a relevance above a user selected scoring threshold;

automatically generating written content using at least a portion of the imported data displayed on the user interface based on the determined relevance of the imported data, wherein a size of the portion of the imported data used to automatically generate the written content decreases as the relevance of the imported data decreases; and

automatically customizing the written content based on a file format of the application.

2. The method of claim 1 , further comprising inputting user defined metrics via a user interface, wherein the ranking factors include at least one of the user defined metrics.

3. The method of claim 2 , further comprising:

setting a scope of the data to be imported via the user interface.

4. The method of claim 1 , wherein automatically generating written content is performed by a narrative science engine.

5. The method of claim 1 , wherein the method is performed by a plug-in or macro of the application.

6. A computer system that includes a processing component, for performing a method for generating written content in an application by performing actions including:

importing data from a plurality of data sources in response to a user query, wherein the plurality of data sources includes at least one website determined to be a reliable source of information by a community of users, at least one internal knowledge management system, and at least one external knowledge management system;

ranking the plurality of data sources based on a plurality of ranking factors, wherein the plurality of ranking factors include: total page views for each website, expertise of at least one author of data presented on each website, comments regarding the data presented on each website, crowd-sourced ratings of each website, a number of times the data presented on each website has been shared, and a reputation of an entity associated with the website;

ranking the imported data imported from the plurality of data sources based on the ranking of the plurality of data sources to determine a relevance of the imported data;

displaying, on a user interface, the imported data having a relevance above a user selected scoring threshold;

automatically generating written content using at least a portion of the imported data displayed on the user interface based on the determined relevance of the imported data, wherein a size of the portion of the imported data used to automatically generate the written content decreases as the relevance of the imported data decreases; and

automatically customizing the written content based on a file format of the application.

7. The system of claim 6 , wherein the method further comprises inputting user defined metrics via a user interface, wherein the ranking factors include at least one of the user defined metrics.

8. The system of claim 7 , wherein the method further comprises:

setting a scope of the data to be imported via the user interface.

9. The system of claim 6 , wherein automatically generating written content is performed by a narrative science engine.

10. The system of claim 6 , wherein the method is performed by a plug-in or macro of the application.

11. A computer program product comprising program code embodied in at least one computer-readable storage medium, which when executed, enables a computer system to implement a method for generating written content in an application, the method comprising:

importing data from a plurality of data sources in response to a user query, wherein the plurality of data sources include at least one website determined to be a reliable source of information by a community of users, at least one internal knowledge management system, and at least one external knowledge management system;

ranking the plurality of data sources based on a plurality of ranking factors, wherein the plurality of ranking factors include: total page views for each website, expertise of at least one author of data presented on each website, comments regarding the data presented on each website, crowd-sourced ratings of each website, a number of times the data presented on each website has been shared, and a reputation of an entity associated with the website;

ranking the imported data imported from the plurality of data sources based on the ranking of the plurality of data sources to determine a relevance of the imported data;

displaying, on a user interface, the imported data having a relevance above a user selected scoring threshold;

automatically generating written content using at least a portion of the imported data displayed on the user interface based on the determined relevance of the imported data, wherein a size of the portion of the imported data used to automatically generate the written content decreases as the relevance of the imported data decreases; and

automatically customizing the written content based on a file format of the application.

12. The computer program product of claim 11 , further comprising inputting user defined metrics via a user interface, wherein the ranking factors include at least one of the user defined metrics.

13. The computer program product of claim 12 , further comprising:

setting a scope of the data to be imported via the user interface.

14. The computer program product of claim 11 , wherein automatically generating written content is performed by a narrative science engine.

15. The computer program product of claim 11 , wherein the method is performed by a plug-in or macro of the application.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 28, 2014
From: CAMA, KARL J.; HERMAN, NORBERT; LAMBERT, DANIEL T.
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 032973/0941 →
Continuity (1)
Related Publication 20150347901A1 · Dec 3, 2015