Cognitive matching of narrative data

Patent metadata

Field	Value
Publication number	US-2016132591-A1
Application number	US-201414537182-A
Country	US
Kind code	A1
Filing date	Nov 10, 2014
Priority date	Nov 10, 2014
Publication date	May 12, 2016
Grant date	—

Abstract

A computer-implemented method for cognitive matching of narrative data may include collecting a set of data for a party and determining, by analyzing the set of data, an identifiable event for the party. In addition, the method may include identifying, using the identifiable event, a relevant feature of a corpus and providing an output corresponding to the relevant feature.

First claim

1 . A computer implemented method for cognitive matching of narrative data, the method comprising:
collecting a set of data for a party; determining, by analyzing the set of data, an identifiable event for the party; identifying, using the identifiable event, a relevant feature of a corpus; and providing an output corresponding to the relevant feature.

2 . The method of claim 1 , wherein collecting the set of data for the user includes aggregating user generated data selected from a group consisting of: a web page, a user profile, a user status, a comment, or a blog.

3 . The method of claim 1 , wherein the corpus includes a narrative content database having one or more types of narrative content selected from a group consisting of: literature data, film data, television data, audio data, and electronic game data.

4 . The method of claim 3 , wherein the narrative content is structured in a set of ontological relationships.

5 . The method of claim 1 , wherein determining, by analyzing the set of data, the identifiable event for the party includes:
extracting metadata from the set of data; determining, based on the metadata of the set of data, a prominence factor of the set of data; and ascertaining that the prominence factor of the set of data achieves a prominence criterion.

6 . The method of claim 5 , further comprising:
parsing, by a natural language processing technique configured to analyze semantic and syntactic content, unstructured data of the set of data; identifying, from the unstructured data of the set of data, a set of story elements; extracting, using the natural language processing technique, a sentiment feature coupled with the set of story elements; and establishing, using the set of story elements and the sentiment feature, a framework component.

7 . The method of claim 1 , identifying, using the identifiable event, the relevant feature of the corpus includes:
comparing a framework component to narrative content of a narrative content database; and determining, based on a set of story elements and a sentiment feature of the framework component and a set of ontological relationships of the narrative content, the relevant feature corresponding to the identifiable event.

8 . The method of claim 1 , wherein providing the output corresponding to the relevant feature includes:
generating, based on the relevant feature, a set of content suggestions; and transmitting, to a user, the set of content suggestions.

9 . The method of claim 8 , further comprising assigning, to the set of content suggestions, a confidence score based on a relationship between the framework component and the relevant feature.

10 . The method of claim 1 , further comprising:
receiving a set of user ratings for the output; and defining, using a machine learning technique configured to process the set of user ratings for the output, a decision parameter for identifying the relevant feature of the corpus.

11 - 20 . (canceled)

Assignees

• IBM

Inventors

• Clark Adam T
• Huebert Jeffrey K
• Payton Aspen L
• Petri John E

Classifications

• G06F16/335 Primary

  Filtering based on additional data, e.g. user or group profiles (filtering in web context G06F16/9535, G06F16/9536) · CPC title

• G06F40/30 Primary

  Semantic analysis · CPC title

• G06F40/205

  Parsing · CPC title

• G06N20/00

  Machine learning · CPC title

• G06F16/3344

  using natural language analysis · CPC title