Back to results
US 2014/0236573 A1Published application
Automatic Semantic Rating and Abstraction of Literature
AssigneeInternational Business Machines Corporation
InventorsCorville Orain Allen, Scott Robert Carrier, Eric Woods
Life of this patent
Estimating the term…
Abstract
Deep semantic analysis is performed on an electronic literary work in order to detect plot elements and optional other storyline elements such as characters within the work. Multiple levels of abstract are generated into a model representing the literary work, wherein each element in each abstraction level may be independently rated for preference by a user. Through comparison of multiple abstraction models and one or more user rating preferences, one or more alternative literary works may be automatically recommended to the user.
Claims24
A method for automatic semantic rating and abstraction of literature comprising:
- extracting by computer system a series of annotations from a first electronic text;
- identifying by a computer system a deep semantic relationship for entries in the annotations to identify literary elements;
- abstracting iteratively by a computer system from the literary elements to form two or more levels in a first electronic model representing the electronic text, wherein the literary elements and deep semantic relationships between the elements are represented in a hierarchical manner;
- comparing by a computer system one or more literary elements and the deep semantic relationships in the first electronic model to one or more literary elements of a second electronic model representing a second electronic text, wherein the second electronic text has an associated user preference indicator;
- responsive to the comparing finding a match above a pre-determined degree of similarity, declaring by a computer system the first electronic text to have an expected user preference indicator as the user preference indicator associated with the second electronic text;
- and
- responsive to the comparing finding a match above pre-determined degree of dissimilarity, declaring by a computer system the first electronic text to have an expected user preference indicator complementary the user preference indicator associated with the second electronic text.
4 more elements
A system for automatic semantic rating and abstraction of literature comprising:
- a processor for performing a logical process;
- and
- at least one computer readable, tangible data storage device, encoded with program instructions for causing the processor to;
- extract a series of annotations from a first electronic text;
- identify a deep semantic relationship for entries in the annotations to identify literary elements;
- abstract iteratively from the literary elements to form two or more levels in a first electronic model representing the electronic text, wherein the literary elements and deep semantic relationships between the elements are represented in a hierarchical manner;
- compare one or more literary elements and the deep semantic relationships in the first electronic model to one or more literary elements of a second electronic model representing a second electronic text, wherein the second electronic text has an associated user preference indicator;
- responsive to the comparing finding a match above a pre-determined degree of similarity, declare the first electronic text to have an expected user preference indicator as the user preference indicator associated with the second electronic text;
- and
- responsive to the comparing finding a match above pre-determined degree of dissimilarity, declare the first electronic text to have an expected user preference indicator complementary the user preference indicator associated with the second electronic text.
7 more elements
A computer program product for automatic semantic rating and abstraction of literature comprising:
- a computer readable, tangible data storage device;
- first program instructions for extracting a series of annotations from an electronic text;
- second program instructions for identifying a deep semantic relationship for entries in the annotations to identify literary elements;
- third program instructions for abstracting iteratively from the literary elements to form two or more levels in a first electronic model representing the electronic text, wherein the literary elements and deep semantic relationships between the elements are represented in a hierarchical manner;
- fourth program instructions for comparing one or more literary elements and the deep semantic relationships in the first electronic model to one or more literary elements of a second electronic model representing a second electronic text, wherein the second electronic text has an associated user preference indicator;
- fifth program instructions for, responsive to the comparing finding a match above a pre-determined degree of similarity, declaring the first electronic text to have an expected user preference indicator as the user preference indicator associated with the second electronic text;
- and
- sixth program instructions for, responsive to the comparing finding a match above pre-determined degree of dissimilarity, declaring the first electronic text to have an expected user preference indicator complementary the user preference indicator associated with the second electronic text;
- wherein the first, second, third, fourth, fifth and sixth program instructions are stored by the computer readable, tangible data storage device.
6 more elements
Dependencies are inferred from the claim text.