Back to results
US 8,897,486 B1Granted
Recognition of characters and their significance within written works
AssigneeAmazon Technologies, Inc.
InventorsPeter Thomas Killalea, Janna S. Hamaker, Eugene Kalenkovich
Life of this patent
Estimating the term…
Abstract
Character identity recognition is applied to identify text strings corresponding to character identities in a written work. The textual strings are grouped according to character identity and, from each group, a primary name is selected. A significance value may be calculated for each of the character identities. The character identities including the primary names are presented in a catalog based on the calculated significance values.
Claims25
A method comprising:
- identifying a group of related written works representing different editions of a single written work;
- for each of the written works in the group of related written works:
- identifying character identities within the written work;
- identifying one or more text strings used within the written work for each character identity;
- calculating a significance value for each character identity;
- and
- selecting a primary text string from the one or more text strings;
- for each character identity identified in the group of related written works;
- calculating a combined significance value from the significance value calculated for each character identity within each written work, the combined significance value combining the character identities across the group of related written works;
- selecting a representative primary text string from the primary text strings selected for each character identity within each written work;
- and
- creating a merged character identity based on the combined significance value and the representative primary text sting;
- and
- associating the merged character identities with the group of related written works.
11 more elements
A method comprising:
- recognizing a plurality of textual strings within a written work, wherein each textual string is associated with a character identity of a plurality of character identities within the written work;
- for the character identity;
- calculating, by one or more hardware processors, a significance value based at least in part on a frequency of occurrence of one or more textual strings associated with the character identity;
- determining that the character identity is included in other written works;
- updating the significance value for the character identity based at least in part on the inclusion of the character identity in the other written works;
- and
- selecting a primary textual string from the one or more textual strings associated with the character identity;
- and
- providing a list of at least a portion of the plurality of character identities, the list including the primary textual string and other primary textual strings for the at least the portion of the plurality of character identities and the list being sorted based at least in part on the significance value.
6 more elements
One or more non-transitory computer-readable storage media storing computer-executable instructions that, when executed, cause one or more processors to perform acts comprising:
- identifying a plurality of named entities within a written work;
- for a named entity of the plurality of named entities:
- identifying one or more textual strings associated with the named entity;
- calculating a significance value based at least in part on a location of the one or more textual strings associated with the named entity within the written work;
- determining that the named entity is included in other written works;
- updating the significance value for the named entity based at least in part on the inclusion of the named entity in the other written works;
- and
- selecting a primary textual string from the one or more textual strings associated with the named entity;
- and
- providing a list of at least a portion of the plurality of named entities, the list including the primary textual string and other primary textual strings for the at least the portion of the plurality of named entities and the list being sorted based at least in part on the significance value.
7 more elements
Dependencies are inferred from the claim text.