JOINT UNDERSTANDING OF ACTORS, LITERARY CHARACTERS, AND MOVIES

Number: 20200050677
Published: 2020-02-13
Filed: 2018-08-07
Assignee: Disney Enterprises, Inc.
Inventors: LI; Boyang, KIM; Hannah, KATERENCHUK; Denys
CPC: G06N3/047; G06F16/248; G06F16/3344; G06N7/01; G06N20/00; G06F16/9535; G06F16/55; G06F16/24578
Verdict: Set aside content/character understanding research, analytics
Source: Google Patents · FreePatentsOnline

Abstract

Systems, methods, and articles of manufacture are disclosed for learning models of movies, keywords, actors, and roles, and querying the same. In one embodiment, a recommendation application optimizes a model based on training data by initializing the mean and co-variance matrices of Gaussian distributions representing movies, keywords, and actors to random values, and then performing an optimization to minimize a margin loss function using symmetrical or asymmetrical measures of similarity between entities. Such training produces an optimized model with the Gaussian distributions representing movies, keywords, and actors, as well as shift vectors that change the means of movie Gaussian distributions and model archetypical roles. Subsequent to training, the same similarity measures used to train the model are used to query the model and obtain rankings of entities based on similarity to terms in the query, and a representation of the rankings may be displayed via, e.g., a display device.

Background

BACKGROUNDField of the Invention

Embodiments presented in this disclosure generally relate to recommendation and search engines. More specifically, embodiments presented herein relate to techniques for learning models of movies, keywords, actors, and roles, and querying the same.Description of the Related Art

The motion picture industry has been extremely risky. Despite the best efforts of directors, casting directors, screenwriters, marketing teams, and experienced executives, it remains difficult to guarantee a return on investment from any movie production.

Recently, the computational understanding of narrative content, in textual and visual formats, has received renewed attention. However, in the context of movies in particular, little attempt has been made to understand movie actors in relation to characters they play and movies they appear in.SUMMARY

One embodiment of this disclosure provides a computer-implemented method that generally includes training, based at least in part on received training data, a model which generally includes Gaussian distributions representing actors, movies, and keywords. The method further includes receiving a query including one or more terms, and ranking, using the trained model, one or more of the actors, movies, or keywords, based at least in part on similarity to the one or more terms in the query.

Another embodiment provides a computer-implemented method that generally includes receiving information specifying at

Claims

1. A computer-implemented method, comprising: training, based at least in part on received training data, a model which includes Gaussian distributions representing actors, movies, and keywords; receiving a first query including one or more terms; and ranking, using the trained model, one or more of the actors, movies, or keywords, based at least in part on similarity to the one or more terms in the first query. 11. A computer-implemented method, comprising: receiving information specifying at least movies, keywords describing the movies, and actors appearing in the movies; initializing means and co-variance matrices of a plurality of Gaussian distributions representing the movies, keywords, and actors with random values; and optimizing, based at least in part on the received information, the plurality of Gaussian distributions. 19. A computer-implemented method, comprising: receiving text describing one or more movies and characters therein; performing coreference resolution to link pronouns in the received text with the characters; identifying words in the received text associated with actions performed by the characters, actions received by the characters, and descriptions of the characters; mapping the identified words associated with the actions performed by the characters, the actions received by the characters, and the descriptions of the characters to numerical representations; averaging the numerical representations of the words associated with the actions performed by the characters, the actions received by the characters, and the descriptions of the characters; concatenating, for each character, the averaged numerical representations associated with the character into a vector representing the character; identifying archetypical roles as clusters of the vectors representing the characters; and training a model based, at least in part, on the identified archetypical roles.