- Number
- 10810367
- Published
- 2020-10-20
- Filed
- 2018-11-13
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Maratta; Concetta, Kennedy; Brian, Toback; Zachary, Wiener; Jared L., Westerwelle; Fabian
- CPC
- G06F40/30; G06N3/02; G06F16/483; G06F40/205; G06F16/783; G06F16/75; G06N20/00; G06F16/908; G06F16/45; G06N3/08; G06F40/295; G06F40/263; G06F40/216; G06F16/683; G06F16/65; G06F40/169
- Verdict
- Set aside content processing automation, business/NLP
- Source
- Google Patents · FreePatentsOnline
Abstract
In one implementation, a content processing system includes a computing platform having a hardware processor and a system memory storing a content classification software code, a natural language processor, and a computer vision analyzer. The hardware processor executes the content classification software code to receive content inputs from multiple content sources, and, for each content input, to parse the content input for metadata describing the content input, obtain a description of language-based content included in the content input from the natural language processor, and obtain a description of visual content included in the content input from the computer vision analyzer. The content classification software code further associates predetermined annotation tags with the content input based on the metadata, the description of the language-based content, and the description of the visual content, and assigns the content input to a predetermined subject matter classification based on the associated annotation tags.
Background
BACKGROUND(1) The timely distribution of news or other information describing dynamic or highly complex events often requires contributions from a geographically dispersed team of journalists, as well as sometimes remote experts having specialized knowledge and/or uniquely relevant experience. Although tools for enabling collaboration exist, those conventional tools are typically optimized for a particular project, e.g., a specific news broadcast or story, or for a specific content distribution platform. There remains a need in the art for a collaboration solution enabling the real-time, accurate, and consistent distribution of information provided by multiple contributors and/or content sources, across a variety of communications platforms.SUMMARY(2) There are provided systems and methods for content processing automation, substantially as shown in and/or described in connection with at least one of the figures, and as set forth more completely in the claims.
Claims
1. A content processing system comprising: a computing platform including a hardware processor and a system memory; the system memory storing a content classification software code, a natural language processor, and a computer vision analyzer; the hardware processor configured to execute the content classification software code to: receive a plurality of content inputs from a plurality of content sources; for a first content input of the plurality of content inputs: parse the first content input for metadata describing the first content input; obtain, from the natural language processor, a description of a language-based content included in the first content input; obtain, from the computer vision analyzer, a description of a visual content included in the first content input; associate a plurality of predetermined annotation tags with the first content input based on the metadata, the description of the language-based content, and the description of the visual content; and assign the first content input to a predetermined subject matter classification based on the plurality of predetermined annotation tags.
11. A method for use by a media content annotation system including a computing platform having a hardware processor and a system memory storing a content classification software code, a natural language processor, and a computer vision analyzer, the method comprising: receiving, using the hardware processor and the content classification software code, a plurality of content inputs from a plurality of content sources; for a first content input of the plurality of content inputs: parsing the first content input, using the hardware processor and the content classification software code, for metadata describing the first content input; obtaining, using the hardware processor and the content classification software code, from the natural language processor, a description of a language-based content included in the first content input; obtaining, using the hardware processor and the content classification software code, from the computer vision analyzer, a description of a visual content included in the first content input; associating, using the hardware processor and the content classification software code, a plurality of predetermined annotation tags with the first content input based on the metadata, the description of the language-based content, and the description of the visual content; and assigning, using the hardware processor and the content classification software code, the first content input to a predetermined subject matter classification based on the plurality of predetermined annotation tags.