Content information auditing service

Patent metadata

Field	Value
Publication number	US-10140518-B1
Application number	US-201514971537-A
Country	US
Kind code	B1
Filing date	Dec 16, 2015
Priority date	Dec 16, 2015
Publication date	Nov 27, 2018
Grant date	Nov 27, 2018

Abstract

Systems and methods are provided for auditing content information for a media work. In embodiments, content information for a plurality of media works that identifies entities associated with each media work may be maintained. In an embodiment, a request to identify a particular media work may be received. One or more words included in a segment of the particular media work may be identified where the segment is configured to be presented. In accordance with at least one embodiment, the one or more identified words may be filtered based on a set of rules to correct errors. An identity of the particular media work may be determined based at least in part on the filtered one or more words and the content information for the plurality of media works.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
maintaining, by a computer system, content information for a plurality of videos that identifies at least one of cast or crew associated with each video;
receiving, by the computer system, a request to identify particular content information and an identity associated with a particular video of the plurality of videos;
determining, by the computer system, a time period within the particular video that is associated with presentation of credit information for the particular video based at least in part on metadata associated with the particular video;
identifying, utilizing optical character recognition, a plurality of words in the credit information of the particular video based at least in part on the time period;
determining, by the computer system, the particular content information associated with the particular video based at least in part on the plurality of words in the credit information of the particular video and the content information for the plurality of videos;
selecting, by the computer system, a set of rules that are utilized to identify errors in the particular content information of the particular video, the set of rules comprising at least a first rule using a first location of a particular word of the plurality of words in a first frame of a segment of the particular video and a second location for the particular word in a second frame of the segment of the particular media work to identify the errors, and a second rule using a statistical operation associated with a word count of the particular word in the segment and a threshold;
updating, by the computer system, a user interface that is configured to present, via a corresponding user device, the errors identified for the particular word in the particular content information of the particular video based at least in part on applying the set of rules to the particular content information, the user interface including one or more words, including the particular word, grouped in a first configuration;
receiving, by the computer system, input from the user interface of the corresponding user device that identifies movement of the particular word to a new location on the user interface, the new location usable to associate the particular word with at least one of a specific cast or crew associated with the particular video, the one or more words grouped in a second configuration based at least in part on the input and the association;
updating, by the computer system, the content information for the plurality of videos based at least in part on the input for the particular content information of the particular video; and
determining, by the computer system, the identity of the particular video based at least in part on a comparison of a classification of entities included in the particular content information of the particular video and the classification of entities included in associated content information from a set of videos of the plurality of videos.

2. The computer-implemented method of claim 1 , wherein identifying the plurality of words in the credit information of the particular video includes performing the optical character recognition for each frame in a portion of the particular video.

3. The computer-implemented method of claim 2 , wherein identifying the plurality of words in the credit information of the particular video includes obtaining a count of each word in the credit information.

4. The computer-implemented method of claim 3 , further comprising filtering, by the computer system, the plurality of words in the credit information of the particular video based at least in part on a comparison of an average count of a particular word of the plurality of words to each occurrence of the particular word in the credit information, the average count of the particular word determined based on the obtained count of each word in the credit information.

5. The computer-implemented method of claim 1 , wherein identifying the plurality of words in the credit information of the particular video includes identifying position information for the plurality of words, utilizing the optical character recognition, in each frame in a portion of the particular video.

6. A system comprising:
a processor; and
a memory including instructions that, when executed by the processor, cause the system to, at least:
maintain content information for a plurality of media works that identifies entities associated with each media work;
receive a request to identify an identity of a particular media work of the plurality of media works using particular content information associated with the particular media work;
identify one or more words included in a segment of the particular media work, the segment configured to be presented as credit information for the particular media work;
filter the one or more words identified in the particular content information associated with the particular media work based at least in part on a set of rules to identify errors included in the one or more words, the set of rules comprising at least a first rule using a first location of a particular word of the one or more words in a first frame of the segment of the particular media work and a second location for the particular word in a second frame of the segment of the particular media work to filter the one or more words, and a second rule using a statistical operation associated with a word count of the particular word in the segment and a threshold;
update a user interface that is configured to present, via a corresponding user device, the filtered one or more words for the particular media work that identify the errors for the segment of the particular media work based at least in part on applying the set of rules to the one or more words, the user interface including a first configuration of the filtered one or more words;
receive input from the user interface of the corresponding user device that identifies movement of the particular word to a new location on the user interface, the new location usable to associate the particular word with a new entity of the entities associated with the particular media work, the one or more words, including the particular word, updated to a second configuration based at least in part on the input and the association;
update the content information for the plurality of media works based at least in part on the input for the particular media work; and
determine the identity of the particular media work based at least in part on a comparison of a classification of entities included in the particular content information of the particular media work and the classification of entities included in the updated content information for the plurality of media works.

7. The system of claim 6 , wherein the threshold is associated with one or more classifications of the entities associated with the particular media work.

8. The system of claim 6 , wherein identifying the one or more words included in the segment of the particular media work comprises performing optical character recognition on each frame of the segment of the particular media work, the optical character recognition identifying coordinates in each frame of the segment of the particular media work of each word of the one or more words.

9. The system of claim 6 , wherein the content information for the plurality of media works further identifies at least one of trivia associated with each media work, music soundtrack data associated with each media work, information indicating order of billing, or redirect links to other information associated with each media work.

10. The system of claim 6 , wherein the instruction

Assignees

• Imdb Com Inc
• Amazon Tech Inc

Inventors

• Williams Richard David
• Hay Jordan Maureen
• Sardar Adil Mohammad
• Wyatt Michael John

Classifications

• G06V20/46

  Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames · CPC title

• G06F16/7844 Primary

  using original textual content or text extracted from visual content or transcript of audio data · CPC title

• G06V30/10

  Character recognition · CPC title

• G11B27/28

  by using information signals recorded by the same method as the main recording {(G11B27/22 takes precedence)} · CPC title

• G11B27/102

  Programmed access in sequence to addressed parts of tracks of operating record carriers (access by moving the head G11B3/08, G11B5/54, G11B7/085, G11B21/022; by moving the record carrier G11B15/005, G11B17/005, by driving of both record carrier and head G11B15/1816) · CPC title