Method and system for preventing upload of multimedia content with objectionable content into a server

Patent metadata

Field	Value
Publication number	US-10841653-B2
Application number	US-201916370899-A
Country	US
Kind code	B2
Filing date	Mar 30, 2019
Priority date	Feb 15, 2019
Publication date	Nov 17, 2020
Grant date	Nov 17, 2020

Abstract

The present invention relates to the field of content identification and more particularly to detection and identification of objectionable content present in a multimedia content. The objectionable content is detected before the upload of the content to a server or social media and it alerts the user about the presence of objectionable content based on the intelligent analytics. Further, during the alerting process the proposed mechanism is configured to consider the consequences of publishing or uploading the given content to a server or social media. Further, it also analyses the potential viewers, their profile, profile of the characters in the multimedia content.

First claim

What is claimed is:

1. A method of preventing upload of multimedia content with objectionable content into a server, the method comprising:
receiving, by a computing unit, the multimedia content from a user;
identifying, by the computing unit, the objectionable content present in the multimedia content, wherein identifying the objectionable content comprises:
determining one or more characters and an environment hosting the one or more characters from the multimedia content to identify one or more topics and a theme of the multimedia content;
identifying interactions among the one or more characters in the multimedia content;
associating sentiments with the one or more characters and actions performed by the one or more characters, wherein the sentiments are associated by computing a sentiment graph, wherein the sentiment graph is generated based on attributes table populated from historical data, action relating to the one or more characters and a machine learning algorithm; and
determining a relationship between at least one of the theme, the one or more topics, the interactions among the one or more characters, the sentiments of the one or more characters and the sentiments of the actions;

providing by the computing unit, an alert to the user about the objectionable content present in the multimedia content while uploading to the server; and
deleting, by the computing unit, the objectionable content present in the multimedia content upon receiving instructions from the user in response to the alert provided to the user, thereby preventing the upload of the multimedia content with the objectionable content to the server.

2. The method of claim 1 , wherein the one or more topics in the multimedia content comprises at least one of one or more subjects and one or more objects in the multimedia content.

3. The method of claim 1 , wherein identifying the one or more topics in the multimedia content comprising a text comprises:
determining at least one attention word from a text present in the multimedia content, wherein the attention word is determined by classifying subject from predicate in the text; and
identifying relative frequency of the subject, wherein the subject is derived as topic based on relative frequency of the subject.

4. The method of claim 1 , further wherein identifying the one or more topics in the multimedia content comprising an audio visual content comprises:
determining at least one of the one or more objects present in the multimedia content,
wherein the at least one of the one or more objects is determined by at least one of facial recognition, user context and attributes associated with the one or more objects from historical data in the multimedia content.

5. The method of claim 1 , wherein identifying the theme is based on at least one of captions, and context graphs in the multimedia content.

6. The method of claim 1 , wherein the interactions among the one or more characters is identified by extracting at least one of predicate associated with one or more subjects, and physical adjacency of one or more objects.

7. The method of claim 1 , comprises predicting a potential proliferation of the multimedia content with the objectionable content based on sensitivity index derived from weights associated with a plurality of parameters, wherein the plurality of parameters include viewer class, type of social media, the one or more topics and attributes associated with the one or more topics, wherein the user is alerted about the predicted potential proliferation while uploading the multimedia content to the server.

8. The method of claim 1 , wherein the user is provided an option to modify the objectionable content present in the multimedia content before uploading.

9. A computing unit for preventing upload of multimedia content with objectionable content into a server comprising:
a processor; and
a memory communicatively coupled to the processor, wherein the memory stores the processor instructions, which, on execution, causes the processor to:
receive the multimedia content from a user;
identify the objectionable content present in the multimedia content, wherein identifying the objectionable content comprises:
determining one or more characters and an environment hosting the one or more characters from the multimedia content to identify one or more topics and a theme of the multimedia content,
identifying interactions among the one or more characters in the multimedia content;
associating sentiments with the one or more characters and actions performed by the one or more characters, wherein the processor is configured to associate the sentiments by computing a sentiment graph, wherein the sentiment graph is generated based on attributes table populated from historical data, action relating to the one or more characters and a machine learning algorithm; and
determining a relationship between at least one of the theme, the one or more topics, the interactions among the one or more characters, the sentiments of the one or more characters and the sentiments of the actions;

alert the user about the objectionable content present in the multimedia content while uploading to the server; and
delete the objectionable content present in the multimedia content upon receiving instructions from the user in response to the alert provided to the user, thereby preventing the upload of the multimedia content with the objectionable content to the server.

10. The computing unit of claim 9 , wherein the one or more topics in the multimedia content comprises at least one of one or more subjects and one or more objects in the multimedia content.

11. The computing unit of claim 9 , wherein the processor is configured to identify the one or more topics comprises:
determining at least one of the one or more objects present in the multimedia content, wherein the at least one of the one or more objects is determined by at least one of face recognition, user context and attributes associated with the one or more objects from historical data in the multimedia content.

12. The computing unit of claim 9 , wherein the processor is configured to identify the one or more topics comprises:
determining at least one of the one or more objects present in the multimedia content,
wherein the at least one of the one or more objects is determined by at least one of face recognition, user context and attributes associated with the one or more objects from historical data in the multimedia content.

13. The computing unit of claim 9 , wherein the processor is configured to identify the theme based on at least one of captions, and context graphs in the multimedia content.

14. The computing unit of claim 9 , wherein the processor is configured to identify the interactions among the one or more characters by extracting at least one of predicate associated with the one or more subjects, and physical adjacency of one or more objects.

15. The computing unit of claim 9 , wherein the processor is configured to predict a potential proliferation of the multimedia content with the objectionable content based on sensitivity index derived from weights associated with a plurality of parameters, wherein the plurality of parameters include viewer class, type of social media, the one or more topics and attributes associated with the one or more topics, wherein the user is alerted about the predicted potential proliferation while uploading the multimedia content to the server.

16. The computing unit of claim 9 , wherein the processor is configured to provide the user an option to modify the objectionable co

Assignees

• Wipro Ltd

Inventors

• Ramachandra Iyer Manjunath
• Agnihotram Gopichand

Classifications

• G06V40/161

  Detection; Localisation; Normalisation · CPC title

• G06N20/00

  Machine learning · CPC title

• H04N21/45452

  applied to an object-based stream, e.g. MPEG-4 streams · CPC title

• G06Q30/00 Primary

  Commerce · CPC title

• H04N21/4542 Primary

  Blocking scenes or portions of the received content, e.g. censoring scenes · CPC title