Filtering media data in an internet of things (IoT) computing environment

Patent metadata

Field	Value
Publication number	US-11146597-B2
Application number	US-201816185068-A
Country	US
Kind code	B2
Filing date	Nov 9, 2018
Priority date	Nov 9, 2018
Publication date	Oct 12, 2021
Grant date	Oct 12, 2021

Abstract

Embodiments for intelligent media data filtering in an Internet of Things (IoT) computing environment by a processor. User preferences for the media data may be determined according to a plurality of identified contextual factors. At least a portion of the media data may be filtered according to one or more user classifications.

First claim

The invention claimed is:

1. A method, by a processor, for intelligent media data filtering in an Internet of Things (IoT) computing environment, comprising:
when viewing media associated with media data, identifying one or more attributes, characteristics, or preferences of a user related to a consumption of the media data, wherein the identifying is inclusive of identifying an age of the user and further determining those portions of the media that negatively impacts the user or is inappropriate for the user to view;
selectively filtering, in real-time, at least a portion of the media data according to the one or more attributes, characteristics, or preferences of the user;
determining a second user has entered within a defined proximity to one or more IoT computing devices displaying the media data;
determining an identity of the second user, wherein, when the second user has not been previously input nor identified, the identifying includes cognitively inferring the one or more attributes, characteristics, or preferences of the second user by auditory cues, wherein the auditory cues include statements from alternative users proximate to the second user by which a prediction is inferred as to the age of the second user and any cultural preferences of the second user;
in conjunction with determining the identity of the second user, determining privacy preferences, stored in a database, associated with the user and the second user, wherein when the privacy preferences are prohibitive of sharing non-anonymized data, the user and the second user are classified into an anonymized user class representing a collection of the one or more attributes, characteristics, or preferences of a plurality of users such that the one or more attributes, characteristics, or preferences of each of the plurality of users is passed through a clustering operation that retains relative statistical distributions of values of the one or more attributes, characteristics, or preferences across the plurality of users to increase difficulty in using the values to specifically identify the user and the second user; and
reconfiguring the selective filtering of the at least a portion of the media data according to one or more user classifications each representing the plurality of users, wherein reconfiguring the selective filtering includes filtering the media data with respect to a cultural classification of the one or more user classifications to selectively remove non-compliant content associated with the cultural preferences of the second user.

2. The method of claim 1 , wherein selectively filtering at least the portion of the media data further includes interpreting legal, ethical, moral, cultural, ethnicity, media data ratings or courteous ones of a plurality of contextual factors in view of the media data.

3. The method of claim 1 , wherein selectively filtering at least the portion of the media data further includes muting audio data, skipping the media data, delaying turning off the media data, switching channels of the one or more IoT computing devices, morphing the media data, switching sounds or tones of the media data, substituting data of the media data, transferring the media data to an alternative IoT computing device, or performing a combination thereof.

4. The method of claim 1 , further including reconfiguring the media data displayed on the IoT computing device according to a plurality of identified contextual factors.

5. The method of claim 1 , further including classifying the user, under the anonymized user class, further into one or more filtering classes according to the one or more attributes, characteristics, or preferences of the user.

6. The method of claim 1 , further including initializing a machine learning mechanism to:
collect feedback data from the user;
learn the one or more corrective actions for filtering the media data; and
learn the one or more corrective actions having a greatest amount of effectiveness in displaying at least the portion of the media data according to the one or more user classifications.

7. A system for intelligent media data filtering in an Internet of Things (IoT) computing environment, comprising:
one or more computers with executable instructions that when executed cause the system to:
when viewing media associated with media data, identify one or more attributes, characteristics, or preferences of a user related to a consumption of the media data, wherein the identifying is inclusive of identifying an age of the user and further determining those portions of the media that negatively impacts the user or is inappropriate for the user to view;
selectively filter, in real-time, at least a portion of the media data according to the one or more attributes, characteristics, or preferences of the user;
determine a second user has entered within a defined proximity to one or more IoT computing devices displaying the media data;
determine an identity of the second user, wherein, when the second user has not been previously input nor identified, the identifying includes cognitively inferring the one or more attributes, characteristics, or preferences of the second user by auditory cues, wherein the auditory cues include statements from alternative users proximate to the second user by which a prediction is inferred as to the age of the second user and any cultural preferences of the second user;
in conjunction with determining the identity of the second user, determine privacy preferences, stored in a database, associated with the user and the second user, wherein when the privacy preferences are prohibitive of sharing non-anonymized data, the user and the second user are classified into an anonymized user class representing a collection of the one or more attributes, characteristics, or preferences of a plurality of users such that the one or more attributes, characteristics, or preferences of each of the plurality of users is passed through a clustering operation that retains relative statistical distributions of values of the one or more attributes, characteristics, or preferences across the plurality of users to increase difficulty in using the values to specifically identify the user and the second user; and

reconfigure the selective filtering of the at least a portion of the media data according to one or more user classifications each representing the plurality of users, wherein reconfiguring the selective filtering includes filtering the media data with respect to a cultural classification of the one or more user classifications to selectively remove non-compliant content associated with the cultural preferences of the second user.

8. The system of claim 7 , wherein the executable instructions, pursuant to filtering at least the portion of the media data, further interpret legal, ethical, moral, cultural, ethnicity, media data ratings or courteous ones of a plurality of contextual factors in view of the media data.

9. The system of claim 7 , wherein the executable instructions, pursuant to filtering at least the portion of the media data, further filter at least the portion of the media data by muting audio data, skipping the media data, delaying turning off the media data, switching channels of the one or more IoT computing devices, morphing the media data, switching sounds or tones of the media data, substituting data of the media data, transferring the media data to an alternative IoT computing device, or a combination thereof.

10. The system of claim 7 , wherein the executable instructions reconfigure the media data displayed on the IoT computing device according to the plurality of identified contextual factors.

11. The system of claim 7 , wherein the execut

Assignees

• IBM

Inventors

• Kwatra Shikhar
• Pandit Sushain
• Weldemariam Komminist
• Castelli Vittorio

Classifications

• H04L65/613

  for the control of the source by the destination (control signals issued by the client directed to the server or network components specially adapted for selective content distribution H04N21/637) · CPC title

• H04L65/61

  for supporting one-way streaming services, e.g. Internet radio · CPC title

• H04L67/52

  specially adapted for the location of the user terminal · CPC title

• H04L65/762

  at the source  (reformatting of additional data in video distribution servers H04N21/2355) · CPC title

• H04L65/1059 Primary

  End-user terminal functionalities specially adapted for real-time communication · CPC title