Content moderation
AssigneeGobubble Ai Tech Limited
InventorsNeil Henry PLATTEN, Marzia Catherine AZAM, Danielle Sarah Lucinda PLATTEN
Life of this patent
Estimating the term…
Abstract
A computer system includes a machine learning content moderation component. The machine learning moderation component receives input data representative of a media post or message made on an online platform; analyses the input data using a plurality of machine learning models; and combines outputs of the plurality of machine learning models to generate a moderation result indicating whether the media post or message contains offensive content.
Claims16
A computer system comprising:
- a machine learning content moderation component, configured to:
- receive input data representative of a media post or message made on an online platform;
- receive a behaviour profile;
- analyse the input data using a plurality of machine learning models;
- and
- combine outputs of the plurality of machine learning models to generate a moderation result indicating whether the media post or message contains offensive content,
- wherein the machine learning content moderation component is further configured to determine, based on the behaviour profile, a combination logic to apply to the outputs of the plurality of machine learning models to generate the moderation result.
A computer-implemented method of moderation, comprising:
- receiving input data representative of a media post or message made on an online platform;
- receiving a behaviour profile;
- analysing the input data using a plurality of machine learning models;
- combining outputs of the plurality of machine learning models to generate a moderation result indicating whether the media post contains offensive content;
- and
- determining, based on the behaviour profile, a combination logic to apply to the outputs of the plurality of machine learning models to generate the moderation result.
A computer-readable storage medium storing instructions which, when executed by a computer, cause the computer to:
- receive input data representative of a media post or message made on an online platform;
- receive a behaviour profile;
- analyse the input data using a plurality of machine learning models;
- and
- combine outputs of the plurality of machine learning models to generate a moderation result indicating whether the media post contains offensive content, the instructions further configured to cause the computer to:
- determine, based on the behaviour profile, a combination logic to apply to the outputs of the plurality of machine learning models to generate the moderation result.
Dependencies are inferred from the claim text.