Samsung electronics co., ltd. (20240233206). METHODS AND SYSTEMS FOR GENERATING ONE OR MORE EMOTICONS FOR ONE OR MORE USERS simplified abstract
Contents
METHODS AND SYSTEMS FOR GENERATING ONE OR MORE EMOTICONS FOR ONE OR MORE USERS
Organization Name
Inventor(s)
Dewesh Deo Singh of Noida (IN)
Sattdeepan Dutta of Noida (IN)
METHODS AND SYSTEMS FOR GENERATING ONE OR MORE EMOTICONS FOR ONE OR MORE USERS - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240233206 titled 'METHODS AND SYSTEMS FOR GENERATING ONE OR MORE EMOTICONS FOR ONE OR MORE USERS
The abstract describes a method for generating emoticons for users based on fictional characters using a Multiple Localized Discriminator Generative Adversarial Network (MLD GAN).
- Receives an image from the MLD GAN based on features of fictional characters.
- Determines weights for each discriminator based on the distance from the features.
- Generates an image info-graph based on the received image.
- Calculates relevance for each discriminator using the info-graph, features, and distance.
- Generates multiple emoticon images based on different sets of features.
Potential Applications: - Customized emoticons for users based on their favorite fictional characters. - Personalized messaging platforms with unique emoticon options.
Problems Solved: - Providing users with emoticons that reflect their interests and preferences. - Enhancing user experience in communication through personalized emoticons.
Benefits: - Increased user engagement and satisfaction. - Improved communication through expressive and relevant emoticons.
Commercial Applications: Title: Personalized Emoticon Generator for Messaging Platforms Description: This technology can be used in messaging apps to offer users a wide range of personalized emoticons based on fictional characters, enhancing user experience and engagement in communication.
Questions about the technology: 1. How does this method improve user interaction in messaging platforms? 2. What sets this emoticon generation method apart from traditional methods?
Original Abstract Submitted
a method for generating one or more emoticons for one or more users with respect to one or more fictional characters is provided. the method includes receiving a first image generated by a multiple localized discriminator (mld) generative adversarial network (gan) based on a set of features from multiple sets of features associated with the one or more fictional characters, resulting in generation of an output value associated with each of the plurality of discriminators, determining a weight associated with each of the plurality of discriminators based on a distance between each discriminator and the set of features, generating an image info-graph associated with the first image generated by the mld gan upon receiving the first image, calculating a relevance associated with each of the plurality of discriminators based on the image info-graph, the set of features and the distance, and generating a plurality of images representing a plurality of emoticons associated with the one or more fictional characters based on each of the multiple sets of features.
