Method and system for enhancing a mutimodal input content

A User Equipment (UE) for enhancing a multimodal input content, comprising:

• a processor;
• and
• a memory communicatively coupled to the processor, wherein the memory is configured to store processor-executable instructions, which, on execution, causes the processor to:
• obtain at least one text-block associated with a multimodal input;
• determine a plurality of features of each of the at least one text-block using a natural language processing (NLP) model, wherein the plurality of features comprises context of each of the at least one text-block and at least one of gender information, contextual lingo information, and lingo usage information;
• identify a usage pattern of the plurality of features based on historic data associated with usage of the plurality of features using a pattern identification neural network (NN) model, wherein the historic data comprises at least one of usage of emoticons and emojis, characteristics of emoticons, lingo usage details, and skin-tone features of emoticons;
• and
• enhance the multimodal input by generating a personalized text for each of the at least one text-block based on the determined plurality of features and the identified usage pattern of the plurality of features,
• wherein the processor is configured to generate the personalized text for each of the at least one text-block by:
• inserting at least one of one or more emoticons and one or more emojis to the at least one text-block with a skin-tone associated with usage pattern of a user, based on the context of each of the at least one text-block and a threshold value, wherein the threshold value is preconfigured based on usage of the at least one of the one or more emoticons and the one or more emojis by the user;
• and
• inserting lingo of each word of the at least one text-block using a user lingo database, wherein the user lingo database comprises information related to a purality of lingo words frequently used by the user.

The non-transitory computer-readable recording medium having recorded thereon a program, which when executed by a computer, performs a method comprising:

• obtaining, by a processor of a user equipment (UE), at least one text-block associated with a multimodal input;
• determining, by the processor, a plurality of features of each of the at least one text-block using a natural language processing (NLP) model, wherein the plurality of features comprises a context of each of the at least one text-block and at least one of gender information, contextual lingo information, and lingo usage information;
• identifying, by the processor, a usage pattern of the plurality of features based on historic data associated with usage of the plurality of features using a pattern identification neural network (NN) model, wherein the historic data comprises at least one of usage of emoticons and emojis, characteristics of emoticons, lingo usage details, and skin-tone features of emoticons;
• and
• enhancing, by the processor, the multimodal input by generating a personalized text for each of the at least one text-block based on the determined plurality of features and the identified usage pattern of the plurality of features,
• wherein generating the personalized text for each of the at least one text-block comprises:
• inserting, by the processor, at least one of one or more emoticons and one or more emojis to the at least one text-block with a skin-tone associated with a usage pattern of a user, based on the context of each of the at least one text-block and a threshold value, wherein the threshold value is preconfigured based on a usage of the at least one of the one or more emoticons and the one or more emojis by the user.