System to calculate a reconfigured confidence score

A method to calculate a reconfigured confidence score, for an extracted text, the method comprising:

• receiving inputs from a plurality of models, wherein inputs from each of the plurality of models include a first text, a plurality of labels corresponding to the first text, and a plurality of confidence scores corresponding to the first text and their respective labels;
• assigning a weightage, by a processor, to each of the inputs received from the plurality of models;
• choosing one input, by an input module, from the inputs received based on the weightage, wherein:
• chosen input comprises of the first text with a first label;
• and
• a first output confidence score is generated by a first coarse correctional model based on the first text and the first label;
• retrieving, by a second coarse correctional model, a second text associated with the first label and generating a second output confidence score based on the first label and the retrieved second text, wherein the second text is different from the first text;
• retrieving, by a third coarse correctional model, a third text with a second label and generating a third output confidence score based on the retrieved third text and the second label, wherein:
• the third text is different from the first text and the second text;
• and
• the second label is different from the first label, wherein the second text, the third text, and the second label are extracted from a database;
• comparing, by a comparison module, the first output confidence score, the second output confidence score, and the third output confidence score;
• and
• generating an output, by an output module, wherein the output comprises the first text, the first label, and a final confidence score, wherein the final confidence score is one among the first output confidence score, the second output confidence score, and the third output confidence score.