Method and apparatus for recognizing a business card using federated learning

A method for recognizing a business card of a server through federated learning, the method comprising:

• transmitting a first common prediction model for recognizing text from an image of a business card received by a terminal;
• transmitting, by the terminal, a hyper-parameter for training the first common prediction model;
• receiving a weight-parameter from the terminal;
• and
• training the first common prediction model using the weight-parameter,
• wherein the first common prediction model is transmitted to one or more of the terminal.

A terminal for performing a method for recognizing a business card through federated learning, the terminal comprising:

• a transceiver;
• a memory;
• a display;
• and
• a processor,
• wherein the processor receives an image of the business card, extracts a feature value from the image including text related to a field of an address book set in the terminal, inputs the feature value into a first common prediction model, determines first text information from an output of the first common prediction model, analyzes a pattern of the first text information, inputs the first text information into the field, caches the first text information and second text information received for error correction of the first text information from a user, and trains the first common prediction model using the image, the first text information, and the second text information,
• wherein the first common prediction model is received through a server and the first text information indicates text which can be mapped by the image.