Method and system for mapping attributes of entities

A data mapping system, comprising:

• at least one hardware processor;
• and
• a memory module storing a plurality of instructions, said plurality of instructions, when executed, cause the hardware processor to:
• receive at least one local database as input, using an Input/Output interface of the data mapping system;
• extract at least one characteristic and at least one description corresponding to each of a plurality of product entries in the local database, using a mapping module of the data mapping system;
• and
• perform an automated mapping between the local database and a corresponding global database, by using the mapping module, wherein the automated mapping comprises of:
• generating a first set of probability distribution and confidence value by applying a Supervised Bayesian Model on the at least one characteristic of each of the plurality of product entries in the local database and product data from the corresponding global database;
• generating a second set of probability distribution and confidence value by applying an Unsupervised Textual Similarity model on the at least one description of each of the plurality of product entries in the local database and the product data from the corresponding global database;
• generating a weighted confidence score and a probability distribution based on the first set of probability distribution and confidence value and the second set of probability distribution and confidence value, wherein the weighted confidence score and probability distribution indicate extent of similarity between the plurality of product entries in the local database and that in the global database;
• and
• mapping the local database and the corresponding global database based on the first set of probability distribution and confidence value, the second set of probability distribution and confidence value, and the weighted confidence score and the probability distribution, wherein all products from the local database are mapped to corresponding product data in the global database.

One or more non-transitory machine readable information storage mediums comprising one or more instructions which when

• executed by one or more hardware processors causes:
• receiving at least one local database as input, via one or more hardware processors;
• extracting at least one characteristic and at least one description corresponding to each of a plurality of product entries in the local database, via the one or more hardware processors;
• and
• performing mapping between the local database and a corresponding global database, by performing an automated mapping, wherein the automated mapping comprises of:
• generating a first set of probability distribution and confidence value by applying a Supervised Bayesian Model on the at least one characteristic of each of the plurality of product entries in the local database and product data from the corresponding global database;
• generating a second set of probability distribution and confidence value by applying an Unsupervised Textual Similarity model on the at least one description of each of the plurality of product entries in the local database and the product data from the corresponding global database;
• generating a weighted confidence score and a probability distribution based on the first set of probability distribution and confidence value and the second set of probability distribution and confidence value, wherein the weighted confidence score and probability distribution indicate extent of similarity between the plurality of product entries in the local database and that in the corresponding global database;
• and
• mapping the local database and the corresponding global database based on the first set of probability distribution and confidence value, the second set of probability distribution and confidence value, and the weighted confidence score and the probability distribution, wherein all products from the local database are mapped to corresponding product data in the global database.