System and method for enrichment of OCR-extracted data

A method for enrichment of OCR extracted data implemented by computing system comprising one or more computing devices, the method comprising:

• accepting a set of extraction criteria and a set of configuration parameters;
• capturing data satisfying an extraction criteria using the configuration parameters;
• adapting captured data using a set of domain specific rules and a set of OCR error patterns;
• generating one or more learning data models using the adapted data and the configuration parameters, wherein the generated learning data models are further optimized based on a confusion matrix where probability values are extracted using a frequency of observed values against ground truth and the confusion matrix is extended for one or more n-grams;
• and
• dynamically updating the extraction criteria using the generated learning data models.

A non-transitory computer readable medium having stored thereon instructions for enriching OCR extracted data comprising machine executable code which when executed by at least one processor, causes the processor to:

• accept a set of extraction criteria and a set of configuration parameters;
• capturing data satisfying an extraction criteria using the configuration parameters;
• adapt captured data using a set of domain specific rules and a set of OCR error patterns;
• generate one or more learning data models using the adapted data and the configuration parameters, wherein the generated learning data models are further optimized based on a confusion matrix where probability values are extracted using a frequency of observed values against ground truth and the confusion matrix is extended for one or more n-grams;
• and
• dynamically update the extraction criteria using the generated learning data models.