Automatic rule prediction and generation for document classification and validation

Patent metadata

Field	Value
Publication number	US-11810381-B2
Application number	US-202117303914-A
Country	US
Kind code	B2
Filing date	Jun 10, 2021
Priority date	Jun 10, 2021
Publication date	Nov 7, 2023
Grant date	Nov 7, 2023

Abstract

A method is provided. The method may include, in response to electronically receiving a document, automatically classifying the document and different parts of the document, by electronically identifying a document type associated with the document and electronically tagging data associated with the different parts of the document based on classification rules. The method may further include automatically extracting the tagged data associated with the automatically classified document based on data extraction rules. The method may further include detecting first feedback associated with the classification rules and second feedback associated with the data extraction rules. The method may further include automatically generating and updating validation rules based on the identified document type, the detected first feedback, and the detected second feedback to validate the automatically classified document and the automatically tagged and extracted data.

First claim

What is claimed is:

1. A computer-implemented method comprising:
in response to electronically receiving a document, automatically classifying the document, wherein automatically classifying the document comprises electronically identifying a document type associated with the document;
based on the document type associated with the document, automatically classifying different parts of the document and electronically tagging data associated with the different parts of the document based on one or more classification rules pertaining to the identified document type and identified data type in the document, wherein automatically classifying the document and automatically classifying the different parts of the document further comprises automatically generating and applying one or more classification rule suggestions for classifying the document and the different parts of the document;
in response to detecting first feedback associated with the one or more classification rule suggestions, updating the one or more classification rules corresponding to the one or more classification rule suggestions based on the first feedback, and applying the updated one or more classification rules;
automatically extracting the tagged data associated with the automatically classified document based on one or more data extraction rules associated with the identified document type and the identified data type, wherein automatically extracting the tagged data associated with the automatically classified document based on one or more data extraction rules further comprises automatically generating and applying one or more data extraction rule suggestions for extracting the tagged data;
in response to detecting second feedback associated with the one more data extraction rule suggestions, updating the one or more data extraction rules corresponding to the one more data extraction rule suggestions based on the second feedback, and applying the updated one or more data extraction rules; and
automatically generating, updating, and applying validation rules based on the identified document type, the detected first feedback, and the detected second feedback to validate the automatically classified document and the automatically tagged and extracted data, wherein automatically generating and applying the validation rules further comprises automatically generating and applying one or more validation rule suggestions for validating the automatically classified document and the automatically tagged and extracted data.

2. The method of claim 1 , wherein automatically classifying the document and the different parts of the document further comprises:
generating the one or more classification rule suggestions based on the one or more classification rules; and
applying at least one classification rule suggestion from the generated one or more classification rules suggestions based on a percentage threshold.

3. The method of claim 1 , wherein automatically extracting the tagged data associated with the automatically classified document further comprises:
generating the one or more data extraction rule suggestions based on the one or more data extraction rules; and
applying at least one data extraction rule suggestion from the generated one or more data extraction rule suggestions based on a percentage threshold.

4. The method of claim 1 , wherein detecting the first feedback associated with the one or more classification rules comprises detecting via a user interface at least one of a selection of a classification rule, an acceptance of a classification rule suggestion, a rejection of the classification rule suggestion, and a edit of the classification rule suggestion.

5. The method of claim 1 , wherein detecting the second feedback associated with the one or more data extraction rules comprises detecting via a user interface at least one of a selection of a data extraction rule, an acceptance of a data extraction rule suggestion, a rejection of the data extraction rule suggestion, and a edit of the data extraction rule suggestion.

6. The method of claim 1 , further comprising:
detecting third feedback, wherein the third feedback comprises data corrections to the automatically tagged and extracted data.

7. The method of claim 1 , further comprising:
automatically generating and updating the validation rules based on at least one of a type of industry associated with the document, an originating geography associated with the document, a company associated with the document.

8. A computer system, comprising:
one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:
in response to electronically receiving a document, automatically classifying the document, wherein automatically classifying the document comprises electronically identifying a document type associated with the document;
based on the document type associated with the document, automatically classifying different parts of the document and electronically tagging data associated with the different parts of the document based on one or more classification rules pertaining to the identified document type and identified data type in the document, wherein automatically classifying the document and automatically classifying the different parts of the document further comprises automatically generating and applying one or more classification rule suggestions for classifying the document and the different parts of the document;
in response to detecting first feedback associated with the one or more classification rule suggestions, updating the one or more classification rules corresponding to the one or more classification rule suggestions based on the first feedback, and applying the updated one or more classification rules;
automatically extracting the tagged data associated with the automatically classified document based on one or more data extraction rules associated with the identified document type and the identified data type, wherein automatically extracting the tagged data associated with the automatically classified document based on one or more data extraction rules further comprises automatically generating and applying one or more data extraction rule suggestions for extracting the tagged data;
in response to detecting second feedback associated with the one more data extraction rule suggestions, updating the one or more data extraction rules corresponding to the one more data extraction rule suggestions based on the second feedback, and applying the updated one or more data extraction rules; and
automatically generating, updating, and applying validation rules based on the identified document type, the detected first feedback, and the detected second feedback to validate the automatically classified document and the automatically tagged and extracted data, wherein automatically generating and applying the validation rules further comprises automatically generating and applying one or more validation rule suggestions for validating the automatically classified document and the automatically tagged and extracted data.

9. The computer system of claim 8 , wherein automatically classifying the document and the different parts of the document further comprises:
generating the one or more classification rule suggestions based on the one or more classification rules; and
applying at least one classification rule suggestion from the generated one or more classification rules suggestions

Assignees

• IBM

Inventors

• Gangadhar Jayanth
• Ramanujam Karthick
• Venkatanarasaiah Vivek
• Basavaraj Ullas M
• Shah Ankur Bharatkumar

Classifications

• G06V30/413 Primary

  Classification of content, e.g. text, photographs or tables · CPC title

• G06F18/2178

  based on feedback of a supervisor · CPC title

• G06F18/24765

  Rule-based classification · CPC title

• G06V10/765

  using rules for classification or partitioning the feature space · CPC title

• G06V30/19153

  using rules for classification or partitioning the feature space · CPC title