Systems and methods for records tagging based on a specific area or region of a record

• US 10,387,456 B2
• Filed: 12/20/2017
• Issued: 08/20/2019
• Est. Priority Date: 08/09/2016
• Status: Active Grant

• Current Assignee: Ripcord Inc.
• Original Assignee: Ripcord Inc.
• Inventors: Moskwinski, Michael, Fielding, Alex, Hall, Kevin Christopher, Lembo, Kimberly
• Primary Examiner(s): Wu, Yicun
• Application Number:
  US15/849,159
• Publication Number:
  US 20180129729A1
• Time in Patent Office: 608 Days
• CPC Class Codes: G06F 16/13 File access structures, e.g. distributed indices arrangements of input from, or output to, record carriers G06F3/06
• CPC Class Codes: G06F 16/287 Visualization; Browsing
• CPC Class Codes: G06F 16/9024 Graphs; Linked lists G06F16/9027 takes precedence
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 7/00 Methods or arrangements for processing data by operating upon the order or content of the data handled logic circuits H03K19/00
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

Provided are systems and methods for classifying and tagging records in a record management system using information extracted and analyzed from specific areas or regions of records. A specific area or region of the record may be scanned, and the content disposed therein processed against a plurality of classification templates. Based on proximity to the classification templates, the record may be assigned one or more tags corresponding to the classification templates.

Claims

1. A computer-implemented method for classifying a record based on an area or region of the record, comprising:

(a) accessing, with aid of one or more computer processors, a library of classification templates, wherein each classification template of the library of classification templates comprises one or more tags and one or more classification units, wherein a classification unit comprises (i) the area or region of the record and (ii) a textual classification method selected from a plurality of textual classification methods, wherein the textual classification method is at least one member selected from the group consisting of (1) a pattern of regular expression, (2) a pattern of part-of-speech, and (3) one or more classification algorithms;

(b) matching the record with a first classification template of the library of classification templates;

(c) scanning the area or region of the record;

(d) applying the textual classification method of the first classification template to textual content disposed in the area or region of the record;

(e) determining a template proximity score for the first classification template for the record, wherein the template proximity score is based at least in part on the textual classification method of the classification template applied to textual content disposed in the area or region in the record; and

(f) assigning the one or more tags of the first classification template to the record based at least in part on the template proximity score.

2. The method of claim 1, further comprising repeating (b)-(f) for a second classification template of the library of classification templates, wherein the second classification template comprises a second classification unit comprising a second textual classification method different from the textual classification method.

3. The method of claim 1, wherein the one or more tags of the first classification template is assigned to the record if the template proximity score is greater than a predetermined threshold score.

4. The method of claim 1, wherein at least two classification templates share the same classification unit.

5. The method of claim 1, further comprising determining a unit proximity score for each classification unit in the first classification template, wherein the unit proximity score is based at least in part on the textual classification method of the classification unit applied to textual content disposed in the area or region of the classification unit in the record, and wherein the template proximity score is an aggregate of the unit proximity scores determined for each classification unit.

6. The method of claim 5, wherein the unit proximity score is binary.

7. The method of claim 1, further comprising:

receiving instructions for assigning a first tag to the record from a user;

assigning the first tag to the record;

storing, in one or more databases, content of the record as training material for classifying as the first tag; and

learning a classification method of records as the first tag from the training material.

8. The method of claim 1, wherein the library of classification templates is accessed from a graph database, wherein the graph database comprises the library of classification templates and a library of classification units.

9. The method of claim 1, wherein matching the record with the first classification template of the library of classification templates comprises, for each classification unit of the first classification template, applying the textual classification method of the each classification unit to textual content disposed in the area or region of the record of the each classification unit.

10. A computer system for classifying a record based on an area or region of the record, comprising:

one or more processors; and

a memory, communicatively coupled to the one or more processors, including instructions executable by the one or more processors, individually or collectively, to implement a method for classifying a record based on the area or region of the record, the method comprising;

(a) receiving, from a user, over a computer network, a definition for a classification template, wherein a classification template is defined by one or more tags and one or more classification units, wherein a classification unit is defined by at least (i) an area or region of the record and (ii) a textual classification method selected from a plurality of textual classification methods, wherein the textual classification method is at least one member selected from the group consisting of (1) a pattern of regular expression, (2) a pattern of part-of-speech, and (3) one or more classification algorithms;

(b) matching the record with the classification template;

(c) applying the textual classification method of the classification template to textual content disposed in the area or region of the record;

(d) determining a template proximity score for the classification template for the record, wherein the template proximity score is based at least in part on the textual classification method of the classification template applied to textual content disposed in the area or region of the record; and

(e) assigning the one or more tags of the classification template to the record based at least in part on the template proximity score.

11. The computer system of claim 10, wherein the method further comprises repeating determining a unit proximity score for each classification unit in the classification template, wherein the unit proximity score is based at least in part on the textual classification method of the classification unit applied to textual content disposed in the area or region of the classification unit in the record, and wherein the template proximity score is an aggregate of the unit proximity scores determined for each classification unit.

12. The computer system of claim 10, wherein the one or more tags of the first classification template is assigned to the record if the template proximity score is greater than a predetermined threshold score.

13. The computer system of claim 10, wherein the classification unit further comprises a page index and dimensions.

14. The computer system of claim 10, wherein the method further comprises displaying, on a graphical user interface, one or more pages of the record.

15. The computer system of claim 14, wherein the definition is received from the graphical user interface.

16. The computer system of claim 15, wherein a definition for the area or region of the record is displayed over the one or more pages of the record on the graphical user interface.

17. The computer system of claim 10, wherein the method further comprises:

receiving instructions for assigning a first tag to the record from a user;

assigning the first tag to the record;

storing, in one or more databases, content of the record as training material for classifying as the first tag; and

learning a classification method of records as the first tag from the training material.

18. The computer system of claim 10, wherein the library of classification templates is accessed from a graph database, wherein the graph database comprises the library of classification templates and a library of classification units.