CONTEXTUALIZATION OF MACHINE INDETERMINABLE INFORMATION BASED ON MACHINE DETERMINABLE INFORMATION

• US 20110182500A1
• Filed: 08/19/2010
• Published: 07/28/2011
• Est. Priority Date: 01/27/2010
• Status: Active Grant

• Current Assignee: DST Technologies, Inc. (SS&C Technologies Holdings Incorporated)
• Original Assignee: DST Technologies, Inc. (SS&C Technologies Holdings Incorporated)
• Inventors: Esposito, Deni, Ives, Paul M., Gentry, Michael V., Clark, Peter E.
• Granted Patent: US 8,600,173 B2
• Time in Patent Office: Days
• US Class Current: 382/159
• CPC Class Codes: G06F 3/04886 by partitioning the display area of the touch-screen or the surface of the digitising tablet into independently controllable areas, e.g. virtual keyboards or menus
• CPC Class Codes: G06V 10/987 with the intervention of an operator
• CPC Class Codes: G06V 30/40 Document-oriented image-based pattern recognition
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables

Abstract

A system for contextualizing machine indeterminable information based on machine determinable information may include a memory, an interface, and a processor. The memory may store an electronic document image which may include information determinable by a machine and information indeterminable by a machine The processor may be operative to receive, via the interface, the electronic document image. The processor may determine the machine determinable information of the electronic document image and may identify the machine indeterminable information of the electronic document image. The processor may contextualize the machine indeterminable information based on the machine determinable information. The processor may present the contextualized machine indeterminable information to the user to facilitate interpretation thereof. In response thereto, the processor may receive, via the interface, data representative of a user determination associated with the machine indeterminable information.

Claims

1. A method of contextualizing machine indeterminable information based on machine determinable information, the method comprising:

receiving an electronic document image, the electronic document image comprising at least a portion of which may be determinable by a machine, the remainder being indeterminable by a machine;

determining machine determinable information of the electronic document image;

identifying machine indeterminable information on the electronic document image;

contextualizing the machine indeterminable information based on the identified machine determinable information; and

presenting the contextualized machine indeterminable information to a user to facilitate interpretation thereof and, in response thereto, receiving data representative of a user determination associated with the machine indeterminable information.

2. The method of claim 1 further comprising storing the data representative of the user determination in a data store.

3. The method of claim 1 further comprising processing the machine indeterminable information based on the data representative of the user determination.

4. The method of claim 1 wherein the data representative of the user determination comprises an identification of the machine indeterminable information.

5. The method of claim 1 wherein the machine determinable information comprises an entity associated with the electronic document image and the machine indeterminable information comprises a document type of the electronic document image.

6. The method of claim 5 wherein contextualizing the machine indeterminable information based on the machine determinable information further comprises retrieving, from a data store, an identifier of each document type used by the entity associated with the electronic document image.

7. The method of claim 6 wherein presenting the contextualized machine indeterminable information to the user to facilitate interpretation thereof and, in response thereto, receiving the data representative of the user determination based on the machine indeterminable information further comprises presenting the identifier of each document type used by the entity and, in response thereto, receiving a selection of the document type of the electronic document image.

8. The method of claim 7 further comprising:

retrieving metadata associated with the selected document type, wherein the metadata identifies a plurality of fields of a database associated with a plurality of regions of the electronic document image; and

storing information contained with the plurality of regions of the electronic document image in the plurality of fields associated therewith.

9. The method of claim 1 further determining a routing destination of the electronic document image based on the received data representative of the user determination.

10. A method of processing electronic document images, the method comprising:

receiving an electronic document image, the electronic document image comprising at least a portion of which may be determinable by a machine;

contextualizing information related to a document type of the electronic document image based on machine determinable information of the electronic document image;

presenting the contextualized information to a user to facilitate interpretation thereof and, in response thereto, receiving data representative of the document type of the electronic document image;

retrieving, from a data store, metadata associated with the document type, wherein the metadata comprises a description of a plurality of regions of the electronic document image, an action criterion and a document handling action;

deriving a plurality of data items from the plurality of regions of the electronic document image described by the metadata;

determining, by a processor, whether the electronic document image satisfies the action criterion based on at least one of the plurality of data items; and

initiating the document handing action when the electronic document image satisfies the action criterion.

11. The method of claim 10 wherein the action criterion comprises a validation criterion for validating the plurality of data item derived from the electronic document image.

12. The method of claim 11 further comprising providing a graphical user interface displaying the electronic document image when the electronic document image does not satisfy the validation criterion.

13. The method of claim 11 further comprising storing an indication that the electronic document image requires further review when the electronic document image does not satisfy the validation criterion.

14. The method of claim 10 wherein the metadata further describes a plurality of data fields of a data store, wherein each data field corresponds to one of the plurality of regions and further comprising:

storing each respective data item of the plurality of data items in the data field of the plurality of data fields corresponding to the region of the plurality of regions from which the data item was derived.

15. The method of claim 10 wherein the document handling action comprises routing the electronic document image to a destination.

16. The method of claim 10 wherein the document handling action comprises generating an alert and communicating the alert, wherein the alert describes at least one of the plurality of data items.

17. The method of claim 10 wherein the document handling action comprises modifying a handling priority associated with the electronic document image.

18. The method of claim 10 wherein the action criterion is satisfied when at least one data item cannot be derived from at least one of the plurality of regions.

19. The method of claim 18 further comprising receiving, via a graphical user interface, the at least one data item which cannot be derived from the at least one of the plurality of regions.

20. The method of claim 10 wherein the action criterion is satisfied when at least one of the plurality of data items is indicative of a high cash transaction.

21. The method of claim 10 wherein the action criterion is satisfied when at least one of the plurality of data items is indicative of an identified entity of a plurality of entities being associated with the electronic document image.

22. The method of claim 10 further comprising receiving a plurality of entity identifiers from a user, wherein each entity identifier identifies an entity the user wishes to monitor and the action criterion is satisfied when at least one of the plurality of data items is indicative of at least one of the plurality of entity identifiers.

23. The method of claim 22 further wherein the document handling action comprises generating an alert and communicating the alert to the user, wherein the alert comprises the at least one of the plurality of entity identifiers.

24. A method for data extraction and classification of an electronic document image, the method comprising:

receiving an electronic document image, the electronic document image comprising at least a portion of which may be determinable by a machine;

processing machine determinable information of the electronic document image to determine a plurality of document types having characteristics similar to the electronic document image and a plurality of corresponding likelihood values, wherein the likelihood value of each document type indicates a likelihood that the electronic document image is characterized by the corresponding document type;

assembling a graphical user interface which displays the electronic document image and a selector corresponding to each of the plurality of document types, wherein each selector comprises a graphical attribute indicative of the likelihood of the electronic document image being characterized by the document type corresponding to each selector;

providing the graphical user interface to a computing device; and

receiving, via the graphical user interface, a selection of the selector corresponding to the document type of the plurality of document types which characterizes the electronic document image.

25. The method of claim 24 wherein processing the electronic document image to determine the plurality of document types having characteristics similar to the electronic document image and the plurality of corresponding likelihood values further comprises:

identifying an entity associated with the electronic document image;

retrieving a plurality of document types associated with the entity; and

processing the electronic document image to determine the plurality of document types which have characteristics similar to the electronic document image and which are associated with the entity, and to determine the plurality of corresponding likelihood values, wherein each of the plurality of corresponding likelihood values indicates the likelihood that the electronic document image is characterized by the corresponding document type.

26. The method of claim 24 further comprising:

initiating an action associated with the document type of the plurality of document types corresponding to the selector of the plurality of selectors.

27. The method of claim 26 wherein the action comprises classifying the electronic document image as associated with the entity and characterized by the document type of the plurality of document types corresponding to the selector of the plurality of selectors.

28. The method of claim 24 wherein the plurality of selectors are ordered in accordance with a frequency of use of each of the plurality of selectors for the entity.

29. The method of claim 24 further comprising:

providing, via the graphical user interface, a plurality of data fields corresponding to the document type of the plurality of document types; and

receiving, via the graphical user interface a plurality of values corresponding to the plurality of data fields.

30. The method of claim 24 further comprising displaying, via the graphical user interface, the likelihood value of each of the plurality of document types.

31. A method of providing a graphical user interface for associating regions of an electronic document image with data fields, the method comprising:

assembling a graphical user interface for selecting regions of electronic document images, wherein the graphical user interface receives selections of regions of an electronic document image and generates identifiers describing relative locations of the regions;

providing the interface to a computing device;

receiving an identifier of a first region of a first electronic document image, the first region being selected by an operator of the computing device, wherein the identifier indicates a relative location of the first region on the first electronic document image;

determining, by a processor, a document type of the first electronic document image; and

storing, in a data store, the identifier of the first region in association with the document type of the first electronic document image.

32. The method of claim 31 further comprising:

receiving a second electronic document image, wherein the second electronic document image is characterized by the document type of the first electronic document image;

retrieving the identifier of the first region stored in association with the document type;

determining a second region of the second electronic document corresponding to the identifier of first region; and

deriving a data item from the determined second region.

33. The method of claim 32 further comprising storing the data item in a data field associated with the second region and the document type.

34. The method of claim 32 further comprising displaying to the operator, via the graphical user interface, the second electronic document image and the data item.

35. The method of claim 34 wherein displaying to the operator, via the graphical user interface, the second electronic document image and the data item further comprises displaying to the operator, via the graphical user interface, the second electronic document image and the data item, wherein the region of the second electronic document image is highlighted.

36. The method of claim 34 further comprising receiving from the operator, via the graphical user interface, a corrected data item and storing the corrected data item in a data field associated with the second region and the document type.

37. The method of claim 34 further comprising receiving from the operator, via the graphical user interface, a confirmation indicating that the data item accurately corresponds to the second region of the second electronic document image.

38. A method for facilitating data extraction from electronic document images, the method comprising:

receiving an electronic document image;

determining a document type which characterizes the electronic document image, wherein the document type comprises metadata describing a plurality of regions of the electronic document image;

deriving a data item from each of the plurality of regions;

assembling a graphical user interface, wherein the graphical user interface displays the electronic document image and the plurality of data items, the plurality of data items being displayed as a plurality of editable values; and

providing the graphical user interface to a computing device.

39. The method of claim 38 wherein each of the plurality of editable values is displayed adjacent to the region of the electronic document image from which each of the plurality of editable values was derived.

40. The method of claim 38 further comprising:

receiving, via the graphical user interface, a confirmation of the plurality of data items; and

storing the plurality of data items in a plurality of data fields associated with the plurality of regions.

41. The method of claim 38 further comprising:

receiving, via the graphical user interface, at least one corrected data item of the plurality of data items;

updating the plurality of data items with the at least one corrected data item; and

storing the plurality of data items in a plurality of data fields associated with the plurality of regions.

42. A method for facilitating data extraction from electronic document images, the method comprising:

receiving an electronic document image, wherein the electronic document image comprises typographic information and a plurality of handwritten items;

determining at least one value corresponding to at least one of the plurality of handwritten items;

assembling a graphical user interface for identifying any remaining values corresponding to the plurality of handwritten items, the graphical user interface displaying the electronic document image, wherein the at least one value of the at least one of the plurality of handwritten items is displayed as an editable value;

providing the graphical user interface to a computing device;

receiving, via the graphical user interface, any remaining values corresponding to the plurality of handwritten items; and

storing the plurality of values in a data store.

43. The method of claim 42 further comprising:

determining a group of pixels corresponding to each of the plurality of handwritten items within the electronic document image; and

modifying the group of pixels corresponding to each of the plurality of handwritten items such that each of the plurality of handwritten items is prominently displayed on the electronic document image.

44. The method of claim 43 wherein modifying the group of pixels corresponding to each of the plurality of handwritten items further comprises adding a colored background to the group of pixels.

45. A system of extracting data from, and classifying, electronic document images, the system comprising:

means for receiving an electronic document image;

means for determining an entity associated with the electronic document image;

means for identifying a plurality of document types associated with the entity;

means for determining, for each of the plurality of document types, a likelihood value indicative of a likelihood that each document type characterizes the electronic document image;

means for assembling, by a processor, a graphical user interface for extracting a plurality of data items from the electronic document image, the graphical user interface comprising a plurality of selectors corresponding to the plurality of document types, wherein each of the plurality of selectors comprises a graphical attribute indicative of the likelihood value of the corresponding document type; and

means for providing the graphical user interface to an operator.

46. A system for contextualizing machine indeterminable information based on machine determinable information, the system comprising:

a memory operative to store an electronic document image, the electronic document image comprising at least a portion of which may be determinable by a machine, the remainder being indeterminable by a machine;

an interface coupled with the memory and operative to receive the electronic document image and communicate with a device of a user; and

a processor coupled with the interface and operative to receive, via the interface, the electronic document image, determine machine determinable information of the electronic document image, identify machine indeterminable information of the electronic document, contextualize the machine indeterminable information based on the machine determinable information, and provide, via the interface, the contextualized machine indeterminable information to the device of the user to facilitate interpretation thereof, and, in response thereto, receive, via the interface, data representative of a user determination associated with the machine indeterminable information.

47. The system of claim 46 wherein the processor further stores, in the memory, the data representative of the user determination.

48. The system of claim 46 wherein the processor further processes the machine indeterminable information based on the data representative of the user determination.

49. The system of claim 46 wherein the data representative of the user determination comprises an identification of the machine indeterminable information.

50. The system of claim 46 wherein the machine determinable information comprises an entity associated with the electronic document image and the machine indeterminable information comprises a document type of the electronic document image.

51. The system of claim 50 wherein the processor further receives, from the memory, an identifier of each document type used by the entity associated with the electronic document image.

52. The system of claim 51 wherein the processor further presents the identifier of each document type used by the entity and, in response thereto, receives a selection of the document type of the electronic document image.

53. The system of claim 46 wherein the processor further determines a routing destination of the electronic document image based on the received data representative of the user determination and routes the electronic document image to the determined routing destination.