Check data lift for error detection

• US 9,384,393 B2
• Filed: 10/29/2013
• Issued: 07/05/2016
• Est. Priority Date: 10/29/2013
• Status: Active Grant

• Current Assignee: Bank of America Corp.
• Original Assignee: Bank of America Corp.
• Inventors: Smith, Michael Gerald, Johnson, Scott Andrew, Govindarajan, Saravana Kumar, Hjellming, Michael Scott, Hanson, Brian David, Koo, Hyunmo
• Primary Examiner(s): YANG, WEI WEN
• Application Number:
  US14/065,821
• Publication Number:
  US 20150117747A1
• Time in Patent Office: 980 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/416 Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors

Abstract

Embodiments for identifying errors based on data extracted from financial record images includes systems that receive one or more financial record images from a user, apply an optical character recognition process to at least a portion of the one or more financial record images, and identify record data based on the applied optical character recognition process comprising at least a name of a party to the financial record. The systems further identify errors associated with the one or more financial record images based on the record data.

Claims

1. A system for identifying errors based on data extracted from a first image, the system comprising:

a computer apparatus including a processor and a memory; and

a software module stored in the memory, comprising executable instructions that when executed by the processor cause the processor to;

receive the first image from a user, the first image comprising a financial record;

apply a first optical character recognition process to at least a portion of the first image, wherein the first optical character recognition process comprises a first algorithm;

identify a first set of record data based on the applied first optical character recognition process comprising at least a name of a party to the financial record;

identify errors associated with the first image based on the first set of record data, the errors comprising at least one of errors associated with the first image, errors associated with a financial transaction, errors associated with processing of the financial record, and errors in the first set of record data;

assign a confidence level to one or more portions of the financial record based on the identified first set of record data and the identified errors of the first image, wherein the confidence level is a pass rating or a fail rating;

determine that a first portion of the one or more portions of the financial record has a first confidence level of a fail rating;

prompt the user to provide a second image of the same side of the first image of the financial record in response to the determination that the first portion of the financial record has a first confidence level of a fail rating, wherein the second image comprises the first portion of the financial record, and wherein the second image portrays the first portion of the financial record at a different angle, portrays the first portion of the financial record in a different light, is captured with different image capturing equipment than the first image, or is a modified version of the first image;

receive the second image from the user via a user computing device associated with the user, wherein the user computing device comprises at least an image capture device that captures the second image and a communication device that communicates the second image from the user;

apply a second optical character recognition process to at least a portion of the second image, wherein the portion of the second image comprises the first portion of the financial record, and wherein the second optical character recognition process comprises a second algorithm that is different from the first algorithm; and

identify a second set of record data based on the second optical character recognition process comprising at least one new record data that is not included in the first set of record data.

2. The system of claim 1, wherein the executable instructions further cause the processor to:

send the second image to an investigation group;

receive instructions from the investigation group; and

process the financial record based on the instructions.

3. The system of claim 1, wherein the executable instructions further cause the processor to:

identify a payee name in the second image based on applying the second optical character recognition process; and

compare the payee name and the user,

wherein the financial record comprises a check.

4. The system of claim 3, wherein the executable instructions further cause the processor to:

determine that the payee name and the user match; and

process the check in response to the match.

5. The system of claim 3, wherein the executable instructions further cause the processor to:

determine that the payee name and the user do not match.

6. The system of claim 5, wherein the executable instructions further cause the processor to:

determine that the user is authorized to deposit the check; and

process the check in response to the authorization determination.

7. The system of claim 5, wherein the executable instructions further cause the processor to:

determine that the user is not authorized to deposit the check; and

send the check image to an investigation group.

8. The system of claim 1, wherein the first set of record data further comprises a payor name, an account number, terms of the financial record, time period that the financial record is in effect, check numbers, endorsements, merchant codes, file identifiers, or source identifiers.

9. A computer program product for identifying errors based on data extracted from a first image, the computer program product comprising:

at least one non-transitory computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising;

computer readable program code configured to receive the first image from a user, the first image comprising a financial record;

computer readable program code configured to apply a first optical character recognition process to at least a portion of the first image, wherein the first optical character recognition process comprises a first algorithm;

computer readable program code configured to identify a first set of record data based on the applied first optical character recognition process comprising at least a name of a party to the first financial record;

computer readable program code configured to identify errors associated with the first image based on the first set of record data, the errors comprising at least one of errors associated with the first image, errors associated with a financial transaction, errors associated with processing of the financial record, and errors in the first set of record data;

computer readable program code configured to assign a confidence level to one or more portions of the financial record based on the identified first set of record data and the identified errors of the first image, wherein the confidence level is a pass rating or a fail rating;

computer readable program code configured to determine that a first portion of the one or more portions of the financial record has a first confidence level of a fail rating;

computer readable program code configured to prompt the user to provide a second image of the same side of the first image of the financial record in response to the determination that the first portion of the financial record has a first confidence level of a fail rating, wherein the second image comprises the first portion of the financial record, and wherein the second image portrays the first portion of the financial record at a different angle, portrays the first portion of the financial record in a different light, is captured with different image capturing equipment than the first image, or is a modified version of the first image;

computer readable program code configured to receive the second image from the user via a user computing device associated with the user, wherein the user computing device comprises at least an image capture device that captures the second image and a communication device that communicates the second image from the user;

computer readable program code configured to apply a second optical character recognition process to at least a portion of the second image, wherein the portion of the second image comprises the first portion of the financial record, and wherein the second optical character recognition process comprises a second algorithm that is different from the first algorithm; and

computer readable program code configured to identify a second set of record data based on the second optical character recognition process comprising at least one new record data that is not included in the first set of record data.

10. The computer program product of claim 9, comprising the computer readable storage medium having computer readable program code embodied therewith, the computer readable program code further configured to:

send the second image to an investigation group;

receiving instructions from the investigation group; and

process the image based on the instructions.

11. The computer program product of claim 9, comprising the computer readable storage medium having computer readable program code embodied therewith, the computer readable program code further configured to:

identify a payee name in the second image based on applying the second optical character recognition process; and

compare the payee name and the user, wherein the financial record comprises a check.

12. The computer program product of claim 9, comprising the computer readable storage medium having computer readable program code embodied therewith, the computer readable program code further configured to determine that the payee name and the user do not match.

13. The computer program product of claim 12, comprising the computer readable storage medium having computer readable program code embodied therewith, the computer readable program code further configured to determine that the user is authorized to deposit the check;

and process the check in response to the authorization determination.

14. A computer-implemented method for identifying errors based on data extracted from a first image, the method comprising:

receiving the first image from a user, the first image comprising a financial record;

applying, by a processor, a first optical character recognition process to at least a portion of the first image, wherein the first optical character recognition process comprises a first algorithm;

identifying, by a processor, a first set of record data based on the applied first optical character recognition process comprising at least a name of a party to the financial record;

identifying, by a processor, errors associated with the first image based on the first set of record data, the errors comprising at least one of errors associated with the first image, errors associated with a financial transaction, errors associated with processing of the financial record, and errors in the first set of record data;

assigning, by a processor, a confidence level to one or more portions of the financial record based on the identified first set of record data and the identified errors of the first image, wherein the confidence level is a pass rating or a fail rating;

determining, by a processor, that a first portion of the one or more portions of the financial record has a first confidence level of a fail rating;

prompting, by a processor, the user to provide a second image of the same side of the first image of the financial record in response to the determination that the first portion of the financial record has a first confidence level of a fail rating, wherein the second image comprises the first portion of the financial record, and wherein the second image portrays the first portion of the financial record at a different angle, portrays the first portion of the financial record in a different light, is captured with different image capturing equipment than the first image, or is a modified version of the first image;

receiving, by a processor, the second image from the user via a user computing device associated with the user, wherein the user computing device comprises at least an image capture device that captures the second image and a communication device that communicates the second image from the user;

applying, by a processor, a second optical character recognition process to at least a portion of the second image, wherein the portion of the second image comprises the first portion of the financial record, and wherein the second optical character recognition process comprises a second algorithm that is different from the first algorithm; and

identifying, by a processor, a second set of record data based on the second optical character recognition process comprising at least one new record data that is not included in the first set of record data.

15. The computer-implemented method of claim 14, further comprising:

sending, by a processor, the second image to an investigation group;

receiving instructions from the investigation group; and

processing, by a processor, the financial record based on the instructions.

16. The computer-implemented method of claim 14, further comprising:

identifying, by a processor, a payee name in the second image based on applying the second optical character recognition process;

comparing the payee name and the user;

determining that the payee name and the user match; and

processing the financial record in response to the match.