Handwriting recognition tool

• US 9,633,173 B2
• Filed: 03/10/2014
• Issued: 04/25/2017
• Est. Priority Date: 03/10/2014
• Status: Active Grant

• Current Assignee: IQVIA, Inc. (IQVIA Holdings, Inc.)
• Original Assignee: Quintiles IMS Incorporated (IQVIA Holdings, Inc.)
• Inventors: Pauletto, Stephan, Ebding, Tilman
• Primary Examiner(s): Tran, Quoc A
• Application Number:
  US14/202,331
• Publication Number:
  US 20150254425A1
• Time in Patent Office: 1,142 Days
• Field of Search: 715209, 715249, 715268, 382119
• CPC Class Codes: G06F 40/103 Formatting, i.e. changing of presentation of documents automatic justification G06F40/189; automatic line break hyphenation G06F40/191
• CPC Class Codes: G06F 40/166 Editing, e.g. inserting or deleting
• CPC Class Codes: G06F 40/171 by use of digital ink
• CPC Class Codes: G06F 40/18 of spreadsheets form-filling G06F40/174
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06V 30/226 of cursive writing
• CPC Class Codes: G06V 30/40 Document-oriented image-based pattern recognition
• CPC Class Codes: G06V 40/33 based only on signature image, e.g. static signature recognition
• CPC Class Codes: G16H 20/10 relating to drugs or medications, e.g. for ensuring correct administration to patients

Abstract

Some implementations may provide a method implemented on a processor, the method includes: receiving, on a computer host, an electronic document representing a pharmaceutical prescription; identifying constituent regions that include at least a first portion and a second portion within the electronic document; identifying first spatial frequencies for the first portion within the electronic document; identifying second spatial frequencies for the second portion within the electronic document; identifying a header based upon the first spatial frequencies; using the header to identify a prescriber; retrieving a profile for the prescriber; analyzing the second spatial frequencies using the profile for the prescriber; and creating, based upon analyzing the second spatial frequencies using the profile for the prescriber, a transaction record on the computer host for a medical transaction associated with the pharmaceutical prescription.

Claims

1. A method implemented on a processor, the method comprising:

receiving, on a computer host, an electronic document representing a pharmaceutical prescription;

identifying constituent regions that include at least a first portion and a second portion within the electronic document;

identifying first spatial frequencies for the first portion within the electronic document;

identifying second spatial frequencies for the second portion within the electronic document;

identifying a header based upon the first spatial frequencies, wherein identifying the first and second spatial frequencies includes performing a fast Fourier Transform on a portion of a document and translating spatial information into frequency information such that (i) the header identifying the prescriber is identified from the first spatial frequencies; and

(ii) the second spatial frequencies are analyzed using the profile of the identified prescriber;

using the header to identify a prescriber;

retrieving a profile specific for the prescriber;

analyzing the second spatial frequencies using the profile specific for the prescriber such that the second spatial frequencies are compared to spatial frequency domain information from the profile specific for the prescriber, the prescriber-specific profile constructed from the prescriber'"'"'s past records and including isolated handwriting of the prescriber in a spatial frequency domain; and

creating, based upon results from analyzing the second spatial frequencies using the profile for the prescriber, a transaction record on the computer host for a medical transaction associated with the pharmaceutical prescription.

2. The method of claim 1, wherein identifying constituent regions includes inspecting an electronic document for a reference object and using the reference object to identify the first and second portions.

3. The method of claim 1, wherein identifying the constituent regions includes identifying constituent regions that are delineated independent of content appearing in the electronic document.

4. The method of claim 1, wherein identifying the constituent regions includes performing a preliminary degree of processing to identify a document format and using the document format to specify the first and second regions.

5. The method of claim 1, wherein identifying the header based upon the first spatial frequencies includes comparing the first spatial frequencies with a library of spatial frequencies of known headers.

6. The method of claim 1, wherein retrieving the profile for the prescriber includes retrieving a dictionary of terms associated with a practice of the prescriber.

7. The method of claim 1, wherein retrieving the profile for the prescriber includes retrieving a dictionary of terms for the prescriber represented in the spatial frequency domain.

8. The method of claim 1, wherein retrieving the profile for the prescriber includes retrieving a computer data structure that describes different spatial frequency representations for a term appearing in a dictionary.

9. The method of claim 1, wherein retrieving the profile for the prescriber includes retrieving a computer data structure that describes different spatial frequency representations for a term appearing in a dictionary.

10. The method of claim 1, wherein retrieving the profile for the prescriber includes retrieving a computer data structure that describes a likelihood of correlation between the second spatial frequencies and different terms appearing in a dictionary.

11. The method of claim 1, wherein creating, based upon results from analyzing the second spatial frequencies using the profile for the prescriber, the transaction record on the computer host includes creating an electronic document prescription based upon the received electronic document representing the pharmaceutical prescription.

12. A computer system, comprising at least one processor, wherein the at least one processor is configured to perform the operations of:

receiving, on a computer host, an electronic document representing a pharmaceutical prescription;

identifying constituent regions that include at least a first portion and a second portion within the electronic document;

identifying first spatial frequencies for the first portion within the electronic document;

identifying second spatial frequencies for the second portion within the electronic document;

identifying a header based upon the first spatial frequencies, wherein identifying the first and second spatial frequencies includes performing a fast Fourier Transform on a portion of a document and translating spatial information into frequency information such that (i) the header identifying the prescriber is identified from the first spatial frequencies; and

(ii) the second spatial frequencies are analyzed using the profile of the identified prescriber;

using the header to identify a prescriber;

retrieving a profile specific for the prescriber;

analyzing the second spatial frequencies using the profile specific for the prescriber such that the second spatial frequencies are compared to spatial frequency domain information from the profile specific for the prescriber, the prescriber-specific profile constructed from the prescriber'"'"'s past records and including isolated handwriting of the prescriber in a spatial frequency domain; and

creating, based upon results from analyzing the second spatial frequencies using the profile for the prescriber, a transaction record on the computer host for a medical transaction associated with the pharmaceutical prescription.

13. The computer system of claim 12, wherein the operation of identifying constituent regions includes inspecting an electronic document for a reference object and using the reference object to identify the first and second portions.

14. The computer system of claim 12, wherein the operation of identifying the constituent regions includes identifying constituent regions that are delineated independent of content appearing in the electronic document.

15. The computer system of claim 12, wherein the operation of identifying the constituent regions includes performing a preliminary degree of processing to identify a document format and using the document format to specify the first and second regions.

16. The computer system of claim 12, wherein the operation of identifying the header based upon the first spatial frequencies includes comparing the first spatial frequencies with a library of spatial frequencies of known headers.

17. The computer system of claim 12, wherein the operation of retrieving the profile for the prescriber includes retrieving a dictionary of terms associated with a practice of the prescriber.

18. The computer system of claim 12, wherein the operation of retrieving the profile for the prescriber includes retrieving a dictionary of terms for the prescriber represented in the spatial frequency domain.

19. The computer system of claim 12, wherein the operation of retrieving the profile for the prescriber includes retrieving a computer data structure that describes different spatial frequency representations for a term appearing in a dictionary.

20. The computer system of claim 12, wherein the operation of retrieving the profile for the prescriber includes retrieving a computer data structure that describes different spatial frequency representations for a term appearing in a dictionary.

21. The computer system of claim 12, wherein the operation of retrieving the profile for the prescriber includes retrieving a computer data structure that describes a likelihood of correlation between the second spatial frequencies and different terms appearing in a dictionary.

22. The computer system of claim 12, wherein the at least one processor is further configured to perform the operations of creating, based upon results from analyzing the second spatial frequencies using the profile for the prescriber, the transaction record on the computer host includes creating an electronic document prescription based upon the received electronic document representing the pharmaceutical prescription.

23. A computer-readable medium comprising software instructions that, when executed by a computer, causes the computer to perform the operations of:

receiving, on a computer host, an electronic document representing a pharmaceutical prescription;

identifying constituent regions that include at least a first portion and a second portion within the electronic document;

identifying first spatial frequencies for the first portion within the electronic document;

identifying second spatial frequencies for the second portion within the electronic document;

identifying a header based upon the first spatial frequencies, wherein identifying the first and second spatial frequencies includes performing a fast Fourier Transform on a portion of a document and translating spatial information into frequency information such that (i) the header identifying the prescriber is identified from the first spatial frequencies; and

(ii) the second spatial frequencies are analyzed using the profile of the identified prescriber;

using the header to identify a prescriber;

retrieving a profile specific for the prescriber;

analyzing the second spatial frequencies using the profile specific for the prescriber such that the second spatial frequencies are compared to spatial frequency domain information from the profile specific for the prescriber, the prescriber-specific profile constructed from the prescriber'"'"'s past records and including isolated handwriting of the prescriber in a spatial frequency domain; and

creating, based upon results from analyzing the second spatial frequencies using the profile for the prescriber, a transaction record on the computer host for a medical transaction associated with the pharmaceutical prescription.