Categorization of information using natural language processing and predefined templates

• US 20050228815A1
• Filed: 05/07/2004
• Published: 10/13/2005
• Est. Priority Date: 03/31/2004
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Dictaphone Corporation (Microsoft Corporation)
• Inventors: Carus, Alwin B., Ogrinc, Harry J.
• Granted Patent: US 7,379,946 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G16H 10/20 for electronic clinical trials or questionnaires
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: Y10S 707/99942 Manipulating data structure, e.g. compression, compaction, compilation
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface
• CPC Class Codes: Y10S 707/99944 Object-oriented database structure
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

Methods and systems for classifying and normalizing information using a combination of traditional data input methods, natural language processing, and predetermined templates are disclosed. One method may include activating a template. Based on this template, template-specific data may also be retrieved. After receiving both an input stream of data and the template-specific data, this information may be processed to generate a report based on the input data and the template specific data. In an alternative embodiment of the invention, templates may include, for example, medical billing codes from a number of different billing code classifications for the generation of patient bills. Alternatively, a method may include receiving an input stream of data and processing the input stream of data. A determination may be made as to whether or not the input stream of data includes latent information. If the data includes latent information, a template associated with latent information may be activated.

Claims

1. A method, comprising:

receiving an input data stream;

processing the input data stream to identify latent information within the data stream;

activating a template based on the latent information in the input data stream

receiving template-specific data based on the retrieved template; and

processing the input data and the template-specific data, whereby the data may be configured to generate a report based on the input data and the template-specific data.

2. The method of claim 1, wherein receiving the input data stream includes receiving an input data stream associated with medical data.

3. The method of claim 1, wherein determining that the input data stream contains a predetermined class of information includes determining that the input data stream contains at least one of a medical problem, a medication, and a medical procedure.

4. The method of claim 1, further comprising:

generating a report based on the processed input data and template-specific data.

5. The method of claim 1, wherein the processing of the input data includes:

identification and classification of a relevant portion of the input data stream, the relevant portion of the input data stream being associated with one of a predetermined class of information; and

performing one of normalization, validation, and extraction on the input data stream.

6. The method of claim 1, further comprising:

identifying a relevant portion of the input data stream;

bounding the relevant portion of the input data stream;

identifying the predetermined class of information; and

normalizing the relevant portion of the input data stream.

7. The method of claim 4, wherein the report is a medical billing report.

8. The method of claim 1, wherein the activating a template includes selecting a template from a predetermined group of templates and activating the selected template.

9. A method of receiving and classifying information in a constrained data input scheme, the method comprising:

inputting generic data, the generic data including latent information;

activating a template based on the latent information;

inputting template-specific data associated with the activated template; and

generating a report based on the generic data and the template-specific data.

10. The method of claim 9, wherein inputting the generic data includes inputting generic data associated with medical data.

11. The method of claim 9, wherein inputting the generic data includes inputting generic data containing at least one of a medical problem, a medication, an allergy, and a medical procedure.

12. The method of claim 9, wherein generating a report includes generating one of a billing report and an accreditation report based on the processed generic and template-specific data.

13. The method of claim 9, wherein the processing of the generic data includes:

identification and classification of a relevant portion of the input data stream, the relevant portion of the input data stream being associated with the latent information; and

performing one of a normalization, a validation, and an extraction on the input data stream.

14. The method of claim 9, further comprising:

identifying a relevant portion of the generic data, the relevant portion of the generic data including the latent information;

bounding the relevant portion of the generic data;

identifying the latent information associated with the input generic data; and

normalizing the relevant portion of the generic data.

15. The method of claim 9, wherein the activating a template includes selecting a template from a predetermined group of templates and activating the selected template.

16. The method of claim 9, wherein the latent information is associated with a predetermined classification of information of a plurality of predetermined classifications of information, the activated template being associated with the predetermined classification of information of the plurality of predetermined classifications of information.

17. Processor-readable code stored on a processor-readable medium, the code comprising code to:

receive generic data, the data including latent information;

activate a template associated with the latent information;

receive template-specific data associated with the activated template; and

process the generic data and the template-specific data to generate a report based on the generic data and the template-specific data.

18. The processor-readable code of claim 17, wherein the code to process the generic data and the template-specific data includes code to perform one of a normalization, a validation, and an extraction on the received generic data and the template-specific data.

19. The processor-readable code of claim 17, wherein the code includes code to receive generic data including medical data.

20. The processor-readable code of claim 17, wherein the code includes code to receive generic data associated with at least one of a medical problem, a medication, an allergy, and a medical procedure.

21. The processor-readable code of claim 17, wherein the code further includes code to generate one of an accreditation report and a billing report based on the processed generic and template-specific data.

22. The processor-readable code of claim 17, wherein the code to process the generic data includes code to:

identify and classify a relevant portion of the generic data, the relevant portion of the generic data being associated with the latent information; and

normalize the generic data.

23. The processor-readable code of claim 17, further comprising code to:

identify a relevant portion of the generic data the relevant portion of the generic data include the latent information;

bound the relevant portion of the generic data;

identify the latent information; and

normalize the relevant portion of the generic data.

24. The processor-readable code of claim 17, wherein the template includes at least one billing code associated with the latent information.