Method to assign world class information

• US 10,515,719 B2
• Filed: 05/29/2018
• Issued: 12/24/2019
• Est. Priority Date: 11/28/2002
• Status: Expired due to Term

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Helletzgruber, Matthias, Rajic, Kresimir
• Primary Examiner(s): Yen, Eric
• Application Number:
  US15/991,861
• Publication Number:
  US 20190139634A1
• Time in Patent Office: 574 Days
• CPC Class Codes: G06F 40/237 Lexical tools
• CPC Class Codes: G06F 40/268 Morphological analysis
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 20/10 relating to drugs or medications, e.g. for ensuring correct administration to patients

Abstract

An assignment device (1) assigns word class information (WKI) to one or more words of text information (ETI). Based on word-class sequence information (WK-AI) formed from this assigned word class information (WKI), actions (A) are executed in order to notify the user of conflicts or to provide the user with background information (HI) relating to words in the text information (TT).

Claims

1. A device, comprising:

at least one computer programmed to perform;

analyzing words in a medical report to assign word-class information to the words in the medical report, the words of the medical report setting out a clinician'"'"'s observations of a patient encounter between the clinician and a patient, wherein analyzing the words in the medical report comprises;

in response to determining that a first word or word sequence in the medical report names a particular medicament, assigning first word-class information to the first word or word sequence in the medical report, the first word-class information identifying the first word or word sequence as relating to a medicament; and

assigning second word-class information to a second word or word sequence in the medical report;

in response to determining that both the first word-class information and the second word-class information were assigned to words in the medical report, performing at least one action related to the particular medicament, wherein performing the at least one action comprises generating a prescription for the patient for the particular medicament.

2. The device of claim 1, wherein analyzing the words in the medical report to assign the word-class information comprises:

searching the words of the medical report for words in a word dictionary memory having word-class information associated with word information; and

assigning word-class information to at least some of the words in the medical report based at least in part on matches between words of the medical report and words in the word dictionary memory.

3. The device of claim 2, wherein analyzing the words in the medical report to assign the word-class information comprises:

finding a particular word or word sequence of the medical report in the word dictionary memory;

reading word-class information for the particular word or word sequence from the word dictionary memory; and

assigning the word-class information read in the reading to the particular word or word sequence in the medical report found in the finding.

4. The device of claim 1, wherein:

the medical report comprises text information, the text information comprising the words of the medical report; and

the at least one computer is further programmed to perform recognizing the text information from input speech by implementing a voice recognition method.

5. The device of claim 4, wherein recognizing the text information from the input speech comprises, during the recognizing, performing the analyzing the words in the medical report.

6. The device of claim 1, wherein the at least one computer is further programmed to perform, in response to determining that the first word or word sequence names the particular medicament, searching for a different medicament that is comparable to the particular medicament.

7. The device of claim 1, wherein generating the prescription for the patient comprises triggering printing of a paper copy of the prescription to be provided to the patient.

8. A method, comprising:

using at least one computer to perform;

analyzing words in a medical report to assign word-class information to the words in the medical report, the words of the medical report setting out a clinician'"'"'s observations of a patient encounter between the clinician and a patient, wherein analyzing the words in the medical report comprises;

in response to determining that a first word or word sequence in the medical report names a particular medicament, assigning first word-class information to the first word or word sequence in the medical report, the first word-class information identifying the first word or word sequence as relating to a medicament; and

assigning second word-class information to a second word or word sequence in the medical report;

in response to determining that both the first word-class information and the second word-class information were assigned to words in the medical report, performing at least one action related to the particular medicament, wherein performing the at least one action comprises generating a prescription for the patient for the particular medicament.

9. The method of claim 8, wherein analyzing the words in the medical report to assign the word-class information comprises:

searching the words of the medical report for words in a word dictionary memory having word-class information associated with word information; and

assigning word-class information to at least some of the words in the medical report based at least in part on matches between words of the medical report and words in the word dictionary memory.

10. The method of claim 9, wherein analyzing the words in the medical report to assign the word-class information comprises:

finding a particular word or word sequence of the medical report in the word dictionary memory;

reading word-class information for the particular word or word sequence from the word dictionary memory; and

assigning the word-class information read in the reading to the particular word or word sequence in the medical report found in the finding.

11. The method of claim 8, wherein:

the medical report comprises text information, the text information comprising the words of the medical report; and

the method further comprises using the at least one computer to perform recognizing the text information from input speech by implementing a voice recognition method.

12. The method of claim 11, wherein recognizing the text information from the input speech comprises, during the recognizing, performing the analyzing the words in the medical report.

13. The method of claim 8, further comprising using the at least one computer to perform, in response to determining that the first word or word sequence names the particular medicament, searching for a different medicament that is comparable to the particular medicament.

14. The method of claim 8, wherein generating the prescription for the patient comprises triggering printing of a paper copy of the prescription to be provided to the patient.

15. At least one non-transitory computer readable medium storing sections of software code executable by at least one computer that, when executed by the at least one computer, cause the at least one computer to perform a method comprising:

analyzing words in a medical report to assign word-class information to the words in the medical report, the words of the medical report setting out a clinician'"'"'s observations of a patient encounter between the clinician and a patient, wherein analyzing the words in the medical report comprises;

in response to determining that a first word or word sequence in the medical report names a particular medicament, assigning first word-class information to the first word or word sequence in the medical report, the first word-class information identifying the first word or word sequence as relating to a medicament; and

assigning second word-class information to a second word or word sequence in the medical report;

in response to determining that both the first word-class information and the second word-class information were assigned to words in the medical report, performing at least one action related to the particular medicament, wherein performing the at least one action comprises triggering generation of a prescription for the patient for the particular medicament.

16. The at least one non-transitory computer-readable medium of claim 15, wherein analyzing the words in the medical report to assign the word-class information comprises:

searching the words of the medical report for words in a word dictionary memory having word-class information associated with word information; and

assigning word-class information to at least some of the words in the medical report based at least in part on matches between words of the medical report and words in the word dictionary memory.

17. The at least one non-transitory computer-readable medium of claim 16, wherein analyzing the words in the medical report to assign the word-class information comprises:

finding a particular word or word sequence of the medical report in the word dictionary memory;

reading word-class information for the particular word or word sequence from the word dictionary memory; and

assigning the word-class information read in the reading to the particular word or word sequence in the medical report found in the finding.

18. The at least one non-transitory computer-readable medium of claim 15, wherein:

the medical report comprises text information, the text information comprising the words of the medical report; and

the method further comprises recognizing the text information from input speech by implementing a voice recognition method.

19. The at least one non-transitory computer-readable medium of claim 15, wherein the method further comprises using the at least one computer to perform, in response to determining that the first word or word sequence names the particular medicament, searching for a different medicament that is comparable to the particular medicament.

20. The at least one non-transitory computer-readable medium of claim 15, wherein triggering generation of the prescription for the patient comprises triggering printing of a paper copy of the prescription to be provided to the patient.