Cognitive care plan recommendation system

Patent metadata

Field	Value
Publication number	US-11094405-B2
Application number	US-201916262334-A
Country	US
Kind code	B2
Filing date	Jan 30, 2019
Priority date	Jan 30, 2019
Publication date	Aug 17, 2021
Grant date	Aug 17, 2021

Abstract

Finding care plan(s) matching desired aspects includes receiving a selection of a model care plan from a user; generating a feature hash vector representing the model care plan, resulting in a model feature hash vector; comparing feature hash vectors of existing care plans to the model feature hash vector to find care plan(s) best matching the desired aspect(s) of a user, resulting in best match(es); and providing one or more care plan recommendation(s) to the user based on the best match(es).

First claim

What is claimed is:

1. A computer-implemented method of finding one or more care plan matching desired aspects, the computer-implemented method comprising:
receiving a selection of a model care plan from a user;
generating a feature hash vector representing the model care plan, resulting in a model feature hash vector;
comparing feature hash vectors of a plurality of existing care plans to the model feature hash vector to find one or more care plan best matching one or more desired aspect of the user, resulting in one or more best match; and
providing one or more care plan recommendation to the user based on the one or more best match.

2. The computer-implemented method of claim 1 , further comprising modifying, by the user, at least one of the one or more best match.

3. The computer-implemented method of claim 1 , further comprising exporting the care plan as a flat text file, wherein generating the feature hash vector comprises generating the feature hash vector based on the flat text file.

4. The computer-implemented method of claim 3 , further comprising applying Natural Language Understanding (NLU) to the flat text file, resulting in NLU output, wherein generating the feature hash vector comprises generating the feature hash vector from the NLU output.

5. The computer-implemented method of claim 1 , wherein the comparing comprises using a cosine similarity function.

6. The computer-implemented method of claim 1 , further comprising filtering the one or more best match.

7. The computer-implemented method of claim 6 , wherein the comparing comprises using a cosine similarity function, and wherein the filtering comprises filtering one or more result of the comparing.

8. The computer-implemented method of claim 1 , further comprising assigning a recommendation score to each of the one or more best match.

9. The computer-implemented method of claim 1 , wherein the selection comprises a model care plan with the one or more desired aspect.

10. The computer-implemented method of claim 9 , wherein at least one of the one or more desired aspect has an assigned weight.

11. A system for finding one or more care plan matching desired aspects, the system comprising:
a memory; and
at least one processor in communication with the memory, the memory storing program code executable by the at least one processor to perform a method, the method comprising:
receiving a selection of a model care plan from a user;
generating a feature hash vector representing the model care plan, resulting in a model feature hash vector;
comparing feature hash vectors of a plurality of existing care plans to the model feature hash vector to find one or more care plan best matching one or more desired aspect of the user, resulting in one or more best match; and
providing one or more care plan recommendation to the user based on the one or more best match.

12. The system of claim 11 , wherein the method further comprises exporting the care plan as a flat text file, wherein generating the feature hash vector comprises generating the feature hash vector based on the flat text file.

13. The system of claim 12 , wherein the method further comprises applying Natural Language Understanding (NLU) to the flat text file, resulting in NLU output, wherein generating the feature hash vector comprises generating the feature hash vector from the NLU output.

14. The system of claim 11 , wherein the comparing comprises using a cosine similarity function.

15. The system of claim 11 , wherein the method further comprises assigning a recommendation score to each of the one or more best match.

16. A computer program product for finding one or more care plan matching desired aspects, the computer program product comprising:
a computer readable storage medium readable by a processor and storing instructions executable by the processor for performing a method of scheduling a meeting, the method comprising:
receiving a selection of a model care plan from a user;
generating a feature hash vector representing the model care plan, resulting in a model feature hash vector;
comparing feature hash vectors of a plurality of existing care plans to the model feature hash vector to find one or more care plan best matching one or more desired aspect of the user, resulting in one or more best match; and
providing one or more care plan recommendation to the user based on the one or more best match.

17. The computer program product of claim 16 , wherein the method further comprises exporting the care plan as a flat text file, wherein generating the feature hash vector comprises generating the feature hash vector based on the flat text file.

18. The computer program product of claim 17 , wherein the method further comprises applying Natural Language Understanding (NLU) to the flat text file, resulting in NLU output, wherein generating the feature hash vector comprises generating the feature hash vector from the NLU output.

19. The computer program product of claim 16 , wherein the comparing comprises using a cosine similarity function.

20. The computer program product of claim 16 , wherein the method further comprises assigning a recommendation score to each of the one or more best match.

Assignees

• IBM

Inventors

• Brady Simon
• Leonard John
• Dalton Shane
• Zolotow Clea Anne
• Delaney John Valentine
• Fagan Patrick Arthur

Classifications

• G06F16/90332 Primary

  Natural language query formulation or dialogue systems · CPC title

• G06F16/90344

  by using string matching techniques · CPC title

• G16H10/60 Primary

  for patient-specific data, e.g. for electronic patient records · CPC title

• G16H40/20

  for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms · CPC title

• G16H50/20

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title