Using cohorts in a question answering system

• US 9,836,693 B2
• Filed: 09/17/2014
• Issued: 12/05/2017
• Est. Priority Date: 09/17/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Clark, Adam T., Huebert, Jeffrey K., Payton, Aspen L., Petri, John E., Stevens, Richard J., Whaley, Kathryn L.
• Primary Examiner(s): Wong, Lut
• Application Number:
  US14/489,124
• Publication Number:
  US 20160078355A1
• Time in Patent Office: 1,175 Days
• Field of Search: 706 11
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06N 5/041 Abduction
• CPC Class Codes: G06N 5/043 Distributed expert systems; Blackboards
• CPC Class Codes: G06N 5/046 Forward inferencing; Production systems

Abstract

A cohort analysis mechanism analyzes cohorts with similar attributes to extrapolate additional knowledge and answer a question in a question answering system. The cohort analysis mechanism identifies cohorts for an entity of the question and extracts relevant data concerning the cohorts. The cohort analysis mechanism aggregates the relevant information for evidence scoring and answer scoring to answer a question posed to the question answering system. The aggregating of the data includes combining and ranking answers from the cohorts, gathering evidence and then answering the question with the gathered evidence.

Claims

1. An apparatus comprising:

at least one processor;

a memory coupled to the at least one processor;

a cohort analysis mechanism residing in the memory and executed by the at least one processor that answers a question by identifying cohorts for a person in the question,

wherein the cohorts are persons meeting a threshold of similar attributes to the person of the question and available in a corpus of data; and

wherein the cohort analysis mechanism aggregates data of the cohorts, extracts answers and evidence from data of the cohorts and combines and ranks the answers and evidence from data of the cohorts to answer the question.

2. The apparatus of claim 1 wherein the attributes include age, race and symptoms.

3. The apparatus of claim 2 wherein the cohort analysis mechanism uses the ranked answers to gather statistically significant evidence of the cohorts to answer the question.

4. The apparatus of claim 3 wherein the cohort analysis mechanism uses the ranked answers to gather statistically significant evidence of the cohorts to answer the question and wherein the cohort analysis mechanism determines an answer to the question using evidence gathered from a set of cohorts where case attributes in the set of cohorts does not exactly match attributes of the question.

5. The apparatus of claim 4 wherein the person in the question is a patient, the question is a medical question for the patient and the cohort analysis mechanism processes the medical history of the patient and finds the cohorts from medical histories of other patients to predict an answer from the cohorts.

6. The apparatus of claim 3 wherein the cohort analysis mechanism combines the answer from the cohorts with answers using conventional question answering in an answer scoring block of a conventional question answering system to answer the question.

7. The apparatus of claim 1 wherein the cohort analysis mechanism is part of a question answering application that answers a natural language question.

8. The apparatus of claim 1 wherein the person in the question is a patient, the question is a medical question for the patient and the cohort analysis mechanism processes the medical history of the patient and finds the cohorts from medical histories of other patients to predict an answer from the cohorts.

9. The method of claim 1 wherein the threshold is a reference percentage allowing the cohorts to be divided into relative strengths for different percentage thresholds and wherein the relative strengths of the cohorts are used to score the answers and evidence.

10. An apparatus comprising:

at least one processor;

a memory coupled to the at least one processor;

a cohort analysis mechanism residing in the memory and executed by the at least one processor that answers a question by identifying cohorts for a person in the question, wherein the cohorts are persons meeting a threshold of similar attributes to the person of the question and available in a corpus of data wherein the attributes include age, race and symptoms;

wherein the cohort analysis mechanism aggregates data of the cohorts, extracts answers and evidence from data of the cohorts, combines and ranks the answers and evidence from data of the cohorts and uses the ranked answers and evidence to gather statistically significant evidence of the cohorts to answer the question,

wherein the person in the question is a patient, the question is a medical question for the patient and the cohort analysis mechanism processes the medical history of the patient and finds the cohorts from medical histories of other patients to predict the answer from the cohorts; and

wherein the cohort analysis mechanism is part of a question answering application that answers a natural language question.

11. The apparatus of claim 10 wherein the attributes include age, race and symptoms.

12. The apparatus of claim 10 wherein the threshold is a reference percentage allowing the cohorts to be divided into relative strengths for different percentage thresholds and wherein the relative strengths of the cohorts are used to score the answers and evidence.

13. A computer-readable article of manufacture comprising:

a cohort analysis mechanism that answers a question by identifying cohorts for a person in the question, wherein the cohorts are persons meeting a threshold of similar attributes to the person of the question and available in a corpus of data wherein the attributes include age, race and symptoms;

wherein the cohort analysis mechanism aggregates data of the cohorts, extracts answers and evidence from data of the cohorts, combines and ranks the answers and evidence from data of the cohorts and uses the ranked answers and evidence to gather statistically significant evidence of the cohorts to answer the question,

wherein the person in the question is a patient, the question is a medical question for the patient and the cohort analysis mechanism processes the medical history of the patient and finds the cohorts from medical histories of other patients to predict the answer from the cohorts; and

a non-transitory computer recordable medium bearing the cohort analysis mechanism.

14. The article of manufacture of claim 13 wherein the attributes include age, race and symptoms.

15. The article of manufacture of claim 13 wherein the threshold is a reference percentage allowing the cohorts to be divided into relative strengths for different percentage thresholds and wherein the relative strengths of the cohorts are used to score the answers and evidence.