Enhanced answers in DeepQA system according to user preferences
A semantic search engine is enhanced to employ user preferences to customize answer output by, for a first user, extracting user preferences and sentiment levels associated with a first question; receiving candidate answer results of a semantic search of the first question; weighting the candidate answer results according to the sentiment levels for each of the user preferences; and producing the selected candidate answers to the first user. Optionally, user preferences and sentiment levels may be accumulated over different questions for the same user, or over different users for similar questions. And, supplemental information may be retrieved relative to a user preference in order to further tune the weighting per the preferences and sentiment levels.
1. A method for using user preferences to customize answer output comprising the steps of:
for a first user and a first question:
extracting by a natural language processor from the question one or more user preferences and one or more sentiment levels;
performing by a computer a semantic search on of the first question;
receiving by a computer a plurality of candidate answers from the semantic search;
selecting by a computer one or more of the received candidate answers, wherein the selection is performed both according to the one or more sentiment levels and according to the one or more user preferences; and
producing by a computer a first user output including the selected one or more candidate answers;
for a second question and a second user, repeating by a computer the step of extracting preferences from the second question;
accumulating by a computer the preferences and sentiments extracted from the second question with the preferences and sentiments extracted from the first question; and
for the second question, repeating by a computer the steps of performing a semantic search, receiving candidate answers, selecting candidate answers according to the accumulated preferences and sentiments, and producing a second output.
2. The method as set forth in claim 1 further comprising the steps of:
for the first user and a third question, extracting by a natural language processor one or more user preferences and one or more sentiment levels, wherein each user preference and each sentiment level is associated with the third question, or associated with the first user, or associated with both the third question and the first user;
searching semantically by a computer on the third question;
receiving by a computer a plurality of candidate answers from the semantic search on the third question;
selecting by a computer one or more of the received candidate answers from the search on the third question, wherein the selection is performed according to a combination of the one or more sentiment levels and according to the one or more user preferences associated with the first and second users and with the first, second and third questions; and
producing by a computer a third user output including the selected one or more candidate answers selected from the search on the third question.
3. The method as set forth in claim 2 further comprising detecting by a computer that the first question is similar to at least the third question.
4. The method as set forth in claim 1 further comprising retrieving by a computer supplemental information regarding the candidate answers, wherein the supplemental information is related to one or more of the user preferences, and wherein the supplemental information is used to adjust the selecting.
5. The method as set forth in claim 1 further comprising extracting by a computer semantic elements according to an architecture for managing unstructured information.
6. The method as set forth in claim 1 wherein the selecting comprises a weighting process.
7. A computer program product for using user preferences to customize answer output comprising:
a computer readable, tangible storage device; and
program instructions stored by the computer readable, tangible storage device, which, when executed by a processor, cause a computing platform to:
for a first user and a first question:
extract by a natural language processor from the question one or more user preferences and one or more sentiment levels;
perform a semantic search on of the first question;
receive a plurality of candidate answers from the semantic search;
select one or more of the received candidate answers, wherein the selection is performed both according to the one or more sentiment levels and according to the one or more user preferences; and
produce a first user output including the selected one or more candidate answers;
for a second question and a second user, repeat the step of extracting preferences from the second question;
accumulate the preferences and sentiments extracted from the second question with the preferences and sentiments extracted from the first question; and
for the second question, repeat the steps of performing a semantic search, receiving candidate answers, selecting candidate answers according to the accumulated preferences and sentiments, and producing a second output.
8. The computer program product as set forth in claim 7 further comprising program instructions stored by the computer readable, tangible storage device, which, when executed by a processor, cause a computing platform to:
for the first user and a third question, extract by a natural language processor one or more user preferences and one or more sentiment levels, wherein each user preference and each sentiment level is associated with the third question, or associated with the first user, or associated with both the third question and the first user;
search semantically on the third question;
receive a plurality of candidate answers from the semantic search on the third question;
selecting by a computer one or more of the received candidate answers from the search on the third question, wherein the selection is performed according to a combination of the one or more sentiment levels and according to the one or more user preferences associated with the first and second users and with the first, second and third questions; and
produce a third user output including the selected one or more candidate answers selected from the search on the third question.
9. The computer program product as set forth in claim 8 further comprising program instructions stored by the computer readable, tangible storage device, which, when executed by a processor, cause a computing platform to detect that the first question is similar to at least the third question.
10. The computer program product as set forth in claim 7 further comprising program instructions stored by the computer readable, tangible storage device, which, when executed by a processor, cause a computing platform to retrieve supplemental information regarding the candidate answers, wherein the supplemental information is related to one or more of the user preferences, and wherein the supplemental information is used to adjust the selecting.
11. The computer program product as set forth in claim 7 further comprising program instructions stored by the computer readable, tangible storage device, which, when executed by a processor, cause a computing platform to extract semantic elements according to an architecture for managing unstructured information.
12. The computer program product as set forth in claim 7 wherein the program instructions which, when executed by a processor, cause a computing platform to select comprise program instructions which, when executed by a processor, cause a computing platform a weighting process.
13. A system for using user preferences to customize answer output comprising:
a computing platform having a processor;
a computer readable, tangible storage device; and
program instructions stored by the computer readable, tangible storage device, which, when executed by the processor, cause a computing platform to:
for a first user and a first question:
extract by a natural language processor from the question one or more user preferences and one or more sentiment levels;
perform a semantic search on of the first question;
receive a plurality of candidate answers from the semantic search;
select one or more of the received candidate answers, wherein the selection is performed both according to the one or more sentiment levels and according to the one or more user preferences; and
produce a first user output including the selected one or more candidate answers;
for a second question and a second user, repeat the step of extracting preferences from the second question;
accumulate the preferences and sentiments extracted from the second question with the preferences and sentiments extracted from the first question; and
for the second question, repeat the steps of performing a semantic search, receiving candidate answers, selecting candidate answers according to the accumulated preferences and sentiments, and producing a second output.
14. The system as set forth in claim 13 further comprising program instructions stored by the computer readable, tangible storage device, which, when executed by a processor, cause a computing platform to:
for the first user and a third question, extract by a natural language processor one or more user preferences and one or more sentiment levels, wherein each user preference and each sentiment level is associated with the third question, or associated with the first user, or associated with both the third question and the first user;
search semantically on the third question;
receive a plurality of candidate answers from the semantic search on the third question;
selecting by a computer one or more of the received candidate answers from the search on the third question, wherein the selection is performed according to a combination of the one or more sentiment levels and according to the one or more user preferences associated with the first and second users and with the first, second and third questions; and
produce a third user output including the selected one or more candidate answers selected from the search on the third question.
15. The system as set forth in claim 14 further comprising program instructions stored by the computer readable, tangible storage device, which, when executed by a processor, cause a computing platform to detect that the first question is similar to at least the third question.
16. The system as set forth in claim 13 further comprising program instructions stored by the computer readable, tangible storage device, which, when executed by a processor, cause a computing platform to retrieve supplemental information regarding the candidate answers, wherein the supplemental information is related to one or more of the user preferences, and wherein the supplemental information is used to adjust the selecting.
17. The system as set forth in claim 13 further comprising program instructions stored by the computer readable, tangible storage device, which, when executed by a processor, cause a computing platform to extract semantic elements according to an architecture for managing unstructured information.
18. The system as set forth in claim 13 wherein the program instructions which, when executed by a processor, cause a computing platform to select comprise program instructions which, when executed by a processor, cause a computing platform a weighting process.