Method and system for classifying a question
View Patent ↗A method, implemented on at least one computing device, each of which has at least one processor, storage, and a communication platform connected to a network for classifying a question is disclosed. A question is received from a person. A question pattern is determined. A model selected based on the question is retrieved. Further, a decision is made as to whether the question is a personal question based on the question pattern and the selected model.
1. A method, implemented on at least one computing device, each of which has at least one processor, storage, and a communication platform connected to a network for classifying a question, the method comprising:
receiving a question from a person;
extracting at least one feature from the received question;
determining a question pattern based on the at least one feature extracted from the question;
retrieving a model selected based on the question;
checking for a match between the at least one feature and information related to the person; and
determining that the question is a personal question based on the match, the question pattern, and the selected model.
2. The method according to claim 1 , wherein the at least one feature extracted from the question is an interrogative word.
3. The method according to claim 1 , wherein the selected model comprises one or more personal question patterns generated based on information associated with a plurality of previously asked questions.
4. The method according to claim 3 , wherein the selected model is trained based on user interactions associated with a plurality of answers to the plurality of previously asked questions.
5. The method according to claim 1 , wherein the at least one feature extracted from the question corresponds to an entity.
6. The method according to claim 3 , wherein the selected model is trained using a machine learning system.
7. The method according to claim 1 , further comprising:
searching for one or more answers from a person-centric knowledge database if it is determined that the question is a personal question.
8. A system having at least one processor, storage, and a communication platform connected to a network for classifying a question, the system comprising:
a user interface implemented on the at least one processor and configured to receive a question from a user;
a feature extractor implemented on the at least one processor and configured to extract at least one feature from the received question;
a question pattern extractor implemented on the at least one processor and configured to determine a question pattern based on the at least one feature extracted from the question;
a classification knowledge retriever implemented on the at least one processor and configured to retrieve a model selected based on the question;
a feature comparator implemented on the at least one processor and configured to check for a match between the at least one feature and information related to the user; and
a classification decision module implemented on the at least one processor and configured to determine that the question is a personal question based on the match, the question pattern, and the selected model.
9. The system according to claim 8 , wherein the at least one feature extracted from the question is an interrogative word.
10. The system according to claim 8 , wherein the selected model comprises one or more personal question patterns generated based on information associated with a plurality of previously asked questions.
11. The system according to claim 10 , wherein the one or more personal question patterns are trained based on user interactions associated with a plurality of answers to the plurality of previously asked questions.
12. A non-transitory machine-readable medium having information recorded thereon for classifying a question, wherein the information, when read by the machine, causes the machine to perform the following:
receiving a question from a person;
extracting at least one feature from the received question;
determining a question pattern based on the at least one feature extracted from the question;
retrieving a model selected based on the question;
checking for a match between the at least one feature and information related to the person; and
determining that the question is a personal question based on the match, the question pattern, and the selected model.
13. The non-transitory machine-readable medium of claim 12 , wherein the at least one feature extracted from the question is an interrogative word.
14. The non-transitory machine-readable medium of claim 12 , wherein the selected model comprises one or more personal question patterns generated based on information associated with a plurality of previously asked questions.
15. The non-transitory machine-readable medium of claim 14 , wherein the one or more personal question patterns are trained based on user interactions associated with a plurality of answers to the plurality of previously asked questions.
16. The system according to claim 8 , wherein the at least one feature extracted from the question corresponds to an entity.
17. The system according to claim 10 , wherein the selected model is trained using a machine learning system.
18. The system according to claim 8 , further comprising:
a person-centric answer search engine implemented on the at least one processor that searches for one or more answers from a person-centric knowledge database if it is determined that the question is a personal question.
19. The non-transitory machine-readable medium of claim 12 , wherein the at least one feature extracted from the question corresponds to an entity.
20. The non-transitory machine-readable medium of claim 12 , wherein the information, when read by the machine, causes the machine to further perform the following:
searching for one or more answers from a person-centric knowledge database if it is determined that the question is a personal question.