Method and system for dynamically generating a card
The present teaching relates to dynamically generating a card. In one example, a request is received for generating a card to be provided to a user. Dynamic information related to the request is obtained. One or more modules are selected to be put into the card based on the dynamic information. The card is generated based on the selected one or more modules.
1. A method for question classification, the method comprising:
classifying, via a machine-learned model based on data from a person-centric space with respect to a user, a question from the user into a personal question or a non-personal question, wherein the person-centric space is constructed by cross-linking information relevant to the user from a public space, a semi-private space, and a private space, and wherein the data indicates whether the question comprises a sender of a private electronic communication sent to the user;
searching for an answer to the question in the person-centric space or in the public space depending on the classification of the question;
presenting the answer to the user; and
updating, based the answer, the person-centric space.
2. The method of claim 1 , wherein the question is classified as a personal question, the method further comprising:
extracting entities and relationships from the question, and traversing a person-centric knowledge database derived from the person-centric space, wherein the person-centric knowledge database comprises one or more entities and relationships between the one or more entities.
3. The method of claim 2 , wherein the extracted entities and relationships match the entities and relationships in the person-centric knowledge database, the method further comprising returning the answer based on the entities and relationships in the person-centric knowledge database.
4. The method of claim 2 , wherein the extracted entities and relationships do not match the entities and relationships in the person-centric knowledge database, the method further comprising returning the answer based on a similarity between the extracted entities and relationships and the entities and relationships in the person-centric knowledge database.
5. The method of claim 1 , wherein:
the question comprises a sender of a private electronic communication sent to the user, and the question is classified as a personal question.
6. The method of claim 1 , wherein:
the question is not related to the private space or the semi-private data, and the question is classified as a non-personal question.
7. The method of claim 1 , wherein the answer is presented to the user via an answer card.
8. A machine-readable, non-transitory and tangible medium having information recorded thereon for question classification, when read by the machine, causes the machine to perform operations comprising:
classifying, via a machine-learned model based on data from a person-centric space with respect to a user, a question from the user into a personal question or a non-personal question, wherein the person-centric space is constructed by cross-linking information relevant to the user from a public space, a semi-private space, and a private space, and wherein the data indicates whether the question comprises a sender of a private electronic communication sent to the user;
searching for an answer to the question in the person-centric space or in the public space depending on the classification of the question;
presenting the answer to the user; and
updating, based the answer, the person-centric space.
9. The medium of claim 8 ,
wherein the question is classified as a personal question, and the operations further comprise:
extracting entities and relationships from the question, and
traversing a person-centric knowledge database derived from the person-centric space, wherein the person-centric knowledge database comprises one or more entities and relationships between the one or more entities.
10. The medium of claim 9 ,
wherein the extracted entities and relationships match the entities and relationships in the person-centric knowledge database, and the operations further comprise returning the answer based on the entities and relationships in the person-centric knowledge database.
11. The medium of claim 9 ,
wherein the extracted entities and relationships do not match the entities and relationships in the person-centric knowledge database, and the operations further comprise: returning the answer based on a similarity between the extracted entities and relationships and the entities and relationships in the person-centric knowledge database.
12. The medium of claim 8 , wherein:
the question comprises a sender of a private electronic communication sent to the user, and the question is classified as a personal question.
13. The medium of claim 8 , wherein:
the question is not related to the private space or the semi-private data, and the question is classified as a non-personal question.
14. The medium of claim 8 , wherein the answer is presented to the user via an answer card.
15. A system for question classification, the system comprising:
memory storing computer program instructions; and
one or more processors that, in response to executing the computer program instructions, effectuate operations comprising:
classifying, via a machine-learned model based on data from a person-centric space with respect to a user, a question from the user into a personal question or a non-personal question, wherein the person-centric space is constructed by cross-linking information relevant to the user from a public space, a semi-private space, and a private space, and wherein the data indicates whether the question comprises a sender of a private electronic communication sent to the user;
searching for an answer to the question in the person-centric space or in the public space depending on the classification of the question;
presenting the answer to the user; and
updating, based the answer, the person-centric space.
16. The system of claim 15 , wherein the question is classified as a personal question, and the operations further comprise:
extracting entities and relationships from the question, and
traversing a person-centric knowledge database derived from the person-centric space, wherein the person-centric knowledge database comprises one or more entities and relationships between the one or more entities.
17. The system of claim 16 , wherein the extracted entities and relationships match the entities and relationships in the person-centric knowledge database, and the operations further comprise returning the answer based on the entities and relationships in the person-centric knowledge database.
18. The system of claim 16 , wherein the extracted entities and relationships do not match the entities and relationships in the person-centric knowledge database, and the operations further comprise returning the answer based on a similarity between the extracted entities and relationships and the entities and relationships in the person-centric knowledge database.
19. The system of claim 15 , wherein:
the question a sender of a private electronic communication sent to the user, and the question is classified as a personal question.
20. The system of claim 15 , wherein:
the question is not related to the private space or the semi-private data, and the question is classified as a non-personal question.