Electronic device and method for controlling the electronic device

1. An electronic device comprising:

a microphone;

a memory configured to store at least one instruction; and

a processor configured to execute the at least one instruction,

wherein the processor is configured to control the electronic device to:

perform voice recognition using automatic speech recognition for an inquiry and acquire a text corresponding to the inquiry based on receiving inquiry input through the microphone,

determine whether the acquired text corresponds to a sample inquiry generated based on a relation graph indicating a relation between the acquired text and data stored in a plurality of databases,

based on determining that the acquired text corresponds to the sample inquiry, generate a plurality of inquiries to acquire response data for the inquiry from the plurality of databases using the acquired text and the relational graph, wherein each inquiry of the plurality of inquiries is related to a corresponding database of the plurality of databases,

acquire response data corresponding to each of the plurality of inquiries from each of the plurality of databases,

generate a response for the inquiry based on the response data acquired from each of the plurality of databases, and

output the response.

2. The electronic device of claim 1 ,

wherein the processor is configured to control the electronic device to:

analyze data fields stored in the plurality of databases and acquire the relation graph indicating a relation among data stored in the plurality of databases.

3. The electronic device of claim 2 ,

wherein the processor is configured to control the electronic device to:

analyze at least one of names of data fields included in the plurality of databases, names of data included in the data fields, or distribution of data and determine similar data fields among the plurality of databases,

determine upper concepts of the determined similar data fields,

designate the upper concepts as upper nodes,

designate the similar data fields as lower nodes of the upper nodes, and

acquire the relation graph.

4. The electronic device of claim 3 ,

wherein the processor is configured to control the electronic device to:

generate the sample inquiry and a sample response based on the upper node and store the sample inquiry and the sample response in the memory.

5. The electronic device of claim 4 ,

wherein the processor is configured to control the electronic device to:

generate the response based on the sample response based on acquiring response data from each of the plurality of databases, and

output the response.

6. The electronic device of claim 3 ,

wherein the processor is configured to control the electronic device to:

determine the upper nodes corresponding to each of a plurality of inquiry elements included in the acquired text, and

generate the plurality of inquiries based on a plurality of lower nodes included in the upper nodes.

7. The electronic device of claim 6 ,

wherein the processor is configured to control the electronic device to:

acquire a plurality of first keywords corresponding to each of the plurality of inquiry elements based on a lower node corresponding to a first database included in the upper node,

generate a first inquiry for the first database based on the plurality of first keywords,

acquire a plurality of second keywords corresponding to each of the plurality of inquiry elements based on a lower node corresponding to a second database included in the upper node, and

generate a second inquiry for the second database based on the plurality of second keywords.

8. The electronic device of claim 1 ,

wherein the processor is configured to control the electronic device to:

determine whether the response is a response generated by integrating the plurality of response data.

9. The electronic device of claim 1 , wherein the processor is further configured to control the electronic device to acquire the relation graph including expanding the relation graph using a conventional knowledge graph storing general knowledge.

10. The electronic device of claim 1 , wherein the processor is further configured to control the electronic device to:

acquire a plurality of first keywords corresponding to each of a plurality of inquiry elements included in the acquired text based on a lower node the relation graph corresponding to a first database included in an upper node;

generate a first inquiry for the first database based on the plurality of first keywords,

acquire a plurality of second keywords corresponding to each of the plurality of inquiry elements based on a lower node the relation graph corresponding to a second database included in the upper node, and

generate a second inquiry for the second database based on the plurality of second keywords,

wherein the upper node being an upper concept of similar data fields among the plurality of databases.

11. A method for controlling an electronic device comprising:

performing voice recognition using automatic speech recognition for an inquiry based on receiving input inquiry through a microphone, and acquiring a text for the inquiry;

determining whether the acquired text corresponds to a sample inquiry generated based on a relation graph indicating a relation between the acquired text and data stored in a plurality of databases,

based at least on determining that the acquired text corresponds to the sample inquiry, generating a plurality of inquiries for acquiring response data for the inquiry from the plurality of databases using the acquired text and the relation graph, wherein each inquiry of the plurality of inquiries is related to a corresponding database of the plurality of databases;

acquiring response data corresponding to each of the plurality of inquiries from each of the plurality of databases;

generating a response for the inquiry based on the response data acquired from each of the plurality of databases; and

outputting the response.

12. The method of claim 11 , comprising:

analyzing data fields stored in the plurality of databases and acquiring the relation graph indicating a relation among data stored in the plurality of databases.

13. The method of claim 12 ,

wherein the acquiring the relation graph comprises:

analyzing at least one of names of data fields included in the plurality of databases, names of data included in the data fields, or distribution of data;

determining similar data fields among the plurality of databases;

determining upper concepts of the determined similar data fields;

designating the upper concepts as upper nodes;

designating the similar data fields as lower nodes of the upper nodes; and

acquiring the relation graph.

14. The method of claim 13 , comprising:

generating the sample inquiry and a sample response based on the upper node and storing the sample inquiry and the sample response in memory of the electronic device.

15. The method of claim 14 ,

wherein the outputting comprises:

generating the response based on the sample response based on acquiring response data from each of the plurality of databases, and outputting the response.

16. The method of claim 13 ,

wherein the generating comprises:

determining the upper nodes corresponding to each of a plurality of inquiry elements included in the acquired text; and

generating the plurality of inquiries based on a plurality of lower nodes included in the upper nodes.

17. The method of claim 16 ,

wherein the generating comprises:

acquiring a plurality of first keywords corresponding to each of the plurality of inquiry elements based on a lower node corresponding to a first database included in the upper node, and generating a first inquiry for the first database based on the plurality of first keywords; and

acquiring a plurality of second keywords corresponding to each of the plurality of inquiry elements based on a lower node corresponding to a second database included in the upper node, and generating a second inquiry for the second database based on the plurality of second keywords.

18. The method of claim 11 , further comprising:

determining whether the response is a response generated by integrating the plurality of response data.