Method and apparatus for question-answering using a database consist of query vectors

1 . A search method performed by an electronic device, the search method comprising:

acquiring a user question from a user;

when an answer to the user question is not stored in a database of the electronic device, generating a user question vector for the user question;

transmitting the user question vector to a server, wherein a database of the server stores one or more question-answer-question vector including a question, a response to the question and a question vector for the question;

when a plurality of similar question candidates are selected by the server using a first similarity analysis model for determining first similarities between question vectors stored in the server and the user question vector, receiving the plurality of similar question candidates and question vectors corresponding to the plurality of similar question candidates together with first similarities associated with the question vectors corresponding to the plurality of similar question candidates or a similarity ranking of the plurality of similar question candidates from the server;

selecting one or more similar questions from the plurality of similar question candidates by the electronic device using a second similarity analysis model for determining second similarities between the received question vectors and the user question vector;

requesting responses to the one or more similar questions from the server;

receiving the responses to the one or more similar questions from the server; and

providing the one or more similar questions and the responses to the similar question together to the user,

wherein

the first similarity analysis model and the second similarity analysis model have different configurations of neural network models or different values of variables included in hidden layers, and

one of the first similarity analysis model and the second similarity analysis model determines a similarity to the user question vector based on a distance from the user question vector in a Euclidean space, and

wherein the first similarity analysis model and the second similarity analysis model are different analysis models.

2 . The search method of claim 1 , further comprising, when the answer to the user question is stored in the database of the electronic device, providing the answer stored in the database to the user.

3 . The search method of claim 1 , wherein the generating of the user question vector for the user question comprises vectorizing the user question using an encoder of the electronic device to generate the user question vector, and

the encoder of the electronic device includes one of bag of words (BOW), term frequency-inverse document frequency (TF-IDF), document to vector (Doc2Vec), a text embedding encoder, and word to vector (Word2Vec).

4 . The search method of claim 1 , wherein the other of the first similarity analysis model and the second similarity analysis model determines a similarity to the user question vector based on a cosine similarity.

5 . The search method of claim 1 , wherein the second similarity analysis model includes a paraphrase model generated by learning a Siamese neural network with first learning data and second learning data,

the first learning data includes a first pair of questions and a label indicating that the first pair of questions are similar to each other, wherein the first pair of questions have similar sentence formats due to similar words and structures and include questions having similar meanings, and

the second learning data includes a second pair of questions and a label indicating that the second pair of questions are dissimilar from each other, wherein the second pair of questions have similar sentence formats due to similar words and structures but include questions having different meanings.

6 . The search method of claim 5 , wherein learning of the neural network with the first learning data and learning of the neural network with the second learning data are performed without distinguishment by mixing the first learning data and the second learning data.

7 . The search method of claim 1 , wherein the plurality of similar question candidates selected by the server correspond to questions associated with question vectors having a first similarity higher than a preset reference among the question vectors stored in the server.

8 . The search method of claim 1 , wherein the selecting one or more similar questions from the plurality of similar question candidates comprises:

grading the received question vectors based on second similarities between the received question vectors and the user question vector; and

selecting the one or more similar questions for each grade.

9 . The search method of claim 1 , wherein the selecting one or more similar questions from the plurality of similar question candidates comprises:

degerming a similarity ranking of the received question vectors based on second similarities between the received question vectors and the user question vector; and

selecting a predetermined number of similar question candidates as the one or more similar questions.

10 . The search method of claim 1 , wherein the selecting one or more similar questions from the plurality of similar question candidates comprises:

selecting one or more question vectors from the received question vectors based on the received first similarities or the received similarity ranking; and

selecting the one or more similar questions from among the plurality of similar question candidates based on second similarities between the one or more selected question vectors and the user question vector.

11 . An electronic device comprising:

a processor; and

a non-transitory memory configured to store instructions executed by the processor,

wherein the processor executes the instructions to:

acquire a user question from a user;

when an answer to the user question is not stored in a database of the electronic device, generate a user question vector for the user question;

transmit the user question vector to a server, wherein a database of the server stores one or more question-answer-question vector including a question, a response to the question and a question vector for the question;

when a plurality of similar question candidates are selected by the server using a first similarity analysis model for determining first similarities between question vectors stored in the server and the user question vector, receive the plurality of similar question candidates and question vectors corresponding to the plurality of similar question candidates together with first similarities associated with the question vectors corresponding to the plurality of similar question candidates or a similarity ranking of the plurality of similar question candidates from the server;

select one or more similar questions from the plurality of similar question candidates by the electronic device using a second similarity analysis model for determining second similarities between the received question vectors and the user question vector;

request responses to the one or more similar questions from the server;

receive the one or more response to the similar questions from the server; and

provide the one or more similar question and the response to the similar question together to the user,

wherein

the first similarity analysis model and the second similarity analysis model have different configurations of neural network models or different values of variables included in hidden layers, and

one of the first similarity analysis model and the second similarity analysis model determines a similarity to the user question vector based on a distance from the user question vector in a Euclidean space, and

wherein the first similarity analysis model and the second similarity analysis model are different analysis models.

12 . A computer-readable recording non-transitory medium in which a computer program executed by an electronic device is recorded, the computer program comprising:

acquiring a user question from a user;

when an answer to the user question is not stored in a database of the electronic device, generate a user question vector for the user question;

transmitting the user question vector to a server, wherein a database of the server stores one or more question-answer-question vector including a question, a response to the question and a question vector for the question;

when a plurality of similar question candidates are selected by the server using a first similarity analysis model for determining first similarities between question vectors stored in the server and the user question vector, receiving the plurality of similar question candidates and question vectors corresponding to the plurality of similar question candidates together with first similarities associated with the question vectors corresponding to the plurality of similar question candidates or a similarity ranking of the plurality of similar question candidates from the server;

selecting one or more similar questions from the plurality of similar question candidates by the electronic device using a second similarity analysis model for determining second similarities between the received question vectors and the user question vector;

requesting responses to the one or more similar question from the server;

receiving the one or more response to the similar question from the server; and

providing the one or more similar question and the response to the similar question together to the user,

wherein

the first similarity analysis model and the second similarity analysis model have different configurations of neural network models or different values of variables included in hidden layers, and

one of the first similarity analysis model and the second similarity analysis model determines a similarity to the user question vector based on a distance from the user question vector in a Euclidean space, and

wherein the first similarity analysis model and the second similarity analysis model are different analysis models.