Method and apparatus for processing questions and answers, electronic device and storage medium

An electronic device, comprising:

• at least one processor;
• and
• a storage device communicatively connected to the at least one processor;
• wherein, the storage device is configured to store an instruction executable by the at least one processor, and the instruction is executed by the at least one processor to enable the at least one processor to:
• acquire a question to be answered;
• input the question to be answered into a first semantic representation model of question and a second semantic representation model of question separately to obtain a first semantic representation vector and a second semantic representation vector for the question to be answered, wherein the first semantic representation model of question is trained based on a question sample and an answer sample corresponding to the question sample, and the second semantic representation model of question is trained based on the question sample and an article title corresponding to the answer sample;
• perform a splicing operation based on the first semantic representation vector and the second semantic representation vector to obtain a target semantic representation vector for the question to be answered;
• match the target semantic representation vector for the question to be answered with each semantic representation vector of answer contained in a pre-established vector index library of answer, wherein the vector index library of answer is established by converting all candidate answers in a sample pool of answer into respective semantic representation vectors, and the semantic representation vector of answer corresponding to each candidate answer is obtained based on the semantic representation vector of the candidate answer and a semantic representation vector of title for the article title corresponding to the candidate answer;
• and
• acquire a target answer based on the semantic representation vector of answer matched with the target semantic representation vector, and outputting the target answer.

A non-transitory computer-readable storage medium, having a computer instruction stored thereon, wherein the computer instruction is configured to cause a computer to perform the a method for processing questions and answers, the method comprising:

• acquiring a question to be answered;
• inputting the question to be answered into a first semantic representation model of question and a second semantic representation model of question separately to obtain a first semantic representation vector and a second semantic representation vector for the question to be answered, wherein the first semantic representation model of question is trained based on a question sample and an answer sample corresponding to the question sample, and the second semantic representation model of question is trained based on the question sample and an article title corresponding to the answer sample;
• performing a splicing operation based on the first semantic representation vector and the second semantic representation vector to obtain a target semantic representation vector for the question to be answered;
• matching the target semantic representation vector for the question to be answered with each semantic representation vector of answer contained in a pre-established vector index library of answer, wherein the vector index library of answer is established by converting all candidate answers in a sample pool of answer into respective semantic representation vectors, and the semantic representation vector of answer corresponding to each candidate answer is obtained based on the semantic representation vector of the candidate answer and a semantic representation vector of title for the article title corresponding to the candidate answer;
• and
• acquiring a target answer based on the semantic representation vector of answer matched with the target semantic representation vector, and outputting the target answer.