Summary generation method and apparatus

1. A summary generation method comprising:

receiving a webpage processing request from a user terminal;

acquiring a target article including a headline and a body of the article according to the received webpage processing request;

determining whether a question is included in the headline;

determining, in the body of the article, an information-satisfied-paragraph including an answer to the question, in response to determining that the question is included in the headline; and

generating a summary of the target article based on the determined information-satisfied-paragraph, and sending the generated summary to the user terminal;

wherein determining that the question is included in the headline comprises:

determining that the question is included in the headline, in response to determining that the headline includes a referential relationship but does not include an object to which the referential relationship refers, and

wherein generating a summary of the target article based on the determined information-satisfied-paragraph comprises:

deleting invalid statements included: the information-satisfied-paragraph, one paragraph preceding the information-satisfied-paragraph, and one paragraph following the information-satisfied-paragraph, the invalid statements comprising statements for describing pictures, statements consistent with the headline, and a header; and

generating the summary based on each paragraph with the invalid statements deleted.

2. The method according to claim 1 , wherein determining that the question is included in the headline comprises further comprises:

determining that the question is included in the headline, where the headline is an interrogative sentence; and

determining that the question is included in the headline, where the headline includes at least one word in a preset set of words.

3. The method according to claim 1 , wherein determining an information-satisfied-paragraph in the body of the article comprises:

determining similarities between the headline and each paragraph in the body of the article; and

determining a paragraph corresponding to a maximum similarity of determined similarities as the information-satisfied-paragraph.

4. The method according to claim 1 , wherein generating a summary of the target article based on the determined information-satisfied-paragraph comprises:

generating, from the information-satisfied-paragraph and at least one paragraph following the information-satisfied-paragraph, the summary.

5. The method according to claim 1 , wherein generating a summary of the target article based on the determined information-satisfied-paragraph comprises:

generating, from the information-satisfied-paragraph and at least one paragraph preceding the information-satisfied-paragraph, the summary in response to determining that a start word of information-satisfied-paragraph is a conjunction.

6. The method according to claim 1 , wherein generating a summary of the target article based on the determined information-satisfied-paragraph comprises:

intercepting a plurality of sentences in the information-satisfied-paragraph in response to determining that a number of words in the information-satisfied-paragraph is greater than a preset word number threshold; and

determining the intercepted sentences as the summary.

7. A summary generation apparatus comprising:

one or more processors; and

storage devices on which one or more programs are stored, when the one or more programs are executed by the one or more processors, the one or more processors are caused to,

receive a webpage processing request from a user terminal;

acquire a target article including a headline and a body of the article according to the received webpage processing request;

determine whether a question is included in the headline;

determine, in the body of the article, an information-satisfied-paragraph including an answer to the question, in response to determining that the question is included in the headline; and

generate a summary of the target article based on the determined information-satisfied-paragraph, and send the generated summary to the user terminal;

wherein determining that the question is included in the headline comprises:

determining that the question is included in the headline, in response to determining that the headline includes a referential relationship but does not include an object to which the referential relationship refers, and

wherein generating a summary of the target article based on the determined information-satisfied-paragraph comprises:

deleting invalid statements included: the information-satisfied-paragraph, one paragraph preceding the information-satisfied-paragraph, and one paragraph following the information-satisfied-paragraph, the invalid statements comprising statements for describing pictures, statements consistent with the headline, and a header; and

generating the summary based on each paragraph with the invalid statements deleted.

8. The apparatus according to claim 7 , wherein when the one or more programs are executed by the one or more processors, the one or more processors are further caused to perform:

determining that the question is included in the headline, where the headline is an interrogative sentence; and

determining that the question is included in the headline, where the headline includes at least one word in a preset set of words.

9. The apparatus according to claim 7 , wherein t when the one or more programs are executed by the one or more processors, the one or more processors are further caused to:

determine similarities between the headline and each paragraph in the body of the article; and

determine a paragraph corresponding to a maximum similarity of determined similarities as the information-satisfied-paragraph.

10. The apparatus according to claim 7 , wherein when the one or more programs are executed by the one or more processors, the one or more processors are further caused to:

generate, from the information-satisfied-paragraph and at least one paragraph following the information-satisfied-paragraph, the summary.

11. The apparatus according to claim 7 , wherein when the one or more programs are executed by the one or more processors, the one or more processors are further caused to:

generate, from the information-satisfied-paragraph and at least one paragraph preceding the information-satisfied-paragraph, the summary in response to determining that a start word of information-satisfied-paragraph is a conjunction.

12. The apparatus according to claim 7 , wherein when the one or more programs are executed by the one or more processors, the one or more processors are further caused to:

intercept a plurality of sentences in the information-satisfied-paragraph in response to determining that a number of words in the information-satisfied-paragraph is greater than a preset word number threshold; and

determine the intercepted sentences as the summary.