Unlock instant, AI-driven research and patent intelligence for your innovation.
A method and device for extracting abstracts
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of summaries and sentences, which is applied in the field of Internet news, can solve the problem of time-consuming manual extraction of summaries, and achieve the effect of improving readability and reading efficiency
Active Publication Date: 2019-08-27
NEUSOFT CORP
View PDF4 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0005] In order to solve the time-consuming technical problem of manually extracting summaries in the prior art, a method and device for extracting summaries are provided, which can automatically extract summaries of news and other manuscripts, and improve the work efficiency of extracting summaries
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0060] see figure 1 , which is a flow chart of Embodiment 1 of the method for extracting abstracts provided by the present invention.
[0061] The method for extracting the abstract provided in this embodiment includes the following steps:
[0062] S101: Split the manuscript to be extracted into paragraphs, and split each of the split paragraphs into sentences;
[0063] It can be understood that the manuscript to be extracted may be any manuscript on the Internet, or various electronic manuscripts. For example, news, biographies, etc.
[0064] It should be noted that splitting a manuscript into paragraphs and splitting a paragraph into sentences is a relatively mature technology at present, and will not be described in detail here.
[0065] S102: Screen candidate abstract sentences according to the correlation between the sentence and the title of the manuscript;
[0066] The title of a general manuscript summarizes the gist of the manuscript. Therefore, the relevance of t...
Embodiment 2
[0077] see figure 2 , which is a flow chart of Embodiment 2 of the method for extracting abstracts provided by the present invention.
[0078] In the method for extracting a summary provided in this embodiment, S201 is the same as S101, and will not be repeated here. And this embodiment only introduces the situation when it is judged that the sum of the word counts of all the abstract candidate sentences is greater than the predetermined word count of the abstract.
[0079] The screening of candidate abstract sentences according to the correlation between the sentence and the title of the manuscript specifically includes:
[0080] S202a: Use the first sentence in each paragraph as the first type of summary candidate sentence.
[0081] It should be noted that since the first sentence of a paragraph is generally a generalization and summary of the entire paragraph, therefore, directly using the first sentence of a paragraph as a candidate sentence for the abstract can also be...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More
PUM
Login to View More
Abstract
The invention provides an abstract extracting method and apparatus. The method includes the steps of dividing a manuscript, of which the abstract is to be extracted, into paragraphs, dividing each paragraph into sentences, selecting abstract selectable sentences according to the correlation degree between the sentences and the title of the manuscript, if the total character number of all abstract selectable sentences is equal to or less than the preset character number of the abstract, taking all abstract selectable sentences as abstract sentences, obtaining the weight values of the abstract selectable sentences if the total character number of all abstract selectable sentences is greater than the preset character number of the abstract, and ranking the abstract selectable sentences according to the weight values, and selecting the abstract selectable sentences ranked in the front as abstract sentences according to the preset character number of the abstract. Through the method, an abstract can be formed automatically according to the contents of a manuscript, which allows a reader to rapidly understand the main contents of the manuscript and improving reading efficiency. Since the abstract sentences are complete sentences directly selected from the manuscript, incomplete short sentences may not generated. The readability of the abstract is improved.
Description
technical field [0001] The invention relates to the technical field of Internet news, in particular to a method and device for extracting abstracts. Background technique [0002] With the rapid development of the Internet, the amount of news information released on the Internet is increasing. Many TV stations need to aggregate Internet news and provide summaries for users. Users browse the abstract and then decide whether to read the corresponding full-text content in detail. [0003] However, the amount of Internet news information is too large and the update frequency is very fast. It takes a long time to manually browse the news content and then extract the summary, and the labor cost is too high. [0004] Therefore, those skilled in the art need to provide a method and device for extracting abstracts, which can automatically extract abstracts of news and other manuscripts. Contents of the invention [0005] In order to solve the technical problem in the prior art th...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More