A method for discovering special news events
A news and topic technology, applied in the field of news topic event discovery, can solve the problems that traditional methods are difficult to extend to new fields, dependence, and difficulty in final clustering results.
Active Publication Date: 2021-04-09
北京百分点科技集团股份有限公司
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, it is often difficult for traditional keyword extraction algorithms to extract keywords that can fully summarize the news content, so that the overall effect of this method is greatly reduced
Secondly, because artificial rules are often introduced into traditional algorithms, it is difficult to extend traditional methods to new fields.
Finally, since traditional algorithms rely on text clustering algorithms, the final clustering results are heavily dependent on proper parameter selection
However, the traditional text clustering method is a black-box algorithm, so parameter selection is more difficult, and often makes it difficult to explain the final clustering results with business knowledge
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0055] The present invention will be further described below in conjunction with the accompanying drawings. It should be noted that this embodiment is based on the technical solution, and provides detailed implementation and specific operation process, but the protection scope of the present invention is not limited to the present invention. Example.
[0056] This embodiment provides a method for discovering special news events, such as figure 1 shown, including the following steps:
[0057] S1, identifying the event topic sentence of the news article;
[0058] Due to the large differences in the content and direction of news reports, it is difficult to identify the event topic sentences of a single news article. In this embodiment, a method of identifying event topic sentences is adopted based on factors such as common news event elements, event trigger words, and positional relationships of sentences in news articles. Specifically, the event topic sentence score T of each...
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 discloses a method for discovering special news events, which mainly includes: S1, identifying event topic sentences for each given news article; S2, extracting event core elements for each given news article; S3, The event core elements of each news article extracted in step S2 are used to determine article similarity. The method of the present invention is based on event element extraction (Event extraction) technology, topic tracking detection (Topic Detection and Tracking), event relationship discovery and topic news incremental addition technology, to realize topic event discovery and clustering of news text, and realize news text The topic-based clustering and discovery method allows users to achieve high-quality thematic clustering and event discovery without providing labeled training data, event type templates, or relevant domain knowledge.
Description
technical field [0001] The invention relates to the technical field of data processing, in particular to a method for discovering special news events. Background technique [0002] Natural language processing (NLP) is the field of interaction between computers and human (natural) language that computer science, artificial intelligence, and linguistics focus on. It is an important direction in the field of computer science and artificial intelligence. The research scope of natural language processing covers various theories and methods that can realize effective communication between humans and computers in natural language. The fields involved include natural semantic understanding, information retrieval, information extraction, text classification, text clustering, automatic question answering system etc. [0003] Topic event discovery refers to the technology of extracting and summarizing topics from a given news collection and classifying news according to the extracted ...
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
Login to View More Patent Type & AuthorityPatents(China)
IPC IPC(8): G06F16/35G06F40/205G06F40/289
CPCG06F16/353G06F40/205G06F40/289
Inventor高体伟苏海波王然孙伟王勋刘钰
Owner北京百分点科技集团股份有限公司