Data processing method and device for quantifying news value based on user release content

A technology of data processing and quantitative processing, which is applied in digital data processing, special data processing applications, unstructured text data retrieval, etc., can solve the problem of low efficiency in finding news clues, and achieve the effect of improving efficiency

Pending Publication Date: 2019-05-24
BEIJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention proposes a data processing method and device for quantifying the value of news based on the content released by users, so as to solve the technical problem in the prior art that the efficiency of artificially searching for news clues is not high

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
  • Data processing method and device for quantifying news value based on user release content
  • Data processing method and device for quantifying news value based on user release content
  • Data processing method and device for quantifying news value based on user release content

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] Embodiment 1 of the present invention provides a data processing method for quantifying news value based on content published by users, see figure 1 As shown, the method includes the steps of:

[0062] Step S101, constructing a news value quantification model in advance.

[0063] The news value quantification model should quantify the news value of user-published content from three dimensions: social importance, deviation and contingency conditions.

[0064] Among them, the social importance is quantified from the three indicators of the importance of the participants, the importance of the event location, and the importance of the event, and the deviation is quantified from the two indicators of event degree conflict and statistical scarcity. Quantitative processing is carried out from the two indicators of information timeliness and information integrity.

[0065] i.e., see figure 2 Shown, the present invention has carried out following definition to news value qu...

Embodiment 2

[0080] Embodiment 2 of the present invention provides a preferred embodiment of a data processing method for quantifying news value based on user published content, including steps:

[0081] Step S201, constructing a news value quantification model in advance.

[0082] Step S202, preprocessing the candidate unstructured text data, and normalizing the data.

[0083] This step is mainly to remove interference factors such as symbols.

[0084] Step S203, using natural language technology to extract information elements, and completing the structuring and quantification processing of the structured data.

[0085] This step S203 mainly includes two main processes of information extraction and quantization processing.

[0086] Information extraction includes the following steps:

[0087] Taking Weibo as an example, in order to quantitatively evaluate news value from Weibo data, it is necessary to extract the information elements in Weibo data, and convert abstract text informatio...

Embodiment 3

[0162] The embodiment of the present invention also provides a data processing device for extracting news clues based on content published by users, including a news value quantification module and an information extraction module.

[0163] The news value quantification module is used to quantify the news value of user-published content from the three dimensions of social importance, deviation and contingency conditions; the social importance is measured from three dimensions: the importance of participants, the importance of event location and the importance of events The indicators are quantified, and the deviation is quantified from the two indicators of event degree conflict and statistical scarcity, and the contingency conditions are quantified from the two indicators of information timeliness and information integrity.

[0164] The information extraction module is used to extract the information elements corresponding to each indicator in the news value quantification mod...

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

No PUM Login to view more

Abstract

The invention discloses a data processing method and device for quantifying news value based on user release content. The method comprises the steps of constructing a news value quantification model in advance, and quantifying the news value of the content published by a user from three dimensions of social importance, deviation and weight change conditions; for three indexes of social importancefrom participants, quantifying event positions and events, two indexes of deviation from event degree conflicts and statistics of scarcity, and quantifying two indexes of weight change condition frominformation timeliness and integrity; and extracting information elements from the user published content, performing quantitative processing, and performing calculation to obtain a news value quantitative value of the user published content. The device comprises a news value quantification module and an information extraction module. According to the method and the device provided by the invention, valuable news clues are found from mass text data, the value index of the published report of the new event in the network is obtained in a more efficient and intelligent manner, the length of a news production chain is shortened, and the timeliness of news clue discovery is improved.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to a data processing method for quantifying news value based on content published by users. Background technique [0002] With the popularization and application of social network platforms such as Weibo, more and more people tend to publish events around them on social networks such as Weibo platforms. These large numbers of events are likely to become valuable clues for journalists to discover. So as to form the source of news reports. Therefore, many traditional media try to use Weibo as an information source to find valuable news clues. News clue mining based on massive Internet data has gradually become an important direction for the development of news production practice. [0003] However, in traditional news practice, news value is usually selected and prioritized by reporters or editors relying on experience and intuition, that is, the traditional way o...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/9535G06F16/35G06F17/27
Inventor 傅湘玲齐佳音李晶闫晨巍
Owner BEIJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products