Unlock instant, AI-driven research and patent intelligence for your innovation.

Hot event monitoring method and device, computer device and readable storage medium

A technology of hot events and computer programs, applied in the field of information processing, can solve the problems of low timeliness, high complexity of time calculation and storage space, difficult to accurately select keywords, etc., to achieve the effect of improving accuracy

Active Publication Date: 2020-08-14
招商局金融科技有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The traditional method of discovering hot news events is generally based on artificially predefined keywords to screen target hot news. This method of hot event discovery has the disadvantage of low timeliness
The traditional evaluation of the importance of massive keywords generated by news streams generally uses the TF-IDF algorithm to find valuable keyword candidate sets, and the calculation of the importance of each keyword depends on the statistical feature results of all keyword sets. When the news flow generates a large number of keywords, the time calculation complexity and storage space complexity are high, which has a great negative impact on the real-time discovery of hot events, and is not friendly enough for new word discovery. Valuable keywords are often not seen in the previous news flow, and the TF-IDF algorithm cannot accurately capture these new words, and it is difficult to accurately select keywords that best represent hot news, resulting in low quality news screening, May be mixed with other irrelevant news noise

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
  • Hot event monitoring method and device, computer device and readable storage medium
  • Hot event monitoring method and device, computer device and readable storage medium
  • Hot event monitoring method and device, computer device and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] figure 1 It is a flowchart of the steps of a preferred embodiment of the hot event monitoring method of the present invention. According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted.

[0046] Refer to figure 1 As shown, the hot event monitoring method specifically includes the following steps.

[0047] Step S11: Extract the keyword stream of the target event from the obtained news stream related to the target event, and filter the keyword stream using preset filtering rules to construct a key according to the multiple keywords obtained by filtering. Word set.

[0048] In one embodiment, the target event may be a designated hot event, which may be determined according to actual needs. For example, the news stream related to the target event can be obtained in real time or at regular time through crawler technology, and then the relevant news stream can be processed according to the preset keyword capture tech...

Embodiment 2

[0120] Figure 4 It is a functional block diagram of a preferred embodiment of the hot event monitoring device of the present invention.

[0121] Refer to Figure 4 As shown, the hot event monitoring device 10 may include a construction module 101, a segmentation module 102, a first processing module 103, a second processing module 104, a punishment module 105, an inheritance module 106, and a monitoring module 107.

[0122] The construction module 101 is configured to extract the keyword stream of the target event from the obtained news stream related to the target event, and filter the keyword stream by using preset filtering rules to filter the multiple keywords obtained Build a keyword set.

[0123] In an embodiment, the target event may be a designated hot event, which may be determined according to actual needs. For example, the news stream related to the target event can be acquired in real time or at regular time through crawler technology, and then the relevant news stream ...

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 hot event monitoring method and device, a computer device and a computer readable storage medium. The method comprises the following steps: extracting a keyword stream of a target event from an obtained news stream related to the target event, and filtering the keyword stream to construct a keyword set; segmenting the keyword set into a plurality of time windows with non-fixed sizes according to timestamps of keywords in the keyword set; carrying out out-of-order processing on the keywords in each time window, removing timestamps of the keywords, and recording time span information of each time window; screening and filtering the keywords in the out-of-order processed time window based on a preset cache filter; and monitoring the screened and filtered keywords inthe time window by using a preset monitoring and updating mechanism to obtain event feature keywords of the keyword set. The keywords capable of representing the hot events can be accurately selected,so that the accuracy of screening news related to the hot events is improved.

Description

Technical field [0001] The present invention relates to the field of information processing technology, in particular to a hot event monitoring method, device, computer device and computer-readable storage medium. Background technique [0002] Traditional news hot event discovery methods generally screen target hot news based on artificially pre-defined keywords. This hot event discovery method has the disadvantage of low timeliness. Traditionally, the evaluation of the importance of massive keywords generated by news streams generally uses the TF-IDF algorithm to find valuable keyword candidate sets. The importance calculation of each keyword depends on the statistical characteristics of all keyword sets. When the news stream generates a large number of keywords, the time calculation complexity and the storage space complexity are both high, which has a large negative impact on the real-time detection of hot events, and is not friendly to the discovery of new words. Hot event ne...

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
IPC IPC(8): G06F16/9532G06F16/9537
CPCG06F16/9532G06F16/9537Y02D10/00
Inventor 黄晨张蓓刘屹徐楠万正勇沈志勇高宏
Owner 招商局金融科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com