Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-granularity real-time hot spot aggregation method

An aggregation method and multi-granularity technology, applied in the field of information retrieval, can solve problems such as ambiguity in meaning of events, influence on users, unclear representation of events, etc., and achieve the effect of improving completeness and accuracy, improving accuracy, and facilitating access

Active Publication Date: 2017-06-20
BEIHANG UNIV
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, since this kind of non-artificial hotspot event detection technology is still in the initial application stage, many situations in the real world cannot be considered in advance, such as similar events, different stages of the same event, etc., which will cause redundancy in time display and affect users' fast Accurately obtain hotspot information within the relevant time period; in addition, the emergence of events such as unclear representation and ambiguous event meaning will also affect the accuracy of users' access to hotspot information

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
  • Multi-granularity real-time hot spot aggregation method
  • Multi-granularity real-time hot spot aggregation method
  • Multi-granularity real-time hot spot aggregation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] Embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0042] figure 1 It is a schematic flowchart of Embodiment 1 of the multi-granularity real-time hotspot aggregation method provided by the present invention. The execution subject of this embodiment may be a multi-granularity real-time hotspot aggregation system, such as figure 1 As shown, the method provided in this embodiment includes the following steps:

[0043] S101. Perform data cleaning processing on the input streaming data, and represent the processed streaming data as structured data.

[0044] Specifically, distributed crawler technology can be used to collect streaming data in the network (for example: Sina Weibo, Sina News, Netease News, etc.), and these streaming data include hot information such as events and news.

[0045] After the collected streaming data is input into the system, the data can be cleaned first according to the set rules to filt...

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 provides a multi-granularity real-time hot spot aggregation method, comprising: performing data cleaning processing on input streaming data, showing the processed streaming data in structural data; performing word segmentation on the structural data in first preset time slice, and calculating weight of each segmented word in all streaming data; according to the weight of each segmented word, calculating weight of each event in the current time slice; aggregating events, and according to the weight of each event, calculating weight of each event cluster after aggregation; and according to the weight of each event cluster, generating a sorted event list. The technical scheme improves granularity of a final event display result, and event integrity and accuracy, and provides convenience for a user to rapidly and accurately obtain hot spot information.

Description

technical field [0001] The invention relates to information retrieval technology, in particular to a multi-granularity real-time hotspot aggregation method. Background technique [0002] The Internet produces a large amount of information all the time, among which valuable and high-volume information can be regarded as hot information. Traditional news media manually edit and publish these hot information to form news, so that people can keep abreast of real-time information. Information, to grasp the latest information. This method of artificially generating news can ensure the accuracy of the news, but it takes a lot of time and sacrifices the real-time and objectivity of the news in a certain sense. [0003] With the development and rise of modern artificial intelligence and natural language processing technology, a non-artificial hotspot event detection system that processes a large amount of streaming information text data has been developed, and machines are used inst...

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): G06F17/30G06F17/27
CPCG06F16/2471G06F16/248G06F16/287G06F16/9535G06F40/284G06F40/30
Inventor 李建欣李晨兰天张日崇彭浩
Owner BEIHANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com