Streaming data event text topic and detection system

A streaming data and detection system technology, applied in network data retrieval, other database retrieval, unstructured text data retrieval, etc., can solve problems affecting retrieval results, complex character reorganization, and users cannot accurately define, etc., to improve accuracy , clustering process balance, and the effect of improving capabilities

Inactive Publication Date: 2021-04-02
10TH RES INST OF CETC
View PDF17 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the evolution of spam content upgrades is too fast, complex character reorganization, special symbols, etc. make audit methods helpless
Traditional retrieval methods are based on the user's deep understanding of their own query needs. That is to say, users need to accurately express their query needs into query expressions when retrieving news information. This is the conversion of query needs into query expressions. Any deviation from will seriously affect the search results
In this type of retrieval needs, users cannot precisely define their own needs and can only describe them abstractly. This type of retrieval needs is difficult to satisfy by today's keyword-based search engines.

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
  • Streaming data event text topic and detection system
  • Streaming data event text topic and detection system
  • Streaming data event text topic and detection system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] refer to figure 1 , figure 2 . In the preferred embodiment described below, a topic or event stream text data detection system includes: a topic detection module that receives information streams, and a topic tracking module, an event identification module, and an event extraction module that are serially connected in series to connect topic The association detection module of the tracking module and the text summarization module for exchanging information with the topic tracking module and the event identification module are characterized in that: the topic detection module independently analyzes the content of the report without specifying the topic and event background information as a reference Content, adjudicating whether two reports or two sets of reports belong to the same topic or event, designing a social media streaming text information processing system, constructing a topic and event detection algorithm model; detecting information without prior knowledge...

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 streaming data event text topic and a detection system, intermediate process redundancy can be eliminated, and the detection time can be reduced. According to the technical scheme, the system is characterized in that a topic detection module constructs a topic and event detection algorithm model, and text data is crawled from all large network media and social platforms in real time through the crawler technology; a topic tracking module gives a topic abstract and keyword information according to the text abstract information provided by a text abstract module; an association detection module detects texts in all directions, divides event affiliation of the texts, sets a time window with a determined length, sends a detected topic clustering result to the topic tracking module to obtain a clustering result with smaller granularity; and an event recognition module carries out event recognition in a hierarchical clustering mode, gives a designed topic abstract and event extraction algorithm and sends the topic abstract and keyword information to an event extraction module, and key information of the topic and event is analyzed, and a large number of topic sets are obtained.

Description

technical field [0001] The invention belongs to the technical field of topic detection and tracking, event detection and extraction, and in particular relates to a topic and event detection system for streaming text data. Background technique [0002] In recent years, with the rapid development of the Internet and the Internet of Things, a large amount of information is generated on the Internet every day, and the large amount of information on the Internet is exploding. It is becoming more and more difficult for people to quickly and accurately retrieve high-quality information from the Internet. Useful news information, and these massive data will appear in many applications, and a large part of this data exists in the form of streaming data. Streaming data is characterized by fast, large volume, disorder, and requires fast response. All kinds of emergencies occur frequently at home and abroad. News websites and social platforms are the most direct and fastest way for peo...

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): G06F16/31G06F16/35G06F16/34G06F16/951
CPCG06F16/313G06F16/353G06F16/345G06F16/951
Inventor 庄旭袁鑫贾莹尹可鑫张乾君
Owner 10TH RES INST OF CETC
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