End-to-end sea-air activity target data rule real-time mining method

A technology of activity goals and laws, applied in the field of end-to-end activity law mining technology, can solve problems such as scattered and complex technology, and achieve the effect of satisfying results, simple implementation principles, and easy engineering implementation.

Active Publication Date: 2021-06-29
10TH RES INST OF CETC
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In order to further improve the intelligence and completeness of target activity law mining, the present invention provides a more concise, intelligent and complete End-to-end real-time mining method of target activity data in sea area, which is beneficial to follow-up target behavior analysis and alarm related work

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
  • End-to-end sea-air activity target data rule real-time mining method
  • End-to-end sea-air activity target data rule real-time mining method
  • End-to-end sea-air activity target data rule real-time mining method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] refer to figure 1 . According to the present invention, firstly, the excavated end-to-end sea area target activity rule data is divided into known targets and unknown targets, and the target is analyzed in multiple dimensions such as time, space, time and space, route, coordination, loading, and supply. The end-to-end sea area target activity law mining data and identity identification are unified in a complete framework, and a unified sea area target activity data law mining framework is constructed, and the sea area target data information is sent to the sea area target activity data law mining framework. The relevant implementation details of the exposed input and output are encapsulated; the sea area target activity data law mining framework determines the target identity according to the target state information, directly mines the known target activity law data, and uses the convolutional network model to create a target identification module. The target identific...

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

According to the end-to-end sea-air activity target data rule real-time mining method disclosed by the invention, automatic discrimination and hidden rule discovery of an unknown target can be completed through end-to-end mining from target input to multiple activity rule output. The method is realized through the following technical scheme: firstly, sea area target activity rule data is divided into a known target and an unknown target, and end-to-end sea area target activity rule mining data and identity identification are unified in a complete sea area target activity data rule framework; a set of unified sea area target activity data rule mining framework is constructed, known target activity rule data is directly mined, meanwhile, a target recognition module is created by adopting a convolutional network model, target recognition is performed on unknown target activity rule data by utilizing a dynamic time warping algorithm and classical track information, and unknown target identities are judged online, then real-time end-to-end mining is performed on the activity rule data of the target multi-dimensional information, and a mining result as an activity rule is outputted.

Description

technical field [0001] The invention relates to law mining technology in many information processing fields such as data mining and pattern recognition, and in particular relates to an end-to-end activity law mining technology. Background technique [0002] With the rapid development of information technology and the introduction of new generation information technologies such as "Internet of Things" and "Cloud Computing", big data has gradually been widely disseminated, linking the real world with the network world and realizing the exponential growth of data. Data mining is a product of the information age, and data mining is the process of mining interesting patterns and knowledge from large amounts of data. Data mining is a new discipline that meets the needs of extracting information from massive data in the information society. It is the intersection of statistics, machine learning, database, pattern recognition, artificial intelligence and other disciplines, and it p...

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): G06F16/26G06F16/28G06N3/04G06N3/08
CPCG06F16/26G06F16/285G06N3/08G06N3/044G06N3/045
Inventor 廖泓舟代翔崔莹戴礼灿丁洪丽陈伟晴
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap