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

System and method for collecting and feeding back massive sensor data

A technology of data collection and data processing engine, which is applied in the field of massive sensor data collection, processing and feedback, which can solve the problems of small test data, inability to effectively use scene recognition and historical parameters, inaccurate response models, etc., to ensure reliability and the effect of high efficiency

Active Publication Date: 2018-04-20
QIANXUN SPATIAL INTELLIGENCE INC
View PDF8 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Its disadvantages include: the equipment that can be used for model parameter learning is only test equipment, the amount of test data processed is small, and the model cannot be accurately reflected; after the model parameters are determined, it is difficult to optimize the parameters and change the model parameters through data accumulation; it cannot be effective Leverage contextual recognition and historical parameters

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
  • System and method for collecting and feeding back massive sensor data
  • System and method for collecting and feeding back massive sensor data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Reliable model parameters need to be obtained by processing massive data. The present invention collects multi-source data through a loosely defined sensor data collection interface; uses distributed storage and distributed computing to process massive data for machine learning algorithms; provides flexible parameter feedback links Solve the above-mentioned shortcomings. Due to the use of crowdsourcing to collect data, the problem of small test data set and too few devices can be avoided, model parameters can be dynamically updated, and multi-source data can be used to enhance the ability of scene recognition, and ultimately improve DR performance.

[0023] Hereinafter, the present invention will be further described in conjunction with the drawings and embodiments.

[0024] figure 1 and figure 2 Respectively, the system architecture diagram and method flow chart of mass sensor data collection processing and feedback of the present invention are as follows:

[0025]...

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 system and method for collecting and feeding back massive sensor data. The method comprises the following steps of: collecting data and a request uploaded by a sensor by a sensor data uploading interface and distributing the data and the request to a gateway; forwarding the request to a service processing node cluster by the gateway; processing the data by the service processing node cluster, and distributing the data and the request into a message queue and a log service; sending the collected data and request into a distributed file system by the message queue and the log service, and sending the collected data and request to an online data processing engine; receiving the data sent by the message queue and the log service by the online data processing engine, carrying out real-time screening and processing on the data to obtain local optimum model parameters and sending the local optimum model parameters to a model verification component; storing massive data by the distributed file system, processing the massive data stored in the distributed file system by an offline data processing engine so as to obtain global optimum model parameters and sending theglobal optimum model parameters to the model verification component; and scheduling the online data processing engine and the offline data processing engine by a scheduling engine.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a system and method for collecting, processing and feeding back massive sensor data. Background technique [0002] DR (Dead Reckoning, dead reckoning, also called inertial navigation, referred to as inertial navigation) can do dead reckoning when the GPS (Global Positioning System, Global Positioning System) signal is poor, and repair GPS positioning deviation within a certain distance. Model the data output by sensor devices (such as gyroscopes, accelerometers, barometers, etc.), scene types (on elevated roads, in tunnels, next to dense buildings), user estimation history, etc., and model estimation accuracy errors will diverge over time Until it is unavailable, when the model is determined, the change of model parameters will affect the performance of the model. Good model parameters can effectively improve the performance of DR calculation, that is, prolong the reliabl...

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): G06F17/30
CPCG06F16/182
Inventor 丁源熊
Owner QIANXUN SPATIAL INTELLIGENCE INC
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