GNSS positioning service-oriented fault treatment system and method

A positioning service and fault technology, applied in the field of fault management systems for GNSS positioning services, can solve problems such as loss, complex analysis latitude, business and user experience risks, and achieve the effect of improving efficiency

Active Publication Date: 2020-05-12
QIANXUN SPATIAL INTELLIGENCE INC
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The difficulty of guaranteeing the availability of GNSS real-time dynamic positioning services based on the Internet and cloud computing architecture lies in the long front-end and back-end technology chains and the complex analysis latitude. time, causing risk or loss to business and user experience

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
  • GNSS positioning service-oriented fault treatment system and method
  • GNSS positioning service-oriented fault treatment system and method
  • GNSS positioning service-oriented fault treatment system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] The present invention provides a fault management system based on machine learning for GNSS positioning services, such as figure 1 As shown, the system is divided into (data) access layer, (data) processing layer, (analysis) engine layer, platform (control) layer, and application layer from bottom to top.

[0047] Access layer: responsible for the collection, storage and access of metadata. Metadata refers to the end-to-end operation and maintenance index data covering from the base station network to the algorithm platform and even the end user terminal. The data types include log / metric / agent, etc. ;

[0048] Processing layer: perform data processing operations such as distribution scheduling, cleaning, conversion, and rule aggregation on the data collected by the access layer, and provide offline analysis or real-time streaming computing services based on big data for the engine layer to directly call on demand, while No need for preprocessing to improve efficiency;...

Embodiment 2

[0066] The present invention also provides a fault management method based on machine learning for GNSS positioning services, such as figure 2 shown, including the following steps:

[0067] Step 1, log data collection and aggregation, specifically includes:

[0068] In step 1.1, the data log gateway preliminarily processes the log data collected from the base station, platform system, algorithm, and user, and stores them in the log database synchronously in real time. Among them, the reference station data is the result log generated by the analysis of GNSS data quality analysis tools, including base stations, satellites, and satellite frequency points. The system platform is mainly the application process of the GNSS broadcast platform and the operation log of the underlying basic system. Algorithm logs include ionospheric delay, STD (standard deviation), and baseline networking (satellite rejection) information. The user layer is mainly client information such as network...

Embodiment 3

[0076] The present invention also provides a memory, the memory stores a computer program, and the computer program performs the following steps:

[0077]The access layer collects, stores, and accesses metadata, which includes user-side data and server-side data, and the processing layer processes the metadata collected by the access layer, and provides services based on offline computing or real-time streaming computing results ;

[0078] The engine layer analyzes the offline calculation results, develops and debugs the algorithm model, evaluates the effect of the algorithm model, publishes the verified algorithm model to the algorithm warehouse, and generates Rule judgment engine; the monitoring and alarm platform triggers the rule judgment engine and algorithm warehouse to perform analysis tasks, and the analysis results enter the result comparison module for scoring;

[0079] The result comparison module outputs the analysis results downwards, displays them to users throu...

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 GNSS positioning service-oriented fault treatment system and method, and the system comprises an access layer which is used for collecting, storing and accessing metadata which comprises the data of a user side and the data of a server side; a processing layer which is used for processing the metadata acquired by the access layer and providing services based on offline calculation or real-time streaming calculation results; an engine layer which is used for carrying out analysis according to the offline calculation result, developing a debugging algorithm model, evaluating the effect of the algorithm model and issuing the algorithm model passing the verification to an algorithm warehouse; a platform layer which is used for controlling the fault treatment system, managing the access layer, the processing layer and the engine layer; and an application layer which is used for calling the algorithm model in the algorithm warehouse according to the application sceneand displaying a calculation result of the algorithm model to the user. According to the invention, reasons and problem nodes of service exception can be accurately positioned, and the efficiency ofservice quality problem discovery and disposal is improved.

Description

technical field [0001] The invention relates to the technical field of positioning service fault management, in particular to a fault management system and method for GNSS positioning service. Background technique [0002] Anomaly detection algorithm based on machine learning: Many algorithms for anomaly detection are based on KPI trend prediction, and some algorithms are based on machine learning, and machine learning algorithms need to be marked. Labeling will bring a lot of overhead to operation and maintenance personnel, so can we do some work to reduce the overhead of labeling? This includes finding similar anomalies. After the operation and maintenance personnel mark an anomaly, the machine learning algorithm can automatically find similar and related anomalies. [0003] The definition of anomaly detection is that for a KPI curve that changes periodically over time, it can quickly and accurately alarm when an abnormality occurs. Its common algorithms are: window-based...

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): G06F11/07
CPCG06F11/0751G06F11/079
Inventor 俞烁
Owner QIANXUN SPATIAL INTELLIGENCE INC
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