Check patentability & draft patents in minutes with Patsnap Eureka AI!

Machine learning model training method, interference detection method and device

A machine learning model and training method technology, applied in the field of satellite navigation signal positioning, can solve problems such as difficult GNSS interference detection and difficult application, and achieve the effect of simple process and low acquisition cost

Pending Publication Date: 2022-03-29
ALIBABA GRP HLDG LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This technology uses an antenna array to track the incident direction of the signal. When it detects that all satellites are incident from the same direction, it means that there is an interference signal. This technology requires an antenna array, and it is difficult to apply to consumer electronics products such as mobile phones equipped with GNSS receivers.
[0008] To sum up, the above-mentioned technologies generally need to involve hardware transformation, and for hardware transformation of consumer electronic products equipped with GNSS receivers, on the one hand, there is a cost problem; on the other hand, there are many types of consumer electronic products, and there are differences in hardware. and software limitations, it is difficult to realize the detection of GNSS interference through the transformation of hardware and software

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
  • Machine learning model training method, interference detection method and device
  • Machine learning model training method, interference detection method and device
  • Machine learning model training method, interference detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0071] Embodiment 1 of the present application provides a training method of a machine learning model, the model is used to detect GNSS signal interference, and its training process is as follows figure 1 shown, including the following steps:

[0072] Step S11: Obtain a training sample set.

[0073] The sample set includes interference samples and normal samples, wherein an interference sample corresponds to a historical GNSS positioning point generated when the device is interfered by GNSS, and a normal sample corresponds to a historical GNSS positioning point generated when the device is not affected by GNSS interference.

[0074] Specifically, the GNSS positioning points in the above and subsequent introductions are positioning points obtained by using a satellite navigation positioning method. Taking the device as a mobile phone as an example, positioning points determined in different ways may be obtained from different network positioning interfaces, for example, GNSS p...

Embodiment 2

[0125] Embodiment 2 of the present application provides a method based on historical GNSS positioning point data to identify the GNSS positioning point generated when the device is interfered by GNSS, that is, the identification method of GNSS interference point. The process is as follows Figure 4 shown, including the following steps:

[0126] Step S41: From the historical GNSS positioning points generated in the same driving process of the same device, determine the GNSS interference positioning start point and the GNSS interference positioning end point.

[0127] Specifically, it may include determining the adjacent historical GNSS positioning points whose distance is greater than the set distance threshold to obtain at least two sets of positioning point pairs with position jumps; The historical GNSS positioning point is determined as the first point of GNSS interference positioning, and the previous historical GNSS positioning point of the next positioning point pair is d...

Embodiment 3

[0139] Embodiment 3 of the present application provides a method based on historical GNSS positioning point data to identify GNSS positioning points generated when GNSS interference occurs, that is, a method for identifying GNSS interference points. The process is as follows Figure 6 shown, including the following steps:

[0140] Step S61: Matching roads for the historical GNSS positioning points of the same trajectory, if the road matching of the consecutive historical GNSS positioning points exceeding the preset number fails, determine the historical GNSS positioning points of which the road matching fails as GNSS interference points.

[0141] If the road matching without historical GNSS positioning points fails, step S92 is executed.

[0142] Step S62: Judging whether there is a road segment that is not connected to other road segments among the obtained multiple road segments.

[0143] If yes, execute step S63; if not, execute step S64.

[0144] Step S63: Use the histor...

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 training method of a machine learning model, and an interference detection method and device. The training method of the machine learning model comprises the steps that a training sample set is acquired, the sample set comprises interference samples and normal samples, one interference sample corresponds to a historical GNSS positioning point generated when a device is subjected to GNSS interference, and one normal sample corresponds to a historical GNSS positioning point generated when the device is not subjected to GNSS interference; determining characteristic values of the samples according to positioning parameters of historical GNSS positioning points corresponding to the samples; and training a set machine learning model by using the training sample set of which the characteristic values are determined, so as to obtain a machine learning model for detecting GNSS signal interference. The signal interference detection model can be quickly and efficiently obtained, the accuracy of model detection is high, and the cost of model training and monitoring is low.

Description

technical field [0001] The present application relates to the technical field of satellite navigation signal positioning, in particular to a machine learning model training method, interference detection method and device. Background technique [0002] With the development of the civilian use of the Global Navigation Satellite System (GNSS), GNSS has brought great convenience to people's lives, especially in the field of travel. GNSS combined with electronic maps can provide users with map navigation, online car-hailing, etc. Various location-related services. [0003] At the same time, new problems have also appeared in civilian scenarios, such as GNSS interference, which will affect GNSS-based positioning, resulting in a decrease in positioning accuracy or failure to locate the position, thus affecting the realization of related location services. Therefore, the detection of GNSS interference becomes a problem that providers of related location services need to solve. ...

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): G01S19/21G06K9/62G06N20/20
CPCG01S19/21G06N20/20G06F18/22G06F18/214
Inventor 方兴杨永光罗雷刚王超刘宇
Owner ALIBABA GRP HLDG LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com