Indoor Survey Data Collection

Patent metadata

Field	Value
Publication number	US-2020349145-A1
Application number	US-201916402450-A
Country	US
Kind code	A1
Filing date	May 3, 2019
Priority date	May 3, 2019
Publication date	Nov 5, 2020
Grant date	—

Abstract

In an approach for an indoor survey data collection, a processor generates reference points based on a site map and an accuracy requirement. A processor collects data at each reference point through a data collecting agent. A processor detects an outlier at the reference points using a feedback from the data collecting agent during the data collection and a database. A processor eliminates the detected outlier and rectifies the data.

First claim

What is claimed is:

1 . A method comprising:
generating, by one or more processors, reference points based on a site map and an accuracy requirement; collecting, by one or more processors, data at each reference point through a data collecting agent; detecting, by one or more processors, an outlier at the reference points using a feedback from the data collecting agent during the data collection and a database; and eliminating, by one or more processors, the detected outlier and rectifying, by one or more processors, the data.

2 . The method of claim 1 , further comprising identifying and rectifying, by one or more processors, an erroneous action of the data collecting agent by using data characteristics and the feedback from the data collecting agent.

3 . The method of claim 1 , further comprising validating, by one or more processors, the data after the data is collected from the reference points.

4 . The method of claim 1 , further comprising re-calibrating, by one or more processors, the reference points based on the data and the feedback from the data collecting agent.

5 . The method of claim 4 , wherein re-calibrating the reference points includes performing a re-survey of a problematic reference point and adaptively changing a minimum distance between the reference points.

6 . The method of claim 1 , wherein detecting an outlier includes using a propagation model which is built with obstacle and location information.

7 . The method of claim 1 , wherein detecting an outlier includes using historical data from a machine learning model.

8 . The method of claim 7 , wherein the data is a Wi-Fi fingerprinting data.

9 . A computer program product for an indoor survey data collection, the computer program product comprising:
one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions comprising: program instructions to generate reference points based on a site map and an accuracy requirement; program instructions to collect data at each reference point through a data collecting agent; program instructions to detect an outlier at the reference points using a feedback from the data collecting agent during the data collection and a database; and program instructions to eliminate the detected outlier and rectify the data.

10 . The computer program product of claim 9 , further comprising:
program instructions, stored on the one or more computer readable storage media, to identify and rectify an erroneous action of the data collecting agent using data characteristics and the feedback from the data collecting agent.

11 . The computer program product of claim 9 , further comprising:
program instructions, stored on the one or more computer readable storage media, to validate the data after the data is collected from the reference points.

12 . The computer program product of claim 9 , further comprising:
program instructions, stored on the one or more computer readable storage media, to re-calibrate the reference points based on the data and the feedback from the data collecting agent.

13 . The computer program product of claim 12 , wherein program instructions to re-calibrate the reference points comprise:
program instructions to perform a re-survey of a problematic reference point and adaptively change a minimum distance between the reference points.

14 . The computer program product of claim 9 , program instructions to detect an outlier comprise:
program instructions to use historical data from a machine learning model based on a Wi-Fi fingerprinting process and nature of Wi-Fi signals.

15 . A computer system for an indoor survey data collection, the computer system comprising:
one or more computer processors, one or more computer readable storage media, and program instructions stored on the computer readable storage media for execution by at least one of the one or more processors, the program instructions comprising: program instructions to generate reference points based on a site map and an accuracy requirement; program instructions to collect data at each reference point through a data collecting agent; program instructions to detect an outlier at the reference points using a feedback from the data collecting agent during the data collection and a database; and program instructions to eliminate the detected outlier and rectify the data.

16 . The computer system of claim 15 , further comprising:
program instructions, stored on the one or more computer readable storage media, to identify and rectify an erroneous action of the data collecting agent using data characteristics and the feedback from the data collecting agent.

17 . The computer system of claim 15 , further comprising:
program instructions, stored on the one or more computer readable storage media, to validate the data after the data is collected from the reference points.

18 . The computer system of claim 15 , further comprising:
program instructions, stored on the one or more computer readable storage media, to re-calibrate the reference points based on the data and the feedback from the data collecting agent.

19 . The computer system of claim 18 , wherein program instructions to re-calibrate the reference points comprise:
program instructions to perform a re-survey of a problematic reference point and adaptively change a minimum distance between the reference points.

20 . The computer system of claim 15 , wherein program instructions to detect an outlier comprise:
program instructions, stored on the one or more computer readable storage media, to use historical data from a machine learning model based on a Wi-Fi fingerprinting process and nature of Wi-Fi signals.

Assignees

• IBM

Inventors

• Sajja Surya Shravan Kumar
• Sree Prakash Ashok Pon Kumar
• Singhee Amith
• Dwivedi Satyam

Classifications

• G06N20/10

  using kernel methods, e.g. support vector machines [SVM] · CPC title

• G06F16/9537 Primary

  Spatial or temporal dependent retrieval, e.g. spatiotemporal queries · CPC title

• G06F16/906

  Clustering; Classification · CPC title

• G06F16/2365 Primary

  Ensuring data consistency and integrity · CPC title

• G06N20/00

  Machine learning · CPC title