RESIDENCE POINT EXTRACTION METHOD, RESIDENCE POINT EXTRACTION DEVICE AND RESIDENCE POINT EXTRACTION PROGRAM

PROBLEM TO BE SOLVED: To improve extraction accuracy of extracting a residence point where a user stopped.SOLUTION: A positioning data extraction part 12 uses a positioning error included in each positioning data acquired from a positioning data DB 11 for calculating positioning accuracy of each pos...

Full description

Saved in:
Bibliographic Details
Main Authors TODA HIROYUKI, WASHISAKI SEIJI, KAZUHARA YOSHIHIKO, ITO ATSUSHI
Format Patent
LanguageEnglish
Japanese
Published 28.09.2015
Subjects
CALCULATING
COMPUTING
COUNTING
DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES
PHYSICS
SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR
Online AccessGet full text

Cover

More Information
Summary:PROBLEM TO BE SOLVED: To improve extraction accuracy of extracting a residence point where a user stopped.SOLUTION: A positioning data extraction part 12 uses a positioning error included in each positioning data acquired from a positioning data DB 11 for calculating positioning accuracy of each positioning data. A positioning data interpolation part 13 adds new positioning data between pieces of positioning data whose positioning time interval is longer than a positioning time interval threshold and a space between positioning points is smaller than a positioning distance interval threshold. A residence point extraction part 14 performs clustering of each positioning point in each positioning data, acquire plural positioning points included in constant radius from an object cluster and in constant time, calculates a centroid with weighting in which positioning accuracy is added as weighting, using the positioning accuracy of these plural positioning points and positioning data, sets the centroid with weighting as a center of the object cluster, and extracts the center as the residence point of the user. 【課題】ユーザが留まった滞留点の抽出精度を改善すること。【解決手段】測位データ抽出部１２が、測位データＤＢ１１から取得した各測位データにそれぞれ含まれる測位誤差を用いて各測位データの測位精度をそれぞれ算出し、測位データ補間部１３が、測位時間間隔が測位時間間隔閾値より大きく、かつ、測位点間が測位距離間隔閾値より小さい測位データ間に新たな測位データを追加し、滞留点抽出部１４が、各測位データにおける各測位点をそれぞれクラスタとし、対象クラスタから一定半径以内かつ一定時間以内に含まれる複数の測位点を取得し、それら複数の測位点の測位精度および測位データを用いて測位精度を重みとする重み付き重心を算出し、その重み付き重心を対象クラスタの中心点とし、その中心点をユーザの滞留点として抽出する。【選択図】図１
Bibliography:Application Number: JP20140047201