• Journal of Geo-information Science
  • Vol. 22, Issue 1, 136 (2020)
Zhixiang FANG1、1、*, Yaqian NI2、2, and Shouqian HUANG1、1
Author Affiliations
  • 1State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China
  • 1武汉大学测绘遥感信息工程国家重点实验室,武汉 430079
  • 2Autonavi Holdings Limited, Beijing 102200, China
  • 2高德软件有限公司,北京 102200
  • show less
    DOI: 10.12082/dqxxkx.2020.190655 Cite this Article
    Zhixiang FANG, Yaqian NI, Shouqian HUANG. Mobile Phone User Stay Behavior Prediction Method Considering Mobile APP Usage Characterization[J]. Journal of Geo-information Science, 2020, 22(1): 136 Copy Citation Text show less
    Basic procedures of the individual stay behavior prediction method
    Fig. 1. Basic procedures of the individual stay behavior prediction method
    The example of individual stay behavior
    Fig. 2. The example of individual stay behavior
    Number of location update records for mobile users from Aug.10, 2015 to Aug.29, 2015
    Fig. 3. Number of location update records for mobile users from Aug.10, 2015 to Aug.29, 2015
    The prediction accuracy distribution of mobile phone user stay behavior
    Fig. 4. The prediction accuracy distribution of mobile phone user stay behavior
    Comparison of mobile phone user stay behavior prediction results with different feature sets
    Fig. 5. Comparison of mobile phone user stay behavior prediction results with different feature sets
    The chi-square value of the top20 stay behavior prediction features
    Fig. 6. The chi-square value of the top20 stay behavior prediction features
    用户ID日期时间事件类型基站编号基站经度/°基站纬度/°
    58****20YY-MM-DD07:30111**115.****29.****
    58****20YY-MM-DD08:30511**115.****29.****
    3
    58****20YY-MM-DD21:30410**115.****29.****
    58****20YY-MM-DD22:301011**115.****29.****
    Table 1. The examples of one user′s mobile phone location update data records
    用户ID归属地日期时间基站编号经度/°纬度/°APP流量/G
    58***HB.WH20YY-MM-DD07:3211**115.***29.***高德地图0.0016
    58***\N20YY-MM-DD08:3211**115.***29.***微信0.0092
    58***\N20YY-MM-DD09:2712**115.***29.***QQ0.0242
    58***\N20YY-MM-DD21:0610**115.***29.***微信0.0016
    58***\N20YY-MM-DD21:3411**115.***29.**新浪新闻0.0554
    Table 2. The examples of one user′s Internet traffic data records
    时段移动/%停留/%无法识别/%
    614.5152.4133.08
    724.9349.9925.07
    831.6649.8718.46
    933.0049.5717.43
    1032.6049.7717.63
    1131.7949.8118.40
    1230.7550.1619.09
    1327.1651.3621.48
    1428.4151.0620.54
    1528.2350.9620.81
    1628.3350.3021.37
    1729.5949.1021.31
    1830.9747.3021.73
    1929.3750.1620.47
    2027.3351.4621.20
    2122.6852.6024.72
    Table 3. The statistics of mobile phone user stay behavior from Aug.10, 2015 to Aug.29, 2015
    地点识别率/%
    78.53
    工作地47.06
    同时识别率40.09
    Table 4. The recognition rate of mobile phone users' home and work location from Aug.10, 2015 to Aug.29, 2015
    预测模型准确率/%运行时间/s参数设置
    本文模型80.310.141
    SVM77.353.996kernel='linear' probability=True
    GBDT76.131.940n_estimators=200
    RF81.540.960n_estimators=200
    一阶Markov71.75-
    MostValue69.45-
    Table 5. Comparison of mobile phone user stay behavior prediction effects between different prediction algorithms
    Zhixiang FANG, Yaqian NI, Shouqian HUANG. Mobile Phone User Stay Behavior Prediction Method Considering Mobile APP Usage Characterization[J]. Journal of Geo-information Science, 2020, 22(1): 136
    Download Citation