Real-World Large-Scale Cellular Localization for Pickup Position Recommendation at Black-Hole Article

Gao, R, Zhu, S, Li, L et al. (2024). Real-World Large-Scale Cellular Localization for Pickup Position Recommendation at Black-Hole . IEEE TRANSACTIONS ON MOBILE COMPUTING, 23(12), 15114-15131. 10.1109/TMC.2024.3453596

cited authors

  • Gao, R; Zhu, S; Li, L; Wang, X; Jiang, Y; Tan, N; Chai, H; Qi, P; Liu, J; Tao, D

authors

abstract

  • Indoor localization availability is still sporadic in industry, especially at the black-hole, i.e., there only exist cellular signals, no GPS or WiFi signals. Based on our 2-year observations at the DiDi ride-hailing platform in China, there are 68k orders everyday created at black-hole. In this paper, we present TransparentLoc, a large-scale cellular localization system for pickup position recommendation of the DiDi platform. Specifically, we design a CNN model for real-time localization based on a crowdsourcing fingerprint set constructed by outdoor trajectories and abnormal cell tower detection. Then we leverage a DeepFM model to recommend an optimal pickup position for passengers. We share our 2-year experience with 50 million orders across 13 million devices in 4541 cities to address practical challenges including sparse cell towers, unbalanced user fingerprints, temporal variations, and abnormal cell towers in terms of four major service metrics, i.e., pickup position error, over-30-meters ratio, cancel ratio, and call ratio. The large-scale evaluations show that our system achieves a 0.54m lower median pickup position error compared to the iOS built-in cellular localization system, regardless of environmental changes, smartphone brands/models, time, and cellular providers. Additionally, the over-30-meters ratio, cancel ratio, and call ratio have significant reductions of 0.88%, 0.88%, and 5.13%, respectively.

publication date

  • January 1, 2024

published in

Digital Object Identifier (DOI)

start page

  • 15114

end page

  • 15131

volume

  • 23

issue

  • 12