End-to-end sparse trajectory recovery method based on road network

The innovative solution addresses the inefficiency of existing trajectory recovery methods by integrating a generative adversarial network (GAN) framework that integrates the trajectory recovery and the accuracy of the map matching process, thereby enhancing the performance of location-based services.

CN119251525APending Publication Date: 2025-01-03TONGJI UNIV
View PDF 0 Cites 4 Cited by

Patent Information

Application Number
CN202411280152.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-12
Publication Date
2025-01-03

AI Technical Summary

Technical Problem

Existing trajectory recovery methods are computationally expensive and fail to fully utilize the intrinsic relationship between trajectory data and the road network, leading to performance degradation in location-based services due to sparse and incomplete trajectories.

Method used

An end-to-end sparse trajectory recovery method using a generative adversarial network (GAN) framework that integrates trajectory recovery and map matching, optimizing generator parameters to balance trajectory integrity and accuracy, incorporating road network constraints through a Seq2Seq architecture with a graph network and LSTM discriminator.

Benefits of technology

Improves trajectory recovery accuracy and significantly reduces computational time by fusing trajectory recovery and map matching, leveraging deep learning technology to enhance the performance of LBS applications.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119251525A_ABST
    Figure CN119251525A_ABST
Patent Text Reader

Abstract

The invention relates to a deep learning algorithm, and provides an end-to-end sparse trajectory recovery method based on a road network, which is realized based on a framework of a generator and a discriminator, and is characterized in that the generator recovers an input sparse trajectory into a complete trajectory with a high sampling rate; the discriminator evaluates the authenticity of the input track and is used for guiding the generator to update parameters; the fusion of trajectory recovery and map matching is realized in an end-to-end manner through a deep learning technology, and parameter updating of a generator is optimized through a GAN (Generative Adversarial Network) framework, so that the balance between the completeness of the recovered trajectory and the accuracy of single-step interpolation is realized. According to the invention, the precision and speed of track recovery can be obviously improved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Cited By

  • City-level large-scale crowd activity track generation method based on mobile phone signaling

    CN119922491A

  • Urban vehicle personalized path planning method and system based on adversarial inverse reinforcement learning

    CN120373586A

  • A method and system for personalized urban vehicle path planning based on adversarial inverse reinforcement learning

    CN120373586B

  • Aeromagnetic data noise reduction method of noise reduction auto-encoder based on adversarial regularization

    CN122045597A