Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
DESTINATION RECOMMENDATION METHOD AND SYSTEM BASED ON MULTI-SOURCE HETEROGENEOUS INFORMATION NETWORK
Document Type and Number:
WIPO Patent Application WO/2023/178608
Kind Code:
A1
Abstract:
A destination recommendation method and system based on a multi-source heterogeneous information network. The system comprises a data preprocessing module, a multi-source information fusion module, and a heterogeneous neural network recommendation module. The data preprocessing module comprises a data acquisition module and a data cleaning module to acquire data of a vehicle driving state from a private vehicle OBD interface and vehicle trajectory information from a GPS interface, and detect and clean an anomaly. Multi-source information fusion comprises trajectory temporal-spatial information processing and a metapath-based heterogeneous graph construction scheme, wherein geographic information and semantic information of a trajectory are combined, and a structured spatial feature is modeled by constructing a multi-metapath. The heterogeneous neural network recommendation module comprises an aggregation module and a dynamic interaction module to mine potential user interactions and analyze a destination preference of a user by using a dynamic heterogeneous network. By analyzing a travel trajectory of a user, relatively accurate destination recommendation can be carried out for the user, and a result is pushed to a user terminal.

Inventors:
CHEN HONGYANG (CN)
FANG HUI (CN)
XIAO ZHU (CN)
Application Number:
PCT/CN2022/082799
Publication Date:
September 28, 2023
Filing Date:
March 24, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
ZHEIJIANG LAB (CN)
International Classes:
G06F16/29
Foreign References:
CN109425355A2019-03-05
CN113505310A2021-10-15
CN104731963A2015-06-24
CN111831897A2020-10-27
US20210380095A12021-12-09
Attorney, Agent or Firm:
HANGZHOU QIUSHI PATENT OFFICE CO.. LTD. (CN)
Download PDF: