Tourist route customization method and system based on deep reinforcement learning

A technology of reinforcement learning and travel routes, which is applied in the field of travel route customization methods and systems based on deep reinforcement learning, can solve problems such as ignoring the optimization of POIs sightseeing time and ignoring the real preferences of POIs, so as to improve satisfaction, experience, and convenience The effect of the service

Pending Publication Date: 2022-03-29
XI AN JIAOTONG UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Existing mainstream methods are various heuristics, mainly focusing on selecting and ranking POIs, but ignoring the optimization of the sightseeing time spent on each POIs, and also ignoring the real traffic and real preferences of tourists for POIs

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Tourist route customization method and system based on deep reinforcement learning
  • Tourist route customization method and system based on deep reinforcement learning
  • Tourist route customization method and system based on deep reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0103] To realize the customization of travel routes based on deep reinforcement learning, the specific process is as follows:

[0104] Step 1, using crawler technology to crawl 64 hotels and 64 scenic spots in Beijing from TripAdvisor.com, Ctrip.com, Meituan.com, Baike.baidu.com and Amap.com in December 2018, POI attribute information, tourists Data related to review information and traffic information. POI attribute information includes POI name, geographical location, tour duration, and business hours; tourist comment information includes tourist ID, play type, comment time, rating, and comment text; traffic information mainly includes self-driving time and bus time between two points.

[0105] Step 2. By analyzing tourist comment information, construct tourist portraits and mine tourist preference scores. The tourist preference score is mined from three aspects: situational factors, review texts and ratings, taking into account the situational factor of tourist type. Sin...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a travel route customization method and system based on deep reinforcement learning. The method comprises the steps of mining historical preference scores of tourists according to hotel, scenic spot and traffic data; a route optimization framework based on a deep reinforcement learning algorithm; obtaining tourist demands, and generating an intelligent and customized route; the route is dynamically updated based on the real-time scene change of the tourist; according to the method, intelligent and customized routes including the hotels and the scenic spots can be quickly obtained, more diversified and convenient services are provided for tourists, and the time for the tourists to select the hotels and the scenic spots and plan the routes is saved; the environment is a tourism environment where tourists are located actually, the tourism environment comprises POI information and tourist input information, routes are generated according to historical preferences and demands of the tourists, and the design requirements of individuation and customization of the tourists can be met; according to the real tourism path of the tourist, the route is dynamically and intelligently planned, and the optimization model is further learned, so that the satisfaction and experience of the tourist can be improved.

Description

technical field [0001] The invention belongs to the field of travel route customization, and specifically relates to a method and system for customizing travel routes based on deep reinforcement learning. Background technique [0002] As an important part of the modern service industry, tourism has gradually become one of the most important economic driving forces in the world. With the popularity of tourism, the behavior of tourists has also undergone great changes, and tourists increasingly prefer "customized tours" and "self-drive tours" instead of pre-organized routes or standard travel packages. [0003] The customized tourist itinerary problem is called the "tourist itinerary design problem", and its purpose is to design tourist itineraries for tourists by maximizing their total preference score according to their constraints. Existing customized tour itineraries pay relatively little attention to hotel selection, which is, however, an important part of multi-day tour...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06Q10/04G06Q50/14G06N3/04G06N3/08
CPCG06Q10/047G06Q50/14G06N3/08G06N3/044
Inventor 赵玺刘佳璠王乐李雨航
Owner XI AN JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products