CrowdPlanner: A crowd-based route recommendation system

Abstract

Abstract-As travel is taking more significant part in our life, route recommendation service becomes a big business and attracts many major players in IT industry. Given a user specified origin and destination, a route recommendation service aims to provide users the routes with the best travelling experience according to criteria such as travelling distance, travelling time, traffic condition, etc. However, previous research shows that even the routes recommended by the big-thumb service providers can deviate significantly from the routes travelled by experienced drivers. It means travellers' preferences on route selection are influenced by many latent and dynamic factors that are hard to be modelled exactly with pre-defined formulas. In this work we approach this challenging problem with a completely different perspective -leveraging crowds' knowledge to improve the recommendation quality. In this light, CrowdPlanner -a novel crowd-based route recommendation system has been developed, which requests human workers to evaluate candidates routes recommended by different sources and methods, and determine the best route based on the feedbacks of these workers. Our system addresses two critical issues in its core components: a) task generation component generates a series of informative and concise questions with optimized ordering for a given candidate route set so that workers feel comfortable and easy to answer; and b) worker selection component utilizes a set of selection criteria and an efficient algorithm to find the most eligible workers to answer the questions with high accuracy.

Landmark-Based Route Recommendation with Crowd Intelligence

“…As route recommendation is a real-time task, the response time of waiting for workers may not be tolerable for users who want to plan the trips immediately. However, our preliminary work [26] neglects the power of reusing the answers of the previous tasks, which is beneficial to reduce the response time. Therefore, we propose a truth reusing component, which utilizes the existing truths from the previous tasks and return the recommended route to users.…”

“…Figure 1b demonstrates the recommended routes from different sources on map, where two routes recommended by WS are different from those by MPR and MFP, respectively. Going beyond the limitation of the route recommendation based on popular routes, our preliminary work [26] takes the emerging concept of crowdsourcing that explicitly leverages human knowledge to resolve complex problems. Specifically, a crowd-based route recommendation system which can effectively blend domain-expert knowledge for route recommendation is proposed.…”

MoTrIS

“…TransDec [6] is a realworld data-driven framework, which obtains data from sensors and analyzes the traffic conditions and historical trajectory data to improve the quality of the results. CrowdPlanner [11] also employs historical information and recommends routes by taking into consideration the preferences of the users. For transportation networks, Graphast [9] is a framework which enables processing of timedependent spatio-temporal network queries [3].…”

A personalized recommendation system for NetEase dating site

“…Recommending appropriate partners from a large amount of candidates becomes an interesting and challenging problem in the field of recommendation system [22,17,9,18,19,14].…”