توسعه يك سامانه همراه توصيه گر و برنامه ريزي مسير براي گردشگرهاي انفرادي

Developing a Mobile Recommender System and Tour Planner for Individual Tourists

با ظهور پديده ­اي جديد در حوزه گردشگري با نام گردشگر انفرادي، توسعه سامانه­اي همراه به‌منظور توصيه افراد مشابه به يكديگر باهدف بازديد از مناطق ديدني به‌صورت مشترك ضروري است. اين سامانه مي­تواند به گردشگراني كه به‌صورت انفرادي سفر مي­كنند كمك كند تا با به اشتراك­ گذاري گردش­هاي خود، از سفرشان بيشتر لذت ببرند. همچنين معمولاً گردشگران با مسيرهاي مقصد گردشگري خود آشنا نيستند و يك برنامه ريز مسير باهدف ارائه مسير به‌صورت جداگانه به هر گردشگر در يك سفر اشتراكي، مي­تواند بسيار سودمند واقع شود. هدف اين مقاله طراحي، توسعه، اجرا و ارزيابي يك سامانه­ي همراه است كه امكان توصيه­ گردشگر­هاي مشابه به يكديگر و برنامه ­ريزي گشت­هاي تفريحي مشترك بر اساس موقعيت­هاي جغرافيايي مختلف آن­ها را ميسر مي­كند. همراه بودن اين سامانه تأثير بسزايي در عملكرد آن به ­خصوص در هنگام ناوبري مي­گذارد. اين سامانه از يك سيستم توصيه­ گر مبتني بر فيلتر جمعيت ­شناسي به‌منظور توصيه گردشگر­هاي مشابه به يكديگر استفاده مي­كند. همچنين الگوريتم مورچه كه يكي از الگوريتم­هاي مشهور هوش مصنوعي است به‌منظور برنامه ­ريزي مسير در اين سامانه مورداستفاده قرارگرفته است. به‌منظور ارزيابي سيستم­ توصيه ­گر اين سامانه، تعدادي پرسشنامه ميان افراد مختلف توزيع شد. همچنين براي ارزيابي الگوريتم برنامه ­ريز مسير، از الگوريتم ژنتيك براي بررسي ميزان دقت و صحت الگوريتم استفاده شد. نتايج ارزيابي مشخص‌كننده ميانگين تفاوت 2/0 بين عملكرد سيستم توصيه­ گر و نتايج حاصل از پرسشنامه بود كه عملكرد مناسب سيستم توصيه­ گر را نشان مي­دهد. الگوريتم برنامه­ريز مسير نيز به كمينه مقدار تابع هدف با انحراف معيار 61/0 دست پيدا مي­كند كه نشان­دهنده دقت بالاي اين الگوريتم است اما الگوريتم ژنتيك با ميانگين مقادير 32/34 صحيح­تر از اين الگوريتم عمل مي­كند.

Nowadays, tourists are planning trips by their own using the available services on the web. Travelling individually does not have the pleasure of group tours, so some tourists decide to find similar friends on their destination to share the joy of tours and trips. Also, they may not be familiar with the routes available in the city. In this paper, a mobile application is designed, developed, implemented and evaluated to recommend similar tourists to each other and generate optimal route based for each individual. This system is integrating mobile GIS, recommender systems and artificial intelligence tour planning algorithms into a single application. Being on a mobile platform is necessary, especially for navigation and tour planning systems. User may have to carry his cellphone in order to follow the suggested tour. The recommender system is a demographic filtering recommender to find the similar tourists. It considers age, nationality, education and interest to find the proper matches. After suggesting similar tourists to each other, one of the versions of Ant Colony Optimization namely Ant System is used to plan the optimal tours for each individual. This problem can be defined as a new version of Multiple Travelling Salesman Problem with mutual nodes to visit simultaneously. Different tourists decide to share a tour that stay in different places. This system should find a proper sequence of sightsees to minimize the length of the tour and also it should maximize the number of mutual streets in a tour to let tourists travel together during the tour. The objective function is to minimize the sum of the distances each tourist traversed and to maximize the number of mutual streets with a proper POI sequence. Maximizing number of mutual streets was considered because tourists want to travel as a group in a shared trip. Implementation of the system took place in Shiraz, Iran. Shiraz is the fifth-most-populous city of Iran and the capital of Fars Province with more than 4000 years of history that made it one of the key tourism sites in Iran. Numbers of questionnaires were distributed among different people to evaluate the people recommendation system. In addition, tour planning algorithm was evaluated using a well-known evolutionary algorithm (i.e. Genetic Algorithm). Mean, standard deviation and the convergence graphs of the two mentioned algorithms were compared. Results indicated accurate performance of the recommender system and high accuracy and precision of the route planning algorithm. Recommender System had a mean difference of 0.2 with the questionnaire results, which indicated its good functionality. Ant System reached the minimum value of the objective function (34.70) with a better standard deviation (0.61) compared to Genetic Algorithm. However, Genetic Algorithm performed better in mean value of the tests (34.32) which is a measure of the precision. Convergence graph of the Genetic Algorithm showed a fast convergence with lower objective values in the beginning. Ant System convergence graph showed a smooth convergence toward the optimal solution with an initial population with higher objective values. This indicated the proper functionality of the Ant System and the possibility of improving the results with generating better initial population.