edu.in Shubham AgrawalUG StudentDepartment of CSESRM University, [email protected] ABSTRACT With the popularity of using google map, users can easily view the route to their destination.We aim to discover travel experiences to facilitate trip planning.
When planning a trip, users always have specific preferences regarding their trips. Instead of restricting users to limited query (locations, activities, or time periods). We consider arbitrary text descriptions as keywords about personalized requirements. Moreover, a diverse and representative set of recommended travel routes is needed. Prior works have elaborated on mining and reviewing in existing routes. To meet the need for automatic trip organization, we claim that more features of Places of Interest (POIs) should be extracted by getting the review from the users.
I. INTRODUCTION LOCATION users to perform check-in and share their check-in data -BASED social network (LBSN) services allow with their friends. In particular, when a user is traveling, the check-in data are in fact a travel route with some photos and tag information.
As a result, a massive number of routes are generated, which play an essential role in many well-established research areas, such as mobility prediction, urban planning, and traffic management. In this paper, we focus on trip planning and intend to discover travel experiences from shared data in location-based social networks. To facilitate trip planning, the prior works in provide an interface in which a user could submit the query region and the total travel time. In contrast, we consider a scenario where users specify their preferences with keywords. For example, when planning a trip to Sydney, one would have “Opera House”. As such, we extend the input of trip planning by exploring possible keywords issued by users. II. RELATED WORK Spatial Keyword: The spatial-keyword search has received considerable attention from the research community.
Some existing works focus on retrieving individual objects by specifying a query consisting of a query location and a set of query keywords (or known as document in some context). Each retrieved object is associated with keywords relevant to the query keywords and is close to the query location 3, 5, 6, 8, 10, 15, 16. The similarity between documents is applied to measure the relevance of two sets of keywords. The content used for querying takes the form of spatial database. Best keyword cover query takes the form of keywords or objects.
For example, Hotels. Given a spatial database P, which consists of a set of points. For a query q, where q belongs to set of objects, it searches for nearest neighbor within the object by searching its or better decision making, the concept of keyword rating was introduced along with its features other than distance. For such search , the query will take the form of a feature of objects. III. Related Terminologies Google maps API: Google, a tech giant provide its application programming interface(API) for location-based services and these help in implementing the API in our project. Google maps API helps in checking the location and providing the location on the basis of latitude and longitudes. Google API contains URL and provides the Unique key that helps in implementing API in any project and these API keys are uniquely provided by Google in every URL for every project.
Data Mining: Data mining, the extraction of hidden predictive information from large databases, is a powerful new technology with great potential to help companies focus on the most important information in their data warehouses. Data mining tools predict future trends and behaviors, allowing businesses to make proactive, knowledge-driven decisions. The automated, prospective analyses offered by data mining move beyond the analyses of past events provided by retrospective tools typical of decision support systems. Data mining tools can answer business questions that traditionally were too time-consuming to resolve. They scour databases for hidden patterns, finding predictive information that experts may miss because it lies outside their expectations.Here Data mining is used to mine the data of reviews and display them accordingly.Recommendation of Route: Recommendation of the route has been done on the basis of Reviews given by people who have been traveling and who has been traveled.
All possible routes have been determined and been displayed on the screen and the best route accordingly will be recommended to the user. IV. Algorithm UsedData Preprocessing Algorithm:Since the sentences are of different length, we pad our sentences with a special token to make the lengths of the two sentences equal.So now we have our sentences modified:Sentence 1: the camera quality is very goodSentence 2: the battery life is good .Now, both the sentences are of the same length.
We proceed to build the vocabulary index.Vocabulary index is a mapping of integer to each unique word in the corpus.In our case, size of vocabulary index will be 9, since there are 9 unique tokens. Vocabulary is as follows Corresponding code from the blogvocab_processor = learn.
preprocessing.VocabularyProcessor(max_document_length)In tensorflow, tensorflow.contrib.learn.preprocessing.VocabularyProcessor is used for building the vocabulary.
Use this link to see how to extract vocabulary from the vocab_processor object.Next, each sentence is converted into a vector of integers.Sentence 1 : 1, 2, 3, 4, 5, 6Sentence 2 : 1, 7, 8, 4, 6, 0Routing Algorithm :Set of all optimal routes from Source to a given destination.-A tree!• Goal of routing algorithm sink trees that are possible in a graph• Shortest Path Routing:– Dijkstra– Uses topology– Greedy approach– Possible shorter path of equal length – need not be Fig.
1 Architecture Diagram V. CONCLUSION & FUTURE WORK This project briefs and provides a recommendation of the route on the basis of reviews. We used efficient algorithm and application programming interface to provide more efficiency and lessen time and space complexity as compared to the previous work. We have even worked on live data sets and improved keyword extraction techniques The application is able to retrieve travel routes that are interesting for users, and outperforms the Google API and routing algorithm in terms of effectiveness and efficiency. Due to the real-time requirements for online systems, we aim to reduce the computation cost by recording repeated queries and to learn the approximate parameters automatically in the future. REFERENCES: 1 Z. Chen, H. T.
Shen, X. Zhou, Y. Zheng, and X. Xie, “Searching trajectories by locations: An efficiency study,” in Proc. ACM SIGMOD Int.
Conf. Manage. Data, 2010, pp.
255–266.2 H.-P. Hsieh and C.-T.
Li, “Mining and planning time-aware routesfrom check-in data,” in Proc. 23rd ACM Int. Conf. Conf. Inf. Knowl.Manage.
, 2014, pp. 481–490.3 V.
S. Tseng, E. H.-C.
Lu, and C.-H. Huang, “Mining temporalmobile sequential patterns in location-based service environments,” in Proc. Int. Conf. Parallel Distrib.
Syst., 2007, pp. 1–8.4 W. T.
Hsu, Y. T. Wen, L. Y. Wei, and W. C. Peng, “Skyline travelroutes: Exploring skyline for trip planning,” in Proc. IEEE 15th Int.
Conf. Mobile Data Manage., 2014, pp. 31–36.
5 Y. Zheng, L. Zhang, X.
Xie, and W.-Y. Ma, “Mining interestinglocations and travel sequences from GPS trajectories,” in Proc.18th Int. Conf.
World Wide Web, 2009, pp. 791–800.6 Ke Deng, Xin Li, and Xiaofang Zhou, “Best Keyword Cover Search,” IEEE Transaction on Knowledge and Data Engineering , vol 27, no 1, January 2015. 7 Joao B Junior, Orestis Gkorghas, Simon Jonassen and Kjetil Norvag, ” Efficient Processing of Top K Spatial Keyword Queries,” in SSTD, pages 205-222, 2012.8 Xin Cao, Gao Cong, Beng Chin, “Collective Spatial Keyword Querying,” ACM Transaction on Database Systems, 2011.
9 Gilsi R Hjaltson and Hanseb Samet, “Distance Browsing in Spatial Databases,” ACM Transaction on Database Systems, June 1999, pp 265-318.10 Ronald Fagin, Ammon Lotem, and Moni Naor, “Optimal Aggregation Algorithms for Middleware,” Journal of Computer and System Sciences, April 2003.