25,26,27,28|A 6,3,11,8,4,2,10,13 live Birds Garden, Grand Show hant's park Analysis: In test 2, according to the characteristics of each group in the designed scenario, the system was able to analyze their preference under such age level and group scope, and recommended proper sites respectively. From this we an tell that the advanced algorithm has the ability to catch and process the users preference information. Therefore, fo our planning problems with proper mathematical scope, the designed functions are all reasonable and the advanced aCa system is effective in processing the users customized information to provide rationa Apart from testing of the system itself, we also considered the test fuser satisfact designed as a contrast test comparing with another system as a control group, and use testing methods a to validate the results. Therefore, we designed a contrast experiment Test 2 to see the d ACAs performance on user experience and satisfaction in the prototype syster Test 3: Contrast Experiment. The control group is designed to be a tour planni v tne same unctioning process and user interface, but with the original ACa as its optimizing 一 However this difference systems optimized recommending tour resul ply interacting with the system.The nt will only be reflected in the am satisfied with the customer flow of those recommended sites in the optim I can accept the weather condition of those system recommended sites Ifeel comfortable with the interaction between me and the system. I will recommend mry friends to adopt this tour planning system when they are travelling in an unfamiliar area Tab. 3 Some Survey Data from Users On the Co User A User B 4 3 User B: Expl19+49+:9813+9+863401 38 L. From the above statistics we can see that these two cases can to some extent reflect tl lent in user satisfaction th the advanced ACA. Even though the data scale was not large enough, but the partial results do have value for further reference, and we expect to see a more convincing breakthrough from continuing surveys 5. Conclusion Our research analyzed the problem facing existing researchers that it is of much significant as well as great difficulty of 时mmmp甲a ffectiveness and user satisfaction improvement of the advanced al our research. We inevitably missed some real context factors, and the scale of testing is still to be enlarged equate points in the authors'knowledge limitation, there are inevitably more context information factors in the weights of the advanced aca to see whether a better 3)Specifying the recommendation process of the system, which will probably help much in gaining higher user satisfaction Referene J, Suh, E, Kim, S, Context-aware systems: A literature review and classification, Expert Systems with lications36(2009)85098522 of Context and Context-Awareness GIT GvU n a context-aware touris heliN Davies The role of adaptive hypermedia 3mm3mN已 ternational Workshop, ANTS 2002, Vol. 2463( [4] Marco Dorigo, Senior Member, IEEE, and Luca Maria Gambardella, Ant Cole Approach to the Traveling Salesman Problem, IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION [5] JG Walls, GR Widmeyer, OA El Sawy, ""Building an Information System Design Theory for Vigilant EIs [6] XU Jinrong, LI Yun at el, Hybrid Genetic Ant Colony Algorithm for Traveling Salesman Problem, Computer I7 Engineering and applications, 200 a velsr23te p. ging based on improved ant colony algorthm omputer traveling salem blem[C]/Proc IEEE nternational Conference on Evolutionary Computation 9 2002.3ng): Yang iazen Ant Colony Algorithim with Adaptive Information Factor (I, Information and Control [10] Cao Lang-cai, Luo Jian. An improved intelligence algorithm over ACS for TSP[CI/Proc of CCC, 2008: 65-69 [1] Paul Harr Robin Shaw, Consumer Satisfaction and Post-purchase Intentions: Al ploratory Study of Museum Visitors[]. International Journal of Arts Management; Winter 2004: 6, 2; ABI/INFORM Global pg [12] Yang Huo, Douglas Miller, Satisfaction Measurement of Small Tourism Sector(Museum): Samoa [], Asia Pacific Journal of Tourism Research, Vol 12, No 2, June 2007Visitors’ Ages 25,26,27,28 All sites to be visited 6,3,11,8,4,2,10,13 Key Point Sites 2,10,13 Sites Info：Swan Lake, Peacock Park, Horse-Riding, Beasts’ Show, Interactive Birds Garden, Grand Show Number of Square, Elephant’s Park Sites 8 Analysis: In test 2, according to the characteristics of each group in the designed scenario, the system was able to analyze their preference under such age level and group scope, and recommended proper sites respectively. From this we can tell that the advanced algorithm has the ability to catch and process the user’s preference information. Therefore, for tour planning problems with proper mathematical scope, the designed functions are all reasonable and the advanced ACA system is effective in processing the user’s customized information to provide rational results. Apart from testing of the system itself, we also considered the test of user satisfaction improvement, which has to be designed as a contrast test comparing with another system as a control group, and use real user testing methods and survey to validate the results. Therefore, we designed a contrast experiment Test 2 to see the advanced ACA’s performance on user experience and satisfaction in the prototype system. Test 3: Contrast Experiment. The control group is designed to be a tour planning system with exactly the same functioning process and user interface, but with the original ACA as its optimizing algorithm. However, this difference won’t be sensed by the user when they are simply interacting with the system. The adjustment will only be reflected in the system’s optimized recommending tour result. In our experiment, we use user survey and statistics analysis to testify the user experience performance – which is the best and only convincible way to verify such measurement. Some of our survey rating statements are like these: ‘I am satisfied with the customer flow of those recommended sites in the optimized route.’ ‘I can accept the weather condition of those system recommended sites.’ ‘I feel comfortable with the interaction between me and the system.’ ‘I will recommend my friends to adopt this tour planning system when they are travelling in an unfamiliar area.’ Tab.3 Some Survey Data from Users On the Contrast Experiment User A Statement # 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Sys 1 (Advanced) 4 3 5 3 4 4 4 3 3 2 4 4 3 3 Sys 2 (Control) 4 3 5 3 4 4 4 3 3 2 4 3 3 2 User B Statement # 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Sys 1 (Advanced) 4 4 5 4 2 4 4 3 3 4 4 4 3 3 Sys 2 (Control) 4 3 5 3 2 4 4 3 3 4 4 3 3 3 According to the above survey statistics, we can calculate the users’ satisfaction index: User A: Exp1=0.5*(4+3+5+4+2+4+3+3)/8+0.5*(3+4+4+3+3+4)/6=3.69 Exp2=0.5*(4+3+5+4+2+4+3+2)/8+0.5*(3+3+4+3+3+3)/6=3.40; ∴Exp1>Exp2; User B: Exp1=0.5*(4+4+5+4+4+4+3+3)/8+0.5*(4+2+4+3+3+4)/6=3.60; Exp2=0.5*(4+3+5+4+4+4+3+3)/8+0.5*(3+2+4+3+3+3)/6=3.38; ∴Exp1>Exp2; From the above statistics we can see that these two cases can to some extent reflect the improvement in user satisfaction with the advanced ACA. Even though the data scale was not large enough, but the partial results do have value for further reference, and we expect to see a more convincing breakthrough from continuing surveys. 5. Conclusions Our research analyzed the problem facing existing researchers that it is of much significant as well as great difficulty of finding a best way of utilizing context information when designing the functions of context-aware tour planning information system in order to provide best user experience in customization and recommendation. Then we proposed an advanced ACA, which quantized context information and processed it as weights of ants’ information factor. Finally, we build up a prototype system, set a real case background of the Shanghai Zoo, design and implemented both single-program and contrast experiments to verify the efficiency, effectiveness and user satisfaction improvement of the advanced algorithm. However, since our research is restricted by the authors’ knowledge limitation, there are inevitably inadequate points in our research. We inevitably missed some real context factors, and the scale of testing is still to be enlarged. Therefore, we hope the continuing research on this topic can focus on: 1) Establishing a mass user testing application to implement system test to a large scale, in order to reach a more convincing and reliable result. 2) Including more context information factors in the weights of the advanced ACA to see whether a better customization performance can be reached. 3) Specifying the recommendation process of the system, which will probably help much in gaining higher user satisfaction. References [1] Hong, J., Suh, E., Kim, S., Context-aware systems: A literature review and classification, Expert Systems with Applications 36 (2009) 8509–8522 [2] K. Dey and Gregory D. Abowd，Towards a Better Understanding of Context and Context-Awareness. GIT, GVU Technical Report GIT-GVU-99-22, June 1999.K. Cheverst, K. Mitchell, N. Davies, The role of adaptive hypermedia in a context-aware tourist GUIDE, Communications of the ACM, Vol. 45, No. 5,2002, pp. 47 - 51 [3] Johann Dreo and Patrick Siarry, A New Ant Colony Algorithm Using the Heterarchical Concept Aimed at Optimization of Multiminima Continuous Functions, Third International Workshop, ANTS 2002, Vol. 2463 (2002) [4] Marco Dorigo, Senior Member, IEEE, and Luca Maria Gambardella, Ant Colony System: A Cooperative Learning Approach to the Traveling Salesman Problem, IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, VOL. 1, NO. 1, APRIL 1997 [5] JG Walls, GR Widmeyer, OA El Sawy, “Building an Information System Design Theory for Vigilant EIS”, Information Systems Research, vol. 3, no. 1, 1992, pp. 36-59.. [6] XU Jinrong, LI Yun at el., Hybrid Genetic Ant Colony Algorithm for Traveling Salesman Problem, Computer Applications, Aug 2008, Vol.28, No.8 [7] XU Feng, DU Junping．Study on travel route planning based on improved ant colony algorithm．Computer Engineering and Applications, 2009，45(23),pp.193 [8] Stutzl T, Hoos H H．The MAX-MIN ant system and local search for the traveling salesman problem[C]//Proc IEEE International Conference on Evolutionary Computation (ICEC’97)，Indianapolis,USA.1997：309-314． [9] Tan Gangli, Yang Jiaben, Ant Colony Algorithm with Adaptive Information Factor [J], Information and Control． 2002,31(3): pp198—201. [10] Cao Lang-cai，Luo Jian． An improved intelligence algorithm over ACS for TSP[C]//Proc of CCC, 2008:65-69． [11] Paul Harrison; Robin Shaw, Consumer Satisfaction and Post-purchase Intentions: An Exploratory Study of Museum Visitors[J]. International Journal of Arts Management; Winter 2004; 6, 2; ABI/INFORM Global pg. 23 [12] Yang Huo, Douglas Miller, Satisfaction Measurement of Small Tourism Sector (Museum): Samoa [J], Asia Pacific Journal of Tourism Research, Vol. 12, No. 2, June 2007