Available via license: CC BY 3.0
Content may be subject to copyright.
Journal of Physics: Conference Series
PAPER • OPEN ACCESS
Construction of Tourism Planning Information System Based on Ant
Colony Algorithm
To cite this article: Ziwen Qu 2020 J. Phys.: Conf. Ser. 1533 022101
View the article online for updates and enhancements.
This content was downloaded from IP address 191.101.84.234 on 18/06/2020 at 13:17
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution
of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
Published under licence by IOP Publishing Ltd
ICAIIT 2020
Journal of Physics: Conference Series 1533 (2020) 022101
IOP Publishing
doi:10.1088/1742-6596/1533/2/022101
1
Construction of Tourism Planning Information System Based
on Ant Colony Algorithm
Ziwen Qu*
School of geographic sciences, Nanjing normal university, Nanjing, 210023, China
*Corresponding author e-mail: 260807798@qq.com
Abstract. Tourism planning is a vital link in tourism. Compared with the traditional
tourism planning based on experience, it is more scientific and reasonable to formulate
through mathematical modeling methods. This paper mainly studies the construction
of tourism planning information system based on ant colony(AC) algorithm. In the
solution process, for the problems with more attractions, you need to divide the area
first, then solve each area separately, and then transform the result of the solution into
the regional self-driving tour route planning, and finally form a self-driving tour route
planning. The experiments in this article found that most of the area tour time is closer
to 15 days, which reduces the number of outings in a year and effectively reduces the
round-trip time. In this paper, the system construction of self-driving tour route
planning problems and ideas for solving specific problems are suitable for route
planning in scenic spots or scenic spots, and have certain reference value.
Keywords: Ant Colony Algorithm, Tourism Planning, Tourism Planning Information
System, System Construction
1. Introduction
China has abundant natural tourism resources and humanistic tourism resources. The potential
advantages of tourism resources have gradually been transformed into economic advantages in which
the Chinese can survive.Over the years, China's tourism industry has made remarkable achievements
in terms of number of visitors, foreign exchange earnings, and construction of tourism infrastructure.
However, with the continuous improvement of the national economic strength, the people's demand
for tourism consumption has also gradually increased, and the number of inbound and outbound
tourism has also increased, and more and more people are blind Consumption of travel abroad is a
burden on the national economy, and at the same time it has a certain impact on China's sustainable
development and social stability. Therefore, we need a feasible domestic tourism planning information
system to make more tourism enthusiasts willing to travel in their own country and bring the national
economy to a higher level.
Tourism Planning Information System (TPIS) is a technology that uses geographic information
system (GIS), remote sensing technology (RS), multimedia and other technologies to collect, store,
analyze, manage, maintain and assist decision-making in tourism planning Support system [1, 2].
Based on the universal geographic information system, some simple tourism planning tasks can be
ICAIIT 2020
Journal of Physics: Conference Series 1533 (2020) 022101
IOP Publishing
doi:10.1088/1742-6596/1533/2/022101
2
directly implemented, and the construction of TPISs is a high-level goal of geographic information
systems in tourism planning.To achieve the purpose of automatically or semi-automatically
completing the complex tasks in tourism planning [3, 4]. The perfect TPIS can enable the integrated
planning functions of TPIS. The basic software platform and core technology for the construction and
application of TPISs is GIS [5]. In recent years, the application of geographic information systems in
tourism planning has mainly focused on the development and application of tourism geographic
information systems. The construction and application of TPISs is one of the important new areas.
Based on the basic principles of tourism planning, geographic information systems, and databases,
this paper proposes the main technical links for building a tourism planning information database. This
paper discusses several spatial mathematical models commonly used in tourism planning, such as the
establishment of overlay analysis, buffer analysis, and network analysis. Based on the GIS spatial
analysis method, the automatic extraction of terrain factors in tourist areas, the analysis of terrain and
the evaluation of the suitability of tourist areas are realized. The idea of constructing a TPIS platform
was proposed, and the overall structure and main functions of the system were preliminarily designed.
Furthermore, the visualization function of the TPIS is applied to the analysis of the source market, the
network model and the suitability model are introduced into the selection of tourist facilities, the
network model and the overlay model are applied to the route design, and the space calculation is
applied to the environmental capacity In the planning process, the plan can be quantified, modeled,
and informatized.
2. Method
2.1 AC Algorithm
For the AC algorithm to solve the TSP principle, just assume that the entire AC contains m ants, and
the number of scenic areas is n, and the distance between scenic area i and scenic area j is
, at a certain time t scenic area. Initially, the pheromone concentration between
njidistij ,...,2,1,
the various scenic areas is the same as . Ant k (k = 1,2, .. m) can determine the next scenic
0
0
ij
area to be visited by the concentration of pheromone between the connecting paths of each scenic area.
Here means that ant k is from scenic area i at time t. The probability of transfer to scenic area j
tPk
ij
is calculated as follows:
(1)
k
k
allowS
isis
ijij
k
ij
allows
allows
tt
tt
P
k
,0
,
Among them, represents the heuristic function, which is the probability that the
ij
ij dist
t1
ant expects to move from scenic area i to scenic area j, and represents the set of scenic areas
k
allow
visited by ant k. And a is the importance factor of pheromone, β is the importance factor of heuristic
function [5, 6].
We set the degree of pheromone volatility to the parameter p (0 <ρ <1). After all the ants have
completed a cycle,that is,
(2)
10
11
1
n
k
k
ijij
ijijij tt
ICAIIT 2020
Journal of Physics: Conference Series 1533 (2020) 022101
IOP Publishing
doi:10.1088/1742-6596/1533/2/022101
3
Among them, represents the concentration of all pheromone released on the connection path
ij
between scenic area i and scenic area j.
In particular, the calculation formula of is:
k
ij
(3)
Other
Ienic spot j from sccenic spott visits sThe KTH an
dist
Q
ij
k
ij
0
2.2 Establishment of Tourism Planning Information Database
Obtaining comprehensive and accurate information is the basis and key link of tourism planning. Its
work is complicated and costly. Compared with the urban planning management information system,
the data collection cost in the TPIS will account for more than 85% of the total system development
cost [7, 8]. Therefore, it is of great significance to explore technology means based on GIS, RS, GPS
and other methods to obtain information, and establish a tourism planning information database based
on GIS to edit, process and analyze data.
Tourism planning information mainly includes four types of information: tourism resource
information, natural, social, and economic conditions, environmental conditions, and tourist source
information. ① Tourism resource information mainly includes the type, quantity, structure, level,
cause of tourism resources and related major historical events and literary works. ② In the natural,
social and economic conditions of the tourist area, natural conditions mainly refer to geological
landforms, meteorology and hydrology, soil vegetation, etc .; social conditions refer to administrative
divisions, population, culture, medical treatment, security, etc .; economic conditions include regional
industrial structure and level , Type, infrastructure, reception service facilities, etc. ③Environmental
conditions, including the background values of important material elements in the atmosphere, water,
upper soil, and lithosphere: including the atmospheric, water, and noise pollution caused by artificial
factors such as industrial and mining enterprises and living services, and the degree of control [9, 10].
④Customer source information, including the scope, quantity, and type of the source market, and the
diversion and synergistic effects of similar resource areas in the vicinity on the source.
1) Travel planning information collection
Obtaining tourist information is the first step in establishing a tourist information database.
Non-digitized information must be converted into digital form before it can be accepted by computers.
In the geographic information system, information is divided into two categories: spatial information
and attribute information. Spatial information is location-related information [11].
2) Classification of tourism planning information
Before entering the data into the computer, it must be classified according to the relevant standards.
The classification criteria should be moderate. Excessive coarseness will affect the accuracy of
analysis and excessively fine storage will be too large. Tourism planning information can be divided
into four categories: tourism resources, natural, social, economic conditions, environmental
conditions, and tourist source markets [12, 13]. Each category can continue to be subdivided until it
can meet the planning needs.
3) Tourism planning information coding.
Coding is to represent classified information with appropriate character strings or numerical values
for easy computer input and identification.
3. Experiment
The construction of TPIS is an advanced goal of GIS application in tourism planning (TP). Combined
with expert knowledge bases and mathematical models, fast are performed to assist planning and
design, and to achieve automatic or semi-automatic The purpose of completing the complex work in
TP. A comprehensive TP management information system can integrate the GIS-assisted planning
ICAIIT 2020
Journal of Physics: Conference Series 1533 (2020) 022101
IOP Publishing
doi:10.1088/1742-6596/1533/2/022101
4
functions discussed in this article.
This system is 64-bit application software, which requires CPUPIII or higher, memory 64M or
higher, hard disk 20G or higher, and Windows NT 4.0 or higher operating environment. The database
management system uses a relational Access management system. The system is developed using
MapX components and Visual Basic 6.0 software.
The hybrid algorithm of this paper and AC algorithm and literature were used to solve the traveling
salesman problem, respectively. The problem and eil51 problem are taken as examples. The three
algorithms were tested 10 times for each case, and the results of each solution were recorded.
4. Discuss
4.1 Performance Simulation Analysis
(1) Search accuracy analysis
Comparing the optimal solutions of this algorithm and the literature AC algorithm, it can be seen
that the algorithm in this paper can find the theoretical optimal solution, and the AC algorithm will fall
into the local optimal solution; meanwhile, comparing the average and average error can be seen The
algorithm cannot guarantee that it can converge to the optimal solution each time, but only has a small
probability to fall into the local optimal solution. Comparing this paper's algorithm with the literature's
particle swarm AC hybrid algorithm, it can be seen that the average error of the particle swarm AC
hybrid algorithm is smaller than the algorithm in this paper, which shows that the particle swarm ant
colony hybrid algorithm has a better effect. The reason is that the parameter values are fixed in the
algorithm in this paper, and the particle swarm AC hybrid algorithm determines the parameters
dynamically through the particle swarm algorithm.
As shown in Table 1 and Figure 1,the average error of the AC algorithm increases faster, the
possibility that the AC algorithm falls into the local optimal solution may greatly increase; While the
average error of the algorithm and the particle swarm AC hybrid algorithm in the city increases, but it
is not obvious, which shows that the algorithm and the particle swarm AC hybrid algorithm have a
better solution to the traveling salesman problem.
Table 1. Path results of three algorithms testing Oliver30
Algorithm
Optimal
solution
Worst
solution
Averag
e value
Theoretical
optimal solution
Averag
e error
AC
Algorithm
427.17
440.96
438.20
423.74
3.4
Algorithm
423.74
426.37
424.26
423.74
0.12
Literature
Algorithm
423.74
425.65
424.13
423.74
0.09
ICAIIT 2020
Journal of Physics: Conference Series 1533 (2020) 022101
IOP Publishing
doi:10.1088/1742-6596/1533/2/022101
5
Optimal solution
Worst solution
Average value
Theoretical optimal
solution
418
420
422
424
426
428
430
432
434
436
438
440
442
Ant Colony Algorithm
Algorithm
Literature Algorithm
Figure 1. Path results of three algorithms testing Oliver30
(2) Solving time
By comparing the solution time of this algorithm with the particle swarm AC hybrid algorithm, the
solution time of this algorithm is less than the particle swarm AC hybrid algorithm. The reason is that
the algorithm has fixed parameter values, while the particle swarm AC hybrid algorithm uses particles.
The swarm algorithm dynamically determines the parameters, so the search accuracy of this algorithm
is slightly worse than the particle swarm AC hybrid algorithm, but the solution time is faster. By
comprehensively comparing search accuracy and solving time, the algorithm in this paper is more
reasonable for solving actual travel route planning problems.
5. Conclusion
This paper studies the basic principles of tourism planning, geographic information systems, and
databases, and proposes the main technical aspects of building a tourism planning information
database. It also discusses several spatial mathematical models commonly used in tourism planning,
such as overlay analysis, buffer analysis, Method for establishing network analysis. At the same time,
the idea of building a TPIS platform is also proposed, and the overall structure and main functions of
the system are preliminarily designed. Then the visualization function of the TPIS is applied to the
analysis of the source market, and the network model suitability model is introduced The site selection
of tourism facilities, network model and overlay model are applied to the route design, and space
measurement is applied to the planning process such as environmental capacity to realize the
quantification, modeling and informationization of the plan.
References
[1] Ai-ke Kan, Guo-qing Li,Xiao Yang.Ecological vulnerability analysis of Tibetan towns with
tourism-based economy:a case study of the Bayi District[J].Journal of Mountain Science,
2018, 15(5):1101-1114.
[2] N Vinky Rahman, Nurlisa Ginting,Subhilhar.Planning a tourism landscape in geosite area:
Sipiso-piso waterfall[J].Iop Conference, 2018, 126(1):012196.
[3] Đurđana OzretićDošen, Jozo Previšić,Zoran Krupka.The role of familiarity in the assessment of
Turkey’s country/destination image:going beyond soap operas [J].International Journal of
ICAIIT 2020
Journal of Physics: Conference Series 1533 (2020) 022101
IOP Publishing
doi:10.1088/1742-6596/1533/2/022101
6
Culture Tourism and Hospitality Research,2018,12(3):277-291.
[4] R Subekti,E R Sari,R Kusumawati.Ant colony algorithm for clustering in portfolio
optimization[J]. Journal of Physics Conference, 2018, 983(1):012096.
[5] Sandhya Parasnath Dubey, S.Balaji, N.Gopalakrishna Kini.A Novel Framework for Ab Initio
Coarse Protein Structure Prediction [J].Advances in Bioinformatics,2018,2018(30):1-17.
[6] Han Wang,Hongjun Zhang,Kun Wang.Off-road Path Planning Based on Improved Ant Colony
Algorithm[J].Wireless Personal Communications,2018,102(2):1705-1721.
[7] Mahmoud Jafarinejad,Morteza Amini.Multi-join query optimization in bucket-based encrypted
databases using an enhanced ant colony optimization algorithm[J].Distributed&Parallel
Databases, 2018, 36(1):1-43.
[8] Ammar A.Aldair,Abdulmuttalib T.Rashid,Mofeed Turky Rashid.Adaptive Fuzzy Control
Applied to Seven-Link Biped Robot Using Ant Colony Optimization Algorithm[J].Iranian
Journal of Science and Technology-Transactions of Electrical Engineering,2019(3):1-15.
[9] Zhaojun Zhang,Funian Hu,Na Zhang.Ant colony algorithm for satellite control resource
scheduling problem[J].Applied Intelligence,2018,48(10):1-11.
[10] W.Zhang, Y.Ma, H.-D.Zhao.Obstacle avoidance path planning of intelligent mobile based on
improved fireworks-ant colony hybrid algorithm [J].Kongzhi yu Juece/Control and
Decision,2019, 34(2):335-343.
[11] Z.Lin, L.Xu.An improved ant colony optimization applied in programing laser welding path
[J].Hanjie Xuebao/transactions of the China Welding Institution, 2018, 39(1):107-110.
[12] Chi-Chung Chen,Li Ping Shen.Improve the Accuracy of Recurrent Fuzzy System Design Using
an Efficient Continuous Ant Colony Optimization[J].International Journal of Fuzzy
Systems,2018, 20(2):1-18.
[13] Sarika D.Patil, Sumant G.Kadwane.Hybrid optimization algorithm applied for selective
harmonic elimination in multilevel inverter with reduced switch topology[J].Microsystem
Technologies,2018, 24(3):1-7.
