[Objectives] Revealing the structural characteristics of tourist flow networks is a prerequisite for achieving complementary advantages and coordinated development among attractions.[Methods] In this study, we employs methods such as travel chain extraction, social network analysis, and community detection to construct a research framework to analyze multi-scale tourist flow networks based on large-scale mobile phone data. The structural characteristics of the tourist flow network in Changsha are explored at microscopic, mesoscopic, and macroscopic scales.[Results] (1) Microscopic scale: The tourist flow network of Changsha shows a significant centralization trend, where a few core attractions such as the Yuelu Mountain and Orange Island have great influences on the whole network. Only 33% of attractions show structural hole efficiency and effectiveness above average, while their constraint is below average, indicating prominent structural holes and limited overall connectivity and efficiency. (2) Mesoscopic scale: The tourist flows of Changsha are highly concentrated, showing obvious spatial clustering characteristics and forming six tourism communities. There are usually two core attractions in each community to drive tourists to visit the surrounding attractions. In addition, the development of tourism communities is unbalanced, with a highly large community centered on Yuelu Mountain and Orange Island. (3) Macroscopic scale: The spatial distribution of the tourist flow network presents the characteristics of single-core strong concentration and overall dispersion, showing a multi-layer structure with the city center as the core and spreading outwards. The global efficiency of the network is only 0.367, with some marginal attractions having poor accessibility. The core attraction plays limited "trickle-down" effects on marginal attractions.

Tourism and leisure have become important aspects of modern life, enhancing the quality of life through recreational activities. However, the development of tourism and leisure is characterized by imbalances and deficiencies that need immediate attention. Geo-information Science provides a spatial analytical framework and methods for studying tourism and leisure. Additionally, the rapid advancement of big data technology has facilitated the widespread application and interest in Geo-information Science in the field of tourism and leisure. This article aims to critically review the current state of research, disciplinary contributions, limitations, and future directions of Geo-Information Science in the field of tourism and leisure. To achieve this objective, we conducted interviews with representative scholars from various fields such as tourism management, Geo-information Science, and geography to gather their insights. Through interviews with twelve experts, we found that one of the major contributions of Geo-information Science to tourism and leisure research is the integration of spatial thinking, including the spatial and temporal dimensions. On one hand, by emphasizing the importance of space, Geo-information Science allows for a deeper understanding of how the geographical environment influences tourist behavior and decision-making processes. Analytical techniques such as spatial analysis, geographic visualization, and spatial modeling offer technical opportunities for valuable insights into various aspects of tourism, including the spatial behavior of tourists, distribution patterns, and the utilization of tourism resources. On the other hand, the use of Geo-information Science rooted in spatiotemporal cognitive logic helps in understanding the generation and evolution of tourism patterns. This approach can analyze changes and impacts of tourism processes at different time and spatial scales, revealing underlying behavioral mechanisms, spatial-temporal distribution patterns of tourist attractions, and temporal trends in the tourism market. However, challenges remain in interpreting research findings, integrating data from multiple sources, and promoting interdisciplinary exchanges. Addressing these challenges requires further exploration and research from scholars. Nonetheless, it is important to recognize the tremendous potential of Geo-information Science in future applications in the field of tourism and leisure. In the era of Artificial Intelligence 2.0, the integration and breakthroughs in combining 3D GIS with human sensory devices, enhancing decision-making abilities through spatiotemporal modeling technologies, the integration of AIGC with Geo-information Science technologies, and the automatic generation of multidimensional virtual spaces all hold exciting prospects. This study aims to provide guidance for the fusion of Geo-information Science with tourism and leisure research and anticipate future directions in this field. By addressing current limitations and exploring future directions, researchers can further enhance our understanding of these fields and contribute to their sustainable development.

The way we capture and analyze human activity and behavior is changing because of big data. A variety of new data sources have emerged to supplement the official data, offering a significant amount of data with potential application value for the research of tourism and leisure while overcoming the common problem of insufficient data in traditional tourism research. Based on the research frontier of big geodata, this paper explains the theoretical foundation of tourism under the background of geographic multi-source big data at three levels: human tourism activities, tourism geographical environments and destinations, and the relationship between tourists and tourist destinations. Secondly, this paper summarizes the application of big geodata, such as human tourism activity data (e.g., UGC data, device data, transaction data) and tourism geographical environment data (e.g., POI, environmental data). Finally, this paper discusses the challenges and prospects of big geodata in three aspects: research paradigm and theory, multi-source data fusion, and analysis methods. For the research paradigm and theory, there is the requirement for standardize and systematize the scientific research paradigm by combining different events and scenarios to create an interpretation system of Chinese tourism geography based on "process-structure-mechanism". In terms of multi-source data fusion, the combination of big data and other data is necessary. In terms of analysis methods, efforts are still needed to improve the adaptability of analysis methods and incorporate the specific variables of tourism phenomena.

Network science provides abstract models for analyzing complex phenomena in the real world. With the support of network science theories and methods, researchers are able to explore the dynamic relationship between research objects in tourism domains from a more systematic perspective. This unique viewpoint is of great significance for further understanding the operation rules of tourism and promoting the balanced and sustainable development of related industries. With the digitalization of tourism, tourism information has become more flexible and scalable, which has significantly increased the applicability of network science theories and methods in tourism domains. Against this background, research on the applications of network science theories and methods in tourism domains has received extensive attention in recent years. In view of this, this paper systematically reviews the published articles related to the applications of network science theories and methods in tourism domains and summarizes the main research contents through a multi-scale perspective. Specifically, this paper first outlines the backgrounds of related theoretical foundations and application scenarios. The most common types of tourism networks, including interpersonal networks, tourist flow networks, economic networks, etc., are summarized through a "node-edge" structure. Important concepts and terms in network science, especially the differences and relations between complex networks and social networks as two "research paradigms", are also highlighted. Following that, this paper summarizes the progress of the applications of network science theories and methods in tourism domains at different scales of observation (i.e., microscopic, mesoscopic, and macroscopic). Among these scales, the microscopic scale focuses on the interactive properties of tourism actors, the mesoscopic scale is often used to describe the aggregation phenomena of tourism actors, and the macroscopic scale focuses on the global topological structural features of the tourism actor networks in tourism domains. Common methods or measures in network science, such as centrality, structural holes, community/cohesive subgroups, core-periphery structure, small worlds, and scale-free effect are also introduced. Based on the review of the research progress, this paper identifies the research problems in current research, including reliability deficiencies in the research data, negligence of multi-scale phenomena, interpretability challenges in the research results, and lack of highlighting theoretical contributions in tourism domains. The aim of this paper is to review the research literature on applications of network science theories and methods in tourism domains from the perspective of research practice, in order to effectively present the substance and compatibility of research at the intersection of network science and tourism.

In the context of culture-tourism integration, digital China, and activated utilization of heritage, heritage tourism has become a hot topic in academia and industry. The mismatch between spatial representation of heritage value and tourists' spatial perception is one of the most prominent contradictions in current heritage tourism. From the perspective of heritage value, this paper combines bibliometric analysis and systematic review to discuss relevant research from four aspects: interpretation and quantification of heritage value, spatial calculation and representation of heritage value, tourists' perception of heritage value and space, and tourists' spatial behavior in heritage site. Besides, comparisons between Chinese and foreign literature of these four themes are conducted to figure out the similarity and difference. The main findings are as follows: (1) there are abundant achievements in the interpretation of heritage value, which mainly focus on the connotation and interpretation technology of heritage value, but lack of quantitative methods; (2) the spatial calculation and representation of heritage value is object-oriented and application-oriented, and the geographic information system and spatial information technology are commonly used methods; (3) studies on tourists’ perception of heritage value and space are mostly from the perspective of tourism destinations of heritage sites but ignore the heritage value and spatial attributes, lacking the exploration of relationship between heritage value, heritage space, and tourists. The measurement dimension of sensory perception is mainly visual; (4) the research on tourist behavior in heritage site mainly focuses on the characteristics, patterns, causes, and influencing factors of behavior. It emphasizes the importance of practical application and reflects the orientation of heritage responsibility; (5) the spatial calculation and representation of heritage value, as well as tourists' perception of heritage value and space, are still lack of concern in the context of natural heritage and mixed heritage; (6) there are similarities and differences in the research objects, methods, and contents of Chinese and foreign literatures; (7) in the future, the interpretation and representation of heritage value will transition from traditional narrative to spatial quantification, and the perception and calculation of heritage space will shift from spatial footprint to perceptual behavior. Based on above findings, this paper puts forward a theoretical framework and methodological path from multidisciplinary perspective for tourists' spatial perception and calculation of heritage value, in order to promote the interdisciplinary theory and technology integration of heritage research. In conclusion, this paper provides theoretical references for related research and practical references for heritage protection, heritage site management, tourism development, and heritage value inheritance.

In recent years, with the improvement of public awareness of environmental protection, the pursuit of harmonious coexistence between man and nature of ecotourism has attracted more and more people's attention. In the face of rich and diverse ecotourism resources and the contradiction between supply and demand of domestic ecotourism, how to orderly develop and make rational use of resources under the premise of maximum protection, and transform "lucid waters and lush mountains" into "gold and silver mountains" scientifically and rationally is a major issue to be addressed at present. Taking Shennongjia Forestry District as an example, based on multi-source geospatial data, we use the XGBoost algorithm to evaluate its ecotourism suitability. The following conclusions are drawn: (1) The ecotourism suitability evaluation model based on XGBoost algorithm integrates machine learning technology and achieves good classification results with the idea of ​​data mining. The overall classification accuracy of the model under 10-fold cross-validation is 89.44%, with a high recall rate (89.68%). The F1 score is 0.8745, based on both the precision and recall. The AUC value of the model is 0.9593, and the overall classification performance of the model is excellent; (2) According to the ranking results of feature importance, the NDVI of ecological environment elements (26.86%), annual average temperature (11.61%), and distance from social and economic factors to the road (8.90%) has the highest contribution to the model; (3) The classification results of ecotourism suitability show that the overall ecotourism resources in Shennongjia Forestry District are rich. Highly suitable areas, moderately suitable areas, marginally suitable areas, and unsuitable areas account for 44.13%, 15.93%, 11.89%, and 28.05% of the total forest area, respectively. The research method of this paper breaks through the limitations of traditional ecotourism suitability assessment methods which are highly subjective, and solves practical problems based on data mining ideas and machine learning technology.

The ecotourism suitability assessment is the basis and a crucial reference for evaluating development potential, formulating plans, and implementing exploitation in ecotourism. In this study, we first analyze the feasibility of machine learning methods for modeling ecotourism suitability, and the Random Forest (RF) algorithm is selected for conducting an empirical study in the Wuling Mountain area in Hunan Province. In the study area, there are abundant tourism resources with an urgent need for ecotourism development, which can not only consolidate and expand the achievements of poverty alleviation, but also effectively connect with rural revitalization, thereby promoting sustainable development of tourism. The results show that: (1) Machine learning, as a new regional ecotourism suitability assessment approach, provides new insights and solutions for further improvement of suitability assessment; (2) The RF algorithm as a typical machine learning method can be effectively applied in the regional ecotourism suitability assessment. The optimized RF model achieves an average testing accuracy of 86.49%, with an area under the curve (AUC) of 0.95. These results also indicate the ecotourism suitability of the Wuling Mountain area in Hunan Province; (3) The ranking of feature importance reveals that land use type contributes most to the model, accounting for 28.98%, followed by other significant factors including population density (16.34%), distance from scenic spots (12.2%), and biological richness (10.65%). The above factors should be all considered in ecotourism development efforts; (4) The ecotourism suitability results show a high proportion of highly and moderately suitable areas, suggesting significant potential for ecotourism development in the study area. Based on the ecotourism suitability assessment, different development directions are proposed: A protective pattern and experiential education-oriented ecotourism are well-suited in highly suitable areas; a joint pattern and supportive ecotourism are appropriate for moderately suitable areas; a restrictive pattern is recommended for marginally suitable areas; and for unsuitable areas, the development should be prohibited. Finally, we present a new development strategy known as "two centers, one belt, and one plate," providing theoretical and technical guidance for ecotourism development and the consolidation of poverty alleviation achievements in the Wuling Mountain area of Hunan Province.

The mobile communication technology and social media has been deeply embedded into people's daily life, affecting people's choices of leisure activities. However, there is still limited understanding of the spatial regularity characteristics of its impact, particularly due to the lack of empirical analysis utilizing specific quantitative indicators. Given that the layout of leisure spaces is closely linked to social equity, it is essential to obtain a better understanding of the emerging spatial patterns in order to improve residents' well-being. To address this gap, leisure check-ins on Xiaohongshu (a Chinese social media platform) and leisure Points of Interest (POI) in Dalian are used to measure the characteristics of these two types of leisure spaces in two dimensions: concentration and clustering, and at two scales: the main urban area and subdistricts. Various spatial analysis methods, including kernel density estimation, head/tail breaks, hot spot analysis (Getis-Ord Gi*), and DBSCAN (Density-Based Clustering), are employed to analyze the data. The findings are that: (1) Leisure check-ins are mostly located in the urban central area, with a smaller distribution range and fewer hotspot cores; (2) At both the main urban area and subdistricts scales, the distribution of leisure check-ins exhibits lower concentration and clustering, with obvious "decentralized dispersion" characteristics. However, the degree of significance of these features varies across different subdistricts; (3) The majority hotspots of leisure check-ins are located in traditional hotspots, with a few emerging in expansion of urban central area or regions with unique features, such as historic urban landscape district and marina space; (4) The distribution patterns of leisure check-ins can be grouped into four types based on differences in subdistricts' concentration and clustering ratio: "original center cluster type", "original center scattered type", "new center scattered type", and "no center scattered type". The subdistricts with these different distribution patterns exhibit differences in functionality, location, and other characteristics. This study analyses the behavioral processes of leisure activities under the influence of social media through the lens of Actor-Network-Theory. Based on the fundamental principles of temporal geography and differences between "space of places" and "space of flows", it is argued that social media engenders a novel "local order" of leisure pursuits, marked by a desire for spatial exploration. This new order reflects the impact of "space of flows" based on virtual connections on "space of places" based on physical presence, which strengthens the role of node attractors, reduces the constraints of accessibility at micro scales, and increases the flexibility of location.

Street space is the main space that affects tourists' experience of tourism sites. The visual quality of street space is crucial to the development of tourism. However, the evaluation method of visual quality needs further exploration. This paper selected Gulangyu, the famous tourism site in Xiamen, as a study case. First, we established a quantitative model of visual quality combining the existing research on street space and the visual elements of tourism sites. Then, we collected street view data of each intersection by traveling like tourists, corrected imaging parameters, and encoded the street view images. Second, based on the deep learning method (Fully Convolutional Networks, FCN), we segmented the collected street view images semantically and extracted the visual elements in street view data. Finally, by combining with GIS, we set up a geographic information database to analyze the visual and spatial characteristics of each sampling point's visual elements. This database was aimed at providing a basis for further evaluation of the visual quality of street space. It was aggregated using the street line as the smallest unit. In our study, we calculated the visual quality indicators to evaluate the street space in Gulangyu. The results show that: (1) There is obvious spatial differentiation in the visual elements of street space in Gulangyu; (2) Building density, street width, and vegetation sketches are the basic visual elements that shape the visual quality of street space; (3) The distribution of botanical parks, major docks, and commercial facilities significantly impacts the street space's visual quality. In detail, green plants, buildings, roads, sky, and street facilities show the differences between a center and a roundabout. While the distribution of pedestrians shows differences between the east and the west. The green view rate, enclosure, sky openness, and diversity of street space also have obvious center-roundabout spatial differentiation. Moreover, there is an obvious spatial agglomeration effect in the green view rate, crowding degree, and diversity of street space. The agglomeration points are mainly parks, docks, and commercial streets. The method in this paper provides a new collection method in street visual quality evaluation. The visual element extraction accuracy based on FCN is fairly high, which can provide a reference for street view images and other types of image data analysis. This paper provides a valuable reference for street space management and planning, resource integration and allocation, human flow guidance, and regulation in tourism sites.

Tourism is an important part of the service industry. As the third space connecting the city and tourists and the main place for recreation and reception, the distribution pattern and spatial process of the tourism accommodation industry play an important role in promoting the co-evolution of the urban spatial structure. Under the background of informatization connection of supply and demand, improvement of transportation capacity, and multi-center development of cities, the site selection decision of the urban accommodation industry has shifted from focusing on traditional factors such as land rent, policy constraints, and consumption thresholds to comprehensively considering spatial factors such as the convenience of the transportation network and the proximity of service facilities. Shared accommodation is a typical representative of non-standard accommodation, that is, the house owner temporarily rents out all or part of the idle house to the lodger relying on the two-way trading platform on the Internet. Since entering the Chinese market in 2015, Airbnb has become a pioneer in the shared accommodation industry in China. Using space syntax and co-location quotient theory, combined with GIS spatial analysis technology, this paper selects the data of Airbnb's active listings, star-rated hotels, urban road network, and points of interest in Hong Kong in 2021 to construct the 'point-line-surface' research framework of 'accommodation unit-traffic axis-functional space' and analyze the spatial layout patterns of shared accommodation and traditional hotels, as well as the structural correlation characteristics with the form of urban road network and urban functional space. The results show that the shared accommodation presents the banded and clumpy distribution in the city center, and forms sub-cores in some new towns, transportation hubs, and tourist islands. Compared with traditional hotels, the shared accommodation is more affected by the road network form, and has higher requirements for traffic passing ability and neighborhood interaction space in visiting communities. On a global scale, the shared accommodation is more inclined to consider agglomeration effects and positive spillover effects when selecting locations. At the local scale, the shared accommodation mainly forms three types of associations with urban functional space: cluster-like association, group-like association, and scatter-like association. The correlation effect between the shared accommodation and the dining space is the most significant. This paper has theoretical significance and practical value for accurately understanding the multi-scale spatial distribution pattern of shared accommodation under the diversified consumption demands of modern cities, promoting the diversified and sustainable development of the urban accommodation industry, and guiding the rational and orderly allocation of urban recreational service resources.

The distribution characteristics, accessibility, fairness, and other spatial configuration of urban public sports facilities are directly related to the equality of basic public services and the integrity of urban spatial structure. Taking Beijing as an example, this paper uses POI data to characterize urban public sports facilities, and uses kernel density estimation, nearest neighbor index, improved two-step mobile search method, and coverage index analysis methods to study the spatial agglomeration characteristics of urban public sports facilities at the street scale in Beijing, as well as the accessibility and fairness from the perspective of supply and demand. The results show that: (1) The improved two-step mobile search method considers the supply scale of public sports facilities at different levels of cities and the travel distance of residents under the concept of "15-min life circle", which is suitable for the accessibility analysis of block level and community level sports facilities. The spatial accessibility of block level and community level facilities in central urban areas is higher; (2) There is a significant spatial agglomeration trend of public sports facilities at all levels in Beijing. The block-level facilities show a trend of "point-like agglomeration and area-like dispersion", and the district-level facilities show a "core-edge" pattern, with more facilities in the central city and less in the surrounding areas. Community-level facilities are in the mode of "small agglomeration and large dispersion", with a uniform spatial distribution; (3) There are many streets with high coverage of public sports facilities at the community level in Beijing, and the spatial allocation is well balanced. There are few streets with high coverage index of public sports facilities at the block level, and the coverage is relatively limited. The results can provide reference for the planning and optimization of public sports facilities in Beijing.

Effective identification of the spatial characteristics of tourism resource supply and demand is the key to enhancing the efficiency of tourism resource utilization, optimizing the spatial layout of tourism resources, and promoting high-quality tourism development. With the development of spatial information technology, multi-source data have expanded new research perspectives for the spatial matching of tourism resources supply and demand and their interaction. Particularly, the mining of POI and digital footprints provides powerful data support for the study of matching tourism resources supply and demand. This study selects the Jiaodong Economic Circle in Shandong Province as the study area and obtains POI data of tourism resources and "O-D" data of tourism flows in the Jiaodong Economic Circle from 2016 to 2021 based on multi-source data channels, such as Gaode Map, Tongcheng, and Mafengwo online travelogue platform. The results show that: (1) The tourism resources of the Jiaodong Economic Zone are characterized by a decreasing quantitative structure of "recreation and leisure, public leisure, ornamental science and culture, and religious rituals", and a spatial distribution of "overall concentration and local dispersion"; (2) Tourism flows are temporally distinctive in terms of holiday effects and seasonality, and spatially there are significant differences between "land and sea", with a spreading trend from coast to land before the epidemic, and a gradual recovery of tourism flows after the normalization of the epidemic. In terms of tourism demand types, recreation and leisure and public leisure are the dominant types of tourism demand; (3) The spatial structure of the supply-demand matching relationship of tourism resources can be divided into three main types: supply-demand balance, supply-led, and demand-led. This study expands the application boundary of tourism resource supply and demand matching based on multi-source heterogeneous data, and provides a theoretical basis and methodological support to promote tourism resource supply and demand matching in the Jiaodong Economic Circle and similar coastal areas.

Food attracts a large number of foodie tourists to travel together. Although previous research has discussed food tourism mainly from the point of view of customer satisfaction, there is still an evident gap in our knowledge about the travel behavior of foodie tourists and the influences of their travel partners on travel patterns. This paper uses travel diary data from Qunar.com and takes foodie tourists in Chongqing, China as an example to analyze the influence of travel partner types on tourists' "dining trajectories". In this paper, we proposed a research framework for the dining behavior characteristics of foodie tourists from the perspective of travel partners based on travel diaries. As restaurants have the characteristics of various categories and dense distribution, the characteristics of tourists' dining behavior were explored from two aspects: food types and spatial distribution of restaurants. Firstly, the foodie tourists' dining behavior network (the flow network between food types and the flow network between restaurants) was constructed. Secondly, the social network analysis of food network was carried out, and the changes of community relationship between food types were explored by community detection and the results of food network structure index analysis. Then the social network analysis of the restaurant network was carried out, and foodie tourists' dining behavior characteristics were explored by structural indicators of the restaurant network. The results show that: (1) The food network characteristics of tourists with different travel partner roles differed significantly. The nodes of food network of solo tourist (no travel partners) were not connected closely, while the food network of other travel partner role showed obvious small-world characteristics; (2) The role of travel partners influenced tourists' choice of specialty food types. In particular, solo tourists showed a "passive and conservative" type of dining, tourists with three or five friends showed a "try all the specialties" type of dining, and tourists with other travel partner roles showed a "casual/interesting" dinning behavior; (3) The characteristics of restaurant network of tourists with different travel partner roles differed significantly. The restaurant network of travel partners as a couple showed obvious small-world characteristics, while the nodes of restaurant network of other travel partner roles were not connected closely. The results provide basis for destination marketing organizations to formulate marketing material and dining route recommendations for foodie tourists. In the future, it is necessary to understand the impact of interpersonal relationships on human mobility and develop spatiotemporal analysis theory and models for dealing with mobile location big data.

Revealing the spatial-temporal behavior patterns of tourists is an important research focus in tourism geography. Trajectory big data mining provides a new way for better understanding tourists' spatial-temporal behavior. However, current research on the spatial-temporal behavior patterns of tourists is mainly based on the analytical framework of individual behavior in time geography, which makes it difficult to extract behavior patterns when dealing with large samples of trajectory data at larger scales. GPS records the user's location information periodically, capturing attributes such as time, space, speed, and direction, with a strong continuity, and travelers can record their own itinerary at any time with their cell phones and upload it to outdoor tourism websites. These processes not only effectively enhances the accuracy of the data but also offers unique advantages in researching travelers' behavior patterns. In this paper, the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm is improved by incorporating temporal, spatial, and directional similarity information, and a typical red tourist destination is selected as the study case using GPS trajectories from 2010 to 2019. The results show that: (1) The research framework and methods constructed in this study are novel, and they effectively extract and reveal the spatial-temporal behavior pattern of tourists in Zunyi City; (2) Red tourism in Zunyi City mainly consists of half-day tours, and summer is the peak season for red tourism; (3) There are six types of red tourism behavior, namely "red + shopping and entertainment", "red + historical culture", "red + mountaineering tourism", "red + ecological leisure", "red + ancient town tourism", and "red + rural tourism", mainly distributed in the northwest, southeast, and southwest of Zunyi City, with a travel length ranging from 12.03~18.42 km and a travel duration ranging from 0.65~13.60 h; (4) A total of 24 tourist routes are extracted from all patterns, including all-red tourist routes (58.33%) and mixed routes (41.67%), with an average length of 17.69 km and an average duration of 2.36 h. Especially, the former Zunyi Conference site is the most popular tourist destination, accounting for 38.46%; (5) The red tourist routes in Zunyi City primarily rely on the Rongzun Expressway, Lanhai Expressway, Hangrui Expressway, and Zunyi Ring Expressway. The method proposed in this paper can be used in the study of tourism behavior patterns and route mining in other regions, and the results of this paper can provide a basis for the optimization of the spatial pattern and route planning of red tourism in Zunyi City.

Spatial behavior reflects tourists' choice and preference for the land and function of tourist areas, which is very important for the management decision of tourist destinations. Based on the complex network analysis of tourists' spatial behavior and mining the correlation characteristics between tourist blocks, the explicit and implicit association rules between land use and function can be explored, the spatial structure of tourist areas can be accurately identified, and the development status of tourist areas can be deeply grasped, which provides support for smart tourism and fine land transformation. Taking Gulangyu Island, a world cultural heritage, as a case, this study extracts tourists' spatial behavior through location-based service big data, analyzes the characteristics of tourists' trajectory network by using complex network, explores the correlation characteristics between the internal land use of tourist areas based on tourists' spatial behavior by using association rule algorithm, and then analyzes the block association rules based on tourists' spatial behavior of different gender, age and source areas by using user portrait data. It is found that the algorithm of "complex network + association rules" can mine the hidden rules in tourists' random behavior and effectively analyze the explicit and implicit association rules between tourist blocks. In the trajectory network of tourists' spatial behavior, each block has both the functions of "center" and "hub". Popular tourist blocks that serve both local tourists and foreign tourists show strong association rules. Popular scenic spots with strong attraction to foreign tourists show high support, and the land for tourist facilities with characteristics shows high promotion. There is a strong correlation between homogeneous tourist blocks, and the difference of population characteristics has a significant impact on the association rules of tourist blocks. Theoretically, this study can enrich the cognition of tourism behavior, especially the relevance of land use caused by behavior, and construct association rules according to different demographic characteristics to supplement the demonstration of tourist demographic characteristics; In terms of methods, this study comprehensively uses complex network and association rule algorithm, which can more accurately fit the node and hierarchical structure of tourist behavior network, mine land association rules that are difficult to find by traditional methods, and provide new ideas for the coupling analysis of tourist behavior and tourist area land; In practice, based on the spatial behavior of tourists, the spatial structure of land use in tourist areas can be accurately identified, the development status of tourist areas can be more deeply grasped, the functional layout can be optimized, and the tourist facilities can be improved, thus providing support for smart tourism and fine land transformation.

Exploring the relationship between walking behavior characteristics and the functional layout of tourist areas by studying the walking track and behavior characteristics of tourists in walking tourist areas is helpful to optimize the functional layout and spatial pattern of walking tourist areas. Based on the mobile phone positioning data that recorded massive individuals' time and space tracks, Gulangyu Islet during the National Day Golden Week is taken as a case, and the spatial analysis method is used to analyze the characteristics of tourists' walking behavior and its relationship with the functional layout from the aspects of the spatial distribution of walking tourists, the network structure of walking tracks, the walking path and speed between blocks, and the walking speed within blocks. Compared with the planning documents, some suggestions are put forward for the development of tourist areas. It is found that the spatial layout of tourist areas has a direct impact on the characteristics of tourists' walking behavior. The functional layout results in the difference in visiting rate and the centrality of each block in the walking track network. Tourists are more inclined to choose streets with more walking people as routes. Although the commercial blocks are crowded with tourists, the flow of tourists on the streets is not large. In the popular scenic spots, the congestion caused by the single tour route leads to the low willingness of tourists to stay. Large-scale development and the lack of interactive experience make natural landscape areas and some popular scenic spots less attractive to tourists. By comparing the spatiotemporal characteristics of tourists' walking with the functional layout of tourist areas, the optimization strategy of functional layout is put forward. This study provides quantitative support for the optimization of land use and tourist routes in tourist areas and has practical significance for smart tourism and high-quality urban construction.

. Online travel notes are self-reported records published by tourists on the Internet, which describe the process of their trip and experience. Extracting itinerary chain from online travel notes and analyzing itinerary structure, can provide important reference for tourists' itinerary formulation and route design. The traditional itinerary extraction mostly relies on manual recognition, and some methods proposed in current studies require extensive data annotation, which is a large workload. Automatic extraction of itinerary chain from online travel notes accurately can improve the efficiency of data processing, which is an open issue and worth of study. In this paper, a syntactic rule-based travel chain extraction method was proposed based on natural language processing technology, which includes the identification of travel nodes, the recognition of nodes order and the generation of itinerary chain. First of all, the paragraph structure and expression characteristics of itinerary in online travel notes were analyzed, and the syntactic expression rules of travel nodes and nodes order were summarized based on word segmentation and dependency syntax analysis of related statements. Secondly, the travel nodes matched by syntactic rules, can be divided into deterministic travel nodes, uncertain travel nodes and non-travel nodes. Thirdly, through regular expression and syntactic rules match, the order of travel nodes was recognized from the specific itinerary description statement. Finally, the uncertain travel nodes were distinguished based on nodes context analysis, and the sequential and cross-arranged travel nodes were merged and connected in series. Meanwhile, the order of nodes in the connected series were verified and adjusted based on previously recognized node orders, and the itinerary chain was generated. In order to verify the effectiveness of proposed method, 17 226 online travel notes text data of Nanjing city were collected on Mafengwo platform, and the longest common subsequence algorithm was used to carry out the experimental verification. Through comparative analysis, the similarity between the extracted result by this method and the real travel chain identified by manual is 86.14%, which is higher than the BERT-BiLSTM-CasRel deep learning model in the field of entity relation extraction (83.1%). Compared with the existed relation extraction method in deep learning field, the proposed method is more convenient in calculation and does not require extensive data annotation. The limitation of method is the construction of regional travel site directory. In the future work, the strong semantic understanding ability of large language model would be carried out to improve the accuracy and data processing efficiency in itinerary chain extraction.

Prediction of users' geolocation plays an important role in location-based applications such as natural disaster monitoring, flu trend prediction, and targeted advertising promotion. Integrating multi-source information, mining user behavior characteristics, and analyzing user social attributes can help improve prediction accuracy and reduce distance error. Existing methods primarily rely on textual content and social networks for location prediction without considering the fusion of these two types of information, and have difficulty in predicting the locations of isolated users in social networks. Therefore, this paper proposes a home location prediction method for social network users integrating text topic and social relationship graph neural network. In the method, first, hybrid features are extracted from text content, using TF-IDF to obtain text feature vectors, and an initial social relationship graph is established based on the mentioned information between users. Then, to address the issue of isolated users in the user social relationship graph and difficulty in estimating their locations, a topic model is established to establish connections for isolated users based on topic vector similarity and supplement the social relationship graph. Finally, based on graph convolutional neural network, social relationship graph data are processed, and text features and network structure are jointly modeled to effectively predict users' geolocation. The effect of topic similarity threshold on prediction performance and graph size is explored on a real-world benchmark dataset GeoText. The experimental results show that our method is able to aggregate most of the user nodes belonging to the same class and increase the proportion of locatable users. The network constructed using multiple types of relationships can maintain the diversity of user relationships and can achieve better prediction accuracy of graph neural network. SRGCN outperforms the existing methods in terms of the average distance error, the median distance error, and the prediction accuracy, which indicates that the multi-view feature learning model is superior for geolocation prediction compared to models based on a single source of information. On the GeoText dataset, the Acc@161 of SRGCN is 1% higher than that of GCN method, and the average error distance is reduced by 16km, which indicates that the SRGCN method is more competitive than the existing best-performing method. Our experimental results demonstrate the effectiveness of SRGCN, which can improve the accuracy of home location prediction of users.

Under the current new development pattern of "dual circulation", the hotel industry meets new opportunities for growth. In this study, we select two areas with distinct environmental differences as study locations, i.e., the Confucius Temple (historical and cultural district) and Xinjiekou (urban commercial center). Using the texts of 12 hotels on Ctrip as the data source, we construct a deep learning model using CNN-BiLSTM-ATT to explore the two-factor tourist hotel experience and analyze the mechanism of the differences. The results show that: (1) The deep learning method using CNN-BiLSTM-ATT provides a systematic theoretical framework for studying hotel experience for better understanding of the characteristics of tourist hotel experience and the mechanism of the differences; (2) The two-factor tourist hotel experience vary significantly under different environmental conditions. Tourists’ motivating experience in the hotels of Confucius Temple involves factors such as location landmarks and dining experiences, while in Xinjiekou, it relates to factors such as entertainment experience and hotel atmosphere. The hygiene experience of tourists in the hotels of Confucius Temple involves factors such as parking facilities and room size; while in Xinjiekou, it relates to factors such as elevator facilities and parking facilities; (3) There are differences in the mechanisms of tourists' two-factor experience. Tourists’ motivating experience of hotels is mainly related to external factors such as location landmark and entertainment experience, while the hygiene experience is mainly related to internal factors such as room size and room sound insulation. This study expands the application of deep learning approach in the study of tourist experience in hotels, providing references for the hotel resilience construction and high-quality development.

Streets are an important attraction for urban tourism. Exploring the influence of street landscape color characteristics on tourists' emotional perception holds important reference value for the rational planning and layout of urban street landscape. This study takes the built-up area within the third ring road of Xi'an city as a study case, and employs the Full Convolutional Neural Network (FCN) and Random Forest (RF) algorithms to construct an emotional perception dataset of street images. We use the streetscape images as the basis to extract the color features of the streetscape using machine learning algorithms, and color quantifiers are constructed and spatially visualized; The RF regression algorithm is used to explore the relationship between streetscape color characteristics and tourists' emotional perception, and the optimal color characteristic parameters are derived. The results show that: (1) There is a distinct spatial distribution pattern of tourists' emotional perception. The emotions of beauty and liveness gradually increase from the central area outward, and emotions of safety and wealth emotions score higher in the area within the second ring road outside the main city. While boring emotions score lower in this area, and depressing emotions gradually decrease from the central area outward. This suggests that the spatial distribution pattern of emotional perception shares somewhat homogeneity between tourists' emotional perception in non-routine environment and residents' perception in familiar environment; (2) The color characteristics of the streetscape show a complex non-linear relationship with tourists' emotional perception. For example, color complexity has less effect on emotions of beauty and liveness compared to color coordination and has a greater effect on emotions of boredom, depression, safety, and wealth than color coordination. Moreover, when the value of color complexity is 0.86 and the value of color coordination is 0.84, tourists can obtain better emotional perception across six dimensions; (3) Under non-routine conditions, the more significant the color characteristics of the street landscape, the better the emotional perception of visitors. Theoretically, this study confirms the conclusion that the more colorful environment leads to better experience for tourists; and methodologically, this paper not only expands the traditional text-based and manually-assigned research methods in the field of tourism emotion, but also enriches the application of streetscape big data and machine learning methods in the field of tourism. This study provides a reference for city managers to understand tourists' visual preferences for streetscapes and to optimize streetscape design.

With China entering the stage of high-quality development in an all-round way, high-level urban leisure supply becomes increasingly important. It is of great significance to systematically explore the relationship between urban leisure supply and residents' mental health to meet people's yearning for a better life. Therefore, this paper calculates the residents' Psychological Distress Index (PDI) from 2011 to 2019 based on Baidu index, applies spatial autocorrelation analysis to specify the spatial-temporal pattern of PDI, and uses stepwise regression analysis to further explore the relationship between PDI and leisure facilities with economic, population, and environmental factors controlled. The results show that: (1) In recent years, the PDI of the whole country and sub-regions has been rising continuously; (2) The more developed the region/city, the higher the PDI of residents. PDI presents a decreasing pattern of East-Central-Northeast-West. It also shows a significant spatial agglomeration, with high-high, low-high, high-low, and low-low agglomeration patterns from the coast to the inland; (3) PDI is significantly associated with the supply level of commercial leisure facilities at night (e.g., midnight snack, bar, and KTV), but not significantly associated with that in the daytime (e.g., shopping mall and cinema). The density of midnight snack, which reflects the degree of overtime work, is significantly positively associated with PDI. While as typical nightlife places, the densities of bars and KTV are significantly negatively associated with PDI. Besides, typical public leisure facilities (e.g., park) can effectively alleviate PDI. This study tentatively verifies the correlation between residents' PDI and different leisure facilities. Such effort offers a better understanding of urban health problem and how to cure it. It is important to improve the pedigree and enrich the supply of urban leisure facilities, so as to meet residents' demand for high-quality leisure life and promote their mental health.

With the widespread application of information technology in the field of tourism, the importance of tourism information science has gradually become prominent. In order to systematically summarize the research progress of tourism information science, this paper collects and organizes research literature in the field of tourism information science at home and abroad from 2011 to 2022, and comprehensively uses literature analysis method and LDA topic model to discuss the literature overview and research progress of tourism information science under the background of interdisciplinary integration. This study summarizes that: In the past 12 years, the research on tourism information science has shown a trend of rapid growth, which has attracted the attention of many disciplines such as tourism, geographic science, environmental science and ecology, and computer science at home and abroad. However, compared to the domestic research, the international research progress in this field is more remarkable in recent years, and Chinese scholars have played an important role in international studies. The methods and theories used in the research show obvious interdisciplinary characteristics. The introduction of multi-disciplinary theories such as the spatial theory of geography, the relationship theory of journalism and communication, and the decision theory of behavior and psychology, the innovation of data acquisition methods such as wireless sensor networks, data mining, and API interfaces, and the comprehensive application of various research methods such as empirical research, model algorithms, mathematical statistics, and econometric analysis have innovated the research ideas of tourism information science. The research content focuses on the promotion of diversified technologies such as geographic information technology, data mining technology, and network communication technology in the field of tourism, and the exploration of the core topics such as tourism information spatiotemporal evolution law, tourism data mining and forecasting, tourism information behavior characteristics, and tourism information technology innovation and application. There are still problems in the field of tourism information science, such as the insufficient cooperation and exchange at home and abroad, the imbalance between theoretical research and practical application, the inflexibility of data methods and technologies, and the lack of innovative and practical research content. Finally, this paper proposes that tourism information science should accelerate the localization process of international frontier research, focus on the sorting and discussion of basic theories and concepts, emphasize the integrated application of multiple technologies and methods, and strengthen the interaction of disciplines in research application.

In order to achieve accurate high-frequency forecasts of tourist flow for tourist attractions, this study proposes a forecasting method based on LBS and deep learning techniques. This method generates spatial-temporally controllable forecasts by converting the LBS data and using the core model — Deep Bidirectional Gated Recurrent Unit (DBi-GRU) model — built based on Bidirectional Recurrent Neural Network and GRU algorithms. To test the performance of our proposed method, we take the Shenzhen Dameisha Waterfront Park as an example, and three analysis methods including fitting curves, error criteria, and DM tests are used to test the forecasting performance of our DBi-GRU model. Additionally, five other deep learning models are set as reference models to compare with our model. The experimental results show that, first, DBi-GRU model proposed in this study has ideal forecasting performance in high-frequency forecast of tourist flow for tourist attractions and yields highly accurate forecasts in peak periods of tourist flow, and its performance is much better than the other deep learning models. Second, Bidirectional Recurrent Neural Network based models, particularly the Bidirectional LSTM based model, generally provide better performance than conventional Recurrent Neural Network based models. Though the forecast accuracy of the Bidirectional LSTM based model is not as high as DBi-GRU model, there is no significant difference between their model capability. Third, using the same network parameters, GRU algorithm has higher forecast accuracy than LSTM and RNN algorithms which are used by previous researchers. This study develops a new method for high-frequency tourist flow forecasting, and the high-frequency information forecasted in this study provides information support for management tasks of tourist attraction such as crowd control, service arrangement, etc..

With the increasing demand of tourists for leisure and entertainment tourism, upland tourism area has become one of the most popular tourism destinations. Applying the emerging and efficient track recording method to dig the dynamic spatio-temporal behavior characteristics and constraints of tourists in upland tourism area at a small scale is particularly important for the route design of upland tourism area and the optimization of upland tourism products. It will also provide suggestions for deepening development and scientific management of upland tourism area. Taking Enshi Grand Canyon in Enshi Prefecture, Hubei Province as an example, this study combines GNSS track and location photo data from "six feet" platform with the scenic spot road network drawn by GIS online map and the POI data obtained from BigMap. This paper selects the conceptual model of GNSS track rasterization to express the temporal and spatial behavior characteristics of tourist tracks in Enshi Grand Canyon, attempts to explore the differences of temporal and spatial behavior characteristics between other types of tourism areas, summarizes the behavior characteristics of upland tourism area, and reveals the influencing factors of behavior characteristics through network comments and travel notes. The results show that: ① At the level of month and season, the tourist behavior in Enshi Grand Canyon is at the peak in May. The holiday effect is obvious, and short holiday tour is preferred. The behavior trajectory of tourists in off and peak seasons has no agglomeration, and the number of tourists in peak seasons is unstable which is mainly affected by climate conditions; ② The tourist behavior trajectory reaches the peak at 11 to 14 o'clock, the tour ends earlier than other types of scenic spots, and the interest points of tourists are in the well-known spot; ③ In terms of spatial distribution characteristics, the trajectory concentration of Qixingzhai scenic spot with a single path is strong controlled by temporal and spatial factors, and its behavior trajectory density is higher than that of Yunlong Difeng scenic spot; ④ All the tourists tend to take pictures in high-quality scenic spot, but there are differences in its distribution for men and women. Men's photographing behavior is mostly in polygon and linear distribution, while women’s photographing behavior is mostly in point distribution. This paper tries to explore the temporal and spatial behavior of tourists in upland tourism area with new data and methods, in the hope of promoting high quality and continuous development of upland tourism areas.

User Generated Content (UGC), as a new type of geographic big data for perceiving the physical space of tourism destination, depicts the objective environment of tourism destination from the perspective of users, which is an important way to explore the perception of tourism destination. However, the traditional tourism research has limited ability to deal with travel photos. The development of deep learning image semantic segmentation technology provides strong support for mining tourists' visual behavior patterns and exploring tourism destination environmental perception. This study proposes a framework for tourists' visual behavior model and perception evaluation, which integrates the big data of online travel photos and small data of questionnaire survey, and applies it to the case of Gulangyu Island. Firstly, 744 tourism trajectories are clustered into six types of visual behavior patterns, and visualized and spatiotemporal analysis is carried out; Secondly, based on the full convolution network algorithm, the semantics of 22 507 travel photos are quantified to explore the spatial differentiation of the elements concerned by tourists with different visual modes; Finally, through the correlation analysis of photo semantics and scene perception questionnaire and the multiple linear regression model, the overall visual perception satisfaction of tourism destination is evaluated, and the corresponding spatial optimization suggestions are put forward. The results show that: (1) the visual behavior patterns of tourists on Gulangyu Island are clustered into six categories: single point tour, island scenery tour, around the island tour, street and lane space tour, heritage building tour, and whole island tour; (2) Tourists with different visual behavior patterns have spatial agglomeration in their visual interest areas, and the transfer of visual space follows the geographical proximity effect; (3) The results of correlation analysis and model show that tourists prefer areas with high spatial openness, and the areas with lower perceived satisfaction have less photography behavior, which is the focus of environmental improvement; (4) Maximizing travel time and cost efficiency, built environment, psychological environment, and social environment are the main factors affecting tourists' visual perception. This study extends the application of artificial intelligence technology in the study of tourists' visual perception, and provides a reference for tourism destination spatial optimization.

Exploring the semantic interaction and interaction pattern of tourist attractions is useful for optimizing the tourism pattern according to the needs of tourists. Existing semantic interaction mining methods ignore the contextual vocabulary that contains human perception information in texts. And there is a lack of research that analyzes the interaction pattern. Therefore, this paper proposes a framework for fine-grained semantic interaction mining and pattern analysis between attractions. First, the contextual information between two attractions is extracted through the co-occurrence relationship of words based on the online travel notes. Then, the semantic connection between attractions is mined by using the method of keyword analysis based on TF-IDF and the method of semantic network analysis from the perspectives of discussion focus and semantic structure. Finally, we regard attraction interaction as an object and use the Spearman rank correlation coefficient and the Graph Kernel (a method for graph similarity measurement) to calculate the correlation between them. Then the network analysis method is used to explore the interaction pattern. The experiment takes Yunnan Province as the case study area, the results of the text mining using travel notes in 2018 show that: (1) The framework is feasible and applicable. The travel experience can be improved according to the needs of tourists by mining and analyzing the fine-grained semantic interaction between attractions. And the route fragments that play a key role in optimizing the tourism pattern can be found by analyzing the semantic interaction pattern of attractions; (2) Cangshan Mountain-Erhai Lake should focus on improving the natural scenery travel experience; while Dali Old Town-Erhai Lake should consider improving tourists’ insufficient attention to branded tourism resources; (3) The coexistence of the three types of semantic interaction patterns, including single-core agglomeration, single-core radial, and multi-regional cooperation, presents the characteristics of node-axes evolving and diffusing. The high betweenness centrality and cross-regional attraction interactions are important for promoting the transformation of the other two models to multi-regional cooperation to develop "global tourism". The research results can provide references for recommending tourism routes and balancing tourism patterns. In the future work, we will explore the dynamic evolution of the semantic interaction between attractions and apply the results to tourist route recommendation.

Improving the accuracy of travel route recommendation is of great significance to the field of tourism recommendation. Considering the problems of data sparsity and cold start involved in the process of travel route recommendation, a multi-objective travel route recommendation method is proposed in this article by integrating user features and group intelligence. First, we obtain scenic spot information and group intelligence data from Ctrip.com, whlyw.net, Baidu Index, and other websites, including the locations of scenic spots, the prices of scenic spots, user comments, user ratings, browsing data, etc. Second, we fuse user features and the group intelligence data to construct the comprehensive attraction index of scenic spots for different kinds of people and calculate the attraction index of travel routes. Finally, a multi-objective optimization function of tourism route recommendation is defined according to the user demand for the most efficient access to scenic spots that are most likely to be of interest to users during travel; thus, the recommendation list is generated by a multi-objective genetic algorithm (non-dominated sorting genetic algorithm-II, NSGA2). Compared to traditional travel route recommendation methods, our proposed method has following advantages: (1) We carefully consider the actual needs of users (consumer side) and the attraction of scenic spots (supplier side), ensuring that users can visit as many popular scenic spots as possible with less travelling time; (2) We consider that scenic spots, especially outdoor scenic spots, show different attraction to tourists in different time periods, and this paper takes into account the travel time of users when calculating the attraction of scenic spots to users; (3) The vehicle selected by a user has a great impact on user travel routes, and our proposed method recommends different travel routes for users according to different vehicles, which better meets user needs; (4) Since different users have different preferences for the same scenic spot, we divide user groups according to user gender, age, trip modes, and trip time, which improves the accuracy of recommendation. The experimental results show that: (1) The factors considered in this paper can effectively improve user satisfaction with the recommendation results; (2) The proposed method considers the factors that can effectively improve user satisfaction during route recommendation and provides diverse recommendation results for users with different features and needs; (3) The proposed method not only gives a higher comprehensive attraction index but also effectively reduces the time spent on the journey. Furthermore, the recommendation results are more diverse, thus contributing to the development of intelligent travel route recommendation.

Tourism development is one of the important ways to eradicate poverty. It is of great significance to study tourism poverty alleviation effect from the perspective of multidimensional poverty. In this study, we take the national-level poverty-stricken counties of the Southwest China region that have been lifted out of poverty as the study cases, and introduce the NPP/VIIRS night light data to measure multidimensional poverty. The Geographically Weighted Regression method is used to explore the multidimensional poverty reduction effect of tourism development from 2012—2019. The results show that: (1) From 2012 to 2019, the level of tourism development in poor counties in Southwest China continued to improve, showing a spatial pattern of "high in the east and low in the west", and the regional difference in tourism development decreased; (2) In the past eight years, multidimensional poverty in poor counties in Southwest China was alleviated steadily. In terms of spatial distribution, the level of multidimensional poverty gradually decreased from the west to the east, and the spatial difference tended to decrease; (3) The tourism development can alleviate multidimensional poverty in economic, educational, medical, and social security aspects at county level. There is obvious spatial heterogeneity in the intensity of tourism multidimensional poverty reduction, with Sichuan's poor counties having the highest intensity of tourism poverty reduction. Overall, the tourism poverty reduction intensity is higher in poor counties in eastern Sichuan, northern Sichuan, and southeastern Yunnan, and lower in western Yunnan, southeastern Chongqing, and western Guizhou; (4) The intensity of tourism poverty reduction is mainly influenced by the endowment of tourism resource, the level of economic development, and the location of transportation. These influencing factors promote tourism development through the development of tourism resource, the strengthening of tourism industry support, and the improvement of tourism accessibility, etc. The tourism industry has a strong industrial linkage that leads to comprehensive regional development, improving economic, educational, medical, and social security levels in poor areas, and achieving multidimensional poverty reduction through tourism development. The intensity of tourism poverty reduction in poor counties is influenced by a variety of factors, so tourism poverty reduction development needs to be considered in the context of the actual situation. The effectiveness of tourism in reducing poverty can be improved by increasing the competitiveness of tourism products and improving transport conditions. In addition, the study finds that the measurement of multidimensional poverty based on night light data has a high accuracy and can provide data support for poverty research. The findings of the study have important reference value for the implementation of China's tourism poverty alleviation strategy, especially for the prevention of poverty return after 2020.

With the continuous development of modern information technology, GIS has been widely used in tourism fields, especially on all aspects research of tourism resources, including the tourism resources spatial classification, tourism resource monomers evaluation, tourism resource planning mapping, tourism resources management, tourism resources development and utilization, which have obtained the significant achievements. The analysis of the current situation and trend of GIS in the research and application of tourism resources in China is of great significance to understand the theoretical technology system and guide the application of tourism resources. Firstly, this paper reviews the literature in which GIS is used in the research of tourism resources for recent years. According to the study, we found that the GIS theory and method have made substantial progress on the mapping and evaluation of tourism resources. However, the cognition, classification and evaluation of tourism resources remain unsolved problems which included spatial scale and dimension, types of recognition and switching, spatial coupling, the transformation relationship between resources and products, development sequence, etc. However, there are still some unsolved problems in the fields, such as tourism resources cognition, classification and evaluation. Secondly, through summarizes the predecessors' research achievements and group for many years, tourism resources survey, evaluation, planning experience, the paper systematically discusses the tourism resources cognition, tourism resources classification, tourism resources standardization and tourism resources evaluation. At the same time, the paper also discusses the GIS spatial analysis method applies to the regional difference of tourism resources, tourism traffic location, spatial combination analysis, trend prediction and the spatial correlation analysis. Through combing GIS modeling and spatial analysis methods in the tourism resources information extraction and analysis, evaluation of tourism resources, tourism resources development planning and other relevant studies,we found that tourism resources research methods changed from qualitative description to quantitative model, and the application results continued to increase, involved in the comprehensive evaluation, spatial structure optimization, spatial layout and site selection, space development trend forecast, space utilization planning, etc. Finally, we put forward the trend of tourism resources in the future, regarding the knowledge model, knowledge mapping, multidimensional simulation and big data of the tourism resources. The trend of the integrated development of GIS and tourism resource research focuses on the innovation of spatial thinking mode and technological method. The new research includes that increasing GIS scholar invested in the research of tourism resources, building a case for the development of tourism resources and the knowledge model, an intelligent dynamic 3d visualization, increasing the immersion, experience and spatial decision making of tourism researchers and tourists.