Tourism management system and method based on big data analysis

Abstract

The invention discloses a tourism management system and method based on big data analysis, and relates to the technical field of tourism management, and the method comprises the steps: obtaining the position information and movement information of tourists in a scenic spot; according to the position information and the movement information of the tourists in the scenic area, whether project recommendation needs to be carried out on the tourists or not is judged, and if project recommendation needs to be carried out on the tourists, project recommendation in the scenic area is carried out on the tourists; if not, continuously monitoring the position information and the movement information of the tourist in the scenic area; according to the information of the items visited by the tourists, the probability that the tourists select visited items is determined, the probability that the tourists select non-visited items is determined based on the probability that the tourists select the visited items, and the items in the scenic spot are recommended for the tourists based on the probability that the tourists select the non-visited items; the state of the tourist is analyzed, project recommendation and path planning are performed after the tourist completes the tour target of the tourist, the project recommendation and path planning effects are improved, and the tourist experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tourism management, and in particular to a tourism management system and method based on big data analysis. Background Art

[0002] With the improvement of people's living standards and the change of consumption concepts, the tourism industry has developed rapidly. The global tourism industry has shown a trend of sustained growth and has become an important part of the world economy. Various countries and regions are actively developing the tourism industry and providing diversified tourism products and services. Big data and artificial intelligence technologies are widely used in tourism market analysis, tourist behavior analysis, tourism product recommendations, etc., to help tourism companies better understand market demand and tourist needs. At present, the route planning for tourists in scenic spots does not take into account the status of tourists, and the recommendation effect is not good; when tourists arrive at the scenic spot for sightseeing, they have a high intention to visit some projects and tend to give priority to visiting. Before the user has visited all the projects he wants to visit, the route planning for tourists is not effective, which is easy to be ignored by tourists and will also affect the tourists' tour experience; for this reason, how to recommend projects and route planning within the scenic spot for tourists based on the status of tourists, and then provide tourists with experience, has become an urgent problem to be solved. Summary of the invention

[0003] The purpose of the present invention is to provide a tourism management system and method based on big data analysis to solve the problems raised in the above background technology.

[0004] In one aspect of the present invention, a tourism management method based on big data analysis is provided, comprising:

[0005] S11, obtaining the location information and movement information of the tourist in the scenic area through the permission granted by the tourist;

[0006] S12, judging whether it is necessary to recommend projects to tourists based on the location information and movement information of tourists in the scenic area, and if so, recommending projects to tourists in the scenic area; if not, continuously monitoring the location information and movement information of tourists in the scenic area;

[0007] S13, based on the information of the projects that the tourists have visited, determine the probability that the tourists will choose the projects that they have visited, determine the probability that the tourists will choose the projects that they have not visited based on the probability that the tourists will choose the projects that they have visited, and recommend projects in the scenic area to the tourists based on the probability that the tourists will choose the projects that they have not visited.

[0008] In step S12, the process of determining whether to recommend an item to a tourist based on the tourist's location information and movement information in the scenic area further includes the following steps:

[0009] According to the characteristics of the project, if the project can only provide tourists with a fixed tour duration, the project will be assigned a short tour label, otherwise the project will be assigned a long tour label; when the tourist is in project A, the tourist's tour time in project A is obtained in real time. If the tour time is not less than the tour time threshold of project A, and project A has a short tour label, it is determined that the project needs to be recommended to the tourist; otherwise, it is determined that there is no need to recommend the project to the tourist.

[0010] The scenic area includes a variety of different projects, some of which can only provide tourists with a fixed tour time, such as amusement facilities with fixed operating hours; while some projects provide tourists with non-fixed tour time, such as scenery projects. When tourists stay too long in a project that can only provide tourists with a fixed tour time, it means that the tourists may not have a specific tour destination next, and tour projects can be recommended to the tourists at this time; the tour time threshold of project A can be determined according to statistical methods; optionally, based on the historical tour time data of project A, the average tour time and the standard deviation of the tour time of project A are calculated, and the tour time threshold of project A is set to the sum of the mean and three times the standard deviation.

[0011] The location information of tourists in the scenic area can be determined through the RFID tags embedded in the maps, tour guides, tickets, etc. issued by the scenic area; when the RFID tag of the tourist is read by a specific point of the project, it is judged that the tourist is in the project, the tourist’s visit time in the project is accumulated, and the visit time is monitored; when the RFID tag of the tourist is read by other projects or specific points on the road section, the time difference between the two readings is the tourist’s complete visit time in the project.

[0012] In step S12, the process of determining whether to recommend an item to a tourist based on the tourist's location information and movement information in the scenic area further includes the following steps:

[0013] When a tourist is on a road section, the moving time and moving speed of the tourist in the road section are obtained, and the moving speed V is calculated by the following formula: V=L / T, where L is the length of the road section, and T is the moving time of the tourist in the road section; the moving time and moving speed are monitored, and if the moving time is not less than the time threshold of the road section or the moving speed of the tourist in the road section decreases abnormally, it is determined that project recommendations need to be made for the tourist, otherwise it is determined that project recommendations do not need to be made for the tourist.

[0014] Optionally, based on the historical movement time data on the road section, the average movement time and the standard deviation of the movement time on the road section are calculated, and the movement time threshold on the road section is set to the sum of the average value and three times the standard deviation; the abnormality caused by the reduction in movement speed is determined by analyzing the movement speeds of tourists on other sections of the road, and the movement speeds of customers on other sections of the road are calculated respectively, and then the box plot method is used to determine whether the movement speed of customers on the current section is too low and an abnormality occurs; since the customers have not completed the movement behavior on the road section, the final movement speed of all customers will be lower than the current calculated value, which can increase the lower edge of the box plot.

[0015] In step S13, determining the probability of a tourist selecting a visited item further comprises the following steps:

[0016] S41, after determining that it is necessary to recommend an item to the tourist, obtain the items that the tourist has visited and arrange them in order of visiting to obtain a set U, U = {A1, A2, ..., An}, A1, A2, ..., An represent the items that the tourist has visited, and n is the number of items that the tourist has visited;

[0017] S42, from the historical tour data of the scenic spot, obtain the tour data of historical tourists from the starting point to the project An, and determine the probability IA1, IA2, ..., IAn of tourists selecting the projects A1, A2, ..., An based on the tour data of the historical tourists; let the similarity between the tour data of the k-th historical tourist and the tour data of the current tourist be simk, simk = nk / NK, let the set of all the projects visited by the k-th historical tourist from the starting point to the project An be V, then NK is the number of elements in the union of the set U and the set V; nk is the number of elements in the intersection of the set U and the set V, in which the tour order of the k-th historical tourist and the current tourist is the same;

[0018] S43, let the probability of tourists choosing the i-th item Ai be IAi, then IAi=∑ k＝1 N (simk×signik) / N, where signik is the sign coefficient. When the kth historical tourist’s travel data includes item Ai, signk is 1, otherwise signik is 0; N is the total number of historical tourists’ travel data.

[0019] When tourists are touring in a scenic area, they may only have clear needs for some projects. In the process of going to projects with clear needs, if there are projects that can be visited along the way, tourists have a probability of visiting the projects along the way; therefore, the projects visited by tourists are not necessarily the projects that tourists have a need to visit, but may also be visited along the way; therefore, it is necessary to determine which projects tourists really need to visit and which projects are just along the way based on historical data, and reflect tourists' demand for projects through probability; when tourists have visited all the projects they want to visit, the state of not needing to recommend projects to tourists is changed to needing to recommend projects to tourists, and the project that the tourist visited last is the project that the tourist wants to visit;

[0020] In order to determine the tourists' demand for the project, the historical data of other tourists are used; the higher the similarity between the historical data of other tourists and the current tourist, the greater the contribution to the probability, and the similarity is determined based on the projects visited by other tourists and the current tourist; when tourists go to projects with clear demand, even if they are on the way, the distance of other projects will also affect whether tourists visit them. When the distance is too far, tourists will not visit other projects even if they are on the way, and different tourists have different acceptance of distance, so the similarity is related to the projects visited by the current tourist and the projects visited by historical tourists. When the historical tourists visit the same projects as the current tourists, When the visited items are exactly the same, the similarity is the largest, and when they are not exactly the same, the similarity is smaller. In addition, the tour order can also reflect the preferences of the current tourists. For the items visited by both the current tourists and historical tourists, the similarity between the historical tourists and the current tourists is determined based on the items with the same tour order. For example, the current tourist visited items A1, A2, A3, and the historical tourist visited items A1, C1, C2, A3. The intersection elements of the two are A1 and A3. Only the relative order of A1 and A3 is analyzed. Since the current tourist and historical tourists visited A1 and A3 in the same order, the number of elements with the same tour order is 2.

[0021] In step S13, the method of determining the probability of a tourist selecting an unvisited item based on the probability of a tourist selecting a visited item further includes the following steps:

[0022] S51, let Bj represent the jth project that has not been visited by tourists, and analyze the influence of the i-th project Ai on Bj; from the historical visit data of the scenic spot, respectively calculate the probability P1ij that the project Bj is visited when the historical tourists have not visited the project Ai and the probability P2ij that the project Bj is visited when the historical tourists have visited the project Ai. If there is no significant error between P1ij and P2ij, it is judged that the project Ai has no influence on the project Bj. If there is a significant error, it is judged that the project Ai has an influence on the project Bj. Indicates that project Ai has not been visited, NUM1 is the number of historical tourists who have not visited project Ai, num1 is the number of historical tourists who have not visited project Ai and visited project Bj; P1ij = P{Bj|Ai} = num2 / NUM2, NUM2 is the number of historical tourists who have visited project Ai, num2 is the number of historical tourists who have visited project Ai and Bj;

[0023] S52, calculate the probability IBj that tourists choose the unvisited items, Where sj is the symbolic coefficient. When it is judged that project Ai has no influence on project Bj, sij is 0, otherwise sij is 1; P{Bj}=num / NUM, NUM is the number of historical tourists, and num is the number of tourists visiting project Bj.

[0024] In step S13, the step of recommending items in the scenic area to tourists based on the probability of tourists selecting unvisited items further includes the following steps:

[0025] S61, taking the projects that tourists have not visited and the end point of the scenic spot as vertices, and the road sections connecting the vertices as edges, to generate a directed weighted graph of the scenic spot, for the road section pointing to the project Bj, the weight is set to the inverse of the probability IBj, and for the road section pointing to the end point of the scenic spot, the weight is set to a fixed value; arrays W and V are set, W is used to record the vertices for which the shortest path has not been found and the path weights from the vertex to the starting point An, if the vertex and the starting point are not adjacent, the path length is infinite; V is used to record the vertices for which the shortest path has been found and the shortest path weights from the vertex to the starting point An; the path weight refers to the sum of the weights of all edges included in the path; the array V initially includes only the starting point An, and the data U includes all vertices except the starting point An; project recommendations and path planning are performed for tourists through the Dijkstra algorithm;

[0026] S62, find the vertex with the shortest path from the array W, and add it to the array V; at the same time, remove the vertex with the shortest path from the array W, and update the distance from each vertex in the array W to the starting point;

[0027] S63, repeat step S62 until all vertices are traversed;

[0028] S64, find the shortest path from the starting point An to the end point of the scenic spot in the array V.

[0029] In another aspect of the present invention, a tourism management system based on big data analysis is provided, comprising: a data acquisition module, a data storage module, a data analysis module, a project recommendation module and a user interaction module; the output end of the data acquisition module is connected to the input end of the data storage module, so as to obtain the location information of tourists in the scenic area; the output end of the data storage module is connected to the input end of the data analysis module and the project recommendation module, so as to store the tour data of historical tourists; the output end of the data analysis module is connected to the input end of the project recommendation module, and judges whether a project recommendation is needed for a tourist based on the location information and movement information of the tourist, and if a project recommendation is needed for a tourist, sends a signal to the project recommendation module; if a project recommendation is not needed for a tourist, the location information and movement information of the tourist are kept monitored; the output end of the project recommendation module is connected to the input end of the user interaction module, and when a signal that a project recommendation is needed for a tourist is received, a project recommendation is made for the tourist and a route planning is performed; the user interaction module is used to provide project recommendation information and route planning information to the tourist.

[0030] The data analysis module also includes a state analysis unit and a speed calculation unit; the speed calculation unit is used to determine the speed of tourists on the road section; the state analysis unit determines the state of tourists based on the tourists' visiting time information, moving time information on the road section and moving speed information. The project recommendation module also includes a first probability determination unit, a second probability determination unit and a path planning unit; the first probability determination unit is used to determine the probability of tourists choosing visited projects, the second probability determination unit is used to determine the probability of tourists choosing unvisited projects, and the path planning unit generates a directed weighted graph of unvisited projects based on the probability of tourists choosing unvisited projects, and performs path planning and project recommendation for tourists. The user interaction module also includes an authority acquisition unit, a communication unit and an output unit; the authority acquisition unit is used to apply for the location information inside the scenic area from tourists; the communication unit is used to transmit the location information of tourists to the data storage module, and obtain the recommended projects and path planning from the project recommendation module; the output unit is used to present the recommended projects and path planning to tourists.

[0031] Compared with the prior art, the beneficial effects achieved by the present invention are: analyzing the status of tourists, recommending projects and planning routes after tourists have completed their sightseeing goals, improving the effects of project recommendations and route planning, and improving tourist experience; analyzing the probability of tourists choosing projects, recommending projects and planning routes for tourists based on the probability, making recommendations more reasonable and effective. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0033] Figure 1 It is a structural schematic diagram of a tourism management system based on big data analysis according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] In the embodiments of the present invention, please refer to Figure 1 , a tourism management system based on big data analysis is provided, comprising: a data acquisition module, a data storage module, a data analysis module, a project recommendation module and a user interaction module; the output end of the data acquisition module is connected to the input end of the data storage module, so as to obtain the location information of tourists in the scenic area; the output end of the data storage module is connected to the input end of the data analysis module and the project recommendation module, so as to store the tour data of historical tourists; the output end of the data analysis module is connected to the input end of the project recommendation module, and judges whether a project recommendation is needed for a tourist based on the location information and movement information of the tourist, and if a project recommendation is needed for a tourist, a signal is sent to the project recommendation module; if a project recommendation is not needed for a tourist, the location information and movement information of the tourist are kept monitored; the output end of the project recommendation module is connected to the input end of the user interaction module, and when a signal that a project recommendation is needed for a tourist is received, a project recommendation is made for the tourist and a route planning is performed; the user interaction module is used to provide the project recommendation information and the route planning information to the tourist.

[0036] The data analysis module also includes a state analysis unit and a speed calculation unit; the speed calculation unit is used to determine the speed of tourists on the road section; the state analysis unit determines the state of tourists based on the tourists' visiting time information, moving time information on the road section and moving speed information. The project recommendation module also includes a first probability determination unit, a second probability determination unit and a path planning unit; the first probability determination unit is used to determine the probability of tourists selecting visited projects, the second probability determination unit is used to determine the probability of tourists selecting unvisited projects, and the path planning unit generates a directed weighted graph of unvisited projects based on the probability of tourists selecting unvisited projects, and performs path planning and project recommendation for tourists. The user interaction module also includes an authority acquisition unit, a communication unit and an output unit; the authority acquisition unit is used to apply for the location information inside the scenic area from tourists; the communication unit is used to transmit the location information of tourists to the data storage module, and obtain the recommended projects and path planning from the project recommendation module; the output unit is used to present the recommended projects and path planning to tourists.

[0037] In an embodiment of the present invention, a tourism management method based on big data analysis is provided, comprising:

[0038] S11, obtaining the location information and movement information of the tourist in the scenic area through the permission granted by the tourist;

[0039] S12, judging whether it is necessary to recommend projects to tourists based on the location information and movement information of tourists in the scenic area, and if so, recommending projects to tourists in the scenic area; if not, continuously monitoring the location information and movement information of tourists in the scenic area;

[0040] According to the characteristics of the project, if the project can only provide tourists with a fixed tour duration, the project will be assigned a short tour label, otherwise the project will be assigned a long tour label; when the tourist is in project A, the tourist's tour time in project A is obtained in real time. If the tour time is not less than the tour time threshold of project A, and project A has a short tour label, it is determined that the project needs to be recommended to the tourist; otherwise, it is determined that there is no need to recommend the project to the tourist.

[0041] When a tourist is on a road section, the moving time and moving speed of the tourist in the road section are obtained, and the moving speed V is calculated by the following formula: V=L / T, where L is the length of the road section, and T is the moving time of the tourist in the road section; the moving time and moving speed are monitored, and if the moving time is not less than the time threshold of the road section or the moving speed of the tourist in the road section decreases abnormally, it is determined that project recommendations need to be made for the tourist, otherwise it is determined that project recommendations do not need to be made for the tourist.

[0042] S13, determining the probability of the tourist selecting the visited project based on the information of the projects that the tourist has visited, determining the probability of the tourist selecting the unvisited project based on the probability of the tourist selecting the visited project, and recommending projects in the scenic area to the tourist based on the probability of the tourist selecting the unvisited project;

[0043] Determining the probability of a tourist choosing a visited item also includes the following steps:

[0044] S41, after determining that it is necessary to recommend an item to the tourist, obtain the items that the tourist has visited and arrange them in order of visiting to obtain a set U, U = {A1, A2, ..., An}, A1, A2, ..., An represent the items that the tourist has visited, and n is the number of items that the tourist has visited;

[0045] S42, from the historical tour data of the scenic spot, obtain the tour data of historical tourists from the starting point to the project An, and determine the probability IA1, IA2, ..., IAn of tourists selecting the projects A1, A2, ..., An based on the tour data of the historical tourists; let the similarity between the tour data of the k-th historical tourist and the tour data of the current tourist be simk, simk = nk / NK, let the set of all the projects visited by the k-th historical tourist from the starting point to the project An be V, then NK is the number of elements in the union of the set U and the set V; nk is the number of elements in the intersection of the set U and the set V, in which the tour order of the k-th historical tourist and the current tourist is the same;

[0046] S43, let the probability of tourists choosing the i-th item Ai be IAi, then IAi=∑ k＝1 N (simk×signik) / N, where signik is the sign coefficient. When the kth historical tourist’s tour data includes item Ai, signk is 1, otherwise signik is 0; N is the total number of historical tourists’ tour data;

[0047] Determining the probability of tourists selecting unvisited items based on the probability of tourists selecting visited items also includes the following steps:

[0048] S51, let Bj represent the jth item that has not been visited by tourists, and analyze the impact of the i-th item Ai on Bj; from the historical visit data of the scenic spot, calculate the probability P1ij that item Bj is visited when historical tourists have not visited item Ai and the probability P2ij that item Bj is visited when historical tourists have visited item Ai. If there is no significant error between P1ij and P2ij, it is judged that item Ai has no impact on item Bj. If there is a significant error, it is judged that item Ai has no impact on item Bj.

[0049] ˉˉIf there is no error, it is judged that project Ai has an impact on project Bj; P1ij=P{Bj|Ai}=num1 / NUM1, Ai means that project Ai has not been visited, NUM1 is the number of historical tourists who have not visited project Ai, num1 is the number of historical tourists who have not visited project Ai and visited project Bj; P1ij=P{Bj|Ai}=num2 / NUM2, NUM2 is the number of historical tourists who visited project Ai, num2 is the number of historical tourists who visited project Ai and visited project Bj;

[0050] Optionally, it is determined whether there is a significant error between P1ij and P2ij by calculating the difference. If |P1ij-P2ij| / min{P1ij, P2ij} is not less than a set value, such as 50%, it is determined that there is a significant error between P1ij and P2ij.

[0051] S52, calculate the probability IBj of tourists choosing unvisited items, IBj=∑ i＝1 n IAi×[(1-sij)×P{Bj}+sij×P{Bj|Ai}], where sj is the symbol coefficient. When it is judged that project Ai has no effect on project Bj, sij is 0, otherwise sij is 1; P{Bj}=num / NUM, NUM is the number of historical tourists, and num is the number of tourists who visited project Bj;

[0052] The method of recommending items in the scenic area to tourists based on the probability of tourists selecting unvisited items also includes the following steps:

[0053] S61, taking the projects that tourists have not visited and the end point of the scenic spot as vertices, and the road sections connecting the vertices as edges, to generate a directed weighted graph of the scenic spot, for the road section pointing to the project Bj, the weight is set to the inverse of the probability IBj, and for the road section pointing to the end point of the scenic spot, the weight is set to a fixed value; arrays W and V are set, W is used to record the vertices for which the shortest path has not been found and the path weights from the vertex to the starting point An, if the vertex and the starting point are not adjacent, the path length is infinite; V is used to record the vertices for which the shortest path has been found and the shortest path weights from the vertex to the starting point An; the path weight refers to the sum of the weights of all edges included in the path; the array V initially includes only the starting point An, and the data U includes all vertices except the starting point An; project recommendations and path planning are performed for tourists through the Dijkstra algorithm;

[0054] For example, the weight of the path from item B1 to item B2 is the inverse of the probability IB2 of item B2; the weight of the path from item B2 to item B1 is the inverse of the probability IB1 of item B1; in particular, when the tourist is on the road section from the starting point An to other items, the starting point of the path planning is the item connected by the path. For example, the starting point An is connected to items B1, B2 and B3, and the user's current section can only reach B2 and B3, then B2 and B3 are used as starting points for path planning respectively, and finally the shortest path is taken to obtain item recommendation and path planning; in particular, when the probability of an item is 0, the weight pointing to the item is positive infinity.

[0055] S62, find the vertex with the shortest path from the array W, and add it to the array V; at the same time, remove the vertex with the shortest path from the array W, and update the distance from each vertex in the array W to the starting point;

[0056] S63, repeat step S62 until all vertices are traversed;

[0057] S64, find the shortest path from the starting point An to the end point of the scenic spot in the array V.

[0058] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0059] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A tourism management method based on big data analysis, characterized in that: The following steps are involved: S11, obtaining the location information and movement information of the tourist in the scenic area through the permission granted by the tourist; S12, judging whether it is necessary to recommend projects to tourists based on the location information and movement information of tourists in the scenic area, and if necessary, recommending projects in the scenic area to tourists; if not, continuously monitoring the location information and movement information of tourists in the scenic area; S13, based on the information of the projects that the tourists have visited, determine the probability that the tourists will choose the projects that they have visited, determine the probability that the tourists will choose the projects that they have not visited based on the probability that the tourists will choose the projects that they have visited, and recommend projects in the scenic area to the tourists based on the probability that the tourists will choose the projects that they have not visited.

2. A tourism management method based on big data analysis according to claim 1, characterized in that: In step S12, the process of determining whether to recommend an item to a tourist based on the tourist's location information and movement information in the scenic area further includes the following steps: According to the characteristics of the project, if the project can only provide tourists with a fixed tour duration, the project will be assigned a short tour label, otherwise the project will be assigned a long tour label; when the tourist is in project A, the tourist's tour time in project A is obtained in real time. If the tour time is not less than the tour time threshold of project A, and project A has a short tour label, it is determined that the project needs to be recommended to the tourist; otherwise, it is determined that there is no need to recommend the project to the tourist.

3. A tourism management method based on big data analysis according to claim 2, characterized in that: In step S12, the process of determining whether to recommend an item to a tourist based on the tourist's location information and movement information in the scenic area further includes the following steps: When a tourist is on a road section, the moving time and moving speed of the tourist in the road section are obtained, and the moving speed V is calculated by the following formula: V=L / T, where L is the length of the road section, and T is the moving time of the tourist in the road section; the moving time and moving speed are monitored, and if the moving time is not less than the time threshold of the road section or the moving speed of the tourist in the road section decreases abnormally, it is determined that project recommendations need to be made for the tourist, otherwise it is determined that project recommendations do not need to be made for the tourist.

4. The tourism management method based on big data analysis according to claim 1 is characterized in that: In step S13, determining the probability of selecting a visited item further comprises the following steps: S41, after determining that it is necessary to recommend an item to the tourist, obtain the items that the tourist has visited and arrange them in order of visiting to obtain a set U, U = {A1, A2, ..., An}, A1, A2, ..., An represent the items that the tourist has visited, and n is the number of items that the tourist has visited; S42, from the historical tour data of the scenic spot, obtain the tour data of historical tourists from the starting point to the project An, and determine the probability IA1, IA2, ..., IAn of tourists selecting the projects A1, A2, ..., An based on the tour data of the historical tourists; let the similarity between the tour data of the k-th historical tourist and the tour data of the current tourist be simk, simk = nk / NK, let the set of all the projects visited by the k-th historical tourist from the starting point to the project An be V, then NK is the number of elements in the union of the set U and the set V; nk is the number of elements in the intersection of the set U and the set V, in which the tour order of the k-th historical tourist and the current tourist is the same; S43, let the probability of tourists choosing the i-th item Ai be IAi, then IAi=∑ k＝1 N (simk×signik) / N, where signik is the sign coefficient. When the kth historical tourist’s travel data includes item Ai, signk is 1, otherwise signik is 0; N is the total number of historical tourists’ travel data.

5. A tourism management method based on big data analysis according to claim 4, characterized in that: In step S13, the method of determining the probability of a tourist selecting an unvisited item based on the probability of a tourist selecting a visited item further includes the following steps: S51, let Bj represent the jth project that has not been visited by tourists, and analyze the impact of the i-th project Ai on Bj; from the historical visit data of the scenic spot, respectively calculate the probability P1ij that project Bj is visited when historical tourists have not visited project Ai and the probability P2ij that project Bj is visited when historical tourists have visited project Ai. If there is no significant error between P1ij and P2ij, it is judged that project Ai has no impact on project Bj. If there is a significant error, it is judged that project Ai has an impact on project Bj; P1ij=P{Bj|Ai}=num1 / NUM1, Ai represents that project Ai has not been visited, NUM1 is the number of historical tourists who have not visited project Ai, num1 is the number of historical tourists who have not visited project Ai and visited project Bj; P1ij=P{Bj|Ai}=num2 / NUM2, NUM2 is the number of historical tourists who visited project Ai, num2 is the number of historical tourists who visited project Ai and visited project Bj; S52, calculate the probability IBj of tourists choosing unvisited items, IBj=∑ i＝1 n IAi×[(1-sij)×P{Bj}+sij×P{Bj|Ai}], where sj is the symbolic coefficient. When it is judged that project Ai has no impact on project Bj, sij is 0, otherwise sij is 1; P{Bj}=num / NUM, NUM is the number of historical tourists, and num is the number of tourists visiting project Bj.

6. A tourism management method based on big data analysis according to claim 5, characterized in that: In step S13, the step of recommending items in the scenic area to tourists based on the probability of tourists selecting unvisited items further includes the following steps: S61, taking the projects that tourists have not visited and the end point of the scenic spot as vertices, and the road sections connecting the vertices as edges, to generate a directed weighted graph of the scenic spot, for the road section pointing to the project Bj, the weight is set to the inverse of the probability IBj, and for the road section pointing to the end point of the scenic spot, the weight is set to a fixed value; arrays W and V are set, W is used to record the vertices for which the shortest path has not been found and the path weights from the vertex to the starting point An, if the vertex and the starting point are not adjacent, the path length is infinite; V is used to record the vertices for which the shortest path has been found and the shortest path weights from the vertex to the starting point An; the path weight refers to the sum of the weights of all edges included in the path; the array V initially includes only the starting point An, and the data U includes all vertices except the starting point An; project recommendations and path planning are performed for tourists through the Dijkstra algorithm; S62, find the vertex with the shortest path from the array W, and add it to the array V; at the same time, remove the vertex with the shortest path from the array W, and update the distance from each vertex in the array W to the starting point; S63, repeat step S62 until all vertices are traversed; S64, find the shortest path from the starting point An to the end point of the scenic spot in the array V.

7. A tourism management system based on big data analysis, characterized in that: include: Data collection module, data storage module, data analysis module, project recommendation module and user interaction module; the output end of the data collection module is connected to the input end of the data storage module, and is used to obtain the location information of tourists in the scenic area; the output end of the data storage module is connected to the input end of the data analysis module and the project recommendation module, and is used to store the sightseeing data of historical tourists; the output end of the data analysis module is connected to the input end of the project recommendation module, and determines whether it is necessary to recommend projects to tourists based on the location information and movement information of tourists. If it is necessary to recommend projects to tourists, a signal is sent to the project recommendation module; If there is no need to recommend items to tourists, the location information and movement information of tourists are monitored; the output end of the item recommendation module is connected to the input end of the user interaction module, and when a signal that an item recommendation is required for tourists is received, items are recommended to tourists and route planning is performed; the user interaction module is used to provide item recommendation information and route planning information to tourists.

8. A tourism management system based on big data analysis according to claim 7, characterized in that: The data analysis module also includes a state analysis unit and a speed calculation unit; the speed calculation unit is used to determine the moving speed of tourists on the road section; the state analysis unit determines the state of tourists based on the tourists' visiting time information in the project, the moving time information on the road section and the moving speed information.

9. A tourism management system based on big data analysis according to claim 7, characterized in that: The project recommendation module also includes a first probability determination unit, a second probability determination unit and a path planning unit; the first probability determination unit is used to determine the probability of tourists selecting visited projects, the second probability determination unit is used to determine the probability of tourists selecting unvisited projects, and the path planning unit generates a directed weighted graph of unvisited projects based on the probability of tourists selecting unvisited projects, and performs path planning and project recommendation for tourists.

10. A tourism management system based on big data analysis according to claim 9, characterized in that: The user interaction module also includes an authority acquisition unit, a communication unit and an output unit; the authority acquisition unit is used to apply for location information inside the scenic area from tourists; the communication unit is used to transmit the location information of tourists to the data storage module, and obtain recommended projects and route planning from the project recommendation module; the output unit is used to present the recommended projects and route planning to tourists.

Images