Intelligent scenic spot intelligent safety guidance system

Abstract

The invention relates to the technical field of scenic spot guidance, and discloses an intelligent scenic spot intelligent safety guidance system comprising a data acquisition module which is provided with a sensor and a camera and is used for monitoring people flow, vehicle and weather information in real time and collecting personal information, position data, health data and the like of users; the data processing and analyzing module is used for cleaning and sorting the collected data and analyzing the data by using a statistical method and a machine learning algorithm; the personalized route recommendation module is used for recommending personalized sightseeing routes to the tourists based on the tourist information; and the safety management module monitors the safety condition of the scenic spot in real time through a camera and a sensor. According to the invention, a dynamic adjustment mechanism, a real-time feedback system and a group route recommendation model are introduced, it is ensured that the recommended route always meets the actual demand of the tourist, and the comprehensive and flexible personalized recommendation mechanism can respond to the change demand of the tourist in the touring process in time and provide more comfortable, safer and personalized touring service for the tourist.

Description

Technical Field

[0001] The present invention relates to the technical field of scenic area guiding, and in particular to an intelligent safety guiding system for a smart scenic area. Background Art

[0002] The intelligent safety guiding system for a smart scenic area is an integrated management system based on technologies such as the Internet of Things, big data, and artificial intelligence, aiming to improve the safety management level of the scenic area and the tourist experience. It can monitor and divert peak crowds, monitor environmental indicators in real time, ensure safety, quickly guide tourists to evacuate, provide real-time guided tours and safety tips.

[0003] Although the intelligent safety guiding system in the prior art performs well in terms of crowd flow distribution and preventing congestion, there are significant deficiencies in personalized route recommendations. This system mainly relies on the initial interests and hobbies of tourists for route planning. This static recommendation method is too single and fails to fully consider the impact of other key factors on the tour experience. For example, the system ignores dynamic factors such as the real-time fatigue state, health condition, and weather changes of tourists during the tour, which will significantly affect the actual needs and comfort of tourists. In addition, the system is particularly weak in personalized recommendations for group tourists. Group tourists usually consist of multiple individuals, and each person's interests and physical conditions are different. The system needs to comprehensively consider the opinions and needs of all members to reach a consensus on the best route. However, the existing systems lack support in this regard and cannot effectively handle the differences that may arise in the group decision-making process, resulting in the recommended route being difficult to meet the needs of all members and easily causing internal conflicts and dissatisfaction;

[0004] In addition, the system lacks a dynamic adjustment mechanism and cannot optimize the recommended route in a timely manner according to the actual state of tourists during the tour, nor can it quickly respond and provide new route suggestions, making the recommended results out of touch with the actual needs of tourists. This static and single-dimensional recommendation method not only limits the flexibility and practicality of the system but also seriously affects the overall experience and satisfaction of tourists.

[0005] Therefore, in order to better adapt to different tourist groups and their dynamically changing needs, the system urgently needs to introduce a more comprehensive and flexible personalized recommendation mechanism, combined with real-time monitoring and data analysis, to provide more accurate and considerate services. Summary of the Invention

[0006] The purpose of the present invention is to solve the drawbacks existing in the prior art and propose an intelligent safety guiding system for a smart scenic area.

[0007] To achieve the above purpose, the present invention adopts the following technical solutions:

[0008] An intelligent safety guiding system for a smart scenic area, comprising: a data collection module: sensors and cameras are set up to monitor the flow of people, vehicles, and weather information in real time, and collect personal information, location data, health data, etc. of users; a data processing and analysis module: cleans and organizes the collected data, analyzes the data using statistical methods and machine learning algorithms, and extracts tourist information; a personalized route recommendation module: recommends personalized sightseeing routes for tourists based on tourist information; a safety management module: formulates emergency plans and conducts regular drills, and monitors the safety status of the scenic area in real time through cameras and sensors.

[0009] As a preferred technical solution of the present invention, the personalized route recommendation module includes: a route recommendation unit: sets up a personalized route recommendation mechanism, and uses this mechanism to recommend sightseeing routes for tourists; a tourist feedback unit: dynamically adjusts the sightseeing route through tourist status feedback.

[0010] As a preferred technical solution of the present invention, the personalized route recommendation mechanism includes but is not limited to: comprehensive score screening: sets up a comprehensive score model, and recommends personalized routes for tourists through this model; priority screening: selects route influencing factors, ranks the route influencing factors in priority order, and conducts step-by-step screening.

[0011] As a preferred technical solution of the present invention, the comprehensive score model is:

[0012]

[0013] Among them, where p i represents the i-th tourist, l j represents the j-th sightseeing route, S(p i , l j ) represents the comprehensive score of the i-th tourist for the j-th sightseeing route, α is a model adjustment parameter, between 0 and 1, k represents different influencing factors, w k represents the weight coefficient of the k-th influencing factor, f k (x k ) represents the scoring function of the k-th influencing factor, where x k represents the computable parameter of the k-th influencing factor.

[0014] As a preferred technical solution of the present invention, the influencing factors in the comprehensive score model include but are not limited to tourist age factors, weather factors, and cost factors.

[0015] As a preferred technical solution of the present invention, a group route score model is also set up in the comprehensive score screening. The group route recommendation model is constrained by the comprehensive score model. The group route score model is:

[0016]

[0017] Among them, S 共识度 (l j ) represents the group consensus degree score for the j-th route, and S(p i , l j ) represents the comprehensive score of the i-th tourist member for the j-th route. S avg (l j ) represents the average comprehensive score of all members for the j-th route, and q represents the total number of tourist members in the group.

[0018] As a preferred technical solution of the present invention, the tourist feedback unit includes: a custom optimization area: tourists can manually modify their own preference and physical condition information through a mobile application, and the system recalculates the comprehensive score according to the modified data by the tourists and recommends a new route; a system automatic optimization area: based on the monitored tourist status data, a route optimization mechanism is set up, and the sightseeing route is dynamically adjusted according to this mechanism.

[0019] As a preferred technical solution of the present invention, the route optimization mechanism includes: setting a tourist fatigue degree scoring model to score the tourist fatigue state; calculating the information of all remaining paths from the current position to the end point according to the current position of the tourist, and the remaining path information includes the remaining total distance, the remaining number of scenic spots, and the remaining number of rest points; setting a remaining route scoring function: S' = B1D(y) + B2A(z) + B2R(h), where D(y), A(z), and R(h) respectively represent the scoring functions of the remaining total distance, the remaining number of scenic spots, and the remaining number of rest points in the remaining route, and B1, B2, and B3 are the weight coefficients of the remaining total distance, the remaining number of scenic spots, and the remaining number of rest points respectively; calculating the score of each remaining route through the remaining route scoring function, and according to the scoring result, selecting the route with the highest score as the new recommended route.

[0020] As a preferred technical solution of the present invention, the numerical values of the weight coefficients B1, B2, and B3 are restricted by the fatigue degree of the tourists.

[0021] As a preferred technical solution of the present invention, the tourist fatigue state is scored every once in a while T, and a threshold u is set. If the difference between the current score and the previous score exceeds u, a remaining route optimization is performed, otherwise the current route remains unchanged.

[0022] The present invention has the following beneficial effects:

[0023] 1. Dynamically adjust the fatigue state: Real-time monitoring and adjustment. By introducing a real-time monitoring mechanism, continuously obtain information such as the current location and fatigue state of tourists, and dynamically adjust the selection of the remaining route based on this data, which can ensure that the recommended route always conforms to the actual state of tourists and avoid uncomfortable experiences caused by increased fatigue.

[0024] 2. Highly personalized route recommendation: Hierarchical weight adjustment. According to the characteristics of different tourist groups, design a hierarchical weight adjustment function to ensure that the weight of each factor can be flexibly adjusted according to the actual situation. This hierarchical design improves the personalization degree of route recommendation and better meets the needs of different tourists.

[0025] 3. Group consensus rating: For group tourists, introduce a group route rating model to calculate the group consensus rating of each route and select the route that best conforms to the overall preference of the group, which helps to reduce internal conflicts and disagreements and improve the overall tour experience of the group.

[0026] 4. Improve the comfort of the user experience: By setting up a fatigue degree rating model and a remaining route rating function, adjust the weights of various influencing factors in combination with the fatigue degree of tourists, so as to recommend a route that not only conforms to the interests of tourists but also is short and has many rest points. This not only improves the comfort of tourists but also effectively relieves the sense of fatigue and improves the tour satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a system block diagram of an intelligent safety guiding system for a smart scenic area proposed by the present invention.

[0028] Figure 2 It is a flowchart of a route optimization mechanism. DETAILED DESCRIPTION OF THE INVENTION

[0029] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments.

[0030] Refer to Figure 1-2 , an intelligent safety guiding system for a smart scenic area, including:

[0031] Data acquisition module: Set sensors and cameras to be used for real-time monitoring of the flow of people, vehicles, and weather information, and collect personal information, location data, health data, etc. of users.

[0032] Data processing and analysis module: Clean and organize the collected data, and analyze the data using statistical methods and machine learning algorithms to extract tourist information.

[0033] Personalized Route Recommendation Module: Recommend personalized sightseeing routes for tourists based on tourist information;

[0034] Safety Management Module: Develop emergency plans and conduct regular drills to monitor the safety status of the scenic area in real time through cameras and sensors.

[0035] Among them, the personalized route recommendation module includes:

[0036] Route Recommendation Unit: Set up a personalized route recommendation mechanism and use this mechanism to recommend sightseeing routes for tourists;

[0037] Tourist Feedback Unit: Dynamically adjust the sightseeing route based on tourist status feedback.

[0038] Furthermore, the personalized route recommendation mechanism includes, but is not limited to, two methods: comprehensive score screening and priority screening. First, set the set of tourists P = {p1, p2, p3... p n}, and the set of sightseeing routes L = {l1, l2, l3... l m}. In priority screening, the system selects route influencing factors, such as hobbies, total distance, cost, etc., ranks the route influencing factors in priority, and conducts step-by-step screening. The method of priority screening can be automatically sorted by the system based on historical data analysis or can be set by the tourists themselves. In comprehensive score screening, a comprehensive score model is set up, and through this model, personalized routes are recommended for tourists. The comprehensive score model is:

[0039]

[0040] Among them, p i represents the i-th tourist, l j represents the j-th sightseeing route, S(p i , l j ) represents the comprehensive score of the i-th tourist for the j-th sightseeing route. α is a model adjustment parameter, which is between 0 and 1. By adjusting the parameter α, a smooth transition can be made between the weighted sum and multiplication models. For example, when α = 1, the model degenerates into a weighted sum model, and when α = 0, the model degenerates into a multiplication model. This can better balance the influence of various factors, avoid a certain factor being too dominant or ignored, and provide higher flexibility, robustness, and adaptability. k represents different influencing factors, w k represents the weight coefficient of the k-th influencing factor, f k (x k ) represents the scoring function of the k-th influencing factor, where x kIt represents the computable parameter of the k-th influencing factor. Using this scoring model, the comprehensive scores of the same tourist for different sightseeing routes can be calculated, and the route with the highest comprehensive score is selected as the recommended route. When there are several sightseeing routes with the same score, the sightseeing route ranked first is default recommended. The influencing factors in the comprehensive scoring model include, but are not limited to, the tourist's physical state factor, weather factor, and cost factor.

[0041] Example 1

[0042] This example considers the tourist's physical state factor. Since there is a strong correlation between the tourist's physical state and age, the age parameter is used to calculate the scoring function f1(x1) of the tourist's physical state factor in the comprehensive scoring model:

[0043] f1(x1) = -μ(x1 – Age0) 2 +b;

[0044] where x1 is the age value of the tourist, μ is a constant used to control the opening size of the parabola to make it more in line with the actual data, and this value is determined through experiments or fitting data. Age0 is a reference age value, usually selected as the age with the best physical strength, such as 30 years old. When the tourist's age is 30 years old, the score is the highest at this time. b represents the score value at the reference age Age0, and usually b = 1.

[0045] Example 2

[0046] This example considers the weather factor and calculates the scoring function f2(x2) of the weather factor in the comprehensive scoring model:

[0047]

[0048] where x2 is the actually measured rainfall value, η is a constant used to control the attenuation rate, which is obtained through experiments or fitting data, and usually η = 1.2. B max is a reference value representing the maximum acceptable rainfall value, and usually B max = 50, that is, the maximum acceptable rainfall for tourists is 50 millimeters. Under the action of this scoring function, the scores of the indoor sightseeing routes in the scenic area will be higher than those of the outdoor sightseeing routes, and as the rainfall increases, the score gradually decreases, indicating that the impact of weather conditions on tourists' experience gradually increases.

[0049] Example 3

[0050] This example considers the cost factor and calculates the scoring function f3(x3) of the cost factor in the comprehensive scoring model:

[0051]

[0052] Among them, x3 represents the maximum consumption value that tourists can accept. λ is a constant used to control the attenuation rate, usually set to 1.5. C0 represents the total cost value of all scenic spots on this route. g(age) is an age correction factor used to adjust the cost sensitivity of tourists of different ages, making the cost sensitivity of young tourists lower and that of older tourists higher. For example, g(age) = 1 + β(age - age0), where age0 is the reference age, usually set to 30 years old, and β is a constant used to control the influence degree of age on cost sensitivity. λ ≈ 1.5, β ≈ 0.0343, age0 = 30. When there are the following three routes, the scores are as follows:

[0053] Route L1: Total cost C0 = 100

[0054] Age = 20, f3(500) ≈ 0.876; Age = 30, f3(500) ≈ 0.741; Age = 60, f3(500)

[0055] ≈ 0.667;

[0056] Route L2: Total cost C0 = 300

[0057] Age = 20, f3(500) ≈ 0.675; Age = 30, f3(500) ≈ 0.407; Age = 60, f3(500)

[0058] ≈ 0.296;

[0059] Route L3: Total cost C0 = 500

[0060] Age = 20, f3(500) ≈ 0.373; Age = 30, f3(500) ≈ 0.223; Age = 60, f3(500)

[0061] ≈ 0.048.

[0062] For young tourists such as 20-year-olds, even if the cost is high, their scores are still relatively high, indicating that they are less sensitive to costs. For older tourists such as 60-year-olds, the higher the cost, the lower the score, indicating that they are more sensitive to costs. This can reflect the different cost sensitivities of tourists of different ages and help select routes more suitable for tourists of different ages.

[0063] Substituting the scores measured in the above embodiments into the comprehensive scoring model, the score values of each route under the influence of tourists' physical states, weather, and cost factors can be calculated.

[0064] Furthermore, a group route scoring model is also provided in the comprehensive scoring screening. The group route recommendation model is constrained by the comprehensive scoring model. When there are multiple people sightseeing together, it is necessary to select a sightseeing route with the highest consensus. At this time, the group route scoring model is:

[0065]

[0066] Among them, S 共识度 (l j ) represents the group consensus score for the jth route, S(p i , l j ) represents the comprehensive score of the i-th tourist member on the j-th route, S avg (l j ) represents the average comprehensive score of all members for the jth route, |S(P i , l j )-S avg (l j )| is the absolute difference between each member's score and the average score. The smaller the absolute difference, the closer the member's score is to the group's average score, that is, the more consistent the member's opinion is with the group's opinion. q represents the total number of tourists in the group. The larger the value calculated by the group route scoring model, the closer the group members' scores on the route are, that is, the more consistent everyone's opinions are, and the higher the consensus is. On the contrary, it means that the group members' scores on the route are quite different, that is, everyone's opinions are quite different, and the consensus is low. The consensus score of each route is calculated by this model, and the route with the highest score is selected as the group sightseeing route. Using this mechanism can help reduce internal conflicts and disagreements, ensure more coordinated team actions, and improve the overall tour experience.

[0067] Furthermore, the visitor feedback unit includes:

[0068] Customized optimization area: During sightseeing, tourists can manually modify their preferences and physical condition information at any time through the mobile application. The system will recalculate the comprehensive score and recommend new routes based on the modified data;

[0069] System automatic optimization area: Based on the monitored tourist data, a route optimization mechanism is set up, and the sightseeing route is dynamically adjusted according to the mechanism. The route optimization mechanism includes:

[0070] Set up a fatigue degree scoring model to score tourists’ fatigue status. The model is:

[0071] S t =A1E+A2R(pi,t)+A3(Vavg-V(pi,t));

[0072] Among them, A1, A2, and A3 are the weight coefficients of each index, E represents the emotional score of tourists, R(pi, t) represents the number of rest times, Vavg represents the average walking speed of tourists, V(pi, t) represents the walking speed, and the higher the score, the more fatigued the tourist is;

[0073] When conducting the emotional score, facial expression recognition is carried out through cameras in the scenic area and using deep learning models such as the convolutional neural network CNN. The emotional score E ranges from [0, 1], where 0 means very non-fatigued and 1 means extremely fatigued;

[0074] According to the current location of the tourist, calculate the remaining path information from the current location to the end point, specifically including the remaining total distance, the remaining number of scenic spots, and the remaining number of rest points;

[0075] Set the remaining route scoring function:

[0076] S' = B1D(y) + B2A(z) + B2R(h);

[0077] Among them

[0078]

[0079] Among them, D(y), A(z), and R(h) respectively represent the scoring functions of the remaining total distance, the remaining number of scenic spots, and the remaining number of rest points in the remaining route. y is the currently calculated remaining total distance, D min represents the minimum value of the remaining total distance among all alternative routes, generally 0, D max represents the maximum value of the remaining total distance among all alternative routes; z is the currently calculated remaining number of scenic spots, A min represents the minimum value of the remaining number of scenic spots among all alternative routes, usually 0, A max represents the maximum value of the remaining number of scenic spots among all alternative routes; among them, h represents the currently calculated remaining number of rest points, R min the minimum value of the remaining number of rest points among all alternative routes, R max represents the maximum value of the remaining number of rest points among all alternative routes; B1, B2, and B3 are the weight coefficients of these information respectively. It is worth mentioning that B1, B2, and B3 are adjusted by the degree of fatigue. The higher the degree of fatigue, the lower the importance of distance, that is, the smaller B1, the lower the importance of the number of scenic spots, that is, the smaller B2, and the higher the importance of the rest point, that is, the larger B3.

[0080] Set a weight adjustment mechanism to link the degree of fatigue of tourists with the weights B1, B2, and B3, and select the corresponding values of B1, B2, and B3 according to the current degree of fatigue of tourists;

[0081] Calculate the score of each remaining route through the remaining route scoring function. According to the comprehensive scoring results, select the route with the highest score as the new recommended route.

[0082] For example, the remaining distance weight B1 = 0.5 + 0.5(1 - S'). When severely fatigued, reduce the weight of the remaining distance; when slightly fatigued, maintain a higher weight.

[0083] The remaining number of scenic spots B2 = 0.7 - 0.4S'. When severely fatigued, reduce the weight of the remaining number of scenic spots; when slightly fatigued, maintain a higher weight.

[0084] The remaining number of rest points B3 = 1 + S'. When severely fatigued, increase the weight of the remaining number of rest points; when slightly fatigued, maintain a higher weight.

[0085] For example, a tourist selects a route for sightseeing. When they have walked half of the way, that is, they have walked 2.5 km, and the fatigue score at this time is S t = 0.7. At this time, there are the following four remaining sightseeing routes:

[0086]

[0087] Calculate the weights according to the fatigue score:

[0088] The remaining distance weight B1 = 0.5 + 0.5(1 - 0.7) = 0.65;

[0089] The remaining number of scenic spots weight B2 = 0.7 - 0.4 × 0.7 = 0.42;

[0090] The remaining number of rest points weight B3 = 1.0 + 1.0 × 0.7 = 1.7;

[0091] Calculate the comprehensive score of each route:

[0092] The remaining sightseeing route L'1:

[0093] The remaining total distance score: D(2.5) = 0.5; the remaining number of scenic spots score: A(1.5) = 0.5; the remaining number of rest points score: R(1) = 0.2;

[0094] The comprehensive score: S' = 0.65 × 0.5 + 0.42 × 0.5 + 1.7 × 0.2 = 0.875;

[0095] The remaining sightseeing route L'2:

[0096] The remaining total distance score: D(1.5) = 0.7; the remaining number of scenic spots score: A(1) = 0.333; the remaining number of rest points score: R(1.5) = 0.3;

[0097] Comprehensive score: S' = 0.65×0.7 + 0.42×0.333 + 1.7×0.3 = 1.105;

[0098] Remaining tour route L'3:

[0099] Remaining total distance score: D(1) = 0.8; Remaining number of scenic spots score: A(1) = 0.167; Remaining number of rest points score: R(2) = 0.4;

[0100] Comprehensive score: S' = 0.65×0.8 + 0.42×0.167 + 1.7×0.4 = 1.27;

[0101] Remaining tour route L'4:

[0102] Remaining total distance score: D(0.5) = 0.9; Remaining number of scenic spots score: A(0) = 0; Remaining number of rest points score: R(2.5) = 0.5;

[0103] Comprehensive score: S' = 0.65×0.9 + 0.42×0 + 1.7×0.5 = 1.435;

[0104] Through comprehensive comparison, the score of route L'4 is the highest, and the system preferentially recommends the remaining tour route L'4 according to the fatigue level of this tourist.

[0105] Furthermore, the fatigue state of tourists is scored every period of time T, and a threshold u is set. If the difference between the current score and the previous score exceeds u, the remaining route is optimized once, otherwise the current route remains unchanged.

[0106] This method ensures that the recommended route can better adapt to the actual state of tourists, providing a more comfortable and satisfactory tour experience. Through a reasonable weight adjustment function, the system can provide the most suitable route suggestions for tourists in different fatigue states.

[0107] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and all should be covered within the protection scope of the present invention.

Claims

1. A smart scenic spot intelligent safety guidance system, characterized in that: include: Data collection module: Set up sensors and cameras to monitor the flow of people, vehicles, and weather information in real time, and collect users' personal information, location data, health data, etc.; Data processing and analysis module: clean and organize the collected data, use statistical methods and machine learning algorithms to analyze the data and extract tourist information; Personalized route recommendation module: recommends personalized sightseeing routes for tourists based on tourist information; Safety management module: formulate emergency plans and conduct drills regularly, and monitor the safety status of the scenic area in real time through cameras and sensors.

2. According to claim 1, the intelligent safety guidance system for a smart scenic spot is characterized in that: The personalized route recommendation module includes: Route recommendation unit: set up a personalized route recommendation mechanism and use it to recommend sightseeing routes for tourists; Tourist feedback unit: dynamically adjust sightseeing routes through tourist status feedback.

3. According to claim 2, the intelligent safety guidance system for a smart scenic spot is characterized in that: The personalized route recommendation mechanism includes but is not limited to: Comprehensive score screening: set up a comprehensive score model to recommend personalized routes for tourists; Priority screening: Select route influencing factors, prioritize them, and screen them step by step.

4. According to claim 3, the intelligent safety guidance system for a smart scenic spot is characterized in that: The comprehensive scoring model is: Among them, p i represents the i-th tourist, l j represents the jth sightseeing route, S(p i , l j ) represents the comprehensive score of the i-th tourist on the j-th sightseeing route, α is the model adjustment parameter, which is between 0 and 1, k represents different influencing factors, and w k represents the weight coefficient of the kth influencing factor, f k (x k ) represents the scoring function of the kth influencing factor, where x k Represents a computable parameter of the kth influencing factor.

5. According to claim 4, the intelligent safety guidance system for a smart scenic spot is characterized in that: The influencing factors in the comprehensive scoring model include but are not limited to tourist age factors, weather factors and cost factors.

6. The intelligent safety guidance system for a smart scenic spot according to claim 5 is characterized in that: The comprehensive scoring screening also includes a group route scoring model. The group route recommendation model is constrained by the comprehensive scoring model. The group route scoring model is: Among them, S 共识度 (l j ) represents the group consensus score for the jth route, S(p i , l j ) represents the comprehensive score of the i-th tourist member on the j-th route, S avg (l j ) represents the average comprehensive score of all members on the jth route, and q represents the total number of tourists in the group.

7. The intelligent safety guidance system for a smart scenic spot according to claim 2 is characterized in that: The visitor feedback unit comprises: Customized optimization area: tourists can manually modify their preferences and physical condition information through the mobile app. The system will recalculate the comprehensive score and recommend new routes based on the modified data; System automatic optimization area: Based on the monitored tourist status data, a route optimization mechanism is set up to dynamically adjust the sightseeing route according to the mechanism.

8. The intelligent safety guidance system for a smart scenic spot according to claim 7 is characterized in that: The route optimization mechanism includes: Set up a tourist fatigue rating model to rate the tourist fatigue status; According to the current location of the tourist, calculate the information of all remaining paths from the current location to the destination, wherein the remaining path information includes the remaining total distance, the remaining number of attractions, and the remaining number of rest spots; Set the remaining route scoring function: S' = B1D(y) + B2A(z) + B2R(h), D(y), A(z), R(h) represent the scoring functions of the remaining total distance, the remaining number of attractions, and the remaining number of rest points in the remaining route, respectively; B1, B2, B3 are the weight coefficients of the remaining total distance, the remaining number of attractions, and the remaining number of rest points, respectively; The score of each remaining route is calculated through the remaining route scoring function, and based on the scoring results, the route with the highest score is selected as the new recommended route.

9. The intelligent safety guidance system for a smart scenic spot according to claim 8 is characterized in that: The values ​​of the weight coefficients B1, B2, and B3 are constrained by the fatigue level of the tourists.

10. The intelligent safety guidance system for a smart scenic spot according to claim 9 is characterized in that: The fatigue status of tourists is scored every time T, and a threshold u is set. If the difference between the current score and the previous score exceeds u, the remaining routes are optimized, otherwise the current route remains unchanged.

Images