A real-time optimization and adjustment system for cultural tourism routes based on big data analysis

Abstract

The present invention discloses a real-time optimization and adjustment system for cultural tourism paths based on big data analysis, which relates to the field of cultural tourism path optimization technology, including a collection and analysis module, the collection and analysis module is connected to a combination and matching module, the combination and matching module is connected to a path optimization module, and the path optimization module is connected to an interactive feedback module, the collection and analysis module is used to collect tourist behavior feature information in real time, using big data analysis technology. The real-time optimization and adjustment system for cultural tourism paths based on big data analysis establishes a personalized model, can tailor tourist paths for tourists, meet their unique travel needs and preferences, improve tourists' satisfaction and participation in the travel process, can timely adjust the travel path according to real-time external data, avoid tourists from falling into unfavorable situations such as congestion and bad weather, and ensure smooth and efficient travel itineraries.

Description

Technical Field

[0001] The present invention relates to the technical field of cultural tourism route optimization, and in particular to a real-time optimization and adjustment system for cultural tourism routes based on big data analysis. Background Art

[0002] With the improvement of people's living standards and the growth of spiritual and cultural needs, the cultural tourism industry has developed rapidly; more and more people choose to experience the cultural characteristics of different regions during travel and enrich their spiritual world; however, the traditional cultural tourism model faces some challenges; on the one hand, tourists' needs are becoming increasingly diversified and personalized; tourists of different ages, interests, hobbies, and cultural backgrounds have different needs and preferences for tourist destinations, types of attractions, modes of transportation, accommodation and catering; traditional fixed tourist routes are difficult to meet the personalized needs of tourists, resulting in poor tourist experience; on the other hand, there are many uncertain factors in the travel process; traffic congestion, excessive flow of people at attractions, weather changes, etc. often affect tourists' itineraries and bring inconvenience to tourists; at the same time, the uneven distribution of tourism resources and information asymmetry also make it difficult for tourists to plan their travel routes, and they are prone to miss some high-quality attractions and experiences. Summary of the invention

[0003] In order to solve the above technical problems, the present invention is implemented through the following technical solutions: a real-time optimization and adjustment system for cultural tourism routes based on big data analysis, comprising a collection and analysis module, the collection and analysis module is connected to a combination and matching module, the combination and matching module is connected to a route optimization module, and the route optimization module is connected to an interactive feedback module;

[0004] The collection and analysis module is used to collect the tourist behavior characteristic information of tourists in real time, and use big data analysis technology to process and analyze the collected tourist behavior characteristic information in combination with the tourists' historical tour records, interests, hobbies and age, determine the tourists' preference for different types of cultural attractions, and establish a personalized tourist model;

[0005] The combined matching module is used to determine the matching degree of the scenic spots based on the personalized model of the tourists and in combination with the travel preferences, wherein the travel preferences include food preferences, accommodation preferences, cultural preferences and transportation preferences;

[0006] The route optimization module is used to obtain real-time external data, obtain traffic information, scenic spot flow information, weather information, and customize the initial travel route in combination with the scenic spot matching degree;

[0007] The interactive feedback module interacts with tourists through a map application on a mobile phone application or an intelligent tour guide device based on a wireless network to provide tourists with real-time routes, including route recommendations and navigation services; during the route recommendation and navigation service, tourists provide feedback on the real-time route, and the system determines the feedback route based on the feedback information.

[0008] Optimally, the process of establishing a personalized tourist model is as follows:

[0009] Step 1: Collect and organize data, collect tourist behavior characteristics in real time, obtain tourist behavior data, preference data and location information, organize and store them according to different categories; at the same time, obtain tourists' historical travel records, interests and hobbies, and age, among which historical travel records include the types of attractions visited in the past, movement speed, stay time and evaluation; obtain interest and hobbies information through filling in the registration form of tourists and social network analysis; extract age information directly from the personal data provided by tourists;

[0010] Step 2: Perform data analysis and feature extraction, analyze the behavior data, preference data, and location information separately and combine them with historical travel records, interests, hobbies, and age to obtain analysis results;

[0011] Step 3: Model building. First, determine the feature weights. Based on the data analysis results, determine the weights of each feature in the personalized model. For example, the evaluation of different types of attractions may have a higher weight because it directly reflects the tourists' preferences. The weight of the age factor may be relatively low, but it will still affect the preference for certain types of attractions.

[0012] Then, a model framework is established, and the decision tree in the machine learning algorithm is used to establish the framework of the tourist personalization model. The tourist behavior characteristic information, historical tour records, interests and hobbies, and age are summarized into tourist data, and the tourist data is used as the input variable, and the tourists' preference for different types of cultural attractions is used as the output variable;

[0013] Then, the model is trained and optimized. The collected tourist data is used for model training, and the model parameters and weights are continuously adjusted to improve the accuracy and generalization ability of the model. The cross-validation method is used to evaluate the performance of the model and optimize it to obtain a personalized tourist model.

[0014] Finally, the model is updated and maintained. As new tourist data is continuously collected, the tourist personalized model is regularly updated and maintained through a preset automatic update mechanism to ensure that the model can accurately reflect the latest preferences and behavioral characteristics of tourists. When the new tourist data reaches a preset amount, the model update process can be automatically triggered. This preset amount can be a data storage threshold or a data collection threshold.

[0015] Preferably, the process of determining the matching degree of attractions is as follows:

[0016] Step 1: Determine the weight of each preference

[0017] Let the dietary preference weight be w 1 , the accommodation preference weight is w 2 , the humanities preference weight is w 3 , the traffic preference weight is w 4 , and satisfies w 1 +w 2 +w 3 +w 4 =1;

[0018] Step 2: Quantify the degree of match of each preference:

[0019] For the dietary preference matching degree, denoted as S 1 :

[0020] The catering score is calculated based on the catering selection records and dietary preference data in the tourist personalized model, as well as the catering situation around the scenic spot. If there are restaurants around the scenic spot that meet the tourists' dietary preferences, the prices are within the acceptable range, and the reviews are good, a higher score will be given. The catering score range is set to 0-100, with 100 points for full compliance, 60 points for partial compliance, and 20 points for non-compliance. The calculation formula considers: restaurant type compliance, price compliance, and review compliance. The calculation formula is: S 1 =a 1 ×Restaurant type compliance + a 2 ×Price compliance+a 3 ×Evaluation compliance, where a 1 、a 2 、a 3 is the weight coefficient, and a 1 +a 2 +a 3 =1;

[0021] For the accommodation preference matching, denoted as S 2 :

[0022] Accommodation rating is performed based on the accommodation preference data in the tourist personalization model and the accommodation facilities near the scenic spot. If there are accommodation facilities near the scenic spot that meet the tourist's accommodation preferences and are close and have good facilities, a higher score will be given. The score range of the accommodation rating is set to 0-100, with 100 points for full compliance, 60 points for partial compliance, and 20 points for non-compliance. The calculation formula takes into account: distance factors and facility compliance. The calculation formula is: S 2 =b 1 ×Distance compliance + b 2 × Facility compliance, where b1 、b 2 is the weight coefficient, and b 1 +b 2 =1;

[0023] For the humanities preference matching degree, denoted as S 3 :

[0024] According to the tourist theme preference and humanistic preference data in the personalized model of tourists, as well as the humanistic characteristics of the scenic spot, a humanistic score is given; if the humanistic characteristics of the scenic spot meet the tourist's humanistic preferences, a higher score is given; for example, for tourists who like historical and cultural theme tours, if the scenic spot is a historical and cultural scenic spot, a higher score is given; the score range of the humanistic score is set to 0-100, with 100 points for full compliance, 60 points for partial compliance, and 20 points for non-compliance; the calculation formula is: S 3 =c 1 ×Humanistic characteristics compliance, where c 1 is the weight coefficient;

[0025] For the traffic preference matching degree, denoted as S 4 :

[0026] The traffic score is calculated based on the traffic preference data in the tourist personalized model and the traffic conditions of the scenic spot. If the traffic convenience of the scenic spot meets the tourists' traffic preferences, a higher score will be given. The traffic score range is set to 0-100, and the calculation formula considers: traffic mode compliance and traffic time factors; the calculation formula is: S 4 =d 1 ×Transportation mode compliance + d 2 × Traffic time compliance, where d 1 ,d 2 is the weight coefficient, and d 1 +d 2 =1;

[0027] Step 3: Calculate the matching degree of scenic spots:

[0028] The scenic spot matching degree is recorded as M and calculated by the following formula: M=w 1 S 1 +w 2 S 2 +w 3 S 3 +w 4 S 4 .

[0029] Preferably, the path optimization module further includes:

[0030] The optimization unit uses personalized demand matching algorithms, such as genetic algorithms and ant colony algorithms, based on the initial travel path to calculate recommended routes that meet tourists' personalized needs and avoid unfavorable factors; and selects the optimal route from the recommended routes based on physical energy consumption and travel expenses;

[0031] The real-time path unit is used to recalculate the path based on the needs of tourists or changes in the external environment to obtain a real-time path.

[0032] Preferably, the initial game path customization process is as follows:

[0033] First, we use the real-time data of the map application to obtain real-time traffic information, including road congestion, public transportation operation time and frequency, and traffic control information; we use the real-time information on social media to collect information about the flow of people at scenic spots, and understand the number of tourists and the degree of congestion at each scenic spot; we use the weather app to collect weather information, including the current weather conditions and weather forecast;

[0034] According to the matching degree of each scenic spot, the scenic spot is given an initial priority, and the initial priority is adjusted in combination with external data to obtain the scenic spot priority.

[0035] For traffic information, if a certain scenic spot has convenient transportation and is easy to reach, its priority can be appropriately increased; on the contrary, if the traffic is congested or difficult to reach, its priority can be lowered;

[0036] For the information of tourist flow, the priority of tourist attractions with less tourist flow can be increased, while the priority of overcrowded tourist attractions can be reduced;

[0037] For weather information, if a certain attraction is more attractive under good weather conditions, such as natural scenery attractions are more suitable for sightseeing on sunny days, its priority will be increased under the corresponding weather conditions; if bad weather will affect the sightseeing experience of the attraction, such as outdoor attractions on rainy days, its priority will be lowered;

[0038] Then plan the initial play path:

[0039] First, select the starting point: determine the starting point of the tour route based on the tourist's current location or a preset starting point, such as a hotel or station;

[0040] Then, based on time constraints, transportation connections, and theme coherence, attractions are selected in order, from high to low priority, to be included in the initial tour route;

[0041] During the selection process, consider the following factors:

[0042] Time limit: according to the tourists' travel time and the estimated visiting time of each attraction, ensure that the tour route is in line with the estimated total visiting time;

[0043] Transportation connection: choose a combination of attractions with convenient transportation to minimize the time spent on transportation;

[0044] Theme coherence: If tourists have a specific travel theme preference, they can choose attractions with related themes for a coherent tour;

[0045] Finally, determine the destination: According to the needs and actual situation of tourists, choose a suitable location as the destination, such as a hotel, a station or another important attraction; thus obtaining the initial tour route.

[0046] Preferably, the process of obtaining the recommended path is:

[0047] First, the encoding scheme represents the initial travel path as a chromosome, which consists of a series of attraction numbers;

[0048] Then, the population is initialized and several chromosomes are randomly generated as the initial population; then, the fitness function is determined. First, the scenic spot matching degree is clarified: according to the scenic spot matching degree calculation method determined previously, the sum of the matching degrees of each scenic spot in the path represented by the chromosome is calculated to obtain the sum of the scenic spot matching degrees; then, unfavorable factors are avoided: the congestion coefficient and the bad weather coefficient are set, and the congestion penalty value and the bad weather penalty value are calculated according to the actual conditions of traffic congestion and bad weather respectively;

[0049] Then, time limit is imposed: the time required for the route is calculated based on the estimated visiting time and traffic time of the scenic spot, and the overtime penalty value is calculated to ensure that the route is within the travel time given by the tourists. If the time required for the route exceeds the travel time, a larger penalty value is given to reduce the fitness;

[0050] Finally, the traffic connection is carried out: the quality of the traffic connection is evaluated according to the convenience of the traffic mode and the number of transfers, and the traffic connection reward value is calculated; among them, a certain reward value is given to the path with convenient transportation to improve the fitness; the fitness function is expressed as: fitness = sum of scenic spot matching - congestion penalty value - bad weather penalty value - timeout penalty value + traffic connection reward value;

[0051] The roulette wheel selection method is used to calculate the probability of being selected according to the fitness value of the chromosome; the higher the fitness value, the greater the probability of being selected; two chromosomes are randomly selected as parents, and multi-point crossover operation is performed to generate offspring; the A scenic spot number in the chromosome is randomly replaced with the B scenic spot number to increase the diversity of the population; the number of iterations C is set, and when the number of iterations C is met, the algorithm is stopped, and the path at this time is the recommended path.

[0052] Preferably, the process of obtaining the optimal path is:

[0053] Analyze and select recommended routes based on physical energy consumption and travel expenses: Estimate the physical energy consumption of tourists on each route based on the distance, terrain and tour time between attractions; and establish a physical energy consumption model to quantify the distance, terrain and tour time and weighted sum them to obtain physical energy consumption; calculate travel expenses based on transportation costs, ticket fees, and catering costs, combined with actual price information and the arrangement of attractions in the route;

[0054] According to tourists' preferences, weights are assigned to physical energy consumption and travel expenses, and the weighted sum of physical energy consumption and travel expenses is taken to obtain a comprehensive index; then the comprehensive indicators of different recommended paths are sorted from large to small, and the path with the smallest comprehensive index is selected as the optimal path; among them, the optimal path can minimize physical energy consumption and travel expenses while meeting the personalized needs of tourists.

[0055] Preferably, the process of obtaining the real-time path is:

[0056] Continuously monitor changes in tourists' needs and external environment, obtain change results, and quantify the change results to obtain change value X, where tourists' needs changes include temporary changes in itinerary, increase or decrease in tour time; external environment changes include changes in traffic congestion, changes in the flow of people at scenic spots, and changes in weather; based on the monitored change results, determine whether the path needs to be recalculated; set the change interval [x, y], when the change value X does not fall into [x, y], it means that the current change result is large, which may affect the feasibility of the current path or tourists' satisfaction, and then recalculate the path;

[0057] When the route needs to be recalculated, real-time external data is collected again, including traffic information, tourist attraction flow information, and weather information. At the same time, the personalized model of tourists is updated to reflect the latest changes in demand. The route is re-optimized according to the process of customizing the initial tour route and obtaining the recommended route and the optimal route. Based on the new data and the changed situation, a real-time route that adapts to the new conditions is calculated. The recalculated real-time route is provided to tourists so that they can adjust their itineraries in a timely manner.

[0058] Preferably, during the route recommendation and navigation service, the information feedback from the chat software in the mobile application, the news list of nearby tourist areas pushed by the news broadcast software in the mobile application app, and the notification information released by the smart tour guide device are collected as feedback information, and the real-time route currently taken by the tourists is fed back. The feedback route is determined based on the feedback information, and the real-time route is temporarily fed back and adjusted online.

[0059] Preferably, the process of performing temporary feedback and adjustment on the real-time path according to the feedback information:

[0060] Tourists communicate with their companions or tourism service personnel in the chat software to share their feelings and questions about the current real-time route; relevant topics and keywords in the chat software are monitored in real time to extract chat feedback information related to the route;

[0061] Based on the news broadcasting software, the news about emergencies in tourist areas, temporary closure of scenic spots, and traffic control are pushed, and the news content is analyzed to determine the information that affects the current real-time route as news feedback information;

[0062] The smart tour guide device detects special situations nearby, including excessive crowds in scenic spots and sudden weather changes, based on its built-in sensors and positioning system, and sends notification information to tourists and serves as feedback for the tour guide;

[0063] Classify and analyze the collected chat feedback information, news feedback information and tour guide feedback information to determine the determining factors that will affect the current real-time path;

[0064] Based on the determinants, according to the urgency, importance and impact of the factors on the trip, the impact on the real-time path is evaluated, the level of impact is determined, and the evaluation results are obtained; based on the determinants and the evaluation results, alternative attractions, routes or modes of transportation are sought to obtain alternative solutions; for example, if an attraction is closed, similar attractions nearby can be found as an alternative; if there is a traffic jam, other transportation routes can be selected;

[0065] Adjust the route planning and re-plan the real-time route based on time constraints, attraction priorities and traffic connections and alternatives; ensure that the new route meets the needs of tourists while minimizing adverse effects; provide the adjusted route to tourists as a feedback route; the feedback route can be displayed on the mobile app and smart tour guide device so that tourists can understand and adjust the itinerary in time; send notifications about the feedback route to tourists through the mobile app and smart tour guide device, including the reasons for the adjustment, new attractions and route arrangements, etc.;

[0066] Visitors can view the feedback route on the mobile app and choose whether to accept the adjustment; if the visitor agrees to the adjustment, the system will update the real-time route; if the visitor disagrees with the adjustment, the current real-time route will continue to be used;

[0067] While tourists are using the feedback path, continue to monitor the feedback information and obtain new feedback information so as to promptly discover new problems and changes; based on the new feedback information, continuously make dynamic adjustments to the real-time path to ensure that tourists can always get the best travel experience.

[0068] The present invention provides a real-time optimization and adjustment system for cultural tourism routes based on big data analysis, which has the following beneficial effects:

[0069] 1. The real-time optimization and adjustment system of cultural tourism routes based on big data analysis improves the tourists' travel experience and has personalized customization functions. By collecting and analyzing tourists' behavioral characteristics, historical records, interests and hobbies and other information, a personalized model is established, which can tailor travel routes for tourists to meet their unique travel needs and preferences, and improve tourists' satisfaction and participation in the travel process; it has real-time optimization and adjustment functions, and can adjust the travel routes in time according to real-time external data, such as traffic information, scenic spot flow, weather conditions, and changes in tourists' needs, to avoid tourists from falling into congestion, bad weather and other unfavorable situations, to ensure the smoothness and efficiency of the travel itinerary; it has a flexible feedback mechanism. During the route recommendation and navigation service, tourists can provide feedback on their opinions on the real-time route through various channels. The system will make temporary feedback and adjustments based on the feedback information, so that the travel route is more in line with the actual needs of tourists, and enhance the autonomy and interactivity of tourists in the travel process.

[0070] 2. The real-time optimization and adjustment system of cultural tourism routes based on big data analysis has improved the efficiency of tourism management and can reasonably plan resources. The system comprehensively considers factors such as attraction matching, physical energy consumption, and tourism expenses to optimize tourism routes, which helps to reasonably allocate tourism resources, avoid excessive crowding in popular attractions, and improve the utilization efficiency of tourism resources; it can dynamically monitor and adjust, continuously monitor tourist needs and changes in the external environment, and can promptly identify problems and make adjustments, reduce uncertainty in tourism management, and improve the response speed and decision-making accuracy of tourism management; it can also improve service quality, by providing tourists with personalized, real-time optimized travel routes and convenient interactive feedback services, thereby improving the quality and level of tourism services and enhancing the competitiveness of tourist destinations.

[0071] 3. The real-time optimization and adjustment system of cultural tourism routes based on big data analysis can promote the development of the cultural tourism industry and carry out precise marketing. Based on the personalized needs and behavioral characteristics of tourists, tourism enterprises and management departments can better understand the needs of tourists, carry out precise marketing activities, and improve the promotion effect and market share of tourism products; it has data-driven decision-making. The large amount of tourism data collected by the system can provide data support for the development of the tourism industry, help enterprises and management departments make market analysis, product development, resource planning and other decisions, and promote the innovation and sustainable development of the cultural tourism industry; it can enhance cultural communication, by recommending cultural attractions and theme tourism routes that suit their interests to tourists, promote cultural dissemination and exchange, and enhance the connotation and value of cultural tourism. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 This is a flow chart of a real-time optimization and adjustment system for cultural tourism routes based on big data analysis according to the present invention. DETAILED DESCRIPTION

[0073] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are provided for the purpose of illustration and description, and are not intended to be exhaustive or to limit the present invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention, and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

[0074] like Figure 1 As shown, the present invention provides a technical solution: a real-time optimization and adjustment system for cultural tourism routes based on big data analysis, comprising a collection and analysis module, the collection and analysis module is connected to a combination and matching module, the combination and matching module is connected to a route optimization module, and the route optimization module is connected to an interactive feedback module;

[0075] The collection and analysis module is used to collect the tourist behavior characteristic information of tourists in real time, and use big data analysis technology to process and analyze the collected tourist behavior characteristic information in combination with the tourists' historical tour records, interests, hobbies and age, determine the tourists' preference for different types of cultural attractions, and establish a personalized tourist model;

[0076] The combined matching module is used to determine the matching degree of the scenic spots based on the personalized model of the tourists and in combination with the travel preferences, wherein the travel preferences include food preferences, accommodation preferences, cultural preferences and transportation preferences;

[0077] The route optimization module is used to obtain real-time external data, obtain traffic information, scenic spot flow information, weather information, and customize the initial travel route in combination with the scenic spot matching degree;

[0078] The interactive feedback module interacts with tourists through a map application on a mobile phone application or an intelligent tour guide device based on a wireless network to provide tourists with real-time routes, including route recommendations and navigation services; during the route recommendation and navigation service, tourists provide feedback on the real-time route, and the system determines the feedback route based on the feedback information.

[0079] Optimally, the process of establishing a personalized tourist model is as follows:

[0080] Step 1: Collect and organize data, collect tourist behavior characteristics in real time, obtain tourist behavior data, preference data and location information, organize and store them according to different categories; at the same time, obtain tourists' historical travel records, interests and hobbies, and age, among which historical travel records include the types of attractions visited in the past, movement speed, stay time and evaluation; obtain interest and hobbies information through filling in the registration form of tourists and social network analysis; extract age information directly from the personal data provided by tourists;

[0081] Step 2: Perform data analysis and feature extraction, analyze the behavior data, preference data, and location information separately and combine them with historical travel records, interests, hobbies, and age to obtain analysis results;

[0082] It should be further explained that, in the specific implementation process, the process of the above data analysis is as follows:

[0083] Behavioral data analysis:

[0084] Analyze shopping records, count the amount of money tourists spend on different types of goods, and determine their shopping preferences, such as souvenirs, specialty foods, and handicrafts;

[0085] Analyze dining selection records to understand tourists' preferences for different types of restaurants, such as Chinese restaurants, Western restaurants, and local specialty restaurants, as well as their acceptable range of dining prices and evaluation tendencies;

[0086] Analyze attendance records to determine visitors’ participation and interest in different types of cultural events, performances and festivals, as well as their enthusiasm as reflected by the length of time they attend;

[0087] Preference data analysis:

[0088] Analyze accommodation preferences to determine tourists' preference for different accommodation facilities such as hotels, B&Bs and resorts. For example, preference for hotels with full facilities may indicate that tourists value comfort, while preference for B&Bs may indicate that tourists like to be close to local life.

[0089] Analyze tourist theme preferences and determine tourists' main tourist interests based on their choices of historical and cultural themed tours, natural scenery themed tours, parent-child tours, and food tours;

[0090] Analyze travel rhythm preferences to understand whether tourists prefer a tight schedule or a leisurely schedule, which will affect the arrangement of attractions and length of stay in route planning;

[0091] Location information analysis:

[0092] Combine the location information and stay time of tourists at different attractions to analyze tourists' preferences for different types of attractions; for example, a longer stay time at historical and cultural attractions may indicate a higher interest in history and culture;

[0093] Combined with historical travel records, interests and hobbies and age analysis:

[0094] Analyze historical travel records to find out the types of attractions and travel patterns that tourists often visited in the past, and compare and verify them with current behavioral characteristics;

[0095] Consider the impact of hobbies on travel behavior. For example, tourists who like photography may prefer scenic spots with beautiful natural scenery.

[0096] Age factors also affect travel preferences. For example, young people may prefer exciting activities and emerging tourist attractions, while older people may pay more attention to comfort and cultural connotations.

[0097] Among them, behavioral data can be collected through smartphones, preference data can be collected through consumption records, and location information can be collected through GPS positioning;

[0098] The above tourism behavior characteristic information reflects the various behavioral characteristics, preference tendencies and location dynamics of tourists during the travel process, providing an important basis for the system to conduct big data analysis and route optimization;

[0099] Step 3: Model building. First, determine the feature weights. Based on the data analysis results, determine the weights of each feature in the personalized model. For example, the evaluation of different types of attractions may have a higher weight because it directly reflects the tourists' preferences. The weight of the age factor may be relatively low, but it will still affect the preference for certain types of attractions.

[0100] Then, a model framework is established, and the decision tree in the machine learning algorithm is used to establish the framework of the tourist personalization model. The tourist behavior characteristic information, historical tour records, interests and hobbies, and age are summarized into tourist data, and the tourist data is used as the input variable, and the tourists' preference for different types of cultural attractions is used as the output variable;

[0101] Then, the model is trained and optimized. The collected tourist data is used for model training, and the model parameters and weights are continuously adjusted to improve the accuracy and generalization ability of the model. The cross-validation method is used to evaluate the performance of the model and optimize it to obtain a personalized tourist model.

[0102] Finally, the model is updated and maintained. As new tourist data is continuously collected, the tourist personalized model is regularly updated and maintained through a preset automatic update mechanism to ensure that the model can accurately reflect the latest preferences and behavioral characteristics of tourists. When the new tourist data reaches a preset amount, the model update process can be automatically triggered. This preset amount can be a data storage threshold or a data collection threshold.

[0103] Through the above process, a model can be established that accurately reflects the personalized needs of tourists, providing strong support for the real-time optimization and adjustment of cultural tourism routes and laying the foundation for providing better tourism services and experiences.

[0104] Preferably, the process of determining the matching degree of attractions is as follows:

[0105] Step 1: Determine the weight of each preference

[0106] Let the dietary preference weight be w 1 , the accommodation preference weight is w 2 , the humanities preference weight is w 3 , the traffic preference weight is w 4 , and satisfies w 1 +w 2 +w 3 +w 4 =1;

[0107] Step 2: Quantify the degree of match of each preference:

[0108] For the dietary preference matching degree, denoted as S 1 :

[0109] The catering score is calculated based on the catering selection records and dietary preference data in the tourist personalized model, as well as the catering situation around the scenic spot. If there are restaurants around the scenic spot that meet the tourists' dietary preferences, the prices are within the acceptable range, and the reviews are good, a higher score will be given. The catering score range is set to 0-100, with 100 points for full compliance, 60 points for partial compliance, and 20 points for non-compliance. The calculation formula considers: restaurant type compliance, price compliance, and review compliance. The calculation formula is: S 1 =a 1 ×Restaurant type compliance + a 2 ×Price compliance+a 3 ×Evaluation compliance, where a 1 、a 2 、a 3 is the weight coefficient, and a 1 +a 2 +a 3 =1;

[0110] For the accommodation preference matching, denoted as S 2:

[0111] Accommodation rating is performed based on the accommodation preference data in the tourist personalization model and the accommodation facilities near the scenic spot. If there are accommodation facilities near the scenic spot that meet the tourist's accommodation preferences and are close and have good facilities, a higher score will be given. The score range of the accommodation rating is set to 0-100, with 100 points for full compliance, 60 points for partial compliance, and 20 points for non-compliance. The calculation formula takes into account: distance factors and facility compliance. The calculation formula is: S 2 =b 1 ×Distance compliance + b 2 × Facility compliance, where b 1 、b 2 is the weight coefficient, and b 1 +b 2 =1;

[0112] For the humanities preference matching degree, denoted as S 3 :

[0113] According to the tourist theme preference and humanistic preference data in the personalized model of tourists, as well as the humanistic characteristics of the scenic spot, a humanistic score is given; if the humanistic characteristics of the scenic spot meet the tourist's humanistic preferences, a higher score is given; for example, for tourists who like historical and cultural theme tours, if the scenic spot is a historical and cultural scenic spot, a higher score is given; the score range of the humanistic score is set to 0-100, with 100 points for full compliance, 60 points for partial compliance, and 20 points for non-compliance; the calculation formula is: S 3 =c 1 ×Humanistic characteristics compliance, where c 1 is the weight coefficient;

[0114] For the traffic preference matching degree, denoted as S 4 :

[0115] The traffic score is calculated based on the traffic preference data in the tourist personalized model and the traffic conditions of the scenic spot. If the traffic convenience of the scenic spot meets the tourists' traffic preferences, a higher score will be given. The traffic score range is set to 0-100, and the calculation formula considers: traffic mode compliance and traffic time factors; the calculation formula is: S 4 =d 1 ×Transportation mode compliance + d 2 × Traffic time compliance, where d 1 ,d 2 is the weight coefficient, and d 1 +d 2 =1;

[0116] Step 3: Calculate the matching degree of scenic spots:

[0117] The scenic spot matching degree is recorded as M and calculated by the following formula: M=w1 S 1 +w 2 S 2 +w 3 S 3 +w 4 S 4

[0118] For example, assuming that the weight of food preference is 0.3, the weight of accommodation preference is 0.2, the weight of humanities preference is 0.3, and the weight of transportation preference is 0.2; the food preference matching degree of a certain scenic spot is 80 points, the accommodation preference matching degree is 70 points, the humanities preference matching degree is 90 points, and the transportation preference matching degree is 80 points, then the matching degree of the scenic spot is: M=0.3×80+0.2×70+0.3×90+0.2×80=24+14+27+16=81 points.

[0119] Preferably, the path optimization module further includes:

[0120] The optimization unit uses personalized demand matching algorithms, such as genetic algorithms and ant colony algorithms, based on the initial travel path to calculate recommended routes that meet tourists' personalized needs and avoid unfavorable factors; and selects the optimal route from the recommended routes based on physical energy consumption and travel expenses;

[0121] The real-time path unit is used to recalculate the path based on the needs of tourists or changes in the external environment to obtain a real-time path.

[0122] Preferably, the initial game path customization process is as follows:

[0123] First, we use the real-time data of the map application to obtain real-time traffic information, including road congestion, public transportation operation time and frequency, and traffic control information; we use the real-time information on social media to collect information about the flow of people at scenic spots, and understand the number of tourists and the degree of congestion at each scenic spot; we use the weather app to collect weather information, including the current weather conditions and weather forecast;

[0124] According to the matching degree of each scenic spot, the scenic spot is given an initial priority, and the initial priority is adjusted in combination with external data to obtain the scenic spot priority.

[0125] For traffic information, if a certain scenic spot has convenient transportation and is easy to reach, its priority can be appropriately increased; on the contrary, if the traffic is congested or difficult to reach, its priority can be lowered;

[0126] For the information of tourist flow, the priority of tourist attractions with less tourist flow can be increased, while the priority of overcrowded tourist attractions can be reduced;

[0127] For weather information, if a certain attraction is more attractive under good weather conditions, such as natural scenery attractions are more suitable for sightseeing on sunny days, its priority will be increased under the corresponding weather conditions; if bad weather will affect the sightseeing experience of the attraction, such as outdoor attractions on rainy days, its priority will be lowered;

[0128] Then plan the initial play path:

[0129] First, select the starting point: determine the starting point of the tour route based on the tourist's current location or a preset starting point, such as a hotel or station;

[0130] Then, based on time constraints, transportation connections, and theme coherence, attractions are selected in order, from high to low priority, to be included in the initial tour route;

[0131] During the selection process, consider the following factors:

[0132] Time limit: according to the tourists' travel time and the estimated visiting time of each attraction, ensure that the tour route is in line with the estimated total visiting time;

[0133] Transportation connection: choose a combination of attractions with convenient transportation to minimize the time spent on transportation;

[0134] Theme coherence: If tourists have a specific travel theme preference, they can choose attractions with related themes for a coherent tour;

[0135] Finally, determine the destination: According to the needs and actual situation of tourists, choose a suitable location as the destination, such as a hotel, a station or another important attraction; thus obtaining the initial tour route.

[0136] Preferably, the process of obtaining the recommended path is:

[0137] First, the encoding scheme represents the initial tour path as a chromosome, which consists of a series of attraction numbers. For example, suppose there are five attractions numbered 1, 2, 3, 4, and 5. A possible chromosome is [1, 3, 2, 5, 4], which means the tour order is attraction 1, attraction 3, attraction 2, attraction 5, and attraction 4.

[0138] Then, initialize the population and randomly generate several chromosomes as the initial population; according to the restrictions on the number of attractions and travel time, ensure that the generated path is feasible in practice; then determine the fitness function, first clarify the attraction matching degree: according to the attraction matching degree calculation method determined earlier, calculate the sum of the matching degrees of each attraction in the path represented by the chromosome to obtain the sum of the attraction matching degrees; for example, for chromosome [1,3,2,5,4], calculate the matching degrees of attractions 1, 3, 2, 5, and 4 respectively, and then sum them up; then avoid unfavorable factors: set the congestion coefficient and bad weather coefficient, and calculate the congestion penalty value and bad weather penalty value according to the actual situation of traffic congestion and bad weather. When a certain attraction in the path is affected by traffic congestion or is in a bad weather area, a certain penalty value will be given to reduce the fitness;

[0139] Then, time limit is imposed: the time required for the route is calculated based on the estimated visiting time and traffic time of the scenic spot, and the overtime penalty value is calculated to ensure that the route is within the travel time given by the tourists. If the time required for the route exceeds the travel time, a larger penalty value is given to reduce the fitness;

[0140] Finally, the traffic connection is carried out: the quality of the traffic connection is evaluated according to the convenience of the traffic mode and the number of transfers, and the traffic connection reward value is calculated; among them, a certain reward value is given to the path with convenient transportation to improve the fitness; the fitness function is expressed as: fitness = sum of scenic spot matching - congestion penalty value - bad weather penalty value - timeout penalty value + traffic connection reward value;

[0141] The roulette wheel selection method is adopted to calculate the probability of being selected according to the fitness value of the chromosome; the higher the fitness value of the chromosome, the greater the probability of being selected; two chromosomes are randomly selected as parents, and multi-point crossover operation is performed to generate offspring; for example, for chromosomes [1,3,2,5,4] and [2,4,1,3,5], they are exchanged at the randomly selected crossover points to generate new offspring chromosomes; the A scenic spot number in the chromosome is randomly replaced with the B scenic spot number to increase the diversity of the population; the number of iterations C is set, and when the number of iterations C is met, the algorithm is stopped, and the path at this time is the recommended path; through the above genetic algorithm, the tourist path can be continuously optimized to meet the personalized needs of tourists and avoid unfavorable factors to generate a recommended path.

[0142] Preferably, the process of obtaining the optimal path is:

[0143] Analyze and select recommended routes based on physical energy consumption and travel expenses: Estimate the physical energy consumption of tourists on each route based on the distance, terrain and tour time between attractions; and establish a physical energy consumption model to quantify the distance, terrain and tour time and weighted sum them to obtain physical energy consumption; calculate travel expenses based on transportation costs, ticket fees, and catering costs, combined with actual price information and the arrangement of attractions in the route;

[0144] According to tourists' preferences, weights are assigned to physical energy consumption and travel expenses, and the weighted sum of physical energy consumption and travel expenses is taken to obtain a comprehensive index; then the comprehensive indicators of different recommended paths are sorted from large to small, and the path with the smallest comprehensive index is selected as the optimal path; among them, the optimal path can minimize physical energy consumption and travel expenses while meeting the personalized needs of tourists.

[0145] Preferably, the process of obtaining the real-time path is:

[0146] Continuously monitor changes in tourists' needs and external environment, obtain change results, and quantify the change results to obtain change value X, where tourists' needs changes include temporary changes in itinerary, increase or decrease in tour time; external environment changes include changes in traffic congestion, changes in the flow of people at scenic spots, and changes in weather; based on the monitored change results, determine whether the path needs to be recalculated; set the change interval [x, y], when the change value X does not fall into [x, y], it means that the current change result is large, which may affect the feasibility of the current path or tourists' satisfaction, and then recalculate the path;

[0147] When the route needs to be recalculated, real-time external data is collected again, including traffic information, tourist attraction flow information, and weather information. At the same time, the personalized model of tourists is updated to reflect the latest changes in demand. The route is re-optimized according to the process of customizing the initial tour route and obtaining the recommended route and the optimal route. Based on the new data and the changed situation, a real-time route that adapts to the new conditions is calculated. The recalculated real-time route is provided to tourists so that they can adjust their itineraries in a timely manner.

[0148] Preferably, during the route recommendation and navigation service, the information feedback from the chat software in the mobile application, the news list of nearby tourist areas pushed by the news broadcast software in the mobile application app, and the notification information released by the smart tour guide device are collected as feedback information, and the real-time route currently taken by the tourists is fed back. The feedback route is determined based on the feedback information, and the real-time route is temporarily fed back and adjusted online.

[0149] Preferably, the process of performing temporary feedback and adjustment on the real-time path according to the feedback information:

[0150] Tourists communicate with their companions or travel service personnel in the chat software to share their feelings and problems about the current real-time route; for example, tourists may report that a certain attraction is too crowded, a certain road section is seriously congested, or they have found a more interesting attraction, etc.; relevant topics and keywords in the chat software are monitored in real time to extract chat feedback information related to the route;

[0151] Based on the news broadcasting software, the news about emergencies, temporary closure of scenic spots, and traffic control in the tourist area are pushed, and the news content is analyzed to determine the information that affects the current real-time route as news feedback information;

[0152] The smart tour guide device detects special situations nearby, including excessive crowds in scenic spots and sudden weather changes, based on its built-in sensors and positioning system, and sends notification information to tourists and serves as feedback for the tour guide;

[0153] Classify and analyze the collected chat feedback information, news feedback information, and tour guide feedback information to determine the determining factors that will affect the current real-time path; for example, traffic jams, attraction closures, weather changes, new attraction discoveries, etc.;

[0154] Based on the determinants, according to the urgency, importance and impact of the factors on the trip, the impact on the real-time path is evaluated, the level of impact is determined, and the evaluation results are obtained; based on the determinants and the evaluation results, alternative attractions, routes or modes of transportation are sought to obtain alternative solutions; for example, if an attraction is closed, similar attractions nearby can be found as an alternative; if there is a traffic jam, other transportation routes can be selected;

[0155] Adjust the route planning and re-plan the real-time route based on time constraints, attraction priorities and traffic connections and alternatives; ensure that the new route meets the needs of tourists while minimizing adverse effects; provide the adjusted route to tourists as a feedback route; the feedback route can be displayed on the mobile app and smart tour guide device so that tourists can understand and adjust the itinerary in time; send notifications about the feedback route to tourists through the mobile app and smart tour guide device, including the reasons for the adjustment, new attractions and route arrangements, etc.;

[0156] Visitors can view the feedback route on the mobile app and choose whether to accept the adjustment; if the visitor agrees to the adjustment, the system will update the real-time route; if the visitor disagrees with the adjustment, the current real-time route will continue to be used;

[0157] While tourists are using the feedback path, they continue to monitor the feedback information and obtain new feedback information so as to promptly discover new problems and changes. Based on the new feedback information, the real-time path is continuously and dynamically adjusted to ensure that tourists can always get the best travel experience. Through the above process, the system can make timely temporary feedback and adjustments to the real-time path based on the feedback information, thereby improving the flexibility and adaptability of the travel path and meeting the needs of tourists.

[0158] It needs to be further explained that, in the specific implementation process, the tourist experience has been improved, and it has a personalized customization function. By collecting and analyzing tourists' behavioral characteristics, historical records, interests and hobbies and other information, a personalized model is established, which can tailor travel routes for tourists to meet their unique travel needs and preferences, and improve tourists' satisfaction and participation in the travel process; it has a real-time optimization and adjustment function, and can adjust the travel route in time according to real-time external data, such as traffic information, scenic spot flow, weather conditions, and changes in tourists' needs, to avoid tourists from falling into congestion, bad weather and other unfavorable situations, and ensure a smooth and efficient travel itinerary; it has a flexible feedback mechanism. During the route recommendation and navigation service, tourists can provide feedback on their opinions on the real-time route through various channels, and the system will make temporary feedback and adjustments based on the feedback information, so that the travel route is more in line with the actual needs of tourists, and enhance the autonomy and interactivity of tourists in the travel process.

[0159] It can promote the development of the cultural tourism industry and carry out precise marketing. Based on the personalized needs and behavioral characteristics of tourists, tourism enterprises and management departments can better understand tourists' needs, carry out precise marketing activities, and improve the promotion effect and market share of tourism products; it has data-driven decision-making. The large amount of tourism data collected by the system can provide data support for the development of the tourism industry, help enterprises and management departments make market analysis, product development, resource planning and other decisions, and promote the innovation and sustainable development of the cultural tourism industry; it can enhance cultural communication, promote cultural dissemination and exchange by recommending cultural attractions and theme tourist routes that suit their interests, and enhance the connotation and value of cultural tourism.

[0160] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field and related fields without creative work should fall within the scope of protection of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention are implemented according to the conventional means in the field unless otherwise specified and limited.

Claims

1. A real-time optimization and adjustment system for cultural tourism routes based on big data analysis, characterized by: It includes a collection and analysis module, the collection and analysis module is connected to a combination and matching module, the combination and matching module is connected to a path optimization module, and the path optimization module is connected to an interactive feedback module; The collection and analysis module is used to collect the tourist behavior characteristic information of tourists in real time, and use big data analysis technology to process and analyze the collected tourist behavior characteristic information in combination with the tourists' historical tour records, interests, hobbies and age, determine the tourists' preference for different types of cultural attractions, and establish a personalized tourist model; The combined matching module is used to determine the matching degree of the scenic spots based on the personalized model of the tourists and in combination with the travel preferences, wherein the travel preferences include food preferences, accommodation preferences, cultural preferences and transportation preferences; The route optimization module is used to obtain real-time external data, obtain traffic information, scenic spot flow information, weather information, and customize the initial travel route in combination with the scenic spot matching degree; The interactive feedback module interacts with tourists through a map application on a mobile phone application or an intelligent tour guide device based on a wireless network to provide tourists with real-time routes, including route recommendations and navigation services; during the route recommendation and navigation service, tourists provide feedback on the real-time route, and the system determines the feedback route based on the feedback information; The process of building a personalized tourist model: Step 1: Collect and organize data, collect tourist behavior characteristics in real time, obtain tourist behavior data, preference data and location information, organize and store them according to different categories; at the same time, obtain tourists' historical travel records, interests and hobbies, and age; Step 2: Perform data analysis and feature extraction, analyze the behavior data, preference data, and location information separately and combine them with historical travel records, interests, hobbies, and age to obtain analysis results; Step 3: Build the model. First, determine the feature weights. Based on the data analysis results, determine the weights of each feature in the personalized model. Then, a model framework is established. The decision tree in the machine learning algorithm is used to establish the framework of the tourist personalization model. The tourist behavior characteristic information, historical tour records, interests and hobbies, and age are summarized into tourist data. The tourist data is used as the input variable, and the degree of tourists' preference for different types of cultural attractions is used as the output variable. Then, the model is trained and optimized. The collected tourist data is used for model training, and the parameters and weights of the model are continuously adjusted to improve the accuracy and generalization ability of the model. The performance of the model is evaluated by cross-validation method and optimized to obtain a personalized tourist model. Finally, the model is updated and maintained. As new tourist data is continuously collected, the tourist personalized model is regularly updated and maintained through the preset automatic update mechanism; The process of determining the matching degree of attractions: Step 1: Determine the weight of each preference Assume that the food preference weight is w1, the accommodation preference weight is w2, the humanities preference weight is w3, and the transportation preference weight is w4, and they satisfy w1+w2+w3+w4=1; Step 2: Quantify the degree of match of each preference: For the dietary preference matching, denoted as S1: The catering scores are made according to the catering selection records and catering preference data in the personalized model of tourists, as well as the catering conditions around the scenic spots; the catering score range is set to 0-100, with 100 points for full compliance, 60 points for partial compliance, and 20 points for non-compliance; the calculation formula considers: restaurant type compliance, price compliance, and evaluation compliance; the calculation formula is: S1=a1×restaurant type compliance+a2×price compliance+a3×evaluation compliance, where a1, a2, and a3 are weight coefficients, and a1+a2+a3=1; For the accommodation preference matching, denoted as S2: Accommodation rating is performed based on the accommodation preference data in the tourist personalization model and the accommodation facilities near the scenic spot; the score range of the accommodation rating is set to 0-100, with 100 points for full compliance, 60 points for partial compliance, and 20 points for non-compliance; the calculation formula considers: distance factors and facility compliance; the calculation formula is: S2=b1×distance compliance+b2×facility compliance, where b1 and b2 are weight coefficients, and b1+b2=1; For the humanities preference matching, it is denoted as S3: According to the tourism theme preference and humanistic preference data in the tourist personalized model, as well as the humanistic characteristics of the scenic spot, a humanistic score is given; the score range of the humanistic score is set to 0-100, with full compliance being 100 points, partial compliance being 60 points, and non-compliance being 20 points; the calculation formula is: S3=c1×humanistic characteristics compliance, where c1 is the weight coefficient; For the traffic preference matching degree, it is denoted as S4: The traffic score is calculated based on the traffic preference data in the tourist personalized model and the traffic conditions of the scenic spot. The traffic score range is set to 0-100, and the calculation formula considers: traffic mode compliance and traffic time factors; the calculation formula is: S4=d1×traffic mode compliance+d2×traffic time compliance, where d1 and d2 are weight coefficients, and d1+d2=1; Step 3: Calculate the matching degree of scenic spots: The scenic spot matching degree is denoted as M and calculated by the following formula: M=w1S1+w2S2+w3S3+w4S4.

2. According to claim 1, a real-time optimization and adjustment system for cultural tourism routes based on big data analysis is characterized by: The path optimization module also includes: The optimization unit uses a personalized demand matching algorithm based on the initial travel route to calculate a recommended route that meets the personalized needs of tourists and avoids unfavorable factors; and obtains the optimal route from the recommended route based on physical energy consumption and travel expenses; The real-time path unit is used to recalculate the path based on the needs of tourists or changes in the external environment to obtain a real-time path.

3. According to claim 2, a real-time optimization and adjustment system for cultural tourism routes based on big data analysis is characterized in that: The initial game path customization process is as follows: First, we use the real-time data from map applications to obtain real-time traffic information, including road congestion, public transportation operation hours and frequencies, and traffic control information. We also use real-time information on social media to collect information about the flow of people at scenic spots and understand the number of tourists and the degree of congestion at each scenic spot. Collect weather information through weather apps, including current weather conditions and weather forecasts; According to the matching degree of each scenic spot, the scenic spot is given an initial priority, and the initial priority is adjusted in combination with external data to obtain the scenic spot priority; Then plan the initial play path: First, select the starting point: determine the starting point of the tour route based on the tourist's current location or the preset starting point; Then, based on time constraints, transportation connections, and theme coherence, attractions are selected in order, from high to low priority, to be included in the initial tour route; Finally, determine the end point: based on the needs and actual situation of tourists, choose a suitable location as the end point; thus obtaining the initial tour route.

4. According to claim 3, a real-time optimization and adjustment system for cultural tourism routes based on big data analysis is characterized in that: The process of getting the recommended path: First, the encoding scheme represents the initial travel path as a chromosome, which consists of a series of attraction numbers; Then, the population is initialized and chromosomes are randomly generated as the initial population; then, the fitness function is determined. First, the scenic spot matching degree is determined: according to the previously determined scenic spot matching degree, the sum of the matching degrees of each scenic spot in the path represented by the chromosome is calculated to obtain the sum of the scenic spot matching degrees; then, unfavorable factors are avoided: the congestion coefficient and the bad weather coefficient are set, and the congestion penalty value and the bad weather penalty value are calculated according to the actual conditions of traffic congestion and bad weather respectively; Then, time limits are imposed: the time required for the route is calculated based on the estimated visiting time and transportation time of the scenic spot, and the overtime penalty value is calculated to ensure that the route is within the travel time given by the tourists; Finally, the traffic connection is carried out: the quality of the traffic connection is evaluated according to the factors of the convenience of the traffic mode and the number of transfers, and the traffic connection reward value is calculated; the fitness function is expressed as: fitness = sum of scenic spot matching - congestion penalty value - bad weather penalty value - timeout penalty value + traffic connection reward value; The roulette wheel selection method is used to calculate the probability of a chromosome being selected according to its fitness value; two chromosomes are randomly selected as parents, and a multi-point crossover operation is performed to generate offspring; the scenic spot number A in the chromosome is randomly replaced with the scenic spot number B; the number of iterations C is set, and when the number of iterations C is met, the algorithm is stopped, and the path at this time is the recommended path.

5. According to claim 4, a real-time optimization and adjustment system for cultural tourism routes based on big data analysis is characterized in that: The process of obtaining the optimal path: Analyze and select recommended routes based on physical energy consumption and travel expenses: Estimate the physical energy consumption of tourists on each route according to the distance between attractions, terrain and tour time; And establish a physical energy consumption model, quantify the distance, terrain and tour time and sum them by weight to obtain physical energy consumption; The travel expenses are calculated based on transportation costs, ticket costs, and food and beverage costs, combined with actual price information and the arrangement of attractions along the route; According to tourists' preferences, weights are assigned to physical energy consumption and travel expenses, and the weighted sum of physical energy consumption and travel expenses is taken to obtain a comprehensive index; then the comprehensive indicators of different recommended paths are sorted from large to small, and the path with the smallest comprehensive index is selected as the optimal path.

6. The real-time optimization and adjustment system for cultural tourism routes based on big data analysis according to claim 5 is characterized by: The process of getting the real-time path: Continuously monitor changes in tourists' needs and external environment, obtain change results, and quantify the change results to obtain change value X, where changes in tourists' needs include temporary changes in itinerary, increase or decrease in tour time; changes in external environment include changes in traffic congestion, changes in the flow of people at scenic spots, and changes in weather; determine whether the path needs to be recalculated based on the monitored change results; set the change interval [x, y], and recalculate the path when the change value X does not fall within [x, y]; When the route needs to be recalculated, real-time external data is collected again, including traffic information, tourist flow information, and weather information. At the same time, the personalized model of tourists is updated. The route is re-optimized according to the process of customizing the initial tour route and obtaining the recommended route and the optimal route. Based on the new data and the changed situation, a real-time route that adapts to the new conditions is calculated. The recalculated real-time route is provided to tourists.

7. The real-time optimization and adjustment system for cultural tourism routes based on big data analysis according to claim 6 is characterized by: During the route recommendation and navigation service, the information feedback from the chat software in the mobile application, the news list of nearby tourist areas pushed by the news broadcast software in the mobile application app, and the notification information released by the smart tour guide device are collected as feedback information to provide feedback on the real-time route currently taken by tourists, and the feedback route is determined based on the feedback information, and temporary feedback and adjustments are made to the real-time route online.

8. The real-time optimization and adjustment system for cultural tourism routes based on big data analysis according to claim 7 is characterized by: The process of providing temporary feedback and adjustment to the real-time path based on feedback information: Tourists communicate with their companions or tourism service personnel in the chat software to share their feelings and questions about the current real-time route; relevant topics and keywords in the chat software are monitored in real time to extract chat feedback information related to the route; Based on the news broadcasting software, the news about emergencies in tourist areas, temporary closure of scenic spots, and traffic control are pushed, and the news content is analyzed to determine the information that affects the current real-time route as news feedback information; The smart tour guide device detects special situations nearby, including excessive crowds in scenic spots and sudden weather changes, based on its built-in sensors and positioning system, and sends notification information to tourists and serves as feedback for the tour guide; Classify and analyze the collected chat feedback information, news feedback information and tour guide feedback information to determine the determining factors that will affect the current real-time path; According to the urgency, importance and impact of the factors on the itinerary, evaluate the impact of the factors on the real-time route, determine the level of impact and obtain the evaluation results; based on the determining factors and evaluation results, find alternative attractions, routes or transportation methods to obtain alternative plans; Combine time constraints, attraction priorities, and transportation connections, and based on alternatives, adjust route planning and re-plan real-time routes; provide the adjusted routes as feedback routes to tourists; While tourists are using the feedback path, the feedback information is continuously monitored to obtain new feedback information; based on the new feedback information, the real-time path is continuously and dynamically adjusted.

Images