A route recommendation method and system based on public transportation

Abstract

The present invention is applicable to the technical field of traffic route recommendation, and provides a route recommendation method and system based on public transportation, which obtains the shared bicycle travel route of the target tourists from their location to their destination, and screens out the cycling-adaptive scenic spots on the shared bicycle travel route; obtains the historical travel data of the target tourists, and determines the target tourists' touring threshold and the expected weights for different categories of scenic spots based on the historical travel data. After the target tourists choose to take a shared bicycle as a public transportation method to arrive at their destination, additional scenic spots are recommended based on the tourists' personal preferences and the actual conditions of the route through scientific methods. By comparing the modified attractiveness score with the touring threshold, scenic spots that meet the tourists' current interests are accurately screened out, and the score is dynamically adjusted in combination with real-time data. This process not only ensures the high relevance and personalization of the recommended scenic spots, but also effectively prevents tourists from having their touring experience affected by factors such as crowding.

Description

Technical Field

[0001] The present invention belongs to the technical field of traffic route recommendation, and in particular to a route recommendation method and system based on public transportation. Background Art

[0002] With the acceleration of urbanization, the diversification of public transportation has gradually become an important feature of urban travel. Traditional public transportation modes such as buses and subways are widely used due to their high efficiency and wide coverage. However, with the development of the sharing economy, shared bicycles, as a flexible and environmentally friendly public transportation mode, are increasingly favored by urban residents and tourists. Especially when the weather conditions are good and the road conditions are suitable, target tourists tend to choose shared bicycles as a way to explore the city and enjoy a freer and closer experience of the city scenery. Shared bicycles can not only cover areas that cannot be directly reached by buses and subways, but also enable tourists to stop at any time to appreciate the attractions along the way, which has flexibility that other modes of transportation do not have.

[0003] However, when recommending attractions to tourists, the existing technology mainly recommends based on the conditions of the attractions themselves, such as popularity, user ratings, and online popularity, and lacks consideration of the target tourists' personal preferences, real-time needs, and current travel routes. This single recommendation method often ignores the personalized needs of tourists and cannot fully combine the actual situation of tourists to provide more targeted recommendations. At the same time, the existing technology usually does not effectively combine shared bicycles as a public transportation method with attraction recommendations in the recommendation process, resulting in the inability to give full play to the flexible and efficient characteristics of shared bicycles in the recommendation process, limiting tourists' travel experience when using shared bicycles and the depth of attraction exploration. Summary of the invention

[0004] The purpose of the present invention is to provide a route recommendation method and system based on public transportation, aiming to solve the problems raised in the background technology.

[0005] The present invention is implemented as follows: a route recommendation method based on public transportation, the method comprising:

[0006] Obtain the shared bicycle travel route of the target tourists from their location to their destination, and filter out suitable riding attractions on the shared bicycle travel route;

[0007] Obtain the historical travel data of target tourists, and determine the target tourists' visit threshold and expected weights for different categories of attractions based on the historical travel data;

[0008] Determine the objective attractiveness index of each cycling-adaptive scenic spot, and calculate the attractiveness score of each cycling-adaptive scenic spot to the target tourists based on the objective attractiveness index and expected weight corresponding to each cycling-adaptive scenic spot;

[0009] The real-time crowd flow information of the cycling-adaptive scenic spots is obtained, and the attractiveness score of the cycling-adaptive scenic spots is corrected based on the real-time crowd flow information to obtain a corrected attractiveness score, and it is determined whether the corrected attractiveness score of the cycling-adaptive scenic spots is greater than a sightseeing threshold, and all the cycling-adaptive scenic spots greater than the sightseeing threshold are marked as additional scenic spots.

[0010] As a further limitation of the technical solution of the embodiment of the present invention, the steps of obtaining the shared bicycle travel route of the target tourist from the location to the destination and screening out the cycling-adaptive scenic spots on the shared bicycle travel route include:

[0011] Obtain the shared bicycle travel route of the target tourist from the location to the destination, and identify all attractions within a preset distance around the shared bicycle travel route;

[0012] Determine whether there is a suitable riding route between all scenic spots within a preset distance around the shared bicycle route and the shared bicycle route;

[0013] If it is determined that there is a suitable cycling route between a certain scenic spot and the shared bicycle route, the scenic spot will be set as a cycling-suitable scenic spot.

[0014] As a further limitation of the technical solution of the embodiment of the present invention, the steps of obtaining historical travel data of target tourists and determining the target tourists' sightseeing threshold and the expected weights for different categories of attractions according to the historical travel data include:

[0015] Obtain historical travel data of target tourists, and extract historical scenic spot travel data of target tourists from the historical travel data, and determine all target historical scenic spots that the target tourists have visited within a preset past period based on the historical scenic spot travel data;

[0016] Obtain the objective attraction indexes of all target historical attractions, and set the average value of all objective attraction indexes as the visit threshold of target tourists;

[0017] Identify the category of each target historical attraction and determine the proportion of each category. Based on the proportion of each category, determine the target tourists' expected weight for each category of attractions.

[0018] As a further limitation of the technical solution of the embodiment of the present invention, the steps of determining the objective attractiveness index of each cycling-adaptive scenic spot, and calculating the attractiveness score of each cycling-adaptive scenic spot to the target tourist based on the objective attractiveness index and the expected weight corresponding to each cycling-adaptive scenic spot include:

[0019] Determine the objective attractiveness index of each ride-suitable attraction;

[0020] Identify the category of each ride-suitable attraction to determine the target tourists' expected weight for each ride-suitable attraction;

[0021] The product of the objective attraction index and the expected weight corresponding to each cycling-adaptive attraction is obtained to obtain the attractiveness score of each cycling-adaptive attraction to the target tourists.

[0022] As a further limitation of the technical solution of the embodiment of the present invention, when obtaining the objective attractiveness index of the target historical scenic spot and the objective attractiveness index of the cycling-adaptive scenic spot, relevant data should be obtained through network data analysis and big data mining technology, including indicators such as network popularity, traffic flow, and user ratings, and these indicators should be weighted calculated to obtain the objective attractiveness index of each scenic spot; when obtaining the objective attractiveness index of the target historical scenic spot, the historical attractiveness index corresponding to the time when the target historical scenic spot occurred should be extracted, and for the cycling-adaptive scenic spot, the real-time current attractiveness index should be obtained.

[0023] As a further limitation of the technical solution of the embodiment of the present invention, the steps of obtaining real-time crowd flow information of the cycling-adaptive scenic spot, and correcting the attractiveness score of the cycling-adaptive scenic spot based on the real-time crowd flow information to obtain a corrected attractiveness score, judging whether the corrected attractiveness score of the cycling-adaptive scenic spot is greater than a sightseeing threshold, and marking all the cycling-adaptive scenic spots greater than the sightseeing threshold as additional scenic spots include:

[0024] Obtaining real-time crowd flow information of the cycling-adapted scenic spot, and determining the degree of congestion of the cycling-adapted scenic spot based on the real-time crowd flow information;

[0025] The attractiveness score of the cycling-adaptive scenic spot is corrected according to the congestion level of the cycling-adaptive scenic spot to obtain a corrected attractiveness score;

[0026] It is determined whether the modified attractiveness score of the cycling-adaptive attractions is greater than the tour threshold, and all cycling-adaptive attractions greater than the tour threshold are marked as additional attractions.

[0027] As a further limitation of the technical solution of the embodiment of the present invention, the step of determining whether the modified attractiveness score of the cycling-adaptive scenic spot is greater than the sightseeing threshold, and marking all the cycling-adaptive scenic spots greater than the sightseeing threshold as additional scenic spots includes:

[0028] Determine whether the modified attractiveness score of the cycling-adapted scenic spots on the shared bicycle route is greater than the sightseeing threshold;

[0029] If the modified attractiveness score of a cycling-adaptive scenic spot on the shared bicycle route is greater than the sightseeing threshold, the cycling-adaptive scenic spot is marked as an additional scenic spot;

[0030] Get the best cycling route with all additional attractions to the shared bike route to obtain a tree diagram of the shared bike route.

[0031] A route recommendation system based on public transportation, the system comprising: a cycling-adaptive scenic spot determination module, a travel data analysis module, an attraction score calculation module and an additional scenic spot determination module, wherein:

[0032] A cycling-suitable scenic spot determination module is used to obtain the shared bicycle travel route of the target tourists from their location to their destination, and to screen out the cycling-suitable scenic spots on the shared bicycle travel route;

[0033] The travel data analysis module is used to obtain the historical travel data of the target tourists and determine the target tourists' visit threshold and the expected weights for different categories of attractions based on the historical travel data;

[0034] An attraction score calculation module is used to determine the objective attraction index of each cycling-adaptive scenic spot, and calculate the attraction score of each cycling-adaptive scenic spot to the target tourists based on the objective attraction index and expected weight corresponding to each cycling-adaptive scenic spot;

[0035] The additional scenic spot determination module is used to obtain the real-time crowd flow information of the cycling-adaptive scenic spots, and based on the real-time crowd flow information, correct the attractiveness score of the cycling-adaptive scenic spots to obtain a corrected attractiveness score, determine whether the corrected attractiveness score of the cycling-adaptive scenic spots is greater than a sightseeing threshold, and mark all cycling-adaptive scenic spots greater than the sightseeing threshold as additional scenic spots.

[0036] As a further limitation of the technical solution of the embodiment of the present invention, the riding-adaptive scenic spot determination module specifically includes:

[0037] A scenic spot identification unit is used to obtain the shared bicycle driving route of the target tourist from the location to the destination, and identify all scenic spots within a preset distance around the shared bicycle driving route;

[0038] A cycling route analysis unit is used to determine whether there is a suitable cycling route between all scenic spots within a preset distance around the shared bicycle route and the shared bicycle route;

[0039] The cycling-adaptive scenic spot determining unit is used to set a certain scenic spot as a cycling-adaptive scenic spot if it is determined that there is a suitable cycling route between a certain scenic spot and the shared bicycle driving route.

[0040] As a further limitation of the technical solution of the embodiment of the present invention, the travel data parsing module specifically includes:

[0041] A target historical scenic spot acquisition unit is used to acquire the historical travel data of the target tourist, and extract the historical scenic spot travel data of the target tourist from the historical travel data, and determine all the target historical scenic spots that the target tourist has visited within a preset past period according to the historical scenic spot travel data;

[0042] A tour threshold calculation unit, used to obtain the objective attraction index of all target historical attractions, and set the average value of all objective attraction indexes as the tour threshold of target tourists;

[0043] The expected weight determination unit is used to identify the category of each target historical attraction and determine the proportion of each category, and determine the expected weight of each category of attractions for the target tourists based on the proportion of each category.

[0044] Compared with the prior art, the present invention obtains the shared bicycle driving route of the target tourists from the location to the destination, and screens out the cycling-adapted attractions on the shared bicycle driving route; obtains the historical travel data of the target tourists, and determines the target tourists' sightseeing threshold and the expected weights of different categories of attractions based on the historical travel data; determines the objective attractiveness index of each cycling-adapted attraction, and calculates the attractiveness score of each cycling-adapted attraction to the target tourists based on the objective attractiveness index and expected weight corresponding to each cycling-adapted attraction; obtains the real-time flow information of the cycling-adapted attractions, and corrects the attractiveness score of the cycling-adapted attractions based on the real-time flow information to obtain the corrected attractiveness score, determines whether the corrected attractiveness score of the cycling-adapted attractions is greater than the sightseeing threshold, and marks all the cycling-adapted attractions greater than the sightseeing threshold as additional attractions. After the target tourists choose the shared bicycle as a public transportation mode to arrive at the destination, additional attractions are recommended according to the tourists' personal preferences and the actual situation of the route through scientific methods. By comparing the corrected attractiveness score with the sightseeing threshold, the attractions that meet the current interests of the tourists are accurately screened out, and the score is dynamically adjusted in combination with real-time data. This process not only ensures the high relevance and personalization of recommended attractions, but also effectively prevents tourists from having their sightseeing experience affected by factors such as crowding. In addition, this technical solution can improve the travel experience of target tourists from multiple angles: on the one hand, it provides highly personalized attraction recommendations, allowing tourists to discover more attractions that suit their interests during the ride; on the other hand, by optimizing the riding routes, it increases the attractiveness and frequency of shared bicycles as a means of public transportation, thereby promoting the popularization and promotion of shared bicycles in cities. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A flowchart of a method provided by an embodiment of the present invention;

[0046] Figure 2 A flow chart of selecting suitable riding attractions on a shared bicycle route in the method provided in an embodiment of the present invention;

[0047] Figure 3 A flow chart of determining the visiting threshold of target tourists and the expected weights of different categories of attractions in the method provided in an embodiment of the present invention;

[0048] Figure 4 A flow chart of determining the attractiveness score of each cycling-adaptive scenic spot to target tourists in the method provided in an embodiment of the present invention;

[0049] Figure 5 A flow chart of obtaining a modified attractiveness score of a riding-adapted scenic spot in the method provided in an embodiment of the present invention;

[0050] Figure 6 A flow chart of determining additional scenic spots on a shared bicycle route in a method provided in an embodiment of the present invention;

[0051] Figure 7 An application architecture diagram of a system provided by an embodiment of the present invention;

[0052] Figure 8 A structural block diagram of a riding-adaptive scenic spot determination module in a system provided in an embodiment of the present invention;

[0053] Fig. 9 This is a structural block diagram of a travel data analysis module in the system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0055] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0056] Specifically, a route recommendation method based on public transportation includes the following steps:

[0057] Step S100, obtaining the shared bicycle travel route of the target tourist from the location to the destination, and screening out the cycling-suitable scenic spots on the shared bicycle travel route.

[0058] Specifically, Figure 2 A flow chart for screening out cycling-suitable scenic spots on a shared bicycle route is shown.

[0059] The process of obtaining the shared bicycle travel route of the target tourists from their location to their destination and selecting suitable riding spots on the shared bicycle travel route specifically includes the following steps:

[0060] Step S101, obtaining a shared bicycle travel route of a target tourist from a location to a destination, and identifying all scenic spots within a preset distance around the shared bicycle travel route;

[0061] Step S102, determining whether there is a suitable riding route between all scenic spots within a preset distance around the shared bicycle route and the shared bicycle route;

[0062] Step S103: If it is determined that there is a suitable cycling route between a certain scenic spot and the shared bicycle driving route, the scenic spot is set as a cycling-suitable scenic spot.

[0063] In the embodiment of the present invention, the purpose of the present invention is to match the target tourists with suitable scenic spots along the way, based on the actual situation of the target tourists' shared bicycle travel route and the target tourists' personalized preferences, on the premise that the target tourists have chosen shared bicycles as a public transportation mode to reach the destination. By recommending shared bicycles as a public transportation mode to more scenic spots based on the shared bicycle travel route, on the one hand, the travel experience of the target tourists is improved, and on the other hand, the shared bicycles as a transportation mode can be effectively promoted, and its popularization and widespread use in the city can be promoted.

[0064] To obtain the shared bicycle travel route of the target tourists from their location to their destination, the navigation software or map application can automatically generate the optimal route based on the starting and ending points entered by the user. The preset distance can be set based on the reasonable range that the target tourists are willing to deviate from the main route, usually a few hundred meters to one kilometer, depending on the city's geographical environment and the preferences of the target tourists. When identifying attractions within the preset distance, a geographic information system (GIS) can be used in combination with tourism data to filter out attractions within the range.

[0065] To determine whether there is a suitable cycling route, it is necessary to consider the cycling safety, accessibility, and suitability of the road conditions. "Suitable" is mainly defined as whether the cycling route has a safe bicycle lane, is unobstructed, and does not require too many detours. For example, if there is a continuous bicycle lane between a certain scenic spot and the shared bicycle route, and it does not need to pass through busy or dangerous roads, then the route can be considered a suitable cycling route, and the scenic spot can be set as a cycling-suitable scenic spot.

[0066] All of the above analysis and judgment can be achieved through existing navigation systems, map applications and geographic information system (GIS) software to ensure the optimal shared bicycle route and identify suitable riding attractions.

[0067] Furthermore, the route recommendation method based on public transportation also includes the following steps:

[0068] Step S200, obtaining historical travel data of target tourists, and determining the target tourists' sightseeing threshold and expected weights for different types of attractions based on the historical travel data.

[0069] Specifically, Figure 3 A flow chart for determining the visit threshold of target tourists and the desired weights for different categories of attractions is shown.

[0070] The process of obtaining the historical travel data of target tourists and determining the target tourists' visit threshold and the expected weights for different types of attractions based on the historical travel data specifically includes the following steps:

[0071] Step S201, obtaining historical travel data of the target tourist, and extracting historical scenic spot travel data of the target tourist from the historical travel data, and determining all target historical scenic spots that the target tourist has visited within a preset past period according to the historical scenic spot travel data;

[0072] Step S202, obtaining the objective attraction indexes of all target historical attractions, and setting the average value of all objective attraction indexes as the target tourist's sightseeing threshold;

[0073] Step S203, identifying the category of each target historical attraction, and determining the proportion of each category, and determining the expected weight of each category of attractions by the target tourists according to the proportion of each category.

[0074] In an embodiment of the present invention, the extraction of historical scenic spot travel data can be achieved by analyzing the historical travel records of the target tourists in the navigation software, which include the travel routes, destinations visited, and duration of stay planned by the tourists through the navigation software. Through data mining technology, all navigation records related to scenic spots are screened out to determine the scenic spots visited by the target tourists in the preset past period, and these scenic spots are the target historical scenic spots. For example, if a tourist has visited historical and cultural scenic spots through the navigation software many times in the past year, these scenic spots will be extracted and marked as target historical scenic spots.

[0075] The visit threshold is set based on the average of the objective attractiveness index of all target historical attractions. The basis of this method is that by calculating the overall attractiveness of the attractions that the target tourists have visited in history, the minimum acceptance standard of the target tourists for new attractions can be inferred. The advantage of this setting method is that the visit threshold can help filter out those attractions whose attractiveness is significantly lower than the average preference of the target tourists, ensuring that the recommended attractions meet the basic interest standards of tourists. For example, if the average attractiveness index of the attractions in the historical data is 75 points, the threshold for recommending new attractions can be set to above 75 points to ensure the quality of the recommendation.

[0076] The expected weight is set based on the proportion of the target historical scenic spot category. By identifying the proportion of each category of scenic spots in the target tourists' historical visit records, the target tourists' preference for different types of scenic spots can be inferred. The advantage of this setting method is that the expected weight can make the recommendation system more personalized and recommend scenic spots based on the tourists' real preferences. For example, if 80% of the target tourists' historical travel records are concentrated in natural scenery attractions, then the expected weight of natural scenery attractions will be correspondingly higher, and destinations matching such attractions will be recommended first, thereby better meeting the personalized needs of the target tourists.

[0077] Furthermore, the route recommendation method based on public transportation also includes the following steps:

[0078] Step S300, determining the objective attraction index of each cycling-adaptive scenic spot, and calculating the attraction score of each cycling-adaptive scenic spot to the target tourist based on the objective attraction index and the expected weight corresponding to each cycling-adaptive scenic spot.

[0079] Specifically, Figure 4 A flow chart for determining the attractiveness score of each ride-compatible attraction for target tourists is shown.

[0080] The objective attraction index of each cycling-adaptive scenic spot is determined, and based on the objective attraction index and expected weight corresponding to each cycling-adaptive scenic spot, the attractiveness score of each cycling-adaptive scenic spot to the target tourists is calculated, which specifically includes the following steps:

[0081] Step S301, determining the objective attraction index of each cycling-adaptive scenic spot;

[0082] Step S302, identifying the category of each cycling-adaptive scenic spot to determine the expected weight of each cycling-adaptive scenic spot by the target tourists;

[0083] Step S303, obtaining the product of the objective attraction index and the expected weight corresponding to each cycling-adaptive scenic spot, so as to obtain the attraction score of each cycling-adaptive scenic spot to the target tourist.

[0084] When obtaining the objective attractiveness index of the target historical attractions and the objective attractiveness index of cycling-compatible attractions, relevant data should be obtained through network data analysis and big data mining technology, including indicators such as network popularity, traffic flow, and user ratings, and these indicators should be weighted calculated to obtain the objective attractiveness index of each attraction; when obtaining the objective attractiveness index of the target historical attractions, the historical attractiveness index corresponding to the time when the target historical attractions occurred should be extracted, and for cycling-compatible attractions, the real-time current attractiveness index should be obtained.

[0085] In the embodiment of the present invention, the attractiveness score is obtained by combining the objective attractiveness index of the cycling-adapted scenic spot and the expected weight of the target tourists, ensuring that the score reflects both the overall popularity of the scenic spot and the personalized preferences of the target tourists. The rationality of this scoring method lies in that it comprehensively considers the general attractiveness of the scenic spot and the personal interests of the tourists, making the recommendation results more accurate and relevant.

[0086] The benefit of this scoring method is that it provides highly personalized attraction recommendations that can dynamically adjust to changes in tourists' interests, ensuring that the recommended attractions always meet the needs of target tourists. Through this scoring, the recommendation system can more effectively improve user satisfaction and enhance tourists' experience during the ride.

[0087] The acquisition method of the above objective attraction index relies on network data analysis and big data mining technology, which has been widely used in various fields and belongs to the category of existing technologies. The attractiveness of scenic spots is evaluated by integrating network popularity, traffic, user ratings and other indicators and performing weighted calculations. This method has been widely used in big data analysis and user preference mining. In addition, extracting historical data and real-time data according to different time points to dynamically adjust the attraction index of scenic spots is also a common practice under the existing technical framework, which can ensure that the evaluation of the attractiveness of scenic spots is more accurate and timely.

[0088] Furthermore, the route recommendation method based on public transportation also includes the following steps:

[0089] Step S400, obtaining real-time crowd flow information of the cycling-adaptive scenic spot, and correcting the attractiveness score of the cycling-adaptive scenic spot based on the real-time crowd flow information to obtain a corrected attractiveness score, determining whether the corrected attractiveness score of the cycling-adaptive scenic spot is greater than a sightseeing threshold, and marking all cycling-adaptive scenic spots greater than the sightseeing threshold as additional scenic spots.

[0090] Specifically, Figure 5 A flow chart for obtaining a modified attraction score for a ride-compatible attraction is shown.

[0091] The process of obtaining the real-time flow information of the cycling-adaptive scenic spots, and correcting the attractiveness score of the cycling-adaptive scenic spots based on the real-time flow information to obtain a corrected attractiveness score, judging whether the corrected attractiveness score of the cycling-adaptive scenic spots is greater than a sightseeing threshold, and marking all the cycling-adaptive scenic spots greater than the sightseeing threshold as additional scenic spots specifically includes the following steps:

[0092] Step S401, obtaining real-time crowd flow information of the cycling-adaptable scenic spot, and determining the congestion level of the cycling-adaptable scenic spot based on the real-time crowd flow information;

[0093] Step S402, correcting the attraction score of the cycling-adaptive scenic spot according to the congestion level of the cycling-adaptive scenic spot to obtain a corrected attraction score;

[0094] Step S403, determining whether the modified attractiveness score of the cycling-adaptive scenic spot is greater than a sightseeing threshold, and marking all cycling-adaptive scenic spots greater than the sightseeing threshold as additional scenic spots.

[0095] In the embodiment of the present invention, the setting of the degree of crowding is based on the ratio of the real-time flow of people to the maximum carrying capacity of the scenic spot, and the degree of crowding is divided into four levels: "low", "medium", "high" and "very high". Specifically, when the flow of people is less than 30% of the capacity, it is low crowding; 30% to 60% is medium crowding; 60% to 90% is high crowding; and more than 90% is very high crowding. This classification method can effectively reflect the current flow of people in the scenic spot.

[0096] When revising the attraction score, appropriate adjustments are made based on different crowding levels. For low crowding levels, the attraction score can be slightly increased, such as by 10%; for medium crowding levels, the score remains unchanged; for high crowding levels, the score is moderately reduced, such as by 20%; and for very high crowding levels, the score is significantly reduced, such as by 40%. This correction method ensures that the score can better reflect the actual experience of the attraction.

[0097] For example, an attraction with an original attractiveness score of 80 points is classified as highly crowded if its current visitor flow is 80% of its maximum capacity. According to the revised rules, the attractiveness score is reduced by 20%, bringing the final score down to 64 points. This revised score helps tourists better evaluate the actual attractiveness of the attraction and avoid the impact of crowding on their visit experience.

[0098] Specifically, Figure 6 A flow chart for determining additional attractions on a shared bicycle travel route is shown.

[0099] The process of judging whether the modified attractiveness score of the cycling-adaptive scenic spot is greater than the sightseeing threshold and marking all the cycling-adaptive scenic spots greater than the sightseeing threshold as additional scenic spots specifically includes the following steps:

[0100] Step S4031, determining whether the corrected attractiveness score of the cycling-adaptive scenic spot on the shared bicycle travel route is greater than the sightseeing threshold;

[0101] Step S4032: if the corrected attractiveness score of a cycling-adaptive scenic spot on the shared bicycle route is greater than the sightseeing threshold, the cycling-adaptive scenic spot is marked as an additional scenic spot;

[0102] Step S4033, obtaining the best riding routes from all additional scenic spots to the shared bicycle driving routes to obtain a tree diagram of the shared bicycle driving routes.

[0103] In the embodiment of the present invention, by comparing the modified attractiveness score with the tour threshold, the additional attractions that are most suitable for the target tourists can be effectively screened. The advantage of this method is that it combines the real-time situation of the attractions with the personalized preferences of tourists, ensuring that only those attractions that are most attractive and in line with the interests of tourists at the current moment are recommended as additional attractions. This not only improves the accuracy of the recommendation, but also optimizes the overall experience of tourists.

[0104] In addition, this approach has significant advantages over existing technologies. By dynamically adjusting the attractiveness score to reflect real-time crowding and other immediate factors, this method can more accurately match the actual needs of target tourists and avoid the limitations of relying solely on static scores. This not only improves the accuracy and personalization of recommendations, but also effectively reduces the negative experience of tourists caused by overcrowding. In addition, combined with the visit threshold for screening, it ensures that the recommended attractions meet the minimum acceptance standards of the target tourists, thereby optimizing the relevance and practicality of the recommendation results, surpassing the capabilities of traditional recommendation systems.

[0105] The best cycling route is obtained by planning the paths of all the places marked as additional attractions and the shared bicycle route. The optimal cycling path between the additional attractions and the main route is calculated using the path optimization algorithm in the navigation system or map application to ensure the continuity and convenience of the route, thereby generating the final shared bicycle route tree diagram.

[0106] In summary, after the target tourists choose shared bicycles as a public transportation mode to arrive at the destination, additional attractions are recommended based on the tourists' personal preferences and the actual situation of the route through a scientific method. By comparing the modified attractiveness score with the tour threshold, the attractions that meet the tourists' current interests are accurately screened, and the scores are dynamically adjusted in combination with real-time data. This process not only ensures the high relevance and personalization of the recommended attractions, but also effectively prevents tourists from affecting their tour experience due to factors such as crowding. The acquisition of the best cycling route further optimizes the use experience of shared bicycles and ensures the continuity and convenience of the itinerary.

[0107] The beneficial effect of this technical solution is that it can enhance the travel experience of target tourists from multiple angles: on the one hand, it provides highly personalized attraction recommendations, allowing tourists to discover more attractions that suit their interests during their rides; on the other hand, by optimizing riding routes, it increases the attractiveness and frequency of shared bicycles as a means of public transportation, thereby promoting the popularization and promotion of shared bicycles in cities.

[0108] Furthermore, Figure 7 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0109] In another preferred embodiment of the present invention, a route recommendation system based on public transportation includes:

[0110] The cycling-suitable scenic spot determination module 100 is used to obtain the shared bicycle travel route of the target tourist from the location to the destination, and screen out the cycling-suitable scenic spots on the shared bicycle travel route.

[0111] Specifically, Figure 8 The structure block diagram of the riding adaptation scenic spot determination module 100 in the system provided by the embodiment of the present invention is shown.

[0112] Among them, in the preferred embodiment provided by the present invention, the riding-adaptive scenic spot determination module 100 specifically includes:

[0113] The scenic spot identification unit 101 is used to obtain the shared bicycle driving route of the target tourist from the location to the destination, and identify all scenic spots within a preset distance around the shared bicycle driving route;

[0114] The cycling route analysis unit 102 is used to determine whether there is a suitable cycling route between all scenic spots within a preset distance around the shared bicycle driving route and the shared bicycle driving route;

[0115] The cycling-adaptive scenic spot determining unit 103 is used to set a certain scenic spot as a cycling-adaptive scenic spot if it is determined that there is a suitable cycling route between a certain scenic spot and the shared bicycle driving route.

[0116] In the embodiment of the present invention, the purpose of the present invention is to match the target tourists with suitable scenic spots along the way, based on the actual situation of the target tourists' shared bicycle travel route and the target tourists' personalized preferences, on the premise that the target tourists have chosen shared bicycles as a public transportation mode to reach the destination. By recommending shared bicycles as a public transportation mode to more scenic spots based on the shared bicycle travel route, on the one hand, the travel experience of the target tourists is improved, and on the other hand, the shared bicycles as a transportation mode can be effectively promoted, and its popularization and widespread use in the city can be promoted.

[0117] To obtain the shared bicycle travel route of the target tourists from their location to their destination, the navigation software or map application can automatically generate the optimal route based on the starting and ending points entered by the user. The preset distance can be set based on the reasonable range that the target tourists are willing to deviate from the main route, usually a few hundred meters to one kilometer, depending on the city's geographical environment and the preferences of the target tourists. When identifying attractions within the preset distance, a geographic information system (GIS) can be used in combination with tourism data to filter out attractions within the range.

[0118] To determine whether there is a suitable cycling route, it is necessary to consider the cycling safety, accessibility, and suitability of the road conditions. "Suitable" is mainly defined as whether the cycling route has a safe bicycle lane, is unobstructed, and does not require too many detours. For example, if there is a continuous bicycle lane between a certain scenic spot and the shared bicycle route, and it does not need to pass through busy or dangerous roads, then the route can be considered a suitable cycling route, and the scenic spot can be set as a cycling-suitable scenic spot.

[0119] All of the above analysis and judgment can be achieved through existing navigation systems, map applications and geographic information system (GIS) software to ensure the optimal shared bicycle route and identify suitable riding attractions.

[0120] Furthermore, the route recommendation system based on public transportation also includes:

[0121] The travel data analysis module 200 is used to obtain the historical travel data of the target tourists, and determine the target tourists' sightseeing threshold and the expected weights for different types of attractions based on the historical travel data.

[0122] Specifically, Fig. 9 It shows a structural block diagram of the travel data parsing module 200 in the system provided by an embodiment of the present invention.

[0123] Among them, in the preferred embodiment provided by the present invention, the travel data parsing module 200 specifically includes:

[0124] The target historical scenic spot acquisition unit 201 is used to acquire the historical travel data of the target tourist, and extract the historical scenic spot travel data of the target tourist from the historical travel data, and determine all the target historical scenic spots that the target tourist has visited within a preset past period according to the historical scenic spot travel data;

[0125] A sightseeing threshold calculation unit 202 is used to obtain the objective attraction index of all target historical attractions and set the average value of all objective attraction indexes as the sightseeing threshold of the target tourists;

[0126] The expected weight determination unit 203 is used to identify the category of each target historical attraction and determine the proportion of each category, and determine the expected weight of each category of attractions for the target tourists according to the proportion of each category.

[0127] In an embodiment of the present invention, the extraction of historical scenic spot travel data can be achieved by analyzing the historical travel records of the target tourists in the navigation software, which include the travel routes, destinations visited, and duration of stay planned by the tourists through the navigation software. Through data mining technology, all navigation records related to scenic spots are screened out to determine the scenic spots visited by the target tourists in the preset past period, and these scenic spots are the target historical scenic spots. For example, if a tourist has visited historical and cultural scenic spots through the navigation software many times in the past year, these scenic spots will be extracted and marked as target historical scenic spots.

[0128] The visit threshold is set based on the average of the objective attractiveness index of all target historical attractions. The basis of this method is that by calculating the overall attractiveness of the attractions that the target tourists have visited in history, the minimum acceptance standard of the target tourists for new attractions can be inferred. The advantage of this setting method is that the visit threshold can help filter out those attractions whose attractiveness is significantly lower than the average preference of the target tourists, ensuring that the recommended attractions meet the basic interest standards of tourists. For example, if the average attractiveness index of the attractions in the historical data is 75 points, the threshold for recommending new attractions can be set to above 75 points to ensure the quality of the recommendation.

[0129] The expected weight is set based on the proportion of the target historical scenic spot category. By identifying the proportion of each category of scenic spots in the target tourists' historical visit records, the target tourists' preference for different types of scenic spots can be inferred. The advantage of this setting method is that the expected weight can make the recommendation system more personalized and recommend scenic spots based on the tourists' real preferences. For example, if 80% of the target tourists' historical travel records are concentrated in natural scenery attractions, then the expected weight of natural scenery attractions will be correspondingly higher, and destinations matching such attractions will be recommended first, thereby better meeting the personalized needs of the target tourists.

[0130] Furthermore, the route recommendation system based on public transportation also includes:

[0131] The attraction score calculation module 300 is used to determine the objective attraction index of each cycling-adaptive scenic spot, and calculate the attraction score of each cycling-adaptive scenic spot to the target tourists based on the objective attraction index and expected weight corresponding to each cycling-adaptive scenic spot;

[0132] The additional scenic spot determination module 400 is used to obtain the real-time crowd flow information of the cycling-adapted scenic spot, and based on the real-time crowd flow information, correct the attractiveness score of the cycling-adapted scenic spot to obtain a corrected attractiveness score, determine whether the corrected attractiveness score of the cycling-adapted scenic spot is greater than a sightseeing threshold, and mark all cycling-adapted scenic spots greater than the sightseeing threshold as additional scenic spots.

[0133] In an embodiment of the present invention, when obtaining the objective attractiveness index of the target historical scenic spot and the objective attractiveness index of the cycling-adaptive scenic spot, relevant data should be obtained through network data analysis and big data mining technology, including indicators such as network popularity, traffic flow, and user ratings, and these indicators should be weighted calculated to obtain the objective attractiveness index of each scenic spot; when obtaining the objective attractiveness index of the target historical scenic spot, the historical attractiveness index corresponding to the time when the target historical scenic spot occurred should be extracted, and for the cycling-adaptive scenic spot, the real-time current attractiveness index should be obtained.

[0134] The attractiveness score is obtained by combining the objective attractiveness index of the cycling-adapted attractions and the expected weight of the target tourists, ensuring that the score reflects both the overall popularity of the attractions and the personalized preferences of the target tourists. The rationality of this scoring method lies in that it comprehensively considers the general attractiveness of the attractions and the personal interests of tourists, making the recommendation results more accurate and relevant.

[0135] The benefit of this scoring method is that it provides highly personalized attraction recommendations that can dynamically adjust to changes in tourists' interests, ensuring that the recommended attractions always meet the needs of target tourists. Through this scoring, the recommendation system can more effectively improve user satisfaction and enhance tourists' experience during the ride.

[0136] The acquisition method of the above objective attraction index relies on network data analysis and big data mining technology, which has been widely used in various fields and belongs to the category of existing technologies. The attractiveness of scenic spots is evaluated by integrating network popularity, traffic, user ratings and other indicators and performing weighted calculations. This method has been widely used in big data analysis and user preference mining. In addition, extracting historical data and real-time data according to different time points to dynamically adjust the attraction index of scenic spots is also a common practice under the existing technical framework, which can ensure that the evaluation of the attractiveness of scenic spots is more accurate and timely.

[0137] The setting of the crowding level is based on the ratio of real-time passenger flow to the maximum carrying capacity of the scenic spot, and the crowding level is divided into four levels: "low", "medium", "high" and "very high". Specifically, when the passenger flow is less than 30% of the capacity, it is low crowding; 30% to 60% is medium crowding; 60% to 90% is high crowding; and more than 90% is very high crowding. This grading method can effectively reflect the current passenger flow of the scenic spot.

[0138] When revising the attraction score, appropriate adjustments are made based on different crowding levels. For low crowding levels, the attraction score can be slightly increased, such as by 10%; for medium crowding levels, the score remains unchanged; for high crowding levels, the score is moderately reduced, such as by 20%; and for very high crowding levels, the score is significantly reduced, such as by 40%. This correction method ensures that the score can better reflect the actual experience of the attraction.

[0139] For example, an attraction with an original attractiveness score of 80 points is classified as highly crowded if its current visitor flow is 80% of its maximum capacity. According to the revised rules, the attractiveness score is reduced by 20%, bringing the final score down to 64 points. This revised score helps tourists better evaluate the actual attractiveness of the attraction and avoid the impact of crowding on their visit experience.

[0140] By comparing the modified attractiveness score with the visit threshold, the additional attractions that are most suitable for target tourists can be effectively screened. The advantage of this method is that it combines the real-time situation of the attractions with the personalized preferences of tourists, ensuring that only those attractions that are most attractive and in line with tourists' interests at the current moment are recommended as additional attractions. This not only improves the accuracy of the recommendation, but also optimizes the overall experience of tourists.

[0141] In addition, this approach has significant advantages over existing technologies. By dynamically adjusting the attractiveness score to reflect real-time crowding and other immediate factors, this method can more accurately match the actual needs of target tourists and avoid the limitations of relying solely on static scores. This not only improves the accuracy and personalization of recommendations, but also effectively reduces the negative experience of tourists caused by overcrowding. In addition, combined with the visit threshold for screening, it ensures that the recommended attractions meet the minimum acceptance standards of the target tourists, thereby optimizing the relevance and practicality of the recommendation results, surpassing the capabilities of traditional recommendation systems.

[0142] The best cycling route is obtained by planning the paths of all the places marked as additional attractions and the shared bicycle route. The optimal cycling path between the additional attractions and the main route is calculated using the path optimization algorithm in the navigation system or map application to ensure the continuity and convenience of the route, thereby generating the final shared bicycle route tree diagram.

[0143] In summary, after the target tourists choose shared bicycles as a public transportation mode to arrive at the destination, additional attractions are recommended based on the tourists' personal preferences and the actual situation of the route through a scientific method. By comparing the modified attractiveness score with the tour threshold, the attractions that meet the tourists' current interests are accurately screened, and the scores are dynamically adjusted in combination with real-time data. This process not only ensures the high relevance and personalization of the recommended attractions, but also effectively prevents tourists from affecting their tour experience due to factors such as crowding. The acquisition of the best cycling route further optimizes the use experience of shared bicycles and ensures the continuity and convenience of the itinerary.

[0144] The beneficial effect of this technical solution is that it can enhance the travel experience of target tourists from multiple angles: on the one hand, it provides highly personalized attraction recommendations, allowing tourists to discover more attractions that suit their interests during their rides; on the other hand, by optimizing riding routes, it increases the attractiveness and frequency of shared bicycles as a means of public transportation, thereby promoting the popularization and promotion of shared bicycles in cities.

[0145] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0146] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0147] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0148] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0149] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A route recommendation method based on public transportation, characterized in that: The method comprises: Obtain the shared bicycle travel route of the target tourists from their location to their destination, and filter out suitable riding attractions on the shared bicycle travel route; Obtain the historical travel data of target tourists, and determine the target tourists' visit threshold and expected weights for different categories of attractions based on the historical travel data; The steps of obtaining the historical travel data of the target tourists and determining the target tourists' visit threshold and the expected weights for different categories of attractions based on the historical travel data include: Obtain historical travel data of target tourists, and extract historical scenic spot travel data of target tourists from the historical travel data, and determine all target historical scenic spots that the target tourists have visited within a preset past period based on the historical scenic spot travel data; Obtain the objective attraction indexes of all target historical attractions, and set the average value of all objective attraction indexes as the visit threshold of target tourists; Identify the categories of each target historical attraction and determine the proportion of each category, and determine the target tourists' expected weight of each category of attractions based on the proportion of each category; Determine the objective attractiveness index of each cycling-adaptive scenic spot, and calculate the attractiveness score of each cycling-adaptive scenic spot to the target tourists based on the objective attractiveness index and expected weight corresponding to each cycling-adaptive scenic spot; Acquire real-time traffic information of cycling-adapted attractions, and modify the attraction score of the cycling-adapted attractions based on the real-time traffic information to obtain a modified attraction score, determine whether the modified attraction score of the cycling-adapted attractions is greater than a sightseeing threshold, and mark all cycling-adapted attractions greater than the sightseeing threshold as additional attractions; The steps of obtaining real-time passenger flow information of the cycling-adaptive scenic spot, and correcting the attractiveness score of the cycling-adaptive scenic spot based on the real-time passenger flow information to obtain a corrected attractiveness score, judging whether the corrected attractiveness score of the cycling-adaptive scenic spot is greater than a sightseeing threshold, and marking all cycling-adaptive scenic spots greater than the sightseeing threshold as additional scenic spots include: Obtaining real-time crowd flow information of the cycling-adapted scenic spot, and determining the degree of congestion of the cycling-adapted scenic spot based on the real-time crowd flow information; The attractiveness score of the cycling-adaptive scenic spot is corrected according to the congestion level of the cycling-adaptive scenic spot to obtain a corrected attractiveness score; Determine whether the modified attractiveness score of the cycling-adaptive scenic spot is greater than the sightseeing threshold, and mark all cycling-adaptive scenic spots greater than the sightseeing threshold as additional scenic spots; The steps of judging whether the modified attraction score of the cycling-adaptive attraction is greater than the tour threshold, and marking all the cycling-adaptive attractions greater than the tour threshold as additional attractions include: Determine whether the modified attractiveness score of the cycling-adapted scenic spots on the shared bicycle route is greater than the sightseeing threshold; If the modified attractiveness score of a cycling-adaptive scenic spot on the shared bicycle route is greater than the sightseeing threshold, the cycling-adaptive scenic spot is marked as an additional scenic spot; Get the best cycling route with all additional attractions to the shared bike route to obtain a tree diagram of the shared bike route.

2. The route recommendation method based on public transportation according to claim 1, characterized in that: The steps of obtaining the shared bicycle travel route of the target tourist from the location to the destination and screening out the cycling-suitable scenic spots on the shared bicycle travel route include: Obtain the shared bicycle travel route of the target tourist from the location to the destination, and identify all attractions within a preset distance around the shared bicycle travel route; Determine whether there is a suitable riding route between all scenic spots within a preset distance around the shared bicycle route and the shared bicycle route; If it is determined that there is a suitable cycling route between a certain scenic spot and the shared bicycle route, the scenic spot will be set as a cycling-suitable scenic spot.

3. The route recommendation method based on public transportation according to claim 1, characterized in that: The steps of determining the objective attractiveness index of each cycling-adaptive attraction and calculating the attractiveness score of each cycling-adaptive attraction to target tourists based on the objective attractiveness index and expected weight corresponding to each cycling-adaptive attraction include: Determine the objective attractiveness index of each ride-suitable attraction; Identify the category of each ride-suitable attraction to determine the target tourists' expected weight for each ride-suitable attraction; The product of the objective attraction index and the expected weight corresponding to each cycling-adaptive attraction is obtained to obtain the attractiveness score of each cycling-adaptive attraction to the target tourists.

4. The route recommendation method based on public transportation according to claim 3, characterized in that: When obtaining the objective attractiveness index of the target historical attractions and the objective attractiveness index of cycling-compatible attractions, relevant data should be obtained through network data analysis and big data mining technology, including indicators such as network popularity, traffic flow, and user ratings, and these indicators should be weighted calculated to obtain the objective attractiveness index of each attraction; when obtaining the objective attractiveness index of the target historical attractions, the historical attractiveness index corresponding to the time when the target historical attractions occurred should be extracted, and for cycling-compatible attractions, the real-time current attractiveness index should be obtained.

5. A route recommendation system based on public transportation, characterized in that: The system includes: a riding-adaptive scenic spot determination module, a travel data analysis module, an attraction score calculation module, and an additional scenic spot determination module, wherein: A cycling-suitable scenic spot determination module is used to obtain the shared bicycle travel route of the target tourists from their location to their destination, and to screen out the cycling-suitable scenic spots on the shared bicycle travel route; The travel data analysis module is used to obtain the historical travel data of the target tourists and determine the target tourists' visit threshold and the expected weights for different categories of attractions based on the historical travel data; An attraction score calculation module is used to determine the objective attraction index of each cycling-adaptive scenic spot, and calculate the attraction score of each cycling-adaptive scenic spot to the target tourists based on the objective attraction index and expected weight corresponding to each cycling-adaptive scenic spot; The additional scenic spot determination module is used to obtain the real-time flow information of the cycling-adapted scenic spots, and to correct the attractiveness score of the cycling-adapted scenic spots based on the real-time flow information to obtain a corrected attractiveness score, to determine whether the corrected attractiveness score of the cycling-adapted scenic spots is greater than a sightseeing threshold, and to mark all the cycling-adapted scenic spots greater than the sightseeing threshold as additional scenic spots; Obtaining real-time crowd flow information of the cycling-adapted scenic spot, and determining the degree of congestion of the cycling-adapted scenic spot based on the real-time crowd flow information; The attractiveness score of the cycling-adaptive scenic spot is corrected according to the congestion level of the cycling-adaptive scenic spot to obtain a corrected attractiveness score; Determine whether the modified attractiveness score of the cycling-adaptive scenic spot is greater than the sightseeing threshold, and mark all cycling-adaptive scenic spots greater than the sightseeing threshold as additional scenic spots; Determine whether the modified attractiveness score of the cycling-adapted scenic spots on the shared bicycle route is greater than the sightseeing threshold; If the modified attractiveness score of a cycling-adaptive scenic spot on the shared bicycle route is greater than the sightseeing threshold, the cycling-adaptive scenic spot is marked as an additional scenic spot; Get the best cycling route with all additional attractions to the shared bike route to obtain a tree diagram of the shared bike route.

6. The route recommendation system based on public transportation according to claim 5, characterized in that: The riding adaptation scenic spot determination module specifically includes: A scenic spot identification unit is used to obtain the shared bicycle driving route of the target tourist from the location to the destination, and identify all scenic spots within a preset distance around the shared bicycle driving route; A cycling route analysis unit is used to determine whether there is a suitable cycling route between all scenic spots within a preset distance around the shared bicycle route and the shared bicycle route; The cycling-adaptive scenic spot determining unit is used to set a certain scenic spot as a cycling-adaptive scenic spot if it is determined that there is a suitable cycling route between a certain scenic spot and the shared bicycle driving route.

7. The route recommendation system based on public transportation according to claim 6, characterized in that: The travel data parsing module specifically includes: A target historical scenic spot acquisition unit is used to acquire the historical travel data of the target tourist, and extract the historical scenic spot travel data of the target tourist from the historical travel data, and determine all the target historical scenic spots that the target tourist has visited within a preset past period according to the historical scenic spot travel data; A tour threshold calculation unit, used to obtain the objective attraction index of all target historical attractions, and set the average value of all objective attraction indexes as the tour threshold of target tourists; The expected weight determination unit is used to identify the category of each target historical attraction and determine the proportion of each category, and determine the expected weight of each category of attractions for the target tourists based on the proportion of each category.

Images