Tourism customization service method and system based on big data

Abstract

The invention discloses a travel customizing service method and system based on big data, and the system comprises a data collection module, a scheme making module and a customizing service module, the data collection module is used for collecting the comprehensive data of each scenic spot, the historical travel data of a user, and the strategy and evaluation data of each scenic spot; the user preference comprehensive data is input into the system, and the scheme making module is used for analyzing user preferences and scenic spot features, analyzing the influence of user evaluation in evaluation data on the scenic spot features, correcting the scenic spot features according to an analysis result, analyzing the influence of weather and season factors on scenic spot recommendation values, calculating recommendation values of all scenic spots and sending the recommendation values to the user management module. The travel time, budget and travel mode of the user are analyzed, a travel route and a travel scheme are planned for the user according to the analysis result, the customization service module is used for booking scenic spot tickets and hotels for the user according to the scheme selected by the user, and the system has the advantages of being high in accuracy and efficiency.

Description

Technical Field

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

[0002] With the continuous development of society, the pace of life has accelerated, which can easily make people feel tired. Traveling is undoubtedly the best way to relax. People will find many travel guides while surfing, which makes people full of longing for travel.

[0003] At present, most of the existing technologies recommend attractions to users by matching the characteristics of attractions according to the user's preferences. However, the characteristics of most attractions are somewhat different from the actual ones, and there are certain differences between the user's preferences and expectations. The existing technologies cannot match the corresponding attractions according to the user's expected characteristics for recommendation, resulting in a large deviation in the recommendation of travel plans. Moreover, the existing technologies only consider a single factor and cannot fully consider the impact of the user's budget, travel time and travel mode, resulting in low travel efficiency and poor user experience. Therefore, it is very necessary to design a travel customization service method and system based on big data with high accuracy and efficiency. Summary of the invention

[0004] The purpose of the present invention is to provide a travel customization service method and system based on big data to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a tourism customization service system based on big data, including a data collection module, a plan formulation module and a customization service module, the data collection module is used to collect comprehensive data of each scenic spot, user historical travel data and strategies and evaluation data of each scenic spot, and enter the user's preference comprehensive data into the system, the plan formulation module is used to analyze the user's preferences and the characteristics of the scenic spot, analyze the influence of the user's evaluation in the evaluation data on the characteristics of the scenic spot, modify the characteristics of the scenic spot according to the analysis results, analyze the influence of weather and seasonal factors on the recommended value of the scenic spot, calculate the recommended value of each scenic spot, select the target scenic spot according to the recommended value of the scenic spot, analyze the user's travel time, budget and travel mode, and plan the travel route and travel plan for the user according to the analysis results, the customization service module is used to book scenic spot tickets and hotels for the user according to the user's selected plan, and the user evaluates the travel experience, and the data collection module, the plan formulation module and the customization service module are connected to each other in communication;

[0006] The feature analysis module includes an expected analysis submodule and a scenic spot feature analysis submodule. The expected analysis submodule is used to analyze the user's preferences and the user's historical travel data and evaluations, and predict the user's expected features based on the analysis results. The scenic spot feature analysis submodule is used to analyze the description data of the scenic spot, analyze the user's evaluation of the scenic spot, and modify the scenic spot features based on the analysis results.

[0007] The scenic spot recommendation module includes a scenic spot matching submodule, a route planning submodule and a plan recommendation submodule. The scenic spot matching submodule is used to analyze the matching degree between the user's expected characteristics and the scenic spot characteristics, and analyze the influence of weather and seasonal factors on the scenic spot recommendation value. The plan recommendation submodule is used to analyze the user's budget, travel time and travel mode, and select scenic spots for the user based on the analysis results. The route planning submodule is used to plan travel routes and itineraries according to the user's scenic spots.

[0008] According to the above technical solution, the data collection module includes a data acquisition module and a user preference data entry module. The data acquisition module is used to collect comprehensive data of each scenic spot, user historical travel data, and strategies and evaluation data of each scenic spot. The user preference data entry module is used to enter the user's comprehensive preference data into the system.

[0009] According to the above technical solution, the solution formulation module includes a feature analysis module, which is used to analyze the user's preferences and the characteristics of the scenic spot, analyze the impact of the user's evaluation in the evaluation data on the characteristics of the scenic spot, and modify the characteristics of the scenic spot according to the analysis results.

[0010] According to the above technical solution, the plan formulation module also includes a scenic spot recommendation module, which is used to analyze the matching degree between the user's expected characteristics and the scenic spot characteristics, analyze the impact of the matching degree, weather factors, seasonal factors and user budget on the scenic spot recommendation value, formulate a travel plan based on the analysis results and plan the travel route and schedule.

[0011] According to the above technical solution, the customized service module includes an evaluation module and a reservation module. The evaluation module is used for users to provide feedback on their travel experience, and the reservation module is used to reserve scenic spot tickets and hotels for users according to the travel plan selected by the users.

[0012] According to the above technical solution, the tourism customized service method mainly includes the following steps:

[0013] Step S1: Collect comprehensive data of each scenic spot, user historical travel data, and guides and evaluation data of each scenic spot through the data collection module, and enter the user's preference comprehensive data into the system through the user preference data entry module;

[0014] Step S2: After data collection is completed, the system starts the feature analysis module, starts analyzing the expected features and scenic spot features of the target user, analyzes the evaluations of other users in the system, and modifies the scenic spot features according to the analysis results;

[0015] Step S3: When recommending scenic spots, the system starts the scenic spot recommendation module, starts to analyze the matching degree between the user's expected characteristics and the scenic spot characteristics, analyzes the influence of weather factors, seasons, user budget and travel time on the recommended value of scenic spots, formulates a travel plan according to the analysis results, and plans the user's travel route according to the formulated travel plan;

[0016] Step S4: After the user determines the travel plan, the reservation module is started to book attraction tickets and hotels for the user according to the formulated travel plan, and the user feeds back the travel experience to the system.

[0017] According to the above technical solution, step S2 further includes the following steps:

[0018] Step S21: obtaining user preference data keyed in by the target user, identifying the user's preference keywords, and retrieving corresponding preference features in the database according to the keywords;

[0019] Step S22: Obtain the historical travel data and corresponding feedback data of the target user, identify the scenic spot features in the historical travel data of the target user, identify the feedback features in the feedback data, retrieve the satisfaction of the corresponding target user to the historical tourist attractions in the database according to the feedback features, if the satisfaction is greater than the maximum threshold, fuse the scenic spot features with the user preference features, if the satisfaction is less than the maximum threshold and greater than the minimum threshold, retrieve the corresponding fusion weight in the database according to the satisfaction, and perform weighted fusion of the scenic spot features with the user preference features, otherwise the system continues to detect, and obtains the user's expected features after fusion;

[0020] Step S23: Obtain the description data of the scenic spot, identify the first feature of the scenic spot, identify the preference features of other users, and compare the preference features of the target user. When the similarity is greater than the threshold, obtain the feedback data of other users in the system, identify the feedback features of other users, and compare the evaluation features in the database. If the similarity between the feedback feature and the evaluation feature in the database is greater than the threshold, use the first feature as the scenic spot feature of the scenic spot. Otherwise, merge the first feature with the feedback feature as the scenic spot feature of the scenic spot.

[0021] According to the above technical solution, step S3 further includes the following steps:

[0022] Step S31: obtaining the expected characteristics of the target user, retrieving the corresponding scenic spot characteristics in the database according to the expected characteristics of the target user, obtaining the scenic spot characteristics for matching, and retrieving the corresponding influence coefficient α on the scenic spot recommendation value in the database according to the matching value;

[0023] Step S32: Acquire the weather data of the scenic spot, identify the weather influencing factor of the scenic spot, and compare it with the database. If the weather influencing factor does not exist in the database, the system continues to detect. Otherwise, the system retrieves the corresponding influence coefficient β on the recommended value of the scenic spot in the database according to the weather, obtains the current season data, identifies the current season, and retrieves the corresponding influence coefficient μ on the recommended value of the scenic spot in the database according to the current season;

[0024] Step S33: Obtain the description data of the target scenic spot, identify the environmental characteristics of the target scenic spot, retrieve the corresponding basic recommendation value P1 in the database according to the environmental characteristics, and calculate the first recommendation value P2 of the target scenic spot according to the formula P2 = α·β·μ·P1, where P2 represents the first recommended value of the scenic spot. If the first recommended value of the scenic spot is greater than the maximum threshold, it is marked as the first scenic spot, otherwise the system continues to detect.

[0025] According to the above technical solution, step S33 further includes the following steps:

[0026] Step S331: Identify the marks in the scenic spots, extract the scenic spots with the first scenic spot mark, randomly combine the scenic spots, identify the ticket unit price of each scenic spot in the scenic spot combination, calculate the total ticket price of the classic combination, compare the target user's budget, if the total ticket price is greater than the target user's budget, then delete the scenic spot combination, otherwise the system continues to detect, identify the distance between the scenic spots in the scenic spot combination and the user's travel duration, according to the scenic spot combination and the distance between the scenic spots, retrieve the corresponding optimal travel duration from the database, if the optimal travel duration of the scenic spot combination is greater than the target user's travel duration, then delete the scenic spot combination, otherwise the system continues to detect;

[0027] Step S332: Identify the first recommended value of each scenic spot in the scenic spot combination, sort the first recommended values ​​in descending order, retrieve the corresponding recommended value weight η in the database according to the sorting order, and calculate the comprehensive recommended value of each scenic spot combination by formula In the formula, i = 1, 2, 3...n, P3 represents the comprehensive recommendation value of each scenic spot combination, P i Indicates the first recommended value of each attraction in the attraction combination, and sorts the recommended values ​​in descending order;

[0028] Step S333: Identify the sorting order of the first characteristic value of the scenic spot in each scenic spot combination, mark the scenic spot according to the sorting order, obtain the position of the first scenic spot and the second scenic spot, establish a coordinate system, calculate the distance between each scenic spot by the distance formula, if the distance between the two scenic spots is less than the first threshold, it is marked as the first distance, if the distance between the two scenic spots is greater than the first threshold and less than the second threshold, it is marked as the second distance, otherwise it is marked as the third distance, identify the mark in the distance between each scenic spot and the first scenic spot, and call the weight in the database according to the first distance, second distance and third distance mark as data volume Calculate the distance between the center of the hotel area and the first scenic spot on the line connecting the first and second scenic spots through the formula In the formula, L1 represents the distance between the first scenic spot and the second scenic spot, and L2 represents the distance between the center point of the hotel area and the first scenic spot on the line connecting the first and second scenic spots. The center point of the hotel is taken as the center of the circle, and the corresponding basic radius in the database is retrieved. The hotels in the circular area are selected according to the hotel budget of the target user, and a travel plan is generated for the user based on the selected scenic spot combination and hotel.

[0029] According to the above technical solution, the selected travel plan is obtained in step S4, and attraction tickets and hotels are booked for the user based on the travel plan selected by the user. When the user travels, the user's travel mode is identified and a travel route is planned for the user.

[0030] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention, by analyzing the descriptive features of scenic spots and analyzing the feedback data of users with the same preference features as the target user on the scenic spots, can avoid the descriptive features of scenic spots being inconsistent with the actual ones, affecting the accuracy of scenic spot recommendations, thereby greatly improving the accuracy of the system; by analyzing the matching degree between scenic spot features and user expected features, and the influence of weather and seasonal factors on scenic spot recommendation values, it can more accurately recommend scenic spots to users, avoid the influence of weather and seasonal factors on scenic spot features, reduce the error between scenic spots matched for users and user expectations, and further improve the accuracy of the system; by analyzing the user's budget and travel time, the scenic spot combination is screened, and the deviation between the budget and travel time of the formulated travel plan and the user's needs can be avoided, thereby accurately and quickly screening out the scenic spot combination that meets the conditions, greatly improving the accuracy and efficiency of the system; by analyzing the weight of the first recommended value of each scenic spot, it can avoid the situation where the first recommended value is relatively average and the comprehensive recommended value of the scenic spot combination is large, resulting in a large deviation in the comprehensive recommended value of the scenic spot combination, that is, the scenic spot combination has a poor feature matching degree with the user, thereby further improving the accuracy of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0032] Figure 1 It is a schematic diagram of the system module composition of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] See also Figure 1 The present invention provides a technical solution: a tourism customization service system based on big data, including a data collection module, a plan formulation module and a customization service module. The data collection module is used to collect comprehensive data of various scenic spots, user historical travel data and strategies and evaluation data of various scenic spots, and enter the comprehensive data of user preferences into the system. The plan formulation module is used to analyze the user's preferences and the characteristics of the scenic spots, analyze the influence of the user's evaluation in the evaluation data on the characteristics of the scenic spots, and modify the characteristics of the scenic spots according to the analysis results. The influence of weather and seasonal factors on the recommended value of the scenic spots is analyzed, and the recommended value of each scenic spot is calculated. The target scenic spot is selected according to the recommended value of the scenic spot, and the user's travel time, budget and travel mode are analyzed. The travel route and travel plan are planned for the user according to the analysis results. The customization service module is used to book scenic spot tickets and hotels for the user according to the user's selected plan, and the user evaluates the travel experience. The data collection module, the plan formulation module and the customization service module are connected to each other in communication;

[0035] The feature analysis module includes an expected analysis submodule and a scenic spot feature analysis submodule. The expected analysis submodule is used to analyze the user's preferences and the user's historical travel data and evaluations, and predict the user's expected features based on the analysis results. The scenic spot feature analysis submodule is used to analyze the description data of the scenic spot, analyze the user's evaluation of the scenic spot, and modify the scenic spot features based on the analysis results.

[0036] The scenic spot recommendation module includes a scenic spot matching submodule, a route planning submodule and a plan recommendation submodule. The scenic spot matching submodule is used to analyze the matching degree between the user's expected characteristics and the scenic spot characteristics, and to analyze the impact of weather and seasonal factors on the scenic spot recommendation value. The plan recommendation submodule is used to analyze the user's budget, travel time and travel mode, and select scenic spots for the user based on the analysis results. The route planning submodule is used to plan travel routes and itineraries based on the user's scenic spots.

[0037] The data collection module includes a data acquisition module and a user preference data entry module. The data acquisition module is used to collect comprehensive data of each scenic spot, user historical travel data, and strategy and evaluation data of each scenic spot. The user preference data entry module is used to enter the user's preference comprehensive data into the system.

[0038] The program formulation module includes a feature analysis module, which is used to analyze the user's preferences and the characteristics of the scenic spot, analyze the impact of the user's evaluation in the evaluation data on the characteristics of the scenic spot, and modify the characteristics of the scenic spot according to the analysis results.

[0039] The plan formulation module also includes an attraction recommendation module, which is used to analyze the matching degree between the user's expected characteristics and the attraction characteristics, analyze the impact of the matching degree, weather factors, seasonal factors and user budget on the attraction recommendation value, formulate a travel plan based on the analysis results and plan the travel route and schedule.

[0040] The customized service module includes an evaluation module and a reservation module. The evaluation module is used for users to provide feedback on their travel experience, and the reservation module is used to book attraction tickets and hotels for users based on the travel plan selected by the users.

[0041] The tourism customization service method mainly includes the following steps:

[0042] Step S1: Collect comprehensive data of each scenic spot, user historical travel data, and guides and evaluation data of each scenic spot through the data collection module, and enter the user's preference comprehensive data into the system through the user preference data entry module;

[0043] Step S2: After data collection is completed, the system starts the feature analysis module, starts analyzing the expected features and scenic spot features of the target user, analyzes the evaluations of other users in the system, and modifies the scenic spot features according to the analysis results;

[0044] Step S3: When recommending scenic spots, the system starts the scenic spot recommendation module, starts to analyze the matching degree between the user's expected characteristics and the scenic spot characteristics, analyzes the influence of weather factors, seasons, user budget and travel time on the recommended value of scenic spots, formulates a travel plan according to the analysis results, and plans the user's travel route according to the formulated travel plan;

[0045] Step S4: After the user determines the travel plan, the reservation module is started to book attraction tickets and hotels for the user according to the formulated travel plan, and the user feeds back the travel experience to the system.

[0046] Step S2 further comprises the following steps:

[0047] Step S21: obtaining user preference data keyed in by the target user, identifying the user's preference keywords, and retrieving corresponding preference features in the database according to the keywords;

[0048] Step S22: Obtain the historical travel data and corresponding feedback data of the target user, identify the scenic spot features in the historical travel data of the target user, identify the feedback features in the feedback data, retrieve the satisfaction of the corresponding target user to the historical tourist attractions in the database according to the feedback features, if the satisfaction is greater than the maximum threshold, fuse the scenic spot features with the user preference features, if the satisfaction is less than the maximum threshold and greater than the minimum threshold, retrieve the corresponding fusion weight in the database according to the satisfaction, and perform weighted fusion of the scenic spot features with the user preference features, otherwise the system continues to detect, and obtains the user's expected features after fusion;

[0049] Step S23: Obtain the description data of the scenic spot, identify the first feature of the scenic spot, identify the preference features of other users, and compare the preference features of the target user. When the similarity is greater than the threshold, obtain the feedback data of other users in the system, identify the feedback features of other users, and compare the evaluation features in the database. If the similarity between the feedback feature and the evaluation feature in the database is greater than the threshold, use the first feature as the scenic spot feature of the scenic spot. Otherwise, merge the first feature with the feedback feature as the scenic spot feature of the scenic spot. By analyzing the description features of the scenic spot and analyzing the feedback data of the scenic spot from users with the same preference features as the target user, it is possible to avoid the description features of the scenic spot being inconsistent with the actual situation, affecting the accuracy of the scenic spot recommendation, thereby greatly improving the accuracy of the system.

[0050] Step S3 further comprises the following steps:

[0051] Step S31: obtaining the expected characteristics of the target user, retrieving the corresponding scenic spot characteristics in the database according to the expected characteristics of the target user, obtaining the scenic spot characteristics for matching, and retrieving the corresponding influence coefficient α on the scenic spot recommendation value in the database according to the matching value;

[0052] Step S32: Acquire the weather data of the scenic spot, identify the weather influencing factor of the scenic spot, and compare it with the database. If the weather influencing factor does not exist in the database, the system continues to detect. Otherwise, the system retrieves the corresponding influence coefficient β on the recommended value of the scenic spot in the database according to the weather, obtains the current season data, identifies the current season, and retrieves the corresponding influence coefficient μ on the recommended value of the scenic spot in the database according to the current season;

[0053] Step S33: Obtain the description data of the target scenic spot, identify the environmental characteristics of the target scenic spot, retrieve the corresponding basic recommendation value P1 in the database according to the environmental characteristics, and calculate the first recommendation value P2 of the target scenic spot according to the formula P2 = α·β·μ·P1, where P2 represents the first recommendation value of the scenic spot. If the first recommendation value of the scenic spot is greater than the maximum threshold, it is marked as the first scenic spot. Otherwise, the system continues to detect. By analyzing the matching degree between the characteristics of the scenic spot and the expected characteristics of the user, and the influence of weather and seasonal factors on the recommended value of the scenic spot, it can more accurately recommend scenic spots to users, avoid the influence of weather and seasonal factors on the characteristics of the scenic spot, reduce the error between the scenic spots matched for users and the user's expectations, and further improve the accuracy of the system.

[0054] Step S33 further includes the following steps:

[0055] Step S331: Identify the marks in the scenic spots, extract the scenic spots with the first scenic spot mark, randomly combine the scenic spots, identify the ticket unit price of each scenic spot in the scenic spot combination, calculate the total ticket price of the classic combination, compare the budget of the target user, if the total ticket price is greater than the budget of the target user, then delete the scenic spot combination, otherwise the system continues to detect, identify the distance between the scenic spots in the scenic spot combination and the user's travel duration, according to the scenic spot combination and the distance between the scenic spots, retrieve the corresponding optimal travel duration from the database, if the optimal travel duration of the scenic spot combination is greater than the travel duration of the target user, then delete the scenic spot combination, otherwise the system continues to detect, by analyzing the user's budget and travel duration, the scenic spot combination is screened, which can avoid the deviation between the budget and travel time of the formulated travel plan and the user's needs, and then accurately and quickly screen out the scenic spot combination that meets the conditions, greatly improving the accuracy and efficiency of the system;

[0056] Step S332: Identify the first recommended value of each scenic spot in the scenic spot combination, sort the first recommended values ​​in descending order, retrieve the corresponding recommended value weight η in the database according to the sorting order, and calculate the comprehensive recommended value of each scenic spot combination by formula In the formula, i = 1, 2, 3...n, P3 represents the comprehensive recommendation value of each scenic spot combination, P i Indicates the first recommended value of each attraction in the attraction combination, and sorts the recommended values ​​in descending order. By analyzing the weights of the first recommended values ​​of each attraction, it is possible to avoid the situation where the first recommended values ​​are relatively average and the comprehensive recommended value of the attraction combination is large, resulting in a large deviation in the comprehensive recommended value of the attraction combination, that is, the attraction combination has a poor feature matching with the user, further improving the accuracy of the system;

[0057] Step S333: Identify the sorting order of the first characteristic value of the scenic spot in each scenic spot combination, mark the scenic spot according to the sorting order, obtain the position of the first scenic spot and the second scenic spot, establish a coordinate system, calculate the distance between each scenic spot by the distance formula, if the distance between the two scenic spots is less than the first threshold, it is marked as the first distance, if the distance between the two scenic spots is greater than the first threshold and less than the second threshold, it is marked as the second distance, otherwise it is marked as the third distance, identify the mark in the distance between each scenic spot and the first scenic spot, and call the weight in the database according to the first distance, second distance and third distance mark as data volume Calculate the distance between the center of the hotel area and the first scenic spot on the line connecting the first and second scenic spots through the formula In the formula, L1 represents the distance between the first scenic spot and the second scenic spot, L2 represents the distance between the center point of the hotel area and the first scenic spot on the line connecting the first and second scenic spots. The center point of the hotel is taken as the center of the circle, and the corresponding basic radius in the database is retrieved. The hotels in the circular area are screened according to the hotel budget of the target user, and a travel plan is generated for the user according to the selected scenic spot combination and hotel. By analyzing the position between each scenic spot and the first and second scenic spots, and then calculating the hotel area position, a better hotel location can be provided for the user, which can reduce the travel time of the user to the scenic spot, reduce fatigue, and further improve the user's travel efficiency and experience.

[0058] In step S4, the selected travel plan is obtained, and according to the travel plan selected by the user, tickets for scenic spots and hotels are booked for the user. When the user travels, the user's travel mode is identified and a travel route is planned for the user.

[0059] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0060] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A tourism customization service system based on big data, including a data collection module, a program formulation module and a customization service module, characterized in that: The data collection module is used to collect comprehensive data of each scenic spot, user historical travel data, and strategies and evaluation data of each scenic spot, and enter the comprehensive data of user preferences into the system. The plan formulation module is used to analyze the user's preferences and the characteristics of the scenic spot, analyze the impact of the user's evaluation in the evaluation data on the characteristics of the scenic spot, modify the characteristics of the scenic spot according to the analysis results, analyze the impact of weather and seasonal factors on the recommended value of the scenic spot, calculate the recommended value of each scenic spot, select the target scenic spot according to the recommended value of the scenic spot, analyze the user's travel time, budget and travel mode, and plan travel routes and travel plans for the user according to the analysis results. The customized service module is used to book scenic spot tickets and hotels for the user according to the user's selected plan, and the user evaluates the travel experience. The data collection module, the plan formulation module and the customized service module are connected to each other in communication; The feature analysis module includes an expected analysis submodule and a scenic spot feature analysis submodule. The expected analysis submodule is used to analyze the user's preferences and the user's historical travel data and evaluations, and predict the user's expected features based on the analysis results. The scenic spot feature analysis submodule is used to analyze the description data of the scenic spot, analyze the user's evaluation of the scenic spot, and modify the scenic spot features based on the analysis results. The scenic spot recommendation module includes a scenic spot matching submodule, a route planning submodule and a plan recommendation submodule. The scenic spot matching submodule is used to analyze the matching degree between the user's expected characteristics and the scenic spot characteristics, and analyze the influence of weather and seasonal factors on the scenic spot recommendation value. The plan recommendation submodule is used to analyze the user's budget, travel time and travel mode, and select scenic spots for the user based on the analysis results. The route planning submodule is used to plan travel routes and itineraries according to the user's scenic spots.

2. A travel customization service system based on big data according to claim 1, characterized in that: The data collection module includes a data collection module and a user preference data entry module. The data collection module is used to collect comprehensive data of each scenic spot, user historical travel data, and strategy and evaluation data of each scenic spot. The user preference data entry module is used to enter the user's preference comprehensive data into the system.

3. A travel customization service system based on big data according to claim 2, characterized in that: The program formulation module includes a feature analysis module, which is used to analyze the user's preferences and the characteristics of the scenic spot, analyze the impact of the user's evaluation in the evaluation data on the characteristics of the scenic spot, and modify the characteristics of the scenic spot according to the analysis results.

4. A travel customization service system based on big data according to claim 3, characterized in that: The plan formulation module also includes a scenic spot recommendation module, which is used to analyze the matching degree between the user's expected characteristics and the scenic spot characteristics, analyze the impact of the matching degree, weather factors, seasonal factors and user budget on the scenic spot recommendation value, formulate a travel plan and plan the travel route and schedule based on the analysis results.

5. A travel customization service system based on big data according to claim 4, characterized in that: The customized service module includes an evaluation module and a reservation module. The evaluation module is used for users to give feedback on their travel experience, and the reservation module is used to reserve scenic spot tickets and hotels for users according to the travel plan selected by the users.

6. A tourism customization service method based on big data, characterized by: The tourism customization service method mainly includes the following steps: Step S1: Collect comprehensive data of each scenic spot, user historical travel data, and guides and evaluation data of each scenic spot through the data collection module, and enter the user's preference comprehensive data into the system through the user preference data entry module; Step S2: After data collection is completed, the system starts the feature analysis module, starts analyzing the expected features and scenic spot features of the target user, analyzes the evaluations of other users in the system, and modifies the scenic spot features according to the analysis results; Step S3: When recommending scenic spots, the system starts the scenic spot recommendation module, starts to analyze the matching degree between the user's expected characteristics and the scenic spot characteristics, analyzes the influence of weather factors, seasons, user budget and travel time on the recommended value of scenic spots, formulates a travel plan according to the analysis results, and plans the user's travel route according to the formulated travel plan; Step S4: After the user determines the travel plan, the reservation module is started to book attraction tickets and hotels for the user according to the formulated travel plan, and the user feeds back the travel experience to the system.

7. A travel customization service method based on big data according to claim 6, characterized in that: The step S2 further comprises the following steps: Step S21: obtaining user preference data keyed in by the target user, identifying the user's preference keywords, and retrieving corresponding preference features in the database according to the keywords; Step S22: Obtain the historical travel data and corresponding feedback data of the target user, identify the scenic spot features in the historical travel data of the target user, identify the feedback features in the feedback data, retrieve the satisfaction of the corresponding target user to the historical tourist attractions in the database according to the feedback features, if the satisfaction is greater than the maximum threshold, fuse the scenic spot features with the user preference features, if the satisfaction is less than the maximum threshold and greater than the minimum threshold, retrieve the corresponding fusion weight in the database according to the satisfaction, and perform weighted fusion of the scenic spot features with the user preference features, otherwise the system continues to detect, and obtains the user's expected features after fusion; Step S23: Obtain the description data of the scenic spot, identify the first feature of the scenic spot, identify the preference features of other users, and compare the preference features of the target user. When the similarity is greater than the threshold, obtain the feedback data of other users in the system, identify the feedback features of other users, and compare the evaluation features in the database. If the similarity between the feedback feature and the evaluation feature in the database is greater than the threshold, use the first feature as the scenic spot feature of the scenic spot. Otherwise, merge the first feature with the feedback feature as the scenic spot feature of the scenic spot.

8. A travel customization service method based on big data according to claim 7, characterized in that: The step S3 further comprises the following steps: Step S31: obtaining the expected characteristics of the target user, retrieving the corresponding scenic spot characteristics in the database according to the expected characteristics of the target user, obtaining the scenic spot characteristics for matching, and retrieving the corresponding influence coefficient α on the scenic spot recommendation value in the database according to the matching value; Step S32: Acquire the weather data of the scenic spot, identify the weather influencing factor of the scenic spot, and compare it with the database. If the weather influencing factor does not exist in the database, the system continues to detect. Otherwise, the system retrieves the corresponding influence coefficient β on the recommended value of the scenic spot in the database according to the weather, obtains the current season data, identifies the current season, and retrieves the corresponding influence coefficient μ on the recommended value of the scenic spot in the database according to the current season; Step S33: Obtain the description data of the target scenic spot, identify the environmental characteristics of the target scenic spot, retrieve the corresponding basic recommendation value P1 in the database according to the environmental characteristics, and calculate the first recommendation value P2 of the target scenic spot according to the formula P2 = α·β·μ·P1, where P2 represents the first recommended value of the scenic spot. If the first recommended value of the scenic spot is greater than the maximum threshold, it is marked as the first scenic spot, otherwise the system continues to detect.

9. A travel customization service method based on big data according to claim 8, characterized in that: The step S33 further comprises the following steps: Step S331: Identify the marks in the scenic spots, extract the scenic spots with the first scenic spot mark, randomly combine the scenic spots, identify the ticket unit price of each scenic spot in the scenic spot combination, calculate the total ticket price of the classic combination, compare the target user's budget, if the total ticket price is greater than the target user's budget, then delete the scenic spot combination, otherwise the system continues to detect, identify the distance between the scenic spots in the scenic spot combination and the user's travel duration, according to the scenic spot combination and the distance between the scenic spots, retrieve the corresponding optimal travel duration from the database, if the optimal travel duration of the scenic spot combination is greater than the target user's travel duration, then delete the scenic spot combination, otherwise the system continues to detect; Step S332: Identify the first recommended value of each scenic spot in the scenic spot combination, sort the first recommended values ​​in descending order, retrieve the corresponding recommended value weight η in the database according to the sorting order, and calculate the comprehensive recommended value of each scenic spot combination by formula In the formula, i = 1, 2, 3...n, P3 represents the comprehensive recommendation value of each scenic spot combination, P i Indicates the first recommended value of each attraction in the attraction combination, and sorts the recommended values ​​in descending order; Step S333: Identify the sorting order of the first characteristic value of the scenic spot in each scenic spot combination, mark the scenic spots according to the sorting order, obtain the positions of the first scenic spot and the second scenic spot, establish a coordinate system, calculate the distance between the scenic spots by using the distance formula, calculate the hotel position according to the weight, select the corresponding hotel according to the hotel budget of the target user, and generate a travel plan for the user based on the selected scenic spot combination and hotel.

10. A travel customization service method based on big data according to claim 9, characterized in that: In the step S4, the selected travel plan is obtained, and according to the travel plan selected by the user, tickets for scenic spots and hotels are booked for the user. When the user travels, the user's travel mode is identified and a travel route is planned for the user.

Images