A tourist route planning method and system based on artificial intelligence

Abstract

The present invention discloses a method and system for planning a tourist route based on artificial intelligence, which belongs to the field of route planning, wherein the method includes: establishing a user data set; reading input data, matching projects of a target scenic spot with user characteristics, planning routes for projects, and generating accommodation selection plans corresponding to the route planning, eliminating projects based on route planning results, project matching values ​​and input data, and reconstructing route planning results; feeding back the reconstructed route planning results to the user to complete the planning and management of tourist routes. The present application solves the technical problem that the existing tourist route planning cannot be well combined with user needs, resulting in poor matching between users and projects, poor route planning, inconvenient passage, and poor user travel experience, and achieves the technical effect of matching projects according to user needs, performing real-time dynamic route planning, providing high-quality route planning, improving the convenience of passage, and enhancing the user's travel experience.

Description

Technical Field

[0001] The present invention relates to the field of route planning, and in particular to a tourist route planning method and system based on artificial intelligence. Background Art

[0002] With the development of tourism, people have higher and higher requirements for tourism quality and personalized experience. At present, in scenic spot tourism, travel route planning usually adopts simple pattern matching or rule recommendation, ignoring the user's characteristic information and preference data, making the project poorly matched with the user's actual needs, resulting in low quality of the planned route, inconvenience in travel, and poor user experience. Summary of the invention

[0003] This application provides a travel route planning method and system based on artificial intelligence, aiming to solve the technical problems that the existing travel route planning cannot well combine user needs, resulting in poor matching between users and projects, poor route planning, inconvenient transportation, and poor user travel experience.

[0004] In view of the above problems, the present application provides a travel route planning method and system based on artificial intelligence.

[0005] The first aspect disclosed in the present application provides a travel route planning method based on artificial intelligence, the method comprising: establishing a user data set, wherein the user data set is a user set established through multiple channels, the multiple channels include historical travel data and questionnaire data, performing time series data verification with the user data set, and establishing user features based on the verification results, wherein the user features include main features and auxiliary features; reading the user's input data, the input data includes an input destination, a planned date period, and an impact factor, wherein the impact factor is a coefficient of variation of the experiential travel set by the user; matching projects of the target scenic spot with the user features, wherein the project matching includes project content matching and project access matching, and establishing a project matching value; planning routes for projects through the input data, and generating accommodation selection plans corresponding to the route planning, eliminating projects based on the route planning results, project matching values ​​and input data, and reconstructing the route planning results; feeding back the reconstructed route planning results to the user to complete the travel route planning management.

[0006] Another aspect disclosed in the present application provides a travel route planning system based on artificial intelligence, the system comprising: a data set establishment module, used to establish a user data set, wherein the user data set is a user set established through multiple channels, the multiple channels include historical travel data, questionnaire data, the user data set is used to perform time series data verification, and user characteristics are established according to the verification results, wherein the user characteristics include main characteristics and auxiliary characteristics; an input data reading module, used to read the user's input data, the input data includes an input destination, a planned date period, and an impact factor, wherein the impact factor is a coefficient of variation of the user-set experiential travel; a matching module, used to match projects of a target scenic spot with user characteristics, wherein project matching includes project content matching, project access matching, and establishing project matching values; a route planning reconstruction module, used to perform route planning for projects through input data, and generate accommodation selection plans corresponding to the route planning, eliminate projects based on the route planning results, project matching values ​​and input data, and reconstruct the route planning results; a result feedback module, used to feed back the reconstructed route planning results to the user to complete the travel route planning management.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] By integrating multi-channel data, including historical tourism data, questionnaire data, etc., a comprehensive user data set is constructed, and the user data set is time-series verified to identify data quality and improve the reliability of user portraits; on this basis, the main and auxiliary features of the user are extracted to form a structured user feature data set, laying the data foundation for personalized route planning; the user input data is read, and the basic information such as the destination, planned date cycle, etc. provided by the user is received. At the same time, the impact factor is introduced as the coefficient of variation, allowing the user to set the experience travel preference, realize interaction with the user, obtain the key parameters required for project matching, and improve the flexibility of route planning; the project matching of the target scenic spot is carried out according to the user characteristics, and the generated user characteristics are used for intelligent matching with the projects of the target scenic spot, and the project content relevance and traffic convenience are considered to generate the project matching value, so as to realize the accurate matching of users and tourism projects. Improve the personalization of route planning; plan the route of the project by inputting data, generate a preliminary route planning plan, and generate corresponding accommodation selection plans according to the route. On this basis, comprehensively consider the route planning results, project matching values ​​and input data to eliminate projects, and reconstruct and optimize the route. While meeting user preferences, it takes into account the rationality and real-time dynamics of the route to improve the overall quality of route planning; feed back the reconstructed route planning results to the user, and complete the technical solution of the intelligent tourism route planning process, which solves the technical problems that the existing tourism route planning cannot be well combined with user needs, resulting in poor matching between users and projects, poor route planning, inconvenient traffic, and poor user travel experience. It achieves the technical effect of matching projects according to user needs, conducting real-time dynamic route planning, providing high-quality route planning, improving traffic convenience, and enhancing user travel experience.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flow chart of a travel route planning method based on artificial intelligence is provided for an embodiment of the present application.

[0011] Figure 2 A structural schematic diagram of an artificial intelligence-based travel route planning system is provided for an embodiment of the present application.

[0012] Explanation of reference numerals: data set establishment module 11 , input data reading module 12 , matching module 13 , route planning reconstruction module 14 , result feedback module 15 . DETAILED DESCRIPTION

[0013] The overall idea of ​​the technical solution provided by this application is as follows:

[0014] The embodiments of the present application provide a travel route planning method and system based on artificial intelligence.

[0015] First, a user feature data set is established through multi-channel data, and time series verification is used to improve the accuracy of user portraits, laying the foundation for personalized route planning. Secondly, the impact factor is introduced to read input data such as user destinations and planned date cycles to obtain key parameters required for planning. Thirdly, the project matching of the target scenic spot is carried out based on user characteristics, and the project content and convenience of access are considered to improve the personalization of route planning. Then, route planning and accommodation selection are carried out based on user input data and project matching results, and route reconstruction and optimization are carried out in combination with project elimination, taking into account the rationality and dynamics of the route. Subsequently, the reconstructed route planning results are fed back to the user to complete the entire intelligent tourism route planning process.

[0016] By matching projects according to user needs, performing real-time dynamic route planning, providing high-quality route planning, and improving travel convenience, the technical effect of enhancing the user's travel experience is achieved.

[0017] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0018] Embodiment 1

[0019] like Figure 1 As shown, the embodiment of the present application provides a travel route planning method based on artificial intelligence, the method comprising:

[0020] S1: Establish a user data set, wherein the user data set is a user set established through multiple channels, and the multiple channels include historical travel data and questionnaire data. The user data set is used to perform time series data verification, and user features are established based on the verification results, wherein the user features include primary features and auxiliary features.

[0021] Specifically, multiple channels are used to collect user data and establish user data sets. The multiple channels include but are not limited to historical travel data and questionnaire data. Historical travel data refers to the user's past travel records, consumption records, location trajectories, etc., which reflect the user's behavioral characteristics in real travel scenarios; questionnaire data collects user preferences for various travel elements in the form of questionnaires, such as preferences for destination types, travel methods, accommodation standards, travel activities, etc.

[0022] After establishing the user data set, we conduct time series data verification on it. By analyzing the data of the same user at different time points, we can check the consistency and continuity of the data, identify and remove abnormal data points, and improve the quality and reliability of the user data set. According to the verified user data set, we establish user features. Among them, user features are divided into two categories: main features and auxiliary features. The main feature refers to the feature that has a dominant role in the user's current preferences, which comes from the data closest to the current time; the auxiliary feature refers to the feature that has a certain influence on the user's preferences but is not dominant, which comes from the data at an earlier time and may have been updated by the main feature. For example, if the user's recent travel preferences are different from those in the past, then the feature reflecting the recent preferences is the main feature, and the past preference feature becomes the auxiliary feature. Through this feature classification, the user's current actual needs can be grasped more accurately. By establishing user features, a solid foundation for user understanding is laid for subsequent personalized travel route planning.

[0023] S2: Reading the user's input data, wherein the input data includes the input destination, the planned date period, and the impact factor, wherein the impact factor is the coefficient of variation of the experiential travel set by the user.

[0024] Specifically, the user's input data is read as the key parameter for generating the travel route planning. Among them, the input data specifically includes the input destination, the planned date cycle and the impact factor. Among them, the input destination refers to the place or area where the user plans to travel. The user can input the destination information in a variety of ways such as text, voice, image, etc., such as the city name, scenic spot name, address, etc. The planned date cycle refers to the start and end dates of the user's expected travel activities. The user can enter a specific date range. According to the planned date cycle entered by the user, the travel itinerary can be reasonably arranged considering factors such as seasons and holidays. The impact factor is a coefficient of variation set by the user subjectively, reflecting the user's willingness to try low-matching projects, and the value range is a real number between 0 and 1. When the impact factor is equal to 0, it means that the user is completely unwilling to try projects with a low degree of match with his or her preferences, and only wants to experience conventional projects that fully meet his or her preferences; when the impact factor is equal to 1, it means that the user is very willing to try projects with a low degree of match with his or her preferences; when the impact factor is between 0 and 1, it means that the user is willing to try low-matching projects to a certain extent. The larger the impact factor value is, the more willing the user is to try low-matching items, and the more likely the generated route will contain low-matching items. Conversely, the smaller the impact factor value is, the less willing the user is to try low-matching items, and the more likely the generated route will be personalized.

[0025] By reading the user's input data on destinations, date periods and impact factors, it provides key support for achieving highly personalized travel planning that meets user needs.

[0026] S3: Matching items in the target scenic spot with the user characteristics, wherein the item matching includes item content matching and item access matching, and establishing an item matching value.

[0027] Specifically, based on the user characteristics, the project matching of the target scenic spot is carried out to select the project combination that best matches the user characteristics from the massive potential scenic spot projects. Project matching specifically includes two aspects: project content matching and project access matching.

[0028] Project content matching refers to comparing user characteristics with the attributes of scenic spot projects to evaluate the similarity and matching between the two. The attributes of scenic spot projects include but are not limited to theme types (such as natural scenery, historical culture, modern cities, etc.), activity types (such as sightseeing, entertainment, sports, leisure, etc.), popularity, popularity, etc. For example, by using machine learning algorithms, through multi-dimensional feature engineering and similarity calculation of user characteristics and project attributes, the content matching score between each project and the user is obtained.

[0029] Project access matching evaluates the difficulty of users reaching and experiencing each scenic spot project from the perspective of traffic convenience, taking into account factors such as the geographical location, traffic conditions, opening hours, and booking difficulty of the scenic spot project. For example, for remote scenic spots, traffic convenience may be poor; and for popular scenic spots, it may be difficult to book tickets or experience congestion during peak hours. For example, combining real-time traffic data, scenic spot reservation data, etc., calculate the access convenience score of each project.

[0030] After completing the project content matching and project access matching, the content matching score and access convenience score of each project are combined to generate a comprehensive project matching value, which indicates the degree of fit between each scenic spot project and user needs. The higher the matching value, the more suitable the project is for recommendation to users.

[0031] Among them, the project matching process is not completed in one go, but a dynamic update process. On the one hand, with the continuous accumulation of user data and the potential changes in user preferences, user characteristics may change; on the other hand, the attributes and status of the scenic spot project itself may also change over time. Therefore, project matching should be updated in real time based on user characteristics and the current attributes of the project to ensure the timeliness and accuracy of the matching results.

[0032] Through project content matching and project access matching, the project matching value between the user and each scenic spot project is obtained to provide support for subsequent travel route planning. Compared with the pattern matching or rule recommendation in the existing technology, the matching degree between the scenic spot project and the user characteristics is quantified, making the subsequent route planning more targeted.

[0033] S4: route planning is performed for the project through the input data, and an accommodation selection plan corresponding to the route planning is generated, project elimination is performed based on the route planning result, project matching value and input data, and the route planning result is reconstructed.

[0034] Specifically, on the basis of completing the project matching, combined with the user's input data, the travel route planning and optimization of the candidate projects are carried out.

[0035] First, the user's input destination, planned date cycle, impact factor, and project matching results are integrated to preliminarily determine a set of candidate route planning schemes. As the route planning results, each scheme contains several scenic spots, as well as the sequence and time allocation between the projects. While generating the preliminary route plan, the accommodation selection scheme that matches each route planning scheme is intelligently generated. For example, through big data analysis, the distance between the accommodation location and the selected scenic spot, transportation convenience, accommodation quality and price are comprehensively considered to recommend the best accommodation combination for each route planning scheme.

[0036] Then, based on the route planning results, project matching values ​​and input data, project elimination is performed to further optimize and screen the route planning scheme. Among them, the project matching value reflects the degree of fit between each scenic spot project and the user's preference. Projects with lower matching values ​​may be eliminated or adjusted in priority; the user's input data represents the user's preference for the travel experience, and the project combination in the route is dynamically adjusted to meet the user's expectations. Through project elimination, projects with low project matching and those that do not meet the user's input data are determined, and these projects are deleted and eliminated from the route planning results, and then the project sequence and time schedule are adjusted to generate an optimized travel route planning scheme, and the reconstructed route planning results are obtained.

[0037] Among them, route planning and reconstruction are dynamically generated processes. First, we make full use of machine learning algorithms and knowledge graph technology to continuously learn and optimize route planning strategies based on massive tourism data and user feedback. At the same time, we also monitor the dynamic changes of tourist destinations (such as weather changes, traffic conditions, etc.) in real time, and dynamically adjust route planning when necessary to ensure the user's travel experience.

[0038] S5: Feedback the reconstructed route planning results to the user to complete the travel route planning management.

[0039] Specifically, after obtaining the reconstructed route planning results, the reconstructed route planning results are presented to the user clearly and intuitively through the human-computer interaction interface. For example, a travel planning report is generated based on the reconstructed route planning results, including daily itinerary arrangements, recommended accommodation arrangements, itinerary maps, project details, and overall cost estimates. Among them, the daily itinerary includes the order of scenic spot projects, expected tour duration, transportation methods, etc.; recommended accommodation arrangements include accommodation locations, hotel names, room types, prices, etc.; itinerary maps intuitively display the geographical distribution of tourist routes and scenic spot projects; project details include the characteristics, highlights, precautions, etc. of each scenic spot project; the overall cost estimate is to estimate the total travel cost based on scenic spot tickets, transportation, accommodation, catering and other factors.

[0040] Users can conveniently access and view travel planning reports through various terminals such as the Web and mobile terminals. At the same time, interactive functions are provided to allow users to further fine-tune and customize travel planning reports, such as adjusting the order of scenic spot items, changing accommodation options, etc., thereby realizing intelligent travel route planning management.

[0041] Furthermore, the embodiment of the present application also includes:

[0042] The project matching value is used to screen projects and establish a project set, wherein the project set is a project collection constructed from projects with a matching value lower than a preset value.

[0043] A selected random number is set according to the impact factor, and items in the item set are randomly selected based on the selected random number.

[0044] Add the randomly selected results of the project as required items to complete the route planning of the project.

[0045] In a feasible implementation, when planning the route of a project, a matching value threshold is set as a preset matching value, and all projects with matching values ​​lower than the preset matching value are screened out to construct a project set, thereby providing a project pool for selecting projects based on the impact factor. The preset matching value is set based on historical data. Subsequently, the impact factor input by the user is converted into a selected random number, and the value of the selected random number is proportional to the size of the impact factor. Then, using the selected random number, a project is randomly selected from the project set, the selected project is determined, and the result of the random selection of the project is obtained. The larger the impact factor, the larger the selected random number, and the more low-matching projects are selected in the project set; conversely, the smaller the impact factor, the smaller the selected random number, and the fewer low-matching projects are selected in the project set.

[0046] Afterwards, the randomly selected items in the random selection results are added to the route planning scheme as mandatory items, representing the trial elements introduced based on the user's impact factor on the basis of personalized recommendations. By adding mandatory items, the original personalized route is reconstructed to form a new route that takes into account user preferences and trial preferences, balancing the personalization and novelty of user travel, thereby completing the route planning of the project.

[0047] Furthermore, the embodiment of the present application also includes:

[0048] The input data is parsed to determine whether there are key items in the parsing result.

[0049] If there are key items, the key items and the random selection results of the items are used as the planning core to perform additional item search.

[0050] Complete route planning for items with additional item search results.

[0051] In a preferred embodiment, first, the user's input data is deeply analyzed to determine whether there are key items that have a decisive impact on route planning. The so-called key items refer to those core items that must be given priority in route planning, such as famous attractions, special experiences, etc., no matter from the perspective of project matching or the quality of tourism experience. For example, the keywords and semantic information in the user's input data are analyzed to identify the required items clearly expressed by the user as key items; combined with user characteristics and tourism big data, it is determined which items are of general importance to the user group as key items. If there are key items, these key items and the project combination of the random selection results of the project are used as the planning core of route planning, wherein the planning core is the project that must be planned when planning a tourist route. After determining the planning core, search for nearby projects based on the planning core to generate more abundant tourism projects. For example, in the vicinity of the planning core, search for projects that are higher than the preset matching value, and include them as additional projects in the search results of the additional projects. Subsequently, the search results of the additional projects are integrated into the existing planning core, and then the route planning is completed based on the search results of the additional projects and all the projects in the planning core.

[0052] Through a series of operations such as input data analysis, planning core determination, and additional project search, the route planning is further optimized and improved based on the random selection of projects, making it more in line with user needs, more in line with actual travel conditions, and improving the user's travel experience.

[0053] Furthermore, the embodiment of the present application also includes:

[0054] Establish a unit distance penalty factor for repeated routes.

[0055] When performing route planning, the planned repeated route penalty is calculated using the unit distance penalty factor to generate a total repeated penalty value.

[0056] The road length constraint is calculated based on the total road length to generate a road length penalty constraint.

[0057] Route planning is screened based on the total value of the repetition penalty and the road length penalty constraint, and route planning is completed according to the screening result.

[0058] In a feasible implementation, a unit distance penalty factor for repeated routes is introduced to quantify the user's aversion to repeated routes, that is, the user's dissatisfaction with repeated walking on the same route. The larger the value of the unit distance penalty factor, the less the user wants repeated sections to appear in the travel route. For example, the default value of the unit distance penalty factor is determined based on user portraits, historical behavior data, etc. At the same time, the user is allowed to adjust the unit distance penalty factor within a certain range to better reflect his personal preferences. By introducing the unit distance penalty factor, a quantitative basis is provided for reasonably controlling the route repetition rate in route planning.

[0059] In the process of route planning, the length of repeated sections in the route planning scheme is determined, and the total value of repeated penalties for repeated sections is obtained based on the unit distance penalty factor. Among them, the total value of repeated penalties is proportional to the length of the repeated sections and the size of the unit distance penalty factor. In addition to repeated routes, the total length of the route is also an important factor affecting the user's travel experience. Too long routes will cause user fatigue and reduce the quality of travel. Therefore, when planning a route, it is also necessary to constrain the total length of the route. First, based on factors such as the user's time budget and travel mode, determine the upper limit of the total length of the route, evaluate the total length of the route in each route planning scheme, and determine the road length penalty constraint value based on the degree to which it exceeds the upper limit of the total length of the route. Among them, the larger the upper limit of the total length of the route, the more unreasonable the total length of the route.

[0060] Then, the weight coefficients of the total value of repeated penalties and the road length penalty constraints are set, and the total value of repeated penalties and the road length penalty constraints are comprehensively considered to obtain the comprehensive score of each route planning scheme based on weighted calculation. Then, the schemes with low comprehensive scores are gradually eliminated to find the route planning scheme that is more reasonable in terms of repeated routes and total length, determine it as the final route planning result, and recommend it to the user to complete the route planning.

[0061] By introducing duplicate route penalties and route length constraint mechanisms, we fully take into account users' aversion to duplicate routes and overly long routes. Through quantitative penalty and constraint calculations, we can more intelligently balance the adventure, personalization and comfort of the route, and plan higher quality travel routes for users.

[0062] Furthermore, the embodiment of the present application also includes:

[0063] A first database is established, wherein the first database is a data set established based on travel order information and tourism planning information.

[0064] A second database is established, wherein the second database is a road traffic data set constructed based on the associated date data.

[0065] Road congestion prediction is performed using the first database and the second database.

[0066] Generate auxiliary elimination constraints based on road congestion prediction results to complete project elimination.

[0067] In a feasible implementation, first, a special database is established as the first database to store and manage a large amount of travel order information and tourism planning information. For each user, the first database will record their travel order records, consumption preferences, travel patterns and other information, and also record the various route planning results planned for different users. Through the accumulation and correlation analysis of massive user data, we can gain insight into the temporal and spatial distribution of tourism activities from a macro perspective, identify the passenger flow change trends of scenic spots and routes at different times, and lay the foundation for subsequent road congestion prediction.

[0068] At the same time, a second database is established to store and manage the road traffic data of the user's travel date, which comes from multiple channels such as traffic management departments, map service providers, and real-time traffic monitoring systems, covering indicators such as traffic flow, travel time, and congestion index at different times and sections of roads. Through road traffic data, we can gain insight into the temporal and spatial distribution of traffic conditions and predict the traffic pressure of key sections in the future, thus providing a realistic basis for project elimination and route reconstruction.

[0069] Subsequently, the overall passenger flow of each scenic spot and route in the future is predicted using the full user data in the first database. By analyzing the periodic laws and holiday effects in the historical data, the popularity level of each scenic spot and each route at different times in the future is estimated, and then the potential traffic pressure of the relevant roads is calculated. At the same time, the road traffic data in the second database is used to evaluate the inherent traffic capacity and congestion probability of each section at different times. By analyzing indicators such as traffic volume and travel time in the historical data, the static properties of each road, that is, the upper limit of its ability to cope with traffic pressure, are portrayed. Afterwards, the tourist passenger flow forecast and the road traffic capacity assessment results are superimposed and analyzed to obtain a more accurate and dynamic road congestion prediction result. The road congestion prediction result is presented in the form of congestion probability or congestion index of each section in each time period, which not only reflects the dynamic changes in tourism transportation demand, but also takes into account the traffic properties of the road itself.

[0070] After obtaining the road congestion prediction results, auxiliary elimination constraints are generated based on them to guide the project elimination process. Specifically, if the road congestion prediction results show that the probability of congestion in certain sections or scenic spots within a certain period of time is very high, the elimination priority of the relevant projects in this period and section will be increased accordingly, or even directly listed as prohibited options; on the contrary, if the prediction shows that the traffic pressure on certain sections or scenic spots is relatively small, the elimination priority of the relevant projects will be appropriately lowered to give them more retention opportunities. By introducing auxiliary elimination constraints, the project screening strategy can be adjusted more flexibly and dynamically, while ensuring the quality of the tourism experience, avoiding the risk of traffic congestion to the greatest extent and improving the comfort of the trip.

[0071] Furthermore, the embodiment of the present application also includes:

[0072] Get the user's selected plan and generate real-time response instructions.

[0073] The real-time response instruction is used to monitor related information, wherein the related information includes road congestion information and weather change information.

[0074] Dynamic adjustment of the selected plan is performed based on the associated information, and dynamic feedback is generated, and the dynamic feedback is sent to the corresponding user.

[0075] In a feasible implementation, after the reconstructed route planning result is fed back to the user, the user selects the corresponding route planning scheme as the selected plan. Then, according to the selected plan, a series of real-time response instructions are generated as the basis for real-time monitoring and dynamic adjustment, so as to continuously track the user's itinerary execution during the travel process and be ready to make necessary adjustments at any time. Among them, the content of the real-time response instruction includes the user's travel time, route direction, stopover attractions, transportation selection, etc., as well as roads, scenic spots, time nodes, etc. that need to be monitored. After the real-time response instruction is generated, the real-time monitoring process is started to continuously track and analyze various types of information related to the user's travel itinerary, including road traffic information and weather change information. For road traffic information, the congestion status, traffic volume, speed and other data of the key sections involved in the user's itinerary are obtained in real time, so as to timely discover traffic problems that may affect the user's travel; for weather change information, the weather forecast, meteorological warning and other data of the user's area and destination are obtained in real time, so as to timely discover weather problems that may affect the user's travel experience.

[0076] After obtaining relevant information in real time, the potential impact of this information on the user's travel itinerary is analyzed, and the original route planning plan is dynamically adjusted accordingly, so as to avoid or reduce the impact of adverse factors such as traffic congestion and bad weather while ensuring the user's travel experience. For example, if a road section is found to be severely congested during a certain period of time, it is recommended that the user detour to other sections or adjust the departure time; if it is found that the user's destination will experience continuous rainfall, it is recommended that the user adjust the order of the tour and visit indoor attractions on rainy days. After the dynamic adjustment is completed, an adjusted route planning plan is generated and sent to the user as dynamic feedback. Feedback will be presented in the form of push notifications, route map updates, etc., so that users can understand the changes in the travel itinerary in a timely manner and make corresponding adjustments.

[0077] By introducing mechanisms such as real-time response instructions, related information monitoring, and dynamic adjustment feedback, dynamic optimization of route planning can be achieved, so that the original planning scheme can be flexibly adjusted according to changes in actual conditions during the travel process, thereby maximizing the quality of the user's travel experience.

[0078] Furthermore, the embodiment of the present application also includes:

[0079] Get the user's sharing permission settings.

[0080] The user's encryption mode is configured with the shared permission information, the user is managed with the encryption mode, and the user's data is encrypted and uploaded to the cloud.

[0081] In a feasible implementation, a user privacy protection mechanism is introduced to encrypt, share and manage user data in the cloud, thereby improving data processing and storage efficiency while also maximizing user information security and privacy rights.

[0082] First, through the human-computer interaction interface, users can set the sharing permissions of their data and obtain the user's set sharing permission information. The sharing permission information will specify the conditions, methods, and subjects under which user data is shared. For example, users can choose whether to allow their data to be used for big data analysis, whether to allow their data to be shared with cooperating third-party service providers, and whether to allow their data to be used for academic research. Users can also set different sharing permissions for different types of data, such as setting higher sharing permissions for travel preference data and lower sharing permissions for personal identity information.

[0083] After obtaining the user's sharing permission information, a personalized data encryption mode is configured for each user according to the user's set sharing permission information. The encryption mode will determine the encryption algorithm, key strength, access control and other parameters of the user data. For example, for sensitive data with low sharing permissions, a higher-strength encryption algorithm and stricter access control are used; while for general data with high sharing permissions, a relatively simple encryption method is used to balance security and processing efficiency. After completing the encryption mode configuration, the user data is encrypted according to the configuration. The encryption process will be performed on the user's local device to ensure that the original data does not leave the user's control. The encrypted data will be uploaded to the cloud for storage and management.

[0084] Through a complete user data encryption sharing and cloud management mechanism, while improving data processing and storage efficiency, the user's privacy and control rights are fully protected. Users can flexibly set data sharing permissions according to their own privacy protection needs, and take corresponding encryption and management measures to ensure the security and confidentiality of user data.

[0085] In summary, the artificial intelligence-based travel route planning method provided in the embodiments of the present application has the following technical effects:

[0086] Establish a user data set, where the user data set is a user collection established through multiple channels, including historical travel data and questionnaire data. Use the user data set to verify the time series data, and establish user features based on the verification results. User features include main features and auxiliary features, laying the data foundation for personalized route planning and providing support for subsequent accurate matching of user needs. Read the user's input data, which includes the input destination, planned date cycle, and impact factor. The impact factor is the coefficient of variation of the user-set experiential travel, to achieve interaction with the user, obtain the key parameters required for route planning, and lay the foundation for generating personalized routes. Use user features to match the projects of the target scenic spot, where project matching includes project content matching and project access matching, establish project matching values, and achieve accurate matching of user interest preferences with tourism projects, so as to improve the quality of route planning. Use input data to plan the route for the project, generate accommodation selection plans corresponding to the route planning, eliminate projects based on the route planning results, project matching values, and input data, and reconstruct the route planning results. While meeting the personalized needs of users, the overall rationality and dynamic optimization of the route are taken into account to improve the quality of route planning. The reconstructed route planning results are fed back to users to complete travel route planning management, improve the matching degree between projects and users, and improve the convenience of travel, thereby enhancing users' travel experience.

[0087] Embodiment 2

[0088] Based on the same inventive concept as the artificial intelligence-based travel route planning method in the aforementioned embodiment, Figure 2 As shown, the embodiment of the present application provides a travel route planning system based on artificial intelligence, the system comprising:

[0089] The data set establishment module 11 is used to establish a user data set, wherein the user data set is a user set established through multiple channels, and the multiple channels include historical travel data and questionnaire data. The user data set is used to perform time series data verification, and user features are established based on the verification results, wherein the user features include main features and auxiliary features.

[0090] The input data reading module 12 is used to read the user's input data, wherein the input data includes an input destination, a planned date cycle, and an impact factor, wherein the impact factor is a coefficient of variation of the experiential travel set by the user.

[0091] The matching module 13 is used to match the items of the target scenic spot with the user characteristics, wherein the item matching includes item content matching and item access matching, and establish an item matching value.

[0092] The route planning reconstruction module 14 is used to perform route planning for the project through the input data, generate accommodation selection plans corresponding to the route planning, eliminate projects based on the route planning results, project matching values ​​and input data, and reconstruct the route planning results.

[0093] The result feedback module 15 is used to feed back the reconstructed route planning result to the user to complete the travel route planning management.

[0094] Furthermore, the route planning reconstruction module 14 includes the following execution steps:

[0095] The project matching value is used to screen projects and establish a project set, wherein the project set is a project collection constructed from projects with a matching value lower than a preset value.

[0096] A selected random number is set according to the impact factor, and items in the item set are randomly selected based on the selected random number.

[0097] Add the randomly selected results of the project as required items to complete the route planning of the project.

[0098] Furthermore, the route planning reconstruction module 14 further includes the following execution steps:

[0099] The input data is parsed to determine whether there are key items in the parsing result.

[0100] If there are key items, the key items and the random selection results of the items are used as the planning core to perform additional item search.

[0101] Complete route planning for items with additional item search results.

[0102] Furthermore, the route planning reconstruction module 14 further includes the following execution steps:

[0103] Establish a unit distance penalty factor for repeated routes.

[0104] When performing route planning, the planned repeated route penalty is calculated using the unit distance penalty factor to generate a total repeated penalty value.

[0105] The road length constraint is calculated based on the total road length to generate a road length penalty constraint.

[0106] Route planning is screened based on the total value of the repetition penalty and the road length penalty constraint, and route planning is completed according to the screening result.

[0107] Furthermore, the route planning reconstruction module 14 further includes the following execution steps:

[0108] A first database is established, wherein the first database is a data set established based on travel order information and tourism planning information.

[0109] A second database is established, wherein the second database is a road traffic data set constructed based on the associated date data.

[0110] Road congestion prediction is performed using the first database and the second database.

[0111] Generate auxiliary elimination constraints based on road congestion prediction results to complete project elimination.

[0112] Furthermore, the embodiment of the present application also includes a planning dynamic adjustment module, which includes the following execution steps:

[0113] Get the user's selected plan and generate real-time response instructions.

[0114] The real-time response instruction is used to monitor related information, wherein the related information includes road congestion information and weather change information.

[0115] Dynamic adjustment of the selected plan is performed based on the associated information, and dynamic feedback is generated, and the dynamic feedback is sent to the corresponding user.

[0116] Furthermore, the embodiment of the present application also includes a user data encryption module, which includes the following execution steps:

[0117] Get the user's sharing permission settings.

[0118] The user's encryption mode is configured with the shared permission information, the user is managed with the encryption mode, and the user's data is encrypted and uploaded to the cloud.

[0119] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0120] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to multiple elements that can be selected individually or in full. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A tourist route planning method based on artificial intelligence, characterized in that: The method comprises: Establishing a user data set, wherein the user data set is a user set established through multiple channels, including historical travel data and questionnaire data, performing time series data verification with the user data set, and establishing user features according to the verification results, wherein the user features include main features and auxiliary features, wherein the main features refer to features that have a dominant effect on the user's current preferences and come from the data closest to the current time; the auxiliary features refer to features that have a certain influence on the user's preferences but are not dominant and come from data at an earlier time; Reading the user's input data, the input data includes the input destination, the planned date period, and the impact factor, wherein the impact factor is the coefficient of variation of the experience travel set by the user. The impact factor is a coefficient of variation set by the user subjectively, reflecting the user's willingness to try low-matching projects, and the value range is a real number between 0 and 1; Matching items of the target scenic spot with the user characteristics, wherein the item matching includes item content matching and item access matching, and establishing an item matching value; Performing route planning for the project through the input data, generating accommodation selection plans corresponding to the route planning, eliminating projects based on the route planning results, project matching values ​​and the input data, and reconstructing the route planning results; Feedback the reconstructed route planning results to the user to complete the travel route planning management; Wherein, the step of planning a route for a project by using the input data includes: Establish a unit distance penalty factor for repeated routes; When performing route planning, the planned repeated route penalty is calculated using the unit distance penalty factor to generate a total repeated penalty value; The road length constraint is calculated through the total road length to generate the road length penalty constraint; Route planning is screened based on the total value of the repetition penalty and the road length penalty constraint, and route planning is completed according to the screening result.

2. The method according to claim 1, characterized in that The step of planning a route for the project using the input data and generating an accommodation selection plan corresponding to the route planning includes: Screening projects with the project matching value to establish a project set, wherein the project set is a collection of projects constructed from projects with a matching value lower than a preset value; A selected random number is set according to the impact factor, and a project in the project set is randomly selected based on the selected random number; Add the randomly selected results of the project as required items to complete the route planning of the project.

3. The method according to claim 2, characterized in that The randomly selected result of the project is added as a required item to complete the route planning of the project, and further includes: Parsing the input data to determine whether there are key items in the parsing results; If there are key items, the key items and the random selection results of the items are used as the planning core to perform additional item search; Complete route planning for items with additional item search results.

4. The method according to claim 1, characterized in that The step of eliminating items based on the route planning result, the item matching value and the input data, and reconstructing the route planning result, further includes: Establishing a first database, wherein the first database is a data set established based on travel order information and tourism planning information; Establishing a second database, wherein the second database is a road traffic data set constructed based on the associated date data; Performing road congestion prediction by using the first database and the second database; Generate auxiliary elimination constraints based on road congestion prediction results to complete project elimination.

5. The method according to claim 1, characterized in that The method further comprises: Obtain the user's selected plan and generate real-time response instructions; Monitor the associated information using the real-time response instruction, wherein the associated information includes road congestion information and weather change information; Dynamic adjustment of the selected plan is performed based on the associated information, and dynamic feedback is generated, and the dynamic feedback is sent to the corresponding user.

6. The method according to claim 1, characterized in that The method further comprises: Get the user's set sharing permission information; The user's encryption mode is configured with the shared permission information, the user is managed with the encryption mode, and the user's data is encrypted and uploaded to the cloud.

7. A travel route planning system based on artificial intelligence, characterized in that: A system for implementing a travel route planning method based on artificial intelligence according to any one of claims 1 to 6, the system comprising: A data set establishment module, the data set establishment module is used to establish a user data set, wherein the user data set is a user set established through multiple channels, the multiple channels include historical travel data, questionnaire data, and the user data set is used to perform time series data verification, and user features are established according to the verification results, wherein the user features include main features and auxiliary features, wherein the main features refer to features that have a dominant effect on the user's current preferences and come from the data closest to the current time; the auxiliary features refer to features that have a certain influence on the user's preferences but are not dominant and come from data at an earlier time; An input data reading module, the input data reading module is used to read the user's input data, the input data includes an input destination, a planned date cycle, and an impact factor, wherein the impact factor is a coefficient of variation of the experience travel set by the user, and the impact factor is a coefficient of variation set by the user subjectively, reflecting the user's willingness to try low-matching projects, and the value range is a real number between 0 and 1; A matching module, the matching module is used to match items of a target scenic spot with the user characteristics, wherein the item matching includes item content matching and item access matching, and establish an item matching value; A route planning reconstruction module, the route planning reconstruction module is used to perform route planning for the project through the input data, generate an accommodation selection plan corresponding to the route planning, eliminate projects based on the route planning results, project matching values ​​and the input data, and reconstruct the route planning results; The result feedback module is used to feed back the reconstructed route planning results to the user to complete the travel route planning management.

Images