Personalized micro tourist route generation method and system based on scene micro tourist portrait, medium and processor

Abstract

The invention provides a personalized micro-tourism route generation method based on scene micro-tourist portraits. The method comprises the following steps: S1, collecting data of tourists in various tourism scenes; s2, generating a scene-based micro tourist portrait according to the data of each tourism scene; s3, carrying out scene classification on scenic spots in the tourist area to obtain a plurality of micro-scenes; and S4, associating the micro scene of the scenic spot or the scenic area with the micro tourist portrait corresponding to the tourist to obtain a first micro tourist portrait, and generating a micro tourist route in the micro scene according to the first micro tourist portrait. The invention aims to provide higher-quality and personalized tourism experience for tourists and promote the intelligent development of the tourism industry at the same time.

Description

Technical Field

[0001] The present invention relates to the field of tourism management technology, and in particular to a method, system, medium and processor for generating personalized micro-tourism routes based on scene micro-tourist portraits. Background Art

[0002] With the improvement of people's living standards, tourism has become an important form of leisure and entertainment for the public. In the current booming tourism market, tourists' requirements for travel experiences are becoming more diversified and personalized. Traditional general tourist routes can no longer meet tourists' needs.

[0003] Previous travel route planning often relied on a simple combination of popular attractions within a scenic area, lacking in-depth consideration of individual tourists' differences. For example, tourists of different ages, interests, hobbies, and travel purposes have vastly different priorities when choosing a travel route. Older adults may prefer leisure and wellness travel, favoring historical and cultural attractions; while younger people may be more interested in exciting and challenging adventure activities and emerging entertainment options. However, existing travel route planning models fail to accurately match tourists' individual needs, making it difficult for them to obtain a satisfactory experience and fully enjoy their travels.

[0004] Furthermore, with the rapid development of information technology, tourism-related data has exploded. Social media platforms are flooded with travel experiences, reviews, photos, and other information shared by tourists. Travel apps have also accumulated a wealth of user behavior data, such as search history, browsing history, and booking information. However, this data is fragmented and lacks effective integration and analysis, making it difficult for the tourism industry to extract valuable information and transform it into a basis for providing personalized services to tourists.

[0005] From the perspective of scenic area management, the lack of accurate visitor profiles and personalized route planning makes it difficult for scenic areas to develop differentiated marketing strategies and service plans for different types of tourists and different scenarios. This not only affects the attractiveness and competitiveness of scenic areas, but also limits the efficient use of tourism resources and the sustainable development of the tourism industry.

[0006] In this context, how to use advanced technical means to integrate multi-source data, build scenario-based micro-tourist portraits, and generate personalized micro-tourism routes has become a key issue that needs to be urgently addressed in the tourism industry.

[0007] In view of this, a method, system, medium and processor for generating personalized micro-tourism routes based on scene micro-tourist portraits are needed. Summary of the Invention

[0008] In response to the lack of accurate tourist portraits and personalized route planning in existing technologies, the method for generating personalized micro-tourism routes based on scenario-based micro-tourist portraits proposed in this paper is designed to address these challenges, providing tourists with a higher-quality, personalized travel experience while promoting the intelligent development of the tourism industry. By utilizing advanced technical means and integrating multi-source data, the method constructs scenario-based micro-tourist portraits and generates personalized micro-tourism routes. The specific technical solution is as follows:

[0009] A method for generating personalized micro-tourism routes based on scenario-based micro-tourist portraits, comprising:

[0010] S1: Collect tourists’ data in various travel scenarios;

[0011] S2: Generate scenario-based micro-tourist portraits based on the data of each tourism scenario;

[0012] S3: Classify the scenic spots in the tourist area and obtain several micro-scenes;

[0013] S4: Associating the micro-scene of the scenic spot or scenic area with the micro-tourist portrait corresponding to the tourist to obtain a first micro-tourist portrait, and generating a micro-tourism route within the micro-scene based on the first micro-tourist portrait.

[0014] Furthermore, step S2 includes the following steps:

[0015] S21: Data cleaning and preprocessing;

[0016] S22: scene-based feature extraction;

[0017] S23: Construction of micro-tourist portraits;

[0018] S24: Portrait verification and update.

[0019] Furthermore, the scene-based feature extraction includes extraction of basic information, scene interest preferences, scene behavior habits or scene demand expectations.

[0020] Furthermore, the scene interest preference feature extraction formula is as follows:

[0021]

[0022] In the above formula, i j S is the tourists’ preference for each item in the scene; interest is the comprehensive interest score of tourists in the project under the scenario; w j is the importance weight of different sports in this scenario.

[0023] Furthermore, associating the micro-scene of the scenic spot or scenic area with the micro-tourist portrait corresponding to the tourist to obtain a first micro-tourist portrait, and generating a micro-tourism route within the micro-scene according to the first micro-tourist portrait, includes the following steps:

[0024] S41: Obtaining the micro-tourist portrait with the highest correlation with the micro-scene as the first micro-tourist portrait;

[0025] S42: Generate a micro-tourism route matching the micro-scene based on the first micro-tourist portrait.

[0026] S43: Optimize and dynamically adjust micro-tourism routes.

[0027] Furthermore, in step S41, obtaining the micro-tourist portrait with the highest correlation with the micro-scene as the first micro-tourist portrait includes the following steps:

[0028] Assume that the feature vector of micro-tourist portrait is represented as where a si Indicates the value of the i-th feature in the portrait in this scene, and the weight of each feature is w si ;

[0029] Assume that the feature vector of the micro scene is expressed as Indicates the value of the i-th feature in the micro scene;

[0030] The similarity between the two is calculated according to the following formula:

[0031]

[0032] In this formula, the numerator multiplies the corresponding elements of the two vectors in the same specific scenario and performs a weighted sum; the denominator is used for normalization to ensure that the similarity value is between -1 and 1. is the similarity between the two;

[0033] by The micro-tourist portrait with the highest value is taken as the first micro-tourist portrait of the micro-scene.

[0034] Furthermore, in step S42, generating a micro-tourism route matching the micro-scene according to the first micro-tourist portrait includes the following steps:

[0035] Let n be the number of visiting points in the micro scene, and the visiting points are recorded as P1, P2, ..., P n ;

[0036] For a possible micro tourism route The calculation formula for the route score S(L) (k≤n, indicating the tour order) is:

[0037]

[0038] In the above formula, The tourists’ opinions on the current visitor spot defined by the first micro-tourist portrait preference weights; Indicates line The jth visiting spot Go to the j+1th visit point distance; start m Indicates the time when the attraction opens to the public; d mn Represents the visiting point P in the micro scene m To the sightseeing spot P n distance; max m,n d mn It represents the maximum distance between all the visiting points; end m Indicates closing time; Indicates the maximum opening time of all visiting spots in the current micro scene; For sightseeing spots opening hours; For sightseeing spots End time; T start is the starting time for the current tourist to tour, T end The end time of the tour available to the current tourists;

[0039] The route with the highest score S(L) is selected as the optimal micro-tourism route in the current micro-scene.

[0040] A personalized micro-tourism route generation system based on scene micro-tourist portraits is applied to the above-mentioned personalized micro-tourism route generation method based on scene micro-tourist portraits, comprising:

[0041] The collection module is used to collect data of tourists in various tourism scenarios;

[0042] A generation module, which is used to generate scenario-based micro-tourist portraits based on the data of each tourism scenario;

[0043] A classification module is used to classify the scenic spots in the tourist area into several micro-scenes;

[0044] The route module is used to associate the micro-scene of a scenic spot or scenic area with the micro-tourist portrait corresponding to the tourist, obtain a first micro-tourist portrait, and generate a micro-tourism route within the micro-scene based on the first micro-tourist portrait.

[0045] A computer-readable storage medium includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned personalized micro-tourism route generation method based on scene micro-tourist portraits.

[0046] A processor is used to run a program, wherein when the program is run, the method for generating personalized micro-tourism routes based on scene micro-tourist portraits is executed.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. Personalized travel route planning: Existing technologies often provide universal travel routes that are difficult to meet the personalized needs of different tourists. This invention collects data on tourists in various travel scenarios to construct scenario-based micro-tourist portraits. It then conducts in-depth analysis of tourists' interests, preferences, behavioral habits, and expectations in different scenarios, such as constructing portraits for natural scenery viewing scenes, historical and cultural experience scenes, and other scenarios. Based on the correlation between micro-tourist portraits and micro-scenes, highly personalized micro-tour routes are generated for tourists, making the travel routes more tailored to their interests and needs, greatly improving the targetedness and personalization of travel routes.

[0049] 2. Efficient Utilization of Multi-Source Data: Traditional approaches underutilize tourism-related data, resulting in a large amount of data scattered across platforms like social media and travel apps, which is not effectively integrated and analyzed. This invention utilizes a combination of online and offline methods to collect data, covering multiple types of data, including basic visitor information, behavioral data, and consumption data. This data is cleaned, preprocessed, and feature extracted, then stored on a unified data platform. It is then labeled and indexed according to different scenarios and data types, fully leveraging the data's value and providing powerful support for personalized itinerary creation.

[0050] 3. Improve scenic area management and service levels: Existing technologies make it difficult for scenic areas to develop differentiated strategies for different tourists, resulting in inadequate resource utilization. This invention categorizes scenic spots by scene, establishing a micro-scene database that records detailed information about each attraction. Based on this information, combined with micro-tourist profiles, scenic areas can more rationally plan facility layouts, arrange activities, and conduct targeted marketing and promotions, thereby increasing their appeal and operational efficiency and achieving efficient utilization of tourism resources.

[0051] 4. Optimizing the Tourist Experience: Existing tour routes can easily lead to tourists missing out on interesting activities and lack flexible adjustment mechanisms. This invention generates micro-tour routes by recommending relevant attractions, activities, and experiences based on micro-tourist profiles, preventing visitors from missing out on interesting content. Furthermore, the system dynamically adjusts routes based on visitor feedback and real-time data, such as foot traffic and weather changes, to timely optimize routes, improve visitor satisfaction, and enhance the travel experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly describes the drawings required for the specific embodiments or the description of the prior art. Similar elements or parts are generally identified by similar reference numerals throughout the drawings. Elements or parts in the drawings are not necessarily drawn to scale.

[0053] Figure 1 This is a flowchart of a method for generating personalized micro-tourism routes based on scenario-based micro-tourist portraits;

[0054] Figure 2 This is a structural diagram of a personalized micro-tourism route generation system based on scenario-based micro-tourist portraits. DETAILED DESCRIPTION

[0055] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0056] It will be understood that when used in this specification and the appended claims, the terms “comprises” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0057] It should also be understood that the terms used in the present specification are only for the purpose of describing particular embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0058] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0059] Example 1

[0060] Figure 1 The figure shows a process flow diagram of a method for generating personalized micro-tourism routes based on scenario-based micro-tourist portraits, which includes the following specific steps:

[0061] S1: Collect data of tourists in various travel scenarios.

[0062] Various tourism scenes include: natural scenery viewing scenes, historical and cultural experience scenes, food exploration scenes, leisure and entertainment scenes, festival activity scenes, parent-child interaction scenes, sports and fitness scenes, shopping and consumption scenes, health and wellness vacation scenes, religious pilgrimage scenes, science and technology research scenes, rural pastoral scenes, etc.

[0063] The specific steps include:

[0064] S11: Determine the data collection point and time.

[0065] Data collection points are set up at key locations in various tourist scenes, such as observation decks and rest areas for natural scenery viewing; museum entrances and explanation areas for historical and cultural experience scenes; restaurant entrances and snack stalls for food exploration scenes, etc.

[0066] Clarify the time range for data collection, covering the peak and off-seasons of tourism, different time periods (such as morning, afternoon, evening), and special holidays, etc., to obtain comprehensive tourist data.

[0067] S12: Data collection is carried out using a combination of online and offline methods.

[0068] Online data collection:

[0069] Develop a special travel APP, requiring tourists to fill in basic information (age, gender, occupation, interests and hobbies, etc.) when registering, and record their search history, browsing history (such as introductions to browsed attractions, travel guides, etc.), and booking information (hotels, tickets, transportation, etc.) during use.

[0070] Cooperate with social media platforms, obtain user authorization through API interfaces, and collect travel-related content posted by users, such as photos, text descriptions, check-in locations, etc.

[0071] Offline data collection:

[0072] Manual questionnaire survey, randomly inviting tourists to fill out questionnaires at the entrance of scenic spots, around scenic spots, etc., including travel purpose, companions, preference for different travel activities, consumption budget, etc.

[0073] Install cameras and sensors, use video analysis technology to identify tourists' behavior (such as length of stay, walking route, frequency of taking photos, etc.), and collect environmental data (temperature, humidity, flow of people, etc.) through sensors.

[0074] Cooperate with merchants in the scenic area to obtain tourists' consumption records, including consumption amount and consumption items (such as purchased souvenirs, dining expenses, etc.).

[0075] S13: Pre-store and manage the data.

[0076] Establish a unified data storage platform and use a database management system (such as MySQL, Oracle, etc.) to store the collected data.

[0077] Detailed labeling and indexing are performed according to different travel scenarios and data types (basic information, behavioral data, consumption data, etc.) to facilitate subsequent data query, analysis, and processing. At the same time, data is backed up regularly to ensure data security and integrity.

[0078] S2: Generate scenario-based micro-tourist portraits based on the data of each tourism scenario.

[0079] This step is to generate micro-tourist portraits in different scenarios based on the collected data of various tourism scenarios. Tourist portraits are different in different scenarios. For example, when drinking a drink, in a wine culture scene, the tourist may choose wine, in a scene focusing on scenery, he may choose a refreshing drink such as lemonade, and in a scene focusing on amusement facilities, he may choose soda. Therefore, people may have different choices for the same type of things in different scenarios. The specific steps include:

[0080] S21: Data cleaning and preprocessing.

[0081] The collected raw data is thoroughly cleaned to remove duplicate, erroneous, incomplete or abnormal data records.

[0082] Standardize numerical data (such as age, consumption amount, length of stay, etc.) to unify the dimension and value range of the data, such as normalizing it to the [0,1] interval or converting it to a standard normal distribution.

[0083] For text data (such as user comments, travel experiences, etc.), word segmentation, part-of-speech tagging, stop word removal and other processing are performed, and then the text is converted into vector representation through word vector models (such as Word2Vec, GloVe, etc.) to facilitate computer analysis and processing.

[0084] S22: Scene-based feature extraction.

[0085] For each tourism scene, extract the features closely related to the scene. For example:

[0086] In the natural scenery viewing scene, features such as tourists' photo taking locations (latitude and longitude information), photo taking frequency, length of stay at different natural landscapes (mountains, lakes, forests, etc.), and frequency of words praising natural landscapes (through text analysis) are extracted.

[0087] In the historical and cultural experience scenario, characteristics such as the length of time tourists stay in museums, historical sites and other places, the number of exhibitions or attractions visited, the length of time they listen to historical and cultural explanations, and the number of questions they ask about historical and cultural issues are extracted.

[0088] In the food exploration scenario, features such as the cuisine chosen by tourists, food taste preferences (spicy, sweet, sour, etc.), amount spent on each meal, and words used to evaluate food (delicious, unique, authentic, etc.) are extracted.

[0089] Feature selection algorithms (such as chi-square test, mutual information, etc.) are used to screen out the most representative and significant features for scene distinction and tourist portrait construction, remove redundant and irrelevant features, reduce data dimensions, and improve analysis efficiency.

[0090] S23: Construction of micro-tourist portraits.

[0091] A micro-tourist portrait is constructed for each tourism scenario. The portrait content includes the following dimensions and is closely centered around the characteristics of the scenario:

[0092] Basic information: covers general information such as age, gender, occupation, and region, and combines it with scenario analysis to analyze its potential impact in the scenario, such as the behavioral differences between tourists of different age groups in parent-child interaction scenarios.

[0093] Scenario interest preference: A detailed description of tourists' interest in specific activities, landscapes, cultural elements, etc. in a specific scenario, such as the preference ranking of running, mountaineering, yoga and other sports in a sports and fitness scenario.

[0094] Scenario behavior habits: records tourists’ behavior patterns in this scenario, including the pattern of stay time (distribution of stay time in the morning, afternoon, and evening), activity frequency (such as the number of times a tourist attraction is visited in a day), consumption habits (consumption time, consumption amount range, consumption item tendencies), etc.

[0095] Scenario demand expectations: Analyze tourists' special needs and expectations for tourism facilities and services in this scenario, such as the degree of demand for a quiet environment, healthy dining, and professional medical services in a health and wellness vacation scenario.

[0096] Weight assignment: Assign preference weights to various interest preferences, behavioral habits, and demand expectations in each scenario.

[0097] When generating micro-tourist portraits, the extracted data must be divided into the scenarios from which they were extracted, so that the final calculation can accurately determine the tourist's preferred behavior in a certain scenario.

[0098] Scene interest preference can be quantified by the following formula:

[0099] In terms of scene interest preference, if we want to calculate the comprehensive interest score of tourists in different sports in the sports and fitness scene, we can set a formula. Let the sports item set be M = {m1,m2,…,m k} (e.g. m1 represents running, m2 represents mountain climbing, etc.), the degree of preference of tourists for each activity is I = {i1,i2,…,i k} (can be obtained through surveys or data statistics, the value range is assumed to be [0,5], the larger the value, the more like it), then the tourists' comprehensive interest score for sports in the sports and fitness scene is S interest It can be expressed as If we consider the importance weights w of different sports in this scenario j The formula can be optimized as follows:

[0100]

[0101] The formula for quantifying behavioral habits is as follows: Taking the calculation of the average length of stay of tourists in a certain scene as an example, let the length of stay of tourists in n visits in this scene be t1, t2,…, t n , the average length of stay For consumption habits, if the amount of tourists’ consumption in m shopping scenarios is c1, c2, …, c m , average consumption amount If you want to further analyze the consumption time pattern, you can divide a day into x time periods and count the number of consumption times f1, f2, ..., f in each time period. x , then the consumption time preference score where p i is the weight of the i-th time period (which can be set according to factors such as tourist off-season and peak season, scenic spot business hours, etc.).

[0102] Demand expectation quantification formula: In the health and wellness vacation scenario, assume that tourists' demand for quiet environment, healthy dining, and professional medical services are r1, r2, and r3 (value range [0,1]), and assign weights q1, q2, and q3 to these three demand dimensions respectively. The comprehensive score of tourists' demand expectations in the health and wellness vacation scenario is S demand =r1×q1+r2×q2+r3×q3.

[0103] By performing quantitative calculations on each dimension, the feature with the highest score is used as the role portrait.

[0104] S24: Portrait verification and update.

[0105] We randomly sampled a sample of tourists for follow-up surveys, comparing their portraits with their actual situations to assess their accuracy and reliability. For portraits with significant deviations, we analyzed the causes and made corrections.

[0106] As time goes by and tourist behavior changes, new data is collected regularly (such as every quarter or half a year) to update the micro-tourist portrait to ensure that the portrait can promptly reflect the latest characteristics and needs of tourists in various scenarios.

[0107] S3: Classify the scenic spots in the tourist area into several micro-scenes.

[0108] Furthermore, each tourist attraction is a micro-scene, such as an attraction that focuses on scenery, an attraction that focuses on humanities, an attraction that focuses on history, an attraction that focuses on food, an attraction that focuses on amusement facilities, etc.

[0109] S31: Comprehensive collection of tourist attraction information.

[0110] Organize a professional team to conduct on-site surveys of all scenic spots in the tourist area, and record in detail the geographical location (accurate to longitude and latitude), area, topography, surrounding environment and other natural information of the scenic spots; as well as the architectural style, historical origins, cultural connotations, main landscape components (such as sculptures, monuments, plant species, etc.), facility layout (parking lots, rest areas, dining areas, toilets, entertainment facilities, etc.), opening hours, ticket prices and other cultural and facility information within the scenic spots.

[0111] We have extensively consulted relevant historical documents, archival materials, academic research results, tourism planning documents, etc. to gain an in-depth understanding of the historical background, cultural value, development changes, and functional positioning and importance of the scenic spots in the tourist area.

[0112] Collect tourists' evaluations and feedback on attractions on various travel platforms and social media, including positive reviews, negative reviews, suggestions, etc., to understand the actual experience and special highlights of the attractions from the perspective of tourists.

[0113] S32: Develop classification standards for micro-scenes from several dimensions.

[0114] Taking into account various factors such as landscape type, functional positioning, cultural theme, and tourist activity type, a detailed scene classification standard is formulated:

[0115] Landscape type dimension: divided into natural landscapes (such as mountains, rivers, lakes, forests, grasslands, etc.), cultural landscapes (such as historical buildings, cultural relics, museums, art galleries, etc.), and man-made landscapes (such as theme parks, amusement parks, film and television cities, etc.).

[0116] Functional positioning dimension: divided into viewing attractions (mainly for tourists to appreciate the scenery, such as observation decks, gardens, etc.), experience attractions (such as folk culture villages, handicraft workshops, etc., where tourists can participate in interactive experiences), entertainment attractions (such as playgrounds, water parks, etc.), educational attractions (such as science museums, historical memorial halls, etc., which have educational significance), and shopping attractions (such as specialty commercial streets, shopping centers, etc.).

[0117] Cultural theme dimension: including red culture theme attractions, religious culture theme attractions, folk culture theme attractions, art and culture theme attractions, etc.

[0118] Tourist activity type dimension: such as hiking and adventure attractions, leisure and vacation attractions, parent-child interaction attractions, sports and fitness attractions, etc.

[0119] S33: Divide the tourist area's attractions into micro-scenes in multiple dimensions.

[0120] According to the established classification standards, the scenic spots in the tourist area are classified one by one, and each scenic spot is subdivided into one or more micro scenes. Ensure that each micro scene has unique characteristics and functions and is clearly distinguishable from other micro scenes.

[0121] Give each micro-scene an accurate, clear, and attractive name, and write a detailed description. For example, "XX Ancient Town Folk Culture In-Depth Experience Micro-scene (featuring traditional handicraft displays, folk performances, and visits to distinctive dwellings, allowing visitors to experience the rich local folk culture)" or "XX Mountain Natural Scenery Photography Micro-scene (featuring multiple excellent viewing platforms and photo spots, perfect for capturing magnificent mountain and river scenery)."

[0122] S34: Establish a complete micro-scene database.

[0123] The divided micro-scene information is entered into the database, including the name of the micro-scene, the scenic spot to which it belongs, classification information, geographical location coordinates, introduction to the main landscapes and activities, details of supporting facilities, opening hours, ticket prices, visitor capacity and other detailed data.

[0124] Carry out real-time management and maintenance of the micro-scene database, and promptly update relevant information of the micro-scene, such as facility renovation, activity adjustment, price changes, etc., to ensure the accuracy and timeliness of the database and provide reliable data support for the subsequent generation of micro-tourism routes.

[0125] S4: Associating the micro-scene of the scenic spot or scenic area with the micro-tourist portrait corresponding to the tourist to obtain a first micro-tourist portrait, and generating a micro-tourism route within the micro-scene based on the first micro-tourist portrait.

[0126] S41: Obtain the micro-tourist portrait with the highest correlation with the micro-scene as the first micro-tourist portrait.

[0127] 1. Design a specialized association algorithm that comprehensively considers the multi-dimensional characteristics of micro-tourist portraits (interest preferences, behavioral habits, demand expectations, etc.) and the characteristics of micro-scenes (landscape type, functional positioning, cultural theme, etc.), and calculates the matching degree between the two. For example, a weighted cosine similarity algorithm is used to assign corresponding weights to different feature dimensions, highlighting the impact of important features on the matching results. The specific association algorithm is as follows:

[0128] Assuming that for a specific scene (such as a natural scenery viewing scene), the feature vector of the micro-tourist portrait is expressed as where a si Indicates the value of the i-th feature in the portrait in this scene, and the weight of each feature is w si For example, a s1 It can be the frequency of tourists taking photos in natural scenery viewing scenes (times / hour), w s1 It is the weight assigned to the feature, which is used to reflect its importance in the matching calculation of the scene.

[0129] Accordingly, the feature vector of the micro-scene that the tourist currently arrives at is expressed as Indicates the value of the i-th feature in the micro scene. For example, b s1 It can be the percentage of locations suitable for taking photos in the micro scene.

[0130] The formula for calculating the similarity between the two is:

[0131]

[0132] The numerator of this formula multiplies the corresponding elements of the two vectors in the same specific scene and takes a weighted sum. The denominator is used for normalization to ensure that the similarity value is between -1 and 1, accurately measuring the similarity between the micro-tourist portrait and the micro-scene in the characteristic dimension of the scene. The closer it is to 1, the higher the match between the two in the scene.

[0133] In this way, the first micro-tourist portrait that is most relevant to the micro-scene that the tourist currently arrives at can be found.

[0134] 2. Machine learning technology can also be used to build a correlation model between micro-scenes and micro-tourist portraits. The model can be trained and optimized through a large amount of annotated historical data (data on the matching relationship between known micro-scenes and micro-tourist portraits) to improve the accuracy and generalization ability of the model. Decision trees, random forests, neural networks and other algorithms can be used for model construction and training. The specific calculation steps are as follows:

[0135] For a specific scenario (such as a historical and cultural experience scenario), it is assumed that the input feature is the combined feature vector of the micro-tourist portrait and the micro-scene in the scenario The parameters of the model are:

[0136]

[0137] First compute the linear combination:

[0138]

[0139] Then z is transformed into s Converted to probability value, the formula of sigmoid function is:

[0140]

[0141] in, It represents the probability that the model predicts that the micro-tourist viewing portrait matches the micro-scene in this specific scene. During the training process, the parameters are adjusted by minimizing the loss function for this scene (such as the logarithmic loss function). The logarithmic loss function formula is:

[0142]

[0143] In the above formula, N s is the number of samples of training data for this scenario, is the actual label of the jth sample in this scenario (1 means match, 0 means no match), is the feature vector of the jth sample in this scenario; through continuous iterative optimization (such as gradient descent method) in this scenario, the loss function Reach the minimum value to obtain the optimal model parameters suitable for this scenario The association model between micro-scenes and micro-tourist portraits in specific scenarios is constructed to obtain the first micro-tourist portrait with the highest probability of matching the specific micro-scene.

[0144] S42: Generate a micro-tourism route matching the micro-scene based on the first micro-tourist portrait.

[0145] According to the matching results obtained by association algorithm and model calculation, the first micro-tourist portrait that is highly matched with the micro-scene where the current tourist arrives is screened out, and the optimal micro-tourism route in the current micro-scene is generated based on the first micro-tourist portrait.

[0146] When generating the optimal micro-tourism route within the current micro-scene, based on the interests and preferences of the first micro-tourist profile, recommendations are made to tourists regarding attractions, activities, and experiences that match the first micro-tourist profile within the current micro-scene. For example, for tourists who enjoy gourmet food, must-try specialty dishes and restaurant locations and information are recommended within the gourmet micro-scene; for tourists interested in history and culture, interesting exhibitions are recommended within the history and culture micro-scene. This can improve tourist travel efficiency and prevent them from missing out on items they care about, are interested in, and would like to experience. The specific generation steps are as follows:

[0147] Assume that there are n visiting points in the current micro scene, which are recorded as P1, P2, ..., P n .

[0148] Define the tourist interest preference weight vector based on the first micro-tourist portrait where w i Indicates tourists' interest in visiting point P i The preference weights of related interests, as follows Also in this range, the value range is [0,1], and When constructing the first micro-tourist profile, the weight vector is determined based on the tourist's interest in different items in each scenario. For example, in the food micro-scenario, if the first micro-tourist profile shows a strong interest in local snacks, then the corresponding values ​​for snack-related attractions (such as snack street stalls and time-honored snack shops) will be higher.

[0149] Use d ij Indicates visit point P i To the sightseeing spot P j The distance (which can be converted by actual distance or travel time) is constructed to construct the distance matrix D = (d ij ) n×n .

[0150] Set up visiting point P i The opening hours are [start i ,end i ], the time interval currently available for tourists to visit is [T start ,T end ].

[0151] For a possible micro tourism route (k≤n, The representation includes a tour order. Due to the large number of possible route combinations, there are n possible permutations of n attractions. However, in practice, the computational effort can be reduced by considering certain constraints, such as time constraints and the physical limitations of tourists. Heuristic algorithms (such as genetic algorithms and simulated annealing) can be used to quickly find a near-optimal solution. For example, genetic algorithms simulate the process of biological evolution, starting from a set of initial routes (populations) and iterating through operations such as selection, crossover, and mutation to gradually refine the optimal route until a certain convergence condition is met. If the route score no longer improves significantly after multiple iterations, the optimal or near-optimal micro-tourism route is output. The route score S(L) is calculated as follows:

[0152]

[0153] In the above formula, the first part of the formula It is calculated based on the score of tourists' interest preferences and the distance between the visited spots. Reflects tourists' current visit points preference weights; The distances between visiting spots are normalized. The smaller the distance, the higher the score, which means that the distance cost is lower and the route is better when tourists move between the preferred visiting spots.

[0154] The second part of the formula The matching degree between the opening hours of the visit sites and the time available for tourists to visit is taken into consideration. The intersection of the opening hours of the tourist attraction and the tourist time is normalized. The longer the intersection time, the higher the score of this part, which reflects that the tourist attraction can be better visited within the tourist's available time. Indicates line The jth visiting point Go to the j+1th visit point It can be the actual geographical distance or the distance calculated based on travel time, transportation cost, etc., which is used to measure the cost of tourists moving between different sightseeing spots. (start m -end m ) is the visiting point P m Opening hours, start m Indicates the time when the attraction starts opening to the public, end m Indicates closing time.

[0155] By calculating the scores S(L) of all possible routes, the route with the highest score is selected as the optimal micro-tourism route in the current micro-scene.

[0156] S43: Optimize and dynamically adjust micro-tourism routes.

[0157] Provide tourists with real-time feedback channels, such as feedback functions within travel apps and information desks within scenic areas. Tourists can provide feedback at any time during their visit, such as long queues at certain attractions, unreasonable route arrangements, lack of interest in certain activities, omissions or inability to find, or difficulty finding activities of interest.

[0158] At the same time, the system dynamically adjusts micro-tourism routes based on visitor feedback and real-time data (such as visitor flow data, weather changes, and traffic conditions). For example, if a particular attraction is overcrowded, the system automatically adjusts the route based on which other attractions within the tourist area match the visitor's micro-tourist profile (each visitor has a micro-tourist profile in different scenarios, and the system searches for other attractions within the scenic area that match the visitor's profile). It recommends that visitors visit other attractions first to avoid peak hours. If weather changes affect certain activities, the system will promptly replace or adjust the activity schedule.

[0159] Regularly evaluate and optimize micro-tourism routes within scenic spots, collect visitor reviews and suggestions, and analyze the rationality, satisfaction, and personalization of routes. Based on the evaluation results, continuously improve the association algorithm, path planning algorithm, and recommendation strategy to enhance the quality of micro-tourism routes and the visitor experience.

[0160] In each micro-scene of a scenic spot or scenic area, a corresponding micro-tourism route in the micro-scene is generated according to the corresponding micro-tourist portrait, realizing personalized micro-tourism route formulation based on micro-scenes, refining the granularity of automatic tour guides, improving the accuracy of tourism route formulation, and enhancing tourists' travel experience.

[0161] Compared with the prior art, the present invention has the following beneficial effects:

[0162] 1. Personalized travel route planning: Existing technologies often provide universal travel routes that are difficult to meet the personalized needs of different tourists. This invention collects data on tourists in various travel scenarios to construct scenario-based micro-tourist portraits. It then conducts in-depth analysis of tourists' interests, preferences, behavioral habits, and expectations in different scenarios, such as constructing portraits for natural scenery viewing scenes, historical and cultural experience scenes, and other scenarios. Based on the correlation between micro-tourist portraits and micro-scenes, highly personalized micro-tour routes are generated for tourists, making the travel routes more tailored to their interests and needs, greatly improving the targetedness and personalization of travel routes.

[0163] 2. Efficient Utilization of Multi-Source Data: Traditional approaches underutilize tourism-related data, resulting in a large amount of data scattered across platforms like social media and travel apps, which is not effectively integrated and analyzed. This invention utilizes a combination of online and offline methods to collect data, covering multiple types of data, including basic visitor information, behavioral data, and consumption data. This data is cleaned, preprocessed, and feature extracted, then stored on a unified data platform. It is then labeled and indexed according to different scenarios and data types, fully leveraging the data's value and providing powerful support for personalized itinerary creation.

[0164] 3. Improve scenic area management and service levels: Existing technologies make it difficult for scenic areas to develop differentiated strategies for different tourists, resulting in inadequate resource utilization. This invention categorizes scenic spots by scene, establishing a micro-scene database that records detailed information about each attraction. Based on this information, combined with micro-tourist profiles, scenic areas can more rationally plan facility layouts, arrange activities, and conduct targeted marketing and promotions, thereby increasing their appeal and operational efficiency and achieving efficient utilization of tourism resources.

[0165] 4. Optimizing the Tourist Experience: Existing tour routes can easily lead to tourists missing out on interesting activities and lack flexible adjustment mechanisms. This invention generates micro-tour routes by recommending relevant attractions, activities, and experiences based on micro-tourist profiles, preventing visitors from missing out on interesting content. Furthermore, the system dynamically adjusts routes based on visitor feedback and real-time data, such as foot traffic and weather changes, to timely optimize routes, improve visitor satisfaction, and enhance the travel experience.

[0166] Example 2

[0167] like Figure 2 As shown, a personalized micro-tourism route generation system based on scene micro-tourist portraits is applied to the above-mentioned personalized micro-tourism route generation method based on scene micro-tourist portraits, including:

[0168] The collection module is used to collect data of tourists in various tourism scenarios;

[0169] A generation module, which is used to generate scenario-based micro-tourist portraits based on the data of each tourism scenario;

[0170] A classification module is used to classify the scenic spots in the tourist area into several micro-scenes;

[0171] The route module is used to associate the micro-scene of a scenic spot or scenic area with the micro-tourist portrait corresponding to the tourist, obtain a first micro-tourist portrait, and generate a micro-tourism route within the micro-scene based on the first micro-tourist portrait.

[0172] Example 3

[0173] A computer-readable storage medium includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned personalized micro-tourism route generation method based on scene micro-tourist portraits.

[0174] Example 4

[0175] A processor is used to run a program, wherein when the program is run, the method for generating personalized micro-tourism routes based on scene micro-tourist portraits is executed.

[0176] This application provides a method for generating personalized micro-tourism routes based on scenario-based micro-tourist portraits, comprising the following steps: S1: collecting tourist data in various tourism scenarios; S2: generating scenario-based micro-tourist portraits based on the data from each tourism scenario; S3: classifying scenic spots in a tourist area to generate a number of micro-scenes; S4: associating the micro-scenes of the scenic spot or scenic area with the corresponding micro-tourist portrait of the tourist to obtain a first micro-tourist portrait, and generating a micro-tourism route within the micro-scene based on the first micro-tourist portrait. This method aims to provide tourists with a higher-quality, personalized tourism experience while promoting the intelligent development of the tourism industry.

[0177] Those skilled in the art will appreciate that the units of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0178] In the embodiments provided by the present invention, it should be understood that the division of units is merely a logical function division, and there may be other division methods in actual implementation, for example, multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored, etc.

[0179] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0180] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-0nly Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc., various media that can store program code.

[0181] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and description of the present invention.

Claims

1. A method for generating personalized micro-tourism routes based on scenario-based micro-tourist portraits, characterized in that: include: S1: Collect tourists’ data in various travel scenarios; S2: Generate scenario-based micro-tourist portraits based on the data of each tourism scenario; S3: Classify the scenic spots in the tourist area and obtain several micro-scenes; S4: Associating the micro-scene of the scenic spot or scenic area with the micro-tourist portrait corresponding to the tourist to obtain a first micro-tourist portrait, and generating a micro-tourism route within the micro-scene based on the first micro-tourist portrait.

2. The method for generating personalized micro-tourism routes based on scenario micro-tourist portraits according to claim 1 is characterized in that: Step S2 includes the following steps: S21: Data cleaning and preprocessing; S22: scene-based feature extraction; S23: Construction of micro-tourist portraits; S24: Portrait verification and update.

3. The method for generating personalized micro-tourism routes based on scenario micro-tourist portraits according to claim 2 is characterized in that: The scene-based feature extraction includes extraction of basic information, scene interest preferences, scene behavior habits or scene demand expectations.

4. The method for generating personalized micro-tourism routes based on scenario micro-tourist portraits according to claim 3 is characterized in that: The scene interest preference feature extraction formula is as follows: In the above formula, i j S is the degree of preference of tourists for each item in the scene; interest is the comprehensive interest score of tourists in the project under the scenario; w j is the importance weight of different sports in this scenario.

5. The method for generating personalized micro-tourism routes based on scenario micro-tourist portraits according to claim 1 is characterized in that: The method of associating the micro-scene of the scenic spot or scenic area with the micro-tourist portrait corresponding to the tourist to obtain a first micro-tourist portrait, and generating a micro-tourism route within the micro-scene according to the first micro-tourist portrait, includes the following steps: S41: Obtaining the micro-tourist portrait with the highest correlation with the micro-scene as the first micro-tourist portrait; S42: generating a micro-tourism route matching the micro-scene according to the first micro-tourist portrait; S43: Optimize and dynamically adjust micro-tourism routes.

6. The method for generating personalized micro-tourism routes based on scenario-based micro-tourist portraits according to claim 5 is characterized in that: In step S41, obtaining the micro-tourist portrait with the highest correlation with the micro-scene as the first micro-tourist portrait includes the following steps: Assume that the feature vector of micro-tourist portrait is represented as where a si Indicates the value of the i-th feature in the portrait in this scene, and the weight of each feature is w si ; Assume that the feature vector of the micro scene is expressed as b si Indicates the value of the i-th feature in the micro scene; The similarity between the two is calculated according to the following formula: In this formula, the numerator multiplies the corresponding elements of the two vectors in the same specific scenario and performs a weighted sum; the denominator is used for normalization to ensure that the similarity value is between -1 and 1. is the similarity between the two; by The micro-tourist portrait with the highest value is taken as the first micro-tourist portrait of the micro-scene.

7. The method for generating personalized micro-tourism routes based on scenario micro-tourist portraits according to claim 1 is characterized in that: In step S42, generating a micro-tourism route matching the micro-scene according to the first micro-tourist portrait includes the following steps: Let n be the number of visiting points in the micro scene, and the visiting points are recorded as P1, P2, ..., P n ; For a possible micro tourism route The calculation formula of the line score S(L) is: In the above formula, The tourists’ opinions on the current visitor spot defined by the first micro-tourist portrait preference weights; Indicates line The jth visiting spot Go to the j+1th visit point distance; start m Indicates the time when the attraction opens to the public; d mn Represents the visiting point P in the micro scene m To the sightseeing spot P n distance; max m,n d mn It represents the maximum distance between all the visiting points; end m Indicates closing time; Indicates the maximum opening time of all visiting spots in the current micro scene; For sightseeing spots opening hours; For sightseeing spots End time; T start is the starting time for the current tourist to tour, T end The end time of the tour available to the current tourists; The route with the highest score S(L) is selected as the optimal micro-tourism route in the current micro-scene; k≤n represents the tour order.

8. A personalized micro-tourism route generation system based on scene micro-tourist portraits, characterized by: The method for generating a personalized micro-tourism route based on a scenario-based micro-tourist portrait as described in any one of claims 1 to 7 comprises: The collection module is used to collect data of tourists in various tourism scenarios; A generation module, which is used to generate scenario-based micro-tourist portraits based on the data of each tourism scenario; A classification module is used to classify the scenic spots in the tourist area into several micro-scenes; The route module is used to associate the micro-scene of a scenic spot or scenic area with the micro-tourist portrait corresponding to the tourist, obtain a first micro-tourist portrait, and generate a micro-tourism route within the micro-scene based on the first micro-tourist portrait.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein, when the program is running, the device where the computer-readable storage medium is located is controlled to execute the personalized micro-tourism route generation method based on scene micro-tourist portraits as described in any one of claims 1 to 7.

10. A processor, characterized in that: The processor is used to run a program, wherein the program, when running, executes the personalized micro-tourism route generation method based on scene micro-tourist portraits described in any one of claims 1 to 7.

Images