Digital intelligence text travel fusion ecological system construction method

Abstract

The invention belongs to the technical field of intelligent text travel, and provides a digital intelligent text travel fusion ecological system construction method, which comprises the following steps of comprehensively carding various text travel resources in a region; behavior data of tourists and feedback information of the social platform are collected, and historical data are integrated; a cloud computing platform is used for large-scale data storage and management; carrying out tourist behavior analysis and trend prediction by applying a machine learning algorithm, analyzing tourist comments and feedbacks through a natural language processing technology, and extracting emotion and theme information; on the basis of tourist behavior analysis and prediction results, personalized recommendation is provided, and ticket prices are dynamically adjusted according to real-time data; constructing a virtual scenic spot and an intelligent guide service; according to the invention, the verbal travel industry fused with an ecological system is combined with a digital intelligence technology, so that the increasingly diversified requirements of modern tourists are met, personalized touring experience and a flexible price adjustment mechanism are provided, and the competitiveness of scenic spots is effectively improved.

Description

Technical Field

[0001] The present invention belongs to the field of smart cultural tourism technology, and specifically, is a method for constructing a digital cultural tourism integrated ecosystem. Background Art

[0002] In today's era of booming cultural and tourism industries, with the development of digital technology, the cultural and tourism industry is undergoing profound changes. Scenic spot operators are facing increasingly fierce market competition and need to seek effective means to optimize services, enhance user experience and improve the economic benefits of scenic spots. At present, although modern technology has been applied to a certain extent in the cultural and tourism industry, there are still many obvious defects in the existing technology in the actual operation and service process, which restricts its effectiveness and comprehensiveness in practical application.

[0003] Existing tourist behavior analysis systems often focus on a single data source (such as ticket sales data or online reviews), lacking multi-dimensional data integration and in-depth analysis. Tourists' behaviors, preferences, and psychological dynamics form a complex system. Relying on a single data source alone cannot fully reflect tourists' real needs and market trends. As a result, scenic area operators often cannot obtain accurate market trend judgments when making decisions. On the other hand, the processing of tourist comments and feedback is still at the stage of manual sampling or simple keyword statistics. It is impossible to use natural language processing technology to extract deep emotional and thematic information, missing many valuable improvement directions, failing to respond to tourists' expectations and demands in a timely manner, and difficult to develop innovative and attractive new products based on market trends.

[0004] In addition, the traditional ticket pricing method is usually based on cost plus or simply refers to the prices of surrounding scenic spots, without fully considering the dynamic changes in market supply and demand. Scenic spots cannot obtain tourist flow data in real time, and it is even more difficult to accurately predict future tourist demand, resulting in the inability to flexibly adjust ticket prices. In the peak tourist season, ticket prices failed to increase reasonably under strong demand, resulting in the loss of potential revenue; and in the off-season, when demand is insufficient, prices failed to be reduced in time to stimulate the market, leaving scenic spot resources idle, greatly reducing resource utilization efficiency and affecting the overall economic benefits of the scenic spot.

[0005] At the same time, some current intelligent recommendation systems are not mature enough in terms of personalization. They can only provide recommendations to tourists based on historical behavior records, and lack the ability to capture tourists' real-time needs and interests. This often makes the recommendation results inconsistent with tourists' actual preferences, resulting in reduced user satisfaction and difficulty in improving tourists' overall experience. In addition, most recommendation systems fail to integrate intelligent tour route planning, resulting in low tour efficiency for tourists, increased waiting and scheduling time, and reduced overall tour satisfaction.

[0006] To this end, technicians in this field have proposed a method for constructing a digital cultural and tourism integration ecosystem, aiming to combine the cultural and tourism industry of the integrated ecosystem with digital technology, meet the increasingly diverse needs of modern tourists, provide personalized tour experience and flexible price adjustment mechanism, and enhance the competitiveness of scenic spots. Summary of the invention

[0007] In order to solve the above technical problems, the present invention provides a method for constructing a digital and intelligent cultural and tourism integrated ecosystem to solve the problems raised in the background technology.

[0008] A method for constructing a digitalized cultural tourism integration ecosystem includes the following steps:

[0009] S1. Comprehensively sort out various cultural and tourism resources in the region, clarify the characteristics, distribution and protection status of the resources, and form a list of cultural and tourism resources;

[0010] S2. Collect tourists’ behavior data and social platform feedback information, and integrate historical data, including tourist flow, consumption records, and weather data;

[0011] S3, using cloud computing platforms to store and manage large-scale data and perform data preprocessing;

[0012] S4. Apply machine learning algorithms to analyze tourist behavior and trend prediction, analyze tourist comments and feedback through natural language processing technology, and extract sentiment and topic information;

[0013] S5. Provide personalized recommendations based on tourist behavior analysis and prediction results, and dynamically adjust ticket prices based on real-time data;

[0014] S6. Use virtual reality (VR) and augmented reality (AR) technologies to build virtual experience applications including virtual scenic spots, digital cultural relics exhibitions, and immersive cultural tourism performances;

[0015] S7. Build mobile APPs and mini-programs to provide tourists with smart tour guide services including real-time positioning, voice explanations, intelligent recommended tour routes, attraction introductions, and surrounding service inquiries.

[0016] Preferably, the various cultural and tourism resources in the region in step S1 include natural landscapes, historical and cultural relics, and folk customs in the region; based on the resource list, 3D scanning and drone technology are used to digitally model the cultural and tourism resources to form digital assets.

[0017] Preferably, step S4 extracts features based on the cultural and tourism resource list R, tourist behavior data B, social platform feedback T, historical traffic data F, consumption records C and weather data W to obtain tourist behavior features f b , time characteristics f t、Environmental characteristics e and social feedback features f s , construct the feature vector X = [f b ,f t ,f e ,f s ], a linear regression model is used to predict tourist flow, expressed as:

[0018]

[0019] in, represents the predicted tourist flow, β 0 represents the bias term, β 1 ,β 2 ,β 3 ,β 4 Represents the corresponding feature weight;

[0020] And time series analysis is used to predict the future trend of tourist flow, which is expressed as:

[0021]

[0022] Among them, y t Represents the past tourist flow data, sequence y t-k ,y t-k ,...,y t represents the continuous observations from time tk to time t, k represents the size of the historical data window, which is used to predict the future value y t+1 The number of past observations of Represents the observation value at time t+1.

[0023] Preferably, the step S4 further analyzes tourist comments and feedback by natural language processing technology, extracts comments from the tourist's social platform feedback data T, performs word segmentation, removes stop words and stems the text, converts it into a vector representation, and uses a sentiment classification model to perform sentiment analysis on the comments. The output of the sentiment analysis classifies the comments into positive, negative or neutral, which is represented as:

[0024]

[0025] in, is the probability distribution of sentiment category, d is the input comment text, Φ(d) represents the vector representation of the text, W, b represent the weight and bias of the sentiment classification model respectively;

[0026] And use the LDA model to perform topic analysis on the comments and extract potential topics, which are expressed as:

[0027]

[0028] Among them, ω represents a word, z represents a topic, θ represents the topic distribution of the document, and β represents the distribution of words in the topic.

[0029] Preferably, in step S5, based on the analysis and prediction results of tourist behavior in step S4, recommendations are made using the characteristics of tourist resources and the historical behaviors of tourists, and the recommendation value is calculated by cosine similarity, which is expressed as:

[0030]

[0031] Among them, each scenic spot j is represented as a feature vector r j , the behavior vector of tourist u is x u , by calculating the similarity between tourist u and each attraction j, a recommendation list is generated for the tourist;

[0032] And for the historical behavior data of tourist u and other tourists v, collaborative filtering is used to make predictions, which can be expressed as:

[0033]

[0034] in, represents the estimated score of the recommended attraction j for tourist u, and N(u) represents the set of tourists with high behavior similarity to tourist u.

[0035] Preferably, the step S5 also dynamically adjusts the ticket price according to the real-time data, and constructs a price adjustment model through the real-time number of tourists at the current time t, that is, the real-time tourist flow C(t) and the demand D predicted by the historical trend obtained by the prediction model in step S4, which is expressed as:

[0036] P(t)=P 0 ·(1+α·(C(t)-D))

[0037] Among them, P 0 represents the basic ticket price, α represents the setting based on historical data and the acceptable elasticity level, P(t) represents the ticket price at the current time t, if C(t)>D, it means that the demand is strong; otherwise, lowering the price will stimulate demand;

[0038] And further dynamic pricing using demand elasticity, expressed as:

[0039]

[0040] Among them, E d represents the demand elasticity coefficient, ΔQ represents the change in demand, Q represents the original demand, ΔP represents the change in price, that is, the increase or decrease in ticket prices, and P represents the original price, that is, the ticket price before the demand changes.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] 1. The present invention can enable scenic area operators to understand tourists' opinions and market trends through analysis and trend prediction of tourists' behaviors, as well as extraction of emotional and thematic information from tourists' comments and feedback, so as to provide a basis for scenic area operators to improve services, optimize facilities, and develop new products, thereby achieving scientific decision-making and refined management. The present invention can also build a price adjustment model based on real-time tourist flow and predicted demand, and dynamically price according to demand elasticity, so as to appropriately increase prices when demand is strong and reduce prices when demand is insufficient, thereby maximizing scenic area revenue and improving resource utilization efficiency.

[0043] 2. The present invention collects and analyzes tourist behavior data, historical data, etc., and uses machine learning algorithms to build models. It can accurately grasp tourists' interests and needs, provide tourists with scenic spot recommendations that meet their preferences, and intelligently recommend tour routes, allowing tourists to tour more efficiently and more in line with their personal preferences. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a flow chart of the method for constructing a digital cultural and tourism integration ecosystem of the present invention. DETAILED DESCRIPTION

[0045] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0046] As attached Figure 1 As shown:

[0047] Embodiment: The present invention provides a method for constructing a digital and intelligent cultural and tourism integrated ecosystem, comprising the following steps:

[0048] S1. Comprehensively sort out various cultural and tourism resources in the region, clarify the characteristics, distribution and protection status of the resources, and form a list of cultural and tourism resources; various cultural and tourism resources in the region include natural landscapes, historical and cultural relics, and folk customs in the region; based on the resource list, use 3D scanning and drone technology to digitally model cultural and tourism resources to form digital assets.

[0049] By comprehensively sorting out various cultural and tourism resources in the region, forming a resource list, and using digital modeling technology to form digital assets, we have achieved efficient integration and management of cultural and tourism resources, and improved resource utilization and protection levels.

[0050] S2. Collect tourists' behavioral data and feedback from social platforms, and integrate historical data, including tourist flow, consumption records, and weather data; understand tourists' needs and expectations in terms of food, accommodation, transportation, travel, shopping, and entertainment through questionnaires, interviews, and online comment analysis, and collect the pain points and demands of cultural and tourism practitioners in terms of operation management, marketing and promotion. At the same time, use web crawler technology to regularly capture cultural and tourism-related news information, tourist evaluations, travel guides and other data on the Internet; extract tourist identity information, tour trajectories, consumption records and other data from business systems such as ticketing systems, access control systems, and tourist service center systems in scenic spots and venues; establish data docking with third-party data platforms (such as weather data platforms, traffic data platforms, etc.) to obtain real-time weather, traffic and other data.

[0051] S3. Build a distributed storage cluster and use Hadoop Distributed File System (HDFS) or other similar distributed storage technologies to classify and store the massive structured, semi-structured and unstructured data collected. Establish a data governance system, formulate data standards and specifications, and perform pre-processing operations such as cleaning, deduplication, and conversion on the data to ensure the accuracy, completeness and consistency of the data.

[0052] S4. Apply machine learning algorithms to analyze tourist behavior and predict trends. Analyze tourist comments and feedback through natural language processing technology to extract emotional and thematic information. Extract features based on the cultural and tourism resource list R, tourist behavior data B, social platform feedback T, historical traffic data F, consumption records C and weather data W to obtain tourist behavior features f b , time characteristics f t 、Environmental characteristics e and social feedback features f s , construct the feature vector X = [f b ,f t ,f e ,f s ], a linear regression model is used to predict tourist flow, expressed as:

[0053]

[0054] in, represents the predicted tourist flow, β 0 represents the bias term, β 1 ,β 2 ,β 3 ,β 4 Represents the corresponding feature weight;

[0055] And time series analysis is used to predict the future trend of tourist flow, which is expressed as:

[0056]

[0057] Among them, y t Represents the past tourist flow data, sequence y t-k ,y t-k ,...,y t represents the continuous observations from time tk to time t, k represents the size of the historical data window, which is used to predict the future value y t+1 The number of past observations of Represents the observation value at time t+1.

[0058] We analyze tourists’ comments and feedback through natural language processing technology, extract comments from tourists’ social platform feedback data T, segment the text, remove stop words and stem it, and convert it into a vector representation. We use a sentiment classification model to perform sentiment analysis on the comments. The output of sentiment analysis classifies the comments into positive, negative or neutral, which is expressed as:

[0059]

[0060] in, is the probability distribution of sentiment category, d is the input comment text, Φ(d) represents the vector representation of the text, W, b represent the weight and bias of the sentiment classification model respectively;

[0061] And use the LDA model to perform topic analysis on the comments and extract potential topics, which are expressed as:

[0062]

[0063] Among them, ω represents a word, z represents a topic, θ represents the topic distribution of the document, and β represents the distribution of words in the topic.

[0064] The analysis and trend prediction of tourist behavior, as well as the extraction of emotional and thematic information from tourist comments and feedback, can enable scenic spot operators to understand tourist opinions and market trends, provide a basis for scenic spots to improve services, optimize facilities, and develop new products, and achieve scientific decision-making and refined management.

[0065] S5. Based on the analysis and prediction results of tourist behavior, provide personalized recommendations and dynamically adjust ticket prices according to real-time data; based on the analysis and prediction results of tourist behavior in step S4, use the characteristics of tourist resources and the historical behavior of tourists to make recommendations, and calculate the recommendation value through cosine similarity, which is expressed as:

[0066]

[0067] Among them, each scenic spot j is represented as a feature vector r j , the behavior vector of tourist u is x u, by calculating the similarity between tourist u and each attraction j, a recommendation list is generated for the tourist;

[0068] And for the historical behavior data of tourist u and other tourists v, collaborative filtering is used to make predictions, which can be expressed as:

[0069]

[0070] in, represents the estimated score of the recommended attraction j for tourist u, and N(u) represents the set of tourists with high behavior similarity to tourist u.

[0071] By collecting and analyzing tourist behavior data, historical data, etc., and using machine learning algorithms to build models, we can accurately grasp tourists' interests and needs, provide tourists with attraction recommendations that suit their preferences, and intelligently recommend tour routes, making tourists' tours more efficient and more in line with their personal preferences.

[0072] The ticket price is also adjusted dynamically according to the real-time data. The price adjustment model is constructed by the real-time number of tourists at the current time t, that is, the real-time tourist flow C(t) and the demand D predicted by the historical trend obtained by the prediction model in step S4, which is expressed as:

[0073] P(t)=P 0 ·(1+α·(C(t)-D))

[0074] Among them, P 0 represents the basic ticket price, α represents the setting based on historical data and the acceptable elasticity level, P(t) represents the ticket price at the current time t, if C(t)>D, it means that the demand is strong; otherwise, lowering the price will stimulate demand;

[0075] And further dynamic pricing using demand elasticity, expressed as:

[0076]

[0077] Among them, E d represents the demand elasticity coefficient, ΔQ represents the change in demand, Q represents the original demand, ΔP represents the change in price, that is, the increase or decrease in ticket prices, and P represents the original price, that is, the ticket price before the demand changes; when E d Less than -1, the price needs to be reduced to stimulate demand. d If E is greater than 0, the price can be raised and the income can be increased. d If it is close to 0, the price change has little effect on the demand, so do not adjust the price.

[0078] A price adjustment model is built based on real-time tourist flow and predicted demand, and dynamic pricing is combined with demand elasticity. When demand is strong, prices are appropriately raised, and when demand is insufficient, prices are reduced to stimulate, maximizing scenic spot revenue and improving resource utilization efficiency.

[0079] S6. Use virtual reality (VR) and augmented reality (AR) technologies to build virtual experience applications including virtual scenic spots, digital cultural relics exhibitions, and immersive cultural and tourism performances. Through 3D modeling, scene rendering, interactive design and other technical means, create immersive cultural and tourism experience scenes for tourists, and enhance tourists' interest and participation in the tour.

[0080] S7. Develop mobile APPs and mini-programs to provide tourists with smart tour guide services including real-time positioning, voice explanations, intelligent recommended tour routes, scenic spot introductions, and surrounding service inquiries. It supports multi-language versions to meet the needs of tourists from different countries and regions. And based on the results of big data analysis, it can carry out functions such as precise advertising, personalized recommendations, member management, and marketing activity planning and execution. Connect with major social media platforms, tourism e-commerce platforms, etc., expand the publicity and promotion channels of cultural and tourism products, and improve marketing effects.

[0081] From the above, we can see that

[0082] Importantly, it should be noted that the construction and arrangement of the present application shown in a plurality of different exemplary embodiments are only exemplary. Although only a few embodiments are described in detail in this disclosure, it should be readily understood by those who refer to this disclosure that many modifications are possible without substantially departing from the novel teachings and advantages of the subject matter described in the application. Without departing from the scope of the present invention, other replacements, modifications, changes and omissions may be made in the design, operating conditions and arrangement of the exemplary embodiments. Therefore, the present invention is not limited to specific embodiments, but extends to a variety of modifications still falling within the scope of the appended claims.

[0083] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those that are not relevant to implementing the invention) may not be described.

[0084] It should be understood that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but for those of ordinary skill having the benefit of this disclosure, without undue experimentation, the development effort will be a routine task of design, fabrication, and production.

[0085] 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 preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for constructing a digitalized cultural and tourism integrated ecosystem, characterized in that: The following steps are involved: S1. Comprehensively sort out various cultural and tourism resources in the region, clarify the characteristics, distribution and protection status of the resources, and form a list of cultural and tourism resources; S2. Collect tourists’ behavior data and social platform feedback information, and integrate historical data, including tourist flow, consumption records, and weather data; S3, using cloud computing platforms to store and manage large-scale data and perform data preprocessing; S4. Apply machine learning algorithms to analyze tourist behavior and trend prediction, analyze tourist comments and feedback through natural language processing technology, and extract sentiment and topic information; S5. Provide personalized recommendations based on tourist behavior analysis and prediction results, and dynamically adjust ticket prices based on real-time data; S6. Use virtual reality (VR) and augmented reality (AR) technologies to build virtual experience applications including virtual scenic spots, digital cultural relics exhibitions, and immersive cultural tourism performances; S7. Build mobile APPs and mini-programs to provide tourists with smart tour guide services including real-time positioning, voice explanations, intelligent recommended tour routes, attraction introductions, and surrounding service inquiries.

2. A method for constructing a digital and intelligent cultural and tourism integrated ecosystem as claimed in claim 1, characterized in that: In step S1, the various cultural and tourism resources in the region include natural landscapes, historical and cultural relics, and folk customs in the region; based on the resource list, 3D scanning and drone technology are used to digitally model the cultural and tourism resources to form digital assets.

3. A method for constructing a digital and intelligent cultural and tourism integrated ecosystem as claimed in claim 1, characterized in that: Step S4 extracts features based on the cultural and tourism resource list R, tourist behavior data B, social platform feedback T, historical traffic data F, consumption records C and weather data W to obtain tourist behavior features f b , time characteristics f t 、Environmental characteristics e and social feedback features f s , construct the feature vector X = [f b ,f t ,f e ,f s ], a linear regression model is used to predict tourist flow, expressed as: in, represents the predicted tourist flow, β0 represents the bias term, and β1, β2, β3, and β4 represent the corresponding feature weights; And time series analysis is used to predict the future trend of tourist flow, which is expressed as: Among them, y t Represents the past tourist flow data, sequence y t-k ,y t-k ,...,y t represents the continuous observations from time tk to time t, k represents the size of the historical data window, which is used to predict the future value y t+1 The number of past observations of Represents the observation value at time t+1.

4. A method for constructing a digital and intelligent cultural and tourism integrated ecosystem as claimed in claim 3, characterized in that: The step S4 also analyzes the tourists' comments and feedback by natural language processing technology, extracts comments from the tourists' social platform feedback data T, performs word segmentation, removes stop words and stems the text, converts it into a vector representation, and uses a sentiment classification model to perform sentiment analysis on the comments. The output of the sentiment analysis classifies the comments into positive, negative or neutral, which is represented as: in, is the probability distribution of sentiment category, d is the input comment text, Φ(d) represents the vector representation of the text, W, b represent the weight and bias of the sentiment classification model respectively; And use the LDA model to perform topic analysis on the comments and extract potential topics, which are expressed as: Among them, ω represents a word, z represents a topic, θ represents the topic distribution of the document, and β represents the distribution of words in the topic.

5. A method for constructing a digital and intelligent cultural and tourism integrated ecosystem as claimed in claim 1, characterized in that: In step S5, based on the analysis and prediction results of tourist behavior in step S4, the characteristics of tourist resources and the historical behavior of tourists are used to make recommendations, and the recommendation value is calculated by cosine similarity, which is expressed as: Among them, each scenic spot j is represented as a feature vector r j , the behavior vector of tourist u is x u , by calculating the similarity between tourist u and each attraction j, a recommendation list is generated for the tourist; And for the historical behavior data of tourist u and other tourists v, collaborative filtering is used to make predictions, which can be expressed as: in, represents the estimated score of the recommended attraction j for tourist u, and N(u) represents the set of tourists with high behavior similarity to tourist u.

6. A method for constructing a digitalized cultural and tourism integrated ecosystem as claimed in claim 5, characterized in that: The step S5 also dynamically adjusts the ticket price according to the real-time data, and constructs a price adjustment model based on the real-time number of tourists at the current time t, that is, the real-time tourist flow C(t) and the demand D predicted by the historical trend obtained by the prediction model in step S4, which is expressed as: P(t)=P0·(1+α·(C(t)-D)) Among them, P0 represents the set basic ticket price, α represents the setting based on historical data and the acceptable elasticity level, P(t) represents the ticket price at the current time t, if C(t)>D, it means that the demand is strong; otherwise, lowering the price will stimulate demand; And further dynamic pricing using demand elasticity, expressed as: Among them, E d represents the demand elasticity coefficient, ΔQ represents the change in demand, Q represents the original demand, ΔP represents the change in price, that is, the increase or decrease in ticket prices, and P represents the original price, that is, the ticket price before the demand changes.

Images