Trout data classification cataloguing system

Abstract

The invention discloses a text travel data classification cataloguing system, and relates to the technical field of text travel data processing, a data collection module is used for collecting online feedback information of tourists on a tourist destination image and tourist experience, and the collected feedback information is preprocessed and sorted into a first data set, a second data set and a third data set; generating a maximum forward feedback value and a maximum forward feedback ratio through a data processing module; if the elements corresponding to the maximum forward feedback value and the maximum forward feedback ratio correspond to the same element, the element is set as a main element; calculating an element corresponding to the highest correlation degree value except the main element associated with the main element through a correlation degree analysis module, and setting the element as a secondary element; whether the secondary elements need to be adjusted or not is judged through the correlation degree verification module, targeted popularization is carried out with the main elements and the secondary elements as the characteristics of a tourism place, and a correct marketing strategy can be made conveniently.

Description

Technical Field

[0001] The present invention relates to the technical field of cultural and tourism data processing, and in particular to a cultural and tourism data classification and cataloguing system. Background Art

[0002] Cultural tourism is a kind of tourism that takes participation in cultural activities, pursuit of cultural celebrities or appreciation of foreign cultures as its main purpose. It emphasizes experiencing and feeling different cultures through tourism, and meets tourists' diverse cultural needs. Cultural tourism has various forms, and its development is of great significance to promoting local economy, protecting and inheriting cultural heritage, and enhancing local image and popularity. However, cultural tourism attractions generally have insufficient understanding of tourists' needs, and are unable to provide services and facilities that meet tourists' needs; they are unable to reasonably plan the resource allocation of attractions, resulting in waste or shortage of resources; it is difficult to formulate reasonable marketing strategies, and they are unable to attract more tourists; they are unable to timely discover and solve the problems existing in attractions, which affects tourists' experience and satisfaction. Therefore, it is very important to conduct a comprehensive analysis of cultural tourism attractions, which can help attractions better understand tourists' needs, optimize resource allocation, formulate marketing strategies, and improve tourists' experience and satisfaction, so as to achieve sustainable development.

[0003] To solve the above problems, the present invention combines tourists' online text comments, videos, and audio feedback on the image of tourist destinations and tourist experiences, comprehensively analyzes the multimodal data of the six elements of tourism consumption, namely, food, accommodation, transportation, sightseeing, shopping, and entertainment, and takes the main elements as the basis for enhancing tourists' experience. It proposes a new path for the integrated development of culture and tourism in tourist attractions that promotes the innovative development of the integration of culture and tourism with the six elements of tourism consumption and uses the main elements as the carrier to create a living cultural and tourism consumption scene. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a cultural and tourism data classification and cataloguing system, which solves the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a cultural and tourism data classification and cataloguing system, the system comprising: The data collection module is used to collect tourists' online feedback information on the image of the tourist destination and the tourist experience, including text comment information, voice comment information, and video comment information, and pre-process the collected feedback information and organize it into the first data set, the second data set, and the third data set; The data processing module is used to classify and integrate the first data set, the second data set, and the third data set that have been sorted, and generate a maximum positive feedback value Zmax and a maximum positive feedback ratio Fmax; If the corresponding elements of the maximum positive feedback value Zmax and the maximum positive feedback ratio Fmax correspond to the same element, then the element is set as the main element, otherwise, it is not set as the main element; The correlation analysis module is used to receive the main element, and based on the main element, calculate the correlation value G of each element other than the main element associated with the main element, and set the element corresponding to the highest correlation value Gmax as the secondary element; The correlation verification module is used to compare and verify the maximum correlation value Gmax with the actual correlation values ​​of each element except the main element, so as to determine whether the secondary element needs to be adjusted.

[0006] Preferably, the collection of tourists' online feedback information on the image of the tourist destination and the tourist experience is obtained through online survey tools, social media monitoring tools and data analysis tools.

[0007] Preferably, the preprocessing of the collected feedback information includes preprocessing of the text comment information, the voice comment information, and the video comment information; The text comment information is preprocessed by using natural language processing (NLP) tools and techniques to classify, perform sentiment analysis, extract keywords, and perform text clustering on the text comment information to form a first data set; the voice comment information and the video comment information are preprocessed by first using the iFlytek Voice Recorder tool to convert the voice comment information and the video comment information into text information, and then using natural language processing (NLP) tools and techniques to classify, perform sentiment analysis, extract keywords, and perform text clustering on the text information to form a second data set and a third data set.

[0008] Preferably, the first data set, the second data set, and the third data set that have been sorted out are classified and integrated, specifically, the first data set, the second data set, and the third data set are integrated according to the positive feedback of the six elements of "food, clothing, housing, transportation, shopping, and entertainment", and the first subset a and the first subset positive feedback unit a1 are obtained respectively; the second subset b and the second subset positive feedback unit b1; the third subset c and the third subset positive feedback unit c1; the fourth subset d and the fourth subset positive feedback unit d1; the fifth subset e and the fifth subset positive feedback unit e1; the sixth subset f and the sixth subset positive feedback unit f1; The maximum positive feedback value Zmax=max(a1,b1,c1,d1,e1,f1); The maximum positive feedback ratio Fmax=max[a1 / a, b1 / b, c1 / c, d1 / d, e1 / e, f1 / f].

[0009] Preferably, based on the main elements, the element corresponding to the highest correlation value Gmax is deduced as the secondary element. Specifically, the point mutual information method is used to calculate the degree of correlation with the main element. The calculation formula of Gmax is: Gmax = max[log(P(x, yi) / (P(x) * P(yi))] Wherein, P(x, yi) represents the probability that the main element x and the i-th element y appear simultaneously, and P(x) and P(yi) respectively represent the probabilities that the main element x and the i-th element y appear alone.

[0010] Preferably, P(x, yi) represents the probability that the main element x and the i-th element y appear simultaneously, and P(x) and P(yi) respectively represent the probabilities that the main element x and the i-th element yi appear alone. Specifically; The calculation formula of P(x, yi) is: P(x, yi) = T(x, yi) / (a + b + c + d + e + f) Wherein T(x, yi) is the number of information containing both the main element x and the i-th element y; The calculation formula of P(x) is: P(x) = T(x) / (a + b + c + d + e + f) Wherein T(x) is the number of information containing the main element x; The calculation formula of P(yi) is: P(yi) = T(yi) / (a + b + c + d + e + f) Wherein T(yi) is the number of information containing the i-th element y.

[0011] Preferably, the highest correlation value Gmax is compared and verified with the correlation values of each element other than the main element that actually occurs. The specific method is: collect the feedback information of tourists on the tourism destination image and tourism experience online within N effective unit times M, where N is an odd number greater than 3. Based on the main element, calculate the highest correlation value Wmax of each element other than the main element; If within more than N / 2 effective unit times M, Wmax ≥ Gmax, the secondary element is not adjusted; If within more than N / 2 effective unit times M, Wmax < Gmax, the secondary element is adjusted.

[0012] The present invention provides a cultural and tourism data classification and cataloging system, which has the following beneficial effects: (1) Through the analysis of tourists' online feedback information, the system can understand the needs and preferences of tourists for the six elements of "eating, dressing, living, traveling, shopping, and entertainment", so as to reasonably plan the resource allocation of scenic spots and avoid resource waste or shortage.

[0013] (2) The system can promptly identify tourists’ needs and problems, and compare and verify the highest correlation value with the actual correlation values ​​of each factor to determine whether the secondary factors need to be adjusted. This helps scenic spot managers to adjust service strategies in a timely manner, improve service quality, and increase tourists’ satisfaction.

[0014] (3) Based on the main elements, the system calculates the correlation values ​​of the elements other than the main elements, and sets the element with the highest correlation value as the secondary element. This can help scenic spot managers better understand tourists' needs and behaviors, formulate more accurate marketing strategies, and attract more tourists.

[0015] (4) The system can comprehensively analyze the multimodal data of the six elements of tourism consumption, namely, food, accommodation, transportation, sightseeing, shopping and entertainment, and propose a new path for the integration of culture and tourism in tourist attractions, which is to promote the innovative development of the integration of culture and tourism with the six elements of tourism consumption and to create a living cultural and tourism consumption scene with the main elements as the carrier. This will help promote the integration of culture and tourism and enhance the attractiveness and competitiveness of tourist destinations. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a schematic diagram of the framework structure of a cultural and tourism data classification and cataloging system of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example

[0018] See also Figure 1 The present invention provides a cultural and tourism data classification and cataloguing system, comprising The data collection module is used to collect tourists' online feedback information on the image of the tourist destination and the tourist experience, including text comment information, voice comment information, and video comment information, and pre-process the collected feedback information and organize it into the first data set, the second data set, and the third data set.

[0019] The data processing module is used to classify and integrate the sorted first data set, second data set and third data set to generate a maximum positive feedback value Zmax and a maximum positive feedback ratio Fmax.

[0020] If the elements corresponding to the maximum positive feedback value Zmax and the maximum positive feedback ratio Fmax correspond to the same element, then the element is set as the main element, otherwise, it is not set as the main element.

[0021] The correlation analysis module is used to receive the main element, and based on the main element, deduce the correlation value G of each element associated with the main element except the main element, and set the element corresponding to the highest correlation value Gmax as the secondary element.

[0022] The correlation verification module is used to compare and verify the maximum correlation value Gmax with the actual correlation values ​​of each element except the main element, so as to determine whether the secondary element needs to be adjusted.

[0023] In this embodiment, data is collected through a data collection module. This module not only collects online feedback information from tourists, but also pre-processes this information for subsequent analysis and processing. The pre-processing steps include data cleaning, deduplication, format conversion, etc. to ensure the accuracy and consistency of the data.

[0024] The main function of the data processing module is to classify and integrate the pre-processed data to generate the maximum positive feedback value and the maximum positive feedback ratio. These indicators can help the system determine which elements have the greatest positive impact on the tourists' experience.

[0025] The correlation analysis module determines the secondary factors based on the primary factors by calculating the correlation values ​​of other factors associated with the primary factors. This helps the system to gain a deeper understanding of the relationship between the factors and provide a basis for subsequent decision-making.

[0026] The function of the correlation verification module is to compare and verify the calculated highest correlation value with the actual correlation values ​​of each factor. This step can ensure that the analysis results of the system are consistent with the actual situation, thereby improving the accuracy and reliability of decision-making.

[0027] In this embodiment, through the collaborative work of the above modules, the cultural and tourism data classification and cataloging system can comprehensively and accurately analyze tourists' online feedback information, determine the main and secondary factors, and perform correlation analysis and verification on these factors, which helps tourism destination managers to better understand tourists' needs and behaviors, optimize resource allocation, formulate marketing strategies, improve tourists' experience and satisfaction, and thus achieve sustainable development.

[0028] In addition, in order to ensure efficient operation and accurate analysis of the system, data storage, management, update and other modules, as well as user interface, permission management and other functions can be added to the system to improve the system's usability and security. At the same time, the system can also be integrated with other related systems, such as tourism destination management systems, marketing systems, etc., to achieve data sharing and interaction, and further enhance the value and role of the system. Example

[0029] This embodiment is explained in Example 1, please refer to Figure 1 Specifically: the feedback information collected from tourists on the image of the tourist destination and the tourist experience is obtained through online survey tools, social media monitoring tools and data analysis tools.

[0030] Online survey tools: Tourist feedback can be collected through online questionnaires, polls, etc. These tools can be posted on tourism websites, social media platforms or dedicated survey platforms, where tourists can fill in their evaluations of the image and experience of the tourist destination.

[0031] Social Media Listening Tools: Leverage user-generated content (UGC) on social media platforms to gain feedback from tourists. Social media listening tools can be used to monitor and analyze topics, tags, or keywords related to the tourist destination to understand tourists’ opinions and experiences.

[0032] Data analysis tools: Use data analysis tools to mine and analyze data related to tourist destinations. These tools can analyze website traffic, user behavior, comment data, etc. to obtain feedback information about tourists' image and experience of tourist destinations.

[0033] In this embodiment, by using these tools, the cultural and tourism data classification and cataloging system can collect tourists' online feedback information comprehensively and in real time, providing strong support for subsequent data analysis and decision-making. At the same time, the use of these tools also helps to improve the accuracy and reliability of the data, and provide more valuable references for the management and development of tourist destinations. In addition, in order to ensure the legality, security and privacy of the data, appropriate security measures must be taken when using these tools to protect tourists' personal information. At the same time, the collected feedback information can be further screened and verified in combination with manual review and verification to improve the quality and credibility of the data. Example

[0034] This embodiment is explained in Example 1, please refer to Figure 1 Specifically: the preprocessing of the collected feedback information includes preprocessing of the text comment information, the voice comment information, and the video comment information.

[0035] The text comment information is preprocessed by using natural language processing (NLP) tools and techniques to classify, perform sentiment analysis, extract keywords, and perform text clustering on the text comment information to form a first data set; the voice comment information and the video comment information are preprocessed by first using the iFlytek Voice Recorder tool to convert the voice comment information and the video comment information into text information, and then using natural language processing (NLP) tools and techniques to classify, perform sentiment analysis, extract keywords, and perform text clustering on the text information to form a second data set and a third data set.

[0036] For text review information, natural language processing (NLP) tools and techniques are used for processing. NLP can help classify text review information, such as classifying reviews into positive, negative or neutral. Sentiment analysis can determine the emotional tendency of reviews, such as happiness, dissatisfaction or disappointment. Keyword extraction can identify important words or topics mentioned in the reviews. Text clustering processing can group similar reviews together for better understanding and analysis.

[0037] For voice comment information and video comment information, you first need to use the iFlytek voice recorder tool to convert it into text information. Then, you can also use NLP tools and technologies to classify, analyze sentiment, extract keywords and cluster text after the conversion.

[0038] In this embodiment, by preprocessing the collected feedback information, different types of information can be converted into a unified format, and valuable information can be extracted to provide a basis for the classification and cataloging of cultural and tourism data. This can better understand the needs and opinions of tourists and provide targeted decision-making basis for the management and development of tourist destinations. Example

[0039] This embodiment is an explanation of Embodiment 3. Specifically, the first data set, the second data set, and the third data set that have been sorted are classified and integrated. Specifically, the first data set, the second data set, and the third data set are integrated according to the positive feedback of the six elements of "food, clothing, housing, transportation, shopping, and entertainment", and the first subset a and the first subset positive feedback unit a1 are obtained respectively; the second subset b and the second subset positive feedback unit b1 are obtained respectively; the third subset c and the third subset positive feedback unit c1 are obtained respectively; the fourth subset d and the fourth subset positive feedback unit d1 are obtained respectively; the fifth subset e and the fifth subset positive feedback unit e1 are obtained respectively; the sixth subset f and the sixth subset positive feedback unit f1 are obtained respectively.

[0040] The maximum positive feedback value Zmax=max(a1,b1,c1,d1,e1,f1); The maximum positive feedback ratio Fmax=max[a1 / a, b1 / b, c1 / c, d1 / d, e1 / e, f1 / f].

[0041] The first, second and third data sets that have been sorted out are classified and integrated according to the six elements of "food, clothing, housing, transportation, shopping and entertainment", which means that the information related to these six elements in the data set is extracted separately to form six subsets.

[0042] For each subset, the positive feedback is further analyzed. Positive feedback can be understood as tourists' positive evaluation or satisfaction with a certain element. By calculating the positive feedback units of each subset, the tourists' satisfaction with each element can be determined.

[0043] The maximum positive feedback value Zmax and the maximum positive feedback ratio Fmax are calculated. The maximum positive feedback value represents the maximum value of the positive feedback unit in all subsets, and the maximum positive feedback ratio represents the maximum value of the ratio of the positive feedback unit of each subset to the total feedback unit of the subset.

[0044] In this embodiment, by analyzing the maximum positive feedback value and the maximum positive feedback ratio, it can be understood which of the six elements of "food, clothing, housing, transportation, shopping, and entertainment" has obtained the highest tourist satisfaction, and which subset has the highest positive feedback ratio. This information can provide targeted guidance for the management and improvement of tourist destinations. For example, the elements that need to be focused on and improved can be determined based on the maximum positive feedback ratio to improve the overall satisfaction of tourists. Example

[0045] This embodiment is an explanation of the embodiment 4. Specifically, based on the main elements, the element corresponding to the highest correlation value Gmax is deduced as the secondary element. Specifically, the point mutual information method is used to calculate the correlation degree between the main elements. The calculation formula of Gmax is: Gmax=max[log(P(x,yi) / (P(x) * P(yi))] Among them, P(x,yi) represents the probability of the main element x and the i-th element y appearing at the same time, and P(x) and P(yi) represent the probability of the main element x and the i-th element y appearing alone, respectively.

[0046] In Example 4, the main factors have been determined. By calculating the degree of association with the main factors, the maximum correlation value Gmax is found, and the point mutual information method is used to calculate the degree of association. The point mutual information is a statistical indicator that measures the degree of mutual dependence between two variables. The factor corresponding to the maximum correlation value Gmax is determined as a secondary factor, which means that the factor has the highest correlation with the main factor.

[0047] In this embodiment, in this way, the secondary factors with the highest correlation with the main factors can be determined. These secondary factors can provide more information about tourists' needs and behaviors, helping tourist destinations to better understand tourists' interests and preferences, so as to make more targeted planning and decisions. It should be noted that the point mutual information method is a commonly used method for calculating correlation, but in actual applications, other methods and factors can also be considered to comprehensively determine the secondary factors. In addition, the quality and accuracy of the data are also very important for the reliability of the results. Example

[0048] This embodiment is explained in Embodiment 5. Specifically, P(x,yi) represents the probability of the main element x and the i-th element y appearing at the same time, and P(x) and P(yi) represent the probability of the main element x and the i-th element yi appearing alone, respectively. Specifically, The calculation formula of P(x,yi) is: P(x,yi)=T(x,yi) / (a+b+c+d+e+f) Where T(x,yi) is the number of information containing both the main element x and the i-th element y; The calculation formula of P(x) is: P(x)=T(x) / (a+b+c+d+e+f) Where T(x) is the amount of information containing the main element x; The calculation formula of P(yi) is: P(yi)=T(yi) / (a+b+c+d+e+f) Where T(yi) is the amount of information contained in the i-th element y.

[0049] In this cultural and tourism data classification and cataloging system, by calculating the probability P(x, y) that the main element x and the i-th element y appear at the same time, the probability P(x) that the main element x appears alone, and the probability P(y) that the i-th element y appears alone, the degree of association between them can be determined more accurately.

[0050] In this embodiment, through these formulas, the degree of association between the main elements and each element can be calculated, and the secondary element with the highest degree of association can be found. These calculation results can help the cultural and tourism data classification and cataloging system better understand and utilize cultural and tourism data, and provide more targeted services and decision-making support. Embodiment

[0051] This embodiment is an explanatory description based on Embodiment 1. See the appendix Figure 1 Specifically: comparing and verifying the highest degree of association value Gmax with the degree of association values of each element other than the main element that actually occurs. The specific method is as follows: collect the feedback information of tourists online on the image of the tourist destination and the tourism experience within N effective unit times M, where N is an odd number greater than 3. Based on the main element, calculate the highest degree of association value Wmax of each element other than the main element; If within more than N / 2 effective unit times M, Wmax ≥ Gmax, then the secondary elements are not adjusted; If within more than N / 2 effective unit times M, Wmax < Gmax, then the secondary elements are adjusted.

[0052] In Embodiment 1, it is mentioned that the feedback information of tourists online on the image of the tourist destination and the tourism experience is collected. In this embodiment, it is further explained that the feedback information within N effective unit times M needs to be collected, where N is an odd number greater than 3.

[0053] Based on the main element, calculate the highest degree of association value Wmax of each element other than the main element, Compare and verify the calculated highest degree of association value Wmax with the degree of association values of each element other than the main element that actually occurs.

[0054] If within more than N / 2 effective unit times M, Wmax is less than Gmax, then the secondary elements need to be adjusted, which means that the originally determined secondary elements may need to be re-evaluated and adjusted to more accurately reflect the needs and behaviors of tourists; if within more than N / 2 effective unit times M, Wmax is greater than or equal to Gmax, then the secondary elements do not need to be adjusted, which means that the originally determined secondary elements are still valid and can continue to be used as the basis for analysis and decision-making.

[0055] In this embodiment, through this method of comparison and verification, the determination of secondary elements can be continuously optimized and adjusted to improve the accuracy and reliability of the cultural and tourism data classification and cataloging system. At the same time, problems can be discovered and solved in a timely manner based on the feedback information of tourists, providing a better tourism experience and service.

[0056] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A cultural and tourism data classification and cataloguing system, characterized in that: The system comprises: The data collection module is used to collect tourists' online feedback information on the image of the tourist destination and the tourist experience, including text comment information, voice comment information, and video comment information, and pre-process the collected feedback information and organize it into the first data set, the second data set, and the third data set; The data processing module is used to classify and integrate the first data set, the second data set, and the third data set that have been sorted, and generate a maximum positive feedback value Zmax and a maximum positive feedback ratio Fmax; If the corresponding elements of the maximum positive feedback value Zmax and the maximum positive feedback ratio Fmax correspond to the same element, then the element is set as the main element, otherwise, it is not set as the main element; The correlation analysis module is used to receive the main element, and based on the main element, calculate the correlation value G of each element other than the main element associated with the main element, and set the element corresponding to the highest correlation value Gmax as the secondary element; The correlation verification module is used to compare and verify the maximum correlation value Gmax with the actual correlation values ​​of each element except the main element, so as to determine whether the secondary element needs to be adjusted.

2. A cultural and tourism data classification and cataloguing system according to claim 1, characterized in that: The feedback information collected from tourists on the image of the tourist destination and the tourist experience is obtained through online survey tools, social media monitoring tools and data analysis tools.

3. A cultural and tourism data classification and cataloguing system according to claim 1, characterized in that: The preprocessing of the collected feedback information includes preprocessing the text comment information, the voice comment information, and the video comment information; The text comment information is preprocessed by using natural language processing (NLP) tools and techniques to classify, perform sentiment analysis, extract keywords, and perform text clustering on the text comment information to form a first data set; the voice comment information and the video comment information are preprocessed by first using the iFlytek Voice Recorder tool to convert the voice comment information and the video comment information into text information, and then using natural language processing (NLP) tools and techniques to classify, perform sentiment analysis, extract keywords, and perform text clustering on the text information to form a second data set and a third data set.

4. A cultural and tourism data classification and cataloguing system according to claim 3, characterized in that: The first data set, the second data set, and the third data set that have been sorted out are classified and integrated, specifically, the first data set, the second data set, and the third data set are integrated according to the positive feedback of the six elements of "food, clothing, housing, transportation, shopping, and entertainment", and the first subset a and the first subset positive feedback unit a1 are obtained respectively; the second subset b and the second subset positive feedback unit b1; the third subset c and the third subset positive feedback unit c1; the fourth subset d and the fourth subset positive feedback unit d1; the fifth subset e and the fifth subset positive feedback unit e1; the sixth subset f and the sixth subset positive feedback unit f1; The maximum positive feedback value Zmax=max(a1,b1,c1,d1,e1,f1); The maximum positive feedback ratio Fmax=max[a1 / a, b1 / b, c1 / c, d1 / d, e1 / e, f1 / f].

5. A cultural and tourism data classification and cataloguing system according to claim 4, characterized in that: Based on the said main elements, the element corresponding to the highest correlation degree value Gmax is deduced as the secondary element. Specifically, the point mutual information method is used to calculate the correlation degree with the main element. The calculation formula of Gmax is as follows: Gmax=max[log(P(x,y i ) / (P(x) * P(y i ))] Among them, P(x,y i ) represents the probability of the main element x and the i-th element y appearing at the same time, P(x) and P(y i ) represent the probability of the main factor x and the i-th factor y appearing alone.

6. A cultural and tourism data classification and cataloguing system according to claim 5, characterized in that: The P(x,y i ) represents the probability of the main element x and the i-th element y appearing at the same time, P(x) and P(y i ) represent the main element x and the i-th element y respectively i The probability of occurrence alone, specifically; The P(x,y i ) is calculated as: P(x,y i ) = T(x,y i ) / (a+b+c+d+e+f) Where T(x,y i ) is the amount of information that contains both the main element x and the i-th element y; The calculation formula of the said P(x) is: P(x)=T(x) / (a + b + c + d + e + f) where T(x) is the number of information containing the main element x; The P(y i ) is calculated as: P(y i ) = T (y i ) / (a+b+c+d+e+f) Where T(y i ) is the amount of information contained in the i-th element y.

7. A cultural and tourism data classification and cataloguing system according to claim 1, characterized in that: The highest correlation degree value Gmax is compared and verified with the correlation degree values of each element other than the said main element that actually occurs. The specific method is as follows: Collect the feedback information of tourists online on the tourism destination image and tourism experience within N effective unit times M, where N is an odd number greater than 3. Based on the said main element, calculate the highest correlation degree value Wmax of each element other than the said main element; If within more than N / 2 effective unit times M, Wmax≥Gmax, then the secondary element is not adjusted; If within more than N / 2 effective unit times M, Wmax<Gmax, then the secondary element is adjusted.

Images