An evaluation method for natural landscape cultural tourism development

Abstract

A method for evaluating the development of natural landscape cultural tourism, which relates to the field of data processing, comprises the following steps: S1, collecting the natural geographical information of the scenic area, and restoring and reproducing it in a virtual space; S2, transforming and modeling different cultural tourism development design schemes in a virtual space, and obtaining 3D results of different designs; S3, designing related interactive functions for different design schemes; S4, inviting users to use VR equipment to test and experience different designs, and collecting multiple test data of users during the experience process; S5, analyzing the data set to obtain a principal component score matrix; S6, calculating the total scores of different design schemes. The method for evaluating the development of natural landscape cultural tourism provided by the present invention can combine the design scheme of cultural tourism development with VR technology, collect and analyze the test data of users while users experience different design schemes, thereby realizing quantitative evaluation of the design schemes.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to an evaluation method for natural landscape cultural tourism development. Background Art

[0002] The cultural tourism development of natural landscapes generally requires huge investment in manpower, material resources and financial resources. Therefore, before investing in development work, it is necessary to ensure the rationality of the design plan, especially to understand whether the design plan can bring more pleasant or shocking feelings to tourists, which also determines the actual value of cultural tourism development. Therefore, before development, it is necessary to conduct a scientific and comprehensive evaluation of the cultural tourism development design plan. In the past, design plans were mainly presented using pictures, texts, etc., which were not intuitive enough and could not give the evaluators an immersive feeling; at the same time, the evaluation of the design was generally an abstract description, without a quantitative and objective data presentation.

[0003] Virtual reality technology (VR technology) encompasses computers, electronic information, and simulation technology. Its basic implementation method is based on computer technology, utilizing and integrating the latest developments in three-dimensional graphics technology, multimedia technology, simulation technology, display technology, servo technology, and other high-tech technologies. With the help of computers and other equipment, it creates a realistic three-dimensional virtual world with multiple sensory experiences such as vision, touch, and smell, thereby giving people in the virtual world an immersive feeling.

[0004] Therefore, different design schemes can be moved into the virtual space, and VR technology can be used at the same time to make the experiencer feel immersive about the cultural tourism design scheme. On this basis, the design scheme needs to be evaluated objectively and quantitatively. Therefore, a quantitative evaluation method is needed for cultural tourism development design schemes of natural landscapes. The present invention solves this technical problem. Summary of the invention

[0005] The present invention provides an evaluation method for natural landscape cultural tourism development, which can combine the design scheme of cultural tourism development with VR technology. While users experience different design schemes, the user's test data is collected and analyzed, so that the design scheme can be quantitatively evaluated according to the results, making the evaluation result more scientific.

[0006] A method for evaluating natural landscape cultural tourism development, comprising the following steps: S1. Collect the natural geographical information of the scenic area and restore it in the virtual space; S2. For different cultural tourism development design schemes, transformation and modeling are carried out in virtual space to obtain 3D results of different designs; S3. Design relevant interactive functions for different design schemes for subsequent VR device testing; S4. Invite users to use VR devices to test different designs, and collect multiple test data of users during the experience process to obtain a data set, each of which represents different features; S5. Analyze the data set to obtain the principal component score matrix of the design scheme; S6. Calculate the total scores of different design solutions based on the principal component score matrix of different design solutions.

[0007] Furthermore, the step S5 includes the following steps: S51, cleaning the test data; S52, performing standardization processing on the cleaned data, and constructing the processed data into a data matrix; S53, calculating the covariance matrix of the data matrix; S54, solving the eigenvalues ​​and corresponding eigenvectors of the covariance matrix; S55. Perform dimensionality reduction processing on the data matrix to obtain a principal component score matrix.

[0008] Furthermore, the step S51 includes the following steps: S511, identifying missing values ​​in the data set, and filling the missing values ​​with the mean of this data; S512. Use the Z-Score method to detect outliers. The formula is as follows: , Among them, Z represents Z-Score, X represents the data value to be tested, μ represents the mean of the data set, and σ is the standard deviation of this data; S513. When the absolute value of Z-scored is greater than or equal to the set value, the data value will be determined as an abnormal value, and the abnormal value needs to be replaced by the mean value of this data.

[0009] Further, the step S52 includes the following steps: S521. Establish standardized formula: , Among them, x represents the original value of a certain data. represents the mean value of this data, σ represents the standard deviation of this data, is the eigenvalue after standardization; S522, calculating the test data using a standardized formula to obtain standardized data, i.e., eigenvalues; S523, constructing the standardized data into a data matrix.

[0010] Furthermore, the step S53 includes the following steps: S531. Calculate the covariance matrix of the data matrix using the following formula: , Among them, X and Y represent two standardized data respectively. is the value of feature X, is the mean of feature X, is the value of feature Y, is the mean of feature Y; S532, calculating the standardized data pairwise using the above formula to obtain the covariance matrix of the data.

[0011] Further, the step S54 includes the following steps: S541. Construct the eigenvalue equation: , Where A represents the covariance matrix, det represents the determinant of the covariance matrix, λ is the eigenvalue, and I is the unit matrix of the same order as A; S542, calculating multiple eigenvalues ​​λ of the covariance matrix by the above formula; S543, substitute each eigenvalue λ into the following equation: , Get the system of equations, solve them and get the eigenvector v.

[0012] Furthermore, the step S55 includes the following steps: S551, select k eigenvectors as principal components; S552. Combine the k eigenvectors into a new matrix, namely the projection matrix: , Each eigenvector is a column vector; S553. The above eigenvectors are arranged according to the magnitude of their corresponding eigenvalues; S554. Multiply the normalized data matrix by the projection matrix to obtain the reduced-dimensional data, i.e., the principal component score matrix.

[0013] Further, the step S6 includes the following steps: S61, calculate the load of the principal component; S62. Analyze the significance of the principal components based on the loads, and determine the weight of each principal component in the further evaluation score based on the actual situation. ; S63, expressing the principal component score matrix as: ; S64. According to the principal component score matrix and the determined weights, the total score of the design solution is calculated by the following formula: .

[0014] The technical effects of the present invention are as follows: (1) This scheme can display the environment of a natural scenic spot in a virtual space, and change the environment of the scenic spot in the virtual space according to the design scheme. Then, it can collect various data of users when they experience the design scheme, and process and analyze the collected data to obtain the score of the design scheme. Therefore, it is possible to achieve quantitative evaluation of different design schemes based on the results, making the evaluation results more scientific. (2) This solution standardizes the collected data and constructs the processed data into a data matrix. The covariance matrix is ​​calculated according to the obtained data matrix. The eigenvalues ​​and corresponding eigenvectors of the covariance matrix are then solved. A part of the eigenvectors are selected to construct the principal component score matrix. Finally, the evaluation score of the design solution is calculated based on the principal component score matrix. This allows the data from different aspects to be quantified and the scores to be obtained, making the scoring more scientific. (3) This scheme can collect multiple data when users experience different design schemes of the scenic spot, ensuring the authenticity of the data and avoiding the subsequent rating being completely determined by the customer's subjective evaluation, so that the final rating has a higher reference value; (4) This scheme combines virtual reality technology to display natural landscapes in virtual space and modify them according to different design schemes. There is no need to actually change the natural landscape, which saves costs. In addition, this method can give users an immersive feeling, so that the subsequent data can reflect the feelings brought to users by the design scheme, making the scoring more reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flowchart of the present invention. DETAILED DESCRIPTION

[0016] The technical solution of the present invention will be clearly and completely described below in conjunction with specific embodiments and drawings.

[0017] See also Figure 1 , an evaluation method for natural landscape cultural tourism development, comprising the following steps: S1. Collect the natural geographical information of the scenic area and restore it in the virtual space; S2. For different cultural tourism development design schemes, transformation and modeling are carried out in virtual space to obtain 3D results of different designs; S3. Design relevant interactive functions for different design schemes for subsequent VR device testing; S4. Invite users to use VR devices to test different designs, and collect multiple test data of users during the experience process to obtain a data set, each of which represents different features; S5. Analyze the data set to obtain the principal component score matrix of the design scheme; S6. Calculate the total scores of different design solutions based on the principal component score matrix of different design solutions.

[0018] The natural geographical information of the scenic area includes topography, vegetation, hydrology, meteorology and other natural geographical information, which needs to be restored and reproduced in the virtual 3D space as realistically as possible to achieve a realistic effect. The terrain information of the natural scenic area can be modeled by collecting data through drone scanning and oblique photography. The vegetation and water systems on the surface can be modeled separately and placed in the scene according to the actual situation. The weather can be simulated through the relevant plug-ins in the corresponding 3D engine. This part is the existing technology known to those skilled in the art and will not be described in detail here.

[0019] The transformation modeling involves carrying out construction in a virtual scene based on the engineering construction design of the plan, simulating the effects that can be achieved based on the plan under real conditions, and thus transforming the environment of the scenic area in a virtual space.

[0020] Preferably, this solution can use 3D development engines such as UE and Unity to develop basic operations for experiencers, such as walking, perspective rotation and other functions. For different design schemes, develop interactive functions related to the design. On this basis, present the relevant applications on the VR device in the form of packaging or streaming. For interactive functions, including basic functions such as walking and perspective rotation, there will be more personalized interaction methods according to different schemes, such as designing users to grasp and throw objects, ride vehicles, and have AI dialogues. VR functions currently have relatively mature solutions that combine various software and hardware, and the above content can be specifically implemented through existing technologies.

[0021] After the natural landscape environment is transformed in the virtual space according to different design schemes, different testers can be invited to use VR equipment to test different designs. At the same time, multiple relevant reaction data of the testers to different designs during the experience process are collected, such as a large amount of test data of different dimensions generated in different categories such as dwell time, body movements, facial expressions, physiological reactions, etc., and each category may include multiple different features. For example, there are many facial expressions that can reflect different feelings of users, so multiple data will be obtained during the test process, and each data represents different features;

[0022] The dwelling time can be obtained by timing the time spent in scenic spots with different designs. The longer the time spent in the scenic spot, the longer the recorded dwelling time. Body movements and facial expressions can be obtained through motion capture devices and facial capture devices. Physiological reactions such as the user's heart rate, blood pressure, and breathing can be obtained through professional medical collection equipment. As long as the corresponding data can be collected, the specific equipment used can be selected based on the common knowledge of technicians in this field and the actual situation.

[0023] Since a large amount of data of different dimensions is generated in the above content, and the data may reflect the tester's preference for different designs more or less strongly, and there must be potential connections between different data indicators, and a large number of dimensions cannot highlight the focus of analysis, this solution selects the principal component analysis method (PCA) to process the data, where the data indicators are the test data of multiple different dimensions mentioned above.

[0024] Further, step S5 includes the following steps: S51, cleaning the test data; S52, performing standardization processing on the cleaned data, and constructing the processed data into a data matrix; S53, calculating the covariance matrix of the data matrix; S54, solving the eigenvalues ​​and corresponding eigenvectors of the covariance matrix; S55. Perform dimensionality reduction processing on the data matrix to obtain a principal component score matrix.

[0025] Further, step S51 includes the following steps: S511, identifying missing values ​​in the data set, and filling the missing values ​​with the mean of this data; S512. Use the Z-Score method to detect outliers. The formula is as follows: , Among them, Z represents Z-Score, X represents the data value to be tested, μ represents the mean of the data set, and σ is the standard deviation of this data; S513. When the absolute value of Z-scored is greater than or equal to the set value, the data value will be determined as an abnormal value, and the abnormal value needs to be replaced by the mean value of this data.

[0026] For the large amount of test data of different dimensions generated under different categories such as user dwell time, body movements, interactive behaviors, facial expressions, physiological reactions, etc., there may be problems such as unstable data quality, data noise, data duplication, etc., so data cleaning is needed. For the replacement of outliers, taking facial expressions as an example, when there are outliers among the multiple facial expression data values ​​obtained, the mean of the facial expression data needs to be used to replace the existing outliers.

[0027] Further, step S52 includes the following steps: S521. Establish standardized formula: , Among them, x represents the original value of a certain data. represents the mean value of this data, σ represents the standard deviation of this data, is the eigenvalue after standardization; S522, calculating the test data using a standardized formula to obtain standardized data, i.e., eigenvalues; S523, constructing the standardized data into a data matrix.

[0028] Since the data range and units of different indicators may be different, they need to be standardized so that the mean value of each characteristic data is 0 and the standard deviation is 1.

[0029] Further, step S53 includes the following steps: S531. Calculate the covariance matrix of the data matrix using the following formula: , Among them, X and Y represent two standardized data respectively. is the value of feature X, is the mean of feature X, is the value of feature Y, is the mean of feature Y; S532, calculating the standardized data pairwise using the above formula to obtain the covariance matrix of the data.

[0030] The resulting covariance matrix is ​​represented as follows:

[0031] Further, step S54 includes the following steps: S541. Construct the eigenvalue equation: , Where A represents the covariance matrix, det represents the determinant of the covariance matrix, λ is the eigenvalue, and I is the unit matrix of the same order as A; S542, calculating multiple eigenvalues ​​λ of the covariance matrix by the above formula; S543, substitute each eigenvalue λ into the following equation: , Get the system of equations, solve them and get the eigenvector v.

[0032] Further, step S55 includes the following steps: S551, select k eigenvectors as principal components; S552. Combine the k eigenvectors into a new matrix, namely the projection matrix: , Each eigenvector is a column vector; S553. The above eigenvectors are arranged according to the magnitude of their corresponding eigenvalues; S554. Multiply the normalized data matrix by the projection matrix to obtain the reduced-dimensional data, i.e., the principal component score matrix.

[0033] This solution can select the eigenvectors corresponding to the first few largest eigenvalues ​​as principal components according to the size of the eigenvalues. The selection can be based on whether the cumulative variance reaches a certain threshold (such as 85%) or other methods, and can be selected according to actual conditions.

[0034] And the eigenvectors in the projection matrix of this scheme are arranged in descending order according to the corresponding eigenvalues, that is, corresponding to the largest eigenvalue, corresponding to the second largest eigenvalue, and so on.

[0035] Further, step S6 includes the following steps: S61, calculate the load of the principal component; S62. Analyze the significance of the principal components based on the loads, and determine the weight of each principal component in the further evaluation score based on the actual situation. ; S63. The principal component score matrix is ​​expressed as: ; S64. According to the principal component score matrix and the determined weights, the total score of the design solution is calculated by the following formula: .

[0036] Among them, i and j represent corresponding numbers, which is a representation method known to those skilled in the art and will not be described in detail here.

[0037] Analyze the meaning of each principal component based on the load. The load represents the weight of the original variable on the principal component. The larger the load, the greater the contribution of the original data to the principal component. The positive and negative signs of the load indicate the relationship between the original data and the principal component. If the load is positive, it means that the variable is positively correlated with the principal component; if it is negative, it means negative correlation. Then, it is necessary to review the characteristics represented by each original data. The load of the original data on the principal component can reveal its importance in the data set. Then, based on the numerical size and sign of the load, try to interpret the possible meaning of each principal component. For example, if the load of the principal component is mainly composed of positive values ​​of "body movements" and "facial expressions", then this principal component may represent that the user is very interested in this design solution.

[0038] It should be noted that the above content is only exemplary. "Body movements" and "facial expressions" actually include many different features. For example, for different designs, users may have different movements and different expressions to reflect their feelings. Therefore, the staff needs to analyze the meaning of the main components according to the actual situation.

[0039] On this basis, it is also necessary to combine the subjective feelings and descriptions of users, as well as the focus of scenic spot development, that is, to determine the weight of each main component in the further evaluation score based on the actual situation. , which can be positive or negative according to its meaning, so that a final score can be made. Through scoring, a quantitative evaluation of different design schemes can be achieved, which will help the cultural and tourism development of natural landscapes.

[0040] The working process of the present invention is as follows:

[0041] First, the natural landscape environment is restored as much as possible in the virtual space. Then, according to different cultural and tourism development design plans, the natural landscape environment is transformed differently in the virtual space to make it conform to the content of the design plan. Then, relevant interactive functions are designed for subsequent testing and experience. Then, users are invited to use VR devices to experience the landscape environment corresponding to different design plans in the virtual space. In the process of user experience, motion capture devices, facial capture devices and professional medical collection devices can be used to obtain various aspects of user data. For the data obtained in different design plans, the principal component analysis method is used to process and analyze them to obtain multiple principal component score matrices. Each principal component score matrix corresponds to a design plan. Then, the meaning of the principal component representation is analyzed according to the load of the original data in the principal component. On the basis of the load, the weight value needs to be determined in combination with the user's subjective feelings and descriptions, as well as the focus of the scenic spot development. Then, the total score of the design is calculated according to the principal component score matrix and the weight value. In this way, the total score of different design plans can be obtained, so that the quantitative evaluation of the design plan can be realized through the score, which is conducive to the subsequent cultural and tourism development.

[0042] The above embodiments are only preferred embodiments of the present invention. Those skilled in the art can derive other embodiments from the above embodiments without creative work. Therefore, this application protects not only the above embodiments, but also the scope consistent with the principles and features of this application.

Claims

1. A method for evaluating the development of natural landscape cultural tourism, characterized in that: The following steps are involved: S1. Collect the natural geographical information of the scenic area and restore it in the virtual space; S2. For different cultural tourism development design schemes, transformation and modeling are carried out in virtual space to obtain 3D results of different designs; S3. Design relevant interactive functions for different design schemes for subsequent VR device testing; S4. Invite users to use VR devices to test different designs, and collect multiple test data of users during the experience process to obtain a data set, each of which represents different features; S5. Analyze the data set to obtain the principal component score matrix of the design scheme; S6. Calculate the total scores of different design solutions based on the principal component score matrix of different design solutions.

2. The evaluation method for natural landscape cultural tourism development according to claim 1 is characterized in that: The step S5 comprises the following steps: S51, cleaning the test data; S52, performing standardization processing on the cleaned data, and constructing the processed data into a data matrix; S53, calculating the covariance matrix of the data matrix; S54, solving the eigenvalues ​​and corresponding eigenvectors of the covariance matrix; S55. Perform dimensionality reduction processing on the data matrix to obtain a principal component score matrix.

3. The evaluation method for natural landscape cultural tourism development according to claim 2 is characterized in that: The step S51 comprises the following steps: S511, identifying missing values ​​in the data set, and filling the missing values ​​with the mean of this data; S512. Use the Z-Score method to detect outliers. The formula is as follows: ， Among them, Z represents Z-Score, X represents the data value to be tested, μ represents the mean of the data set, and σ is the standard deviation of this data; S513. When the absolute value of Z-scored is greater than or equal to the set value, the data value will be determined as an abnormal value, and the abnormal value needs to be replaced by the mean value of this data.

4. The evaluation method for natural landscape cultural tourism development according to claim 2 is characterized in that: The step S52 comprises the following steps: S521. Establish standardized formula: ， Among them, x represents the original value of a certain data. represents the mean value of this data, σ represents the standard deviation of this data, is the eigenvalue after standardization; S522, calculating the test data using a standardized formula to obtain standardized data, i.e., eigenvalues; S523, constructing the standardized data into a data matrix.

5. The evaluation method for natural landscape cultural tourism development according to claim 2 is characterized in that: The step S53 comprises the following steps: S531. Calculate the covariance matrix of the data matrix using the following formula: ， Among them, X and Y represent two standardized data respectively. is the value of feature X, is the mean of feature X, is the value of feature Y, is the mean of feature Y; S532, calculating the standardized data pairwise using the above formula to obtain the covariance matrix of the data.

6. The evaluation method for natural landscape cultural tourism development according to claim 2 is characterized in that: The step S54 comprises the following steps: S541. Construct the eigenvalue equation: , Where A represents the covariance matrix, det represents the determinant of the covariance matrix, λ is the eigenvalue, and I is the unit matrix of the same order as A; S542, calculating multiple eigenvalues ​​λ of the covariance matrix by the above formula; S543, substitute each eigenvalue λ into the following equation: , Get the system of equations, solve them and get the eigenvector v.

7. The evaluation method for natural landscape cultural tourism development according to claim 2 is characterized in that: The step S55 comprises the following steps: S551, select k eigenvectors as principal components; S552. Combine the k eigenvectors into a new matrix, namely the projection matrix: , Each eigenvector is a column vector; S553. The above eigenvectors are arranged according to the magnitude of their corresponding eigenvalues; S554. Multiply the normalized data matrix by the projection matrix to obtain the reduced-dimensional data, i.e., the principal component score matrix.

8. The evaluation method for natural landscape cultural tourism development according to claim 7 is characterized in that: The step S6 comprises the following steps: S61, calculate the load of the principal component; S62. Analyze the significance of the principal components based on the loads, and determine the weight of each principal component in the further evaluation score based on the actual situation. ; S63, expressing the principal component score matrix as: ； S64. According to the principal component score matrix and the determined weights, the total score of the design solution is calculated by the following formula: 。

Images