A smart tourism Internet service system and method based on VR technology

Abstract

The present invention relates to the field of tourism service technology, specifically a smart tourism Internet service system and method based on VR technology, the system includes a sight behavior response module, an emotion analysis module, a virtual content dynamic adjustment module and a real-time optimization module. In the present invention, by integrating sight tracking and emotion analysis technology, deep personalization and real-time adjustment of the passenger experience are achieved. By analyzing the sight behavior of passengers in a virtual environment, the system can accurately adjust the landscape rendering parameters, optimize the visual presentation, and improve the clarity and visual appeal of the image. Combined with the emotion analysis of heart rate and facial expression, it can capture the emotional changes of passengers in real time and adjust the rhythm and depth of the virtual scene accordingly. The adaptive content presentation not only enhances the user's sense of immersion, but also improves the satisfaction of the personalized experience. It can respond to the specific needs of passengers in real time during the tour, optimize the perceived quality of the entire tourism experience, and improve user satisfaction and participation.

Description

Technical Field

[0001] The present invention relates to the field of tourism service technology, and in particular to a smart tourism Internet service system and method based on VR technology. Background Art

[0002] The field of tourism service technology focuses on improving the quality and efficiency of tourism experience through modern scientific and technological means. It combines information technology, mobile computing, big data analysis, artificial intelligence and other technologies to optimize the provision of tourism services, covering intelligent recommendation of tourism resources, customization of personalized travel routes, online booking systems, virtual reality travel experience and tourist behavior analysis. With the continuous advancement of science and technology, the field of tourism service technology is also constantly promoting the digital and intelligent transformation of the tourism industry, aiming to provide travelers with more convenient and personalized travel services and help tourism companies improve management efficiency and customer satisfaction.

[0003] Among them, the smart tourism Internet service system is an application platform that integrates various information technologies. It aims to improve the tourism experience through data analysis and intelligent algorithms. The system can provide users with real-time tourism information, recommend personalized tourism content and services, and realize online booking and electronic payment functions. In addition, the system can also provide customized services based on user preferences and historical behaviors, making tourism activities more efficient and satisfactory. Its main uses include improving the accessibility and convenience of tourism services, optimizing resource allocation, and enhancing the interaction between tourists and tourist destinations.

[0004] Although existing tourism service technologies integrate information technology and big data, they often rely on preset virtual scenes and general interaction modes in terms of virtual reality tourism experience, lacking in-depth understanding and immediate response to users' specific behaviors and emotional reactions. This limitation may cause the user experience to be inconsistent with personal expectations, reducing immersion and satisfaction. At the same time, the existing system is not efficient in processing personalized data, making it difficult to achieve refined tourism recommendations and content adjustments, limiting the dynamic optimization of the experience and the depth of personalization, affecting the competitiveness of tourism services. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a smart tourism Internet service system and method based on VR technology.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: A smart tourism Internet service system based on VR technology includes:

[0007] The sight behavior response module collects the user's sight data in VR tourism, analyzes the sight stop points and duration, adjusts the landscape rendering parameters according to the user's gaze points in the virtual scene tourism, and generates a visual optimization parameter set;

[0008] The emotion analysis module obtains the current user's emotion data from the facial expression and heart rate monitoring device, analyzes the current user's emotion changes in the VR tourism experience, and adjusts the rhythm and visual content depth of the virtual scene according to the analysis results combined with the visual optimization parameter set to obtain emotion matching content;

[0009] The virtual content dynamic adjustment module collects and analyzes current user behavior based on the emotion matching content, predicts the virtual scene adjustment needs, dynamically updates the virtual landscape content according to the prediction results, determines the optimal display strategy for the virtual landscape content, and generates customized content display results;

[0010] The real-time optimization module displays the customized content results based on the user's behavior and location data in the virtual scene tourism, compares and analyzes the user's feedback, optimizes the content provision strategy, matches the user's needs, and outputs the user's VR tourism experience results.

[0011] As a further solution of the present invention, the step of obtaining the visual optimization parameter set is:

[0012] Collect the sight data in VR tourism, track the sight coordinates of user u at time point t, and use the formula:

[0013] S(u,t)=(x,y,z,t)

[0014] Where u represents the user, t represents time, and (x, y, z) represents the line of sight coordinate point in three-dimensional space. The user's line of sight trajectory is recorded to generate a line of sight dataset S(u, t);

[0015] Using the sight data set S(u,t), analyze the time the sight stays at the coordinate point. If the coordinates are continuously recorded as the same, the cumulative stay time is calculated using the formula:

[0016]

[0017] Where D(u,p) represents the cumulative time that user u stays at point p, t start and t end are the start and end timestamps of the point p’s stay, t i Generate the analysis results of sight dwell time for the timestamps of consecutive points with the same coordinates;

[0018] Based on the analysis results of the sight stay time, the stay time of all users is averaged to calculate the average stay time of each point. The formula is:

[0019]

[0020] Where T(p) is the average stay time of all users at point p, n is the total number of users staying at point p, and the key gaze point analysis results are obtained;

[0021] According to the analysis results of the key gaze points, the landscape rendering parameters are adjusted using the formula:

[0022]

[0023] Among them, R(p) is the original landscape rendering parameter, λ and ∈ are the weight coefficient and stability coefficient respectively, avoiding the zero division error and generating the visual optimization parameter set P(p).

[0024] As a further solution of the present invention, the steps of analyzing the emotional changes of the current user in the VR tourism experience are:

[0025] Use facial expression recognition technology and heart rate monitoring equipment to capture the current user's facial expression index E in real time t and heart rate H t , generate facial expression sequences and heart rate sequences, and obtain initial emotion data {E t , H t};

[0026] According to the initial emotion data {E t ,H t}, apply the formula,

[0027]

[0028] Calculate the sentiment index, where EI t represents the emotion index value, α and β are adjustment parameters used to adjust the impact of heart rate and facial expression, and q is a small positive number used to stabilize the value to generate emotion index data;

[0029] Use the emotional index data to analyze the current user's emotional fluctuations in the VR experience, and use the formula:

[0030]

[0031] Calculate the degree of emotional fluctuation, where EV represents the value of emotional fluctuation, N is the total number of measurements, and evaluate the volatility of emotions by calculating the square difference of the emotional index to generate the emotional fluctuation result.

[0032] As a further solution of the present invention, the step of acquiring the emotion matching content is:

[0033] According to the emotion fluctuation results, combined with the visual optimization parameter set, through the formula,

[0034]

[0035] Among them, γ and δ are integration coefficients, which adjust the influence weights of emotional data and visual parameters, and ρ is an additional coefficient used to adjust the influence of visual parameters. The comprehensive adjustment factor IF is calculated and obtained;

[0036] Apply the comprehensive adjustment factor to adjust the rhythm and visual content of the virtual scene.

[0037]

[0038] Among them, σ and η are adjustment parameters, which adjust the influence of the integration factor and the original visual parameters respectively, and generate the adjusted scene parameters SA;

[0039] Based on the adjusted virtual scene parameters, create content that matches the current user's emotions, integrating all visual and emotional parameters,

[0040] MC=∫SAdt

[0041] Among them, MC represents the total amount of emotion matching content, and outputs emotion matching content to ensure that the content is consistent with the current user's emotional fluctuations.

[0042] As a further solution of the present invention, the step of predicting the virtual scene adjustment demand is:

[0043] Monitor the current user's interaction with the emotion matching content in the virtual environment, collect the current user behavior data, including path tracking, interaction objects and frequency, and record and generate time series data B t ;

[0044] Analyze the time series data, calculate statistical indicators, use formulas,

[0045]

[0046] Among them, μ is the mean of the time series data, κ is the degree of freedom adjustment parameter, m represents the total number of data points, and M represents the variance of the current user behavior data, generating the current user behavior statistics;

[0047] According to the current user behavior statistics, the scene adjustment needs are predicted, using the formula:

[0048]

[0049] Among them, A represents the scenario adjustment requirement, g and h are adjustment coefficients used to adjust the sensitivity of the model and the baseline adjustment level, and e -M It is an exponential decay term, which is used to adjust the influence of M, to ensure that when M increases, the adjustment demand A will not be over-amplified, and to output the forecast result of the scenario adjustment demand.

[0050] As a further solution of the present invention, the steps of obtaining the customized content display result are:

[0051] Dynamically update the virtual landscape according to the scenario adjustment demand forecast results, using the formula,

[0052]

[0053] Among them, L is the updated virtual landscape parameter, Y is the original landscape parameter, x and y are adjustment coefficients, and the calculation accuracy is increased by square and square root operations to ensure that the landscape update matches the current user needs and obtain the updated virtual landscape content;

[0054] Using the updated virtual landscape content, the optimal display strategy is determined using the formula:

[0055] S=R·log(1+|L|)

[0056] Among them, S is the optimal display strategy value, R is the display strategy adjustment parameter, and the flexibility and adaptability of the strategy are ensured through logarithmic and absolute value processing to obtain the optimal display strategy;

[0057] According to the optimal display strategy, the virtual landscape display is customized, using the formula,

[0058]

[0059] Among them, D is the quantitative parameter of customized display, and F is the personalized adjustment parameter. The dynamics of the display result is adjusted by using the cosine function and the square term to output the customized content display result.

[0060] As a further solution of the present invention, the steps for obtaining the VR travel experience result of the current user are:

[0061] According to the customized content display result, the current user's behavior W is collected in the virtual scene t and position G t data,

[0062] Z={(W t ,G t )|t=1,2,…,z}

[0063] Integrate data points to construct a time series of current user behavior and location, generating a time series dataset Z;

[0064] Perform in-depth analysis on the time series data set, calculate the integrated analysis index I of behavior and location, and use the formula for feature extraction.

[0065]

[0066] Among them, I represents the comprehensive analysis index combining behavioral and positional data, the fourth power is introduced to adjust the sensitivity of the data, π·z is used to normalize the results and increase mathematical significance, and z represents the total number of data points to generate behavioral and positional analysis results;

[0067] Based on the behavior and location analysis results, adjust and optimize the content delivery strategy and use formulas to adjust virtual content.

[0068]

[0069] Among them, K represents the adjusted content provision strategy indicator, a, b and c are adjustment coefficients, which are used to adjust the impact of I, strengthen the dynamic and nonlinear response of the model, and use sine and cosine functions to introduce periodic factors to simulate the natural fluctuations of current user behavior and obtain the optimization strategy;

[0070] Based on the optimization strategy, adjust the virtual scene, strengthen user interaction and participation, and use the formula to calculate the current user experience score.

[0071]

[0072] Among them, V represents the satisfaction score of user experience, d is the intensity adjustment parameter, and the hyperbolic tangent function tanh and the exponential function of the natural logarithm are used to adjust the sensitivity and complexity of the model to changes in the optimization strategy, and output the user's VR tourism experience results.

[0073] A smart tourism Internet service method based on VR technology, comprising the following steps:

[0074] S1: Collect sight data in VR tourism, track the user's sight coordinates, analyze the sight's stay time at the coordinate point, calculate the average stay time at each point, adjust the landscape rendering parameters, and generate a visual optimization parameter set;

[0075] S2: Capture the current user's facial expression index and heart rate in real time, obtain initial emotion data, calculate the emotion index based on the initial emotion data, analyze the user's emotion fluctuations in VR experience, and generate emotion fluctuation results;

[0076] S3: according to the emotion fluctuation results, combined with the visual optimization parameter set, a comprehensive adjustment factor is calculated, the rhythm and visual content of the virtual scene are adjusted, all visual and emotion parameters are integrated, and emotion matching content is output;

[0077] S4: According to the emotion matching content, collect current user behavior data, calculate statistical indicators, predict scene adjustment needs according to the calculation results, and output scene adjustment demand prediction results;

[0078] S5: dynamically updating the virtual landscape according to the scenario adjustment demand prediction result, ensuring that the landscape update matches the current user demand, determining the optimal display strategy, adjusting the dynamics of the display result, and outputting the customized content display result;

[0079] S6: According to the customized content display result, collect the behavior and location data of the current user in the virtual scene, construct a time series data set and perform in-depth analysis, calculate the integrated analysis indicators of behavior and location, optimize the content provision strategy, adjust the virtual scene, calculate the current user experience score, and output the current user VR travel experience result.

[0080] Compared with the prior art, the advantages and positive effects of the present invention are:

[0081] In the present invention, by integrating gaze tracking and emotion analysis technology, deep personalization and real-time adjustment of the passenger experience are achieved. By analyzing the passenger's gaze behavior in the virtual environment, the system can accurately adjust the landscape rendering parameters, optimize the visual presentation, and improve the clarity and visual appeal of the image. Combined with the emotion analysis of heart rate and facial expressions, it can capture the passenger's emotional changes in real time and adjust the rhythm and depth of the virtual scene accordingly. The adaptive content presentation not only enhances the user's sense of immersion, but also improves the satisfaction of the personalized experience. It can not only respond to the specific needs of passengers in real time during the travel process, but also optimize the perceived quality of the entire travel experience, thereby improving user satisfaction and participation. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Figure 1 is a system flow chart of the present invention;

[0083] Figure 2 A flowchart of obtaining a visual optimization parameter set of the present invention;

[0084] Figure 3 This is a flow chart for analyzing the emotional changes of the current user in the VR tourism experience of the present invention;

[0085] Figure 4 This is a flow chart of obtaining emotion matching content of the present invention;

[0086] Figure 5 A flow chart for predicting the demand for adjusting the virtual scene of the present invention;

[0087] Figure 6 A flowchart for obtaining the customized content display result of the present invention;

[0088] Figure 7 This is a flow chart for obtaining the VR travel experience results of the current user in the present invention. DETAILED DESCRIPTION

[0089] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0090] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0091] Embodiment 1

[0092] See also Figure 1 The present invention provides a technical solution: a smart tourism Internet service system based on VR technology includes:

[0093] The sight behavior response module collects the user's sight data in VR tourism, analyzes the sight stop points and duration, adjusts the landscape rendering parameters according to the user's gaze points in the virtual scene tourism, and generates a visual optimization parameter set;

[0094] The emotion analysis module obtains the current user's emotion data from facial expression and heart rate monitoring devices, analyzes the current user's emotional changes in the VR tourism experience, and adjusts the rhythm and visual content depth of the virtual scene based on the analysis results and the visual optimization parameter set to obtain emotion matching content;

[0095] The virtual content dynamic adjustment module collects and analyzes current user behaviors based on emotion matching content, predicts virtual scene adjustment needs, dynamically updates virtual landscape content based on prediction results, determines the optimal display strategy for virtual landscape content, and generates customized content display results;

[0096] The real-time optimization module displays the results based on customized content, utilizes the current user's behavior and location data in the virtual scene tourism, optimizes the content provision strategy by comparing and analyzing the current user feedback, matches the current user's needs, and outputs the current user's VR tourism experience results.

[0097] The visual optimization parameter set includes rendering quality, lighting effects and color saturation. The emotion matching content includes scene dynamic content, sound effect adjustment results and scene interactive elements. The customized content display results include landscape details, interaction design results and virtual landscape content update frequency. The current user VR tourism experience results include the current user satisfaction score record, the current user engagement index and the current user's personalized feedback content.

[0098] See also Figure 2 , the steps to obtain the visual optimization parameter set are:

[0099] Collect the sight data in VR tourism, track the sight coordinates of user u at time point t, and use the formula:

[0100] S(u,t)=(x,y,z,t)

[0101] Where u represents the user, t represents time, and (x, y, z) represents the line of sight coordinate point in three-dimensional space. The user's line of sight trajectory is recorded to generate a line of sight dataset S(u, t);

[0102] Use the sight data set S(u,t) to analyze the time the sight stays at the coordinate point. If the coordinates are recorded continuously and are the same, the cumulative stay time is calculated using the formula:

[0103]

[0104] Where D(u,p) represents the cumulative time that user u stays at point p, t start and t end are the start and end timestamps of the point p’s stay, t i Generate the analysis results of sight dwell time for the timestamps of consecutive points with the same coordinates;

[0105] Based on the analysis results of the sight dwell time, the dwell time of all users is averaged to calculate the average dwell time of each point. The formula is:

[0106]

[0107] Where T(p) is the average stay time of all users at point p, n is the total number of users staying at point p, and the key gaze point analysis results are obtained;

[0108] According to the key gaze point analysis results, the landscape rendering parameters are adjusted using the formula:

[0109]

[0110] Among them, R(p) is the original landscape rendering parameter, λ and ∈ are the weight coefficient and stability coefficient respectively, avoiding the zero division error and generating the visual optimization parameter set P(p).

[0111] Assume that the sight coordinates of user u at time t = 5 seconds are (1, 2, 3), then,

[0112] S(u,5)=(1,2,3,5)

[0113] It means that at 5 seconds, the coordinates of user u's sight position in 3D space are (1, 2, 3).

[0114] Assume that user u stays at point p = (1, 2, 3) for a period of time from t start = 5 seconds to t end = 10 seconds, then,

[0115] D(u, (1, 2, 3)) = (10-5) = 5 seconds

[0116] It means that the total stay time of user u at point (1, 2, 3) is 5 seconds.

[0117] Assume that the number of users staying at point p = (1, 2, 3) is n = 2, the first user stays for 5 seconds, and the second user stays for 3 seconds, then,

[0118]

[0119] It means that the average residence time at point (1, 2, 3) is 4 seconds.

[0120] Assume that λ is 1.5, ∈ is 0.1, and the original rendering parameters R((1,2,3))=100. According to the above calculation, T((1,2,3))=4 seconds.

[0121] Substituting into the formula, we get:

[0122]

[0123] The adjusted rendering parameter is 136.6, which means that based on the user's average gaze time, the original rendering parameter can be increased by 36.6% to improve the rendering quality and details of the user's gaze area.

[0124] See also Figure 3 ,The analysis steps of the current user’s emotional changes in VR tourism experience are:

[0125] Use facial expression recognition technology and heart rate monitoring equipment to capture the current user's facial expression index E in real time t and heart rate H t , generate facial expression sequences and heart rate sequences, and obtain initial emotion data {E t , H t};

[0126] Based on the initial sentiment data {Et ,H t}, apply the formula,

[0127]

[0128] Calculate the sentiment index, where EI t represents the emotion index value, α and β are adjustment parameters used to adjust the impact of heart rate and facial expression, and q is a small positive number used to stabilize the value to generate emotion index data;

[0129] Use the emotional index data to analyze the user's emotional fluctuations in VR experience, and use the formula to

[0130]

[0131] Calculate the degree of emotional fluctuation, where EV represents the value of emotional fluctuation, N is the total number of measurements, and evaluate the volatility of emotions by calculating the square difference of the emotional index to generate the emotional fluctuation result.

[0132] Assume that at time t=1 second, the captured heart rate is 80 bpm and the facial expression index (representing the liveliness of facial movements) is 20, which means H(1)=80 and E(1)=20.

[0133] Assume α is 0.5, β is 0.3, and q is 0.01.

[0134] Take the data of t=1 second as an example:

[0135] H(1)=80

[0136] E(1)=20

[0137] but,

[0138]

[0139] Continue to calculate:

[0140] log(1+6400)=log(6401)≈3.81

[0141] 20 2 =400

[0142]

[0143] The value (120.7) indicates that at the first second, the user's emotional index is 120.7, and a higher value indicates a stronger emotional response of the user.

[0144] Assume that there are sentiment index data at three time points (N=3): 120.7 (time 1), 130 (time 2), and 125 (time 3).

[0145] Substituting into the formula, we get:

[0146] (130-120.7) 2 +(125-130) 2 =86.49+25=111.49

[0147]

[0148] The results show that the degree of emotional fluctuation of users throughout the VR experience is 6.1, and the numerical value reflects the intensity of emotional fluctuation. Higher values ​​indicate greater fluctuations in emotional responses, which may be related to the content of the VR experience.

[0149] See also Figure 4 , the steps to obtain emotion matching content are:

[0150] According to the results of emotional fluctuations, combined with the visual optimization parameter set, through the formula,

[0151]

[0152] Among them, γ and δ are integration coefficients, which adjust the influence weights of emotional data and visual parameters, and ρ is an additional coefficient used to adjust the influence of visual parameters. The comprehensive adjustment factor IF is calculated and obtained;

[0153] Apply comprehensive adjustment factors to adjust the rhythm and visual content of the virtual scene.

[0154]

[0155] Among them, σ and η are adjustment parameters, which adjust the influence of the integration factor and the original visual parameters respectively, and generate the adjusted scene parameters SA;

[0156] Create content that matches the current user's emotions based on the adjusted virtual scene parameters, integrating all visual and emotional parameters.

[0157] MC=∫SAdt

[0158] Among them, MC represents the total amount of emotion matching content, and outputs emotion matching content to ensure that the content is consistent with the current user's emotional fluctuations.

[0159] Assuming γ is 0.4, δ is 0.6, and ρ is 0.05, EV = 6.1 is obtained from the above calculation. Assuming the visual optimization parameter P = 50, substitute it into the formula and calculate:

[0160]

[0161] Calculate step by step,

[0162] 6.1 2≈37.21

[0163] 0.4 37.21 + 0.6 50 = 9.37 + 30 = 44.884

[0164]

[0165] IF=12.824 represents the adjustment factor after comprehensive emotional changes and visual optimization parameters, which is used for the adjustment of subsequent scenes.

[0166] Assume σ is 2.0 and η is 1.0,

[0167] Continue to use the IF=12.824 and P=50 obtained in the previous step and substitute them into the formula to calculate:

[0168]

[0169] Calculation process:

[0170]

[0171] log(51)≈1.71

[0172] SA=2.0·3.58+1.71=8.87

[0173] SA=8.87 indicates the adjusted virtual scene parameters, which are used to improve the user experience and match its emotional changes.

[0174] If SA remains constant at 8.87 and the duration of the virtual experience T is 60 seconds, then,

[0175]

[0176] MC=532.2 indicates the total amount of emotion-matching content generated, which enhances immersion and satisfaction by adjusting the virtual scene to provide experience content consistent with the user's emotional fluctuations.

[0177] See also Figure 5 ,The prediction steps of virtual scene adjustment requirements are:

[0178] Monitor the current user's interaction with emotion-matching content in the virtual environment, collect current user behavior data, including path tracking, interaction objects and frequency, and record and generate time series data B t ;

[0179] Analyze time series data, calculate statistical indicators, use formulas,

[0180]

[0181] Among them, μ is the mean of the time series data, κ is the degree of freedom adjustment parameter, m represents the total number of data points, and M represents the variance of the current user behavior data, generating the current user behavior statistics;

[0182] According to the behavior statistics, the scenario adjustment needs are predicted and the formula is used.

[0183]

[0184] Among them, A represents the scenario adjustment requirement, g and h are adjustment coefficients used to adjust the sensitivity of the model and the baseline adjustment level, and e -M It is an exponential decay term, which is used to adjust the influence of M, to ensure that when M increases, the adjustment demand A will not be over-amplified, and to output the forecast result of the scenario adjustment demand.

[0185] Assume there are 5 data points (100, 105, 95, 103, 107), that is, m = 5, calculate the statistical indicators of the behavior pattern:

[0186]

[0187] Assume κ = 1 and substitute into the formula:

[0188]

[0189] M=22 represents the variance of user behavior data, and the value indicates the volatility or consistency of user behavior. A larger variance indicates that user behavior is more diverse, which is a key statistical indicator for adjusting virtual scenes.

[0190] Based on M = 22, assuming g = 0.5, h = 10, then,

[0191]

[0192] The result A≈12.345 represents the adjustment demand index. This value indicates that based on the volatility of the current user behavior, the virtual scene needs a greater degree of adjustment to adapt to the user's behavior pattern. The value of 12.345 can be used to directly map to specific parameters of virtual environment adjustment, such as adjusting the dynamic elements or interactivity intensity of the scene.

[0193] See also Figure 6 , the steps to obtain customized content display results are:

[0194] Dynamically update the virtual landscape according to the forecast results of scene adjustment demand, using the formula,

[0195]

[0196] Among them, L is the updated virtual landscape parameter, Y is the original landscape parameter, x and y are adjustment coefficients, and the calculation accuracy is increased by square and square root operations to ensure that the landscape update matches the current user needs and obtain the updated virtual landscape content;

[0197] Using the updated virtual landscape content, determine the optimal display strategy, using the formula,

[0198] S=R·log(1+|L|)

[0199] Among them, S is the optimal display strategy value, R is the display strategy adjustment parameter, and the flexibility and adaptability of the strategy are ensured through logarithmic and absolute value processing to obtain the optimal display strategy;

[0200] Customize virtual landscape display according to the optimal display strategy, using formula,

[0201]

[0202] Among them, D is the quantitative parameter of customized display, and F is the personalized adjustment parameter. The dynamics of the display result is adjusted by using the cosine function and the square term to output the customized content display result.

[0203] Assume A = 12.345 (obtained from the above calculation), Y = 50, x = 2, y = 3, substitute into the formula:

[0204]

[0205] L≈6.27 represents the updated virtual landscape parameters. This value represents the adjusted landscape settings based on user behavior data. Application in a virtual environment may involve adjusting lighting effects, scene dynamic elements, etc. to better adapt to user expectations and behaviors.

[0206] Assuming L = 6.27 (obtained from the above calculation), R = 1.5, then,

[0207] S = 1.5·log(1+|6.27|)

[0208] S=1.5·log(7.27)≈1.5·0.862=1.293

[0209] The calculated result S≈1.293 indicates the optimal display strategy value. This value is used to adjust the display mode of the virtual landscape, affecting the depth and color saturation of the visual rendering, aiming to enhance the user's immersion and satisfaction.

[0210] Assuming S = 1.293 (obtained from the above calculation), F = 5, then,

[0211]

[0212] The calculation result D≈1.869 represents the quantitative parameter of customized display, which represents the intensity of enhancing certain visual elements, such as increasing brightness or contrast, to match the user's visual comfort or expectations.

[0213] See also Figure 7 , the steps to obtain the current user's VR travel experience results are:

[0214] According to the customized content display results, the current user's behavior W is collected in the virtual scene t and position G t data,

[0215] Z={(W t ,G t )|t=1,2,…,z}

[0216] Integrate data points to construct a time series of current user behavior and location, generating a time series dataset Z;

[0217] Perform in-depth analysis on the time series data set, calculate the integrated analysis index I of behavior and location, and use the formula for feature extraction.

[0218]

[0219] Among them, I represents the comprehensive analysis index combining behavioral and positional data, the fourth power is introduced to adjust the sensitivity of the data, π·z is used to normalize the results and increase mathematical significance, and z represents the total number of data points to generate behavioral and positional analysis results;

[0220] Adjust and optimize content delivery strategies based on behavioral and location analysis results, and use formulas to adjust virtual content.

[0221]

[0222] Among them, K represents the adjusted content provision strategy indicator, a, b and c are adjustment coefficients, which are used to adjust the impact of I, strengthen the dynamic and nonlinear response of the model, and use sine and cosine functions to introduce periodic factors to simulate the natural fluctuations of current user behavior and obtain the optimization strategy;

[0223] Based on the optimization strategy, adjust the virtual scene, strengthen the current user interaction and participation, and use the formula to calculate the current user experience score.

[0224]

[0225] Among them, V represents the satisfaction score of the current user experience, d is the intensity adjustment parameter, and the hyperbolic tangent function tanh and the exponential function of the natural logarithm are used to adjust the sensitivity and complexity of the model to changes in the optimization strategy, and output the current user's VR travel experience results.

[0226] Suppose in a VR scene, data is collected at three time points:

[0227] Time 1: W1=2, G1=3;

[0228] Time 2: W2=4, G2=1;

[0229] Time 3: W3=3, G3=5;

[0230] The data points directly constitute the dataset Z:

[0231] Z = {(2,3), (4,1), (3,5)}

[0232] Dataset Z is a collection of behavior and location data, where data points represent the movement and behavior patterns of users in the virtual environment.

[0233] Continuing with the above data points:

[0234]

[0235] Calculation I:

[0236]

[0237] I≈5.57 is a comprehensive analytical indicator derived from raw behavioral and location data, measuring the intensity and distribution of users' activities in the virtual environment, providing a basis for further content strategies.

[0238] Setting the parameters a = 0.5, b = 0.8, c = 0.1, and using I = 5.57, we get:

[0239]

[0240] K≈0.184 represents the indicator of the adjusted content provision strategy. The indicator is small, indicating that the adjustment strategy needs to increase the participation of activities or improve the interactivity of content to better attract users.

[0241] Set d = 1.2, and use K = 0.184, and substitute into the formula:

[0242]

[0243] V≈0.283 represents the satisfaction score of the user experience, which is a small value, indicating that fine-tuning of the current content strategy requires more improvement to enhance the overall user experience.

[0244] A smart tourism Internet service method based on VR technology, comprising the following steps:

[0245] S1: Collect sight data in VR tourism, track the user's sight coordinates, analyze the sight's stay time at the coordinate point, calculate the average stay time at each point, adjust the landscape rendering parameters, and generate a visual optimization parameter set;

[0246] S2: Capture the current user's facial expression index and heart rate in real time, obtain initial emotion data, calculate the emotion index based on the initial emotion data, analyze the current user's emotion fluctuations in VR experience, and generate emotion fluctuation results;

[0247] S3: Based on the emotion fluctuation results, combined with the visual optimization parameter set, the comprehensive adjustment factor is calculated, the rhythm and visual content of the virtual scene are adjusted, all visual and emotion parameters are integrated, and the emotion matching content is output;

[0248] S4: According to the emotion matching content, collect the current user behavior data, calculate the statistical indicators, predict the scene adjustment needs according to the calculation results, and output the scene adjustment needs prediction results;

[0249] S5: Dynamically update the virtual landscape according to the scenario adjustment demand prediction results, ensure that the landscape update matches the current user needs, determine the optimal display strategy, adjust the dynamics of the display results, and output customized content display results;

[0250] S6: Based on the customized content display results, collect the current user's behavior and location data in the virtual scene, build a time series data set and conduct in-depth analysis, calculate the integrated analysis indicators of behavior and location, optimize the content provision strategy, adjust the virtual scene, calculate the user experience score, and output the current user's VR travel experience results.

[0251] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A smart tourism Internet service system based on VR technology, characterized by: The system comprises: The sight behavior response module collects the user's sight data in VR tourism, analyzes the sight stop points and duration, adjusts the landscape rendering parameters according to the user's gaze points in the virtual scene tourism, and generates a visual optimization parameter set; The emotion analysis module obtains the current user's emotion data from the facial expression and heart rate monitoring device, analyzes the current user's emotion changes in the VR tourism experience, and adjusts the rhythm and visual content depth of the virtual scene according to the analysis results combined with the visual optimization parameter set to obtain emotion matching content; The virtual content dynamic adjustment module collects and analyzes current user behavior based on the emotion matching content, predicts the virtual scene adjustment needs, dynamically updates the virtual landscape content according to the prediction results, determines the optimal display strategy for the virtual landscape content, and generates customized content display results; The real-time optimization module displays the customized content results, utilizes the behavior and location data of the current user in the virtual scene tourism, optimizes the content provision strategy by comparing and analyzing the current user feedback, matches the current user needs, and outputs the current user VR tourism experience results; The steps for obtaining the visual optimization parameter set are: Collect the sight data in VR tourism, track the sight coordinates of user u at time point t, and use the formula: S(u,t)=(x,y,z,t) Where u represents the user, t represents time, and (x, y, z) represents the line of sight coordinate point in three-dimensional space. The user's line of sight trajectory is recorded to generate a line of sight dataset S(u, t); Using the sight data set S(u,t), analyze the time the sight stays at the coordinate point. If the coordinates are continuously recorded as the same, the cumulative stay time is calculated using the formula: Where D(u,p) represents the cumulative time that user u stays at point p, t start and t end are the start and end timestamps of the point p’s stay, t i Generate the analysis results of sight dwell time for the timestamps of consecutive points with the same coordinates; Based on the analysis results of the sight stay time, the stay time of all users is averaged to calculate the average stay time of each point. The formula is: Where T(p) is the average stay time of all users at point p, n is the total number of users staying at point p, and the key gaze point analysis results are obtained; According to the analysis results of the key gaze points, the landscape rendering parameters are adjusted using the formula: Among them, R(p) is the original landscape rendering parameter, λ and ∈ are the weight coefficient and stability coefficient respectively, avoiding the zero division error and generating the visual optimization parameter set P(p).

2. The smart tourism Internet service system based on VR technology according to claim 1 is characterized by: The analysis steps of the current user's emotional changes in VR tourism experience are as follows: Use facial expression recognition technology and heart rate monitoring equipment to capture the user's facial expression index E in real time t and heart rate H t , generate facial expression sequences and heart rate sequences, and obtain initial emotion data {E t , H t }; According to the initial emotion data {E t ,H t }, apply the formula, Calculate the sentiment index, where EI t represents the emotion index value, α and β are adjustment parameters used to adjust the impact of heart rate and facial expression, and q is a small positive number used to stabilize the value to generate emotion index data; Use the emotional index data to analyze the current user's emotional fluctuations in the VR experience, and use the formula: Calculate the degree of emotional fluctuation, where EV represents the value of emotional fluctuation, N is the total number of measurements, and evaluate the volatility of emotions by calculating the square difference of the emotional index to generate the emotional fluctuation result.

3. The smart tourism Internet service system based on VR technology according to claim 2 is characterized by: The steps of acquiring the emotion matching content are as follows: According to the emotion fluctuation results, combined with the visual optimization parameter set, through the formula, Among them, γ and δ are integration coefficients, which adjust the influence weights of emotional data and visual parameters, and ρ is an additional coefficient used to adjust the influence of visual parameters. The comprehensive adjustment factor IF is calculated and obtained; Apply the comprehensive adjustment factor to adjust the rhythm and visual content of the virtual scene. Among them, σ and η are adjustment parameters, which adjust the influence of the integration factor and the original visual parameters respectively, and generate the adjusted scene parameters SA; Based on the adjusted virtual scene parameters, create content that matches the current user's emotions, integrating all visual and emotional parameters, MC=∫SAdt Among them, MC represents the total amount of emotion matching content, and outputs emotion matching content to ensure that the content is consistent with the current user's emotional fluctuations.

4. The smart tourism Internet service system based on VR technology according to claim 1 is characterized by: The steps for predicting the virtual scene adjustment requirements are as follows: Monitor the current user's interaction with the emotion matching content in the virtual environment, collect the current user behavior data, including path tracking, interaction objects and frequency, and record and generate time series data B t ; Analyze the time series data, calculate statistical indicators, use formulas, Among them, μ is the mean of the time series data, κ is the degree of freedom adjustment parameter, m represents the total number of data points, and M represents the variance of the current user behavior data, generating the current user behavior statistics; According to the current user behavior statistics, the scene adjustment needs are predicted, using the formula: Among them, A represents the scenario adjustment requirement, g and h are adjustment coefficients used to adjust the sensitivity of the model and the baseline adjustment level, and e -M It is an exponential decay term, which is used to adjust the influence of M, to ensure that when M increases, the adjustment demand A will not be over-amplified, and to output the forecast result of the scenario adjustment demand.

5. The smart tourism Internet service system based on VR technology according to claim 4 is characterized by: The steps for obtaining the customized content display result are: Dynamically update the virtual landscape according to the scenario adjustment demand forecast results, using the formula, Among them, L is the updated virtual landscape parameter, Y is the original landscape parameter, x and y are adjustment coefficients, and the calculation accuracy is increased by square and square root operations to ensure that the landscape update matches the user's needs and obtain the updated virtual landscape content; Using the updated virtual landscape content, the optimal display strategy is determined using the formula: S=R·log(1+|L|) Among them, S is the optimal display strategy value, R is the display strategy adjustment parameter, and the flexibility and adaptability of the strategy are ensured through logarithmic and absolute value processing to obtain the optimal display strategy; According to the optimal display strategy, the virtual landscape display is customized, using the formula, Among them, D is the quantitative parameter of customized display, and F is the personalized adjustment parameter. The dynamics of the display result is adjusted by using the cosine function and the square term to output the customized content display result.

6. The smart tourism Internet service system based on VR technology according to claim 1 is characterized by: The steps for obtaining the VR travel experience result of the current user are: According to the customized content display result, the current user's behavior W is collected in the virtual scene t and position G t data, From={(W t ,G t )∣t=1,2,…,z} Integrate data points to construct a time series of current user behavior and location, generating a time series dataset Z; Perform in-depth analysis on the time series data set, calculate the integrated analysis index I of behavior and location, and use the formula to extract features. Among them, I represents the comprehensive analysis index combining behavioral and positional data, the fourth power is introduced to adjust the sensitivity of the data, π·z is used to normalize the results and increase mathematical significance, and z represents the total number of data points to generate behavioral and positional analysis results; Based on the behavior and location analysis results, adjust and optimize the content delivery strategy and use formulas to adjust virtual content. Among them, K represents the adjusted content provision strategy indicator, a, b and c are adjustment coefficients, which are used to adjust the impact of I, strengthen the dynamic and nonlinear response of the model, and use sine and cosine functions to introduce periodic factors to simulate the natural fluctuations of current user behavior and obtain the optimization strategy; Based on the optimization strategy, adjust the virtual scene, strengthen the current user interaction and participation, and use the formula to calculate the current user experience score. Among them, V represents the satisfaction score of user experience, d is the intensity adjustment parameter, and the hyperbolic tangent function tanh and the exponential function of the natural logarithm are used to adjust the sensitivity and complexity of the model to changes in the optimization strategy, and output the user's VR tourism experience results.

7. A smart tourism Internet service method based on VR technology, characterized in that: According to any one of claims 1 to 6, a smart tourism Internet service system based on VR technology is implemented, comprising the following steps: Collect sight data in VR tourism, track the user's sight coordinates, analyze the time the sight stays at the coordinate point, calculate the average stay time at each point, adjust the landscape rendering parameters, and generate a visual optimization parameter set; Capture the current user's facial expression index and heart rate in real time, obtain initial emotion data, calculate the emotion index based on the initial emotion data, analyze the user's emotion fluctuations in VR experience, and generate emotion fluctuation results; According to the emotion fluctuation results, combined with the visual optimization parameter set, a comprehensive adjustment factor is calculated, the rhythm and visual content of the virtual scene are adjusted, all visual and emotion parameters are integrated, and emotion matching content is output; According to the emotion matching content, current user behavior data is collected, statistical indicators are calculated, scene adjustment needs are predicted based on the calculation results, and scene adjustment demand prediction results are output; Dynamically update the virtual landscape according to the scenario adjustment demand prediction results, ensure that the landscape update matches the current user needs, determine the optimal display strategy, adjust the dynamics of the display results, and output customized content display results; According to the customized content display results, the current user's behavior and location data are collected in the virtual scene, a time series data set is constructed and in-depth analysis is performed, the integrated analysis indicators of behavior and location are calculated, the content provision strategy is optimized, the virtual scene is adjusted, the current user experience score is calculated, and the current user VR travel experience result is output.

Images