Multimodal embodied interactive cultural tourism lighting art effect generation method and system

Abstract

The present invention provides a method and system for generating cultural and tourism lighting art effects with multimodal embodied interaction, which relates to the field of cultural and tourism lighting art technology, including: collecting and analyzing user interaction data to construct a behavioral feature sequence; dividing the interactive space and generating a spatial vitality map to establish a dynamic mapping relationship of lighting effects; generating initial lighting effects and collecting feedback; extracting user preference features and optimizing lighting control parameters to generate optimal lighting control instructions, which can achieve precise interaction between lighting effects and user behavior, and enhance the immersion and experience satisfaction of cultural and tourism scenes.

Description

Technical Field

[0001] The present invention relates to the field of cultural tourism lighting art technology, and in particular to a method and system for generating cultural tourism lighting art effects with multi-modal embodied interaction. Background Art

[0002] As an important part of the modern tourism industry, cultural and tourism lighting art provides tourists with an immersive visual experience by combining lighting installations with artistic design, enhancing the appeal and experience of cultural and tourism attractions. With the development of multimedia technology, cultural and tourism lighting art has developed from a single static lighting display to a multimodal interactive experience, allowing tourists to become not only viewers but also participants, interacting with lighting installations through various means such as body movements, expressions, and sounds, thereby creating personalized lighting art effects.

[0003] Currently, cultural and tourism lighting art design mainly relies on designers pre-designing fixed lighting effects based on the characteristics of the scenic area, or using simple sensors to trigger preset lighting changes. With the development of Internet of Things technology, lighting interaction systems based on user behavior analysis have begun to be applied in cultural and tourism scenarios. By collecting visitor activity data to adjust lighting effects, tourists' sense of participation and experience are enhanced.

[0004] However, existing technologies still lack comprehensive analysis of multimodal interaction data and are unable to fully capture users' behavioral patterns and emotional changes in cultural and tourism scenarios, resulting in a disconnect between lighting art effects and users' actual experience needs. They also lack the ability to dynamically perceive and analyze the overall spatial vitality distribution, and are unable to generate corresponding lighting effects based on the differentiated changes in user activity and emotional intensity in different areas. This results in a lack of spatial coherence and fluidity in lighting art effects, as well as an inability to adaptively optimize lighting effects based on real-time user feedback on them. This leads to a gap between lighting effects and user preferences, making it difficult to meet the personalized needs of different user groups.

[0005] Therefore, a solution is urgently needed to solve the problems in the prior art. Summary of the Invention

[0006] The embodiments of the present invention provide a method and system for generating cultural and tourism lighting art effects with multimodal embodied interaction, which can at least solve some of the problems existing in the prior art.

[0007] A first aspect of an embodiment of the present invention provides a method for generating a multimodal embodied interactive cultural tourism lighting art effect, comprising:

[0008] Collect initial user interaction data in cultural tourism scenarios and analyze temporal correlations, extract user behavior features, construct user behavior feature sequences, and calculate the changing trends of user behavior feature sequences. Obtain information on the light intensity, crowd density, and cultural element distribution of cultural tourism scenarios, and combine user behavior feature sequences and corresponding changing trends to generate scenario interaction data streams.

[0009] Based on the scene interaction data stream, the interactive space is divided, the activity and emotional intensity of users in each space are calculated and a spatial vitality map is generated. The energy difference between adjacent spaces is calculated based on the spatial vitality map, and the lighting gradient coefficient is determined. Based on the lighting gradient coefficient, the real-time changes in spatial vitality are tracked to establish a dynamic mapping relationship of lighting effects;

[0010] Outputting and executing lighting control instructions according to the dynamic mapping relationship, generating an initial lighting effect and collecting user interactive feedback data on the initial lighting effect;

[0011] Based on the interactive feedback data, extract the user's preference characteristics for lighting effects, construct a lighting effect evaluation index, optimize and sort the lighting control parameters according to the lighting effect evaluation index, establish a parameter optimization strategy, iteratively adjust the lighting control instructions based on the parameter optimization strategy, and generate the optimal lighting control instructions;

[0012] The optimal lighting control instruction is output, executed and the optimal lighting effect is recorded.

[0013] In an optional embodiment,

[0014] Collect the initial interaction data of users in the cultural tourism scene and analyze the time series correlation, extract user behavior characteristics, construct the user behavior feature sequence and calculate the change trend of the user behavior feature sequence, obtain the light intensity, crowd density and cultural element information distribution of the cultural tourism scene, and combine the user behavior feature sequence and the corresponding change trend to generate the scene interaction data stream including:

[0015] Collecting the user's initial interaction data in the cultural tourism scene, wherein the initial interaction data includes posture information, motion trajectory information, voice commands and emotional intonation information;

[0016] Constructing a time-dimensional correlation matrix and extracting the temporal correlation of the initial interaction data; constructing a user behavior feature sequence based on the temporal correlation; the user behavior feature sequence includes the duration of the behavior, the frequency of the behavior, the change in the intensity of the behavior, and the spatial location of the behavior; and calculating the change trend of the user behavior feature sequence at different scales;

[0017] Collect the light intensity, crowd density and cultural element information distribution of the cultural and tourism scene, map the user behavior feature sequence to the scene grid corresponding to the cultural and tourism scene according to the spatial position, determine the behavioral activity of each grid, calculate the activity difference value between different grids, and determine the scene interaction data flow in combination with the change trend, wherein the scene interaction data flow includes the real-time status and predicted status of the interaction data.

[0018] In an optional embodiment,

[0019] The interactive space is divided based on the scene interaction data stream, the activity and emotional intensity of users in each space are calculated and a spatial vitality map is generated. The energy difference between adjacent spaces is calculated based on the spatial vitality map, and the lighting gradient coefficient is determined. The real-time changes in spatial vitality are tracked based on the lighting gradient coefficient, and a dynamic mapping relationship of lighting effects is established, including:

[0020] Dividing the cultural tourism scene into multiple interactive spaces based on the scene interaction data stream, establishing a three-dimensional coordinate system in the interactive space, dividing the interactive space into multiple grid units, and calculating the ratio of the number of interactive events in each grid unit to the grid volume to obtain the interaction density;

[0021] Calculate the weighted sum of the basic behavior intensity, movement trajectory complexity, and interaction density of each user in the interactive space to obtain user activity; calculate the weighted sum of the physiological characteristic emotion value, voice emotion value, and gesture emotion value of each user in the interactive space to obtain emotion intensity; and perform a linear weighted combination of the user activity and the emotion intensity to obtain a spatial vitality map;

[0022] Determining the spatial vitality corresponding to each interactive space based on the spatial vitality map, calculating the absolute difference between the vitality values ​​of the center points of adjacent interactive spaces to obtain an energy difference, substituting the energy difference into an exponential function to obtain a light gradient coefficient, wherein the input of the exponential function is the negative of the ratio of the energy difference to a preset energy threshold parameter;

[0023] Based on the light gradient coefficient, the real-time changes in spatial vitality are tracked, the crowd flow characteristics are extracted to calculate the dynamic partition boundaries, a cross-region gradient function is constructed to optimize the light gradient coefficient, the group behavior pattern is identified to predict the vitality change trend and perform error compensation, and a dynamic mapping relationship between the real-time changes in spatial vitality and the lighting effects is established.

[0024] In an optional embodiment,

[0025] Based on the light gradient coefficient, the real-time changes in spatial vitality are tracked, crowd flow characteristics are extracted to calculate dynamic partition boundaries, a cross-region gradient function is constructed to optimize the light gradient coefficient, group behavior patterns are identified, vitality change trends are predicted, and error compensation is performed. The dynamic mapping relationship between the real-time changes in spatial vitality and lighting effects is established, including:

[0026] Acquire real-time data on changes in spatial vitality, generate a vitality mapping baseline value based on the real-time data on changes in spatial vitality and a preset light gradient coefficient, collect crowd movement data within the interactive space, extract crowd flow characteristics, and multiply the crowd flow characteristics by the crowd density of the interactive space to calculate the flow intensity;

[0027] Generate an adjustment factor for the dynamic partition boundary based on the difference in crowd flow characteristics and crowd density between adjacent interactive spaces, and adjust the boundaries of adjacent interactive spaces based on the adjustment factor;

[0028] Constructing a cross-region gradient function for the adjacent interactive spaces, substituting the flow intensity and spatial distance into the cross-region gradient function, and fusing the calculated result with the preset light gradient coefficient to generate an optimized light gradient coefficient;

[0029] Extracting group behavior pattern characteristics based on the flow intensity, inputting the group behavior pattern characteristics and pre-collected historical vitality data into a prediction model to calculate a vitality change trend, performing error compensation on the vitality change trend and the real-time collected spatial vitality data, and outputting a compensated spatial vitality mapping value;

[0030] A dynamic mapping function is established based on the compensated space vitality mapping value, the optimized light gradient coefficient and the pre-set environmental constraint parameters, and a dynamic mapping relationship is established between the real-time changes in the space vitality and the lighting effects. The dynamic mapping relationship is dynamically adjusted with the change rate of the compensated space vitality mapping value and the change rate of the optimized light gradient coefficient.

[0031] In an optional embodiment,

[0032] Outputting and executing lighting control instructions according to the dynamic mapping relationship, generating an initial lighting effect, and collecting user interactive feedback data on the initial lighting effect include:

[0033] Output and execute lighting control instructions according to the dynamic mapping relationship, wherein the lighting control instructions include lighting brightness, color temperature and gradient timing parameters;

[0034] generating an initial lighting effect according to the lighting control instruction, wherein the initial lighting effect is dynamically adjusted as the vitality of the space changes in real time;

[0035] Collect user interaction feedback data on the initial lighting effect, wherein the interaction feedback data includes user stay time, interaction frequency and pre-set emotional feedback indicators.

[0036] In an optional embodiment,

[0037] Based on the interactive feedback data, extracting user preference characteristics for lighting effects, constructing a lighting effect evaluation index, optimizing and ranking lighting control parameters according to the lighting effect evaluation index, establishing a parameter optimization strategy, and iteratively adjusting lighting control instructions based on the parameter optimization strategy to generate optimal lighting control instructions includes:

[0038] Collecting user interactive feedback data on lighting effects, constructing a multidimensional feature vector based on user dwell time, interaction frequency, and emotional feedback indicators in the interactive feedback data, and inputting the multidimensional feature vector into a pre-set user preference scoring module to obtain a preference score;

[0039] Performing weighted fusion of the preference score, the comfort index, and the spatial coordination index to generate a comprehensive evaluation value, and constructing a time series evaluation matrix based on the comprehensive evaluation value, wherein the time series evaluation matrix includes a sequence of evaluation values ​​within a historical time window;

[0040] Calculate the sensitivity of the comprehensive evaluation value to the lighting control parameters, use kernel density estimation to build a parameter sensitivity distribution module, suppress the influence of abnormal samples through iterative reweighted least squares method, and determine the parameter priority and sort based on historical optimization results;

[0041] Based on the sorting results of the lighting control parameters, a parameter optimization objective function is sequentially constructed, with minimizing the mean square error of the evaluation value sequence in the time series evaluation matrix as the optimization objective, and the amplitude of parameter changes at adjacent moments as a constraint condition. The lighting control parameters are gradient iteratively updated based on the optimization objective function, and the iteration is stopped when the difference between the comprehensive evaluation values ​​at adjacent moments is less than a preset threshold, and the optimized lighting control parameters are output;

[0042] According to the optimized lighting control parameters and the preset environmental constraint parameters, the optimal lighting control instructions are generated in combination with the preset dynamic gain matrix.

[0043] In an optional embodiment,

[0044] Calculate the sensitivity of the comprehensive evaluation value to the lighting control parameters, use kernel density estimation to build the parameter sensitivity distribution module, suppress the influence of abnormal samples through iterative reweighted least squares method, and determine the parameter priority and sorting based on historical optimization results, including:

[0045] Obtain historical adjustment data of lighting control parameters and corresponding preference scores. Based on the historical adjustment data and corresponding preference scores, calculate the first-order sensitivity of the comprehensive evaluation value to the lighting control parameters through partial derivatives, calculate the second-order interactive sensitivity through mixed partial derivatives, and construct the Jacobian matrix using the central difference method to obtain an initial sensitivity sequence;

[0046] A Gaussian kernel function is used to perform kernel density estimation on the initial sensitivity sequence, an optimal bandwidth parameter is adaptively calculated based on the sample standard deviation, the initial sensitivity sequence is transformed by the kernel function to obtain a continuous probability distribution, and the distribution characteristics of the parameter sensitivity are output;

[0047] A Huber-type M-estimation loss function is constructed to detect anomalies of the distribution characteristics of the parameter sensitivity, a sample weight matrix is ​​adaptively calculated based on the residual size, the sample weight matrix is ​​applied to an iterative reweighted least squares calculation, the influence of abnormal samples is suppressed through multiple rounds of iterative optimization, and a corrected sensitivity value is output;

[0048] Calculate the time series weight of the pre-acquired historical evaluation data based on the time decay exponential function, and perform weighted summation of the time series weight and the historical comprehensive evaluation value to obtain the historical optimization effect of the parameters;

[0049] The corrected sensitivity value, the historical parameter optimization effect, and the parameter stability index are subjected to multi-objective weighted fusion to determine the parameter priority. The lighting control parameters are sorted in descending order according to the parameter priority to generate a parameter optimization sequence table, wherein the parameter stability index includes parameter fluctuation amplitude, convergence speed, and disturbance recovery.

[0050] A second aspect of an embodiment of the present invention provides a multimodal embodied interactive cultural tourism lighting art effect generation system, comprising:

[0051] The first unit is used to collect initial user interaction data in cultural tourism scenarios and analyze time series correlations, extract user behavior features, construct user behavior feature sequences, and calculate the changing trends of user behavior feature sequences. It also obtains the distribution of light intensity, crowd density, and cultural element information in cultural tourism scenarios, and combines the user behavior feature sequences and corresponding changing trends to generate scene interaction data streams.

[0052] The second unit is used to divide the interactive space based on the scene interaction data stream, calculate the activity and emotional intensity of users in each space and generate a spatial vitality map. Based on the spatial vitality map, it calculates the energy difference between adjacent spaces and determines the lighting gradient coefficient. Based on the lighting gradient coefficient, it tracks the real-time changes in spatial vitality and establishes a dynamic mapping relationship for lighting effects.

[0053] The third unit is configured to output and execute lighting control instructions according to the dynamic mapping relationship, generate an initial lighting effect, and collect user interactive feedback data on the initial lighting effect;

[0054] A fourth unit is configured to extract user preference characteristics for lighting effects based on the interactive feedback data, construct a lighting effect evaluation index, optimize and sort lighting control parameters according to the lighting effect evaluation index, establish a parameter optimization strategy, iteratively adjust the lighting control instructions based on the parameter optimization strategy, and generate optimal lighting control instructions;

[0055] The fifth unit is used to output the optimal lighting control instruction, execute and record the optimal lighting effect.

[0056] According to a third aspect of an embodiment of the present invention, an electronic device is provided, including:

[0057] A processor and a memory for storing processor-executable instructions, wherein the processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0058] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described above is implemented.

[0059] In the present invention, by collecting and analyzing the interaction data of users in cultural and tourism scenes, personalized and intelligent control of lighting art effects is achieved, which effectively enhances the user's immersive experience and avoids the shortcomings of traditional lighting art effects that are single and static. The lighting art effects can be dynamically adjusted in real time according to user behavior and emotions, thereby enhancing the interactivity and attractiveness of cultural and tourism scenes. By calculating the energy difference between adjacent spaces to determine the light gradient coefficient, the continuity and harmony of the lighting effect in space are guaranteed, and the overall beauty of the lighting art and the ability to create a spatial atmosphere are improved. By iteratively adjusting the lighting control instructions and continuously optimizing the lighting effects, a closed-loop multimodal embodied interaction system is formed, which enables the lighting art effects to continuously learn and adapt to user preferences, thereby improving the system's self-improvement ability and user satisfaction, and providing an intelligent solution for the lighting art design of cultural and tourism scenes. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 This is a flow chart of a method for generating cultural tourism lighting art effects using multimodal embodied interaction according to an embodiment of the present invention;

[0061] Figure 2 Generate a system structure diagram for cultural tourism lighting art effects based on multimodal embodied interaction;

[0062] Figure 3Schematic diagram of the performance comparison of cultural and tourism lighting art effect systems based on multimodal embodied interaction. DETAILED DESCRIPTION

[0063] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings 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 making creative efforts shall fall within the scope of protection of the present invention.

[0064] The following specific embodiments are used to describe the technical solution of the present invention in detail. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0065] Figure 1 This is a flow chart of a method for generating cultural tourism lighting art effects with multimodal embodied interaction according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0066] Collect initial user interaction data in cultural tourism scenarios and analyze temporal correlations, extract user behavior features, construct user behavior feature sequences, and calculate the changing trends of user behavior feature sequences. Obtain information on the light intensity, crowd density, and cultural element distribution of cultural tourism scenarios, and combine user behavior feature sequences and corresponding changing trends to generate scenario interaction data streams.

[0067] Based on the scene interaction data stream, the interactive space is divided, the activity and emotional intensity of users in each space are calculated and a spatial vitality map is generated. The energy difference between adjacent spaces is calculated based on the spatial vitality map, and the lighting gradient coefficient is determined. Based on the lighting gradient coefficient, the real-time changes in spatial vitality are tracked to establish a dynamic mapping relationship of lighting effects;

[0068] Outputting and executing lighting control instructions according to the dynamic mapping relationship, generating an initial lighting effect and collecting user interactive feedback data on the initial lighting effect;

[0069] Based on the interactive feedback data, extract the user's preference characteristics for lighting effects, construct a lighting effect evaluation index, optimize and sort the lighting control parameters according to the lighting effect evaluation index, establish a parameter optimization strategy, iteratively adjust the lighting control instructions based on the parameter optimization strategy, and generate the optimal lighting control instructions;

[0070] The optimal lighting control instruction is output, executed and the optimal lighting effect is recorded.

[0071] In an optional embodiment,

[0072] Collect the initial interaction data of users in the cultural tourism scene and analyze the time series correlation, extract user behavior characteristics, construct the user behavior feature sequence and calculate the change trend of the user behavior feature sequence, obtain the light intensity, crowd density and cultural element information distribution of the cultural tourism scene, and combine the user behavior feature sequence and the corresponding change trend to generate the scene interaction data stream including:

[0073] Collecting initial interaction data of users in cultural tourism scenarios, wherein the initial interaction data includes posture information, motion trajectory information, voice commands, emotional tone information, heart rate data, and facial expression data;

[0074] Constructing a time-dimensional correlation matrix and extracting the temporal correlation of the initial interaction data; constructing a user behavior feature sequence based on the temporal correlation; the user behavior feature sequence includes the duration of the behavior, the frequency of the behavior, the change in the intensity of the behavior, and the spatial location of the behavior; and calculating the change trend of the user behavior feature sequence at different scales;

[0075] Collect the light intensity, crowd density and cultural element information distribution of the cultural and tourism scene, map the user behavior feature sequence to the scene grid corresponding to the cultural and tourism scene according to the spatial position, determine the behavioral activity of each grid, calculate the activity difference value between different grids, and determine the scene interaction data flow in combination with the change trend, wherein the scene interaction data flow includes the real-time status and predicted status of the interaction data.

[0076] Collect users' initial interaction data in cultural and tourism scenarios, including user posture information, motion trajectory information, voice commands, and emotional intonation information.

[0077] After acquiring the initial interaction data, a correlation matrix for the time dimension was constructed and the temporal correlations of the initial interaction data were extracted. The collected data was divided into time windows, with each window set to 5 seconds and adjacent windows overlapping by 2 seconds. For the data within each time window, the correlation coefficients between different data types were calculated to construct a 6×6 correlation matrix. For example, when analyzing users viewing an exhibition of ancient architecture, the correlation between facial expression data and heart rate data was 0.78, indicating a high degree of consistency between the user's emotions and physiological responses. The correlation between posture information and movement trajectory was 0.65, indicating a moderate correlation between the user's posture changes and movement behavior.

[0078] Based on temporal correlation, a user behavior feature sequence was constructed, including behavior duration, frequency, intensity, and spatial location. It was determined that users' viewing behavior in the cultural relic display area lasted an average of 120 seconds. Users issued the "details" voice command five times per hour. Heart rate fluctuations were greatest during performances, with an average fluctuation of 15 beats per minute. Users' primary activity area was concentrated in the center of the exhibition hall, with coordinates ranging from (35.2, 42.8) to (68.5, 75.3). Trends in user behavior feature sequences were calculated at different time scales, including 10-minute, 30-minute, and 60-minute scales. Analysis showed that the duration of user viewing decreased at the 60-minute scale, from an initial 120 seconds to 85 seconds. The frequency of voice commands increased initially and then decreased at the 30-minute scale. Heart rate fluctuations were highly correlated with the display content at all time scales.

[0079] Environmental information about cultural tourism scenes is collected, including light intensity, crowd density, and the distribution of cultural elements. Light intensity is collected by light sensors placed throughout the scene, with a value range of 0 to 1000 lux. Crowd density is calculated using a video analysis system, with density levels categorized as low (0-0.2 people / m2), medium (0.2-0.5 people / m2), and high (>0.5 people / m2). Cultural element distribution information includes the type of exhibits, historical value level, and interactivity level, and is obtained through scene preset information.

[0080] The user behavior feature sequence is mapped to the scene grid corresponding to the cultural tourism scene according to the spatial location. The scene is divided into 10m × 10m grid units, forming a 15 × 20 grid matrix. Based on the user's stay time, interaction frequency, emotional changes and physiological indicator changes in each grid, the behavioral activity score (0-100 points) of each grid is calculated. For example, in the ancient clothing display area (grid coordinates [5, 8]), the user behavior activity is 85 points; in the rest area (grid coordinates [12, 3]), the user behavior activity is 25 points. The activity difference between different grids is calculated. The average difference between adjacent grids is 18 points, and the maximum difference is 65 points (between the cultural relics display area and the aisle area).

[0081] Combining the changing trends of user behavior feature sequences with grid activity differences, a scene interaction data stream is generated, containing both real-time and predicted interaction data. The real-time status displays the current user's activity level, emotional state, and interaction propensity in each grid. The predicted status, based on historical data and current trends, predicts potential changes in user behavior over the next 30 minutes. For example, it is predicted that if light intensity decreases by 10%, user dwell time in the display area will increase by 15%, while if crowd density increases by 0.2 people per square meter, the frequency of user voice interactions will decrease by 20%.

[0082] In this embodiment, by collecting multi-dimensional initial interaction data, comprehensive perception of user interaction behavior is achieved, a time dimension correlation matrix is ​​constructed to extract temporal correlation, and through multi-scale analysis of user behavior feature sequences, the dynamic changes of user behavior patterns are effectively captured. By mapping user behavior feature sequences to scene grids and combining environmental factors, a refined scene-behavior correlation model is established, which realizes real-time state perception and predictive state evaluation of scene interaction data.

[0083] In an optional embodiment,

[0084] The interactive space is divided based on the scene interaction data stream, the activity and emotional intensity of users in each space are calculated and a spatial vitality map is generated. The energy difference between adjacent spaces is calculated based on the spatial vitality map, and the lighting gradient coefficient is determined. The real-time changes in spatial vitality are tracked based on the lighting gradient coefficient, and a dynamic mapping relationship of lighting effects is established, including:

[0085] Dividing the cultural tourism scene into multiple interactive spaces based on the scene interaction data stream, establishing a three-dimensional coordinate system in the interactive space, dividing the interactive space into multiple grid units, and calculating the ratio of the number of interactive events in each grid unit to the grid volume to obtain the interaction density;

[0086] Calculate the weighted sum of the basic behavior intensity, movement trajectory complexity, and interaction density of each user in the interactive space to obtain user activity; calculate the weighted sum of the physiological characteristic emotion value, voice emotion value, and gesture emotion value of each user in the interactive space to obtain emotion intensity; and perform a linear weighted combination of the user activity and the emotion intensity to obtain a spatial vitality map;

[0087] Determining the spatial vitality corresponding to each interactive space based on the spatial vitality map, calculating the absolute difference between the vitality values ​​of the center points of adjacent interactive spaces to obtain an energy difference, substituting the energy difference into an exponential function to obtain a light gradient coefficient, wherein the input of the exponential function is the negative of the ratio of the energy difference to a preset energy threshold parameter;

[0088] Based on the light gradient coefficient, the real-time changes in spatial vitality are tracked, the crowd flow characteristics are extracted to calculate the dynamic partition boundaries, a cross-region gradient function is constructed to optimize the light gradient coefficient, the group behavior pattern is identified to predict the vitality change trend and perform error compensation, and a dynamic mapping relationship between the real-time changes in spatial vitality and the lighting effects is established.

[0089] Figure 2 Generate a system structure diagram for cultural tourism lighting art effects based on multimodal embodied interaction, such as Figure 2As shown, the pre-collected scene interaction data stream is obtained, the interaction data is analyzed using a spatial clustering algorithm, and the entire cultural tourism scene is divided into multiple interaction spaces according to the spatial distribution characteristics of the interaction events. In each interaction space, a three-dimensional rectangular coordinate system is established, with the origin set at the geometric center of the space, and the X-axis, Y-axis, and Z-axis corresponding to the east-west, north-south, and vertical directions, respectively. Each interaction space is further divided into grid cells of size 0.5 m × 0.5 m × 0.5 m, and the number of interaction events in each grid cell is calculated and divided by the grid volume (0.125 cubic meters) to obtain the interaction density. For example, if 15 interaction events are recorded in a grid cell, the interaction density of the grid cell is 15 / 0.125=120 times / cubic meter.

[0090] For the calculation of user activity in each interactive space, three factors are taken into consideration: basic behavior intensity, motion trajectory complexity, and interaction density. Basic behavior intensity is obtained by analyzing the amplitude and frequency of the user's body movements. For example, a value of 0.2 is assigned to the static state, 0.5 to the walking state, 0.8 to the running state, and 1.0 to the jumping state. The complexity of the motion trajectory is obtained by calculating the curvature and turning frequency of the user's movement path. For example, the complexity of straight-line movement is 0.3, the complexity of curved movement is 0.6, and the complexity of frequent turning is 0.9. The system assigns weights of 0.4, 0.3, and 0.3 to the basic behavior intensity, motion trajectory complexity, and interaction density, respectively, and takes a weighted sum to obtain the user activity. For example, if a user is walking (0.5), their trajectory is a curved movement (0.6), and the interaction density of their grid unit is 120 times / cubic meter (normalized to 0.7), then the user's activity level is 0.5×0.4+0.6×0.3+0.7×0.3=0.59.

[0091] The calculation of emotion intensity comprehensively considers physiological emotion values, voice emotion values, and gesture emotion values. The physiological emotion value is determined by user feedback on preference. The voice emotion value is derived by analyzing the pitch, volume, and speed of the user's voice. For example, a calm tone is assigned a value of 0.2, an excited tone is assigned a value of 0.7, and a cheering tone is assigned a value of 0.9. The gesture emotion value is obtained by identifying the user's gestures. For example, a directional gesture is assigned a value of 0.4, a waving gesture is assigned a value of 0.6, and a hand-raising gesture is assigned a value of 0.9. The system assigns weights of 0.4, 0.3, and 0.3 to the physiological emotion values, voice emotion values, and gesture emotion values, respectively, and then sums them to obtain the emotion intensity. For example, if a user has a heart rate of 90 bpm (0.6), speaks with an excited tone (0.7), and makes a waving gesture (0.6), the user's emotion intensity is 0.6 × 0.4 + 0.7 × 0.3 + 0.6 × 0.3 = 0.63.

[0092] The spatial vitality map is generated by linearly weighting the user's activity and sentiment intensity, with weights of 0.5 and 0.5, respectively. For example, if the user's activity is 0.59 and the sentiment intensity is 0.63, then the user's spatial vitality value is 0.59 × 0.5 + 0.63 × 0.5 = 0.61. The average spatial vitality value of all users in the interactive space is calculated as the overall spatial vitality of the interactive space. For example, if there are five users in an interactive space, and their spatial vitality values ​​are 0.61, 0.58, 0.72, 0.65, and 0.53, respectively, then the overall spatial vitality of the interactive space is (0.61 + 0.58 + 0.72 + 0.65 + 0.53) / 5 = 0.618.

[0093] Based on the generated spatial vitality map, the energy difference between adjacent interactive spaces is calculated. The absolute difference in the vitality values ​​of the center points of adjacent interactive spaces is used as the energy difference. For example, the vitality value of the center point of space A is 0.618, and the vitality value of the center point of the adjacent space B is 0.452. The energy difference between them is |0.618-0.452|=0.166. The system substitutes the energy difference into the exponential function to calculate the light gradient coefficient. The exponential function is defined as the negative power of e, and the power value is the ratio of the energy difference to the preset energy threshold parameter. If the energy threshold parameter is set to 0.2, the light gradient coefficient is e^(-(0.166 / 0.2))=e^(-0.83)≈0.436.

[0094] The calculated lighting gradient coefficient is used to track real-time changes in spatial vitality. By analyzing the crowd flow characteristics in the monitoring data, the system updates the dynamic partition boundaries in real time. For example, when an increase in the flow of people between two originally independent interaction areas is detected, the system adjusts the boundaries of the two areas to form a transition area. The system constructs a cross-area gradient function to create a smooth transition of lighting effects between adjacent areas. For example, if the light brightness of two adjacent areas is 80% and 50% respectively, and the gradient coefficient is 0.436, the light brightness in the transition area will change smoothly from 80% to 50%, and the rate of change is controlled by the gradient coefficient.

[0095] Table 1: Lighting effect dynamic mapping experiment results;

[0096]

[0097] Table 1 systematically presents the mapping relationship between spatial vitality values ​​and lighting parameters, as well as user experience evaluation. In the five main interactive spaces and two transition areas, spatial vitality values ​​exhibit a clear positive correlation with lighting brightness, color temperature, and change rate.

[0098] High-vibrancy spaces (e.g., Space 3, with a Vibrancy value of 0.723) corresponded to higher lighting brightness (85%), color temperature (4500K), and a change rate (7.2 times / minute), and received the highest user satisfaction rating (9.1). In contrast, low-vibrancy spaces (e.g., Space 4, with a Vibrancy value of 0.385) used softer lighting parameters (50% brightness, 3500K color temperature) and a slower change rate (3.8 times / minute).

[0099] Of particular note is the data from the transition zone, demonstrating the system's successful implementation of a smooth lighting transition. The parameters of transition zones 1-2 all fall between those of spaces 1 and 2, demonstrating the effective application of the lighting gradient coefficient. User satisfaction scores (averaging 8.3 points) demonstrate the significant effectiveness of dynamic lighting mapping technology in enhancing the immersive experience of cultural and tourism scenarios.

[0100] Machine learning algorithms identify group behavior patterns and predict trends in vitality. For example, when a group of tourists is detected approaching a particular attraction, the area's vitality is predicted to rise within a short period of time. Furthermore, by comparing predicted values ​​with actual collected data to compensate for errors, the accuracy of the prediction model is continuously optimized. A dynamic mapping relationship is established between real-time changes in spatial vitality and lighting effects, encompassing parameters such as brightness, color temperature, color, and rate of change. This allows lighting effects to adaptively respond to changes in spatial vitality, creating an immersive lighting experience for cultural and tourism scenarios.

[0101] In this embodiment, the refined division of the interactive space is achieved through the quantitative calculation of the interaction density of grid units, which provides a basic metric for vitality assessment. The spatial vitality map is constructed in combination with user activity to comprehensively characterize the spatial vitality characteristics. The lighting gradient coefficient is obtained through energy difference calculation and exponential function mapping, and a quantitative correlation between spatial vitality and lighting effects is established, achieving a smooth transition of lighting effects. Based on the dynamic analysis of crowd flow characteristics and group behavior patterns, a cross-regional gradient function and error compensation mechanism are constructed to ensure the real-time response accuracy of lighting effects to changes in spatial vitality.

[0102] In an optional embodiment,

[0103] Based on the light gradient coefficient, the real-time changes in spatial vitality are tracked, crowd flow characteristics are extracted to calculate dynamic partition boundaries, a cross-region gradient function is constructed to optimize the light gradient coefficient, group behavior patterns are identified, vitality change trends are predicted, and error compensation is performed. The dynamic mapping relationship between the real-time changes in spatial vitality and lighting effects is established, including:

[0104] Acquire real-time data on changes in spatial vitality, generate a vitality mapping baseline value based on the real-time data on changes in spatial vitality and a preset light gradient coefficient, collect crowd movement data within the interactive space, extract crowd flow characteristics, and multiply the crowd flow characteristics by the crowd density of the interactive space to calculate the flow intensity;

[0105] Generate an adjustment factor for the dynamic partition boundary based on the difference in crowd flow characteristics and crowd density between adjacent interactive spaces, and adjust the boundaries of adjacent interactive spaces based on the adjustment factor;

[0106] Constructing a cross-region gradient function for the adjacent interactive spaces, substituting the flow intensity and spatial distance into the cross-region gradient function, and fusing the calculated result with the preset light gradient coefficient to generate an optimized light gradient coefficient;

[0107] Extracting group behavior pattern characteristics based on the flow intensity, inputting the group behavior pattern characteristics and pre-collected historical vitality data into a prediction model to calculate a vitality change trend, performing error compensation on the vitality change trend and the real-time collected spatial vitality data, and outputting a compensated spatial vitality mapping value;

[0108] A dynamic mapping function is established based on the compensated space vitality mapping value, the optimized light gradient coefficient and the pre-set environmental constraint parameters, and a dynamic mapping relationship is established between the real-time changes in the space vitality and the lighting effects. The dynamic mapping relationship is dynamically adjusted with the change rate of the compensated space vitality mapping value and the change rate of the optimized light gradient coefficient.

[0109] In interactive spaces, a sensor network collects real-time spatial vitality data, including metrics such as foot traffic, dwell time, and movement speed. The initial light gradient coefficient matrix is ​​preset to [0.3, 0.5, 0.7, 0.9], corresponding to different levels of vitality. The collected vitality data is normalized and then weighted averaged with the preset light gradient coefficients to generate a vitality mapping baseline value. For example, if an area has a vitality value of 0.65 and a corresponding light gradient coefficient of 0.7, the resulting vitality mapping baseline value is 0.675.

[0110] A camera array installed within the interactive space collects crowd movement data at a rate of 25 frames per second. Image processing algorithms extract crowd flow characteristics, including flow direction vectors and flow velocity scalars. The area is divided into 10×10 grid cells, and the crowd density is calculated for each grid cell. Fifteen people are detected within a grid cell with an area of ​​25 square meters, resulting in a crowd density of 0.6 people / square meter. Multiplying the crowd flow velocity of 0.8 m / s for this grid cell by the crowd density of 0.6 people / square meter yields a flow intensity of 0.48.

[0111] Dynamic boundary adjustments between adjacent interactive spaces are based on differences in crowd flow characteristics and crowd density. The difference in flow characteristics between adjacent areas A and B is calculated over a 5-second period. If the flow velocity in area A is 0.9 m / s and in area B is 0.6 m / s, the difference is 0.3 m / s; if the crowd density in area A is 0.7 people / m2 and in area B is 0.5 people / m2, the difference is 0.2 people / m2. These two differences are multiplied by the weight coefficients [0.6, 0.4] to obtain an adjustment factor of 0.26. When the adjustment factor exceeds the preset threshold of 0.25, the boundary is adjusted 2 meters toward area B, where the crowd density is lower, to achieve dynamic zoning.

[0112] The cross-region gradient function uses an exponential decay model. The flow intensities in adjacent regions A and B are 0.48 and 0.36, respectively, and the actual distance between the regions is 15 meters. Substituting the flow intensity and spatial distance into the cross-region gradient function, the calculated decay coefficient is 0.08. The original preset light gradient coefficients are [0.3, 0.5, 0.7, 0.9]. After integrating the decay coefficients, the optimized light gradient coefficients are adjusted to [0.324, 0.54, 0.756, 0.972].

[0113] Group behavior pattern feature extraction is based on the time-series variation of flow intensity. Using a 30-minute observation window, the changing pattern of flow intensity is analyzed. Extracted features include peak intensity, fluctuation frequency, and duration. The time-series data for flow intensity in a certain area from 12:00 PM to 12:30 PM on weekdays is [0.25, 0.37, 0.52, 0.68, 0.72, 0.65, 0.48, 0.31]. The extracted features are: peak intensity 0.72, fluctuation frequency 0.0667 Hz, and duration 30 minutes. These features, along with historical activity data, are input into a prediction model to predict activity trends over the next 30 minutes. The predicted results are [0.28, 0.42, 0.58, 0.65, 0.60, 0.52, 0.39, 0.27].

[0114] The real-time spatial activity data collected is [0.30, 0.45, 0.60, 0.68, 0.63, 0.54, 0.40, 0.29]. The error is calculated with the predicted results to obtain the error sequence [0.02, 0.03, 0.02, 0.03, 0.03, 0.02, 0.01, 0.02]. The error compensation algorithm is applied to fuse the error sequence with the predicted results, and the compensated spatial activity map value is output as [0.29, 0.44, 0.59, 0.67, 0.62, 0.53, 0.40, 0.28].

[0115] During the creation of the dynamic mapping function, the compensated spatial vitality mapping value, the optimized lighting gradient coefficient, and environmental constraints are combined. These constraints include a maximum illuminance of 300 lux, a minimum illuminance of 50 lux, and a color temperature range of 3000K-5000K. The dynamic mapping function converts the compensated spatial vitality mapping value of 0.67 into corresponding lighting parameters: an illuminance of 218 lux, a color temperature of 4200K, and a lighting gradient time of 1.5 seconds. If the rate of change of the spatial vitality mapping value exceeds 15%, the rate of change of the lighting gradient coefficient is dynamically adjusted. For example, if the vitality mapping value drops rapidly from 0.67 to 0.53 (a rate of change of 20.9%), the rate of change of the lighting gradient coefficient is automatically increased from the standard 10% to 16%, making the lighting effect more sensitive to changes in spatial vitality.

[0116] In this embodiment, a dynamic boundary adjustment mechanism based on flow intensity is established by incorporating a comprehensive analysis of crowd flow characteristics and density. This effectively addresses the boundary mutation problem caused by traditional fixed partitions. The dynamic mapping mechanism enables adaptive adjustment of lighting effects based on the rate of change of spatial vitality and the rate of change of the gradient coefficient. This ensures that lighting effects are sensitive to changes in spatial vitality while avoiding excessive and frequent lighting adjustments.

[0117] Existing technologies typically adjust the lighting effects of interactive spaces using fixed mapping relationships or simple linear transformations. These adjustments fail to accurately respond to dynamic changes in spatial activity and are prone to sudden changes in lighting effects at spatial partition boundaries, impacting the continuity of the lighting experience. This lack of in-depth analysis of crowd activity patterns makes it difficult to predict changing trends in spatial activity, leading to lags in lighting adjustment and an inability to adapt promptly to rapid changes in spatial activity.

[0118] This embodiment achieves a smooth transition of lighting effects between adjacent spaces by constructing a cross-region gradient function, thereby improving the continuity of the lighting experience. It combines real-time data for error compensation, significantly improving the real-time and accuracy of lighting adjustment. Through the fusion analysis and dynamic optimization of multi-dimensional data, it realizes the intelligent linkage between lighting effects and spatial vitality, improves the lighting system's ability to adapt to changes in spatial vitality, and provides a new technical approach to improving the lighting experience of interactive spaces.

[0119] Figure 3This diagram shows a performance comparison of cultural and tourism lighting art effect systems based on multimodal embodied interaction. This system demonstrates significant advantages across all evaluation dimensions. In terms of boundary transition smoothness, this system achieved 78.2%, significantly higher than the 32.5% achieved by traditional fixed mapping and the 48.8% achieved by simple dynamic adjustment, demonstrating that this system effectively addresses the issue of sudden changes in lighting effects at spatial boundaries. Regarding the vitality change response time metric, this system achieved an 84.3% score, reflecting its sensitivity to changes in spatial vitality, an improvement of approximately 33 percentage points compared to traditional methods.

[0120] Particularly impressive is the system's prediction accuracy. By incorporating group behavior pattern analysis and an error compensation mechanism, this system has increased prediction accuracy to 86.2%, more than double the 39.6% achieved by traditional fixed mapping methods. User satisfaction scores also confirm the successful translation of technological advantages into an improved experience, with this system achieving a high satisfaction rate of 87.3%, significantly outperforming other solutions.

[0121] In an optional embodiment,

[0122] Outputting and executing lighting control instructions according to the dynamic mapping relationship, generating an initial lighting effect, and collecting user interactive feedback data on the initial lighting effect include:

[0123] Output and execute lighting control instructions according to the dynamic mapping relationship, wherein the lighting control instructions include lighting brightness, color temperature and gradient timing parameters;

[0124] generating an initial lighting effect according to the lighting control instruction, wherein the initial lighting effect is dynamically adjusted as the vitality of the space changes in real time;

[0125] Collect user interaction feedback data on the initial lighting effect, wherein the interaction feedback data includes user stay time, interaction frequency and pre-set emotional feedback indicators.

[0126] Acquire spatial vitality data, including indicators such as crowd density, activity frequency, and ambient noise. For example, an infrared sensor array is used to monitor changes in crowd flow within a 10m x 10m space at a sampling rate of four times per second. Motion sensors record the number of changes in a person's position per unit time (e.g., per minute). A noise sensor is also used to measure ambient decibel levels, with a threshold set between 45 and 75 decibels. An increase in crowd density from 0.1 to 0.3 people per square meter indicates increased spatial vitality. An increase in ambient noise from 45 to 60 decibels also indicates increased activity.

[0127] When establishing a dynamic mapping relationship, spatial activity data is mapped to lighting parameters. When the pedestrian density is 0.1 people / square meter, the lighting brightness is set to 300 lumens; when the pedestrian density increases to 0.3 people / square meter, the brightness is increased accordingly to 500 lumens. Similarly, when the ambient noise level is 45 decibels, the lighting color temperature is set to 2700K (warm white light); when the noise level rises to 60 decibels, the color temperature is adjusted to 4000K (neutral white light). When the frequency of human activity changes position 1-2 times per minute, the lighting gradient cycle is set to 30 seconds; when the frequency increases to 5-6 times per minute, the gradient cycle is shortened to 10 seconds, providing a more dynamic lighting effect.

[0128] During the lighting control command output and execution phase, based on the mapping relationship, lighting control commands are generated in real time, including brightness, color temperature, and gradient timing. These commands are transmitted to the lighting control module via wireless communication protocols such as ZigBee, Wi-Fi, or Bluetooth 5.0. For example, if a crowd density of 0.2 people / square meter, ambient noise of 55 decibels, and a movement frequency of three position changes per minute are detected, the command is generated: brightness 400 lumens, color temperature 3500K, and gradient period 20 seconds. After receiving the command, the control module controls the LED driver circuit via PWM (pulse width modulation) signals, precisely adjusting the output power to achieve brightness control; adjusting the ratio of cool and warm LEDs to achieve color temperature; and executing the lighting effect transition according to the specified gradient timing parameters.

[0129] During the initial lighting effect generation phase, the lighting effects are adjusted in real time based on control commands, dynamically responding to changes in spatial activity. When a change in spatial activity from low to high is detected (for example, the crowd density increases from 0.1 to 0.25 people / square meter within 5 minutes), the lighting brightness is gradually transitioned from 300 lumens to 450 lumens, the color temperature is increased from 2700K to 3500K, and the gradient cycle is shortened from 30 seconds to 15 seconds. This gradual change avoids abrupt lighting changes and provides users with a comfortable light environment adaptation process. To identify specific activity patterns, such as when people gather at the beginning of a meeting but the frequency of activity decreases, the system maintains a medium brightness (e.g., 400 lumens) but adjusts to a meeting-appropriate color temperature (e.g., 4000K). The gradient cycle is then extended to 45 seconds to reduce distractions.

[0130] During the stage of collecting user interaction feedback data, various sensor devices are used to record user reactions to lighting effects. User dwell time is measured by position sensors, which record how long users stay under specific lighting effects. For example, when the light is set to 400 lumens and 3500K color temperature, the average user dwell time is 15 minutes; while at 500 lumens and 4000K, the average dwell time is shortened to 8 minutes, indicating that users prefer the former setting. The frequency of interaction records the number of times users adjust the lights through the control panel, voice or gestures. Experimental data shows that in dynamic response mode, the average number of times users adjust the lights per hour is reduced from 7-8 times with traditional fixed lighting to 2-3 times, proving that the system's automatic adjustment is more in line with user needs.

[0131] Emotional feedback indicators are collected through an intelligent questionnaire system to collect subjective scores after user experience, and the comfort level is evaluated using a 1-10 point system.

[0132] In this embodiment, by establishing a dynamic mapping relationship to output lighting control instructions, real-time response of lighting effects to changes in spatial vitality is achieved, so that the lighting effects can accurately reflect the dynamic changing characteristics of spatial vitality. Through the dynamic adjustment mechanism of the initial lighting effect, the lighting system can continuously track the changing trend of spatial vitality, ensure the synchronization of lighting effects and spatial vitality status, and improve the continuity and smoothness of lighting control. Based on the collection of multi-dimensional interactive data such as user residence time, interaction frequency and emotional feedback, an evaluation and feedback mechanism for lighting effects is established, which provides effective data support for the optimization of lighting control strategies.

[0133] In an optional embodiment,

[0134] Based on the interactive feedback data, extracting user preference characteristics for lighting effects, constructing a lighting effect evaluation index, optimizing and ranking lighting control parameters according to the lighting effect evaluation index, establishing a parameter optimization strategy, and iteratively adjusting lighting control instructions based on the parameter optimization strategy to generate optimal lighting control instructions includes:

[0135] Collecting user interactive feedback data on lighting effects, constructing a multidimensional feature vector based on user dwell time, interaction frequency, and emotional feedback indicators in the interactive feedback data, and inputting the multidimensional feature vector into a pre-set user preference scoring module to obtain a preference score;

[0136] Performing weighted fusion of the preference score, the comfort index, and the spatial coordination index to generate a comprehensive evaluation value, and constructing a time series evaluation matrix based on the comprehensive evaluation value, wherein the time series evaluation matrix includes a sequence of evaluation values ​​within a historical time window;

[0137] Calculate the sensitivity of the comprehensive evaluation value to the lighting control parameters, use kernel density estimation to build a parameter sensitivity distribution module, suppress the influence of abnormal samples through iterative reweighted least squares method, and determine the parameter priority and sort based on historical optimization results;

[0138] Based on the sorting results of the lighting control parameters, a parameter optimization objective function is sequentially constructed, with minimizing the mean square error of the evaluation value sequence in the time series evaluation matrix as the optimization objective, and the amplitude of parameter changes at adjacent moments as a constraint condition. The lighting control parameters are gradient iteratively updated based on the optimization objective function, and the iteration is stopped when the difference between the comprehensive evaluation values ​​at adjacent moments is less than a preset threshold, and the optimized lighting control parameters are output;

[0139] According to the optimized lighting control parameters and the preset environmental constraint parameters, the optimal lighting control instructions are generated in combination with the preset dynamic gain matrix.

[0140] A questionnaire survey collects user feedback on lighting effects, including user dwell time, interaction frequency, and emotional feedback. For example, if users adjust the lighting less frequently under a certain lighting effect, it indicates that the lighting effect better meets user needs. For example, if users report an increase in smiling under a specific lighting effect, a positive score is assigned.

[0141] The collected data is constructed into a multidimensional feature vector, where dwell time is measured in seconds, ranging from 0 to 3600 seconds; interaction frequency is the number of operations per hour, ranging from 0 to 100 times; and the emotional feedback index ranges from -1 to 1, with 1 indicating extreme satisfaction and -1 indicating extreme dissatisfaction. In practical applications, for an office environment with a color temperature of 5000K and a brightness of 500 lux, if the user dwells for 2 hours, interacts 5 times per hour, and the emotional feedback index is 0.8, the constructed feature vector is [7200, 5, 0.8].

[0142] The constructed multidimensional feature vector is input into a pre-configured user preference scoring module. Using a support vector machine-based scoring algorithm, the input feature vector is mapped to a preference score range of 0-100. During the training phase, the model is trained using a labeled user feedback dataset. For example, a feature vector of [7200, 5, 0.8] might be mapped to a high preference score of 85.

[0143] After obtaining the preference score, a comprehensive evaluation is conducted based on objective lighting effect evaluation indicators. The comfort index is calculated based on the matching degree of color temperature, brightness, and ambient brightness, ranging from 0-100. The spatial coordination index measures the uniformity and layering of lighting within the space, also ranging from 0-100. These three indicators are weighted and combined, with the weights assigned as follows: preference score 0.5, comfort index 0.3, and spatial coordination index 0.2, to generate a comprehensive evaluation value. For example, if the preference score is 85, the comfort index is 90, and the spatial coordination index is 80, the comprehensive evaluation value is 85 × 0.5 + 90 × 0.3 + 80 × 0.2 = 85.5.

[0144] The comprehensive evaluation values ​​in continuous time are organized into a time series evaluation matrix, and the evaluation values ​​every 30 minutes in the past 24 hours are recorded to form an evaluation sequence of 48 time points.

[0145] For lighting control parameter optimization, calculate the sensitivity of the comprehensive evaluation value to each control parameter. Control parameters include brightness (range: 100-1000 lux), color temperature (range: 2700-6500K), and illumination angle (range: 0-180 degrees). By making small adjustments to these parameters and observing the rate of change in the comprehensive evaluation value, we determine the sensitivity. For example, if the comprehensive evaluation value changes from 85.5 to 88.0 when the brightness is adjusted from 500 lux to 550 lux, the sensitivity is 0.05 (every 1% change results in a 0.05% increase in the evaluation value).

[0146] A parameter sensitivity distribution model is constructed using kernel density estimation. Each parameter sensitivity sample in the historical data is weighted to generate a continuous sensitivity distribution curve. To mitigate the impact of outliers, the system applies iterative reweighted least squares, dynamically adjusting sample weights based on their deviation from the central trend. For example, if the majority of the data indicates a brightness sensitivity range of 0.04-0.06, but a few samples show a sensitivity of 0.2, the system will downweight these outliers.

[0147] Based on parameter sensitivity analysis and historical optimization results, the parameters are prioritized and sorted. In actual applications, if the analysis results show that the color temperature sensitivity is 0.08, the brightness sensitivity is 0.05, and the illumination angle sensitivity is 0.03, the optimization order is color temperature, brightness, and illumination angle.

[0148] Based on the sorting results, we construct parameter optimization objective functions one by one. Taking color temperature as an example, the objective function aims to minimize the mean square error of the evaluation value sequence in the time series evaluation matrix. At the same time, we limit the color temperature change between adjacent moments to no more than 200K to avoid abrupt changes that affect the user experience. We iteratively update the parameter values ​​using gradient descent, stopping the iteration when the difference in the comprehensive evaluation value between consecutive iterations is less than 0.5.

[0149] In this embodiment, the efficient integration of user interaction data is achieved through the construction of multi-dimensional feature vectors, which can fully capture the user's experience feedback on lighting effects, integrate user preference scores with comfort indicators and spatial coordination indicators, establish a comprehensive evaluation system that takes into account multiple needs, and improve the scientificity and reliability of the evaluation results. By constructing a time series evaluation matrix, the evaluation information in the historical optimization process is retained, providing a more complete decision-making basis for parameter optimization. The sensitivity analysis method based on kernel density estimation improves the accuracy of parameter importance assessment. The iterative reweighting mechanism effectively reduces the interference effect of abnormal samples, making the parameter priority sorting more stable and reliable. The optimization strategy based on minimizing the mean square error of the evaluation value sequence is adopted, which not only ensures the stability of the lighting effect, but also avoids drastic fluctuations by constraining the parameter change amplitude at adjacent moments.

[0150] In an optional embodiment,

[0151] Calculate the sensitivity of the comprehensive evaluation value to the lighting control parameters, use kernel density estimation to build the parameter sensitivity distribution module, suppress the influence of abnormal samples through iterative reweighted least squares method, and determine the parameter priority and sorting based on historical optimization results, including:

[0152] Obtain historical adjustment data of lighting control parameters and corresponding preference scores. Based on the historical adjustment data and corresponding preference scores, calculate the first-order sensitivity of the comprehensive evaluation value to the lighting control parameters through partial derivatives, calculate the second-order interactive sensitivity through mixed partial derivatives, and construct the Jacobian matrix using the central difference method to obtain an initial sensitivity sequence;

[0153] A Gaussian kernel function is used to perform kernel density estimation on the initial sensitivity sequence, an optimal bandwidth parameter is adaptively calculated based on the sample standard deviation, the initial sensitivity sequence is transformed by the kernel function to obtain a continuous probability distribution, and the distribution characteristics of the parameter sensitivity are output;

[0154] A Huber-type M-estimation loss function is constructed to detect anomalies of the distribution characteristics of the parameter sensitivity, a sample weight matrix is ​​adaptively calculated based on the residual size, the sample weight matrix is ​​applied to an iterative reweighted least squares calculation, the influence of abnormal samples is suppressed through multiple rounds of iterative optimization, and a corrected sensitivity value is output;

[0155] Calculate the time series weight of the pre-acquired historical evaluation data based on the time decay exponential function, and perform weighted summation of the time series weight and the historical comprehensive evaluation value to obtain the historical optimization effect of the parameters;

[0156] The corrected sensitivity value, the historical parameter optimization effect, and the parameter stability index are subjected to multi-objective weighted fusion to determine the parameter priority. The lighting control parameters are sorted in descending order according to the parameter priority to generate a parameter optimization sequence table, wherein the parameter stability index includes parameter fluctuation amplitude, convergence speed, and disturbance recovery.

[0157] Collect historical lighting control data, including parameters such as brightness, color temperature, and illuminance, and their corresponding user preference scores. The scores are based on the subjective evaluation of the lighting effects under different parameter combinations by the experiment participants on a 1-10 scale.

[0158] The collected parameter data matrix P and the corresponding score matrix S are processed. P contains n sets of parameter records, each containing m control parameters, such as {brightness: 80%, color temperature: 4500K, illuminance: 650lux}. The first-order sensitivity is calculated for each parameter by taking the partial derivative of the comprehensive evaluation value with respect to that parameter. For example, when calculating the sensitivity of the brightness parameter, the brightness is varied from 70% to 90%, and the score changes from 7.2 to 8.4, resulting in a preliminary sensitivity of 0.06. Using the central difference method, small positive and negative perturbations are made to the parameters and the changes in the evaluation values ​​are recorded. For example, if the brightness fluctuates by 5% at the 85% point, the score changes by ±0.3, resulting in a sensitivity of 0.03 at that point.

[0159] When calculating second-order interaction sensitivity, adjust two parameters simultaneously and observe the change in the score. For example, adjust brightness and color temperature simultaneously, record the change in the score, and obtain the interaction sensitivity matrix. Summarize all the calculation results to construct a complete Jacobian matrix. Each element in the matrix represents the sensitivity value of the corresponding parameter, such as brightness 0.042, color temperature 0.035, illuminance 0.028, and so on, forming the initial sensitivity sequence.

[0160] To obtain more accurate sensitivity distribution characteristics, a kernel density estimation method was used. A Gaussian kernel function was selected as the basic kernel function and the initial sensitivity sequence was transformed. The bandwidth parameter h was adaptively calculated and determined based on the sample standard deviation. For example, if the sensitivity sample standard deviation was 0.018, the bandwidth parameter was set to 0.015. A kernel function transformation was applied to the sensitivity sequence of each parameter, converting discrete sensitivity values ​​into a continuous probability distribution. For example, the sensitivity distribution peak for the brightness parameter occurs near 0.045, indicating that this parameter has the most significant impact around this value.

[0161] Identify and address the impact of outliers on sensitivity calculations, and construct a Huber-type M-estimation loss function. Set the threshold k to 1.345. Use a squared loss when the absolute value of the residual is less than k, and a linear loss when it is greater than k. Initial fitting yields a brightness sensitivity of 0.042. For an outlier sample with a residual of 2.6, the system calculates a weight of 0.52 for this sample based on the Huber function. Construct a sample weight matrix W, where the diagonal elements represent the sample weights, such as diag(1.0, 0.95, 0.52, ...).

[0162] An iterative reweighted least squares method was applied, updating the parameter sensitivity estimates in each iteration. After the first iteration, the brightness sensitivity was adjusted from 0.042 to 0.039. After five iterations, it converged to 0.038, which was determined as the final corrected value. Similarly, corrected sensitivity values ​​for other parameters were obtained, such as color temperature (0.033) and illuminance (0.027).

[0163] Taking into account historical optimization results, a time-decay exponential function is introduced to calculate historical data weights. Recent data is weighted more heavily, while long-term data is weighted less heavily. For example, data from the past week is weighted 0.8, data from a month ago is weighted 0.5, and data from three months ago is weighted 0.2. Combining the time series weights with the historical evaluation values, the historical optimization scores for brightness parameters are calculated to be 8.2, color temperature 7.8, and illuminance 7.5.

[0164] Evaluate parameter stability indicators, including the system's ability to return to a stable state after parameter adjustments. The measured luminance parameter fluctuation range was ±3%, with a convergence time of 1.2 seconds and a disturbance resilience of 0.92; the color temperature fluctuation range was ±150K, with a convergence time of 1.5 seconds and a disturbance resilience of 0.88; and the illuminance fluctuation range was ±50 lux, with a convergence time of 1.8 seconds and a disturbance resilience of 0.85.

[0165] The corrected sensitivity value, historical optimization effect, and stability index are subjected to a multi-objective weighted fusion. The sensitivity weight is set to 0.5, the historical effect weight is set to 0.3, and the stability weight is set to 0.2. The calculated overall priority of brightness is 0.81, color temperature is 0.76, and illuminance is 0.71. The parameters are sorted in descending order based on the overall priority to generate an optimization sequence table: brightness (0.81), color temperature (0.76), illuminance (0.71), color rendering index (0.68), and projection angle (0.65). The lighting control system optimizes parameters according to this sequence table, prioritizing high-priority parameters to improve optimization efficiency and meet user lighting environment preferences.

[0166] In this embodiment, a joint analysis mechanism of first-order sensitivity and second-order interactive sensitivity is introduced. The Jacobian matrix is ​​constructed to achieve a comprehensive evaluation of the independent influence and interaction of parameters. A robust outlier processing mechanism is established by introducing the Huber-type M-estimation loss function and iterative reweighted least squares method, which effectively reduces the interference of abnormal samples on sensitivity calculation.

[0167] In existing technologies, optimizing and ranking lighting control parameters typically uses a single sensitivity analysis method. This method only considers the simple linear relationship between parameters and evaluation indicators, ignoring the interaction between parameters. This method has limited ability to handle abnormal data and is susceptible to noise interference, resulting in unstable parameter importance assessment results. It also tends to neglect the use of historical optimization experience, making it impossible to effectively inherit existing optimization results.

[0168] This embodiment uses the kernel density estimation method to perform continuous processing on the sensitivity sequence, which improves the reliability of sensitivity analysis and makes parameter importance assessment more accurate. The design of timing weights fully utilizes historical optimization experience, enabling the system to inherit and develop existing optimization results. By introducing stability indicators such as parameter fluctuation amplitude, convergence speed, and disturbance recovery, a comprehensive parameter evaluation system is constructed, which achieves accurate evaluation and reliable ranking of the importance of lighting control parameters, provides a more scientific decision-making basis for subsequent parameter optimization, and improves the optimization efficiency of the lighting control system and the stability of the control effect.

[0169] A second aspect of an embodiment of the present invention provides a multimodal embodied interactive cultural tourism lighting art effect generation system, comprising:

[0170] The first unit is used to collect initial user interaction data in cultural tourism scenarios and analyze time series correlations, extract user behavior features, construct user behavior feature sequences, and calculate the changing trends of user behavior feature sequences. It also obtains the distribution of light intensity, crowd density, and cultural element information in cultural tourism scenarios, and combines the user behavior feature sequences and corresponding changing trends to generate scene interaction data streams.

[0171] The second unit is used to divide the interactive space based on the scene interaction data stream, calculate the activity and emotional intensity of users in each space and generate a spatial vitality map. Based on the spatial vitality map, it calculates the energy difference between adjacent spaces and determines the lighting gradient coefficient. Based on the lighting gradient coefficient, it tracks the real-time changes in spatial vitality and establishes a dynamic mapping relationship for lighting effects.

[0172] The third unit is configured to output and execute lighting control instructions according to the dynamic mapping relationship, generate an initial lighting effect, and collect user interactive feedback data on the initial lighting effect;

[0173] A fourth unit is configured to extract user preference characteristics for lighting effects based on the interactive feedback data, construct a lighting effect evaluation index, optimize and sort lighting control parameters according to the lighting effect evaluation index, establish a parameter optimization strategy, iteratively adjust the lighting control instructions based on the parameter optimization strategy, and generate optimal lighting control instructions;

[0174] The fifth unit is used to output the optimal lighting control instruction, execute and record the optimal lighting effect.

[0175] According to a third aspect of an embodiment of the present invention, an electronic device is provided, including:

[0176] A processor and a memory for storing processor-executable instructions, wherein the processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0177] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described above is implemented.

[0178] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.

[0179] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for generating cultural tourism lighting art effects based on multimodal embodied interaction, characterized in that: include: Collect initial user interaction data in cultural tourism scenarios and analyze temporal correlations, extract user behavior features, construct user behavior feature sequences, and calculate the changing trends of user behavior feature sequences. Obtain information on the light intensity, crowd density, and cultural element distribution of cultural tourism scenarios, and combine user behavior feature sequences and corresponding changing trends to generate scenario interaction data streams. Based on the scene interaction data stream, the interactive space is divided, the activity and emotional intensity of users in each space are calculated and a spatial vitality map is generated. The energy difference between adjacent spaces is calculated based on the spatial vitality map, and the lighting gradient coefficient is determined. The real-time changes in spatial vitality are tracked based on the lighting gradient coefficient, and a dynamic mapping relationship of lighting effects is established, including: Dividing the cultural tourism scene into multiple interactive spaces based on the scene interaction data stream, establishing a three-dimensional coordinate system in the interactive space, dividing the interactive space into multiple grid units, and calculating the ratio of the number of interactive events in each grid unit to the grid volume to obtain the interaction density; Calculate the weighted sum of the basic behavior intensity, movement trajectory complexity, and interaction density of each user in the interactive space to obtain user activity; calculate the weighted sum of the physiological characteristic emotion value, voice emotion value, and gesture emotion value of each user in the interactive space to obtain emotion intensity; and perform a linear weighted combination of the user activity and the emotion intensity to obtain a spatial vitality map; Determining the spatial vitality corresponding to each interactive space based on the spatial vitality map, calculating the absolute difference between the vitality values ​​of the center points of adjacent interactive spaces to obtain an energy difference, substituting the energy difference into an exponential function to obtain a light gradient coefficient, wherein the input of the exponential function is the negative of the ratio of the energy difference to a preset energy threshold parameter; Based on the light gradient coefficient, the real-time changes in spatial vitality are tracked, crowd flow characteristics are extracted to calculate dynamic partition boundaries, a cross-region gradient function is constructed to optimize the light gradient coefficient, group behavior patterns are identified, vitality change trends are predicted and error compensation is performed, and a dynamic mapping relationship between the real-time changes in spatial vitality and lighting effects is established; Outputting and executing lighting control instructions according to the dynamic mapping relationship, generating an initial lighting effect and collecting user interactive feedback data on the initial lighting effect; Based on the interactive feedback data, extract the user's preference characteristics for lighting effects, construct a lighting effect evaluation index, optimize and sort the lighting control parameters according to the lighting effect evaluation index, establish a parameter optimization strategy, iteratively adjust the lighting control instructions based on the parameter optimization strategy, and generate the optimal lighting control instructions; The optimal lighting control instruction is output, executed and the optimal lighting effect is recorded.

2. The method according to claim 1, characterized in that Collect the initial interaction data of users in the cultural tourism scene and analyze the time series correlation, extract user behavior characteristics, construct the user behavior feature sequence and calculate the change trend of the user behavior feature sequence, obtain the light intensity, crowd density and cultural element information distribution of the cultural tourism scene, and combine the user behavior feature sequence and the corresponding change trend to generate the scene interaction data stream including: Collecting the user's initial interaction data in the cultural tourism scene, wherein the initial interaction data includes posture information, motion trajectory information, voice commands and emotional intonation information data; Constructing a time-dimensional correlation matrix and extracting the temporal correlation of the initial interaction data; constructing a user behavior feature sequence based on the temporal correlation; the user behavior feature sequence includes the duration of the behavior, the frequency of the behavior, the change in the intensity of the behavior, and the spatial location of the behavior; and calculating the change trend of the user behavior feature sequence at different scales; Collect the light intensity, crowd density and cultural element information distribution of the cultural and tourism scene, map the user behavior feature sequence to the scene grid corresponding to the cultural and tourism scene according to the spatial position, determine the behavioral activity of each grid, calculate the activity difference value between different grids, and determine the scene interaction data flow in combination with the change trend, wherein the scene interaction data flow includes the real-time status and predicted status of the interaction data.

3. The method according to claim 1, characterized in that Based on the light gradient coefficient, the real-time changes in spatial vitality are tracked, crowd flow characteristics are extracted to calculate dynamic partition boundaries, a cross-region gradient function is constructed to optimize the light gradient coefficient, group behavior patterns are identified, vitality change trends are predicted, and error compensation is performed. The dynamic mapping relationship between the real-time changes in spatial vitality and lighting effects is established, including: Acquire real-time data on changes in spatial vitality, generate a vitality mapping baseline value based on the real-time data on changes in spatial vitality and a preset light gradient coefficient, collect crowd movement data within the interactive space, extract crowd flow characteristics, and multiply the crowd flow characteristics by the crowd density of the interactive space to calculate the flow intensity; Generate an adjustment factor for the dynamic partition boundary based on the difference in crowd flow characteristics and crowd density between adjacent interactive spaces, and adjust the boundaries of adjacent interactive spaces based on the adjustment factor; Constructing a cross-region gradient function for the adjacent interactive spaces, substituting the flow intensity and spatial distance into the cross-region gradient function, and fusing the calculated result with the preset light gradient coefficient to generate an optimized light gradient coefficient; Extracting group behavior pattern characteristics based on the flow intensity, inputting the group behavior pattern characteristics and pre-collected historical vitality data into a prediction model to calculate a vitality change trend, performing error compensation on the vitality change trend and the real-time collected spatial vitality data, and outputting a compensated spatial vitality mapping value; A dynamic mapping function is established based on the compensated space vitality mapping value, the optimized light gradient coefficient and the pre-set environmental constraint parameters, and a dynamic mapping relationship is established between the real-time changes in the space vitality and the lighting effects. The dynamic mapping relationship is dynamically adjusted with the change rate of the compensated space vitality mapping value and the change rate of the optimized light gradient coefficient.

4. The method according to claim 1, wherein Outputting and executing lighting control instructions according to the dynamic mapping relationship, generating an initial lighting effect, and collecting user interactive feedback data on the initial lighting effect include: Output and execute lighting control instructions according to the dynamic mapping relationship, wherein the lighting control instructions include lighting brightness, color temperature and gradient timing parameters; generating an initial lighting effect according to the lighting control instruction, wherein the initial lighting effect is dynamically adjusted as the vitality of the space changes in real time; Collect user interaction feedback data on the initial lighting effect, wherein the interaction feedback data includes user stay time, interaction frequency and pre-set emotional feedback indicators.

5. The method according to claim 1, wherein Based on the interactive feedback data, extracting user preference characteristics for lighting effects, constructing a lighting effect evaluation index, optimizing and ranking lighting control parameters according to the lighting effect evaluation index, establishing a parameter optimization strategy, and iteratively adjusting lighting control instructions based on the parameter optimization strategy to generate optimal lighting control instructions includes: Collecting user interactive feedback data on lighting effects, constructing a multidimensional feature vector based on user dwell time, interaction frequency, and emotional feedback indicators in the interactive feedback data, and inputting the multidimensional feature vector into a pre-set user preference scoring module to obtain a preference score; Performing weighted fusion of the preference score, the comfort index, and the spatial coordination index to generate a comprehensive evaluation value, and constructing a time series evaluation matrix based on the comprehensive evaluation value, wherein the time series evaluation matrix includes a sequence of evaluation values ​​within a historical time window; Calculate the sensitivity of the comprehensive evaluation value to the lighting control parameters, use kernel density estimation to build a parameter sensitivity distribution module, suppress the influence of abnormal samples through iterative reweighted least squares method, and determine the parameter priority and sort based on historical optimization results; Based on the sorting results of the lighting control parameters, a parameter optimization objective function is sequentially constructed, with minimizing the mean square error of the evaluation value sequence in the time series evaluation matrix as the optimization objective, and the amplitude of parameter changes at adjacent moments as a constraint condition. The lighting control parameters are gradient iteratively updated based on the optimization objective function, and the iteration is stopped when the difference between the comprehensive evaluation values ​​at adjacent moments is less than a preset threshold, and the optimized lighting control parameters are output; According to the optimized lighting control parameters and the preset environmental constraint parameters, the optimal lighting control instructions are generated in combination with the preset dynamic gain matrix.

6. The method according to claim 5, characterized in that Calculate the sensitivity of the comprehensive evaluation value to the lighting control parameters, use kernel density estimation to build the parameter sensitivity distribution module, suppress the influence of abnormal samples through iterative reweighted least squares method, and determine the parameter priority and sorting based on historical optimization results, including: Obtain historical adjustment data of lighting control parameters and corresponding preference scores. Based on the historical adjustment data and corresponding preference scores, calculate the first-order sensitivity of the comprehensive evaluation value to the lighting control parameters through partial derivatives, calculate the second-order interactive sensitivity through mixed partial derivatives, and construct the Jacobian matrix using the central difference method to obtain an initial sensitivity sequence; A Gaussian kernel function is used to perform kernel density estimation on the initial sensitivity sequence, an optimal bandwidth parameter is adaptively calculated based on the sample standard deviation, the initial sensitivity sequence is transformed by the kernel function to obtain a continuous probability distribution, and the distribution characteristics of the parameter sensitivity are output; A Huber-type M-estimation loss function is constructed to detect anomalies of the distribution characteristics of the parameter sensitivity, a sample weight matrix is ​​adaptively calculated based on the residual size, the sample weight matrix is ​​applied to an iterative reweighted least squares calculation, the influence of abnormal samples is suppressed through multiple rounds of iterative optimization, and a corrected sensitivity value is output; Calculate the time series weight of the pre-acquired historical evaluation data based on the time decay exponential function, and perform weighted summation of the time series weight and the historical comprehensive evaluation value to obtain the historical optimization effect of the parameters; The corrected sensitivity value, the historical parameter optimization effect, and the parameter stability index are subjected to multi-objective weighted fusion to determine the parameter priority. The lighting control parameters are sorted in descending order according to the parameter priority to generate a parameter optimization sequence table, wherein the parameter stability index includes parameter fluctuation amplitude, convergence speed, and disturbance recovery.

7. A multimodal embodied interactive cultural tourism lighting art effect generation system, used to implement the method described in any one of claims 1 to 6, characterized in that: include: The first unit is used to collect initial user interaction data in cultural tourism scenarios and analyze time series correlations, extract user behavior features, construct user behavior feature sequences, and calculate the changing trends of user behavior feature sequences. It also obtains the distribution of light intensity, crowd density, and cultural element information in cultural tourism scenarios, and combines the user behavior feature sequences and corresponding changing trends to generate scene interaction data streams. The second unit is used to divide the interactive space based on the scene interaction data stream, calculate the activity and emotional intensity of users in each space and generate a spatial vitality map. Based on the spatial vitality map, it calculates the energy difference between adjacent spaces and determines the lighting gradient coefficient. Based on the lighting gradient coefficient, it tracks the real-time changes in spatial vitality and establishes a dynamic mapping relationship for lighting effects. The third unit is configured to output and execute lighting control instructions according to the dynamic mapping relationship, generate an initial lighting effect, and collect user interactive feedback data on the initial lighting effect; A fourth unit is configured to extract user preference characteristics for lighting effects based on the interactive feedback data, construct a lighting effect evaluation index, optimize and sort lighting control parameters according to the lighting effect evaluation index, establish a parameter optimization strategy, iteratively adjust the lighting control instructions based on the parameter optimization strategy, and generate optimal lighting control instructions; The fifth unit is used to output the optimal lighting control instruction, execute and record the optimal lighting effect.

8. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images