Immersion adaptation design method and system for cultural heritage travel scene

Abstract

The invention relates to the technical field of tourism management, and discloses a cultural heritage travel scene immersion adaptation design method and system, and the method comprises the steps: collecting the multi-dimensional state data of tourists in a cultural heritage travel scene, and the multi-dimensional state data comprise real-time behavior data, physiological feedback data and environment interaction data; performing personalized fusion analysis on the multi-dimensional state data to obtain emotional state analysis data; performing multi-dimensional feature matching on the emotional state analysis data to obtain a personalized culture experience scheme; performing effect simulation on the personalized culture experience scheme in the cultural heritage travel scene, and monitoring behavior state feedback data of tourists in real time; performing adaptive adjustment on the personalized culture experience scheme to obtain an optimized culture experience scheme; performing immersion effect verification on the optimization experience scheme to obtain a target immersion adaptation design scheme; according to the invention, the efficiency of the immersion adaptation design of the cultural heritage travel scene can be improved.

Description

Technical Field

[0001] This invention relates to the field of tourism management technology, and in particular to a design method and system for immersive adaptation of cultural heritage tourism scenarios. Background Technology

[0002] In the field of immersive design for cultural heritage and tourism scenarios, existing technologies generally suffer from limitations in data collection and integration, particularly regarding visitor status. They fail to comprehensively cover key information such as real-time visitor behavior, physiological responses, and environmental interactions, resulting in inaccurate and incomplete analysis of visitor emotional states. The lack of in-depth fusion and analysis of multi-source data makes it difficult to construct precise profiles tailored to individual visitor characteristics. This leads to highly homogenized cultural experience solutions that fail to effectively align with visitors' actual needs and emotional inclinations, thus hindering the enhancement of immersion.

[0003] Existing cultural experience solutions lack dynamic adaptive adjustment mechanisms, making it difficult to optimize in a timely manner based on real-time feedback data from visitors. Furthermore, the matching process between cultural heritage elements and visitor needs fails to adequately consider individual preferences and the coherence and logical order of cultural themes, resulting in insufficient matching accuracy. Simultaneously, the lack of a comprehensive immersion effect verification process prevents scientific evaluation and calibration of the actual immersive performance of the solution, leading to poor stability in the final experience and making it difficult to consistently meet visitors' demands for high-quality immersive experiences. Overall, the design efficiency and effectiveness need improvement. Summary of the Invention

[0004] This invention provides a method and system for adapting cultural heritage tourism scenes to create an immersive experience, in order to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides an immersive adaptation design method for cultural heritage tourism scenes, comprising:

[0006] S1. Collect multi-dimensional state data of tourists in cultural heritage tourism scenarios, including real-time behavioral data, physiological feedback data and environmental interaction data;

[0007] S2. Perform personalized fusion analysis on the multidimensional state data to obtain the emotional state analysis data of the tourist;

[0008] S3. Based on a preset cultural heritage element library, perform multi-dimensional feature matching on the emotional state analysis data to obtain a personalized cultural experience plan for the tourist.

[0009] S4. Simulate the effect of the personalized cultural experience plan in the cultural heritage tourism scene, and monitor the behavioral status feedback data of the tourists in real time;

[0010] S5. Based on the behavioral status feedback data, the personalized cultural experience plan is adaptively adjusted to obtain the optimized cultural experience plan for the tourist.

[0011] S6. Verify the immersive effect of the optimized experience scheme to obtain the target immersive adaptation design scheme for the cultural heritage tourism scene.

[0012] In a preferred embodiment, the collection of multidimensional state data of tourists in the cultural heritage tourism scenario includes real-time behavioral data, physiological feedback data, and environmental interaction data, including:

[0013] Real-time collection of tourists' movement trajectories and postures in the cultural heritage exhibition area constitutes the tourists' real-time behavioral data;

[0014] The physiological feedback data of the tourists is obtained by continuously monitoring their heart rate variability and skin conductance response using the physiological signal acquisition device.

[0015] The number of times tourists touch cultural heritage entities, the duration of their gaze, and the content of their voice interactions are recorded by the interactive devices and environmental sensing devices set up in the scene, thus forming the tourists' environmental interaction data.

[0016] According to a unified timestamp, the real-time behavioral data, the physiological feedback data, and the environmental interaction data are aligned and fused to obtain the structured state data sequence of the tourist;

[0017] Missing values ​​are imputed in the tourist status data sequence to obtain the multidimensional status data of the tourist.

[0018] In a preferred embodiment, the personalized fusion analysis of the multidimensional state data to obtain the tourist's emotional state analysis data includes:

[0019] The movement pattern characteristics of the tourist are obtained by analyzing key elements of the real-time behavior data;

[0020] Spectral analysis was performed on the physiological feedback data to obtain the emotional response characteristics of the tourists;

[0021] The environmental interaction data is statistically analyzed to obtain the tourist's attention characteristics.

[0022] Based on the tourist's personal preference information, the movement pattern features, emotional response features, and attention features are correlated and deduced to construct a personalized profile of the tourist.

[0023] Based on the weight configuration in the personalized profile, the movement pattern feature, the emotional response feature and the attention feature are fused from multiple sources to obtain the tourist's preliminary emotional state vector.

[0024] The preliminary emotional state vector is compared and calibrated with a preset emotional baseline for cultural heritage scenes to eliminate common scene interference and obtain the emotional state analysis data of the tourists.

[0025] In a preferred embodiment, the step of correlating and extrapolating the movement pattern features, emotional response features, and attention features based on the tourist's personal preference information to construct a personalized profile of the tourist includes:

[0026] Personalized data mining is performed on the tourists' personal registration information and historical travel records to obtain the tourists' initial set of personal preferences;

[0027] The initial set of personal preferences is structured and classified to obtain the category preference information of the tourists. The category preference information includes cultural content preference, interaction form preference, and environmental atmosphere preference.

[0028] The cultural content preference class is associated with the gaze duration and voice interaction content of specific cultural heritage elements in the attention features; the interaction form preference class is associated with the path complexity and touch frequency in the movement pattern features; and the environmental atmosphere preference class is associated with the emotional valence tendency in the emotional response features, thus obtaining the tourist's preference feature mapping relationship.

[0029] Based on the preference feature mapping relationship, the correlation strength between the category preference information and the corresponding feature is calculated, and the movement pattern feature, the emotional response feature and the attention feature are weighted and integrated based on the correlation strength to construct the initial personalized profile of the tourist.

[0030] In a preferred embodiment, the formula for calculating the correlation strength is as follows:

[0031] ;

[0032] In the formula, For the first The strength of the association between the category preference information and the corresponding features. The preset feature correlation adjustment coefficient, For the first The category preference information mentioned above, For the preference feature mapping relationship, the first... The feature vectors of the aforementioned category preference information For the first The category preference information With the corresponding feature vector The Pearson correlation coefficient between them For the corresponding feature vector The standard deviation within the preset time window, The preset characteristic significance adjustment coefficient, The duration of the current scene. It is a natural constant.

[0033] In a preferred embodiment, the step of performing multi-dimensional feature matching on the emotional state analysis data based on a preset cultural heritage element library to obtain a personalized cultural experience plan for the tourist includes:

[0034] Multi-category label extraction is performed on the preset cultural heritage element library to obtain a multi-dimensional feature set of cultural heritage in the cultural heritage tourism scene;

[0035] The intensity distribution and tendency of emotions in the emotional state analysis data are analyzed by feature space mapping to obtain the multi-dimensional feature vector of the tourist's emotions;

[0036] The matching degree between the emotional multidimensional feature vector and the cultural heritage multidimensional feature set is evaluated, and based on the evaluation results, a set of highly relevant elements of the cultural heritage multidimensional feature set is selected.

[0037] Based on the cultural theme coherence and logical experience sequence among the elements in the highly relevant element set, an initial cultural experience sequence for the cultural heritage tourism scene is constructed.

[0038] The initial cultural experience sequence is subjected to immersion consistency verification, and the order of elements and interaction are adjusted to obtain the tourist's personalized cultural experience plan.

[0039] In a preferred embodiment, the step of simulating the effect of the personalized cultural experience program in the cultural heritage tourism scenario and monitoring the behavioral feedback data of the tourists in real time includes:

[0040] The cultural content and interactive processes planned in the personalized cultural experience scheme are transformed into a series of multimedia control commands that drive augmented reality devices, projection devices and audio devices in the cultural heritage tourism scene.

[0041] Based on the multimedia control command sequence, corresponding virtual cultural elements and interactive guidance are synchronously rendered and superimposed in the actual physical scene where the tourist is located to simulate the effect.

[0042] During the simulation, facial expression image data, body movement trajectory data, and voice semantic data of the tourists are collected simultaneously.

[0043] Feature fusion is performed on the facial expression image data, the body movement trajectory data, and the speech semantic data to obtain the tourist's behavioral state feedback data.

[0044] In a preferred embodiment, the step of adaptively adjusting the personalized cultural experience plan based on the behavioral state feedback data to obtain an optimized cultural experience plan for the tourist includes:

[0045] Based on a preset effect evaluation threshold, the immersion index, interaction response index and emotional resonance index in the behavioral state feedback data are traversed and compared to obtain the indicators to be optimized in the behavioral state feedback data.

[0046] By performing key element correlation analysis between the personalized cultural experience scheme and the indicators to be optimized, the target cultural elements and target interaction flow of the personalized cultural experience scheme are obtained.

[0047] Based on a pre-set cultural heritage element library, the presentation duration of the target cultural element, the guidance intensity of the target interactive process, and the visual complexity of the virtual cultural element are adjusted.

[0048] The optimized cultural experience plan for the tourists is determined after the parameter adjustments are completed.

[0049] In a preferred embodiment, the step of verifying the immersive effect of the optimized experience scheme to obtain the target immersive adaptation design scheme for the cultural heritage tourism scene includes:

[0050] The optimized cultural experience solution is loaded into the verification mode of the cultural heritage tourism scene, and an immersive effect verification invitation is sent to the tourists.

[0051] After the tourists accept the invitation, the optimized cultural experience plan is fully implemented, and the tourists' full-cycle verification feedback data is collected simultaneously.

[0052] The full-cycle verification feedback data is compared with the preset immersion achievement conditions, which include the attention concentration threshold, the positive emotional fluctuation threshold, and the stable range of physiological arousal.

[0053] When the full-cycle verification feedback data meets the immersion achievement criteria, the currently executed optimized cultural experience scheme is determined as the target immersion adaptation design scheme.

[0054] To address the aforementioned problems, the present invention also provides an immersive adaptation design system for cultural heritage tourism scenarios, the system comprising:

[0055] The data acquisition module is used to collect multi-dimensional status data of tourists in cultural heritage and tourism scenarios. The multi-dimensional status data includes real-time behavioral data, physiological feedback data, and environmental interaction data.

[0056] The personalized fusion analysis module is used to perform personalized fusion analysis on the multidimensional state data to obtain the emotional state analysis data of the tourist.

[0057] The feature matching module is used to perform multi-dimensional feature matching on the emotional state analysis data based on a preset cultural heritage element library to obtain a personalized cultural experience plan for the tourist.

[0058] The effect simulation and monitoring module is used to simulate the effect of the personalized cultural experience plan in the cultural heritage tourism scene and monitor the behavioral status feedback data of the tourists in real time.

[0059] An adaptive adjustment module is used to adaptively adjust the personalized cultural experience plan based on the behavioral state feedback data to obtain an optimized cultural experience plan for the tourists.

[0060] The immersive effect verification module is used to verify the immersive effect of the optimized experience scheme and obtain the target immersive adaptation design scheme for the cultural heritage tourism scene.

[0061] Compared with the prior art, the present invention has the following beneficial effects:

[0062] 1. This invention collects multi-dimensional state data consisting of tourists' real-time behavior, physiological feedback, and environmental interactions. Through alignment, fusion, and missing value imputation, it forms a complete and structured data support. Combined with tourists' personal preference information, multi-source feature correlation inference is conducted to construct a precise personalized profile. Then, emotional baseline calibration eliminates common scene interference, making the emotional state analysis data more closely aligned with individual tourist characteristics. Based on the precise matching of this analysis data with the multi-dimensional characteristics of cultural heritage, and the verification of cultural theme coherence and immersion consistency, the resulting personalized cultural experience plan deeply resonates with tourists' emotional inclinations and needs, significantly improving the adaptability and immersion of the cultural experience.

[0063] 2. This invention simulates the scenario-based effects of personalized experience solutions through a multimedia control command sequence, simultaneously collecting multi-dimensional behavioral feedback data from tourists. Based on preset thresholds, it accurately identifies indicators to be optimized and adjusts parameters, achieving dynamic adaptive optimization of the experience solution. By comparing full-cycle verification feedback data with clearly defined immersion achievement conditions, it ensures that the optimized solution has a stable immersive effect. This not only improves the accuracy and effectiveness of immersive adaptation design for cultural heritage tourism scenarios but also optimizes the closed-loop efficiency of the design process, providing tourists with a high-quality, personalized cultural immersion experience and fully exploring the cultural tourism value of cultural heritage. Attached Figure Description

[0064] Figure 1 This is a flowchart illustrating an immersive adaptation design method for cultural heritage tourism scenes, provided in an embodiment of the present invention.

[0065] Figure 2 This is a functional module diagram of an immersive adaptation design system for cultural heritage and tourism scenes provided in an embodiment of the present invention;

[0066] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0067] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0068] This application provides a method for adapting to an immersive cultural heritage tourism scene. The execution subject of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cluster of cloud servers. The server can be an independent server or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0069] Reference Figure 1 The diagram shown is a flowchart illustrating an immersive design method for cultural heritage tourism scenes according to an embodiment of the present invention. In this embodiment, the immersive design method for cultural heritage tourism scenes includes:

[0070] S1. Collect multi-dimensional state data of tourists in cultural heritage tourism scenarios, including real-time behavioral data, physiological feedback data and environmental interaction data;

[0071] In this embodiment of the invention, the collection of multidimensional state data of tourists in cultural heritage tourism scenarios includes real-time behavioral data, physiological feedback data, and environmental interaction data, including:

[0072] Real-time collection of tourists' movement trajectories and postures in the cultural heritage exhibition area constitutes the tourists' real-time behavioral data;

[0073] The physiological feedback data of the tourists is obtained by continuously monitoring their heart rate variability and skin conductance response using the physiological signal acquisition device.

[0074] The number of times tourists touch cultural heritage entities, the duration of their gaze, and the content of their voice interactions are recorded by the interactive devices and environmental sensing devices set up in the scene, thus forming the tourists' environmental interaction data.

[0075] According to a unified timestamp, the real-time behavioral data, the physiological feedback data, and the environmental interaction data are aligned and fused to obtain the structured state data sequence of the tourist;

[0076] Missing values ​​are imputed in the tourist status data sequence to obtain the multidimensional status data of the tourist.

[0077] Millimeter-wave radar and high-definition visual acquisition equipment are deployed at key path nodes and around cultural heritage sites in the cultural heritage exhibition area. The millimeter-wave radar emits millimeter-wave signals and receives echo signals reflected from the bodies of visitors. By analyzing the time difference and phase difference of the echo signals, the real-time coordinates of visitors in the two-dimensional plane of the exhibition area are determined. The coordinate points are recorded every 0.5 seconds, and the continuously recorded coordinate points are connected in chronological order to form the visitor's movement trajectory. The high-definition visual acquisition equipment captures images of visitors' body movements. By comparing the positional changes of the limb joints in the images frame by frame, specific movements and postures such as raising and lowering arms and turning heads are determined. The movement trajectory and movement postures are integrated to form the visitor's real-time behavioral data.

[0078] Tourists are equipped with wristband-type physiological signal acquisition devices. The device's built-in heart rate sensor is in close contact with the tourist's wrist skin to sense the micro-vibrations of the skin caused by the heartbeat. Each vibration is recorded as one heartbeat, and the number of heartbeats per minute is counted to obtain the instantaneous heart rate. The instantaneous heart rate is continuously recorded for 5 minutes, and the difference between two adjacent instantaneous heart rates is calculated. The average of the absolute values ​​of all differences is the heart rate variability. The device's built-in skin conductance sensor contacts the tourist's wrist skin through two electrode pads to measure the skin conductivity between the two electrode pads. The real-time value change of the skin conductivity is the skin conductance response. The real-time data of heart rate variability and skin conductance response are integrated to obtain the tourist's physiological feedback data.

[0079] Thin-film pressure sensors are installed on the surface of cultural heritage sites as touch interaction devices. When a visitor's hand touches the sensor surface, the sensor detects pressure changes. A valid touch is determined when the pressure value exceeds 50 Pa. The sensor automatically records the time and number of touches. An eye-tracking device is installed in front of the cultural heritage site as a gaze environment perception device. The device emits near-infrared light and captures the position of the light spot reflected by the visitor's eyeball. The change in the position of the light spot determines the visitor's gaze point. Timing starts when the gaze point falls within the range of the cultural heritage site and stops when the gaze leaves the range. The time difference between the two timings is the single gaze duration. The total gaze duration is obtained by accumulating all single gaze durations. A voice interaction device is installed in the exhibition area. The built-in microphone of the device collects the voice content of the visitors. The voice interaction content is recorded by converting the voice signal into a text signal. The number of touches and gaze duration are integrated with the voice interaction content to form the visitor's environmental interaction data.

[0080] A unified timestamp format is assigned to real-time behavioral data, physiological feedback data, and environmental interaction data. The timestamp format is year, month, day, hour, minute, second, and millisecond, accurate to the millisecond level. Based on the collection time of real-time behavioral data, data points in physiological feedback data and environmental interaction data whose timestamps are completely consistent with the timestamps of real-time behavioral data are matched. For data points whose timestamps are not completely consistent, the data point closest to the target timestamp is selected for matching. After matching, the real-time behavioral data, physiological feedback data, and environmental interaction data corresponding to the same timestamp are integrated into a single data record. All data records are arranged in order of timestamp from earliest to latest to obtain the structured state data sequence of the tourist.

[0081] Each data record in the structured state data sequence is examined to determine if there is any missing data in a certain category of real-time behavioral data, physiological feedback data, or environmental interaction data. For missing data points, the average of two adjacent valid data points is used for interpolation. Specifically, the two nearest valid data points before and after the missing data point are determined, the sum of the values ​​corresponding to these two valid data points is calculated, and the sum is divided by 2 to obtain the interpolated value. The interpolated value is then filled into the position of the missing data point. After interpolating all missing data points, the multidimensional state data of the tourist is obtained.

[0082] The beneficial effects include the comprehensive and accurate collection of multi-dimensional state data of tourists in cultural heritage tourism scenarios. This is achieved by using multiple types of devices to collaboratively acquire real-time behavioral data, physiological feedback data, and environmental interaction data of tourists. A unified timestamp is used to achieve accurate alignment and fusion of various types of data. The average interpolation method of adjacent effective data points is used to ensure the integrity of the structured state data sequence. This clearly presents the characteristics of tourists' attention to cultural heritage and their interaction preferences, providing reliable data support for service optimization and experience upgrade in cultural heritage tourism scenarios.

[0083] S2. Perform personalized fusion analysis on the multidimensional state data to obtain the emotional state analysis data of the tourist;

[0084] In this embodiment of the invention, the step of performing personalized fusion analysis on the multidimensional state data to obtain the tourist's emotional state analysis data includes:

[0085] The movement pattern characteristics of the tourist are obtained by analyzing key elements of the real-time behavior data;

[0086] Spectral analysis was performed on the physiological feedback data to obtain the emotional response characteristics of the tourists;

[0087] The environmental interaction data is statistically analyzed to obtain the tourist's attention characteristics.

[0088] Based on the tourist's personal preference information, the movement pattern features, emotional response features, and attention features are correlated and deduced to construct a personalized profile of the tourist.

[0089] Based on the weight configuration in the personalized profile, the movement pattern feature, the emotional response feature and the attention feature are fused from multiple sources to obtain the tourist's preliminary emotional state vector.

[0090] The preliminary emotional state vector is compared and calibrated with a preset emotional baseline for cultural heritage scenes to eliminate common scene interference and obtain the emotional state analysis data of the tourists.

[0091] The process of constructing a personalized profile of a tourist by associating and deducing the movement pattern features, emotional response features, and attention features based on the tourist's personal preference information includes:

[0092] Personalized data mining is performed on the tourists' personal registration information and historical travel records to obtain the tourists' initial set of personal preferences;

[0093] The initial set of personal preferences is structured and classified to obtain the category preference information of the tourists. The category preference information includes cultural content preference, interaction form preference, and environmental atmosphere preference.

[0094] The cultural content preference class is associated with the gaze duration and voice interaction content of specific cultural heritage elements in the attention features; the interaction form preference class is associated with the path complexity and touch frequency in the movement pattern features; and the environmental atmosphere preference class is associated with the emotional valence tendency in the emotional response features, thus obtaining the tourist's preference feature mapping relationship.

[0095] Based on the preference feature mapping relationship, the correlation strength between the category preference information and the corresponding feature is calculated, and the movement pattern feature, the emotional response feature and the attention feature are weighted and integrated based on the correlation strength to construct the initial personalized profile of the tourist.

[0096] The formula for calculating the correlation strength is as follows:

[0097] ;

[0098] In the formula, For the first The strength of the association between the category preference information and the corresponding features. The preset feature correlation adjustment coefficient, For the first The category preference information mentioned above, For the preference feature mapping relationship, the first... The feature vectors of the aforementioned category preference information For the first The category preference information With the corresponding feature vector The Pearson correlation coefficient between them For the corresponding feature vector The standard deviation within the preset time window, The preset characteristic significance adjustment coefficient, The duration of the current scene. It is a natural constant.

[0099] The source of the feature correlation moderating coefficient is the complete association data of category preference information and corresponding feature vectors of the past 1,000 visitors to the cultural heritage exhibition area. The correlation strength calculated under different moderating coefficients is statistically analyzed to match the actual preferences of the visitors. The coefficient value corresponding to the matching result that is completely consistent with the actual preferences is selected as the moderating coefficient. This value is fixed and unique and is used to adjust the influence of the correlation between category preference information and feature vectors on the correlation strength.

[0100] No. The source of each category preference information is the category preference information obtained after structured classification of the initial personal preference set of tourists. Specifically, it is extracted one preference item from each of the three categories: cultural content preference, interaction form preference, and environmental atmosphere preference. Each preference item corresponds to a sequence number, which is directly used as the basic data for calculating the association strength. In the preference feature mapping relationship, the first... The source of the feature vector of each category preference information is based on the preference feature mapping relationship. The feature data associated with the category preference information corresponding to the index is extracted and arranged in a fixed order. For example, the gaze duration and voice interaction content related data corresponding to the cultural content preference category, and the path complexity and touch frequency data corresponding to the interaction form preference category are all integrated into the feature vector in a preset order.

[0101] No. The Pearson correlation coefficient between a category preference and its corresponding feature vector is calculated as follows: First, the mean of all values ​​for the category preference and the mean of each dimension of the feature vector are calculated. Then, the difference between each value of the category preference and its own mean, and the difference between each dimension of the feature vector and its own mean are calculated. These differences are multiplied and summed. Simultaneously, the sum of the squares of the two types of differences is calculated. The result is the correlation coefficient, used to quantify the degree of linear association between the two. The standard deviation of the corresponding feature vector within a preset time window is calculated as follows: The preset time window is set to ten minutes. First, all data for each dimension of the feature vector within this time window are acquired, and the mean of these data is calculated. Then, the difference between each data point and the mean is calculated and squared. The sum of all squared values ​​is divided by the number of data points, and the arithmetic square root of the result is taken to obtain the standard deviation, which reflects the degree of fluctuation of the feature vector data within the set time period. The source of the feature significance adjustment coefficient is the same as that of the feature correlation adjustment coefficient. Based on historical data of 1,000 tourists, the influence of the standard deviation of the feature vector on the association strength under different adjustment coefficients is statistically analyzed. The coefficient value that can accurately distinguish whether feature fluctuations reflect true preferences is selected as the adjustment coefficient and kept unchanged. It is used to adjust the influence of the degree of feature vector fluctuations on the association strength.

[0102] The duration of the current scene is derived from the real-time cumulative recording of the time by timing devices deployed in the exhibition area, starting from when tourists enter the corresponding cultural heritage exhibition area and begin to generate category preference information and feature data. The timing accuracy is in seconds, and it is directly used as the basis for calculating the denominator of the formula. The value of the natural constant is fixed at 2.71828, which is a universal constant in mathematics. It is used to construct the attenuation term of the scene duration on the association strength and does not require additional calculation or acquisition.

[0103] The significance of this formula lies in integrating three core factors: the correlation between category preference information and the corresponding feature vector, the fluctuation degree of the feature vector, and the duration of the current scene. By adjusting the influence weight of the first two factors through feature correlation adjustment coefficients and feature significance adjustment coefficients, and by using the exponential decay of scene duration in the denominator, the influence of duration on the reliability of feature data is balanced. The final calculated association strength can accurately quantify the degree of association between the category preference information corresponding to the index and the corresponding feature. This provides accurate data support for subsequent weighted integration of motion pattern features, emotional response features, and attention features based on association strength to construct an initial personalized profile, ensuring that the initial personalized profile can match the actual preferences of tourists.

[0104] Extract movement trajectories and postures from real-time behavior data, identify locations within a preset area surrounding the cultural heritage site in the movement trajectory, count the number of locations and the duration of continuous stay, and simultaneously count the number of times the arm is raised to point at the cultural heritage site and the number of times the head turns towards the cultural heritage site in the posture. Integrate the number of locations, duration of continuous stay, number of times the arm is raised, and number of times the head turns to obtain the movement pattern characteristics of the tourist.

[0105] Continuous recordings of heart rate variability and skin conductance responses from physiological feedback data were selected. These data were divided into multiple data segments with fixed time lengths. For each segment, the variation period and amplitude were statistically analyzed. The variation period reflects the interval pattern of data fluctuation over time, and the variation amplitude reflects the degree of data deviation from the mean. The variation periods and amplitudes of all data segments were summarized to obtain the emotional response characteristics of the visitors. Touch counts and gaze durations from environmental interaction data, along with voice interaction content, were analyzed. The proportion of touch counts and total gaze duration per unit time to the total time visitors spent in the exhibition area was statistically analyzed. Simultaneously, the number of statements mentioning cultural heritage entities in the voice interaction content was identified. The ratio of touch counts and total gaze duration per unit time to the number of related statements was integrated to obtain the visitors' attention characteristics.

[0106] The system retrieves pre-collected personal preference information of tourists, which includes the types of cultural heritage that tourists are interested in and the types of tour experiences they hope to obtain. It matches the number of locations and dwell time corresponding to the types of cultural heritage that tourists are interested in from the movement pattern characteristics, the change cycle and change range corresponding to the types of tour experiences that tourists hope to obtain from the emotional response characteristics, and the proportion of touch frequency and gaze duration corresponding to the types of cultural heritage that tourists are interested in from the attention characteristics. Based on the degree of matching, it determines the tourists' attention tendency and experience needs for different cultural heritages. Based on the attention tendency and experience needs, it forms content containing tourists' characteristic preferences and needs, and constructs the tourists' personalized profile.

[0107] The relevant content of attention and demand tendencies for different types of cultural heritage and tour experience is extracted from the personalized profile. According to the strength of attention and the clarity of demand, corresponding weights are assigned to the movement pattern feature, emotional response feature, and attention feature. The stronger the attention and the clearer the demand, the higher the corresponding feature weight. The movement pattern feature, emotional response feature, and attention feature are integrated according to their corresponding weights. In the integration process, the performance of high-weight features is highlighted and the performance of low-weight features is weakened to form a feature combination that includes the tourist's emotional tendencies, thus obtaining the tourist's preliminary emotional state vector.

[0108] A preset emotional baseline for cultural heritage scenes is retrieved. This baseline is a combination of benchmark features obtained by collecting emotional state data from a large number of ordinary tourists in the cultural heritage exhibition area and calculating the mean. Each feature in the preliminary emotional state vector is compared one by one with the corresponding benchmark features in the emotional baseline of the cultural heritage scene. The common parts that are consistent with the benchmark features and the individual parts that differ from the benchmark features are identified in the preliminary emotional state vector. The common parts are removed and the individual parts are retained. The retained individual parts are the content after eliminating the interference of common scene features, and the emotional state analysis data of the tourists is obtained.

[0109] The system retrieves the personal registration information filled in by tourists when registering on the cultural tourism platform, as well as their historical visit records of three or more visits to the cultural heritage exhibition area. The personal registration information includes age, occupation, and actively selected interest tags. The historical visit records include the duration of stay in each exhibition area, the names and number of interactive projects participated in, and cultural heritage content collected or shared. The system extracts the content reflecting preferences from the above information. If the "Ancient Architecture" tag is selected during registration, and the tourist stays in the Ancient Architecture exhibition area for more than 30 minutes in a single visit and participates in more than two touch interactions, then "Ancient Architecture" is included in the preference range. If the tourist participates in audio guide interactions multiple times, then "Audio Guide Interaction" is included in the preference range. All extracted preference content is integrated to obtain the tourist's initial personal preference set.

[0110] Each preference in the initial set of personal preferences is categorized according to preset criteria. The cultural content preference category corresponds to specific cultural heritage types, including four categories: ancient architecture, traditional calligraphy and painting, unearthed artifacts, and folk crafts. All preferences related to specific cultural heritage types are classified into this category. The interactive form preference category corresponds to interactive tour methods, including three categories: touch experience, voice Q&A, and VR simulation. All preferences related to interactive methods are classified into this category. The environmental atmosphere preference category corresponds to the environmental conditions of the exhibition area, including three categories: quiet and low light, bright and lively, and natural ventilation. All preferences related to the environmental requirements of the exhibition area are classified into this category. After classification, the content is organized into a clear structure to obtain the visitor's category preference information.

[0111] For each item in the cultural content preference category, the gaze duration and voice interaction content corresponding to specific cultural heritage elements are extracted from the attention features. For example, if the cultural content preference category includes "ancient architecture," the gaze duration of ancient architectural components and the sentences mentioning related terms such as "ancient architecture" and "dougong" in voice interaction are extracted, and a corresponding relationship is established between the two. For each item in the interaction form preference category, the path complexity and touch frequency corresponding to the movement pattern features are extracted. Path complexity is determined by the number of turns in the tour path every 10 minutes, and touch frequency is counted according to the number of touches for the corresponding interaction form. For example, if "touch experience" is preferred, touch frequency data is extracted, and a corresponding relationship is established between the two. For each item in the environmental atmosphere preference category, the emotional valence tendency in the emotional response features is extracted. The emotional valence tendency is determined by heart rate variability and skin conductance response. For example, if "quiet and low light" is preferred, the corresponding valence tendency is when the difference between two consecutive heart rate variability fluctuations is ≤5 and the skin conductance response value is ≤20. A corresponding relationship is established between the two. All corresponding relationships are integrated to obtain the tourist's preference feature mapping relationship.

[0112] Based on the preference feature mapping relationship, the association strength between category preference information and corresponding features is calculated. The association strength is divided into three levels according to the degree of matching: 10 points for a complete match, 5 points for a partial match, and 0 points for no match. A corresponding association strength score is calculated for each category preference information. Weights are assigned according to the association strength scores: 40% for features with 10 points, 20% for features with 5 points, and 0% for features with 0 points. Based on this weight, movement pattern features, emotional response features, and attention features are integrated, highlighting the content corresponding to high-weight features and weakening the content corresponding to low-weight features. The integrated content includes the tourist's core preferences and corresponding feature performance, in order to construct the tourist's initial personalized profile.

[0113] The beneficial effects include achieving deep integration of multi-dimensional state data and personal preference information of tourists in cultural heritage tourism scenarios. By collecting tourists' personal registration information and historical visit records, the system accurately mines and categorizes these data to form category preference information. A clear mapping relationship is established between category preference information and movement pattern characteristics, emotional response characteristics, and attention characteristics. The correlation strength is scientifically calculated and weighted to construct an initial personalized profile. Based on the personalized profile, feature weights are rationally allocated, and a preliminary emotional state vector is generated. Combined with a pre-set emotional baseline for cultural heritage scenarios, common interference is eliminated, accurately obtaining tourist emotional state analysis data. The entire process is clear and reproducible, without ambiguous descriptions or black-box processing. It accurately captures tourists' core preferences and true emotional tendencies, providing reliable data support for subsequent personalized optimization of cultural tourism services and upgrading of scene experiences, effectively improving the tourist experience and service quality of cultural heritage tourism scenarios.

[0114] S3. Based on a preset cultural heritage element library, perform multi-dimensional feature matching on the emotional state analysis data to obtain a personalized cultural experience plan for the tourist.

[0115] In this embodiment of the invention, the step of performing multi-dimensional feature matching on the emotional state analysis data based on a preset cultural heritage element library to obtain a personalized cultural experience plan for the tourist includes:

[0116] Multi-category label extraction is performed on the preset cultural heritage element library to obtain a multi-dimensional feature set of cultural heritage in the cultural heritage tourism scene;

[0117] The intensity distribution and tendency of emotions in the emotional state analysis data are analyzed by feature space mapping to obtain the multi-dimensional feature vector of the tourist's emotions;

[0118] The matching degree between the emotional multidimensional feature vector and the cultural heritage multidimensional feature set is evaluated, and based on the evaluation results, a set of highly relevant elements of the cultural heritage multidimensional feature set is selected.

[0119] Based on the cultural theme coherence and logical experience sequence among the elements in the highly relevant element set, an initial cultural experience sequence for the cultural heritage tourism scene is constructed.

[0120] The initial cultural experience sequence is subjected to immersion consistency verification, and the order of elements and interaction are adjusted to obtain the tourist's personalized cultural experience plan.

[0121] The pre-defined cultural heritage element library contains all cultural heritage entities, interactive projects, explanatory content, and scene arrangements within the exhibition area. Each element is associated with detailed attribute information, covering cultural themes, presentation formats, interaction methods, and emotional compatibility types. Tag tags are extracted for each element in the library. Cultural theme tags are categorized by ancient architecture, traditional calligraphy and painting, unearthed artifacts, and folk crafts; presentation format tags are categorized by physical display, audio explanation, and video playback; interaction method tags are categorized by touch experience, voice Q&A, and VR simulation; and emotional compatibility type tags are categorized by calmness, pleasure, curiosity, and focus. All element tags are organized and summarized according to a unified dimension to ensure accurate correspondence between each tag and element, resulting in a multi-dimensional feature set of the cultural heritage tourism scene. Emotional state analysis data includes tourists' individual emotional tendencies and corresponding expressions after removing common scene interference. Feature space mapping analysis is performed on the distribution and tendency of emotional intensity, first dividing it into four core emotional dimensions: calmness, pleasure, curiosity, and focus.

[0122] The intensity of each dimension is determined according to specific standards. Calmness is determined based on the stability of heart rate variability and skin conductance response. A high level is defined as a heart rate variability difference of ≤5 and a skin conductance response value of ≤20. A medium level is defined as a heart rate variability difference of 6-10 and a skin conductance response value of 21-30. A level outside the above range is defined as low. The intensity of the other dimensions is determined according to fixed standards corresponding to physiological feedback and behavioral characteristics. The intensity of the four dimensions is arranged in the order of calmness, pleasure, curiosity, and focus to obtain the multi-dimensional feature vector of the tourist's emotions.

[0123] A correspondence rule was established between the emotional dimension and the multi-dimensional feature set labels of cultural heritage. Calmness corresponds to the label of calmness, pleasure to pleasure, curiosity to curiosity, and focus to focus. The strength of each dimension of the emotional multi-dimensional feature vector was matched and evaluated with its corresponding label. Each dimension matching the corresponding strength requirement received 25 points, with a maximum score of 100 points across all four dimensions. The matching score for each element was calculated, and elements with scores ≥80 points were selected. These elements, satisfying tourists' multi-dimensional emotional needs, were integrated to form a highly relevant element set of the cultural heritage multi-dimensional feature set. The cultural themes of each element in the highly relevant element set were analyzed, grouping elements with the same or similar themes into the same group, such as grouping ancient architecture elements together and traditional calligraphy and painting elements together, ensuring the continuity of the cultural theme within the same group.

[0124] Following the logical order of typical visitor paths, different themed groups are arranged sequentially from the entrance to the exit of the exhibition area. Within each group, elements are ordered by experience depth, starting with basic display elements and then interactive elements. For example, in the ancient architecture group, elements for viewing actual ancient buildings are arranged first, followed by interactive elements for touching ancient architectural components. All elements are connected in this order to construct the initial cultural experience sequence of the cultural heritage tourism scene. Immersion consistency is checked based on the emotional matching type corresponding to each element. It is determined whether there are conflicts in the emotional matching types of adjacent elements in the initial cultural experience sequence; that is, if the emotional matching type of the preceding element is calm, and the following element is lively, it is considered a conflict.

[0125] When conflicts arise, adjust the order of elements, arranging elements with similar emotional appeal adjacently. Simultaneously, optimize the interaction transitions, setting a 15-second transition time when switching between adjacent elements, playing soft background music with the corresponding theme during the transition to avoid a sense of interruption. Once all conflicts are adjusted and the interaction transitions are smooth, the personalized cultural experience plan for the tourists is obtained.

[0126] The beneficial effects include extracting multi-dimensional feature sets from a pre-defined cultural heritage element library to achieve a precise correspondence between cultural heritage elements and tourists' emotional needs. By performing feature space mapping analysis on emotional state data, multi-dimensional emotional feature vectors that accurately reflect tourists' true emotional tendencies are generated. Matching degree assessments are conducted based on clear correspondence rules to select highly relevant element sets that closely match tourists' emotional needs. An initial cultural experience sequence is constructed by combining cultural theme coherence and tour logic. The order of elements and interaction connections are adjusted through immersion consistency checks to avoid emotional experience conflicts and ensure a smooth experience. The entire process is reproducible and unambiguous, resulting in a personalized cultural experience plan that accurately matches tourists' emotional preferences and cultural needs, enhancing tourists' immersion and cultural perception, and improving the personalized service capabilities and experience quality of cultural heritage tourism scenarios.

[0127] S4. Simulate the effect of the personalized cultural experience plan in the cultural heritage tourism scene, and monitor the behavioral status feedback data of the tourists in real time;

[0128] In this embodiment of the invention, the step of simulating the effect of the personalized cultural experience scheme in the cultural heritage tourism scenario and monitoring the behavioral status feedback data of the tourists in real time includes:

[0129] The cultural content and interactive processes planned in the personalized cultural experience scheme are transformed into a series of multimedia control commands that drive augmented reality devices, projection devices and audio devices in the cultural heritage tourism scene.

[0130] Based on the multimedia control command sequence, corresponding virtual cultural elements and interactive guidance are synchronously rendered and superimposed in the actual physical scene where the tourist is located to simulate the effect.

[0131] During the simulation, facial expression image data, body movement trajectory data, and voice semantic data of the tourists are collected simultaneously.

[0132] Feature fusion is performed on the facial expression image data, the body movement trajectory data, and the speech semantic data to obtain the tourist's behavioral state feedback data.

[0133] The personalized cultural experience solution includes the presentation format of virtual cultural elements, interactive guidance nodes and corresponding content. For each piece of content, the corresponding devices and control details are clearly defined. The instructions for augmented reality devices include the display position, display size and duration of virtual elements. The instructions for projection devices include the projection area, projection content and resolution parameters. The instructions for audio devices include the playback content, volume and playback time. According to the interactive process planned in the solution, all device instructions are arranged by time nodes to form an orderly multimedia control instruction sequence.

[0134] The corresponding equipment is activated according to the time nodes of the multimedia control command sequence. The augmented reality equipment captures the location of the cultural heritage entity through the built-in spatial positioning module and accurately superimposes the virtual cultural elements next to the entity to ensure that the virtual elements and the physical objects are in perfect alignment. The projection equipment projects warm yellow interactive guidance signs on the designated ground area. The signs are continuously projected until the visitor enters the next experience node. The audio equipment plays the corresponding content in sync, with the volume stabilized at 60 decibels. The presentation of virtual elements and the projection of guidance signs are precisely synchronized, achieving a natural integration of virtual cultural elements, interactive guidance and physical scene, and completing the effect simulation.

[0135] Throughout the simulation, high-definition cameras deployed in the experience area captured key muscle movements of the visitor's face, such as the corners of their mouth, eyes, and eyebrows, frame by frame. Millimeter-wave radar and high-definition visual acquisition equipment simultaneously tracked the visitor's body coordinates and limb joint movements, recording specific actions such as raising hands, pausing, and turning around. Directional microphones focused on the visitor's location to collect voice content, recording only voice with a volume higher than 50 decibels. All data was collected synchronously at a frequency of one frame per second to ensure real-time correspondence with the simulation process. Muscle movement features were extracted from facial expression image data: an upturned mouth corresponds to pleasure, a furrowed brow to confusion, and a blank expression to indifference, generating content related to emotional inclination. Key movements were extracted from limb movement trajectory data: pausing for ≥3 seconds corresponds to attention, raising hands to touch virtual elements corresponds to active participation, and quickly passing by corresponds to indifference, generating content related to participation. Keywords were extracted from speech semantic data, distinguishing between praise, question, and neutral expressions. Emotional inclination, participation, and speech expression features at the same point were integrated in chronological order, with the features corroborating each other to form complete data content, obtaining the visitor's behavioral state feedback data.

[0136] The beneficial effects include accurately translating personalized cultural experience plans into multimedia control command sequences, clarifying the operating parameters and coordination timing of various devices, and ensuring the orderly linkage of augmented reality devices, projection devices, and audio equipment. This achieves a natural integration of virtual cultural elements, interactive guidance, and actual physical scenes, restoring the design effect of the plan and enhancing the realism and coordination of the experience simulation. Real-time collection of tourists' facial expressions, body movements, and speech semantic data throughout the process effectively filters environmental interference, ensuring the targeted and complete nature of data collection. By integrating multi-dimensional behavioral data through feature fusion, complete behavioral status feedback data is formed, providing precise basis for subsequent optimization of personalized cultural experience plans and strengthening the effectiveness of cultural heritage tourism scene experience simulation and the rationality of service adjustments.

[0137] S5. Based on the behavioral status feedback data, the personalized cultural experience plan is adaptively adjusted to obtain the optimized cultural experience plan for the tourist.

[0138] In this embodiment of the invention, the step of adaptively adjusting the personalized cultural experience plan based on the behavioral state feedback data to obtain an optimized cultural experience plan for the tourist includes:

[0139] Based on a preset effect evaluation threshold, the immersion index, interaction response index and emotional resonance index in the behavioral state feedback data are traversed and compared to obtain the indicators to be optimized in the behavioral state feedback data.

[0140] By performing key element correlation analysis between the personalized cultural experience scheme and the indicators to be optimized, the target cultural elements and target interaction flow of the personalized cultural experience scheme are obtained.

[0141] Based on a pre-set cultural heritage element library, the presentation duration of the target cultural element, the guidance intensity of the target interactive process, and the visual complexity of the virtual cultural element are adjusted.

[0142] The optimized cultural experience plan for the tourists is determined after the parameter adjustments are completed.

[0143] The preset effectiveness evaluation thresholds are set based on past visitor experience data for the cultural heritage exhibition area. Immersion indicators are defined as an average dwell time of ≥3 seconds per experience node and a facial expression of pleasure or focus of ≥60%. Interaction responsiveness indicators are defined as the number of times virtual elements are actively touched per node at least once and at least one sentence of voice interaction containing relevant keywords. Emotional resonance indicators are defined as the proportion of praising expressions in voice at least 30% and the absence of negative expressions. Each of the three indicators in the behavioral feedback data is compared with its corresponding threshold. Indicators that do not meet any of the above standards are considered indicators to be optimized in the behavioral feedback data. By analyzing all cultural elements and interaction processes in the personalized cultural experience plan, the indicators to be optimized are correlated one by one with the plan content. If the indicator to be optimized is that the immersion level is not up to standard, the cultural elements and interactive processes that guide the stay at the corresponding experience node are identified; if the interaction responsiveness is not up to standard, the interactive cultural elements and interactive processes that guide the operation are identified; if the emotional resonance indicator is not up to standard, the content of the cultural element presentation and the emotional guidance process are identified. These associated elements and processes are the target cultural elements and target interaction processes of the personalized cultural experience plan.

[0144] The system retrieves a pre-defined library of cultural heritage elements and references the appropriate presentation duration for similar cultural elements. If the immersion level is insufficient, the presentation duration of the target cultural element is extended from the basic 5 seconds to 8 seconds to ensure visitors have ample time to perceive the content. For the target interactive process, if the responsiveness is insufficient, the guidance intensity is enhanced by extending the duration of the projected guidance signage to 2 seconds after the visitor triggers the interactive action, while the audio equipment repeats the guidance voice once. If the emotional resonance is insufficient and the feedback data shows confused expressions, the visual complexity of the virtual cultural elements is simplified by removing unnecessary decorative lines and retaining only the core cultural symbols to ensure a concise and easy-to-understand visual presentation.

[0145] The adjusted parameters, including the presentation duration of the target cultural elements, the intensity of the target interactive flow guidance, and the visual complexity of the virtual cultural elements, are synchronously updated into the original personalized cultural experience plan. The corresponding multimedia control command sequences are then corrected to ensure that the equipment operating parameters are consistent with the adjusted plan. The overall logical coherence of the plan is checked to confirm that the adjusted content is conflict-free and conforms to the cultural heritage element library specifications, with no omissions of adjustment items corresponding to the indicators to be optimized. At this point, the adjusted experience plan is complete, and it becomes the optimized cultural experience plan for the tourists.

[0146] The beneficial effects include accurately identifying indicators for optimization in behavioral feedback data based on preset effect evaluation thresholds, and pinpointing target cultural elements and interaction flows that need adjustment in personalized cultural experience plans through key element correlation analysis. Combined with the cultural heritage element database standards, the presentation duration, guidance intensity, and visual complexity of target content are adjusted in a targeted manner to ensure that the adjustments align with actual visitor feedback. The optimized cultural experience plan, resulting from the parameter updates, effectively addresses the shortcomings of the original plan, strengthens the adaptability of the plan to visitor needs, and enhances the visitor's immersion and emotional resonance in cultural heritage tourism scenarios.

[0147] S6. Verify the immersive effect of the optimized experience scheme to obtain the target immersive adaptation design scheme for the cultural heritage tourism scene.

[0148] In this embodiment of the invention, the step of verifying the immersive effect of the optimized experience scheme to obtain the target immersive adaptation design scheme for the cultural heritage tourism scene includes:

[0149] The optimized cultural experience solution is loaded into the verification mode of the cultural heritage tourism scene, and an immersive effect verification invitation is sent to the tourists.

[0150] After the tourists accept the invitation, the optimized cultural experience plan is fully implemented, and the tourists' full-cycle verification feedback data is collected simultaneously.

[0151] The full-cycle verification feedback data is compared with the preset immersion achievement conditions, which include the attention concentration threshold, the positive emotional fluctuation threshold, and the stable range of physiological arousal.

[0152] When the full-cycle verification feedback data meets the immersion achievement criteria, the currently executed optimized cultural experience scheme is determined as the target immersion adaptation design scheme.

[0153] The verification mode for cultural heritage tourism scenarios is a collaborative simulation operation mode, which can replicate the device linkage logic and environmental feedback in real-world tour scenarios. The multimedia control command sequence corresponding to the optimized cultural experience solution is completely imported into this mode, and the parameters of virtual cultural elements, interaction flow timing, and device operation standards are updated synchronously. Invitations are initiated simultaneously via pop-up windows on augmented reality devices and voice prompts on audio equipment within the exhibition area. The pop-up displays verification instructions, and the voice clearly informs visitors of the verification duration and that no additional operational requirements are needed. Visitors then confirm acceptance of the invitation via the touch panel of the augmented reality device.

[0154] After the tourist confirms via the touch panel, the verification mode is activated and the optimized cultural experience plan is fully executed. Augmented reality devices, projection equipment, and audio equipment are linked in sequence according to the plan to present content and guide interaction, ensuring a seamless and complete process. Simultaneously, full-cycle data collection equipment is activated: high-definition cameras capture facial expressions, millimeter-wave radar and visual devices track body movements, physiological signal acquisition devices record heart rate variability and skin conductance, and directional microphones collect voice data. All data is recorded with a unified timestamp, covering the entire process from start to finish, forming the tourist's full-cycle verification feedback data.

[0155] The preset immersion achievement criteria are set based on the immersive experience requirements of cultural heritage and tourism scenarios. The attention concentration threshold is that the proportion of time tourists spend focusing on cultural elements and directional signs during the total execution time of the plan is ≥70%. The positive emotional fluctuation threshold is that the proportion of facial pleasant and focused expressions is ≥60% with no negative expressions. The stable range of physiological arousal is that the difference between adjacent fluctuations in heart rate variability is ≤8 and the skin conductance response value is maintained between 20 and 35. The values ​​of the corresponding indicators in the full-cycle verification feedback data are extracted one by one and compared with the above three achievement criteria to determine whether each indicator meets the corresponding requirements.

[0156] When the proportion of attention concentration and the proportion of positive emotional expressions in the full-cycle verification feedback data both reach the corresponding thresholds, and the physiological arousal index is completely within a stable range, the immersion criteria are deemed met. At this point, no further adjustments are made to the optimized cultural experience plan; instead, the currently implemented plan is directly designated as the target immersion adaptation design plan for the cultural heritage tourism scene, and the verification results are recorded as a reference for the design of similar tourist plans in the future.

[0157] The beneficial effects include replicating the real-world visitor environment based on the verification model of cultural heritage tourism scenarios, fully loading and executing optimized cultural experience solutions, and inviting tourists to participate in verification through standardized procedures. Feedback data is collected throughout the entire implementation cycle of the solution, ensuring the comprehensiveness and accuracy of the verification data. Comparisons are conducted based on clearly defined immersion achievement criteria to ensure the objectivity and reliability of the verification results. Once the criteria are met, a target immersion adaptation design scheme is determined, providing a highly adaptable immersive experience design basis for cultural heritage tourism scenarios, strengthening the practical application value of the solution, and enhancing tourists' immersive experience within the scenario.

[0158] like Figure 2 The diagram shown is a functional module diagram of an immersive adaptation design system for cultural heritage tourism scenes provided in an embodiment of the present invention.

[0159] The immersive adaptation design system 100 for cultural heritage and tourism scenes described in this invention can be installed in an electronic device. According to the functions implemented, the immersive adaptation design system 100 for cultural heritage and tourism scenes includes a data acquisition module 101, a personalized fusion analysis module 102, a feature matching module 103, an effect simulation and monitoring module 104, an adaptive adjustment module 105, and an immersive effect verification module 106. The modules described in this invention can also be referred to as units, which are a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0160] In this embodiment, the functions of each module / unit are as follows:

[0161] The data acquisition module 101 is used to collect multi-dimensional status data of tourists in cultural heritage tourism scenarios. The multi-dimensional status data includes real-time behavior data, physiological feedback data and environmental interaction data.

[0162] The personalized fusion analysis module 102 is used to perform personalized fusion analysis on the multidimensional state data to obtain the emotional state analysis data of the tourist.

[0163] The feature matching module 103 is used to perform multi-dimensional feature matching on the emotional state analysis data based on a preset cultural heritage element library to obtain a personalized cultural experience plan for the tourist.

[0164] The effect simulation and monitoring module 104 is used to simulate the effect of the personalized cultural experience scheme in the cultural heritage tourism scene and monitor the behavioral status feedback data of the tourists in real time.

[0165] The adaptive adjustment module 105 is used to adaptively adjust the personalized cultural experience plan based on the behavioral state feedback data to obtain the optimized cultural experience plan for the tourist.

[0166] The immersive effect verification module 106 is used to verify the immersive effect of the optimized experience scheme and obtain the target immersive adaptation design scheme of the cultural heritage tourism scene.

[0167] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0168] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0169] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0170] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0171] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0172] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A cultural heritage travel scene immersion adaptation design method, characterized in that, The method comprises: S1, collecting multi-dimensional state data of tourists in a cultural heritage travel scene, the multi-dimensional state data comprising real-time behavior data, physiological feedback data and environmental interaction data; S2, performing individualized fusion analysis on the multi-dimensional state data to obtain emotional state analysis data of the tourists; S3, performing multi-dimensional feature matching on the emotional state analysis data based on a preset cultural heritage element library to obtain an individualized cultural experience scheme for the tourists; S4, simulating the effect of the individualized cultural experience scheme in the cultural heritage travel scene and monitoring the behavior state feedback data of the tourists in real time; S5, performing adaptive adjustment on the individualized cultural experience scheme based on the behavior state feedback data to obtain an optimized cultural experience scheme for the tourists; S6, verifying the immersion effect of the optimized experience scheme to obtain a target immersion adaptation design scheme for the cultural heritage travel scene.

2. The cultural heritage travel scene immersion adaptation design method of claim 1, wherein, The method comprises: S1, collecting multi-dimensional state data of tourists in a cultural heritage travel scene, the multi-dimensional state data comprising real-time behavior data, physiological feedback data and environmental interaction data; S2, performing individualized fusion analysis on the multi-dimensional state data to obtain emotional state analysis data of the tourists; S3, performing multi-dimensional feature matching on the emotional state analysis data based on a preset cultural heritage element library to obtain an individualized cultural experience scheme for the tourists; S4, simulating the effect of the individualized cultural experience scheme in the cultural heritage travel scene and monitoring the behavior state feedback data of the tourists in real time; S5, performing adaptive adjustment on the individualized cultural experience scheme based on the behavior state feedback data to obtain an optimized cultural experience scheme for the tourists; 3. The cultural heritage travel scene immersion adaptation design method of claim 1, wherein, S6, verifying the immersion effect of the optimized experience scheme to obtain a target immersion adaptation design scheme for the cultural heritage travel scene. The method comprises: S1, collecting multi-dimensional state data of tourists in a cultural heritage travel scene, the multi-dimensional state data comprising real-time behavior data, physiological feedback data and environmental interaction data; S2, performing individualized fusion analysis on the multi-dimensional state data to obtain emotional state analysis data of the tourists; S3, performing multi-dimensional feature matching on the emotional state analysis data based on a preset cultural heritage element library to obtain an individualized cultural experience scheme for the tourists; S4, simulating the effect of the individualized cultural experience scheme in the cultural heritage travel scene and monitoring the behavior state feedback data of the tourists in real time; S5, performing adaptive adjustment on the individualized cultural experience scheme based on the behavior state feedback data to obtain an optimized cultural experience scheme for the tourists; 4. The cultural heritage travel scene immersion adaptation design method of claim 3, wherein, S6, verifying the immersion effect of the optimized experience scheme to obtain a target immersion adaptation design scheme for the cultural heritage travel scene. The method comprises: S1, collecting multi-dimensional state data of tourists in a cultural heritage travel scene, the multi-dimensional state data comprising real-time behavior data, physiological feedback data and environmental interaction data; S2, performing individualized fusion analysis on the multi-dimensional state data to obtain emotional state analysis data of the tourists; S3, performing multi-dimensional feature matching on the emotional state analysis data based on a preset cultural heritage element library to obtain an individualized cultural experience scheme for the tourists; S4, simulating the effect of the individualized cultural experience scheme in the cultural heritage travel scene and monitoring the behavior state feedback data of the tourists in real time; S5, performing adaptive adjustment on the individualized cultural experience scheme based on the behavior state feedback data to obtain an optimized cultural experience scheme for the tourists; S6, verifying the immersion effect of the optimized experience scheme to obtain a target immersion adaptation design scheme for the cultural heritage travel scene. Personal registration information and historical tour records of the tourists are subjected to personalized data mining to obtain an initial personal preference set of the tourists; The initial personal preference set is subjected to structured classification to obtain category preference information of the tourists, the category preference information including a cultural content preference category, an interactive form preference category, and an environment atmosphere preference category; The cultural content preference category is associated with a gaze duration on a specific cultural heritage element and voice interaction content in the attention degree feature, the interactive form preference category is associated with path complexity and touch frequency in the motion mode feature, and the environment atmosphere preference category is associated with an emotional valence tendency in the emotional response feature, to obtain a preference feature mapping relationship of the tourists; Based on the preference feature mapping relationship, an association strength of the category preference information and corresponding features is calculated, and the motion mode feature, the emotional response feature, and the attention degree feature are weighted and integrated based on the association strength, to construct an initial personalized portrait of the tourists.

5. The cultural heritage travel scene immersion adaptation design method of claim 4, wherein, The calculation formula of the association strength is as follows: ； In the formula, For the first The strength of the association between the category preference information and the corresponding features. The preset feature correlation adjustment coefficient, For the first The category preference information, For the preference feature mapping relationship, the first... The feature vectors of the aforementioned category preference information For the first The category preference information With the corresponding feature vector The Pearson correlation coefficient between them For the corresponding feature vector The standard deviation within the preset time window, The preset characteristic significance adjustment coefficient, The duration of the current scene. It is a natural constant.

6. The cultural heritage travel scene immersion adaptation design method of claim 1, wherein, Based on the preset cultural heritage element library, the emotional state analysis data is subjected to multi-dimensional feature matching to obtain a personalized cultural experience scheme of the tourists, including: Multi-category label extraction is performed on the preset cultural heritage element library to obtain a cultural heritage multi-dimensional feature set of the cultural heritage travel scene; Feature space mapping analysis is performed on the intensity distribution and tendency of emotions in the emotional state analysis data to obtain an emotional multi-dimensional feature vector of the tourists; The emotional multi-dimensional feature vector and the cultural heritage multi-dimensional feature set are subjected to matching degree evaluation, and based on the evaluation result, a high correlation element set of the cultural heritage multi-dimensional feature set is screened out; Based on cultural theme coherence and logical experience order between elements in the high correlation element set, an initial cultural experience sequence of the cultural heritage travel scene is constructed; Immersion consistency verification is performed on the initial cultural experience sequence, and element order and interactive connection are adjusted to obtain the personalized cultural experience scheme of the tourists.

7. The cultural heritage travel scene immersion adaptation design method of claim 1, wherein, The personalized cultural experience scheme is subjected to effect simulation in the cultural heritage travel scene, and behavior state feedback data of the tourists are monitored in real time, including: Cultural content and interactive processes planned in the personalized cultural experience scheme are converted into a multimedia control instruction sequence for driving augmented reality equipment, projection equipment, and sound equipment in the cultural heritage travel scene; Based on the multimedia control instruction sequence, corresponding virtual cultural elements and interactive guidance are synchronously rendered and superimposed in an actual physical scene where the tourists are located, to perform effect simulation; In the process of effect simulation, facial expression image data, body movement trajectory data, and voice semantic data of the tourists are synchronously collected; The facial expression image data, the body movement trajectory data, and the voice semantic data are subjected to feature fusion to obtain behavior state feedback data of the tourists. 8.The cultural heritage and travel scene immersion adaptation design method of claim 1, wherein, The adaptive adjustment of the individualized cultural experience scheme based on the behavior state feedback data obtains an optimized cultural experience scheme of the tourist, including: Based on a preset effect evaluation threshold, the immersion degree index, the interactive response degree index, and the emotional resonance index in the behavior state feedback data are iteratively compared to obtain a to-be-optimized index of the behavior state feedback data; The key element association analysis of the individualized cultural experience scheme and the to-be-optimized index obtains a target cultural element and a target interactive process of the individualized cultural experience scheme; According to a preset cultural heritage element library, the presentation time length of the target cultural element, the guidance intensity of the target interactive process, and the visual complexity of the virtual cultural element are parameter adjusted; The experience scheme after the parameter adjustment is determined as the optimized cultural experience scheme of the tourist. 9.The cultural heritage and travel scene immersion adaptation design method of claim 1, wherein, The immersion effect verification of the optimized experience scheme obtains a target immersion feeling adaptation design scheme of the cultural heritage travel scene, including: The optimized cultural experience scheme is loaded into the verification mode of the cultural heritage travel scene, and an immersion effect verification invitation is initiated to the tourist; After the tourist accepts the invitation, the optimized cultural experience scheme is completely executed, and full-cycle verification feedback data of the tourist is synchronously collected; The full-cycle verification feedback data is compared with a preset immersion feeling standard condition, wherein the immersion feeling standard condition includes an attention concentration degree threshold, an emotional positive fluctuation threshold, and a physiological arousal degree stable interval; When the full-cycle verification feedback data meets the immersion feeling standard condition, the currently executed optimized cultural experience scheme is determined as the target immersion feeling adaptation design scheme.

10. A cultural heritage travel scene immersion adaptation design system, characterized in that, A cultural heritage travel scene immersion feeling adaptation design method for realizing the method of claim 1, the system comprising: A data collection module for collecting multi-dimensional state data of tourists in a cultural heritage travel scene, the multi-dimensional state data including real-time behavior data, physiological feedback data, and environmental interaction data; An individualized fusion analysis module for individualized fusion analysis of the multi-dimensional state data to obtain emotional state analysis data of the tourist; A feature matching module for multi-dimensional feature matching of the emotional state analysis data based on a preset cultural heritage element library to obtain an individualized cultural experience scheme of the tourist; An effect simulation and monitoring module for effect simulation of the individualized cultural experience scheme in the cultural heritage travel scene and real-time monitoring of behavior state feedback data of the tourist; An adaptive adjustment module for adaptive adjustment of the individualized cultural experience scheme based on the behavior state feedback data to obtain an optimized cultural experience scheme of the tourist; An immersion effect verification module for immersion effect verification of the optimized experience scheme to obtain a target immersion feeling adaptation design scheme of the cultural heritage travel scene.

Images