Exhibition layout design effect analysis and evaluation method

Abstract

The invention belongs to the technical field of display design evaluation, and particularly relates to an exhibition display layout design effect analysis and evaluation method, which comprises the following steps of: constructing a dynamic spatial topology network by collecting audience moving tracks, exhibit information and spatial structure data in real time; the problem of insufficient attention on space utilization influenced by dynamic factors such as human traffic fluctuation is solved. And dynamic changes in the space are converted into quantifiable network nodes and connection relationships, so that the space utilization state is changed from static design to dynamic monitoring, accurate capture of the real-time use condition of the exhibition space is realized, a comprehensive and real-time data basis is provided for subsequent analysis, and the real-time monitoring of the exhibition space is realized. Meanwhile, the dynamic space topology network is analyzed by means of spatial-temporal feature fusion to determine the edge weight and the exhibition area correlation degree, the spatial efficiency index and the dynamic line rationality index are generated in combination with an analytic hierarchy process and multi-dimensional analysis, and the defect that a space utilization rate core evaluation index is not established in the prior art is overcome.

Description

Technical Field

[0001] This invention belongs to the field of exhibition design evaluation technology, and more specifically, it relates to a method for analyzing and evaluating the effect of exhibition layout design. Background Technology

[0002] Modern exhibition design needs to comprehensively consider multiple dimensions such as space planning, exhibit display, information delivery, visitor flow guidance, and interactive experience. It needs to meet aesthetic requirements and achieve goals such as education, commerce, or cultural dissemination. This figure highlights the importance and necessity of evaluating the effectiveness of exhibition hall layout design.

[0003] Existing technologies, such as the data processing method and device for exhibition hall layout design disclosed in Chinese invention patent application No. 202410064780.X, solve the problems of low efficiency and insufficient adaptability of manual layout design by using technical means such as association analysis of preset data processing models and module combination optimization based on exhibition hall theme content data and layout design modular parameters, thereby realizing the automatic generation of data-driven modular layout and improving the universality and scene adaptability of design schemes.

[0004] Existing technical solutions primarily focus on how to design exhibition layouts, paying less attention to the impact of dynamic factors such as fluctuations in visitor traffic on space utilization. Consequently, no core evaluation indicators for space utilization have been established, nor has a mechanism for balancing exhibit display effectiveness and space efficiency been established. This makes it impossible to accurately measure space utilization efficiency, and consequently, to further optimize the exhibition layout and improve its adaptability. Summary of the Invention

[0005] In view of this, a method for analyzing and evaluating the design effect of exhibition layout is proposed to solve the problem of accurately measuring the space utilization efficiency of existing technologies.

[0006] The objective of this invention can be achieved through the following technical solution: This invention provides a method for analyzing and evaluating the design effect of exhibition layout, which includes: real-time collection of audience movement trajectories, exhibit information and spatial structure data in the exhibition space, and construction of a dynamic spatial topology network including basic topology nodes, dynamic virtual nodes and topology edges.

[0007] The dynamic spatial topology network is analyzed by spatiotemporal feature fusion to determine the edge weights and the correlation between each exhibition area.

[0008] By integrating edge weights and audience trajectory sequences, a spatial efficiency index is generated using the analytic hierarchy process (AHP). Furthermore, by combining the aforementioned correlation and visitor movement trajectories, a circulation rationality index is generated through multidimensional analysis.

[0009] A layout rationality index is generated based on the weighted fusion of the space efficiency index and the circulation rationality index. When the index is lower than a preset threshold, the display layout is optimized.

[0010] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) The present invention solves the problem of insufficient attention to the impact of dynamic factors such as fluctuations in visitor flow on space utilization in the prior art by collecting visitor movement trajectories, exhibit information and spatial structure data in real time and constructing a dynamic spatial topology network. It transforms the dynamic changes in the space into quantifiable network nodes and connections, so that the space utilization status shifts from static design to dynamic monitoring, and realizes accurate capture of the real-time usage of the exhibition space, providing a comprehensive and real-time data foundation for subsequent analysis.

[0011] (2) This invention utilizes spatiotemporal feature fusion analysis of dynamic spatial topology networks to determine edge weights and exhibition area correlations. Simultaneously, it combines analytic hierarchy process (AHP) and multidimensional analysis to generate spatial efficiency and circulation rationality indices, thus overcoming the deficiency of existing technologies in establishing core evaluation indicators for space utilization. This forms a dual-core evaluation system encompassing both spatial efficiency and user experience, thereby accurately measuring space utilization efficiency from multiple perspectives and changing the previous extensive evaluation model that relied solely on experience or a single indicator.

[0012] (3) This invention generates a layout rationality index by weighting and fusing the space efficiency index and the circulation rationality index, and triggers display layout optimization when the index is below a threshold, thus constructing a balance mechanism between exhibit display effect and space efficiency. Furthermore, while considering space utilization efficiency, it also takes into account the audience's viewing experience, avoiding the imbalance between the two in existing technologies. This achieves a shift from passive design to active optimization, enabling the display layout to be dynamically adjusted based on real-time data, significantly improving the adaptability of the display layout to different exhibition scenarios and changes in visitor flow. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a schematic diagram of the implementation steps of the method of the present invention.

[0015] Figure 2 This is a schematic diagram of the dynamic spatial topology network construction process of the present invention.

[0016] Figure 3 This is a schematic diagram illustrating the specific process of dynamic edge weighting in this invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Please see Figure 1 As shown, the present invention provides a method for analyzing and evaluating the design effect of exhibition layout. The method includes: S1, collecting visitor movement trajectories, exhibit information and spatial structure data in real time within the exhibition space, and constructing a dynamic spatial topology network including basic topology nodes, dynamic virtual nodes and topology edges.

[0019] Specifically, the three-dimensional structural data includes spatial dimensions, passage width, obstacle distribution locations and obstacle geometric parameters, as well as the exhibition themes of each exhibition area and their actual coordinate positions in the exhibition space, which are obtained through a combination of laser scanning and BIM modeling.

[0020] The exhibit information consists of the center coordinates of each exhibit, which are obtained in real time through distributed readers by embedding RFID tags in the exhibit base.

[0021] The audience movement trajectory is a sequence of audience position coordinates, which is collected by fusing UWB positioning tags with a visual tracking system.

[0022] It should be added that the deployment of the UWB positioning tags meets the following requirements: the anchor array covers the exhibition space in a cellular topology, the distance between adjacent anchor points does not exceed 8 meters, and the communication delay compensation between the tags and anchor points is achieved through a timestamp synchronization mechanism.

[0023] Further, please refer to Figure 2 As shown, the specific construction process of the dynamic spatial topology network includes: S11, dividing the exhibition space into regular grid units with a preset precision, assigning a unique identifier to each grid unit, and marking whether it is a passable area.

[0024] S12. Use the coordinates of the exhibit locations, entrances and exits, and functional area boundaries generated by the three-dimensional spatial segmentation algorithm as fixed nodes.

[0025] It should be added that the generation of functional area boundary coordinates includes: extracting the three-dimensional structural features of the exhibition space through a point cloud segmentation algorithm, and clustering the segmented areas based on functional semantic labels to generate the boundary coordinates of the guide area, interactive area, and rest area. Furthermore, the point cloud segmentation algorithm is a relatively mature existing algorithm, and its specific execution process will not be elaborated here.

[0026] S13. Based on the exhibit information, map the center coordinates of each exhibit to its nearest accessible grid to generate exhibit nodes, then label the IDs of the exhibit nodes, and construct a basic topology node set based on the fixed nodes and exhibit nodes.

[0027] S14. Denoise the audience trajectory data and statistically analyze the preprocessed audience trajectory data to obtain the dwell time of each audience member in each grid cell.

[0028] It should be added that the audience trajectory data is preprocessed by denoising the original coordinate data using the Kalman filter algorithm to filter out outliers caused by signal interference.

[0029] It should also be added that the preprocessed audience trajectory data is matched to the corresponding grid cells in the order of timestamps, grouped by audience ID and grid number, the time difference between adjacent trajectory points within the group is calculated and the time difference within the same grid is accumulated to obtain the dwell time of each audience member in each grid cell.

[0030] S15. When the time a viewer stays in a certain grid cell exceeds a preset threshold, and the change in the coordinates of adjacent timestamps is less than the corresponding preset position coordinate change threshold, it is determined to be a valid staying area. The centroid coordinates of the staying area are generated and used as the position coordinates of the staying point.

[0031] S16. Map a single visitor's stop point to the nearest basic topology node or grid cell, and aggregate similar stop points according to a preset time window to generate a dynamic virtual node set.

[0032] It should be added that aggregating similar data is a clustering method, which is a relatively common data processing method. The specific processing steps will not be elaborated here.

[0033] S17. Based on the passable regions in the grid space, the node connection relationship is defined using the graph theory adjacency matrix method. Topological edges are generated based on the node connection relationship, and the effective topological edges are obtained after removing unreachable topological edges.

[0034] In one specific embodiment, the graph theory adjacency matrix method is an existing algorithm, and its specific definition process will not be described in detail here.

[0035] It should be noted that for the node pairs corresponding to the removed unreachable paths, the detour path can be recalculated in the remaining network using the A* algorithm, and alternative topological edges can be added as alternative paths. The A* algorithm and the subsequent Dijkstra algorithm are existing algorithms, and will not be explained further here.

[0036] It should also be noted that the specific process for generating alternative paths is as follows: After the paths between pairs of nodes in the basic topology are eliminated, alternative paths are automatically generated. Based on the remaining reachable nodes, the shortest alternative path is calculated using Dijkstra's algorithm. The overlap rate between the alternative path and the obstacle mask is calculated twice to ensure that the overlap rate is below a threshold. Alternative edges are added to the topology network, and the edge weight is set to the product of the original path weight and the detour coefficient. The detour coefficient typically ranges from 1.2 to 1.5.

[0037] Understandably, the precise value of the detour coefficient needs to take into account a variety of factors, such as the specific conditions of the exhibition space, the characteristics of audience behavior, and the nature and objectives of the exhibition. At the spatial level, the main considerations are the width of the passageway and the complexity of the spatial layout.

[0038] If the passageway is wide, it is relatively easy for audiences to navigate around it, so a smaller detour coefficient can be used. Conversely, if the passageway is narrow, a larger value should be used. The specific value can be calculated using the following formula: , This is the detour coefficient. For channel width, To set a reference width for a simple passageway, for example, a value of 5 meters could be used in a large exhibition hall.

[0039] If the exhibition space layout is complex, such as having multiple winding passages or irregular functional area divisions, the complexity is determined by calculating the ratio of the number of winding passages to the total number of passages, and the ratio of the number of irregular functional areas to the total number of functional areas. The weighted sum of these ratios yields the exhibition space layout complexity. If the complexity is greater than or equal to a preset first threshold, the detour coefficient is set to 1.5. If the complexity is greater than or equal to a second preset threshold but less than the first preset threshold, the complexity and the first preset threshold are respectively set as follows: and ,Will As the final value of the detour coefficient, if the complexity of the exhibition space layout is less than the second preset threshold, the detour coefficient will be assigned a value of 1.2.

[0040] In summary, the above steps enable the accurate identification and efficient elimination of unreachable paths in the exhibition space, ensuring that the topology accurately reflects the actual traffic capacity and providing a reliable foundation for subsequent path planning and traffic analysis.

[0041] The specific process for determining unreachable topological edges includes: calculating the Euclidean distance between any adjacent basic topological node, any dynamic virtual node, and any basic topological node and its adjacent dynamic virtual node.

[0042] If the Euclidean distance between two nodes is less than a set threshold, these two nodes will be paired as a pre-selected node pair.

[0043] For each pre-selected node pair, a ray is emitted along the line connecting the two points. The AABB tree is used to quickly detect whether the ray intersects with the triangular mesh face of the obstacle. If the ray intersects with any obstacle or is not a ray, it is determined to be an unreachable path and recorded as an unreachable topological edge.

[0044] The crowd density in each grid cell is obtained by statistically analyzing the preprocessed audience trajectory data. When the crowd density in a grid cell is greater than a set density threshold, all connecting edges of the grid cell are treated as unreachable topological edges.

[0045] Understandably, Euclidean distance and AABB trees are existing algorithms, and the crowd density is the ratio of the number of spectators to the area of ​​the corresponding grid cell.

[0046] It is also understandable that a three-level accessibility verification mechanism has been added to the node connection edge construction stage. The first layer is based on Euclidean distance pre-screening to quickly filter long-distance node pairs. The second layer performs three-dimensional ray collision detection. The third layer sets a dynamic density threshold to deal with temporary crowd obstacles. Then, through three-dimensional collision detection and dynamic obstacle perception, the inaccessible path is accurately eliminated, taking into account both static structural constraints and the impact of temporary crowd flow.

[0047] S18. Combine the basic topological node set, effective topological edges, and dynamic virtual node set to generate a dynamic spatial topological relationship network.

[0048] This invention addresses the problem in existing technologies of insufficient attention to the impact of dynamic factors such as visitor flow fluctuations on space utilization by collecting real-time visitor movement trajectories, exhibit information, and spatial structure data and constructing a dynamic spatial topology network. It transforms dynamic changes within the space into quantifiable network nodes and connections, shifting space utilization from static design to dynamic monitoring. This enables precise capture of real-time exhibition space usage, providing a comprehensive and real-time data foundation for subsequent analysis.

[0049] S2. Determine the edge weights and the correlation between each exhibition area by analyzing the dynamic spatial topology network through spatiotemporal feature fusion.

[0050] Specifically, determining the edge weights includes setting basic edge weights and dynamic edge weights. The basic edges are the connecting edges corresponding to adjacent basic topology nodes, and the dynamic edges are the connecting edges between dynamic virtual nodes and adjacent basic topology nodes.

[0051] The basic edge weights are obtained by normalizing the inverse of the distance between corresponding unobstructed nodes in the basic topology.

[0052] It should be added that the obstacle-free distance can be calculated using an improved A* algorithm or Dijkstra's algorithm, with the obstacle-free area in the topology network as the search space, and the distance corresponding to the shortest path between nodes is calculated as the obstacle-free distance.

[0053] Please see Figure 3 As shown, the specific setting process of the dynamic edge weight is as follows: B1. Generate audience trajectory sequence based on the real-time collected audience movement trajectory, and extract the average crowd density of the exhibition area where the dynamic virtual node is located.

[0054] B2. For each visitor entering the exhibition area where the dynamic virtual node is located, record their entry time and exit time, and calculate the difference to obtain the individual stay time, and then calculate the average stay time.

[0055] B3. Calculate the rate of change of crowd density according to the preset time window, calculate the average rate of change of crowd density within the window, and calculate the standard deviation of the dwell time of different audiences to obtain the dwell time fluctuation rate.

[0056] B4. If the rate of change of average pedestrian density or the rate of fluctuation of dwell time is greater than or equal to the corresponding set threshold, set a weight compensation factor.

[0057] B5. After normalizing the average pedestrian density and average dwell time, the basic weights are obtained by linear weighting.

[0058] B6. The basic weights are corrected based on the weight compensation factor to obtain the final weights, which are then used as the edge weights of the exhibition area where the corresponding virtual node is located.

[0059] Furthermore, the specific setting process of the weight compensation factor includes: if the average rate of change of pedestrian density is greater than or equal to the corresponding set threshold, the average rate of change of pedestrian density and the corresponding set threshold are used as variables, respectively denoted as... and ,Will As a weighting compensation factor, denoted as , It is a natural constant.

[0060] If the volatility of the duration of stay exceeds the corresponding set threshold, the volatility of the duration of stay and the corresponding set threshold will be used as variables, and then... The settings are configured similarly, and denoted as follows: .

[0061] If both are greater than the set threshold, for and The final weighted compensation factor is obtained by performing a weighted summation calculation, denoted as... ,and The maximum value is 1.

[0062] It should be added that in real-world scenarios, the impact of factors such as the rate of change in average pedestrian density and the fluctuation rate of dwell time on the system is not fixed. When these factors change beyond the set threshold, the original weights cannot accurately reflect their impact, and a weight compensation factor needs to be introduced to adjust the weights to adapt to actual dynamic changes and be flexibly adjusted according to the real situation.

[0063] More specifically, the specific analysis process of the correlation between the various exhibition areas includes: E1, after textualizing the exhibition themes of each exhibition area, obtaining the similarity between the themes of different exhibition areas, and generating a theme similarity matrix. .

[0064] It should be added that the textual processing of the exhibition theme includes: extracting the theme keywords of the exhibition area, generating theme word vectors, and calculating theme similarity using algorithms such as cosine similarity. Among these, calculating theme similarity using algorithms such as cosine similarity is a common existing technique, and its specific calculation formula will not be shown.

[0065] E2. Classify and code the exhibit types, calculate the overlap of exhibit types in different exhibition areas, and construct an exhibit type association matrix. .

[0066] Understandably, the exhibits in each exhibition area are classified and coded to generate a set of codes. The degree of overlap between exhibit types in different exhibition areas is statistically analyzed by calculating the intersection size of the code sets or the Jaccard coefficient.

[0067] E3. Based on the audience movement trajectory, count the number of audience transfers from each starting exhibition area to other target exhibition areas within a preset time window, and construct a transfer frequency matrix. The average dwell time of visitors in each exhibition area was calculated, and then a dwell time correlation matrix was generated using the Pearson correlation coefficient. .

[0068] E4. Based on the actual coordinates of the exhibition areas within the exhibition space, calculate the shortest travel distance between the exhibition areas and construct a distance matrix. .

[0069] E5, to , , , and After normalizing the elements, a weighted sum is calculated according to the set weights to obtain the comprehensive correlation matrix between the exhibition areas. The formula for calculating the correlation matrix is ​​as follows: , Indicates exhibition area and exhibition area The degree of correlation between them ~ These represent the weights corresponding to the topic similarity matrix, exhibit type association matrix, dwell time association matrix, and distance matrix, respectively. , , , and Each represents an exhibition area and exhibition area The similarity between themes, the degree of overlap in exhibit types, the number of visitor transfers, the correlation of average dwell time, and the shortest passage distance.

[0070] It should be added that the methods for calculating the shortest travel distance include: based on the obstacle distribution and passage structure of the exhibition space, using the Dijkstra algorithm or the A* algorithm to calculate the shortest reachable path length between exhibition areas.

[0071] Understandably, the relevance of exhibition areas is influenced by a combination of factors. Factors such as thematic similarity, overlap in exhibit types, visitor movement frequency, dwell time correlation, and distance all reflect the connections between exhibition areas from different dimensions. This formula quantifies and weights these factors to comprehensively consider their effects and avoid the bias of relying on a single factor. Furthermore, it allows for precise quantitative calculation of the relevance between exhibition areas, providing a scientific basis for exhibition layout optimization and resource allocation, and comprehensively and scientifically reflecting the actual relevance between exhibition areas.

[0072] S3. By integrating edge weights and audience trajectory sequences, a spatial efficiency index is generated using the analytic hierarchy process (AHP). Combined with the aforementioned correlation and visitor movement trajectories, a circulation rationality index is generated through multidimensional analysis.

[0073] Specifically, the analysis process of the spatial efficiency index includes: J1, converting the audience's movement trajectory into an ordered sequence of location points, each location point containing a timestamp and location coordinates, and statistically analyzing the trajectory density, maximum continuous dwell time, and transfer probability of each exhibition area.

[0074] J2. The spatial efficiency index is the target layer, the edge weight, trajectory density, dwell time and transfer probability are the criteria layers, and each exhibition area is the scheme layer.

[0075] J3. Construct the judgment matrix of the criterion layer to the target layer and the judgment matrix of the scheme layer to each criterion respectively, and determine the weight allocation after passing the consistency test.

[0076] When performing a consistency test on the judgment matrix, a consistency index and a random consistency index are calculated, and the ratio of the two is recorded as the consistency ratio. When the consistency ratio is less than 0.1, the test can be considered passed.

[0077] J4. Based on the weights of edge weights, trajectory density, dwell time, and transition probability, calculate the partial spatial efficiency index of each exhibition area under each criterion layer, and obtain the comprehensive spatial efficiency index by weighted summation.

[0078] It should be added that trajectory density is calculated by dividing the spatiotemporal grid or kernel density estimation to determine the distribution intensity of location points within a unit area. The maximum sustained dwell time is obtained by identifying dwell time segments within a continuous time window where the rate of change of coordinates is lower than a preset threshold, and extracting the longest duration. The transition probability is obtained by statistically analyzing the proportion of transition frequencies within the interval.

[0079] Understandably, trajectory density reflects the frequency with which a certain area is visited by viewers, dwell time indicates how long viewers stay in a certain area, reflecting the area's attractiveness to viewers, and transfer probability refers to the likelihood of viewers moving from one area to another, reflecting the degree of correlation between areas.

[0080] Understandably, the criterion layer weights are calculated using the eigenvalue method, while the scheme layer weights are generated based on the relative importance of each exhibition area under a single criterion.

[0081] More specifically, experts, designers, and operators in the exhibition field are invited to compare the relative importance of factors such as dynamic edge weights, trajectory density, dwell time, and transition probability in the criterion layer to the generated spatial efficiency index, based on their experience and professional knowledge. A 1-9 scale is used; for example, 1 indicates that two factors are equally important, 3 indicates that one factor is slightly more important than the other, 5 indicates that one factor is significantly more important than the other, 7 indicates that one factor is strongly more important than the other, and 9 indicates that one factor is extremely more important than the other. 2, 4, 6, and 8 are the intermediate values ​​of the above adjacent judgments, constructing a judgment matrix M. For example: .

[0082] More specifically, for each factor in the criterion layer, a judgment matrix for that factor is constructed in the scheme layer. For example, for the dynamic edge weight factor, the dynamic edge weights corresponding to each exhibition area are compared to construct a judgment matrix. For the trajectory density factor, the trajectory density data of each exhibition area are statistically analyzed, and a judgment matrix is ​​constructed after comparison. Similarly, the judgment matrices for the duration of stay are obtained respectively. and the judgment matrix regarding the transition probability .

[0083] The consistency of the judgment matrix of each factor in the criterion layer is checked by the scheme layer. After the check is passed, the weight of each exhibition area relative to the edge weight, trajectory density, dwell time and transition probability is calculated by the eigenvalue method.

[0084] For example, based on the edge weights corresponding to each exhibition area and their weights in the criterion layer, a partial spatial efficiency index based on edge weights is calculated for each exhibition area. The specific calculation formula is as follows: ,in, Indicates the edge weight in The components in Indicates exhibition area exist The components in, among which, Represents the judgment matrix After passing the consistency test, the criterion layer weights are calculated using the eigenvalue method. , Represents the judgment matrix A consistency check is performed. After the check passes, the weight of each exhibition area relative to the edge weight is calculated. Similarly, the partial spatial efficiency index of the exhibition area based on the dwell time and the exhibition area based on the transfer frequency is calculated.

[0085] The spatial efficiency indices of the above-mentioned parts are weighted and summed according to the weight of the criterion layer to obtain the comprehensive spatial efficiency index of each exhibition area.

[0086] Specifically, the analysis process of the circulation rationality index includes: F1, identifying high-frequency paths, hotspot areas, turning points and congestion points based on the exhibition visitor movement trajectory, and then determining the exhibition visitor circulation route.

[0087] F2. For the visitor flow, extract the correlation between adjacent exhibition areas and sum them. After normalization, generate a correlation sub-index.

[0088] F3. Based on the exhibition trajectory data, calculate the deviation between the dwell time of each exhibition area and the preset suggested dwell time, and record it as the dwell time deviation. Also, count the number of backtracking paths and the proportion of exhibition areas with a coverage correlation greater than a set threshold, and record the proportion as the coverage of highly correlated exhibition areas.

[0089] F4. A comprehensive trajectory sub-index is generated by combining the deviation of dwell time, the number of return paths, and the proportion of coverage of highly related exhibition areas.

[0090] F5. The correlation sub-index and the trajectory comprehensive sub-index are weighted and fused to obtain the movement line rationality index.

[0091] It should be added that determining the exhibition flow requires using positioning technologies such as UWB, Bluetooth beacons, and Wi-Fi fingerprinting to collect time-stamped trajectory data. After preprocessing such as noise reduction and map matching, the high-frequency paths, hotspot areas, turning points, and congestion points in the trajectory are analyzed to extract the naturally formed behavioral patterns of the audience. The above data is then cross-compared with the exhibition content logic, such as the order of exhibit importance, thematic narrative, and spatial physical conditions, to identify key exhibition area coverage gaps, route redundancy, or traffic bottlenecks. Based on this, the flow structure is adjusted—strengthening the signage and guidance of high-frequency paths, widening passageways at congested nodes, and adding content connection prompts at turning points. The optimized flow is then verified through AnyLogic simulation, including average travel time and audience satisfaction, ultimately forming an exhibition flow plan that conforms to real-world behavioral patterns.

[0092] For example, the high-frequency path uses the DBSCAN algorithm to cluster the trajectory sequence, extracts the sequence of continuous location points with an occurrence frequency > 30%, calculates the transition probability between nodes on the path, the transition probability is the ratio of the number of transitions to the number of people staying at the starting point, and retains path segments with a probability greater than a set threshold. Specifically, the set threshold corresponding to the retention probability can be 0.6.

[0093] For example, the hotspot stay area is defined by dividing the space into 1m×1m grids, counting the time the audience stays in each grid, and selecting grids with a cumulative number of stays greater than a set threshold for the number of stays as hotspot areas. Specifically, a single user stay of more than 2 minutes is counted as 1 valid stay, and 50 stays per hour is the set threshold for the number of stays.

[0094] Turning nodes are determined by detecting changes in the azimuth of adjacent points in the trajectory. When the azimuth is greater than a set azimuth difference and the distance between the two points is less than a set distance threshold, the node is distinguished as passive or active turning based on the dwell time at the node. The set azimuth difference is 45°, the set distance threshold is 2m, and the dwell time is limited to less than 30 seconds. Passive turning occurs when the passage is narrow, while active turning occurs when the content is attractive.

[0095] The congestion point is determined by calculating the audience density of each area based on real-time location data. The audience density is the ratio of the number of people to the area. When the density of a certain area is greater than a set density threshold and the duration is greater than a set duration, the area is determined to be a congestion point. The set density threshold is 1.5 people / square meter, and the set duration is 10 minutes.

[0096] Understandably, high-frequency paths and hotspot areas reflect actual visitor preferences, relevance reflects the logical connection between exhibition areas, dwell time deviation measures the degree of visitor attention matching with exhibits, and the number of return paths and the coverage ratio of highly relevant exhibition areas reflect the smoothness of the circulation and the completeness of the displayed content, respectively. By integrating these elements, the interactive effectiveness of "people-space-exhibits" in circulation design can be fully captured.

[0097] Understandingly, the relevance sub-index ensures that the exhibition area sequence conforms to the logical presentation theme, avoiding disorderly transitions. The trajectory comprehensive sub-index quantifies the efficiency and experience of the audience's actual movement. For example, excessively long dwell times or frequent backtracking reflect insufficient guidance, while a low-to-high relevance exhibition area coverage ratio indicates that the exhibition content has not effectively reached the target audience. After weighted integration, both can accurately pinpoint "logical gaps" and "experience pain points" in the movement design, such as the lack of effective path loops in highly relevant exhibition areas or congestion in popular exhibit areas leading to poor flow.

[0098] This invention utilizes spatiotemporal feature fusion to analyze dynamic spatial topology networks to determine edge weights and exhibition area correlations. Simultaneously, it combines the analytic hierarchy process (AHP) with multidimensional analysis to generate spatial efficiency and circulation rationality indices, overcoming the deficiency of existing technologies in establishing core evaluation indicators for space utilization. This forms a dual-core evaluation system encompassing both spatial efficiency and user experience, thereby accurately measuring space utilization efficiency from multiple perspectives and changing the previous extensive evaluation model that relied solely on experience or a single indicator.

[0099] S4. Generate a layout rationality index based on the weighted fusion result of the space efficiency index and the circulation rationality index. When the index is lower than the preset threshold, trigger the display layout optimization.

[0100] It should be added that the priority of the two is dynamically adjusted through a weighted fusion coefficient during the optimization process: when the space efficiency index is too low, priority is given to ensuring the accessibility of exhibits and space utilization, such as reducing inefficient display areas. When the circulation rationality index is too low, priority is given to optimizing the visitor movement experience, such as avoiding forced detours or ineffective backtracking.

[0101] Understandably, through iterative optimization, the final layout will achieve "convenient access to highly relevant exhibition areas, efficient utilization of popular exhibit areas, and reasonable configuration of auxiliary spaces," significantly improving the adaptability of the exhibition layout to dynamic scenarios such as fluctuations in visitor flow and changes in exhibits.

[0102] This invention generates a layout rationality index by weighting and fusing a space efficiency index and a circulation rationality index. When the index falls below a threshold, it triggers layout optimization, thus establishing a balance mechanism between exhibit display effectiveness and space efficiency. This approach considers both space utilization efficiency and visitor experience, avoiding the imbalance problem in existing technologies. It represents a shift from passive design to proactive optimization, enabling the display layout to dynamically adjust based on real-time data, significantly improving its adaptability to different exhibition scenarios and varying visitor flow.

[0103] Furthermore, the above formula is a formula derived from software simulation using a large amount of collected data to obtain the most recent real-world situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0104] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0105] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0106] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0107] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0108] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for analyzing and evaluating the design effect of exhibition layout, characterized in that, The method includes: Real-time collection of visitor movement trajectories, exhibit information, and spatial structure data within the exhibition space; construction of a dynamic spatial topology network including basic topology nodes, dynamic virtual nodes, and topology edges. The edge weights and the correlation between each exhibition area are determined by analyzing the dynamic spatial topology network through spatiotemporal feature fusion. By integrating edge weights and audience trajectory sequences, a spatial efficiency index is generated using the analytic hierarchy process (AHP). Furthermore, by combining the aforementioned correlation degree and the visitor movement trajectory, a circulation rationality index is generated through multidimensional analysis. A layout rationality index is generated based on the weighted fusion of the space efficiency index and the circulation rationality index. When the index is lower than a preset threshold, the display layout is optimized.

2. The method for analyzing and evaluating the design effect of exhibition layout according to claim 1, characterized in that: The three-dimensional structural data includes spatial dimensions, passage width, obstacle distribution location and obstacle geometric parameters, as well as the exhibition theme of each exhibition area and its actual coordinate position in the exhibition space, which is obtained by combining laser scanning and BIM modeling. The exhibit information consists of the center coordinates of each exhibit, which are obtained in real time by embedding RFID tags in the exhibit base and using a distributed reader. The audience movement trajectory is a sequence of audience position coordinates, which is collected by fusing UWB positioning tags with a visual tracking system.

3. The method for analyzing and evaluating the design effect of exhibition layout according to claim 1, characterized in that: The specific construction process of the dynamic spatial topology network includes: The exhibition space is divided into regular grid units with a preset precision, and each grid unit is given a unique identifier to indicate whether it is a passable area. The coordinates of the exhibit locations, entrances and exits, and functional area boundaries generated by a 3D spatial segmentation algorithm within the exhibition space are used as fixed nodes. Based on the exhibit information, the center coordinates of each exhibit are mapped to its nearest accessible grid to generate exhibit nodes, and then the IDs of the exhibit nodes are labeled. A basic set of topological nodes is constructed based on fixed nodes and exhibit nodes. The audience trajectory data is preprocessed to remove noise, and the preprocessed audience trajectory data is statistically analyzed to obtain the dwell time of each audience member in each grid cell; When a viewer stays in a grid cell for a longer period than a preset threshold, and the change in the coordinates of adjacent timestamps is less than the corresponding preset position coordinate change threshold, it is determined to be a valid staying area. The centroid coordinates of the staying area are generated and used as the coordinates of the staying point. Map individual visitor stops to the nearest basic topology node or grid cell, and aggregate similar stops according to a preset time window to generate a dynamic virtual node set; Based on the passable regions in the grid space, the node connection relationship is defined by the graph theory adjacency matrix method. The topological edges are generated based on the node connection relationship and the unreachable topological edges are removed to obtain the effective topological edges. A dynamic spatial topological relationship network is generated by combining the basic topological node set, effective topological edges, and dynamic virtual node set.

4. The method for analyzing and evaluating the design effect of exhibition layout according to claim 3, characterized in that: The specific process for determining unreachable topological edges includes: Calculate the Euclidean distance between any two adjacent basic topology nodes, any dynamic virtual node, and any basic topology node and its adjacent dynamic virtual nodes. If the Euclidean distance between two nodes is less than a set threshold, these two nodes will be paired as a pre-selected node pair. For each pre-selected node pair, a ray is emitted along the line connecting the two points. The AABB tree is used to quickly detect whether the ray intersects with the triangular mesh face of the obstacle. If the ray intersects with any obstacle or the ray is not an obstacle, it is determined to be an unreachable path and recorded as an unreachable topological edge. The crowd density in each grid cell is obtained by statistically analyzing the preprocessed audience trajectory data. When the crowd density in a grid cell is greater than a set density threshold, all connecting edges of the grid cell are treated as unreachable topological edges.

5. The method for analyzing and evaluating the design effect of exhibition layout according to claim 1, characterized in that: Determining edge weights includes setting basic edge weights and dynamic edge weights. The basic edge is the connection edge corresponding to adjacent basic topology nodes, and the dynamic edge is the connection edge between a dynamic virtual node and an adjacent basic topology node. The basic edge weights are obtained by normalizing the inverse of the distance between corresponding unobstructed nodes in the basic topology.

6. The method for analyzing and evaluating the design effect of exhibition layout according to claim 5, characterized in that: The specific process for setting the dynamic edge weights is as follows: A sequence of audience movement trajectories is generated based on real-time collected audience movement trajectories, and the average crowd density of the exhibition area where the dynamic virtual nodes are located is extracted. The crowd density is the ratio of the number of audience members staying to the area of ​​the exhibition area. For each visitor entering the exhibition area where the dynamic virtual node is located, their entry time and exit time are recorded and the difference is calculated to obtain the individual stay time, and then the average stay time is calculated. The rate of change of crowd density is calculated according to a preset time window. The average rate of change of crowd density is obtained by calculating the average value within the window. The standard deviation of the dwell time of different audiences is calculated to obtain the dwell time fluctuation rate. If the rate of change in average pedestrian density or the rate of fluctuation in dwell time is greater than or equal to the corresponding threshold, a weighting compensation factor is set. The basic weights are obtained by normalizing the average pedestrian density and average dwell time and then calculating them using linear weighting. The final weight is obtained by correcting the basic weight based on the weight compensation factor, and is used as the edge weight of the exhibition area where the corresponding virtual node is located.

7. The method for analyzing and evaluating the design effect of exhibition layout according to claim 6, characterized in that: The specific process for setting the weight compensation factor includes: If the rate of change of average pedestrian density is greater than or equal to the corresponding set threshold, the rate of change of average pedestrian density and the corresponding set threshold are used as variables, denoted as follows: and ,Will As a weighting compensation factor, denoted as , It is a natural constant; If the volatility of the duration of stay exceeds the corresponding set threshold, the volatility of the duration of stay and the corresponding set threshold will be used as variables, and then... The settings are configured similarly, and denoted as follows: ; If both are greater than the set threshold, for and The final weighted compensation factor is obtained by performing a weighted summation calculation, denoted as... ,and The maximum value is 1.

8. The method for analyzing and evaluating the design effect of exhibition layout according to claim 1, characterized in that: The specific analysis process of the correlation between the various exhibition areas includes: After textualizing the exhibition themes of each exhibition area, the similarity between the themes of different exhibition areas is obtained, and a theme similarity matrix is ​​generated. ; The exhibits were categorized and coded, and the degree of overlap between exhibit types in different exhibition areas was statistically analyzed to construct an exhibit type association matrix. ; Based on the audience movement trajectories, the number of audience transfers from each starting exhibition area to other target exhibition areas within a preset time window is counted, and a transfer frequency matrix is ​​constructed. The average dwell time of visitors in each exhibition area was calculated, and then a dwell time correlation matrix was generated using the Pearson correlation coefficient. ; Based on the actual coordinates of the exhibition areas within the exhibition space, the shortest travel distance between the exhibition areas is calculated, and a distance matrix is ​​constructed. ; right , , , and After normalizing the elements, a weighted sum is calculated according to the set weights to obtain the comprehensive correlation matrix between the exhibition areas. The formula for calculating the correlation matrix is ​​as follows: , Indicates exhibition area and exhibition area The degree of correlation between them ~ These represent the weights corresponding to the topic similarity matrix, exhibit type association matrix, dwell time association matrix, and distance matrix, respectively. , , , and Each represents an exhibition area and exhibition area The similarity between themes, the degree of overlap in exhibit types, the number of visitor transfers, the correlation of average dwell time, and the shortest passage distance.

9. The method for analyzing and evaluating the design effect of exhibition layout according to claim 1, characterized in that: The specific analysis process of the spatial efficiency index includes: The audience movement trajectory is transformed into an ordered sequence of location points, each location point containing a timestamp and location coordinates. The trajectory density, maximum continuous dwell time and transfer probability of each exhibition area are statistically analyzed. The spatial efficiency index is the target layer, edge weight, trajectory density, dwell time and transition probability are the criteria layer, and each exhibition area is the scheme layer. Construct the judgment matrix of the criterion layer to the target layer and the judgment matrix of the scheme layer to each criterion respectively, and determine the weight allocation after passing the consistency test; Based on the weights of edge weights, trajectory density, dwell time, and transition probability, partial spatial efficiency indices of each exhibition area under each criterion layer are calculated, and a comprehensive spatial efficiency index is obtained by weighted summation.

10. The method for analyzing and evaluating the design effect of exhibition layout according to claim 1, characterized in that: The specific analysis process of the circulation rationality index includes: Based on the visitor movement trajectory, high-frequency paths, hot spots, turning points and congestion points are identified, and then the visitor flow route is determined; For the exhibition visitor flow, the correlation between adjacent exhibition areas is extracted and summed, and then normalized to generate a correlation sub-index; Based on the exhibition trajectory data, the deviation between the dwell time in each exhibition area and the preset suggested dwell time is calculated and recorded as the dwell time deviation. The number of backtracking paths and the proportion of exhibition areas with a coverage correlation greater than a set threshold are also counted and recorded as the coverage of highly correlated exhibition areas. A comprehensive trajectory sub-index is generated by combining the deviation in dwell time, the number of backtracking paths, and the proportion of coverage of highly relevant exhibition areas; The correlation sub-index and the trajectory comprehensive sub-index are weighted and fused to obtain the movement line rationality index.

Images