An exhibition design method and system based on deep learning

Abstract

The application relates to the technical field of computer-aided design, and discloses a fair design method and system based on deep learning, which comprises the following steps: collecting multi-dimensional data of a fair environment, analyzing the staying time and visiting sequence in a historical behavior track of a visitor, constructing an exhibition item interest correlation network based on the staying time and visiting sequence, analyzing high-frequency co-occurrence exhibition item combinations in the exhibition item interest correlation network, generating exhibition item layout guide rules according to the co-occurrence strength, determining an exhibition item space distribution scheme based on the guide rules, planning a visiting guide path in the exhibition item space distribution scheme, detecting path decision conflict points by simulating the flow of visitors, adjusting the relative positions of the exhibition items to form an optimized exhibition space relationship, and checking the safety and standard compliance of the optimized exhibition space relationship to identify areas that do not meet the safety distance. The application can realize the organic unification of display effect, visiting experience and safety standards, and significantly enhance the adaptability and landing effect of fair design.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer-aided design, and in particular to an exhibition design method and system based on deep learning. BACKGROUND

[0002] Exhibition design is to fully display the value of the exhibition, help exhibitors to convey brand image and core information, improve the efficiency of visitors to obtain effective content, promote the interaction between exhibitors and visitors, and ensure the orderly flow of people on the exhibition site, meet the safety specifications and management requirements of the site use, and help the exhibition to achieve the core goal of communication and business conversion.

[0003] The existing exhibition design has core technical bottlenecks in the coordination and optimization of exhibition layout, path planning and safety compliance. The root cause lies in the insufficient in-depth mining of the behavior characteristics of individual and group visitors, the inability to effectively integrate the associated information in the historical access trajectory, the difficulty in accurately identifying the potential relationship between the exhibitions, and the static space division-based path planning, which fails to fully simulate the dynamic changes of people flow, and the fixed standard-based safety distance setting, which lacks dynamic adaptation to the distribution density of the exhibition and the demand of people flow, resulting in the difficulty in balancing the display effect, the visiting efficiency and the safety guarantee of the design scheme. SUMMARY

[0004] The present application provides an exhibition design method and system based on deep learning to solve the problems raised in the background.

[0005] To achieve the above purpose, the present application provides an exhibition design method based on deep learning, comprising:

[0006] S1, collecting multi-dimensional data of the exhibition environment, analyzing the stay time and access order of the historical behavior trajectory of the visitors, and constructing an exhibition interest association network based on the stay time and access order;

[0007] S2, analyzing the high-frequency co-occurrence exhibition combination in the exhibition interest association network, generating an exhibition layout guide rule according to the co-occurrence strength, and determining an exhibition space distribution scheme based on the guide rule;

[0008] S3, planning a visit guide path in the exhibition space distribution scheme, detecting path decision conflict points by simulating the flow of visitors, adjusting the relative position of the exhibition to form an optimized exhibition space relationship;

[0009] S4, checking the safety specification compliance of the optimized exhibition space relationship, identifying the area that does not meet the safety distance, and adjusting the distance parameter between the exhibitions to form a safety space configuration;

[0010] S5, integrating the exhibition item space distribution scheme, optimizing the exhibition space relationship and safe space configuration, generating the final exhibition design scheme, and outputting the executable design file.

[0011] Preferably, the multi-dimensional data of the exhibition environment is collected, the stay duration and access order in the historical behavior trajectory of the visitor are analyzed, and an exhibition item interest association network is constructed based on the stay duration and access order, including:

[0012] The historical behavior trajectory data of the visitor is obtained, and the data format and coordinates are unified to obtain preprocessed trajectory data;

[0013] The stay points are identified from the preprocessed trajectory data, and the duration and spatial position of the stay points are determined;

[0014] Based on the spatial position, the stay points are mapped to the corresponding exhibition items, the exhibition item access sequence is generated and the duration is associated to form interest basic data;

[0015] Taking the exhibition items as nodes, the edges between the nodes are constructed based on the access sequence co-occurrence relationship in the interest basic data, and the duration is taken as the weight of the edge to generate the exhibition item interest association network.

[0016] Preferably, the high-frequency co-occurrence exhibition item combination in the exhibition item interest association network is analyzed, including:

[0017] The exhibition item interest association network is accessed, and the connection relationship in the network is dynamically sliced based on the time window to distinguish the co-occurrence relationship in different time periods;

[0018] The co-occurrence relationships in different time periods are fused, and transient noise connections are removed to extract a stable core co-occurrence relationship set;

[0019] The core co-occurrence relationship set is verified for spatial proximity, and the core co-occurrence relationship that passes the verification is confirmed as a high-frequency co-occurrence exhibition item combination.

[0020] Preferably, the exhibition layout guide rules are generated according to the co-occurrence strength, and the exhibition space distribution scheme is determined based on the guide rules, including:

[0021] The co-occurrence strength of the high-frequency co-occurrence exhibition item combination is quantified as the association gravitational value between the exhibition items, and the association gravitational value is corrected based on the visitor flow resistance;

[0022] According to the corrected association gravitational value, the exhibition layout guide rules are constructed to maximize the overall association gravitational force;

[0023] The exhibition layout guide rules are applied to generate multiple candidate space distribution schemes through iterative permutation;

[0024] A conflict detection and resolution mechanism is introduced to screen the candidate space distribution schemes to obtain the exhibition space distribution scheme.

[0025] Preferably, the planning of the visiting guide path in the exhibition space distribution scheme, the path decision conflict point is detected by simulating the visitor flow, including:

[0026] Extracting the continuity exhibition visit pairs in the historical visit sequence, mapping the visit pairs to the space guide segments in the exhibition space distribution scheme;

[0027] Superimposing the space guide segments, grading the density of the superimposed area, and marking the high-density superimposed area;

[0028] In the high-density superimposed area, identifying the intersection nodes with different guide directions, and defining the intersection nodes as path decision conflict points.

[0029] Preferably, the adjusting of the relative positions of the exhibitions forms an optimized exhibition space relationship, including:

[0030] Tracing from the path decision conflict point to the guide segments constituting the point, and mapping the guide segments back to their corresponding original exhibition pairs;

[0031] Adjusting the relative distance between the two exhibitions in the original exhibition pair, and synchronously introducing a third exhibition with correlation to construct an exhibition triangular topological relationship;

[0032] Based on the exhibition triangular topological relationship, the guide path through the area is regenerated, and the regenerated guide path is superimposed and compared with the path decision conflict point;

[0033] Iteratively performing distance adjustment and relationship reconstruction operations to obtain an optimized exhibition space relationship.

[0034] Preferably, the safety specification compliance check of the optimized exhibition space relationship identifies areas that do not meet the safety distance, including:

[0035] Decomposing the safety specification articles, converting the qualitative description and quantitative provisions therein into constraint conditions that can be mapped to spatial attributes;

[0036] Fusing the constraint conditions with the exhibition space attributes in the optimized exhibition space relationship to generate a dynamic compliance threshold field for each exhibition boundary;

[0037] Scanning the dynamic compliance threshold field to identify discrete conflict points that do not meet the preset safety level, and clustering the discrete conflict points into a conflict area atlas that does not meet the safety distance based on spatial proximity.

[0038] Preferably, the adjusting of the exhibition distance parameters forms a safety space configuration, including:

[0039] Analyzing the conflict area atlas to establish a resolution priority sequence according to the spatial correlation and severity of the conflict;

[0040] Based on the resolution priority sequence, the topology of the exhibit clusters that caused the core conflict is restructured to generate a set of candidate security space configurations;

[0041] The candidate safe space configuration set is back-mapped to the conflict area map for verification. The optimal configuration that can completely eliminate all conflict nodes in the map is selected to form the final safe space configuration.

[0042] Preferably, the integration of exhibition space distribution scheme, optimization of booth space relationships and safety space configuration, to generate the final exhibition design scheme and output an executable design file includes:

[0043] The spatial layout of the integrated exhibition space distribution scheme, the topological connection of the optimized booth space relationship, and the spacing parameters of the safety space configuration are used to form a unified data fusion structure;

[0044] Verify the coordination of various elements in the data fusion structure and identify potential contradictions between the arrangement, connection and parameters;

[0045] Potential contradictions are resolved by applying the triangular topological relationship of exhibits and the resolution priority sequence, and the final exhibition design scheme is generated.

[0046] The final exhibition design scheme is converted into a format that the exhibition system can recognize, and then assembled into an executable design file.

[0047] To address the aforementioned problems, this invention also provides a deep learning-based exhibition design system, the system comprising:

[0048] The network construction module is used to collect multi-dimensional data of the exhibition environment, analyze the dwell time and access order in the historical behavior trajectory of visitors, and construct an interest association network of exhibits based on the dwell time and access order.

[0049] The exhibit distribution determination module is used to analyze high-frequency co-occurring exhibit combinations in the exhibit interest association network, generate exhibit layout guidance rules based on co-occurrence intensity, and determine exhibit spatial distribution schemes based on the guidance rules.

[0050] The booth space optimization module is used to plan visitor guidance paths in the exhibition space distribution scheme. By simulating visitor flow, it detects path decision conflict points and adjusts the relative positions of exhibition items to form an optimized booth space relationship.

[0051] The space configuration adjustment module is used to check the safety compliance of optimized booth space relationships, identify areas that do not meet the safety spacing, and adjust the booth spacing parameters to form a safe space configuration.

[0052] The design file output module is used to integrate the exhibition space distribution plan, optimize the booth space relationship and safety space configuration, generate the final exhibition design plan, and output an executable design file.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] 1. This exhibition design methodology constructs the logical association of exhibits by deeply mining visitor behavior data, and systematically integrates the design elements of exhibit layout, path planning and safety configuration throughout the entire process. This enables the exhibition design scheme to closely match the actual behavioral characteristics and interests of visitors, improve the scientific nature and integrity of the design scheme, achieve the organic unity of display effect, visitor experience and safety standards, and significantly enhance the adaptability and implementation effectiveness of the exhibition design.

[0055] 2. Further enhance the accuracy of data processing and the targeted nature of design optimization. By dynamically analyzing the relationships between exhibits, refining the handling of path conflicts, and intelligently adapting to security constraints, we can effectively improve the rationality of exhibit layout, the smoothness of path planning, and the adaptability of security configuration. This will make the design scheme more detailed and the logic more rigorous, further strengthening the feasibility and practical application value of the overall design scheme, and ensuring the efficiency of the entire process from planning to implementation of the exhibition design. Attached Figure Description

[0056] Figure 1 A flowchart illustrating a deep learning-based exhibition design method according to an embodiment of the present invention;

[0057] Figure 2 A functional block diagram of a deep learning-based exhibition design system provided in an embodiment of the present invention;

[0058] 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

[0059] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0060] This application provides a deep learning-based exhibition design method. The execution entity of this deep learning-based exhibition design 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, a deep learning-based exhibition design 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 cloud server cluster. The server can be a standalone 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.

[0061] Example 1, referring to Figure 1 The diagram shown is a flowchart illustrating a deep learning-based exhibition design method according to an embodiment of the present invention. In this embodiment, the deep learning-based exhibition design method includes:

[0062] S1. Collect multi-dimensional data of the exhibition environment, analyze the dwell time and access order in the historical behavior trajectory of visitors, and construct an interest association network of exhibits based on dwell time and access order;

[0063] S2. Analyze the high-frequency co-occurring exhibit combinations in the exhibit interest association network, generate exhibit layout guidance rules based on co-occurrence intensity, and determine the exhibit spatial distribution scheme based on the guidance rules;

[0064] S3. Plan visitor guidance paths in the exhibition space distribution scheme, detect path decision conflict points by simulating visitor flow, and adjust the relative positions of exhibits to form an optimized exhibition space relationship.

[0065] S4. Conduct a safety compliance check on the optimized booth space relationship, identify areas that do not meet the safety spacing requirements, and adjust the booth spacing parameters to form a safe space configuration;

[0066] S5. Integrate the exhibition space distribution plan, optimize the booth space relationship and safety space configuration, generate the final exhibition design plan, and output executable design files.

[0067] In a preferred embodiment, multidimensional data of the exhibition environment is collected, and the dwell time and access order in the historical behavior trajectory of visitors are analyzed. Based on the dwell time and access order, an interest association network for exhibits is constructed, including:

[0068] Acquire visitor historical behavior trajectory data, and standardize the data format and coordinates to obtain preprocessed trajectory data;

[0069] Identify stop points from preprocessed trajectory data and determine their duration and spatial location;

[0070] Based on spatial location, the dwell points are mapped to the corresponding exhibits, generating exhibit visit sequences and associating them with durations to form basic interest data;

[0071] Using exhibits as nodes, edges are constructed between nodes based on the co-occurrence relationship of access sequences in the basic interest data, and the duration is used as the weight of the edges to generate an exhibit interest association network.

[0072] Specifically, visitor historical behavior trajectory data is obtained, such as raw data exported from the Bluetooth positioning system deployed at the exhibition, including unique visitor identifiers and Bluetooth signal coordinates at various time points. The time format of all data is unified to YYYY-MM-DDHH:MM:SS, and the coordinates are uniformly converted to Cartesian coordinates within the exhibition with the main entrance as the origin, east-west as the horizontal axis, and north-south as the vertical axis. The coordinate conversion is completed by manually checking the exhibition floor plan, and finally, the data is organized into a structured table containing visitor IDs, unified time, and unified coordinates to obtain preprocessed trajectory data.

[0073] The trajectory points of each visitor in the preprocessed trajectory data are sorted in chronological order. The spatial distance between adjacent trajectory points is calculated. When the spatial distance between consecutive trajectory points is less than the minimum radius of the exhibition booth and more than 5 consecutive time points occur, these trajectory points are designated as dwell points. The duration is determined by the difference between the earliest and latest time of the dwell point. The spatial location is determined by the arithmetic mean of all coordinates of the dwell point.

[0074] Fixed spatial coordinate ranges are marked for each exhibit on the exhibition floor plan in advance. The spatial location of the stop point is compared with the coordinate range of each exhibit one by one. If the coordinates of the stop point fall within the coordinate range of an exhibit, the stop point is mapped to the corresponding exhibit. The exhibits mapped by each visitor are arranged in chronological order to form an exhibit visit sequence. At the same time, the duration of each stop point is filled into the corresponding position of the exhibit in the sequence. The sequence and time data of all visitors are integrated to generate basic interest data.

[0075] Treat each exhibit as an independent node, traverse all exhibit access sequences in the basic interest data, and determine that there is a co-occurrence relationship between two exhibits if they appear sequentially in the same access sequence. Establish an edge between the corresponding nodes, calculate the total duration of all dwell points under the same co-occurrence relationship, and assign the total duration as the weight of the edge. Finally, an exhibit interest association network is formed with exhibits as nodes, co-occurrence relationships as edges, and the total duration as weight.

[0076] In summary, by collecting multi-dimensional data of the exhibition environment and standardizing the format and coordinates, the standardization and comparability of trajectory data are ensured. Precise identification of dwell points and determination of duration and spatial location from preprocessed trajectory data accurately reflects visitors' attention to different exhibits. Mapping dwell points to corresponding exhibits generates exhibit visit sequences with associated durations, providing a solid foundation of interest-based data for uncovering potential connections between exhibits. An exhibit interest association network is constructed using exhibits as nodes, co-occurrence relationships of visit sequences as edges, and duration as weights, clearly presenting the strength and logic of associations between exhibits. This allows exhibition design to closely align with visitors' actual behavioral characteristics and interests, moving away from reliance on subjective experience. It provides a scientific basis for generating subsequent exhibit layout guidance rules, helping to improve the rationality and relevance of exhibit layout, and laying a data and logical foundation for the collaborative optimization of the overall exhibition design.

[0077] In a preferred embodiment, analyzing high-frequency co-occurring exhibit combinations in the exhibit interest association network includes:

[0078] Access the exhibit interest association network and dynamically slice the connection relationships in the network based on time windows to distinguish co-occurrence relationships in different time periods;

[0079] By integrating co-occurrence relationships from different time periods and removing transient noise connections, a stable set of core co-occurrence relationships can be extracted.

[0080] Spatial proximity verification was performed on the core co-occurrence relation set, and the core co-occurrence relations that passed the verification were confirmed as high-frequency co-occurrence exhibit combinations.

[0081] Specifically, the network of interest associations for exhibits is accessed. For example, the exhibition time is divided into two fixed time windows each day: 9:00 AM to 12:00 PM and 1:00 PM to 5:00 PM. For each time window, the connection relationships and corresponding weights between all exhibit nodes in the network during that time period are extracted. The co-occurrence relationship slices for the morning and afternoon periods are sorted out respectively, and dynamic slicing based on time windows is completed to distinguish the co-occurrence relationships in different time periods.

[0082] The co-occurrence relationship slices of the morning and afternoon sessions are merged, and the number of times each exhibit connection appears in the two slices is counted. Only the connections that appear in both slices are retained, and the connections that appear only in a single slice are removed as transient noise connections. Finally, a stable core co-occurrence relationship set is obtained.

[0083] The center coordinates of all exhibits on the exhibition floor plan are collected in advance. For each group of exhibits in the core co-occurrence relationship set, the straight-line distance between their center booths is measured. If the distance is less than the maximum spacing between adjacent booths set in the exhibition plan, the spatial proximity verification is deemed to have passed. Such core co-occurrence relationships that have passed verification are confirmed as high-frequency co-occurrence exhibit combinations.

[0084] In this embodiment, exhibit layout guidance rules are generated based on co-occurrence intensity, and exhibit spatial distribution schemes are determined based on the guidance rules, including:

[0085] The co-occurrence intensity of high-frequency co-occurrence exhibit combinations is quantified as the correlation attraction value between exhibits, and the correlation attraction value is corrected based on visitor flow resistance.

[0086] Based on the corrected correlation gravity value, construct the exhibit layout guidance rules with the goal of maximizing the overall correlation gravity;

[0087] The application of exhibit layout guidance rules generates multiple candidate spatial distribution schemes through iterative replacement.

[0088] A conflict detection and resolution mechanism is introduced to screen candidate spatial distribution schemes, resulting in a spatial distribution scheme for exhibits.

[0089] Specifically, the sum of the edge weights of high-frequency co-occurring exhibit combinations is used as the quantitative basis for co-occurrence strength and directly assigned as the correlation attraction value between exhibits. The average daily traffic flow and width of the passage between exhibits are statistically analyzed. When the passage width is less than the standard width of the exhibition or the average daily traffic flow exceeds the threshold, the correlation attraction value between the corresponding exhibits is reduced proportionally to complete the correction based on visitor flow resistance.

[0090] With the goal of maximizing overall correlation attraction, it is determined that high-frequency co-occurring exhibit combinations should be arranged in adjacent booth areas or straight-line connecting areas of passageways. The top three combinations with the highest correlation attraction values ​​should be prioritized for placement along the main entrance to the main passageway. Based on this, exhibit layout guidance rules are constructed.

[0091] First, initial booths are randomly assigned according to the type of exhibit to form an initial layout. Each time, the booths of two non-high-frequency co-occurring exhibits are selected for replacement. The overall correlation gravity value after replacement is calculated and recorded. The replacement operation is repeated fifty times to generate fifty candidate spatial distribution schemes.

[0092] For each candidate scheme, check whether the projected area of ​​the exhibits and booths overlaps and whether the width of the passage between exhibits meets the minimum value stipulated by the exhibition. If there is overlap or insufficient width, adjust the position of the corresponding exhibits until the conflict is eliminated. The scheme with no conflict and the highest overall correlation gravity value is retained as the exhibit space distribution scheme.

[0093] In a preferred embodiment, the correction of the associated gravitational value based on visitor flow resistance is achieved using the following formula:

[0094]

[0095] in, Indicate exhibits and The corrected correlation gravity value between them Indicate exhibits and The original gravitational correlation between them Indicates the drag attenuation coefficient. Indicate exhibits and Standardized spatial distance between them Indicate exhibits and The path complexity factor considers factors such as the number of turns and changes in path width. Represents the natural constant.

[0096] It should be noted that the original correlation gravity value is taken from the sum of the edge weights of the high-frequency co-occurring exhibit combinations in the exhibit interest correlation network. The resistance attenuation coefficient is determined by statistically analyzing the correspondence between visitor flow trajectory data of similar past exhibitions and the correlation gravity correction effect. The standardized spatial distance is obtained by measuring the actual straight-line distance between the booth centers of two exhibits in the exhibit spatial distribution scheme, and then dividing this distance by the maximum booth spacing between all exhibits in the exhibition to obtain a value within a uniform range. The path complexity factor is obtained by statistically analyzing the number of turns in the passage between two exhibits, measuring the passage width segment by segment and recording the number of width changes, and adding the number of turns to the number of width changes to obtain the specific value.

[0097] The core of this formula is to adjust the original association attraction value by combining the flow resistance of visitors. The flow resistance is composed of standardized spatial distance and path complexity factor. The final output is a corrected association attraction value that can truly reflect the actual association strength between exhibits.

[0098] As the standardized spatial distance increases or the path complexity factor rises, the resistance to visitor flow increases accordingly. The corrected correlation gravity value will show a gradual downward trend. The larger the resistance attenuation coefficient, the faster this downward trend will be, and vice versa.

[0099] Overall, the formula reflects the physical law that the strength of visitors' interest associations decreases exponentially with the increase of spatial distance and path complexity when they move through the actual space. With this correction, the exhibit layout guidance rules can better fit the real visitor experience, thereby generating a more reasonable exhibit space distribution scheme.

[0100] In summary, accessing the exhibit interest association network and dynamically slicing the connection relationships based on time windows can avoid misjudgments of co-occurrence relationships caused by differences in visitor behavior at different times. By integrating co-occurrence relationships from different time periods and eliminating transient noise connections, it can filter out accidental associations and retain a stable core co-occurrence relationship set. Spatial proximity verification of the core co-occurrence relationship set ensures that the confirmed high-frequency co-occurrence exhibit combinations have the basic conditions for actual spatial layout, making subsequent design more in line with the actual site. The co-occurrence intensity of high-frequency co-occurrence exhibit combinations is quantified into association attraction values ​​and corrected by visitor flow resistance, making the association intensity more consistent with the flow patterns in real visitor scenarios. Based on the corrected association attraction values, layout guidance rules are constructed with the goal of maximizing overall association attraction, allowing exhibit layout to closely revolve around visitor interest associations. Iterative replacement generates multiple candidate spatial distribution schemes, increasing the possibility of scheme optimization. Introducing conflict detection and resolution mechanisms to screen schemes can eliminate problems such as exhibit overlap and insufficient passage width. The final determined exhibit spatial distribution scheme has both interest adaptability and practicality, effectively improving the scientific rationality of the exhibition layout and the adaptability of the visitor experience.

[0101] In a preferred embodiment, visitor guidance paths are planned within the exhibition space distribution scheme, and conflict points in path decision-making are detected by simulating visitor flow, including:

[0102] Extract consecutive exhibit access pairs from the historical access sequence and map the access pairs as spatial guide segments in the exhibit spatial distribution scheme;

[0103] The superimposed spatial guide segment classifies the density of the superimposed area and marks the high-density superimposed area;

[0104] In high-density overlay regions, intersecting nodes with different guiding directions are identified and defined as path decision conflict points.

[0105] Specifically, from the exhibit visit sequences in the basic interest data, two adjacent exhibits in each sequence are extracted as continuous exhibit visit pairs. On the exhibition floor plan corresponding to the exhibit spatial distribution scheme, the center positions of each pair of exhibits are connected by straight lines to form the spatial guidance segment of the corresponding visit pair.

[0106] All continuous exhibit access pairs and their corresponding spatial guide segments are plotted one by one on the exhibit spatial distribution plan. The number of times each 1m×1m grid area on the plan is covered by the spatial guide segment is counted. The coverage number is divided into three levels: low, medium and high. The grid area with the highest coverage number is marked as a high-density overlay area.

[0107] Within a high-density overlapping area, select the center of the booth or the intersection of the passage as a node, and check the direction of the spatial guide segment connected to each node. If the spatial guide segment connected to the same node has three or more different extension directions, then the node is determined to be a meeting node with different guide directions, and such meeting nodes are defined as path decision conflict points.

[0108] In this embodiment, adjusting the relative positions of exhibits to optimize booth space relationships includes:

[0109] Tracing the path decision conflict point back to the guiding segment that constitutes that point, and mapping the guiding segment back to its corresponding original item pair;

[0110] Adjust the relative distance between the two exhibits in the original exhibit pair, and simultaneously introduce a related third exhibit to construct an exhibit triangle topology;

[0111] Based on the triangular topological relationship of the exhibits, a new guide path is generated through the area, and the regenerated guide path is superimposed and compared with the path decision conflict point;

[0112] Iteratively perform distance adjustment and relationship reconstruction operations to obtain optimized booth space relationships.

[0113] Specifically, starting from the path decision conflict point, all spatial guide segments connected to that point are marked, and the continuous exhibit access pairs corresponding to each spatial guide segment are checked one by one. These access pairs are then directly mapped to the original exhibit pairs that constitute the conflict point.

[0114] Measure the current distance between the center of the booths of the two original exhibits, shorten this distance to 1.5 times the minimum distance between adjacent booths specified by the exhibition, select a third exhibit from the high-frequency co-occurrence exhibit combination that has a co-occurrence relationship with both of the two exhibits, and place the booth of the third exhibit at the midpoint of the line connecting the center of the two exhibits' booths, forming an exhibit triangular topology relationship consisting of three exhibits.

[0115] Using the center of the booth of the three exhibits in the triangular topology of the exhibits as a node, connect the adjacent nodes in sequence to form a new spatial guidance segment. Integrate these guidance segments to generate a new guidance path through the area. Draw the new guidance path on the spatial distribution plan of the exhibits and overlay it with the position of the original path decision conflict point to check whether the new guidance path passes through the conflict point.

[0116] If the new guiding path still passes through the decision conflict point of the original path, the spacing of the original exhibit pair is adjusted again or the third exhibit is replaced to reconstruct the triangular topology relationship of the exhibits. The operations of distance adjustment, relationship reconstruction and path generation comparison are repeated until the new guiding path completely avoids the decision conflict point of the original path. The relative position of the exhibits determined at this time is the optimized booth space relationship.

[0117] In summary, by extracting continuous exhibit visit pairs from historical visit sequences and mapping them to spatial guidance segments in the exhibit spatial distribution scheme, the visitor guidance path planning aligns with visitors' actual visiting habits. By overlaying spatial guidance segments and classifying the density of the overlay areas, high-density areas where crowds tend to concentrate can be accurately located. In high-density overlay areas, intersections with disparate guidance directions are identified and defined as path decision conflict points, allowing for the early detection of potential path congestion and decision-making confusion. Tracing the path decision conflict point back to the guidance segment that constitutes that point and mapping it back to the original exhibit pair allows for the precise identification of the exhibits causing the path conflict. Adjusting the relative distance of the original exhibit pairs and simultaneously introducing a related third exhibit to construct an exhibit triangular topological relationship optimizes the spatial association logic between exhibits. Based on the exhibit triangular topological relationship, a new guidance path is generated and compared with the conflict point. Combined with iterative execution of distance adjustment and relationship reconstruction operations, path conflicts can be completely eliminated. The resulting optimized booth spatial relationship makes the visitor path smoother, effectively improving visitor efficiency and avoiding on-site crowd congestion.

[0118] In a preferred embodiment, a safety compliance check is performed on the optimized booth space relationship to identify areas that do not meet safety spacing requirements, including:

[0119] Deconstruct safety regulations and transform their qualitative descriptions and quantitative provisions into constraints that can be mapped to spatial attributes;

[0120] By integrating constraints with the spatial attributes of exhibits in optimizing booth spatial relationships, a dynamic compliance threshold field is generated for the boundary of each exhibit.

[0121] Scan the dynamic compliance threshold field, identify discrete conflict points whose field strength does not meet the preset safety level, and cluster the discrete conflict points into a conflict area map that does not meet the safety distance based on spatial proximity.

[0122] Specifically, the quantitative provisions in the exhibition safety regulations, such as "the width of the main passage between exhibits shall not be less than 3 meters", "the horizontal distance between exhibits and fire hydrants shall not be less than 1.5 meters", and "exhibits made of flammable materials shall maintain a distance of more than 5 meters from exhibits containing heat sources", as well as the qualitative description that "exhibits next to evacuation routes shall not protrude and encroach on the passage space", shall be transformed into constraints that directly correspond to spatial location and attributes, such as passage width constraints, distance constraints from fire-fighting facilities, and spatial isolation constraints for exhibit types.

[0123] Extract spatial attributes such as boundary coordinates, material type, and specific location of surrounding fire protection facilities for each exhibit in the optimized booth spatial relationship. For each boundary point of each exhibit, set the minimum allowable distance from the point to the boundary of the adjacent exhibit in combination with the passage width constraint, and set the minimum allowable distance from the point to the nearest fire hydrant in combination with the fire protection facility constraint. Match and label these thresholds one by one according to the spatial location of the exhibit boundary to generate a dynamic compliance threshold field covering all exhibit boundaries.

[0124] Each exhibit boundary point in the dynamic compliance threshold field is checked against the actual spatial parameters and thresholds. If the actual distance from a boundary point to an adjacent exhibit is less than the set threshold, or the actual distance to a fire hydrant is less than the threshold, or the actual distance from the boundary point of a flammable exhibit to the boundary point of a heat source exhibit is insufficient, then the point is marked as a discrete conflict point. The spatial straight-line distance between all discrete conflict points is calculated, and discrete conflict points with a distance of less than 2 meters are grouped into the same group. Each group forms a continuous area, and the areas of all groups are integrated to draw a map of conflict areas that do not meet the safety distance.

[0125] As a preferred implementation, the dynamic compliance threshold field is defined by the following function, which is used to calculate the dynamic compliance threshold at any point in the space:

[0126]

[0127] in, Represents spatial coordinates Dynamic compliance thresholds at the location; The basic safety clearance is derived directly from the quantitative provisions in the safety regulations. For dynamic adjustment coefficients, Indicates position The attractiveness weight of the exhibits at each location Factors influencing human traffic flow Indicates position The estimated pedestrian density at the location.

[0128] It should be noted that the basic safety distance is directly extracted from the quantitatively specified values ​​in the exhibition safety regulations, such as the fixed values ​​clearly defined in the regulations, such as the "minimum safety distance between exhibits" and the "safe distance from fire-fighting facilities". The dynamic adjustment coefficient is determined by statistically analyzing the safety compliance inspection data and actual safety accident occurrences of the past five similar exhibitions to determine a fixed value that balances safety and space utilization efficiency. The exhibit attractiveness weight at a location is determined based on the sum of the edge weights of the exhibit corresponding to that spatial coordinate in the exhibit interest association network. The higher the sum of the edge weights, the larger the weight value. The visitor flow influencing factor is determined by referring to the exhibition venue capacity and the average daily number of visitors of the same period in history to determine a fixed value. The estimated visitor flow density at a location is based on the high-frequency co-occurrence combination of the exhibit in the exhibit interest association network, combined with the average dwell time and visit frequency of the exhibit in the historical visit sequence, to calculate the estimated number of people per unit area.

[0129] This function is used to calculate the dynamic compliance threshold at any coordinate point in space. Based on the basic safety distance, it combines the attraction weight of the exhibits at that location with the estimated pedestrian flow density. By dynamically adjusting the coefficients and pedestrian flow influencing factors, it obtains the safety distance requirements that are adapted to the actual situation of the specific location, thus forming a dynamic compliance threshold field.

[0130] When the attraction weight of exhibits at a location increases or the estimated foot traffic density rises, the dynamic compliance threshold of that coordinate point will increase accordingly. The larger the value of the dynamic adjustment coefficient, the more significant the effect of the exhibit attraction weight on the dynamic compliance threshold. The larger the value of the foot traffic influence factor, the more significant the effect of the estimated foot traffic density on the dynamic compliance threshold.

[0131] Overall, the innovation of the formula lies in its combination of static safety standards with dynamic exhibition operation factors such as exhibit attractiveness weights and estimated visitor density, generating an intelligent safety standard that changes with spatial location. This makes safety inspections no longer mechanical measurements, but a proactive design based on risk assessment, which can more precisely balance space utilization and visitor experience while ensuring safety.

[0132] In this embodiment, adjusting the exhibit spacing parameters to form a safe space configuration includes:

[0133] Analyze conflict area maps and establish a resolution priority sequence based on the spatial correlation and severity of conflicts;

[0134] Based on the resolution priority sequence, the topology of the exhibit clusters that caused the core conflict is restructured to generate a set of candidate security space configurations;

[0135] The candidate safe space configuration set is back-mapped to the conflict area map for verification. The optimal configuration that can completely eliminate all conflict nodes in the map is selected to form the final safe space configuration.

[0136] Specifically, the conflict zone map is analyzed to determine whether each conflict zone involves key safety nodes such as fire-fighting facilities and evacuation routes. Conflicts involving key nodes are defined as high severity. Conflicts not involving key nodes are classified according to the number of exhibits covered by the conflict zone. The more exhibits, the higher the severity. Then, the correlation between conflict zones is determined based on the spatial overlap. The larger the overlap area, the stronger the correlation. A resolution priority sequence is established in the order of "high severity + high correlation", "high severity + low correlation", "low severity + high correlation", and "low severity + low correlation".

[0137] Based on the resolution priority sequence, the core conflict exhibit cluster ranked first is processed first. The triangular topological relationship of the exhibits within the cluster remains unchanged. The entire cluster is moved away from fire-fighting facilities or evacuation routes. At the same time, the spacing between exhibits within the cluster is increased proportionally. This operation is repeated to generate five schemes with different translation distances and spacing ratios, forming a candidate safe space configuration set.

[0138] The boundary coordinates and spacing data of each candidate security space configuration set are mapped back to the conflict area map. The positions corresponding to the original discrete conflict points are checked one by one to see if they meet the requirements of the dynamic compliance threshold field. After confirming that the actual parameters of all conflict points meet the safety standards and that there are no remaining conflict nodes in the conflict area map, the candidate configuration with the smallest translation distance and the smallest adjustment range of the item spacing in the cluster is selected to form the final security space configuration.

[0139] In summary, deconstructing safety regulations transforms qualitative descriptions and quantitative provisions into constraints that can be mapped to spatial attributes. This avoids deviations in the implementation of safety requirements due to vague wording, provides clear spatial judgment criteria for safety inspections, and integrates the constraints with the spatial attributes of exhibits in optimizing booth spatial relationships to generate a dynamic compliance threshold field for each exhibit boundary. This breaks free from the rigid limitations of fixed safety standards, allowing safety requirements to adapt to the spatial characteristics of different exhibits. Scanning the dynamic compliance threshold field identifies discrete conflict points where the field strength does not meet the preset safety level, and then clusters them into a conflict area map based on spatial proximity. This can accurately and intuitively locate areas that do not meet safety distances, providing direction for subsequent adjustments. The conflict area map is analyzed to establish a resolution priority sequence based on the spatial correlation and severity of conflicts. This allows for the priority handling of core conflicts that affect the overall security of the exhibition, avoiding resource misallocation. Based on the priority, the topology of the exhibit clusters that cause core conflicts is reconstructed to generate a candidate safe space configuration set, providing multiple adjustment schemes to improve the probability of the optimal solution. The candidate configurations are then mapped back to the conflict area map for verification and selection to find the optimal configuration that can completely eliminate all conflict nodes. The resulting safe space configuration not only meets security specifications but also retains the rationality of optimizing the spatial relationship of the exhibition booths to the greatest extent, ensuring a balance between exhibition security and visitor experience.

[0140] In a preferred embodiment, the exhibition space distribution scheme is integrated, the booth space relationship and safety space configuration are optimized, and a final exhibition design scheme is generated, outputting an executable design file, including:

[0141] The spatial layout of the integrated exhibition space distribution scheme, the topological connection of the optimized booth space relationship, and the spacing parameters of the safety space configuration are used to form a unified data fusion structure;

[0142] Verify the coordination of various elements in the data fusion structure and identify potential contradictions between the arrangement, connection and parameters;

[0143] Potential contradictions are resolved by applying the triangular topological relationship of exhibits and the resolution priority sequence, and the final exhibition design scheme is generated.

[0144] The final exhibition design scheme is converted into a format that the exhibition system can recognize, and then assembled into an executable design file.

[0145] Specifically, the booth coordinates and area division information of each exhibit in the exhibition space distribution plan are extracted, the triangular topology connection objects and connection methods of exhibits in the booth space relationship are optimized, and the spacing values ​​between exhibits in the safety space configuration are integrated into a unified table. The table includes exhibit ID, booth coordinates, topology connection exhibit ID, connection method, and adjacent exhibit spacing parameters. Each exhibit corresponds to one row of data, forming a unified data fusion structure.

[0146] Check one by one whether the actual spacing calculated from the booth coordinates of the exhibits in the data fusion structure is consistent with the spacing parameters configured in the safety space. Check whether the positions of the topologically connected exhibits are within the area of ​​the exhibit spatial distribution scheme. If the adjacent spacing of an exhibit calculated by coordinates is less than the safety spacing parameter, or if the topologically connected exhibits exceed their respective areas, it is marked as a potential contradiction between the layout, connection and parameters.

[0147] For the identified potential conflicts, the booth coordinates of the conflicting exhibits are adjusted with reference to the triangular topological relationship of the exhibits to maintain the integrity of the triangular structure. At the same time, conflicts involving evacuation routes are handled first according to the resolution priority sequence, and the positions or topological connection methods of the relevant exhibits are adjusted until all potential conflicts are eliminated, and the final exhibition design scheme is generated.

[0148] The coordinates of exhibits in the final exhibition design are converted into a CAD coordinate format compatible with the exhibition system. The topological connection relationship is converted into a line layer in CAD, and the spacing parameters are labeled as text layers. At the same time, a PDF document containing an exhibit list, location description, and safety spacing requirements is generated. The CAD file and the PDF document are integrated and packaged to obtain an executable design file.

[0149] In summary, the unified data fusion structure, which integrates the spatial layout of exhibits, the topological connections of optimized booth relationships, and the spacing parameters of safety space configuration, breaks down information barriers between different design stages. This allows exhibit layout, path logic, and safety parameters to form an organic whole, avoiding design deviations caused by fragmented elements. It verifies the coordination of various elements in the data fusion structure and identifies potential contradictions between layout, connection, and parameters. It can proactively identify issues such as mismatches between exhibit locations and topological connections, and conflicts between safety spacing and spatial layout, reducing subsequent adjustment costs. By applying exhibit triangular topological relationships and resolution priority sequences to resolve potential contradictions, it can efficiently balance various design requirements while ensuring exhibit association logic and safety priority. This ensures that the final exhibition design scheme is both scientific and feasible. The final exhibition design scheme is converted into a format that the exhibition system can recognize and assembled into an executable design file, eliminating the tediousness and errors of manual format conversion. This allows the design scheme to directly connect with actual exhibition operations, significantly improving the efficiency and accuracy of exhibition implementation.

[0150] Example 2, as Figure 2 The diagram shown is a functional block diagram of a deep learning-based exhibition design system provided in an embodiment of the present invention.

[0151] This invention discloses a deep learning-based exhibition design system 100 that can be installed in an electronic device. Depending on the functions implemented, the deep learning-based exhibition design system 100 may include a network construction module 101, an exhibit distribution determination module 102, an exhibit space optimization module 103, a space configuration adjustment module 104, and a design file output module 105. The modules of 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 perform a fixed function, and are stored in the memory of the electronic device.

[0152] In this embodiment, the functions of each module / unit are as follows:

[0153] Network construction module 101 is used to collect multi-dimensional data of the exhibition environment, analyze the dwell time and access order in the historical behavior trajectory of visitors, and construct an interest association network of exhibits based on dwell time and access order;

[0154] The exhibit distribution determination module 102 is used to analyze the high-frequency co-occurring exhibit combinations in the exhibit interest association network, generate exhibit layout guidance rules based on the co-occurrence intensity, and determine the exhibit spatial distribution scheme based on the guidance rules.

[0155] The booth space optimization module 103 is used to plan visitor guidance paths in the exhibition space distribution scheme. By simulating visitor flow, it detects path decision conflict points and adjusts the relative positions of exhibition items to form an optimized booth space relationship.

[0156] The space configuration adjustment module 104 is used to check the safety compliance of the optimized booth space relationship, identify areas that do not meet the safety spacing, and adjust the exhibition item spacing parameters to form a safe space configuration.

[0157] The design document output module 105 is used to integrate the exhibition space distribution scheme, optimize the booth space relationship and safety space configuration, generate the final exhibition design scheme, and output an executable design document.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] The embodiments of this application 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.

[0163] 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 deep learning-based exhibition design method, characterized in that, The method includes: S1. Collect multi-dimensional data of the exhibition environment, analyze the dwell time and access order in the historical behavior trajectory of visitors, and construct an interest association network of exhibits based on dwell time and access order; S2. Analyze the high-frequency co-occurring exhibit combinations in the exhibit interest association network, generate exhibit layout guidance rules based on co-occurrence intensity, and determine the exhibit spatial distribution scheme based on the guidance rules; S3. Plan visitor guidance paths in the exhibition space distribution scheme, detect path decision conflict points by simulating visitor flow, and adjust the relative positions of exhibits to form an optimized exhibition space relationship. S4. Conduct a safety compliance check on the optimized booth space relationship, identify areas that do not meet the safety spacing requirements, and adjust the booth spacing parameters to form a safe space configuration; S5. Integrate the exhibition space distribution plan, optimize the booth space relationship and safety space configuration, generate the final exhibition design plan, and output an executable design file; The planning of visitor guidance paths in the exhibition space distribution scheme, and the detection of path decision conflict points through visitor flow simulation, include: Extract consecutive exhibit access pairs from the historical access sequence and map the access pairs as spatial guide segments in the exhibit spatial distribution scheme; The superimposed spatial guide segment classifies the density of the superimposed area and marks the high-density superimposed area; In high-density overlay areas, intersecting nodes with different guiding directions are identified and defined as path decision conflict points. The adjustment of the relative positions of exhibits to optimize booth space includes: Tracing the path decision conflict point back to the guiding segment that constitutes the path decision conflict point, and mapping the guiding segment back to its corresponding original item pair; Adjust the relative distance between the two exhibits in the original exhibit pair, and simultaneously introduce a related third exhibit to construct an exhibit triangle topology; Based on the triangular topological relationship of the exhibits, a new guide path is generated through the area, and the regenerated guide path is superimposed and compared with the path decision conflict point; Iteratively perform distance adjustment and relationship reconstruction operations to obtain optimized booth space relationships.

2. The exhibition design method based on deep learning as described in claim 1, characterized in that, The process involves collecting multi-dimensional data about the exhibition environment, analyzing visitor behavior patterns including dwell time and visit order, and constructing an interest association network for exhibits based on dwell time and visit order. Acquire visitor historical behavior trajectory data, and standardize the data format and coordinates to obtain preprocessed trajectory data; Identify stop points from preprocessed trajectory data and determine their duration and spatial location; Based on spatial location, the dwell points are mapped to the corresponding exhibits, generating exhibit visit sequences and associating them with durations to form basic interest data; Using exhibits as nodes, edges are constructed between nodes based on the co-occurrence relationship of access sequences in the basic interest data, and the duration is used as the weight of the edges to generate an exhibit interest association network.

3. The exhibition design method based on deep learning as described in claim 1, characterized in that, The analysis of high-frequency co-occurring exhibit combinations in the exhibit interest association network includes: Access the exhibit interest association network and dynamically slice the connection relationships in the network based on time windows to distinguish co-occurrence relationships in different time periods; By integrating co-occurrence relationships from different time periods and removing transient noise connections, a stable set of core co-occurrence relationships can be extracted. Spatial proximity verification was performed on the core co-occurrence relation set, and the core co-occurrence relations that passed the verification were confirmed as high-frequency co-occurrence exhibit combinations.

4. The exhibition design method based on deep learning as described in claim 3, characterized in that, The step of generating exhibit layout guidance rules based on co-occurrence intensity and determining exhibit spatial distribution schemes based on the guidance rules includes: The co-occurrence intensity of high-frequency co-occurrence exhibit combinations is quantified as the correlation attraction value between exhibits, and the correlation attraction value is corrected based on visitor flow resistance. Based on the corrected correlation gravity value, construct the exhibit layout guidance rules with the goal of maximizing the overall correlation gravity; The application of exhibit layout guidance rules generates multiple candidate spatial distribution schemes through iterative replacement. A conflict detection and resolution mechanism is introduced to screen candidate spatial distribution schemes, resulting in a spatial distribution scheme for exhibits.

5. The exhibition design method based on deep learning as described in claim 1, characterized in that, The aforementioned safety compliance check of the optimized booth space relationship, identifying areas that do not meet safety spacing requirements, includes: Deconstruct safety regulations and transform their qualitative descriptions and quantitative provisions into constraints that can be mapped to spatial attributes; By integrating constraints with the spatial attributes of exhibits in optimizing booth spatial relationships, a dynamic compliance threshold field is generated for each exhibit boundary. Scan the dynamic compliance threshold field, identify discrete conflict points whose field strength does not meet the preset safety level, and cluster the discrete conflict points into a conflict area map that does not meet the safety distance based on spatial proximity.

6. The exhibition design method based on deep learning as described in claim 5, characterized in that, The adjustment of exhibit spacing parameters to form a safe space configuration includes: Analyze conflict area maps and establish a resolution priority sequence based on the spatial correlation and severity of conflicts; Based on the resolution priority sequence, the topology of the exhibit clusters that caused the core conflict is restructured to generate a set of candidate security space configurations; The candidate safe space configuration set is back-mapped to the conflict area map for verification. The optimal configuration that can completely eliminate all conflict nodes in the map is selected to form the final safe space configuration.

7. The exhibition design method based on deep learning as described in claim 6, characterized in that, The integrated exhibition space distribution scheme, optimized booth space relationships and safety space configuration generate the final exhibition design scheme and output executable design files, including: The spatial layout of the integrated exhibition space distribution scheme, the topological connection of the optimized booth space relationship, and the spacing parameters of the safety space configuration are used to form a unified data fusion structure; Verify the coordination of various elements in the data fusion structure, and identify potential contradictions between the topological connections for spatial arrangement and optimization of booth spatial relationships and the spacing parameters for safe space configuration; Potential contradictions are resolved by applying the triangular topological relationship of exhibits and the resolution priority sequence, and the final exhibition design scheme is generated. The final exhibition design scheme is converted into a format that the exhibition system can recognize, and then assembled into an executable design file.

8. A deep learning-based exhibition design system, used to implement the deep learning-based exhibition design method according to any one of claims 1-7, characterized in that, The system includes: The network construction module is used to collect multi-dimensional data of the exhibition environment, analyze the dwell time and access order in the historical behavior trajectory of visitors, and construct an interest association network of exhibits based on the dwell time and access order. The exhibit distribution determination module is used to analyze high-frequency co-occurring exhibit combinations in the exhibit interest association network, generate exhibit layout guidance rules based on co-occurrence intensity, and determine exhibit spatial distribution schemes based on guidance rules. The booth space optimization module is used to plan visitor guidance paths in the exhibition space distribution scheme. By simulating visitor flow, it detects path decision conflict points and adjusts the relative positions of exhibition items to form an optimized booth space relationship. The space configuration adjustment module is used to check the safety compliance of optimized booth space relationships, identify areas that do not meet the safety spacing, and adjust the exhibition item spacing parameters to form a safe space configuration; The design file output module is used to integrate the exhibition space distribution plan, optimize the booth space relationship and safety space configuration, generate the final exhibition design plan, and output an executable design file.

Images