Exhibition hall management system and method based on big data

Abstract

The invention provides an exhibition hall management system and method based on big data, relates to the technical field of exhibition hall management, and is used for solving the technical problem of passive lag of an existing exhibition hall management system in related technologies. Comprising a data acquisition module used for acquiring preset exhibit static data and real-time visitor position data; the space-time grid construction module is used for constructing a space-time grid model for representing the space layout of the exhibition hall; the field domain value mapping module is used for setting a corresponding static value quantity for each exhibit and generating a value reference map covering the exhibition hall space; the dynamic congestion degree quantization module is used for quantizing to obtain the real-time congestion degree of each grid unit; the path potential evaluation module is used for evaluating the path potential score of the alternative path from the current position of the specific visitor to the position of any target exhibit; and the navigation instruction generation module is used for selecting the alternative path with the highest path potential score and generating a navigation instruction pointing to the corresponding target exhibit.

Description

Technical Field

[0001] This application relates to the field of exhibition hall management technology, and in particular to an exhibition hall management system and method based on big data. Background Technology

[0002] In recent years, with the development of information technology, some exhibition halls have begun to introduce visitor counting systems to monitor real-time visitor flow in different exhibition halls and issue warnings or implement temporary flow control measures when the flow of people is too dense. These systems have improved the safety management level of exhibition halls to some extent. However, existing exhibition hall management technology solutions generally have limitations.

[0003] Existing crowd management systems are mostly reactive, intervening only after congestion is detected, lacking the ability to predict crowd trends and proactively guide traffic. This passive management model fails to prevent congestion at its source, often leading to a decline in visitor experience. Traditional guidance methods, whether fixed route design or simple recommendations based on a few popular exhibits, ignore individual visitor differences and the dynamically changing environment within the exhibition hall. The system cannot provide personalized, dynamic navigation services based on each visitor's interests, current location, and real-time crowd distribution within the exhibition hall.

[0004] Existing systems typically treat all visitors and all visitor paths as homogeneous, lacking a quantitative evaluation framework to measure the value of the exhibition hall that different visitor behaviors can "activate." The core value of an exhibition hall lies in the culture and knowledge contained in its exhibits, but how to guide visitors to efficiently experience and discover these values, thereby maximizing the overall value of the exhibition hall, remains an unsolved problem. Summary of the Invention

[0005] This application provides a big data-based exhibition hall management system and method to improve at least one of the technical problems of existing exhibition hall management systems, including being passive and lagging, having a single guidance method, lacking quantitative value assessment, and having insufficient data integration.

[0006] To achieve the above objectives, the embodiments of this application adopt the following technical solutions:

[0007] Firstly, this application provides a big data-based exhibition hall management system, comprising: a data acquisition module for acquiring preset static data of exhibits and real-time visitor location data; a spatiotemporal grid construction module for dividing the physical space of the exhibition hall into multiple grid units to construct a spatiotemporal grid model representing the spatial layout of the exhibition hall; and a field value mapping module for assigning a corresponding static value to each exhibit based on the static data of the exhibits, and mapping each static value to a corresponding grid unit in the spatiotemporal grid model based on preset value dissipation rules, to generate a value covering the exhibition hall space. The system includes: a value benchmark map; a dynamic congestion quantification module, used to count the number of visitors falling into each grid cell based on the visitor location data, and quantify the real-time congestion of each grid cell accordingly; a path potential assessment module, used to assess the path potential score of alternative paths from the current location of a specific visitor to any target exhibit location based on the value benchmark map, the real-time congestion, and preset exhibit associations; and a navigation instruction generation module, used to select the alternative path with the highest path potential score and generate navigation instructions pointing to its corresponding target exhibit.

[0008] In one possible implementation of the first aspect, the field value mapping module is specifically used for: setting center point coordinates for each of the grid units; for any grid unit, obtaining the spatial distance between its center point coordinates and the position coordinates of each exhibit; based on the spatial distance, using a preset distance decay function, calculating the value contribution of each exhibit to the grid unit; summing the value contributions of all exhibits to the grid unit to obtain the total value of the grid unit, and using the total value of all grid units to construct the value benchmark map.

[0009] In one possible implementation of the first aspect, the dynamic congestion quantification module is specifically used to: take the volume of each grid cell as a reference quantity; obtain the number of visitors accommodated by each grid cell in the current time slice; and perform a combined calculation with the number of visitors and the reference quantity to obtain the real-time congestion degree characterizing the visitor space density.

[0010] In one possible implementation of the first aspect, the data acquisition module is further configured to acquire visitor type tags associated with the specific visitor; when evaluating the path potential score, the path potential assessment module also sets a basic activation coefficient for the specific visitor based on the visitor type tags; the evaluation process of the path potential score includes: combining the basic activation coefficient with the static value corresponding to the target exhibit to generate an activation value expectation that is suitable for the specific visitor.

[0011] In one possible implementation of the first aspect, the path potential assessment module is specifically used to: obtain the total value of the grid cell where the target exhibit is located in the value benchmark map as the basic path value; obtain the real-time congestion of each grid cell traversed by the alternative path and accumulate them to obtain the path congestion cost; query the preset exhibit association relationship to obtain the association strength value between the previous exhibit visited by the specific visitor and the target exhibit; and weight and combine the basic path value, the path congestion cost, and the association strength value to obtain the path potential score.

[0012] In one possible implementation of the first aspect, the system further includes: a disturbance correction module, configured to monitor the real-time congestion of all grid cells, mark the grid cell as a high-congestion area if the real-time congestion of any grid cell exceeds a preset congestion threshold; and when the path potential assessment module evaluates the score of the alternative path passing through the high-congestion area, introduce a preset congestion repulsion factor for the alternative path to reduce its final path potential score.

[0013] Secondly, this application also provides a big data-based exhibition hall management method, including: acquiring preset static exhibit data and real-time visitor location data; dividing the physical space of the exhibition hall into multiple grid units to construct a spatiotemporal grid model representing the spatial layout of the exhibition hall; assigning a corresponding static value to each exhibit based on the static exhibit data, and mapping each static value to a corresponding grid unit in the spatiotemporal grid model based on preset value dissipation rules to generate a value benchmark map covering the exhibition hall space; counting the number of visitors falling into each grid unit based on the visitor location data, and quantifying the real-time congestion of each grid unit accordingly; for a specific visitor, evaluating the path potential score of alternative paths from the current location of the specific visitor to the location of any target exhibit based on the value benchmark map, the real-time congestion, and preset exhibit associations; selecting the alternative path with the highest path potential score, and generating navigation instructions pointing to the corresponding target exhibit.

[0014] In one possible implementation of the second aspect, the step of generating the value benchmark map specifically includes: setting center point coordinates for each grid cell; for any grid cell, obtaining the spatial distance between its center point coordinates and the position coordinates of each exhibit; based on the spatial distance, using a preset distance decay function, calculating the value contribution of each exhibit to the grid cell; summing the value contributions of all exhibits to the grid cell to obtain the total value of the grid cell, and using the total value of all grid cells to construct the value benchmark map.

[0015] In one possible implementation of the second aspect, the step of evaluating the path potential score specifically includes: obtaining the total value of the grid cell where the target exhibit is located in the value benchmark map as the basic path value; obtaining the real-time congestion of each grid cell traversed by the alternative path and accumulating them to obtain the path congestion cost; querying the preset exhibit association relationship to obtain the association strength value between the previous exhibit visited by the specific visitor and the target exhibit; and weighting and combining the basic path value, the path congestion cost, and the association strength value to obtain the path potential score.

[0016] In one possible implementation of the second aspect, the method further includes: monitoring the real-time congestion of all grid cells, and marking the grid cell as a high-congestion area when the real-time congestion of any grid cell exceeds a preset congestion threshold; and introducing a preset congestion repulsion factor for the alternative path to reduce its final path potential score when evaluating the score of the alternative path through the high-congestion area. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the structure of a big data-based exhibition hall management system provided for some embodiments of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0019] In the following description, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0020] Furthermore, in this application, directional terms such as "upper," "lower," "left," and "right" may be defined relative to the orientation of the components shown in the accompanying drawings. It should be understood that these directional terms can be relative concepts, used for relative description and clarification, and may change accordingly depending on the orientation of the components in the accompanying drawings.

[0021] In this application, unless otherwise expressly specified and limited, the term "connection" should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral part; it can be a direct connection or an indirect connection through an intermediate medium. Furthermore, the term "electrical connection" can refer to the manner in which an electrical connection is used to achieve signal transmission.

[0022] As used herein, “about,” “approximately,” or “approximately” includes the stated value and a reference value within an acceptable range of deviation from the given value, characterized in that the acceptable range of deviation is determined by a person skilled in the art taking into account the measurement under discussion and the error associated with the measurement of the given quantity (i.e., the limitations of the measurement method).

[0023] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be described in detail below. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0024] This invention provides a big data-based exhibition hall management system and method, aiming to solve the technical problems of existing exhibition hall management methods being relatively passive and unable to provide refined and forward-looking guidance to visitors, resulting in uneven utilization of overall exhibition hall resources and difficulty in maximizing the individual experience value of visitors.

[0025] See attached document Figure 1 The system may include a data acquisition module, a spatiotemporal grid construction module, a field value mapping module, a dynamic congestion quantification module, a path potential assessment module, and a navigation instruction generation module.

[0026] The data acquisition module is responsible for obtaining heterogeneous data from multiple sources required to build the decision model. In one specific embodiment of the present invention, the data acquired by the data acquisition module mainly includes static exhibit data and real-time visitor location data.

[0027] The static data of the exhibits refers to persistent information describing the inherent attributes of the exhibits that does not change with time or environment. The data acquisition module can obtain this data by accessing the collection information database in the exhibition hall's backend, connecting to a digital archive system, or through manual entry by management personnel. For example, the static data of the exhibits may include: a unique identifier (ID) for the exhibit. exhibit ), the historical value score of the exhibits (Score) history ), art grade (Grade) art Author popularity index author ), Topic Categories (Tag) topicAnd its precise three-dimensional spatial coordinates ((x,y,z)) within the exhibition hall. exhibit These data together constitute a static portrait of the exhibit.

[0028] The real-time visitor location data is crucial information reflecting the dynamic distribution and flow of people within the exhibition hall. To achieve high-precision real-time positioning, the data acquisition module can integrate multiple positioning technologies to ensure data coverage and accuracy. For example, ultra-wideband (UWB) positioning technology can be used, equipping each visitor with a UWB tag and deploying multiple positioning base stations within the exhibition hall to achieve centimeter-level precision. Alternatively, Wi-Fi fingerprint positioning, Bluetooth iBeacon technology, or a fusion positioning system combining the inertial measurement unit (IMU) built into a smartphone can be used. The data acquisition module collects the real-time coordinate data of all visitors at a preset time frequency (e.g., once per second), forming a format: (Visitor ID, timestamp, (x, y, z)). visitor ) data flow.

[0029] Optionally, in another embodiment, the data acquisition module is also used to obtain visitor type tags (T tags) associated with a specific visitor. visitor This tag can be obtained through various methods upon visitor entry. For example, when purchasing tickets or entering the venue, visitors can select a theme of interest through an interactive interface (such as a mobile app or on-site touchscreen), such as "In-depth Tour of Ancient Art," "Interactive Technology Experience," or "Family Route." Based on their selection, the system assigns a corresponding visitor type tag. This tag will be used in subsequent personalized route recommendations.

[0030] The spatiotemporal grid construction module is responsible for dividing the physical space of the entire exhibition hall (including all exhibition halls, corridors, rest areas, etc.) into multiple regular or irregular, spatially adjacent grid cells. This process constructs a digital twin model representing the spatial layout of the exhibition hall, namely the spatiotemporal grid model (M). grid ).

[0031] In a preferred embodiment of the present invention, the spatiotemporal grid model is a three-dimensional grid in a Cartesian coordinate system. The spatiotemporal grid construction module first acquires the architectural floor plan or 3D BIM model of the exhibition hall and determines its spatial boundaries and dimensions ((L×W×H)). Then, according to the required analysis accuracy, the size of the grid cells is set; for example, each grid cell can be set as a 1m×1m×1m cube. Thus, the entire exhibition hall space is divided into a large number of grid cells with unique three-dimensional indices ((i,j,k)). Each grid cell becomes the basic unit carrying various subsequent attribute data (such as value, crowding). This processing method transforms the complex spatial problem into a discrete, computable grid data problem, simplifying subsequent analysis and calculation.

[0032] To facilitate calculation, the spatiotemporal grid construction module also assigns a center point coordinate (P) to each grid cell (i,j,k). cell (i,j,k)). These center point coordinates will serve as the representative position of this grid cell, used to calculate its distance from exhibits or other spatial entities.

[0033] The site value mapping module diffuses and superimposes the static value of each exhibit into the spatiotemporal grid model of the entire exhibition hall in a manner that decays with spatial distance, thereby generating a value benchmark map that can intuitively reflect the "value potential" of various parts of the exhibition hall. value ).

[0034] The influence of any exhibit with cultural or scientific value is not limited to its physical boundaries but radiates into the surrounding space. Even without being physically close to the exhibit, a visitor can perceive its presence and appreciate its general appearance from a certain distance, thus "activating" some of its value. The intensity of this influence naturally decreases with increasing distance. The field value mapping module is constructed precisely to provide a quantitative description of this inherent law.

[0035] The specific implementation steps are as follows:

[0036] The module first processes the static data of the exhibits received from the data acquisition module. Based on a preset weighting system, it assigns weights to multiple static attributes of the exhibits (such as Score). history Grade art Index author We perform a weighted summation on each exhibit (e) to calculate a single, comprehensive static value (V). static,e ).

[0037] For example, the static value can be obtained by combining the following methods:

[0038] V static,e =w1·Scorehistory,e +w2·Grade art,e +w3·Index author,e

[0039] Where w1, w2, and w3 are preset weight coefficients, and their sum is 1. static,e This represents the inherent value base of exhibit e.

[0040] The module pre-defines a value dissipation rule, which uses a distance decay function (f) decay (d) is used to describe the decay behavior of value with spatial distance (d).

[0041] For example, a decay rule in the form of a Gaussian function can be used:

[0042]

[0043] Where d is the distance between the spatial point and the exhibit source, and σ is a preset "value influence radius" parameter that controls the rate of value decay. The larger the value of σ, the wider the influence range of the exhibit.

[0044] The module iterates through each grid cell in the spatiotemporal grid model. i,j,k For any given grid cell, the processing flow is as follows:

[0045] Obtain the center point coordinates P of the grid cell. cell (i,j,k).

[0046] Iterate through all exhibits in the exhibition hall. For each exhibit e, calculate its position coordinates (x, y, z). exhibit,e The Euclidean distance d between the current grid cell center point coordinates Pcell(i,j,k) and the grid cell center point coordinates Pcell(i,j,k) e .

[0047]

[0048] Next, this distance d e Substitute the preset distance decay function f decay (d) Obtain the value contribution V of exhibit e to the current grid cell. contrib (e,i,j,k)=V static,e ·f decay (d e ).

[0049] The total value (V) of the grid cell is obtained by summing the value contributions of all exhibits to that grid cell. cell (i,j,k)):

[0050]

[0051] The module will convert the V values ​​of all grid cells cell The values ​​(i,j,k) are combined to form a three-dimensional data matrix with the same size as the spatiotemporal raster model. This matrix is ​​the aforementioned value benchmark map. value Each element in this map represents the overall value potential of its corresponding location within the exhibition space. High-value areas typically appear around important exhibits or in areas where the value fields of multiple exhibits overlap. This map is static and remains unchanged once generated unless the exhibit layout changes.

[0052] The dynamic congestion quantification module uses real-time visitor location data to quantify the congestion level of each grid cell at the current moment, generating a dynamically updated congestion map. crowd ).

[0053] The specific implementation steps of this module are as follows:

[0054] The module receives all visitor location data streams sent by the data acquisition module within a fixed time window (e.g., the most recent 1 second). For each visitor location data entry (visitor ID, timestamp, (x, y, z)... visitor The module will determine the coordinates (x, y, z) based on the module's behavior. visitor This maps it precisely to its current grid cell, GridCell(i,j,k).

[0055] The module maintains a dynamic counter for each grid cell (GridCell(i,j,k)). Within each time window, the module counts the total number N visitors that fall into that grid cell. visitor (i,j,k).

[0056] To obtain a standardized, physically meaningful congestion index, the module performs quantitative calculations. In a preferred embodiment, the real-time congestion index (D...) is... crowd (i,j,k) is defined as the visitor density per unit space.

[0057] The module first obtains the volume Vol of the raster cell from the spatiotemporal raster construction module. cell As a baseline, the real-time congestion level is then calculated using the following combination of operations:

[0058]

[0059] This value is measured in "people per cubic meter," which directly reflects the level of crowding in the space. D crowd The higher the value, the more crowded the area.

[0060] S230, Generate and update the crowding map. The module converts the D values ​​of all grid cells. crowd The values ​​of (i,j,k) are combined to form a three-dimensional data matrix with the same size as the spatiotemporal raster model, namely the crowding map. crowd Because visitors are constantly moving, this map is dynamically refreshed at a high frequency (e.g., once per second) to reflect the real-time distribution changes of people within the exhibition hall.

[0061] The path potential assessment module is used when it is necessary to assess the potential of a specific visitor (V). target When making navigation recommendations, this module can comprehensively utilize the aforementioned generated value benchmark map. value Real-time congestion map (Map) crowd In addition to other supporting information, a comprehensive and quantitative potential assessment is conducted on the alternative routes from the visitor's current location to each potential target exhibit, and a path potential score (S) is calculated for each alternative route. path ).

[0062] The specific implementation steps are as follows:

[0063] This module is activated when the system triggers a navigation request (e.g., a visitor actively requests a recommendation, or the system detects that the visitor has lingered in a certain area for too long). First, the evaluation subject is determined, namely the specific visitor V. target And obtain its current grid cell. current At the same time, the module will determine the set E of all exhibits that can serve as navigation targets. candidate (Exhibits that the visitor has recently viewed can be excluded).

[0064] For each candidate target exhibit e∈E candidate The module needs to plan a route from Cell current To the cell where the exhibit is located exhibit,e Alternative paths e Path planning can employ algorithms well-known to those skilled in the art, such as the A* algorithm or Dijkstra's algorithm, performed on a spatiotemporal grid model. The walking cost here is not only determined by geometric distance but can also take into account congestion levels to plan a physically reasonable path.

[0065] S320, Multi-dimensional Factor Quantification and Combination. For each alternative path... e The module extracts and calculates evaluation factors from multiple dimensions, and finally combines them into a path potential score S. path,e .

[0066] In a preferred embodiment, the assembly process is as follows:

[0067] Basic path value (Val) base This represents the value attractiveness of the path's endpoint. The module directly queries the value benchmark map (Map). value ), obtain the grid cell containing the target exhibit e. exhibit,e Total value V cell This is taken as the basic path value.

[0068] Val base =Map value (Cell exhibit,e )

[0069] Path congestion cost crowd The ') represents the 'congestion cost' required to reach the destination. The module iterates through the alternative paths. e Each grid cell passed through p Query real-time congestion map (Map) crowd The congestion level D is obtained. crowd (Cell p Then, the congestion of all grid cells along the path is summed (or weighted summed, for example, multiplied by the length of the path in that grid) to obtain the total congestion cost.

[0070]

[0071] The larger this value, the more congested the path, and the worse the visitor experience may be. Therefore, it should be treated as a negative factor in the final combination.

[0072] Exhibit association strength value (Val) relation This is designed to encourage logical and thematic sequential visits. The system pre-sets an exhibit association matrix (M). relation This matrix stores the correlation strength between any two exhibits. For example, artifacts from the same dynasty or works by the same painter have a high correlation strength. The module queries this matrix to obtain the current visitor V. target The previous exhibit I just visited prev The correlation strength value between the candidate target exhibit e and the candidate exhibit e.

[0073] Val relation =M relation (e prev e)

[0074] The higher this value, the stronger the logic of visiting in this order, and it should be given bonus points. If this is the visitor's first recommendation, this item can be 0 or a default value.

[0075] In embodiments that introduce visitor type tags, the expected visitor activation value (Val) is...activation This module is used to implement personalized recommendations. It is based on visitor V. target Visitor type tag T visitor Query a pre-defined mapping table and assign it a base activation coefficient (C). base For example, the label "history student" is used when visiting historical sites, and its C base The coefficient might be 1.5 for "ordinary tourists" and 1.0 for "general tourists." Then, this coefficient is compared with the static value V of the target exhibit. static,e Combine these elements to generate an activation value expectation that is "tailor-made" for the visitor.

[0076] Val activation =C base ·V static,e

[0077] This factor makes the system tend to recommend exhibits that are of the highest value to a particular type of visitor.

[0078] The module integrates all the above factors through a preset combination function to obtain the final path potential score S. path,e .

[0079] For example, a linear combination function could be:

[0080] S path,e =α·Val base +β·Val activation -γ·Cost crowd ·η convert +δVal relation

[0081] Here, α, β, γ, and δ are preset weighting coefficients used to adjust the importance of different factors in the final decision. These coefficients are configured by the exhibition hall managers according to their operational strategies (e.g., whether to prioritize crowd dispersal or enhancing the value experience).

[0082] η convert This is the congestion cost-value conversion coefficient. It's a system-preset constant that means each unit of cumulative path congestion should be considered equivalent to a loss of several units of value. For example, if η... convert =5 means that for every 1 unit of "person / cubic meter" of congestion accumulated along the path, 5 value units will be deducted from the final score.

[0083] By examining all candidate exhibits e∈E candidate By repeating the above evaluation process, the module will eventually obtain a series of alternative paths and their corresponding potential scores.

[0084] After the path potential assessment module completes the assessment of all candidate paths, the navigation instruction generation module selects the path with the highest path potential score (max(S)). path,e The alternative path is selected and recommended as the best option.

[0085] The module then translates this optimal path into navigation instructions that the user can understand. This can be done by drawing a dynamic navigation map on the visitor's mobile app, or by sending text or voice instructions, such as: "We recommend you go to the 'Along the River During the Qingming Festival' exhibition area on the second floor. Please walk straight for 10 meters in your current direction and then turn left." These instructions guide visitors to the globally optimal destination calculated by the system.

[0086] In one embodiment, the system further includes a perturbation correction module for dynamic feedback and adaptive adjustment of the recommendation system itself, so as to avoid new problems caused by the recommendation behavior itself, such as recommendation congestion.

[0087] The disturbance correction module runs continuously as a background monitoring process. Its core function is to monitor the global real-time congestion map (Map). crowd The module has a preset congestion threshold (D). threshold At each time slice, the module iterates through the real-time congestion D of all grid cells. crowd (i,j,k).

[0088] When the module detects the crowding level D of any one or more grid cells crowd (i,j,k) exceeds the preset threshold D threshold At that time, it will dynamically mark these grid cells as "high-crowding areas".

[0089] This "high congestion zone" marker immediately acts as a global disturbance signal, affecting the operation of the path potential assessment module. Specifically, when the path potential assessment module is evaluating any alternative path... e The cost of congestion crowd When a path needs to pass through a grid cell marked as a "high-congestion area," the system will introduce a preset, penalizing congestion repulsion factor λ for that path. repel .

[0090] This repulsion factor can be introduced in several ways. For example, it can be directly applied to the final path potential score. The modified score calculation function becomes:

[0091]

[0092] in, It is a path eThe number of grid cells that the upper part passes through in a highly congested area. λ repel It is a large positive number, and its introduction will significantly reduce the score of any path that attempts to enter or traverse a congested area.

[0093] Through this mechanism, the system forms a closed-loop feedback loop. When the system's recommendations lead to an increase in crowds in a certain area, once the congestion level in that area exceeds a threshold, the system will immediately and proactively "avoid" that area in subsequent recommendations, guiding crowds to other, less desirable but more spacious areas. This dynamic, real-time-based disturbance correction ensures that the distribution of crowds throughout the exhibition hall tends towards a dynamic equilibrium, guaranteeing full utilization of high-value areas while avoiding the degradation of the experience and safety hazards caused by localized overheating.

[0094] The following simplified scenario example will be used to illustrate the complete method flow provided by this invention.

[0095] Suppose there are two exhibits, A and B, in an exhibition hall. Visitor Mr. Li is currently at point P, and the system needs to recommend his next destination.

[0096] The system has collected static data for exhibits A and B, and calculated their static values ​​as V respectively. static,A =100,V static,B =80. Exhibit A and Exhibit B are highly related in terms of theme, and their correlation strength value Val is 80. relation (A,B)=50.

[0097] The system has divided the exhibition space into 1m×1m×1m grids and generated a value benchmark map based on the value dissipation rule. value .

[0098] The system uses UWB positioning to obtain the real-time location of Mr. Li and all other visitors, and generates a real-time congestion map based on this. crowd .

[0099] Mr. Li selected the "Art Appreciation" theme upon entry, and the system assigned him a relatively high base activation coefficient C. base =1.2.

[0100] Path potential assessment:

[0101] The system planned a path for Mr. Li from point P to point A. A and the path to point B B .

[0102] Evaluation Path A:

[0103] Basic Path Value Val base,A =Map value (CellA =95 (Assuming A is the core exhibit and its grid has high value).

[0104] Activate Value Expectations Val activation,A =C base ·V static,A =1.2·100=120.

[0105] Path congestion cost crowd,A =15 (assuming there are more people on path A).

[0106] Association strength value Val relation,A =0 (assuming Mr. Li had not visited any other exhibits before).

[0107] Assume the weights are α = 1, β = 0.5, γ = 1, δ = 1, and η convert =2, then the potential score for path A is:

[0108] S path,A =1.95 + 0.5.120 - 1.15.2 + 1.0 = 95 + 60 - 30 = 125.

[0109] Evaluation Path B:

[0110] Basic Path Value Val base,B =Map value (Cell B =70.

[0111] Activate Value Expectations Val activation,B =C base ·V static,B =1.2·80=96.

[0112] Path congestion cost crowd,B =5 (assuming there are few people on path B).

[0113] Association strength value Val relation,B =0.

[0114] Potential score for path B:

[0115] S path,B =1.70 + 0.5.96 - 1.5.2 + 1.0 = 70 + 48 - 10 = 108.

[0116] Navigation instruction generation:

[0117] Compare scores, S path,A (125)>S path,B (108). The system decided to recommend Mr. Li to visit exhibit A.

[0118] The system generates the instruction: "We recommend that you visit exhibit A ahead. Please proceed along the current route."

[0119] Suppose that due to continuous recommendations from the system, a large number of visitors flock to exhibit area A, causing Cell... A Crowding degree D of the grid and its surrounding grid crowd Exceeded threshold D threshold .

[0120] The disturbance correction module marks these grids as "high-crowding areas".

[0121] At this point, another Ms. Wang also requested a recommendation, and the system re-evaluated path A. When calculating the score, because path A passed through a highly congested area, its score was penalized by a repulsion factor:

[0122] S' path,A =125-λ repel ·1=125-50=75 (assuming λ) repel =50).

[0123] At this time S' path,A (75) path,B (108). Therefore, the system will recommend exhibit B, which has fewer visitors, to Ms. Wang, thus achieving a dynamic balance of visitor flow.

[0124] In summary, this invention, through the construction of a complete technical solution encompassing a spatiotemporal grid model, field value mapping, dynamic congestion quantification, multi-dimensional path evaluation, and dynamic disturbance correction, deeply integrates big data analysis with the refined management of exhibition halls. It not only optimizes the overall utilization efficiency of exhibition hall resources from a macro perspective but also provides each visitor with a personalized, high-quality experience, thereby significantly improving the management level and intelligence of the exhibition hall.

[0125] Those skilled in the art should understand that the above embodiments are merely examples, and various modifications and combinations can be made without departing from the spirit and scope of the invention. For example, the rules for value dissipation, the combination function of path potential scores, and the quantification method of congestion can all be adjusted and optimized according to specific application scenarios and management objectives. All such variations and equivalent substitutions based on the core ideas of the present invention should fall within the protection scope of the present invention.

[0126] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0127] ​In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another apparatus, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0128] The units described as separate components may or may not be physically separate. A component shown as a unit can be one physical unit or multiple physical units; that is, it can be located in one place or distributed in multiple different places. Depending on actual needs, some or all of the units can be selected to achieve the purpose of this embodiment.

[0129] Furthermore, the functional units in the various embodiments of this application 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 described above can be implemented in hardware.

[0130] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope 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.

Claims

1. A big data-based exhibition hall management system, characterized in that, include: The data acquisition module is used to acquire preset static data of exhibits and real-time visitor location data; The spatiotemporal grid construction module is used to divide the physical space of the exhibition hall into multiple grid units to construct a spatiotemporal grid model representing the spatial layout of the exhibition hall. The site value mapping module is used to set a corresponding static value for each exhibit based on the exhibit's static data, and to map each static value to a corresponding grid cell in the spatiotemporal grid model based on a preset value dissipation rule, so as to generate a value benchmark map covering the exhibition space. The dynamic congestion quantification module is used to count the number of visitors falling into each of the grid cells based on the visitor location data, and quantify the real-time congestion of each of the grid cells accordingly. The path potential assessment module is used to assess the path potential score of alternative paths from the current location of a specific visitor to any target exhibit location, based on the value benchmark map, the real-time congestion level, and the preset exhibit association relationships. The navigation instruction generation module is used to select the candidate path with the highest path potential score and generate navigation instructions pointing to the corresponding target exhibit.

2. The system according to claim 1, characterized in that, The field value mapping module is specifically used for: Set the center point coordinates for each of the grid cells; For any given grid cell, obtain the spatial distance between its center point coordinates and the position coordinates of each given exhibit; Based on the spatial distance, a preset distance attenuation function is used to calculate the value contribution of each exhibit to the grid unit. The total value of the grid cell is obtained by summing up the value contribution of all exhibits to the grid cell, and the total value of all grid cells is used to construct the value benchmark map.

3. The system according to claim 1, characterized in that, The dynamic congestion quantification module is specifically used for: The volume of each grid cell is used as a reference quantity; Get the number of visitors accommodated in each of the grid cells within the current time slice; The number of visitors is combined with the baseline quantity to obtain the real-time congestion level, which characterizes the spatial density of visitors.

4. The system according to claim 1, characterized in that, The data acquisition module is also used to obtain visitor type tags associated with the specific visitor; When evaluating the path potential score, the path potential assessment module also sets a basic activation coefficient for the specific visitor based on the visitor type label. The evaluation process of the path potential score includes: combining the basic activation coefficient with the static value corresponding to the target exhibit to generate an activation value expectation that is suitable for the specific visitor.

5. The system according to claim 1, characterized in that, The path potential assessment module is specifically used for: The total value of the grid cell containing the target exhibit in the value benchmark map is used as the base path value. The real-time congestion of each grid cell traversed by the alternative path is obtained and accumulated to obtain the path congestion cost. Query the preset exhibit association relationships to obtain the association strength value between the previous exhibit visited by the specific visitor and the target exhibit; The path potential score is obtained by weighting and combining the basic path value, the path congestion cost, and the association strength value.

6. The system according to any one of claims 1-5, characterized in that, The system also includes: The disturbance correction module is used to monitor the real-time congestion of all grid cells. If the real-time congestion of any grid cell exceeds a preset congestion threshold, the grid cell is marked as a high-congestion area. When the path potential assessment module evaluates the score of the alternative path passing through the high-congestion area, a preset congestion repulsion factor is introduced for the alternative path to reduce its final path potential score.

7. A big data-based exhibition hall management method, characterized in that, include: Acquire preset static exhibit data and real-time visitor location data; The physical space of the exhibition hall is divided into multiple grid units to construct a spatiotemporal grid model representing the spatial layout of the exhibition hall. Based on the static data of the exhibits, a corresponding static value is set for each exhibit, and based on the preset value dissipation rule, each static value is mapped to the corresponding grid cell in the spatiotemporal grid model to generate a value benchmark map covering the exhibition space. Based on the visitor location data, the number of visitors falling into each of the grid cells is counted, and the real-time congestion of each grid cell is quantified accordingly. For a specific visitor, based on the value benchmark map, the real-time congestion level, and the preset exhibit associations, the path potential score of alternative paths from the specific visitor's current location to any target exhibit location is evaluated. Select the candidate path with the highest path potential score and generate navigation instructions pointing to the corresponding target exhibit.

8. The method according to claim 7, characterized in that, The steps for generating the value benchmark map specifically include: Set the center point coordinates for each of the grid cells; For any given grid cell, obtain the spatial distance between its center point coordinates and the position coordinates of each given exhibit; Based on the spatial distance, a preset distance attenuation function is used to calculate the value contribution of each exhibit to the grid unit. The total value of the grid cell is obtained by summing up the value contribution of all exhibits to the grid cell, and the total value of all grid cells is used to construct the value benchmark map.

9. The method according to claim 7, characterized in that, The steps for evaluating the potential score of the path specifically include: The total value of the grid cell containing the target exhibit in the value benchmark map is used as the base path value. The real-time congestion of each grid cell traversed by the alternative path is obtained and accumulated to obtain the path congestion cost. Query the preset exhibit association relationships to obtain the association strength value between the previous exhibit visited by the specific visitor and the target exhibit; The path potential score is obtained by weighting and combining the basic path value, the path congestion cost, and the association strength value.

10. The method according to any one of claims 7-9, characterized in that, The method further includes: Monitor the real-time congestion of all grid cells, and mark the grid cell as a high-congestion area if the real-time congestion of any grid cell exceeds a preset congestion threshold. When evaluating the score of alternative routes through the high-congestion area, a preset congestion repulsion factor is introduced for the alternative route to reduce its final route potential score.

Images