A modeling method and system based on 3D engine and POI aggregation algorithm

Abstract

The present application provides a modeling method and system based on a 3D engine and a POI aggregation algorithm, including: acquiring target data of an object to be modeled; performing hierarchical aggregation processing and spatial clustering on the POI data to obtain a clustering result; performing importance evaluation processing on the clustering result to obtain an importance ranking result; using the 3D engine, the importance ranking result, and the 3D terrain and building data to model and render the object to be modeled to obtain a 3D model of the object to be modeled, thereby realizing efficient processing of multi-level information of POIs, optimizing data display through clustering analysis and importance evaluation, and seamlessly integrating with the 3D city model to realize accurate visualization of the dynamic characteristics of urban POIs, and promoting the depth and breadth of the application of digital twin technology in smart city construction.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of 3D modeling, and in particular, to a modeling method and system based on a 3D engine and a POI aggregation algorithm. Background Art

[0002] With the acceleration of urbanization and the rapid development of information technology, the concept of digital twins has shown great potential in the fields of smart cities, geographic information systems, urban planning and management, etc. Digital twin technology creates a virtual mirror of the physical world, realizes real-time simulation, monitoring and optimization of the physical environment, and provides unprecedented decision-making support capabilities for urban management, resource allocation, disaster warning, etc.

[0003] However, when building digital twin models of complex urban environments, there are two major challenges: one is how to efficiently integrate and display massive amounts of urban geographic information; the other is how to accurately reflect the dynamic changes in people's activities and preferences in the city. Traditional 3D modeling methods focus on the geometric reconstruction of static objects, and often ignore the dynamic characteristics of points of interest (POIs) that are closely related to human interaction, such as popularity fluctuations in commercial areas and changes in activity hotspots within a specific time period. Summary of the invention

[0004] The embodiments of the present application provide a modeling method and system based on a 3D engine and a POI aggregation algorithm to solve the problems existing in the above-mentioned background technology.

[0005] In a first aspect, an embodiment of the present application provides a modeling method based on a 3D engine and a POI aggregation algorithm, comprising: obtaining target data of an object to be modeled, wherein the target data at least includes: POI data and 3D terrain and building data, and the POI data includes: location information, popularity index, object category, time sensitivity factor, distance attenuation factor and user preference factor; performing hierarchical aggregation processing and spatial clustering on the POI data to obtain clustering results; performing importance evaluation processing on the clustering results to obtain importance ranking results; using the 3D engine, the importance ranking results and the 3D terrain and building data to model and render the object to be modeled to obtain a 3D model of the object to be modeled.

[0006] Furthermore, the POI data is subjected to hierarchical aggregation processing and spatial clustering to obtain a clustering result, including: determining a preset radius based on a user perspective; determining the number of remaining objects to be modeled within the preset radius with the target modeling object as the center, wherein the target modeling object is any one of the objects to be modeled, and the remaining objects to be modeled are objects other than the target modeling object among the objects to be modeled; if the number is greater than a preset threshold, determining the target modeling object and the remaining objects to be modeled within the preset radius as a cluster; traversing all objects to be modeled to obtain the clustering result.

[0007] Furthermore, the clustering results are processed for importance assessment to obtain importance ranking results, including: calculating the importance assessment value of each object to be modeled in each cluster based on the POI data and the importance assessment calculation formula, wherein the importance assessment value is used to characterize the priority of the object to be modeled displayed in the user interface; and sorting the importance assessment value of each object to be modeled corresponding to each cluster to obtain the ranking result.

[0008] Furthermore, the importance evaluation calculation formula is: ;

[0009] in, is the importance assessment value, and is the weight value, is the weighted value of the popularity index, is the weight of the object category, is the time sensitive factor, is the distance attenuation factor, is the user preference factor.

[0010] Furthermore, the clustering results are evaluated for importance to obtain importance ranking results, including: inputting the POI data of the objects to be modeled contained in each cluster into the machine learning model so that the machine learning model outputs the importance ranking results, wherein the machine learning model is a machine learning model based on gradient boosting tree and deep neural network components.

[0011] Furthermore, the machine learning model is further optimized using an online learning mechanism and a preset loss function; the preset loss function is:

[0012] ;

[0013] in, is the loss function value, is the number of objects to be modeled contained in the cluster, is the total number of possible ranking positions, Used to represent the object to be modeled Is the ranking position of , For the object to be modeled In ranking position The unnormalized score output when , For ranking position For the object to be modeled The softmax probability of is the set of objects to be modeled contained in the cluster, For the object to be modeled the output scores in the machine learning model, For the object to be modeled the output scores in the machine learning model, is an adjustable margin, For the object to be modeled In ranking position The unnormalized score output when , For ranking position For the object to be modeled The softmax probability of .

[0014] Furthermore, the object to be modeled is modeled and rendered using a 3D engine, the importance ranking result, and the 3D terrain and building data to obtain a 3D model of the object to be modeled, including: using a 3D engine and the 3D terrain and building data to construct an initial 3D model of the object to be modeled; based on the importance ranking result, matching the description information of the object to be modeled to the initial 3D model of the object to be modeled to obtain the 3D model of the object to be modeled, wherein the description information includes: text description, pictures, and links.

[0015] In the second aspect, an embodiment of the present application provides a modeling system based on a 3D engine and a POI aggregation algorithm, comprising: an acquisition unit, used to acquire target data of an object to be modeled, wherein the target data includes at least: POI data and 3D terrain and building data, and the POI data includes: location information, popularity index, object category, time sensitivity factor, distance attenuation factor and user preference factor; a clustering unit, used to perform hierarchical aggregation processing and spatial clustering on the POI data to obtain a clustering result; an evaluation unit, used to perform importance evaluation processing on the clustering result to obtain an importance ranking result; a modeling unit, used to use the 3D engine, the importance ranking result and the 3D terrain and building data to model and render the object to be modeled to obtain a 3D model of the object to be modeled.

[0016] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the method described in the first aspect above.

[0017] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, which, when executed by a computer, implements the method described in the first aspect above.

[0018] In an embodiment of the present invention, target data of the object to be modeled is obtained; hierarchical aggregation processing and spatial clustering are performed on POI data to obtain clustering results; importance evaluation processing is performed on the clustering results to obtain importance ranking results; the object to be modeled is modeled and rendered using a 3D engine, importance ranking results, and 3D terrain and building data to obtain a 3D model of the object to be modeled, thereby achieving efficient processing of multi-level information of POIs, optimizing data display through clustering analysis and importance evaluation, and seamlessly integrating with the 3D city model to achieve accurate visualization of the dynamic characteristics of urban POIs, thereby promoting the depth and breadth of the application of digital twin technology in smart city construction.

[0019] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 A flowchart of a modeling method based on a 3D engine and a POI aggregation algorithm provided in an embodiment of the present application;

[0022] Figure 2 A flowchart of a modeling system based on a 3D engine and a POI aggregation algorithm provided in an embodiment of the present application;

[0023] Figure 3 A schematic diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example

[0025] According to an embodiment of the present invention, an embodiment of a modeling method based on a 3D engine and a POI aggregation algorithm is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0026] Figure 1 is a flow chart of a modeling method based on a 3D engine and a POI aggregation algorithm according to an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0027] Step S102, obtaining target data of the object to be modeled, wherein the target data at least includes: POI data and 3D terrain and building data, and the POI data includes: location information, popularity index, object category, time sensitivity factor, distance attenuation factor and user preference factor;

[0028] Step S104, performing hierarchical aggregation processing and spatial clustering on the POI data to obtain a clustering result;

[0029] Step S106, performing importance evaluation processing on the clustering results to obtain importance ranking results;

[0030] Step S108, using a 3D engine, the importance ranking result and the 3D terrain and building data, modeling and rendering the object to be modeled to obtain a 3D model of the object to be modeled.

[0031] The following is an example of building a digital twin model in a large urban park to monitor and predict the distribution of pedestrian flows in real time and assist in urban planning and commercial activity decision-making to illustrate the above steps.

[0032] First, the detailed information of all POIs in the area is obtained from the map service provider through the API interface, including latitude and longitude, object category (such as catering, shopping, leisure and entertainment), historical visit volume (as popularity index), user ratings, etc. At the same time, the time-sensitive factor is obtained based on social media analysis, that is, the popularity change of a specific POI in different time periods.

[0033] Use drone photogrammetry and satellite image processing technology to generate high-precision 3D terrain models. Obtain the three-dimensional structure and appearance texture of the building through BIM (Building Information Modeling) data or LiDAR scanning.

[0034] The above steps ensure that the basic information for model construction is comprehensive and accurate, which is the prerequisite for the digital twin model to truly reflect the physical world.

[0035] According to the user's perspective (such as from a macroscopic city bird's eye view to a block-level view), the parameters of the DBSCAN algorithm (such as the radius ε) are dynamically adjusted to spatially cluster POIs to avoid information overload in high-density areas. Then, based on the clustering results, the POIs in each cluster are further hierarchically aggregated by category and time-sensitive factors. For example, at noon on weekdays, the aggregation weight of catering POIs is increased.

[0036] According to the importance ranking results, icons or 3D models of different styles and sizes are designed to represent various POIs. For example, popular restaurants are marked with eye-catching 3D models, while low-priority POIs are displayed with simple icons. When users approach or click, detailed information is displayed through information bubbles.

[0037] Then, a comprehensive score is calculated for each cluster or individual high-priority POI. By comprehensively considering multiple factors, the information displayed by the model is more in line with the actual needs of users and the characteristics of the scene.

[0038] Finally, in the Unity 3D engine, import the processed 3D terrain and building data to build the basic scene.

[0039] According to the importance ranking results, icons or 3D models of different styles and sizes are designed to represent various POIs. For example, popular restaurants are marked with eye-catching 3D models, while low-priority POIs are displayed with simple icons. When users approach or click, detailed information is displayed through information bubbles.

[0040] Preferably, a user interface can also be developed to allow users to observe changes in crowd distribution at different time periods by sliding the timeline, query specific POIs through the search box, experience the block environment through virtual roaming, adjust the lighting to match the actual time and weather, and apply real material textures to increase the realism and immersion of the scene.

[0041] In the embodiment of the present invention, hierarchical aggregation processing and spatial clustering are performed on the POI data to obtain clustering results, including:

[0042] Based on the user's perspective, a preset radius is determined;

[0043] Taking the target modeling object as the center, determining the number of the remaining objects to be modeled within the preset radius, wherein the target modeling object is any one of the objects to be modeled, and the remaining objects to be modeled are objects among the objects to be modeled except the target modeling object;

[0044] If the number is greater than a preset threshold, the target modeling object and the remaining objects to be modeled within the preset radius are determined as a cluster;

[0045] All objects to be modeled are traversed to obtain the clustering result.

[0046] In an embodiment of the present invention, the visual range of an observer in the real world is simulated. Considering that digital twin applications usually need to support multi-scale browsing (from the overall park layout to the details of a single attraction), the selection of the preset radius should adapt to the observation needs in different scenarios. For example, if the user is mainly concerned about how to efficiently plan a path from one popular attraction to another, the preset radius may be set to cover the distance of 2-3 major attractions around, ensuring that the user can intuitively see the surrounding related facilities.

[0047] By counting the number of POIs around the target modeling object, it can be determined whether these POIs need to be clustered. This step helps reduce visual clutter, making it easier for users to focus on important areas or areas with concentrated points of interest, and also provides basic information for subsequent space optimization.

[0048] When the number of the target object and its surrounding objects exceeds the preset threshold, it indicates that the area has a high concentration of activities or functional relevance. Treating it as a cluster can effectively integrate information display and reduce interface complexity. For example, during peak hours, the cluster formed around a popular restaurant may also include nearby rest areas and toilets, making it easier for tourists to quickly understand surrounding supporting services.

[0049] Traverse all the objects to be modeled and repeat the above steps to ensure that all potential high-density or high-correlation areas in the entire park are identified and reasonably clustered. This not only improves the efficiency of information organization, but also provides an orderly basis for subsequent dynamic rendering and data analysis (such as crowd flow simulation and resource allocation optimization).

[0050] Through the above steps, a hierarchical and easy-to-navigate digital twin model can be created for the city park. In the final model, users can observe the overall layout of the park from a macro perspective and quickly locate the area of ​​interest through zooming and panning operations; and when focusing on a specific attraction, it can automatically display the POI clustering in the area, displaying detailed information on related facilities and the flow of people. This design greatly improves the user experience and also provides intuitive data support for park managers, helping them better understand visitor behavior and make more scientific management decisions.

[0051] In the embodiment of the present invention, the clustering results are evaluated for importance to obtain importance ranking results, including the following two methods:

[0052] Method 1: Based on the POI data and the importance evaluation calculation formula, the importance evaluation value of each object to be modeled in each cluster is calculated, wherein the importance evaluation value is used to characterize the priority of the object to be modeled displayed in the user interface;

[0053] The importance evaluation value of each object to be modeled corresponding to each cluster is sorted to obtain the sorting result.

[0054] Specifically, the importance assessment calculation formula is:

[0055] ;

[0056] in, is the importance assessment value, and is the weight value;

[0057] is the weighted value of the popularity index, The adjustment factor allows nonlinear adjustment of the impact of popularity based on project demand. >1, the role of popularity is highly emphasized; otherwise, it is relatively weakened.

[0058] The weights of the object categories may be set more finely, such as dynamically adjusting the weights of certain categories according to time periods (daytime / nighttime) or specific events (such as holidays).

[0059] The time-sensitive factor considers the popularity or availability of POIs over time, for example, the weight of restaurants increases during mealtimes, and the weight of nighttime entertainment venues increases during the nighttime hours.

[0060] The distance attenuation factor reflects the influence of the distance between the user and the POI. The closer the distance is, the higher the score of the POI may be. It can be expressed as follows: The calculation is done in the form of is the distance from the user's current location to the POI, and β is the attenuation coefficient, which controls the intensity of the distance effect.

[0061] The user preference factor can be used to adjust the score of the POI in a personalized manner according to the user's browsing history, favorite record or explicitly set preference, thereby enhancing the personalization of the user experience.

[0062] Method 2: Input the POI data of the objects to be modeled contained in each cluster into the machine learning model so that the machine learning model outputs the importance ranking result, wherein the machine learning model is a machine learning model based on gradient boosting tree and deep neural network components.

[0063] Preferably, the machine learning model can be further optimized by using an online learning mechanism and a preset loss function;

[0064] The preset loss function is:

[0065] ;

[0066] in, is the loss function value, is the number of objects to be modeled contained in the cluster, is the total number of possible ranking positions, Used to represent the object to be modeled Is the ranking position of , For the object to be modeled In ranking position The unnormalized score output when , For ranking position For the object to be modeled The softmax probability of is the set of objects to be modeled contained in the cluster, For the object to be modeled the output scores in the machine learning model, For the object to be modeled the output scores in the machine learning model, is an adjustable margin, For the object to be modeled In ranking position The unnormalized score output when , For ranking position For the object to be modeled The softmax probability of .

[0067] In an embodiment of the present invention, the object to be modeled is modeled and rendered using a 3D engine, the importance ranking result, and the 3D terrain and building data to obtain a 3D model of the object to be modeled, including:

[0068] Using a 3D engine and the 3D terrain and building data, construct an initial 3D model of the object to be modeled;

[0069] Based on the importance ranking result, the description information of the object to be modeled is matched to the initial 3D model of the object to be modeled to obtain the 3D model of the object to be modeled, wherein the description information includes: text description, pictures and links.

[0070] In the embodiment of the present invention, in a 3D engine (such as Unity), the previously collected and processed 3D terrain and building data are first used to construct a basic 3D model of the commercial center area, including accurate reproduction of the terrain, the appearance and structural details of the buildings, and the layout of public facilities such as roads and green spaces. This provides a realistic physical environment framework and an intuitive visual basis for users and decision makers.

[0071] According to the ranking results of POI importance, corresponding description information is assigned to each important POI (such as shopping malls, restaurants, and public transportation stations) in the 3D model, including a label with a text description for each POI location in the 3D model to display its name, category, special services and other basic information. In addition, interactive elements are added to some POIs, such as an information window that pops up after clicking the POI icon, which contains detailed text descriptions, real-life pictures and official website links. This design makes the model not only a visual display, but also an information-rich interactive platform where users can gain in-depth understanding of the details of each location and provide data support for business decisions.

[0072] Through the above steps, the final 3D model is not only a highly restored virtual urban space, but also a digital twin full of information and interactive possibilities. Planners and investors can virtually roam in this model, intuitively experience the future urban space layout, and evaluate the value of each commercial plot; at the same time, by analyzing the flow simulation data and user behavior preferences, optimize the facility configuration and commercial layout to improve space utilization efficiency and user experience. Example

[0073] An embodiment of the present invention also provides a modeling system based on a 3D engine and a POI aggregation algorithm, which is used to execute the modeling method based on a 3D engine and a POI aggregation algorithm provided in the above content of the embodiment of the present invention. The following is a specific introduction to the modeling system based on a 3D engine and a POI aggregation algorithm provided in an embodiment of the present invention.

[0074] like Figure 2 As shown, Figure 2 Schematic diagram of the modeling system based on the 3D engine and POI aggregation algorithm, the system includes:

[0075] An acquisition unit 10 is used to acquire target data of an object to be modeled, wherein the target data at least includes: POI data and 3D terrain and building data, and the POI data includes: location information, popularity index, object category, time sensitivity factor, distance attenuation factor and user preference factor;

[0076] A clustering unit 20, used for performing hierarchical aggregation processing and spatial clustering on the POI data to obtain a clustering result;

[0077] An evaluation unit 30, configured to perform importance evaluation processing on the clustering result to obtain an importance ranking result;

[0078] The modeling unit 40 is used to model and render the object to be modeled by using a 3D engine, the importance ranking result and the 3D terrain and building data to obtain a 3D model of the object to be modeled.

[0079] The embodiment of the present invention obtains target data of the object to be modeled; performs hierarchical aggregation processing and spatial clustering on POI data to obtain clustering results; performs importance evaluation processing on the clustering results to obtain importance ranking results; uses a 3D engine, importance ranking results and 3D terrain and building data to model and render the object to be modeled to obtain a 3D model of the object to be modeled, thereby achieving efficient processing of multi-level information of POI, optimizing data display through clustering analysis and importance evaluation, and seamlessly integrating with the 3D city model to achieve accurate visualization of the dynamic characteristics of urban POIs, thereby promoting the depth and breadth of the application of digital twin technology in smart city construction. Example

[0080] The embodiment of the present invention further provides a computing device for executing a program of the method described in the first embodiment, such as Figure 3 As shown, the computing device may include a storage component 41 and a processing component 42;

[0081] The storage component 41 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 42 .

[0082] The processing component 42 may include one or more processors to execute computer instructions to complete all or part of the steps in the method of embodiment 1. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0083] The storage component 41 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0084] The display component 43 may be an electroluminescent (EL) element, a liquid crystal display or a micro display having a similar structure, or a retinal direct display or a similar laser scanning display.

[0085] Of course, a computing device may also include other components, such as input / output interfaces, communication components, etc.

[0086] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0087] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0088] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform. Example

[0089] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The method of the illustrated embodiment.

[0090] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0091] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0092] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A modeling method based on a 3D engine and a POI aggregation algorithm, characterized in that: include: Acquire target data of the object to be modeled, wherein the target data at least includes: POI data and 3D terrain and building data, and the POI data includes: location information, popularity index, object category, time sensitivity factor, distance attenuation factor and user preference factor; Performing hierarchical aggregation processing and spatial clustering on the POI data to obtain a clustering result; Performing importance evaluation processing on the clustering results to obtain importance ranking results; Modeling and rendering the object to be modeled by using a 3D engine, the importance ranking result, and the 3D terrain and building data to obtain a 3D model of the object to be modeled; The clustering results are evaluated for importance to obtain importance ranking results, including: Inputting the POI data of the objects to be modeled contained in each cluster into a machine learning model so that the machine learning model outputs the importance ranking result, wherein the machine learning model is a machine learning model constructed based on a gradient boosting tree and a deep neural network; The method further comprises: Utilizing an online learning mechanism and a preset loss function to further optimize the machine learning model; The preset loss function is: ； in, is the loss function value, is the number of objects to be modeled contained in the cluster, is the total number of possible ranking positions, Used to represent the object to be modeled Is the ranking position of , For the object to be modeled In ranking position The unnormalized score output when , For ranking position For the object to be modeled The softmax probability of is the set of objects to be modeled contained in the cluster, For the object to be modeled the output scores in the machine learning model, For the object to be modeled the output scores in the machine learning model, is an adjustable margin, For the object to be modeled In ranking position The unnormalized score output when , For ranking position For the object to be modeled The softmax probability of .

2. The method according to claim 1, characterized in that Performing hierarchical aggregation processing and spatial clustering on the POI data to obtain clustering results, including: Based on the user's perspective, a preset radius is determined; Taking the target modeling object as the center, determining the number of the remaining objects to be modeled within the preset radius, wherein the target modeling object is any one of the objects to be modeled, and the remaining objects to be modeled are objects among the objects to be modeled except the target modeling object; If the number is greater than a preset threshold, the target modeling object and the remaining objects to be modeled within the preset radius are determined as a cluster; All objects to be modeled are traversed to obtain the clustering result.

3. The method according to claim 1, characterized in that The clustering results are evaluated for importance to obtain importance ranking results, including: Based on the POI data and the importance evaluation calculation formula, an importance evaluation value of each object to be modeled in each cluster is calculated, wherein the importance evaluation value is used to characterize the priority of the object to be modeled displayed in the user interface; The importance evaluation value of each object to be modeled corresponding to each cluster is sorted to obtain the sorting result.

4. The method according to claim 3, characterized in that The importance assessment calculation formula is: ； in, is the importance assessment value, and is the weight value, is the weighted value of the popularity index, is the weight of the object category, is the time sensitive factor, is the distance attenuation factor, is the user preference factor.

5. The method according to claim 1, characterized in that Modeling and rendering the object to be modeled using a 3D engine, the importance ranking result, and the 3D terrain and building data to obtain a 3D model of the object to be modeled, including: Using a 3D engine and the 3D terrain and building data, construct an initial 3D model of the object to be modeled; Based on the importance ranking result, the description information of the object to be modeled is matched to the initial 3D model of the object to be modeled to obtain the 3D model of the object to be modeled, wherein the description information includes: text description, pictures and links.

6. A modeling system based on a 3D engine and a POI aggregation algorithm, used to execute the modeling method based on a 3D engine and a POI aggregation algorithm according to any one of claims 1 to 5, characterized in that: include: An acquisition unit, used for acquiring target data of an object to be modeled, wherein the target data at least includes: POI data and 3D terrain and building data, and the POI data includes: location information, popularity index, object category, time sensitivity factor, distance attenuation factor and user preference factor; A clustering unit, used for performing hierarchical aggregation processing and spatial clustering on the POI data to obtain a clustering result; An evaluation unit, used to perform importance evaluation processing on the clustering result to obtain an importance ranking result; The modeling unit is used to model and render the object to be modeled by using a 3D engine, the importance ranking result and the 3D terrain and building data to obtain a 3D model of the object to be modeled.

7. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the method according to any one of claims 1 to 5.

8. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, the method according to any one of claims 1 to 5 is implemented.

Images