Modeling method and rendering method of park three-dimensional model, electronic equipment and medium

Abstract

The invention relates to the technical field of smart parks, in particular to a modeling method and rendering method of a park three-dimensional model, electronic equipment and a medium. According to the modeling method of the park three-dimensional model, multi-source real-time park data are collected for various park items in a target park through an Internet of Things device; performing data standardization operation based on the multi-source real-time park data to obtain standardized Internet of Things data; the data prediction module is used for uploading the standardized Internet of Things data to a cloud server; in a data prediction module, performing park item state evolution prediction based on the standardized Internet of Things data to obtain item prediction data corresponding to each park item; and in the model construction module, three-dimensional model construction is performed based on the standardized Internet of Things data, the item prediction data and the park model preform, and a park three-dimensional model corresponding to the target park is obtained. Therefore, the park three-dimensional model which can reflect the park state more accurately in real time can be constructed.

Description

Technical Field

[0001] This application relates to the field of smart park technology, and in particular to a modeling and rendering method for a 3D model of a park, an electronic device, and a medium. Background Technology

[0002] In the construction and development of smart parks, building a 3D model that can realistically and in real-time reflect the park's status has become a key technological requirement for improving management efficiency. However, related technologies face a series of technical problems in this field, which restrict their in-depth application and effectiveness in real-world scenarios.

[0003] Due to limitations in the current system architecture, such as insufficient real-time data acquisition and compatibility, low efficiency in updating 3D models and poor rendering performance, weak data processing capabilities and lack of intelligent analysis, as well as uneven network coverage, the 3D models of the park currently constructed cannot accurately and in real-time reflect the park's status. Summary of the Invention

[0004] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes a modeling and rendering method, electronic equipment, and media for a 3D model of a park, thereby constructing a 3D model of the park that can more accurately and in real-time reflect the park's status.

[0005] The method for modeling a 3D model of a park according to a first aspect of this application is applied to a smart park system, the smart park system including IoT devices, edge computing nodes, and a data platform deployed in the target park, and a data prediction module and a model building module deployed on a cloud server, the method comprising: The IoT device is used to collect multi-source real-time park data for various park items in the target park. Based on the multi-source real-time park data, data standardization operations are performed to obtain standardized IoT data; The standardized IoT data is uploaded to the data prediction module of the cloud server; In the data prediction module, the state evolution prediction of park items is performed based on the standardized IoT data to obtain the item prediction data corresponding to each park item. In the model building module, a three-dimensional model is built based on the standardized IoT data, the predicted object data, and the prefabricated park model to obtain the three-dimensional park model corresponding to the target park.

[0006] According to some embodiments of this application, the smart park system further includes edge computing nodes and a data communication network deployed in the target park. The step of performing data standardization operations based on the multi-source real-time park data to obtain standardized IoT data includes: Coarse verification processing is performed on the multi-source real-time park data to obtain coarsely verified IoT data of various IoT data types; The coarse-verification IoT data of various IoT data types are transmitted to the edge computing node through the data communication network. In the edge computing node, the corresponding coarse-verified IoT data is subjected to fine-verification processing based on the IoT data type to obtain fine-verified IoT data of various IoT data types; The data platform performs data fusion operations on the precisely verified IoT data of various IoT data types to obtain the standardized IoT data.

[0007] According to some embodiments of this application, the IoT data types include timeliness requirement types, reliability requirement types, and reachability requirement types; the data communication network includes a wide-area high-speed backbone network, an indoor high-density access network, and a long-distance low-power IoT network; and the step of transmitting the coarse-checked IoT data of various IoT data types to the edge computing node through the data communication network includes: The coarse-verification IoT data of the time-sensitive demand type is transmitted to the edge computing node through the wide-area high-speed backbone network. The coarse-verification IoT data of the reliability requirement type is transmitted to the edge computing node through the indoor high-density access network. The coarse-verified IoT data of the reachability requirement type is transmitted to the edge computing node via the long-distance low-power IoT network.

[0008] According to some embodiments of this application, the step of collecting multi-source real-time park data for various park items in the target park through the IoT device includes: Outdoor video stream data, park mobile device data, and park key equipment data are collected as the coarse verification IoT data for the timeliness requirement type. Indoor video stream data, dense access signals from user terminals, and indoor environmental sensing signals are collected as coarse-check IoT data for the reliable demand type. The collected corner sensing signals, object security status signals, and park asset tracking signals serve as the coarse-verification IoT data for the reachability requirement type.

[0009] According to some embodiments of this application, the coarse verification processing of the multi-source real-time park data to obtain coarsely verified IoT data of various IoT data types includes: The integrity screening of the multi-source real-time park data was performed to obtain the integrity screening results; If the integrity screening result meets the preset integrity screening conditions, the rationality screening of the multi-source real-time park data is performed through a predetermined normal IoT value range to obtain the rationality screening result; If the rationality screening result meets the preset rationality screening conditions, the multi-source real-time park data is determined as the corresponding coarse-verification IoT data according to the IoT data type of the multi-source real-time park data.

[0010] According to some embodiments of this application, the fine verification processing of the corresponding coarse-verified IoT data based on the IoT data type to obtain fine-verified IoT data of various IoT data types includes: Obtain the original checksum; wherein the original checksum is obtained by performing a checksum calculation on the multi-source real-time park data using a preset checksum algorithm; Based on the verification algorithm, the coarse-verified IoT data is verified to obtain the actual verification code; The original check code and the calculated check code are compared to obtain the check calculation result; If the verification calculation result meets the preset verification conditions, the coarse verification IoT data is determined as the corresponding fine verification IoT data.

[0011] According to some embodiments of this application, the fine verification processing of the corresponding coarse-verified IoT data based on the IoT data type to obtain fine-verified IoT data of various IoT data types includes: The coarse-calibrated IoT data and the IoT data type corresponding to the coarse-calibrated IoT data are input into a pre-trained IoT data calibration model, so as to perform fine calibration on the coarse-calibrated IoT data through the IoT data calibration model to obtain fine calibration results. If the fine verification result reflects the absence of the coarse verification IoT data, retrieve historical IoT data of the same IoT data type from the pre-built historical IoT database; Based on the historical IoT data of the same IoT data type, the coarse-verified IoT data is interpolated and completed to obtain the corresponding fine-verified IoT data.

[0012] According to some embodiments of this application, the step of predicting the state evolution of park items based on the standardized IoT data to obtain item prediction data corresponding to each park item includes: Multiple candidate item evolution prediction models are obtained; wherein each item evolution prediction model is used to predict the evolution of one of the target items. Based on the IoT data type corresponding to the standardized IoT data, the target item evolution prediction model is determined from multiple candidate item evolution prediction models; The standardized IoT data is input into the corresponding target item evolution prediction model to predict the state evolution of items in the park, thereby obtaining the item prediction data.

[0013] According to some embodiments of this application, the step of inputting the standardized IoT data into the corresponding target item evolution prediction model to predict the state evolution of park items, and obtaining the item prediction data, includes: The standardized IoT data is input into the corresponding target item evolution prediction model; wherein, the evolution prediction type corresponding to the standardized IoT data includes item numerical regression type or item event probability type; When the evolution prediction type is the item numerical regression type, the target item evolution prediction model performs numerical regression prediction based on the standardized IoT data to obtain item numerical prediction data as the item prediction data. When the evolution prediction type is the item event probability type, the event probability is predicted based on the standardized IoT data by the target item evolution prediction model, and the event occurrence probability is obtained as the item prediction data.

[0014] According to some embodiments of this application, the step of inputting the standardized IoT data into the corresponding target item evolution prediction model to predict the state evolution of park items, and obtaining the item prediction data, includes: Based on the item attributes corresponding to the target item, determine the confidence conditions for item evolution prediction; The standardized IoT data is input into the corresponding target item evolution prediction model to predict the state evolution of items in the park, thereby obtaining candidate prediction data and prediction confidence corresponding to the candidate prediction data; In response to the prediction confidence level satisfying the item evolution prediction confidence condition, the candidate prediction data is determined as the item prediction data.

[0015] The method for rendering a 3D model of a park according to a second aspect embodiment of this application, applied to a target terminal, includes: Determine the model display requirements, terminal performance parameters, and terminal screen parameters of the target terminal; The three-dimensional model of the park obtained by the modeling method of any one of the embodiments of the first aspect of this application; The rendering operation is performed on the 3D model of the park based on the model display requirements, the terminal performance parameters, and the terminal screen parameters.

[0016] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the modeling method for a 3D model of a park as described in any one of the embodiments of the first aspect of this application, or the rendering method for a 3D model of a park as described in the embodiments of the second aspect of this application.

[0017] Fourthly, embodiments of this application provide a computer-readable storage medium storing a program that is executed by a processor to implement the modeling method for a 3D park model as described in any one of the embodiments of the first aspect of this application, or the rendering method for a 3D park model as described in the embodiments of the second aspect of this application.

[0018] The modeling and rendering method for the three-dimensional model of the park according to the embodiments of this application, as well as the electronic device and medium, have at least the following beneficial effects: The 3D modeling method for a park according to embodiments of this application is applied to a smart park system. The smart park system includes IoT devices, edge computing nodes, and a data platform deployed in the target park, as well as a data prediction module and a model building module deployed on a cloud server. The 3D modeling method requires first collecting multi-source real-time park data from various park items in the target park using IoT devices; then performing data standardization operations on the multi-source real-time park data to obtain standardized IoT data; uploading the standardized IoT data to the data prediction module on the cloud server; in the data prediction module, predicting the state evolution of park items based on the standardized IoT data to obtain item prediction data corresponding to each park item; and in the model building module, constructing a 3D model based on the standardized IoT data, item prediction data, and a pre-fabricated park model to obtain the 3D model of the target park. This allows for the construction of a more accurate and real-time 3D park model that reflects the park's state.

[0019] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0020] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which: Figure 1 A flowchart illustrating the modeling method for a 3D model of a park provided in this application embodiment; Figure 2 Another flowchart illustrating the modeling method for the 3D model of the park provided in this application embodiment; Figure 3Another flowchart illustrating the modeling method for the 3D model of the park provided in this application embodiment; Figure 4 Another flowchart illustrating the modeling method for the 3D model of the park provided in this application embodiment; Figure 5 Another flowchart illustrating the modeling method for the 3D model of the park provided in this application embodiment; Figure 6 Another flowchart illustrating the modeling method for the 3D model of the park provided in this application embodiment; Figure 7 Another flowchart illustrating the modeling method for the 3D model of the park provided in this application embodiment; Figure 8 Another flowchart illustrating the modeling method for the 3D model of the park provided in this application embodiment; Figure 9 Another flowchart illustrating the modeling method for the 3D model of the park provided in this application embodiment; Figure 10 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0021] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0022] In the description of this application, "several" means one or more, "more than" means two or more, "greater than," "less than," and "exceeding" are understood to exclude the stated number, while "above," "below," and "within" are understood to include the stated number. The use of "first" and "second" in the description is merely for distinguishing technical features and should not be construed as indicating or implying relative importance, or implicitly indicating the number of indicated technical features, or implicitly indicating the order of the indicated technical features.

[0023] In the description of this application, it should be understood that the orientation descriptions, such as up, down, left, right, front, and back, are based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0024] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0025] In the description of this application, it should be noted that, unless otherwise explicitly defined, terms such as "setting," "installation," and "connection" should be interpreted broadly. Those skilled in the art can reasonably determine the specific meaning of the above terms in this application based on the specific content of the technical solution. Furthermore, the identification of specific steps in the following text does not imply a limitation on the order of steps or execution logic. The execution order and logic between each step should be understood and inferred from the content described in the embodiments.

[0026] In the construction and development of smart parks, building a 3D model that can realistically and in real-time reflect the park's status has become a key technological requirement for improving management efficiency. However, related technologies face a series of technical problems in this field, which restrict their in-depth application and effectiveness in real-world scenarios.

[0027] At the data acquisition and transmission level, traditional technical solutions suffer from significant real-time performance and compatibility bottlenecks. IoT devices such as sensors and cameras deployed within the park often employ diverse communication protocols, such as Modbus and OPC UA. These protocols lack natural interoperability, necessitating customized gateway devices for protocol conversion in the data acquisition system. This process not only increases hardware costs and system complexity but also prolongs the deployment cycle. Simultaneously, the network infrastructure upon which data transmission relies, such as 4G or early Wi-Fi technologies, is prone to high latency and packet loss in complex park environments. This prevents the data flow from the acquisition end to the processing end from meeting the real-time requirements of seconds or even milliseconds, creating a fundamental obstacle to subsequent real-time modeling and monitoring.

[0028] In terms of building and updating 3D models, existing technologies generally rely on manual modeling or static Building Information Modeling (BIM). While this method can create high-precision models, its production cycle can take weeks or even months, and it is costly. More importantly, when the physical state of the park changes, such as equipment relocation or the addition of new buildings, the entire model needs to be rebuilt, resulting in extremely low update efficiency. This leads to a severe disconnect between the digital model and the physical world, making it unreliable for real-time management and decision-making. There is also an irreconcilable contradiction between model accuracy and system performance. When high-precision models run on ordinary terminal devices, insufficient computing and rendering resources often result in screen lag and interactive stuttering, severely impacting the user experience.

[0029] In the field of data processing and analysis, traditional technologies are also proving inadequate. The park generates a massive amount of data daily, including diverse heterogeneous data such as sensor readings, video streams, and equipment logs. Existing solutions mostly employ a centralized cloud processing model, uploading all raw data to the cloud. This not only consumes significant network bandwidth but also places enormous computational pressure on cloud servers, leading to increased data processing latency. Regarding data analysis methods, traditional technologies are largely limited to basic statistical queries and simple threshold alarms, lacking the ability to deeply integrate and correlate multi-source data. They cannot uncover hidden patterns within the data, such as the intrinsic relationship between equipment operating efficiency and environmental parameters, and are even less capable of advanced intelligent analysis functions such as predicting equipment failures. This leaves management decisions still at a rudimentary stage, relying heavily on human experience.

[0030] Furthermore, the overall architecture of the property park modeling system suffers from deficiencies in scalability and adaptability. Many existing solutions employ a tightly coupled, integrated design, with functional modules deeply bound together. When the park expands or new monitoring equipment needs to be added, the expansion of the embodiments in this application often requires hardware redeployment and large-scale software reconstruction, a cumbersome, time-consuming, and costly process. Uneven network coverage is also a prominent issue; a single network standard is difficult to adapt to all areas within the park, and data interruptions are prone to occur in areas with weak signals, such as underground parking garages and remote corners, affecting the continuity and integrity of the digital twin model data.

[0031] The aforementioned deficiencies in the real-time performance and compatibility of data acquisition, low efficiency in updating 3D models and poor rendering performance, weak data processing capabilities and lack of intelligent analysis, as well as the lack of flexibility in system architecture and uneven network coverage, have made it difficult for the current 3D model solution for industrial parks to achieve the true management goals of "real-time, accurate, intelligent, and highly adaptable". This clarifies the direction and necessity for technical improvement in this invention.

[0032] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes a modeling and rendering method, electronic equipment, and media for a 3D model of a park, thereby constructing a 3D model of the park that can more accurately and in real-time reflect the park's status.

[0033] The following explanation is based on the accompanying drawings.

[0034] The modeling method for a 3D model of a park according to embodiments of this application is applied to a smart park system. The smart park system includes IoT devices, edge computing nodes, and a data platform deployed in the target park, as well as a data prediction module and a model building module deployed on a cloud server. Notably, the smart park system constructs a collaborative technical architecture integrating sensing, transmission, computing, analysis, and presentation. Its core lies in accurately and in real-time mapping the operational status of the physical park to the digital space. This system, through the rationally distributed IoT devices, edge computing nodes, and data platform in the target park, and the data prediction and model building modules deployed on a remote cloud server, forms a hierarchical and functionally complementary organic whole.

[0035] Reference Figure 1 The modeling method for the 3D model of the park in this application embodiment may include: Step S101: Collect multi-source real-time park data for various park items in the target park through IoT devices; Step S102: Perform data standardization operations based on multi-source real-time park data to obtain standardized IoT data; Step S103: Upload standardized IoT data to the data prediction module on the cloud server; Step S104: In the data prediction module, the state evolution prediction of park items is performed based on standardized IoT data to obtain the item prediction data corresponding to each park item. Step S105: In the model building module, a three-dimensional model is built based on standardized IoT data, object prediction data, and park model prefabrication to obtain the three-dimensional model of the target park.

[0036] The 3D modeling method for smart parks according to embodiments of this application addresses core pain points in smart park construction by establishing a complete technical closed loop from data acquisition to model rendering. The method first uses various IoT devices deployed in the target park to collect multi-source real-time data on buildings, equipment, and the environment. This step directly addresses the issues of insufficient real-time performance and compatibility in data acquisition. Its key lies in the fact that the IoT devices integrate multi-protocol automatic adaptation technology, enabling seamless connection to sensors of different standards. Data aggregation can be completed without customized gateways, ensuring broad coverage and low latency in data acquisition from the source.

[0037] In step S101 of some embodiments, multi-source real-time park data is collected for various park items in the target park through IoT devices; It's important to note that comprehensive perception of the physical world is achieved through IoT devices deployed throughout the park. These devices include temperature and humidity sensors installed inside buildings, vibration monitors attached to mechanical equipment, high-definition cameras distributed in public areas, and smart meters deployed in the pipeline system. They continuously collect operational status data from various items within the park at preset frequencies, forming a raw data stream containing multi-dimensional information such as equipment parameters, environmental indicators, energy consumption, and personnel flow. The key to this step lies in the diversity of device types and the extensive deployment, ensuring a complete picture of the park's operation.

[0038] According to some embodiments of this application, step S101, which involves collecting multi-source real-time park data for various park items in a target park using an Internet of Things (IoT) device, may include: Outdoor video stream data, mobile device data in the park, and key equipment data in the park are collected as coarse-grained verification IoT data for time-sensitive requirements. Indoor video stream data, dense access signals from user terminals, and indoor environmental sensing signals are collected as coarse-grained verification IoT data for reliable demand types. Collect corner sensing signals, object safety status signals, and park asset tracking signals as coarse-grained verification IoT data for reachability requirements.

[0039] In the data acquisition phase, this embodiment of the application classifies the acquired multi-source real-time campus data into three types based on different data characteristics and application scenarios, and matches a corresponding transmission strategy for each type. This classification acquisition method can more effectively utilize network resources and ensure that different types of data can receive appropriate transmission guarantees.

[0040] First, this application categorizes outdoor video stream data, campus mobile device data, and campus key equipment data into time-sensitive data types. Outdoor video stream data mainly comes from high-definition cameras deployed on the main roads, entrances and exits, and public areas of the campus; this data requires real-time monitoring and rapid response. Campus mobile device data includes real-time location information and environmental perception data transmitted by mobile equipment such as inspection robots and drones. Campus key equipment data refers to the operating parameters of equipment with extremely high real-time requirements, such as the working status of precision instruments and equipment indicators in the core computer room. A common characteristic of these data is that they all need to be transmitted to the processing center quickly and promptly; any delay may affect the timeliness of decision-making.

[0041] Secondly, this application's embodiments categorize indoor video stream data, dense user terminal access signals, and indoor environmental sensing signals into reliable demand-type data. Indoor video stream data originates from surveillance cameras in indoor areas such as office buildings and production workshops. Dense user terminal access signals refer to data generated by numerous employees' laptops, mobile phones, and other terminal devices in densely populated areas such as offices and meeting rooms. Indoor environmental sensing signals include environmental parameters such as temperature, humidity, and lighting in offices. A common characteristic of these types of data is the high requirement for connection stability and reliability, necessitating stable transmission quality even in environments with densely packed devices.

[0042] Finally, this application embodiment categorizes park corner sensing signals, object safety status signals, and park asset tracking signals as reachability requirement type data. Park corner sensing signals come from sensors distributed in network coverage edge areas such as underground pipe networks and remote green belts, including data such as environmental monitoring and manhole cover status. Object safety status signals refer to safety-related data such as fire-fighting facility pressure and electrical box status. Park asset tracking signals are location tracking information for assets such as materials and vehicles. The common characteristic of these data is that they do not require high transmission rates, but need to ensure reliable transmission even in network coverage edge areas.

[0043] By employing this categorized data collection method, the embodiments of this application can more accurately match data characteristics with network resources. Time-sensitive data prioritizes transmission speed, reliable data focuses on connection stability, and reachable data primarily addresses coverage issues. This differentiated processing approach not only meets the specific needs of different services but also improves the overall system's resource utilization efficiency, laying a solid foundation for subsequent data processing and business applications.

[0044] In step S102 of some embodiments, data standardization is performed based on multi-source real-time park data to obtain standardized IoT data; It's important to note that standardizing the collected raw data is a crucial step in ensuring data quality and usability. Because devices from different manufacturers and models may use varying data formats and communication protocols, the raw data suffers from inconsistencies in format and units. Data standardization first involves parsing and decoding the multi-source data, then cleaning to remove outliers and noise, followed by format conversion and unit standardization, and finally, reorganization according to a predefined data model. This process transforms the chaotic raw data into standardized IoT data with a clear structure and consistent format, laying the foundation for subsequent analysis and processing.

[0045] Reference Figure 2 According to some embodiments of this application, the smart park system also includes edge computing nodes and a data communication network deployed in the target park. Step S102 performs data standardization operations based on multi-source real-time park data to obtain standardized IoT data, which may include: Step S201: Perform coarse verification processing on multi-source real-time park data to obtain coarse verification IoT data of various IoT data types; Step S202: Transmit coarse-verification IoT data of various IoT types to the edge computing node through the data communication network; Step S203: In the edge computing node, the corresponding coarse-verified IoT data is fine-verified based on the IoT data type to obtain fine-verified IoT data of multiple IoT data types. Step S204: Perform data fusion operation on the precisely verified IoT data of each IoT data type through the data platform to obtain standardized IoT data.

[0046] In step S201 of some embodiments, coarse verification processing is performed on multi-source real-time park data to obtain coarse verification IoT data of various IoT data types. It should be noted that the collected multi-source real-time campus data first undergoes coarse verification. This process is mainly completed at the data acquisition terminal or a nearby gateway device, and its core task is to perform preliminary screening and filtering of the data. Specifically, coarse verification checks the basic integrity of the data, verifies whether the data format meets expectations, and identifies and marks values ​​that clearly exceed reasonable ranges. For example, temperature sensor readings from step S1000℃ or data from devices experiencing transmission interruptions will be identified at this stage. This stage uses a relatively simple verification algorithm to ensure processing speed and reduce hardware resource requirements.

[0047] Reference Figure 3 According to some embodiments of this application, step S201 performs coarse verification processing on multi-source real-time park data to obtain coarsely verified IoT data of various IoT data types, which may include: Step S301: Perform integrity screening on the multi-source real-time park data to obtain the integrity screening results; Step S302: If the integrity screening result meets the preset integrity screening conditions, the rationality screening of multi-source real-time park data is carried out through a predetermined normal IoT value range to obtain the rationality screening result. Step S303: If the rationality screening results meet the preset rationality screening conditions, the multi-source real-time park data is determined as the corresponding coarse verification IoT data according to the IoT data type of the multi-source real-time park data.

[0048] In some embodiments, step S301 involves performing integrity screening on multi-source real-time park data to obtain integrity screening results. It should be noted that in the initial stage of data processing, this embodiment performs coarse verification on the collected multi-source real-time campus data. This process begins with integrity screening. This embodiment checks whether each incoming data packet has a complete structure, verifies the existence of necessary data fields, and confirms whether the data length meets the expected specifications. For example, for a device status data packet, this embodiment checks whether its key fields such as timestamp, device identifier, and measurement value are complete. This screening can quickly identify data loss or data packet corruption caused by network fluctuations or device malfunctions during transmission.

[0049] In step S302 of some embodiments, if the integrity screening result meets the preset integrity screening conditions, the rationality screening of multi-source real-time park data is performed through a predetermined normal IoT value range to obtain the rationality screening result; It should be noted that after the data passes the integrity screening, this embodiment further performs a reasonableness screening. This step relies on a pre-determined normal IoT value range, which is set based on device specifications, historical operating data, and physical laws. This embodiment compares the value of each data item with the corresponding reasonable range to identify outliers that significantly deviate from the normal range. For example, indoor temperature readings appearing at tens of degrees below zero or hundreds of degrees below zero will be marked as unreasonable data. This screening mainly targets obviously erroneous data caused by momentary sensor failures or external interference.

[0050] In step S303 of some embodiments, if the rationality screening result meets the preset rationality screening conditions, the multi-source real-time park data is determined as the corresponding coarse verification IoT data according to the IoT data type of the multi-source real-time park data.

[0051] It should be noted that data that has completed the rationality screening enters the classification and confirmation stage. In this embodiment, the data is categorized into different IoT data types based on its source and characteristics. For example, video stream data from high-definition cameras is classified as time-sensitive demand type, data from indoor environmental sensors is labeled as reliable demand type, and data from monitoring equipment in remote areas is classified as reachable demand type. This classification process provides a basis for subsequent data transmission and processing strategy selection.

[0052] It's important to note that the entire coarse validation process forms a progressive filtering mechanism. Integrity screening ensures basic data usability, rationality screening filters out obvious outliers, and the final classification indicates the subsequent processing path for the data. This hierarchical validation approach guarantees a certain level of data processing quality while avoiding overly complex calculations at the data acquisition end, which aligns with the limited resources of edge devices.

[0053] Through this coarse verification process, the embodiments of this application can complete basic quality control at the initial stage of data generation, reducing the burden on subsequent fine verification and in-depth processing. At the same time, this processing mechanism also improves the system's response speed, ensuring that large amounts of real-time data can quickly pass through initial screening and enter subsequent processing stages. This design achieves a good balance between ensuring data quality and processing efficiency.

[0054] In step S202 of some embodiments, coarse-check IoT data of various IoT types are transmitted to the edge computing node via a data communication network; It should be noted that data is transmitted through a data communication network deployed within the park. This network typically employs a hybrid networking approach, combining wired and wireless transmission technologies to ensure the reliability and real-time nature of data transmission. Different types of IoT data are allocated different transmission priorities and bandwidth resources based on their characteristics and importance. For example, security monitoring data may be given a higher transmission priority, while environmental monitoring data can adopt a more lenient transmission strategy. This step ensures that data can be delivered from the collection point to the edge computing node in a timely and stable manner.

[0055] Reference Figure 4 According to some embodiments of this application, the IoT data types include timeliness requirement types, reliability requirement types, and reachability requirement types; the data communication network includes wide-area high-speed backbone networks, indoor high-density access networks, and long-distance low-power IoT networks; step S202, through the data communication network, transmits coarse-checked IoT data of various IoT data types to the edge computing node, and may include: Step S401: Transmit coarse-verification IoT data of time-sensitive requirements to edge computing nodes through a wide-area high-speed backbone network; Step S402: Transmit coarse-verification IoT data of reliable requirement type to edge computing node through indoor high-density access network; Step S403: Transmit coarse-verification IoT data of the reachability requirement type to the edge computing node via a long-distance low-power IoT network.

[0056] In the data transmission stage, this application adopts a classification transmission strategy based on the different characteristics of IoT data. The core of this strategy lies in identifying the essential needs of the data and matching them with the most suitable network technology. Specifically, this application divides IoT data into three basic types: time-sensitive data with strict requirements for transmission speed, reliable data with high requirements for connection stability, and reachable data with specific coverage requirements. This classification method ensures that each type of data receives the most suitable transmission guarantee.

[0057] In step S401 of some embodiments, coarse-verification IoT data of time-sensitive demand type is transmitted to edge computing nodes through a wide-area high-speed backbone network; It should be noted that for data requiring timely processing, this embodiment of the application chooses to transmit it via a wide-area high-speed backbone network. This type of data typically includes high-definition video surveillance footage, real-time equipment operating parameters, and emergency command information. The wide-area high-speed backbone network is built upon advanced communication technologies such as 5G, featuring high bandwidth and low latency, ensuring that data reaches edge computing nodes quickly and promptly. For example, when an emergency occurs within the park, footage captured by on-site high-definition cameras needs to be transmitted in real-time through this network to the processing center so that management personnel can make rapid decisions.

[0058] In step S402 of some embodiments, coarse-verification IoT data of reliable requirement type is transmitted to the edge computing node through an indoor high-density access network; It's important to note that reliable data requirements are primarily transmitted via indoor high-density access networks. This type of data mainly originates from fixed devices in indoor environments such as office areas and production workshops, including office terminal data, indoor security information, and production line status data. Indoor high-density access networks, based on technologies such as Wi-Fi 6, possess high concurrency connection capabilities and anti-interference characteristics, maintaining stable connection quality even in densely populated environments. This network ensures that a large number of indoor devices can maintain reliable data transmission simultaneously, preventing data loss or delays due to an excessive number of connected devices.

[0059] In some embodiments, step S403 involves transmitting coarse-verified IoT data of the reachability requirement type to an edge computing node via a long-distance low-power IoT network.

[0060] It's important to note that data transmission for reachable data types relies on long-range, low-power IoT networks. This type of data primarily originates from widely distributed, remotely located sensing devices, including environmental monitoring data, smart meter readings, and infrastructure status information. Long-range, low-power IoT networks, based on technologies such as LoRa, feature long transmission distances and low power consumption, enabling them to cover areas difficult for traditional networks to reach. For example, soil moisture sensors distributed on the edge of a campus or water level monitoring devices installed in remote locations can transmit data to edge computing nodes via this network.

[0061] It should be understood that this categorized transmission mechanism, by allocating appropriate network resources to different types of data, ensures both the transmission quality of critical services and improves the utilization efficiency of network resources. The high-speed backbone network focuses on handling services with high real-time requirements, the indoor access network ensures connection reliability in dense environments, and the long-range IoT network solves the communication problems in coverage blind spots. The three networks each perform their respective functions, complementing each other to form a complete campus data transmission system.

[0062] In actual operation, this network architecture can also be dynamically adjusted according to changes in business needs. For example, during special periods, the network priority of certain areas can be temporarily increased to ensure the transmission quality of important data. Simultaneously, this embodiment continuously monitors the operational status of each network, promptly identifying and addressing potential network problems to ensure the stability and reliability of the entire data transmission process. This flexible and reliable network architecture provides crucial support for the normal operation of the smart park system.

[0063] In step S203 of some embodiments, in the edge computing node, the corresponding coarse-verified IoT data is subjected to fine-verification processing based on the IoT data type to obtain fine-verified IoT data of multiple IoT data types. It's important to note that the received coarse-check data undergoes fine-check processing at the edge computing nodes. Compared to coarse-check, fine-check employs more complex and refined verification algorithms. It combines historical operational data from the devices to establish a dynamic data quality assessment model, performing multi-dimensional analysis and verification of the data. For example, for device operational data, fine-check not only checks the reasonableness of instantaneous values ​​but also analyzes whether the data's changing trends conform to the device's operational patterns. Simultaneously, fine-check performs cross-validation on different data sources to ensure data consistency and reliability. This process can identify more subtle data anomalies that are difficult to detect in coarse-check.

[0064] Reference Figure 5 According to some embodiments of this application, step S203 performs fine verification processing on the corresponding coarse-verified IoT data based on the IoT data type to obtain fine-verified IoT data of various IoT data types, which may include: Step S501: Obtain the original check code; wherein, the original check code is obtained by a preset check algorithm to verify and calculate the multi-source real-time park data; Step S502: Perform verification calculation on the coarse verification IoT data based on the verification algorithm to obtain the actual verification code; Step S503: Compare the original check code and the calculated check code to obtain the check calculation result; Step S504: If the verification calculation result meets the preset verification conditions, the coarse verification IoT data is determined as the corresponding fine verification IoT data.

[0065] In some embodiments, step S501 involves obtaining the original verification code; wherein the original verification code is obtained by performing verification calculations on multi-source real-time campus data using a preset verification algorithm. It should be noted that in the initial step of the fine verification process, this embodiment requires obtaining the original checksum. This original checksum is generated at the initial stage of data acquisition. Specifically, after the IoT device acquires the raw data, it immediately performs a calculation on the data using a preset verification algorithm, and the result is the original checksum. This original checksum is packaged and transmitted together with the raw data, and its function is to serve as a true record of the data in its source state, providing a benchmark reference for subsequent integrity verification.

[0066] According to some specific embodiments of this application, in the scenario of IoT data verification in smart parks, a suitable verification algorithm needs to balance computational efficiency, error detection capability, and resource consumption. The following are several applicable verification algorithms.

[0067] Firstly, the Cyclic Redundancy Check (CRC) algorithm. The CRC algorithm is particularly suitable for verifying IoT data transmission. This algorithm generates a short checksum by performing polynomial division on the data packet. CRC-16 and CRC-32 are two commonly used variants, with CRC-16 providing a 16-bit checksum and CRC-32 providing a 32-bit checksum. The advantages of the CRC algorithm are its high computational efficiency and low resource consumption, making it suitable for running on IoT devices with limited computing power. It effectively detects burst errors and has a good ability to identify consecutive bit errors caused by interference during transmission. In a campus environment, the CRC-16 algorithm is suitable for devices with medium data volumes such as sensors and meters, while CRC-32 can be considered for large data volume transmissions such as video streams.

[0068] Secondly, checksums are a relatively practical and error-resistant verification method. They generate a checksum by adding or XORing all bytes in the data packet. This method requires minimal computation and has low performance requirements, making it suitable for low-power devices with extremely limited resources, such as LoRa terminals and battery-powered sensors. However, checksums have relatively weak error detection capabilities, only detecting certain types of errors. They are suitable for scenarios where reliability requirements are not extremely high, such as environmental monitoring and status reporting of non-critical data.

[0069] Thirdly, hash algorithms. For data with high security requirements, such as access control and security alarms, lightweight hash algorithms can be considered. MD5 and SHA-1 are two common choices, generating unique digital fingerprints with strong collision resistance. These algorithms are relatively complex to compute and are suitable for execution on edge computing nodes or gateways to verify data integrity and authenticity. In campus systems, critical security data and control commands can be strengthened using these algorithms.

[0070] Third, XOR check. The checksum is obtained through byte-by-byte XOR operations. The calculation is extremely simple, making it suitable for ultra-low power devices and small data packet verification. Although its error detection capability is limited, it is still applicable to monitoring data with small volume and low value, such as temperature sensors, humidity sensors, and other routine environmental monitoring.

[0071] In practical applications, the embodiments of this application can adopt a layered verification strategy: preliminary verification is performed on the device side using computationally simple checksums or XOR checks; complete verification is performed on the edge computing nodes using cyclic redundancy check; and final verification of critical data is performed on the cloud using hash algorithms. This layered verification can ensure both overall system efficiency and data reliability, while also taking into account the resource constraints of different devices.

[0072] It should be understood that when selecting a specific verification method, factors such as data packet size, device computing power, power consumption limitations, and reliability requirements must be considered, and appropriate verification schemes should be flexibly configured in different application scenarios within the park.

[0073] In some embodiments, step S502 involves performing verification calculations on the coarse-verification IoT data based on a verification algorithm to obtain the actual verification code. It should be noted that in this embodiment, the same verification calculation is performed on the received coarse-check IoT data at the edge computing node. This process is completely consistent with the calculation for generating the original checksum, using the same preset verification algorithm. By performing algorithmic calculations on the currently received data content, a new checksum value, i.e., the actual checksum, is obtained. The purpose of this step is to verify whether the data has maintained its integrity during transmission, ensuring that the data has not undergone any unexpected changes from sending to receiving.

[0074] In some embodiments, step S503 involves comparing the original check code and the calculated check code to obtain the check calculation result. It should be noted that after obtaining the calculated checksum, this embodiment of the application proceeds to the comparison stage. In this step, the calculated checksum is precisely compared with the initially obtained original checksum. The comparison result of the two checksums directly reflects the integrity status of the data during transmission. If the two checksums are completely identical, it indicates that the data has not changed at all during the entire transmission process from acquisition to reception; if there are differences, it indicates that the data may have been corrupted or erroneous during transmission.

[0075] In step S504 of some embodiments, if the verification calculation result meets the preset verification conditions, the coarse verification IoT data is determined as the corresponding fine verification IoT data.

[0076] It should be noted that the embodiments of this application make judgments based on the comparison results. When the verification calculation result meets the preset verification conditions, which usually means that the two check codes match perfectly, the embodiments of this application determine the corresponding coarse-verified IoT data as fine-verified IoT data. This verified data will be marked as high-quality data and enter the subsequent data processing flow. For data that fails verification, the embodiments of this application will mark it as unreliable data and process it accordingly according to preset strategies, such as discarding it or recording an anomaly log.

[0077] This fine-grained verification process adds a crucial layer of assurance to data quality through algorithmic validation. Compared to the basic screening in the coarse-grained verification stage, fine-grained verification provides a higher level of data integrity guarantee, ensuring that data entering the core processing stage has a reliable quality foundation. This verification mechanism is particularly suitable for application scenarios with high requirements for data accuracy, providing key technical support for the reliable operation of smart park systems.

[0078] Reference Figure 6 According to some embodiments of this application, step S203 performs fine verification processing on the corresponding coarse-verified IoT data based on the IoT data type to obtain fine-verified IoT data of various IoT data types, which may include: Step S601: Input the coarse-calibrated IoT data and the IoT data type corresponding to the coarse-calibrated IoT data into the pre-trained IoT data calibration model, so as to perform fine calibration on the coarse-calibrated IoT data through the IoT data calibration model and obtain the fine calibration result. Step S602: If the fine verification result reflects the absence of coarse verification IoT data, retrieve historical IoT data of the same type from the pre-built historical IoT database. Step S603: Based on historical IoT data of the same type, interpolate and complete the coarse-verification IoT data to obtain the corresponding fine-verification IoT data.

[0079] In step S601 of some embodiments, the coarse-calibrated IoT data and the IoT data type corresponding to the coarse-calibrated IoT data are input into a pre-trained IoT data calibration model so as to perform fine calibration processing on the coarse-calibrated IoT data through the IoT data calibration model to obtain fine calibration results. It should be noted that, in the fine verification process, this embodiment first inputs the coarsely verified IoT data and its corresponding data type into a pre-trained IoT data verification model. This data verification model is trained based on a large amount of historical normal data and can identify the reasonable fluctuation range and inherent change patterns of various types of data. The model performs in-depth analysis on the input coarsely verified data, evaluating its numerical rationality, consistency of change trends, and other multi-dimensional characteristics, and finally outputs the fine verification results. This process can discover complex anomaly patterns that are difficult to identify in coarse verification, such as situations where the value is within the normal range but the rate of change is abnormal.

[0080] In step S602 of some embodiments, if the fine verification result reflects the absence of coarse verification IoT data, historical IoT data of the same IoT data type are retrieved from a pre-built historical IoT database. It should be noted that when the verification results indicate data loss, this embodiment will activate a data completion mechanism. Data loss may manifest as the loss of an entire data segment or the absence of certain fields within a data packet. This embodiment will retrieve historical data of the same type from a pre-built historical IoT database based on the IoT data type of the current data. This historical database stores various IoT data accumulated during the long-term operation of the park and is organized according to multiple dimensions such as data type, time period, and device location to ensure that relevant data reference sets can be quickly found.

[0081] In step S603 of some embodiments, the coarse-verified IoT data is interpolated and completed based on historical IoT data of the same IoT data type to obtain the corresponding fine-verified IoT data.

[0082] It should be noted that after acquiring relevant historical data, this embodiment of the application performs interpolation completion. Interpolation completion is not a simple data replacement, but rather a process based on the changing patterns of similar historical data, combined with currently available data, to reconstruct the missing data content using algorithms. For example, for missing temperature sensor data, this embodiment of the application will refer to the historical temperature change curves of the same period, combined with currently known temperature readings at previous and subsequent time points, to calculate a reasonable temperature value for the missing period. This completion method can maintain the continuity and accuracy of the data to the greatest extent possible.

[0083] It is important to emphasize that the entire process of fine-tuning and completion forms a complete data quality improvement chain. Intelligent verification through pre-trained models ensures in-depth verification of data quality; historical data comparison provides a reliable basis for data completion; and scientific interpolation algorithms ultimately produce complete and usable high-quality data. This approach is particularly suitable for applications with high requirements for data continuity, such as trend analysis and predictive modeling, providing a data foundation for the refined management of smart parks.

[0084] In step S204 of some embodiments, the data fusion operation is performed on the precisely verified IoT data of each IoT data type through the data middle platform to obtain standardized IoT data.

[0085] It's important to note that the meticulously verified data of various types is then fed into a data platform for data fusion. The data platform first standardizes the format and aligns the semantics of data from different sources, eliminating data heterogeneity issues caused by equipment differences. Then, by establishing a unified data model and association rules, data from different systems are organically integrated. For example, equipment operation data is correlated with environmental monitoring data, and energy consumption data is matched with production scheduling data. This fusion process not only solves the problem of data silos but also enhances the integrity and value of information through data complementarity.

[0086] As can be seen, the layered and progressive data processing architecture of this embodiment effectively reduces the amount of invalid data transmitted and alleviates network transmission pressure by performing coarse verification at the device end. The fine verification at the edge computing nodes completes complex data quality verification close to the data source, ensuring the reliability of downstream data while avoiding concentrating all computational pressure on the cloud. Finally, the data platform's fusion processing achieves deep integration of multi-source data, providing a high-quality, standardized data foundation for subsequent data analysis and applications. The entire processing flow forms a complete closed loop from data acquisition to standardized output, ensuring that the smart park system receives accurate and reliable data support.

[0087] In some embodiments, step S103 involves uploading standardized IoT data to the data prediction module of a cloud server. It should be noted that the processed, standardized data is uploaded to the cloud. In this process, this embodiment considers data priority and real-time requirements, employing a priority transmission strategy for critical monitoring data to ensure that important information reaches the cloud in a timely manner. Simultaneously, data compression and encryption technologies ensure data security while maintaining transmission efficiency. This step establishes a reliable connection between edge devices and the cloud system, enabling data distributed across various locations to converge on the central processing platform.

[0088] In step S104 of some embodiments, in the data prediction module, the state evolution prediction of park items is performed based on standardized IoT data to obtain the item prediction data corresponding to each park item. It should be noted that the aggregated data undergoes in-depth analysis in the cloud-based data prediction module. This module utilizes machine learning algorithms and time series analysis techniques to establish state evolution models for various park items based on historical operating data and real-time status information. Through data pattern mining and recognition, this embodiment can predict potential equipment failures, assess facility lifespan, and estimate energy consumption trends, generating time-dimensional prediction data for each park item. These prediction results not only reflect the current state of the equipment but, more importantly, reveal its future trends.

[0089] Reference Figure 7 According to some embodiments of this application, in step S104, predicting the state evolution of park items based on standardized IoT data to obtain item prediction data corresponding to each park item may include: Step S701: Obtain multiple candidate item evolution prediction models; wherein, each item evolution prediction model is used to predict the evolution of a target item. Step S702: Based on the IoT data type corresponding to the standardized IoT data, determine the target item evolution prediction model from multiple candidate item evolution prediction models; Step S703: Input the standardized IoT data into the corresponding target item evolution prediction model to predict the state evolution of items in the park and obtain item prediction data.

[0090] In some embodiments, step S701 involves obtaining multiple candidate item evolution prediction models; wherein each item evolution prediction model is used to predict the evolution of a target item. It should be noted that in the initial stage of state evolution prediction, this embodiment requires the preparation of corresponding prediction model resources. This process is achieved by acquiring multiple candidate item evolution prediction models. Each prediction model is specifically trained for a particular type of park item and has different internal structures and parameter settings. For example, a prediction model for elevator operation status will focus on features such as vibration frequency and number of start-stop cycles, while a prediction model for air conditioner energy consumption will focus on parameters such as temperature, humidity, and operating time. After these models are pre-trained, they are stored in a model library, forming a set of candidate models that can be called upon.

[0091] In step S702 of some embodiments, the target item evolution prediction model is determined from multiple candidate item evolution prediction models based on the IoT data type corresponding to the standardized IoT data. It should be noted that, in determining which specific model to use, this embodiment of the application needs to analyze the currently input standardized IoT data. This process is based on matching the IoT data type corresponding to the data, because different data types represent different types of park items. This embodiment of the application parses the metadata of the data, identifies its IoT data type, and then selects the corresponding target item evolution prediction model from the candidate model set according to a preset mapping relationship. For example, when the input data belongs to the elevator operation data type, this embodiment of the application will automatically select the elevator state prediction model as the target model.

[0092] In step S703 of some embodiments, standardized IoT data is input into the corresponding target item evolution prediction model to predict the state evolution of items in the park, thereby obtaining item prediction data.

[0093] It should be noted that after selecting the target model, this embodiment of the application inputs standardized IoT data into the model for state evolution prediction. The prediction model performs feature extraction and pattern recognition on the input data, and calculates the future state evolution trend based on the learned historical patterns. This process outputs item prediction data, which may include specific indicators such as equipment remaining life assessment, failure probability, and performance degradation trend. For example, for a water pump, the prediction model may output the number of days its bearing is expected to continue operating normally, or the probability value of leakage within the next week.

[0094] It is important to clarify that the entire prediction process in this application embodies professional division of labor and collaboration. By establishing dedicated prediction models for different types of park items, the professionalism and accuracy of the predictions are ensured. An automatic model selection mechanism based on data type guarantees the automation and operational efficiency of the prediction process. This design enables the system to adapt to the complex prediction needs of various items within the park, providing reliable predictive data support for subsequent 3D visualization and operational decision-making.

[0095] Reference Figure 8 According to some embodiments of this application, step S703, which involves inputting standardized IoT data into the corresponding target item evolution prediction model to predict the state evolution of items in the park and obtaining item prediction data, may include: Step S801: Input the standardized IoT data into the corresponding target item evolution prediction model; wherein, the evolution prediction type corresponding to the standardized IoT data includes item numerical regression type or item event probability type; Step S802: When the evolution prediction type is the item numerical regression type, numerical regression prediction is performed on the basis of standardized IoT data through the target item evolution prediction model to obtain item numerical prediction data as item prediction data. Step S803: When the evolution prediction type is the item event probability type, the event probability is predicted based on the standardized IoT data through the target item evolution prediction model to obtain the item event occurrence probability as the item prediction data.

[0096] In step S801 of some embodiments, standardized IoT data is input into the corresponding target item evolution prediction model; wherein, the evolution prediction type corresponding to the standardized IoT data includes item numerical regression type or item event probability type; It should be noted that during the model prediction execution phase, this embodiment first inputs standardized IoT data into the corresponding target item evolution prediction model. In this process, this embodiment needs to clarify the type of the current prediction task, which is mainly divided into two basic types: item numerical regression type and item event probability type. The numerical regression type focuses on predicting the future values ​​of continuous variables, such as specific values ​​of temperature, pressure, and energy consumption; the event probability type focuses on the probability of discrete events occurring, such as the probability of equipment failure and abnormal alarms. This distinction determines that the model will adopt different output methods and calculation logic.

[0097] In step S802 of some embodiments, when the evolution prediction type is the item numerical regression type, the numerical regression prediction is performed on the basis of standardized IoT data through the target item evolution prediction model to obtain item numerical prediction data as item prediction data. It should be noted that when the evolution prediction type is item numerical regression, the model will perform numerical regression predictive analysis. This process is based on the input standardized IoT data, and through the data change patterns learned internally by the model, it infers the numerical change trend within a specific future time period. For example, for air conditioning energy consumption data, the model will analyze factors such as current energy consumption level, ambient temperature, and operating time to predict the energy consumption curve for the next 24 hours. The output item numerical prediction data typically includes predicted values, confidence intervals, and timestamps, providing a quantitative basis for resource scheduling and energy management.

[0098] In step S803 of some embodiments, when the evolution prediction type is the item event probability type, the event probability is predicted based on standardized IoT data by using the target item evolution prediction model to obtain the item event occurrence probability as item prediction data.

[0099] It's important to note that when the evolution prediction type is the item event probability type, the model performs event probability prediction analysis. This process is also based on the input standardized IoT data, but the model's computational objective shifts to assessing the likelihood of a specific event occurring. For example, for predicting the failure of critical equipment, the model analyzes the historical trends and current state of the equipment's operating parameters to calculate the probability of failure occurring within a future period. The output item event probability is typically expressed as a percentage and may include a confidence assessment, providing decision support for preventative maintenance and risk management.

[0100] In this way, this categorized predictive processing mechanism enables the system to flexibly respond to different predictive needs in park management. For scenarios requiring precise quantitative management, numerical regression prediction provides specific numerical guidance; for risk prevention and control scenarios, event probability prediction provides early warning basis. The two prediction methods together constitute a complete object state evolution prediction system, which not only meets the need for quantitative data in park operation, but also meets the need for risk early warning in safety operation and maintenance, providing comprehensive data support for the refined management of the park.

[0101] Reference Figure 9 According to some embodiments of this application, step S703, which involves inputting standardized IoT data into the corresponding target item evolution prediction model to predict the state evolution of items in the park and obtaining item prediction data, may include: Step S901: Determine the confidence conditions for item evolution prediction based on the item attributes corresponding to the target item; Step S902: Input the standardized IoT data into the corresponding target item evolution prediction model to predict the state evolution of items in the park, and obtain candidate prediction data and prediction confidence corresponding to the candidate prediction data; Step S903: In response to the prediction confidence level satisfying the prediction confidence condition for item evolution, the candidate prediction data is determined as the item prediction data.

[0102] In some embodiments, step S901 involves determining the confidence conditions for item evolution prediction based on the item attributes corresponding to the target item. It should be noted that, in the process of predicting the state evolution of objects, the embodiments of this application first need to set the confidence level standard for the prediction results. This step determines the confidence conditions for the object evolution prediction based on the specific attributes of the target object. Different objects have different levels of importance in park operations, and their reliability requirements also differ. For example, for critical facilities such as elevators and power supply equipment, a higher confidence threshold needs to be set to ensure that the prediction results have a high degree of reliability; while for general objects such as ordinary lighting and environmental monitoring, the confidence conditions can be appropriately relaxed. This differentiated standard setting allows the prediction system to better adapt to the actual needs of park management.

[0103] In step S902 of some embodiments, standardized IoT data is input into the corresponding target item evolution prediction model to predict the state evolution of items in the park, thereby obtaining candidate prediction data and prediction confidence corresponding to the candidate prediction data. It should be noted that, after determining the confidence conditions, this embodiment of the application inputs standardized IoT data into the target item evolution prediction model for calculation and analysis. While processing the input data, the prediction model generates two important outputs: one is candidate prediction data derived from data pattern analysis, and the other is the model's assessment of the reliability of its own prediction results, i.e., the prediction confidence level. The prediction confidence level is usually expressed numerically, reflecting the degree of credibility of the model's predictions under the current data conditions. For example, when the input data is complete and conforms to historical patterns, the model will give a high confidence level; while when the data contains noise or abnormal patterns, the confidence level will decrease accordingly.

[0104] In some embodiments, step S903 involves determining candidate prediction data as item prediction data in response to the prediction confidence level satisfying the item evolution prediction confidence condition.

[0105] It should be noted that the embodiments of this application require reliability verification of the prediction results. This process is achieved by comparing the prediction confidence level with the preset item evolution prediction confidence conditions. When the prediction confidence level meets or exceeds the set confidence conditions, the embodiments of this application formally determine the candidate prediction data as usable item prediction data, which can be safely used for subsequent 3D visualization and management decisions. If the prediction confidence level fails to meet the confidence conditions, the embodiments of this application will mark these prediction results as low-confidence data and may trigger subsequent processing procedures such as re-prediction, data review, or manual auditing.

[0106] It should be understood that this prediction mechanism, which incorporates confidence level assessment, effectively improves the quality and usability of the prediction results. By setting differentiated confidence standards for items of varying importance, the embodiments of this application can reasonably allocate resources of concern, ensuring that the prediction results for critical equipment have sufficient reliability. Simultaneously, the confidence level assessment also provides a clear quality indicator for the use of the prediction results, helping managers better understand and utilize this prediction data, thereby improving the scientific rigor and accuracy of park operation decisions.

[0107] In step S105 of some embodiments, in the model building module, a three-dimensional model is built based on standardized IoT data, object prediction data and park model prefabrication to obtain the three-dimensional model of the target park.

[0108] It's important to note that the final presentation stage of the entire process transforms the results of data processing and prediction into an intuitive and visual 3D model. The model building module first retrieves the corresponding 3D model components from the prefabricated library based on the actual type and location information of the objects in the park. Then, it binds the standardized IoT data collected in real time to the model, enabling it to accurately reflect the current actual state of the park. Simultaneously, the predicted data generated in step S104 is presented in the model in a visual manner, such as using different colors to indicate equipment health status and using dynamic curves to display energy consumption trends. The 3D park model constructed in this way not only achieves an accurate mirror of the physical world but, more importantly, incorporates predictive insights into the future, providing comprehensive decision support for park management.

[0109] The 3D model of the park in this embodiment adopts a dynamic update mechanism, which has advantages over traditional manual modeling or static models. Traditional methods require a full update of the entire model, taking up to 4 hours. In contrast, this embodiment uses prefab calls and incremental update technology to perform local updates only on changed equipment or areas, reducing the model refresh time to less than 1 minute. This update mechanism not only ensures real-time synchronization between the model and the physical environment but also reduces model maintenance costs from hundreds of thousands of yuan in traditional methods to tens of thousands of yuan, achieving significant optimization of operation and maintenance costs.

[0110] In terms of operation and maintenance management, the system achieves deep integration of 3D visualization and real-time data. When equipment malfunctions or environmental parameters exceed limits, this embodiment automatically locates and highlights the problem location in the 3D model, enabling managers to quickly identify the fault point. This function reduces fault location time from the traditional 30 minutes to less than 5 minutes, improving operation and maintenance efficiency by up to 80%. Simultaneously, this embodiment uses predictive maintenance algorithms to identify potential equipment faults 72 hours in advance, effectively avoiding production interruptions caused by sudden failures and reducing annual operation and maintenance costs for the park by 15%-20%.

[0111] This application improves the resource utilization efficiency of the park through intelligent analysis based on data mining. The embodiments of this application establish a dynamic resource allocation mechanism by analyzing the correlation between personnel flow patterns, equipment energy consumption characteristics, and environmental parameters. During peak personnel flow periods, the number of elevators in operation is automatically increased, and the brightness of streetlights is adjusted according to real-time light intensity, achieving refined management of resources such as water and electricity. This data-driven management approach reduces the park's average annual energy consumption by more than 10%, achieving both energy conservation and emission reduction goals and improving the overall operational efficiency of the park.

[0112] These technological improvements collectively constitute a complete smart park management solution. From model update mechanisms to fault location systems and resource optimization, each step demonstrates the practical benefits of technological upgrades through specific and quantifiable indicators. This solution not only addresses the efficiency bottlenecks in traditional park management but also provides reliable technical support for the sustainable development of parks through predictive maintenance and intelligent control.

[0113] The method for rendering a 3D model of a park according to an embodiment of this application, when applied to a target terminal, may include: Determine the model display requirements, terminal performance parameters, and terminal screen parameters of the target terminal; The three-dimensional model of the park obtained by the modeling method of the embodiment of this application; The rendering operation is performed on the 3D model of the park based on the model display requirements, terminal performance parameters, and terminal screen parameters.

[0114] In the initial stage of rendering the 3D model of the park, the target terminal first needs to assess its own status and requirements. This process includes determining three key parameters: model display requirements, terminal performance parameters, and terminal screen parameters. Model display requirements refer to the user's specific viewing requirements for the 3D model, such as whether they need to view the overall park layout or focus on the details of a specific device; terminal performance parameters involve the device's processing power, memory size, and graphics card performance; terminal screen parameters include display characteristics such as screen resolution, size, and pixel density. Accurate acquisition of these parameters provides a foundation for subsequent rendering optimization.

[0115] After collecting terminal parameters, this embodiment of the application needs to obtain the 3D model data to be rendered. This 3D model of the park is generated using the aforementioned modeling method and includes 3D information such as building structures, equipment models, and environmental elements, while incorporating real-time data binding and predicted state annotations. The model data is loaded from a cloud server or local cache, and the data packet size is automatically adjusted according to network conditions during transmission to ensure that complete model information can be successfully obtained under various network environments.

[0116] Upon entering the rendering phase, this embodiment of the application will perform adaptive rendering processing on the 3D model based on the terminal parameters collected in the early stage. For high-performance terminal devices, such as graphics workstations, this embodiment of the application will adopt a high-precision rendering mode, load high-resolution textures, enable dynamic lighting and shadow effects, and display the complete details of the model. For ordinary office computers or mobile terminals, this embodiment of the application will activate an optimized rendering strategy, appropriately reduce the complexity of the model, use simplified materials, and turn off some special effects to ensure the smoothness of interactive operations.

[0117] During the rendering process, this embodiment continuously monitors the terminal's operating status. When it detects excessively high device temperature, excessive memory usage, or a drop in frame rate, this embodiment dynamically adjusts rendering parameters, such as further reducing rendering quality or decreasing the number of models displayed simultaneously. This dynamic adjustment mechanism ensures that the terminal maintains a usable operating state on terminals with different performance levels, avoiding system lag or crashes caused by device overload.

[0118] The final rendering result fully considers the display characteristics of the terminal screen. This embodiment automatically adjusts the interface layout and font size according to the screen resolution and size, ensuring a good visual experience on different devices such as mobile phones, tablets, and desktops. Simultaneously, this embodiment also performs color correction based on the screen's color gamut and brightness level, ensuring the visibility and recognizability of important information. This targeted rendering process enables the 3D model of the park to effectively serve management decisions and business operations on various terminal devices.

[0119] It is worth noting that the core of the rendering operation of the 3D model of the park in this application lies in establishing an adaptive rendering mechanism, which can dynamically adjust the rendering strategy according to the actual situation of the operating environment. Upon startup, this application embodiment automatically detects the hardware performance of the terminal device, including key parameters such as processor computing power, graphics card performance, and memory capacity. Simultaneously, this application embodiment monitors the currently available network bandwidth in real time. These environmental parameters constitute the basis for rendering decisions, enabling the system to adopt corresponding rendering schemes for different hardware configurations and network conditions.

[0120] During the rendering process, this embodiment automatically adjusts the rendering precision based on the device's performance level. For lower-performance terminal devices, such as ordinary office computers or mobile terminals, this embodiment activates a simplified rendering mode. This mode reduces the device's graphics computing load by lowering the resolution of model textures, reducing the number of models displayed simultaneously, and simplifying the number of geometric faces. For example, when displaying a group of buildings, distant buildings may use simplified model versions, while only nearby buildings will be loaded with high-precision details. This hierarchical rendering strategy ensures a smooth interactive experience across various terminals.

[0121] To address the challenge of limited network bandwidth, this embodiment employs a progressive loading technique to optimize data transmission. When a user requests to view a 3D model, this embodiment prioritizes transmitting the basic model structure and low-precision textures, ensuring the user can quickly view the overall scene. Subsequently, high-precision textures and complex details continue to be loaded in the background, gradually improving scene quality through layered loading. This technique effectively avoids prolonged white screen or lag caused by waiting for large amounts of data to load, enhancing the continuity of the user experience.

[0122] Building upon rendering optimization, this application also achieves multi-terminal adaptation capabilities. By establishing a unified rendering interface and differentiated implementation schemes, the same 3D model can run normally on different devices such as desktops, laptops, tablets, and mobile phones. This application automatically identifies the device type and screen size, adjusting the interface layout and control methods to ensure an interactive experience that conforms to the user habits of each device. This cross-platform compatibility allows users to use the system without a professional graphics workstation, significantly lowering the hardware barrier.

[0123] In terms of interaction design, this application embodiment pays special attention to conforming to the usage habits of management personnel. It provides an intuitive click-based query function, allowing users to view relevant information and data reports simply by clicking on equipment or buildings in the model. This application embodiment also integrates graphical reporting tools, transforming complex operational data into easily understandable charts. These design considerations significantly reduce the learning cost for users, enabling management personnel without a professional background to quickly master the system's operation, thereby ensuring the practical effectiveness of the technical solution.

[0124] Reference Figure 10 , Figure 10 This illustration shows the hardware structure of an electronic device according to another embodiment. The electronic device may include: The processor 1001 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 1002 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1002 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1002 and is called and executed by the processor 1001 to execute the modeling method of the 3D campus model of the embodiments of this application. Input / output interface 1003 is used to implement information input and output; The communication interface 1004 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 1005 transmits information between various components of the device (e.g., processor 1001, memory 1002, input / output interface 1003, and communication interface 1004); The processor 1001, memory 1002, input / output interface 1003 and communication interface 1004 are connected to each other within the device via bus 1005.

[0125] This application also provides a computer program product, which includes a computer program. The processor of a computer device reads and executes the computer program, causing the computer device to perform the modeling method for the aforementioned 3D model of the park.

[0126] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in this disclosure and the foregoing drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “including,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatuses.

[0127] It should be understood that in this disclosure, "at least one item" means one or more, and "more than one" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0128] It should be understood that in the description of the embodiments of this application, "multiple" means two or more, "greater than", "less than", "exceeding" etc. are understood to exclude the number itself, and "above", "below", "within" etc. are understood to include the number itself.

[0129] In the several embodiments provided in this disclosure, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of 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 system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0130] The units described as separate components may or may not be physically separate. The components shown as units 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 units can be selected to achieve the purpose of this embodiment according to actual needs.

[0131] Furthermore, the functional units in the various embodiments of this disclosure 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 as a software functional unit.

[0132] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this disclosure. The aforementioned storage medium may include: a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and other media capable of storing program code.

[0133] It should also be understood that the various implementation methods provided in this application can be combined arbitrarily to achieve different technical effects.

[0134] The above is a detailed description of the embodiments of this disclosure. However, this disclosure is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this disclosure. All such equivalent modifications or substitutions are included within the scope defined by the claims of this disclosure.

Claims

1. A method for modeling a 3D model of a park, characterized in that, The method, applied to a smart park system, which includes IoT devices, edge computing nodes, and a data platform deployed in the target park, and a data prediction module and a model building module deployed on a cloud server, includes: The IoT device is used to collect multi-source real-time park data for various park items in the target park. Based on the multi-source real-time park data, data standardization operations are performed to obtain standardized IoT data; The standardized IoT data is uploaded to the data prediction module of the cloud server; In the data prediction module, the state evolution prediction of park items is performed based on the standardized IoT data to obtain the item prediction data corresponding to each park item. In the model building module, a three-dimensional model is built based on the standardized IoT data, the predicted object data, and the prefabricated park model to obtain the three-dimensional park model corresponding to the target park.

2. The method according to claim 1, characterized in that, The smart park system also includes edge computing nodes and a data communication network deployed in the target park. The process of standardizing data based on the multi-source real-time park data to obtain standardized IoT data includes: Coarse verification processing is performed on the multi-source real-time park data to obtain coarsely verified IoT data of various IoT data types; The coarse-verification IoT data of various IoT data types are transmitted to the edge computing node through the data communication network. In the edge computing node, the corresponding coarse-verified IoT data is subjected to fine-verification processing based on the IoT data type to obtain fine-verified IoT data of various IoT data types; The data platform performs data fusion operations on the precisely verified IoT data of various IoT data types to obtain the standardized IoT data.

3. The method according to claim 2, characterized in that, The IoT data types include timeliness requirement types, reliability requirement types, and reachability requirement types. The data communication network includes a wide-area high-speed backbone network, an indoor high-density access network, and a long-distance low-power IoT network. The process of transmitting the coarse-checked IoT data of various IoT data types to the edge computing node through the data communication network includes: The coarse-verification IoT data of the time-sensitive demand type is transmitted to the edge computing node through the wide-area high-speed backbone network. The coarse-verification IoT data of the reliability requirement type is transmitted to the edge computing node through the indoor high-density access network. The coarse-verified IoT data of the reachability requirement type is transmitted to the edge computing node via the long-distance low-power IoT network.

4. The method according to claim 3, characterized in that, The process of collecting multi-source real-time park data for various park items in the target park through the IoT device includes: Outdoor video stream data, park mobile device data, and park key equipment data are collected as the coarse verification IoT data for the timeliness requirement type. Indoor video stream data, dense access signals from user terminals, and indoor environmental sensing signals are collected as coarse-check IoT data for the aforementioned reliable demand type. Collect corner sensing signals, object security status signals, and park asset tracking signals as coarse-verification IoT data for the reachability requirement type.

5. The method according to claim 2, characterized in that, The coarse verification process is performed on the multi-source real-time park data to obtain coarsely verified IoT data of various IoT data types, including: The integrity screening of the multi-source real-time park data was performed to obtain the integrity screening results; If the integrity screening result meets the preset integrity screening conditions, the rationality screening of the multi-source real-time park data is performed through a predetermined normal IoT value range to obtain the rationality screening result; If the rationality screening result meets the preset rationality screening conditions, the multi-source real-time park data is determined as the corresponding coarse-verification IoT data according to the IoT data type of the multi-source real-time park data.

6. The method according to claim 5, characterized in that, The process of performing fine verification on the corresponding coarse-verified IoT data based on the IoT data type yields fine-verified IoT data of various IoT data types, including: The coarse-calibrated IoT data and the IoT data type corresponding to the coarse-calibrated IoT data are input into a pre-trained IoT data calibration model, so as to perform fine calibration on the coarse-calibrated IoT data through the IoT data calibration model to obtain fine calibration results. If the fine verification result reflects the absence of the coarse verification IoT data, retrieve historical IoT data of the same IoT data type from the pre-built historical IoT database; Based on the historical IoT data of the same IoT data type, the coarse-verified IoT data is interpolated and completed to obtain the corresponding fine-verified IoT data.

7. The method according to claim 1, characterized in that, The prediction of the state evolution of park items based on the standardized IoT data, to obtain the item prediction data corresponding to each park item, includes: Multiple candidate item evolution prediction models are obtained; wherein each item evolution prediction model is used to predict the evolution of a target item. Based on the IoT data type corresponding to the standardized IoT data, the target item evolution prediction model is determined from multiple candidate item evolution prediction models; The standardized IoT data is input into the corresponding target item evolution prediction model to predict the state evolution of items in the park, thereby obtaining the item prediction data.

8. A method for rendering a 3D model of a park, characterized in that, Applied to target terminals, including: Determine the model display requirements, terminal performance parameters, and terminal screen parameters of the target terminal; A three-dimensional model of a park obtained by the modeling method of any one of claims 1 to 7; The rendering operation is performed on the 3D model of the park based on the model display requirements, the terminal performance parameters, and the terminal screen parameters.

9. An electronic device, characterized in that, include: The system includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the modeling method for a 3D model of a park as described in any one of claims 1 to 7, or the rendering method for a 3D model of a park as described in claim 8.

10. A computer-readable storage medium, characterized in that, The storage medium stores a program, which is executed by a processor to implement the modeling method of the three-dimensional model of the park as described in any one of claims 1 to 7, or the rendering method of the three-dimensional model of the park as described in claim 8.

Images