A 5G-A-based massive internet of things device connection management method and system

Abstract

The application discloses a kind of based on 5G-A large-scale internet of things equipment connection management method and system, it is related to internet of things technical field.The method includes: obtaining the equipment characteristics and coordinates of equipment cluster, form characteristic set and coordinate set;Obtain mobile parameter set from characteristic set by equipment movement analyzer, and compensate the compensation coordinate set of the coordinates to the direction away from base station;Combining characteristic set, mobile parameter set and compensation coordinate set, by mobile signal quality analysis path evaluation and iteration optimization, obtain optimized access parameter set;According to the parameter set, equipment cluster is accessed to 5G-A internet of things.The system contains data acquisition, mobile analysis and coordinate compensation, access parameter optimization and equipment access module.The application realizes the full-dimensional adaptation of equipment static attribute, dynamic movement and spatial position, improves the connection stability and resource utilization, adapts multi-scene large-scale equipment access demand.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) technology, and more specifically to a method and system for managing large-scale IoT device connections based on 5G-A. Background Technology

[0002] The Internet of Things (IoT) is a network concept that extends the "Internet concept" to enable information exchange and communication between any two objects. It connects all objects to the Internet through information sensing devices, facilitating information exchange—that is, mutual communication between things—to achieve intelligent identification and management. 5G-A technology, as an enhanced evolution of 5G, boasts higher bandwidth, lower latency, and stronger connectivity, providing robust support for large-scale IoT device connections.

[0003] However, in practical applications, IoT devices often have characteristics such as large differences in mobility and wide distribution range. Traditional device connection management methods do not take into account the differences in device characteristics and are difficult to adapt to the dynamic mobility characteristics of devices and their different location relationships with base stations, which can easily lead to unstable device access quality and low network resource utilization. Summary of the Invention

[0004] This invention provides a method and system for managing large-scale IoT device connections based on 5G-A, aiming to solve problems such as unstable IoT connection quality, insufficient mobile device support, and bottlenecks in large-scale access caused by neglecting differences in device characteristics, lack of dynamic adaptability, and inefficient resource allocation in the prior art.

[0005] In a first aspect, this application provides a method for managing large-scale IoT device connections based on 5G-A, the method comprising:

[0006] Obtain the device characteristics and coordinates of the device cluster to be connected to the Internet of Things, and obtain the device characteristic set and device coordinate set;

[0007] Based on the equipment feature set, equipment movement analysis is performed to obtain a set of equipment movement parameters. The equipment coordinate set is then compensated to obtain a compensated equipment coordinate set. Each equipment movement parameter includes movement speed and movement distance.

[0008] Based on the device feature set, device movement parameter set, and compensation device coordinate set, 5G-A access parameters are optimized to obtain an optimized access parameter set.

[0009] According to the optimized access parameter set, the device cluster is connected to the Internet of Things using 5G-A.

[0010] Secondly, this application provides a large-scale IoT device connection management system based on 5G-A, characterized in that it includes:

[0011] The data acquisition module is configured to acquire the device characteristics and device coordinates of the device cluster to be connected to the Internet of Things, and obtain the device characteristic set and device coordinate set.

[0012] The motion analysis and coordinate compensation module is configured to perform device motion analysis based on the device feature set to obtain a device motion parameter set, and to use the device motion parameter set to compensate the device coordinate set to obtain a compensated device coordinate set, wherein each device motion parameter includes a motion speed and a motion distance;

[0013] The access parameter optimization module is configured to optimize 5G-A access parameters based on the device feature set, device movement parameter set, and compensation device coordinate set to obtain an optimized access parameter set.

[0014] The device access module is configured to connect the device cluster to the Internet of Things using 5G-A technology according to the optimized access parameter set.

[0015] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0016] By analyzing device characteristics, acquiring movement parameters, and compensating for coordinates, it can accurately adapt to the diverse device types and varying movement states in large-scale IoT. Devices with different movement characteristics can obtain suitable 5G-A access parameters, solving the problem that traditional connection management cannot cope with dynamic changes in devices and improving device access stability. With the help of device mobility analyzers, machine learning training of mobile signal quality analysis paths, and iterative optimization of access parameters, the access effect is improved from the dimensions of signal quality and resource allocation, ensuring the efficiency and reliability of data interaction of large-scale devices. By corresponding system modules and method steps one by one, a complete device connection management closed loop is constructed, which is convenient for integration and deployment on IoT platforms, forming a full-process optimization of the large-scale IoT device connection management system. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating a large-scale IoT device connection management method based on 5G-A provided in an embodiment of this application;

[0019] Figure 2 This is a schematic diagram of the structure of a large-scale IoT device connection management system based on 5G-A provided in an embodiment of this application;

[0020] Figure 3 A logical schematic diagram of a large-scale IoT device connection management system based on 5G-A provided in an embodiment of this application;

[0021] The components represented by each number in the attached diagram are explained below:

[0022] Data acquisition module 11, motion analysis and coordinate compensation module 12, access parameter optimization module 13, device access module 14. Detailed Implementation

[0023] This application provides a method and system for managing large-scale IoT device connections based on 5G-A, aiming to solve problems in the existing technology such as unstable IoT connection quality, insufficient mobile device support, and bottlenecks in large-scale access caused by ignoring differences in device characteristics, lack of dynamic adaptability, and inefficient resource allocation.

[0024] The technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0026] Figure 1 This is a flowchart illustrating a large-scale IoT device connection management method based on 5G-A provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of a large-scale IoT device connection management system based on 5G-A provided in an embodiment of this application; Figure 3 A logical diagram of a large-scale IoT device connection management system based on 5G-A provided in this application embodiment; wherein, Figure 2 The components represented by each number are described as follows: Data acquisition module 11, Motion analysis and coordinate compensation module 12, Access parameter optimization module 13, and Device access module 14.

[0027] Example 1, as Figure 1 and Figure 2As shown, this application provides a method for managing large-scale IoT device connections based on 5G-A. The method is applied to a large-scale IoT device connection management system based on 5G-A. The logic includes a data acquisition module 11, a motion analysis and coordinate compensation module 12, an access parameter optimization module 13, and a device access module 14. The method includes:

[0028] S100: Obtain the device characteristics and device coordinates of the device cluster to be connected to the Internet of Things, and obtain the device characteristic set and device coordinate set;

[0029] In this embodiment, obtaining the device characteristics and coordinates of the device cluster to be connected to the Internet of Things (IoT), and acquiring the device feature set and device coordinate set, is the basic data collection step. Here, a device cluster refers to a whole composed of multiple devices that need to be connected to the IoT; it may be similar devices within the same area or heterogeneous devices across different scenarios. For example, all security cameras in a smart park constitute a device cluster.

[0030] The device characteristics include physical attributes (such as device type, communication module model, power consumption level, and computing power), functional attributes (such as data transmission frequency, service priority, and supported communication protocols), and historical behavior attributes. These characteristics directly affect the device's connectivity requirements and adaptability. Device coordinates refer to the device's location information in physical space, such as latitude and longitude, distance or orientation relative to the base station. This information can be obtained through GPS, BeiDou positioning, or base station triangulation and is used to determine the spatial relationship between the device and the 5G-A base station, providing a basis for subsequent signal quality analysis.

[0031] The features and coordinates of all devices are integrated into device feature sets and device coordinate sets to form structured data. The feature sets are used to distinguish the connection requirements of devices, and the coordinate sets are used to determine the signal coverage environment of devices. This provides data support for subsequent on-demand optimization of access parameters and facilitates batch analysis and processing of large-scale device data by subsequent algorithms.

[0032] Step S100 in the method provided in this application embodiment includes:

[0033] Obtain the device characteristics and coordinates of the device cluster to be connected to the Internet of Things;

[0034] Integrate the equipment features and coordinates of all equipment to obtain the equipment feature set and equipment coordinate set.

[0035] In this embodiment, device features are retrieved from the device archive of the IoT management platform through the device's built-in identification module (such as IMEI or MAC address), and coordinate information is uploaded in real time through the device's built-in positioning module (such as GPS). The collected raw data is cleaned and preprocessed to remove outliers, fill in missing feature parameters, and write the data into the device feature set and device coordinate set in a unified standard to avoid noise data affecting the accuracy of subsequent analysis.

[0036] S200: Based on the equipment feature set, perform equipment movement analysis to obtain a set of equipment movement parameters, and compensate the equipment coordinate set to obtain a compensated equipment coordinate set, wherein each equipment movement parameter includes movement speed and movement distance;

[0037] Among these parameters, movement speed refers to the distance a device may move per unit time, reflecting its dynamic rate of change and serving as a key indicator for determining whether high-frequency signal adjustment is needed. Movement distance refers to the maximum straight-line distance a device may move within a certain period, used to correct spatial deviations in the device's coordinates. For example, an inspection robot in a smart park is a mobile device with a movement speed of 0.5 m / s (meaning it may move 0.5 meters per unit time). Due to its low movement speed, it does not require high-frequency signal parameter adjustment. However, the autonomous driving shuttle vehicle in the park moves at a speed of 5 m / s, exhibiting a high rate of dynamic change, requiring high-frequency signal adjustment to adapt to signal fluctuations caused by its rapid movement. Regarding movement distance, the inspection robot's inspection cycle is set to 1 hour, within which the maximum movement distance is 100 meters. Therefore, its original coordinates are compensated by 100 meters away from the base station to correct spatial deviations. Fixed environmental sensors, on the other hand, are fixed devices with a movement distance of 0 meters; their coordinates do not require compensation and can remain in their original positions.

[0038] Step S200 in the method provided in this application embodiment includes:

[0039] Each device feature in the device feature set is input into the device movement analyzer to obtain a device movement parameter set, wherein each device movement parameter includes movement speed and movement distance;

[0040] The device coordinate set is compensated using the device movement distance set within the device movement parameter set to obtain a compensated device coordinate set, wherein coordinate compensation is performed in the direction away from the 5G-A base station.

[0041] In this embodiment, the device movement analyzer is the core tool for predicting movement parameters. Essentially, it is a machine learning model trained on historical data. The training process ensures that the model can accurately output movement parameters based on device characteristics. The specific steps are as follows:

[0042] Based on historical management data of IoT devices, a set of sample device features is collected, and the maximum moving speed and maximum moving distance of devices with different sample device features during use are collected and labeled to obtain a set of sample moving speeds and a set of sample moving distances.

[0043] A device movement analyzer built based on machine learning;

[0044] The device movement analyzer is iteratively trained using the sample device feature set, sample movement speed set, and sample movement distance set until the loss converges.

[0045] In the proposed embodiments, the process of training the device mobility analyzer is based on the mapping relationship between device features and mobility parameters. When extracting data from the historical management database of IoT devices, the data to be collected includes sample device feature data and sample device mobility data. The sample device feature data includes the inherent attributes of the device, such as device type, hardware specifications, application scenario characteristics, and historical behavior tags. The sample device mobility data includes the device's maximum moving speed and maximum moving distance. After collection, the raw data also needs to be cleaned and preprocessed, outliers handled, missing values ​​filled, and normalized to standardize the data.

[0046] Machine learning refers to using machine learning algorithms to build a model that can learn and predict motion parameters from device feature data. Its core is to establish a mapping relationship between device features and motion characteristics through a data-driven approach, rather than relying on manual rules or fixed formulas. Machine learning first requires multiple features of the device as input; then, algorithms automatically mine the potential patterns between features and motion parameters from historical data; finally, it analyzes the features of new devices and outputs accurate motion parameter prediction results.

[0047] Specifically, during model training, each input sample (device feature) corresponds to a specific output (sample moving speed, moving distance). The model adjusts its parameters by comparing the difference between the prediction results and the true labels. After multiple rounds of training, the parameters are gradually corrected, and the error is continuously reduced. When the model prediction error stabilizes at an extremely low level and no longer decreases significantly, iterative training continues until the loss converges, indicating that the model has fully learned the sample patterns and has reached a usable state.

[0048] After training, the device motion analyzer predicts speed and distance with an error of no more than 10% compared to the actual values ​​when the input source is a previously trained device type. When the input source is a new, unseen device feature, it can still output reasonable predictions based on the learning patterns of similar features, predicting similar motion parameters. This process, through data-driven iterative optimization, evolves the model into an accurate predictor, providing a reliable basis for subsequent coordinate compensation and access parameter optimization.

[0049] The device coordinate set is compensated by using the device movement distance set within the device movement parameter set. This step involves spatially correcting the original coordinates by the device movement distance. The core is to reserve signal redundancy based on the potential movement range of the device to ensure that the 5G-A access parameter optimization can adapt to the dynamic position changes of the device.

[0050] Coordinate compensation refers to making targeted corrections to the original device coordinates based on the potential movement characteristics of the device, generating "compensated coordinates" that are more in line with the actual use scenario of the device. Its core purpose is to enable subsequent 5G-A access parameter optimization to adapt to the dynamic position changes of the device and avoid signal quality degradation or connection interruption caused by device movement.

[0051] The locations of IoT devices (such as mobile devices like vehicle sensors and inspection robots) are not fixed but change over time. If access parameters are optimized solely based on the "original coordinates" at the time of data collection, these parameters may no longer be applicable once the device moves. For example, signal strength weakens as the device moves away from the base station, but the parameters are not adjusted in time. Coordinate compensation, by predicting the maximum range of device movement, preemptively corrects the coordinates to the "most unfavorable signal scenario," ensuring that the parameters cover the locations the device might reach. This solves the signal instability problem caused by the dynamic location of large-scale mobile device connections.

[0052] It is worth noting that coordinate compensation in the direction away from the 5G-A base station aims to pre-determine the maximum distance the device will move in the direction away from the base station during the access period. By using coordinate compensation to adapt to this extreme situation in advance, the access parameters optimized based on the compensated coordinates can cover the farthest movement range of the device, thus avoiding signal interruption due to sudden changes in location.

[0053] S300: Optimize 5G-A access parameters based on the device feature set, device movement parameter set, and compensation device coordinate set to obtain an optimized access parameter set;

[0054] Among them, the device feature set refers to the static attributes of the device, that is, the device features of the device cluster to be connected to the Internet of Things are obtained in process S100; the device movement parameter set refers to the device movement parameter set obtained by inputting each device feature in the device feature set into the device movement analyzer in process S200; and the compensated device coordinate set refers to the compensated device coordinate set obtained by compensating the device coordinate set through the device movement parameter set in process S200.

[0055] The synergistic effect of these three elements enables access parameters to match the inherent attributes of the devices, cope with their dynamic movement, and cover changes in their spatial location. Optimizing 5G-A access parameters involves systematically searching and iteratively optimizing all possible values ​​of the access parameters to find a set of parameter configurations that achieves the optimal overall access quality for the entire device cluster. By globally optimizing 5G-A access parameters, the optimal set of parameters that achieves the best overall access quality for the device cluster can be obtained, thus finding the optimal parameter configuration that adapts to the complex needs of large-scale heterogeneous devices.

[0056] Based on the device feature set, device movement parameter set, and compensated device coordinate set, 5G-A access parameters are optimized to obtain an optimized access parameter set, including:

[0057] Randomly generate the first set of access parameters for the device cluster;

[0058] The first access parameters of each device are combined with the device characteristics and the device's moving speed and input into the mobile signal quality analysis path to obtain the first set of mobile access quality parameters.

[0059] The first access parameters of each device are combined with device characteristics and the coordinates of the compensated device and input into the mobile signal quality analysis path to obtain the first distance access quality parameter set;

[0060] Multiple mobile weights and multiple distance weights are configured based on multiple mobile speeds. The first mobile access quality parameter set and the first distance access quality parameter set are weighted and calculated to obtain the first access quality parameter set. The mean value is then calculated to obtain the first cluster access quality parameter.

[0061] Continue to randomly generate access parameter sets for iterative optimization to obtain an optimized access parameter set with the maximum cluster access quality parameters.

[0062] First, random sampling ensures that the initial parameters are not limited to a local range, providing a sufficiently broad search starting point for subsequent global optimization. Second, the first mobile access quality parameter set and the first distance access quality parameter set are obtained through mobile signal analysis paths, and the adaptability of the first access parameter set is evaluated from the dimensions of "mobility" and "spatial distance". In addition, since the influence weights of "mobility" and "spatial distance" are different for different devices, precise fusion needs to be achieved through dynamic weighting. The first mobile access quality parameter set and the first distance access quality parameter set are weighted and calculated to obtain the first access quality parameter set.

[0063] The first access parameter set refers to the randomly generated initial 5G-A access parameter combination; the first access quality parameter set refers to the comprehensive quality set obtained by weighting the "first mobile access quality parameter set" and the "first distance access quality parameter set" with mobile weight and distance weight. Each device corresponds to a comprehensive quality parameter, which reflects the overall adaptation effect of the device under the current access parameters.

[0064] For example, if device A moves at a speed of 1 m / s (the maximum movement speed of the cluster is 5 m / s), the movement weight = 1 / 5 = 0.2, and the distance weight = 1 - 0.2 = 0.8, then:

[0065] If the packet loss rate is 1.2% in a mobile scenario, then the mobile access quality is 1 - 0.012 = 98.8%.

[0066] If the packet loss rate is 0.3% in the corresponding distance scenario, then the distance access quality = 1 - 0.003 = 99.7%.

[0067] First access quality parameter = 98.8%×0.2+99.7%×0.8=19.76%+79.76%=99.52% (overall adaptation effect is excellent).

[0068] Device B moves at a speed of 5 m / s (maximum speed 5 m / s), has a movement weight of 5 / 5 = 1, and a distance weight of 0. Therefore:

[0069] If the packet loss rate is 0.4% in a high-speed mobile scenario, then the mobile access quality is 1 - 0.004 = 99.6%.

[0070] If the packet loss rate is 1.8% in the corresponding distance scenario, then the distance access quality = 1 - 0.018 = 98.2%.

[0071] The first access quality parameter = 99.6% × 1 + 98.2% × 0 = 99.6% (the overall adaptation effect is excellent).

[0072] It should be noted that the access quality parameters do not have specific physical units; they are quantitative evaluation scores used to reflect the signal quality adaptation effect, expressed as a percentage of "1 minus packet loss rate." The packet loss rate refers to the ratio of the number of data packets lost by IoT devices during data transmission through the 5G-A network to the total number of data packets sent, and this value is positively correlated with access quality.

[0073] Access quality parameters ≥99.5% (corresponding to packet loss rate ≤0.5%): Excellent access quality, almost lossless signal transmission, suitable for high reliability requirements (such as industrial control).

[0074] Access quality parameters 98%~99.5% (corresponding to packet loss rate 0.5%-2%): good access quality, occasional minor packet loss, suitable for regular data transmission (such as environmental sensing).

[0075] Access quality parameter <98% (corresponding to packet loss rate >2%): The access quality is poor, and there is a risk of frequent packet loss. Access parameters need to be optimized.

[0076] The score is essentially a comprehensive quantification of the effect of "adapting access parameters to the device's dynamic movement and spatial location". The higher the score, the more closely the current parameters match the actual device scenario, and the better the connection stability and resource utilization.

[0077] Therefore, the first access quality parameter set of the cluster is [86, 85]. The first access quality parameter set of the randomly generated device cluster can be obtained by processing the first access parameter set of the random generated device cluster according to the above method.

[0078] Secondly, calculating the mean refers to averaging the comprehensive quality parameters of all devices in the "first access quality parameter set" to obtain the "first cluster access quality parameter," which is used to quantitatively evaluate the overall adaptability of the current access parameter set to the entire device cluster. The first cluster access quality parameter is obtained by averaging the first access quality parameter set calculated above.

[0079] It is important to note that a single random parameter set is unlikely to achieve global optimum. Multiple iterations are needed to gradually approach the optimal solution. The maximum cluster access quality refers to the highest value among all access parameter sets corresponding to the "cluster access quality parameters" during the iterative optimization process. This represents the optimal level of overall access quality for the device cluster, and the corresponding parameter set is the optimized access parameter set. Finally, multiple rounds of random search and quality screening are required to overcome local optima traps and ensure that globally optimal parameters suitable for the entire device cluster are found. The optimized access parameter set refers to the combination of access parameters that maximizes the "cluster access quality parameters" after multiple rounds of iterative optimization, optimally adapting to the characteristics, mobility, and spatial location requirements of the device cluster.

[0080] The steps for constructing the mobile signal quality analysis path include:

[0081] Based on device connection data over a historical period, a set of sample access parameters, a set of sample device movement speeds, and a set of sample movement access quality parameters were collected.

[0082] Construct a machine learning-based mobile signal quality analysis path;

[0083] Using the sample access parameter set, sample device movement speed set, and sample mobile access quality parameter set, the mobile signal quality analysis path is iteratively supervised and trained until the loss converges.

[0084] It should be noted that the sample access parameter set refers to the set of access parameters actually used by the device, extracted from historical data, including signal transmission power, channel bandwidth, modulation and coding scheme, etc., which serve as input samples for model training; the sample device movement speed set refers to the set of device movement speed data corresponding to the sample access parameters, such as "0m / s (fixed device), 5m / s (low-speed mobile device), 30m / s (high-speed mobile device)," reflecting the dynamic state of the device under the corresponding access parameters; and the sample mobile access quality parameter set refers to the set of actual signal quality indicators corresponding to the sample access parameter set and movement speed set, including quantitative indicators such as packet loss rate and transmission rate, which serve as output samples for model training and are compared with the model prediction data.

[0085] The construction of a mobile signal quality analysis path is essentially a process of training a machine learning model using historical data, enabling it to assess the adaptability of access parameters to device status. The core objective is to allow the model to accurately predict device signal quality under different access parameters. When constructing a mobile signal quality analysis path, the first step is to build a knowledge base for model training, i.e., to collect sample data. When building the evaluation model framework, since the inputs are access parameters and device speed, and the output is signal quality parameters, it is a regression prediction problem. Gradient boosting trees (such as XGBoost and LightGBM) or fully connected neural network model structures can be chosen. Gradient boosting trees are suitable for small to medium-sized samples, effectively handle mixed-type features, and are highly interpretable, clearly outputting the weights of each parameter's impact on signal quality. Fully connected neural networks are more suitable for large-scale sample scenarios, capturing the complex nonlinear relationship between access parameters and device speed through a multi-layered neuron structure, especially performing better when dealing with complex interactions such as the combined impact of high power and high-speed mobility on signal quality.

[0086] Finally, iterative supervised training is performed using a set of sample access parameters, a set of sample device movement speeds, and a set of sample mobile access quality parameters. The model parameters are continuously adjusted through prediction, loss calculation, and parameter optimization until the loss converges, enabling the model to have a stable and accurate signal quality prediction capability.

[0087] In this embodiment of the application, multiple mobility weights and multiple distance weights are configured based on multiple mobility speeds, and a first mobile access quality parameter set and a first distance access quality parameter set are weighted and calculated to obtain a first access quality parameter set, including:

[0088] Calculate the ratio of each device's moving speed to its maximum moving speed, and use this as the movement weight;

[0089] The distance weight is obtained by subtracting the movement weight from 1;

[0090] By using the mobility weight and distance weight of each device, the first mobile access quality parameter and the first distance access quality parameter of each device are weighted and calculated to obtain the first access quality parameter, and the first access quality parameter set of the device cluster is obtained.

[0091] For example, when device A moves at a speed of 1 m / s and has a maximum speed of 5 m / s, the movement weight is 0.2, indicating that the signal quality of this device is less affected by mobility. The distance weight, as a complementary value, is 0.8, and is more affected by spatial distance.

[0092] Specifically, multiple mobile weights and multiple distance weights are configured based on multiple mobile speeds. The first mobile access quality parameter set and the first distance access quality parameter set are weighted and calculated to obtain the first access quality parameter set. Essentially, the weights are dynamically allocated based on the mobile characteristics of the device to achieve a precise fusion of two-dimensional quality assessment. The core is to ensure that the overall quality not only highlights the dynamic adaptation needs of high-mobile devices, but also guarantees the distance coverage effect of fixed devices.

[0093] In this process, firstly, the ratio of each device's moving speed to its maximum moving speed is calculated as the moving weight, with a value ranging from 0 to 1. A larger value indicates a more significant impact of device mobility on signal quality. Secondly, the distance weight is obtained by subtracting the moving weight from 1, forming a complementary relationship with the moving weight. A larger value indicates a more prominent impact of spatial distance on signal quality. Finally, the moving weight and distance weight of each device are used to weight and calculate the first mobile access quality parameter and the first distance access quality parameter of each device, i.e., the comprehensive quality of a single device = (mobile access quality × moving weight) + (distance access quality × distance weight). The comprehensive quality of all devices is then integrated to obtain the first access quality parameter set of the device cluster, providing a quantitative basis for evaluating the cluster adaptation effect of the current access parameter set.

[0094] For example, when device B moves at a speed of 5 m / s and has a maximum speed of 5 m / s, its movement weight is 1, indicating that the signal quality of this device is extremely affected by mobility. The distance weight, as a complementary value, is 0, and its influence from spatial distance is completely weakened.

[0095] S400: According to the optimized access parameter set, the device cluster is connected to the Internet of Things using 5G-A.

[0096] S400 applies optimized access parameters to the execution phase of actual network connection. Essentially, it transforms the "optimized access parameter set" obtained from the previous steps into specific operations for device clusters to access 5G-A IoT. The core is to enable a large number of devices to achieve stable and efficient connections based on parameters adapted to their characteristics and mobility.

[0097] In this step, firstly, parameter instructions are issued through the core network and access network equipment of the 5G-A base station based on the optimized access parameter set; secondly, each device in the device cluster completes access negotiation with the base station according to its own characteristics and optimized parameters, such as synchronization signals, channel selection, power adjustment, etc.; finally, all devices establish 5G-A connection based on the optimized parameters, access the Internet of Things and perform data transmission, ensuring that the overall access quality of the cluster reaches the optimal state, and realizing efficient collaborative communication of large-scale heterogeneous devices under the 5G-A network.

[0098] In summary, the embodiments of this application have at least the following technical effects:

[0099] This application's embodiments achieve multi-dimensional technological breakthroughs through the aforementioned end-to-end solution: On the one hand, relying on device feature analysis, motion parameter prediction, and coordinate compensation, 5G-A access parameters can accurately adapt to the static attributes, dynamic motion trends, and spatial location boundaries of devices. Highly mobile devices, by adapting to mobility characteristics in advance, solve the pain point of the traditional coarse-grained static parameter adaptation. On the other hand, through the mobile signal quality analysis path, a dual-dimensional quality assessment is achieved. Combined with dynamic weight fusion and iterative optimization, congestion and waste caused by resource allocation imbalance are avoided in large-scale concurrent device scenarios. At the same time, the machine learning-based device motion analyzer and signal quality assessment model can adapt to heterogeneous devices and complex scenarios without manual rule adjustments, and are compatible with mainstream 5G-A standards and infrastructure. Through coordinate compensation to reserve signal redundancy and global parameter optimization, a comprehensive improvement in device connection stability, resource efficiency, and scenario adaptability is achieved.

[0100] Example 2, as Figure 2 and Figure 3 As shown, based on the same inventive concept as the 5G-A-based large-scale IoT device connection management method provided in Embodiment 1, this embodiment of the invention also provides a 5G-A-based large-scale IoT device connection management system, including:

[0101] Data acquisition module 11 is configured to acquire the device characteristics and device coordinates of the device cluster to be connected to the Internet of Things, and obtain a set of device characteristics and a set of device coordinates;

[0102] The motion analysis and coordinate compensation module 12 is configured to perform device motion analysis based on the device feature set to obtain a device motion parameter set, and use the device motion parameter set to compensate the device coordinate set to obtain a compensated device coordinate set, wherein each device motion parameter includes a motion speed and a motion distance.

[0103] The access parameter optimization module 13 is configured to optimize 5G-A access parameters based on the device feature set, device movement parameter set and compensation device coordinate set to obtain an optimized access parameter set.

[0104] The device access module 14 is configured to connect the device cluster to the Internet of Things using 5G-A technology according to the optimized access parameter set.

[0105] The data acquisition module 11 is further configured to:

[0106] Obtain the device characteristics and coordinates of the device cluster to be connected to the Internet of Things;

[0107] Integrate the equipment features and coordinates of all equipment to obtain the equipment feature set and equipment coordinate set.

[0108] The motion analysis and coordinate compensation module 12 is further used for:

[0109] Each device feature in the device feature set is input into the device movement analyzer to obtain a device movement parameter set, wherein each device movement parameter includes movement speed and movement distance;

[0110] The device coordinate set is compensated using the device movement distance set within the device movement parameter set to obtain a compensated device coordinate set, wherein coordinate compensation is performed in the direction away from the 5G-A base station.

[0111] The training steps for the device mobility analyzer include:

[0112] Based on historical management data of IoT devices, a set of sample device features is collected, and the maximum moving speed and maximum moving distance of devices with different sample device features during use are collected and labeled to obtain a set of sample moving speeds and a set of sample moving distances.

[0113] A device movement analyzer built based on machine learning;

[0114] The device movement analyzer is iteratively trained using the sample device feature set, sample movement speed set, and sample movement distance set until the loss converges.

[0115] The access parameter optimization module 13 is further used for:

[0116] Based on the device feature set, device movement parameter set, and compensated device coordinate set, 5G-A access parameters are optimized to obtain an optimized access parameter set, including:

[0117] Randomly generate the first set of access parameters for the device cluster;

[0118] The first access parameters of each device are combined with the device characteristics and the device's moving speed and input into the mobile signal quality analysis path to obtain the first set of mobile access quality parameters.

[0119] The first access parameters of each device are combined with device characteristics and the coordinates of the compensated device and input into the mobile signal quality analysis path to obtain the first distance access quality parameter set;

[0120] Based on multiple mobile speeds, multiple mobile weights and multiple distance weights are configured. The first mobile access quality parameter set and the first distance access quality parameter set are weighted and calculated to obtain the first access quality parameter set. The mean value is then calculated to obtain the first cluster access quality parameter.

[0121] Continue to randomly generate access parameter sets for iterative optimization to obtain an optimized access parameter set with the maximum cluster access quality parameters.

[0122] The steps for constructing the mobile signal quality analysis path include:

[0123] Based on device connection data over a historical period, a set of sample access parameters, a set of sample device movement speeds, and a set of sample movement access quality parameters were collected.

[0124] Construct a machine learning-based mobile signal quality analysis path;

[0125] Using the sample access parameter set, sample device movement speed set, and sample mobile access quality parameter set, the mobile signal quality analysis path is iteratively supervised and trained until the loss converges.

[0126] Specifically, multiple mobility weights and multiple distance weights are configured based on multiple mobility speeds, and a first mobile access quality parameter set and a first distance access quality parameter set are weighted and calculated to obtain a first access quality parameter set, including:

[0127] Calculate the ratio of each device's moving speed to its maximum moving speed, and use this as the movement weight;

[0128] The distance weight is obtained by subtracting the movement weight from 1;

[0129] By using the mobility weight and distance weight of each device, the first mobile access quality parameter and the first distance access quality parameter of each device are weighted and calculated to obtain the first access quality parameter, and the first access quality parameter set of the device cluster is obtained.

[0130] The device access module 14 is further configured to:

[0131] According to the optimized access parameter set, the device cluster is connected to the Internet of Things using 5G-A.

[0132] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0133] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0134] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A method for managing large-scale IoT device connections based on 5G-A, characterized in that, The method includes: Obtain the device characteristics and coordinates of the device cluster to be connected to the Internet of Things, and obtain the device characteristic set and device coordinate set; Based on the equipment feature set, equipment movement analysis is performed to obtain a set of equipment movement parameters. The equipment coordinate set is then compensated to obtain a compensated equipment coordinate set. Each equipment movement parameter includes movement speed and movement distance. Based on the device feature set, device movement parameter set, and compensation device coordinate set, 5G-A access parameters are optimized to obtain an optimized access parameter set. According to the optimized access parameter set, the device cluster is connected to the Internet of Things using 5G-A. Based on the equipment feature set, equipment movement analysis is performed to obtain a set of equipment movement parameters. The equipment coordinate set is then compensated to obtain a compensated equipment coordinate set, including: Each device feature in the device feature set is input into the device movement analyzer to obtain a device movement parameter set, wherein each device movement parameter includes movement speed and movement distance; The device coordinate set is compensated using the device movement distance set within the device movement parameter set to obtain a compensated device coordinate set, wherein coordinate compensation is performed in the direction away from the 5G-A base station. Based on the device feature set, device movement parameter set, and compensated device coordinate set, 5G-A access parameters are optimized to obtain an optimized access parameter set, including: Randomly generate the first set of access parameters for the device cluster; The first access parameters of each device are combined with the device characteristics and the device's moving speed and input into the mobile signal quality analysis path to obtain the first set of mobile access quality parameters. The first access parameters of each device are combined with device characteristics and the coordinates of the compensated device and input into the mobile signal quality analysis path to obtain the first distance access quality parameter set; Based on multiple mobile speeds, multiple mobile weights and multiple distance weights are configured. The first mobile access quality parameter set and the first distance access quality parameter set are weighted and calculated to obtain the first access quality parameter set. The mean value is then calculated to obtain the first cluster access quality parameter. Continue to randomly generate access parameter sets for iterative optimization to obtain an optimized access parameter set with the maximum cluster access quality parameters.

2. The method for managing large-scale IoT device connections based on 5G-A according to claim 1, characterized in that, Obtain the device characteristics and coordinates of the device cluster to be connected to the Internet of Things, and obtain the device characteristic set and device coordinate set, including: Obtain the device characteristics and coordinates of the device cluster to be connected to the Internet of Things; Integrate the equipment features and coordinates of all equipment to obtain the equipment feature set and equipment coordinate set.

3. The method for managing large-scale IoT device connections based on 5G-A according to claim 1, characterized in that, The training steps for the device mobility analyzer include: Based on historical management data of IoT devices, a set of sample device features is collected, and the maximum moving speed and maximum moving distance of devices with different sample device features during use are collected and labeled to obtain a set of sample moving speeds and a set of sample moving distances. A device movement analyzer built based on machine learning; The device movement analyzer is iteratively trained using the sample device feature set, sample movement speed set, and sample movement distance set until the loss converges.

4. The method for managing large-scale IoT device connections based on 5G-A according to claim 1, characterized in that, The steps for constructing the mobile signal quality analysis path include: Based on device connection data over a historical period, a set of sample access parameters, a set of sample device movement speeds, and a set of sample movement access quality parameters were collected. Construct a machine learning-based mobile signal quality analysis path; Using the sample access parameter set, sample device movement speed set, and sample mobile access quality parameter set, the mobile signal quality analysis path is iteratively supervised and trained until the loss converges.

5. The method for managing large-scale IoT device connections based on 5G-A according to claim 1, characterized in that, Based on multiple mobile speeds, multiple mobile weights and multiple distance weights are configured. A weighted calculation is performed on the first mobile access quality parameter set and the first distance access quality parameter set to obtain the first access quality parameter set, which includes: Calculate the ratio of each device's moving speed to its maximum moving speed, and use this as the movement weight; The distance weight is obtained by subtracting the movement weight from 1; By using the mobility weight and distance weight of each device, the first mobile access quality parameter and the first distance access quality parameter of each device are weighted and calculated to obtain the first access quality parameter, and the first access quality parameter set of the device cluster is obtained.

6. A large-scale IoT device connection management system based on 5G-A, characterized in that, The system is used to perform the method according to any one of claims 1-5, comprising: The data acquisition module is configured to acquire the device characteristics and device coordinates of the device cluster to be connected to the Internet of Things, and obtain the device characteristic set and device coordinate set. The motion analysis and coordinate compensation module is configured to perform device motion analysis based on the device feature set to obtain a device motion parameter set, and to use the device motion parameter set to compensate the device coordinate set to obtain a compensated device coordinate set, wherein each device motion parameter includes a motion speed and a motion distance; The access parameter optimization module is configured to optimize 5G-A access parameters based on the device feature set, device movement parameter set, and compensation device coordinate set to obtain an optimized access parameter set. The device access module is configured to connect the device cluster to the Internet of Things using 5G-A technology according to the optimized access parameter set.

Images