A remote collaborative control method and system for smart devices based on the Internet of Things

Abstract

This invention relates to the field of remote control technology, specifically to a method and system for remote collaborative control of intelligent devices based on the Internet of Things (IoT). The method includes the following steps: based on an IoT platform, monitoring and adjusting the CPU utilization and memory usage of intelligent devices; optimizing data acquisition and network resource allocation; analyzing device performance and network load balancing indicators to achieve device connection priority ranking and task load management; and dynamically adjusting task execution and connection frequencies to meet real-time task requirements and improve system efficiency. This invention significantly improves data processing speed and reduces resource waste by dynamically adjusting data transmission intervals through real-time monitoring of device performance indicators. Real-time load analysis and optimization of network nodes ensure efficient use of network resources, avoiding data delays caused by network congestion. Regarding device connection management, an intelligent priority determination mechanism allows critical devices to quickly access the network in emergency situations.

Description

Technical Field

[0001] This invention relates to the field of remote control technology, and in particular to a method and system for remote collaborative control of smart devices based on the Internet of Things. Background Technology

[0002] Remote control is a technology that uses communication technology to monitor and operate remote devices or systems. With the rapid development of the Internet of Things, wireless communication technology and the Internet, remote control technology has been widely used in many fields such as smart homes, industrial automation, environmental monitoring, and health management. Through remote control, users can monitor and adjust the device in real time from a distance by means of the network or other communication methods, which improves the convenience and security of operation.

[0003] Among them, the remote collaborative control method of smart devices in the Internet of Things (IoT) is an application of remote control technology. It aims to enable different smart devices to work remotely collaboratively through IoT technology. This method allows multiple smart devices to be interconnected through networks, share information, and interact in real time, so as to achieve unified management and control of smart devices. Its main purpose is to enhance the collaborative capabilities and automation level between devices, improve the operating efficiency and reliability of smart devices, and it is widely used in smart home systems, equipment management of industrial production lines, and environmental monitoring.

[0004] Existing technologies have a fixed data update frequency, which cannot be quickly adjusted to sudden events. This results in an inability to react in time when equipment status changes rapidly, affecting the accuracy of decision-making. In terms of network management, existing technologies fail to optimize network load in real time and cannot effectively cope with load fluctuations, making data transmission delays or losses likely. In addition, the priority management of device access lacks a dynamic adjustment mechanism, which cannot guarantee that critical tasks will be given priority processing when network resources are scarce. This is particularly disadvantageous in demanding real-time monitoring and control scenarios, which can easily lead to delays or failures in the processing of important data, affecting the overall control stability and security. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by proposing a remote collaborative control method and system for smart devices based on the Internet of Things.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a remote collaborative control method for intelligent devices based on the Internet of Things, comprising the following steps:

[0007] S1: Based on the Internet of Things (IoT) platform, monitor the CPU utilization and memory usage of smart devices, collect the status data of smart devices regularly through IoT communication interfaces, and dynamically adjust the data transmission interval by analyzing the performance of smart devices in real time to obtain a device performance monitoring dataset.

[0008] S2: Based on the device performance monitoring dataset, obtain the bandwidth utilization, signal strength and network response time of the smart device in the edge network, compare the network parameters, identify and adjust the network nodes whose load has reached the upper limit, and obtain the network load balance index.

[0009] S3: Based on the network load balancing index, analyze the CPU utilization and memory usage of the smart devices. According to the response time and signal strength of the network nodes connected to each smart device, automatically prioritize the connection requests, mark high-priority devices as having priority connection rights, and postpone the connection of other devices to obtain the access priority index.

[0010] S4: Based on the access priority index, evaluate the task queue length and memory usage of the connected devices, adjust the task allocation ratio according to the data processing performance of the devices, and obtain task load management information.

[0011] The present invention is improved in that the device performance monitoring dataset includes performance trends, resource utilization, and status feedback information; the network load balancing index includes load capacity and adjustment response results; the access priority index includes weight level, sorting logic, and response priority; and the task load management information includes processing capacity, queue optimization results, and task response speed.

[0012] The present invention is improved in that the steps for obtaining the device performance monitoring dataset are specifically as follows:

[0013] S111: Based on the Internet of Things platform, use the communication interface to collect the status data of smart devices, monitor CPU utilization, memory usage and current network bandwidth usage, identify missing data and fill it in, and obtain the resource utilization time series.

[0014] S112: Based on the resource utilization time series, analyze the state data of the intelligent device in the continuous operation cycle, calculate its rate of change within the time period, compare it with the known stable variation range, mark the period exceeding the fluctuation benchmark, and obtain the stability fluctuation trend.

[0015] S113: Regarding the aforementioned stability fluctuation trend, analyze the fluctuation range within the current cycle and the fluctuation change level within historical stable cycles, using the following formula:

[0016]

[0017] Obtain the performance variation intensity DE of the i-th device. i The data transmission interval is dynamically adjusted to obtain a device performance monitoring dataset, where Δce i Let Δme be the change in CPU utilization of the i-th device. iLet be the change in memory usage of the i-th device. i Let re be the bandwidth fluctuation frequency of the i-th device. i Let de be the response time lag factor of the i-th device. i Let qe be the data interaction density factor of the i-th device. ik Let n be the concurrent device impact coefficient of the i-th device in the k-th time period. de This represents the total number of time periods.

[0018] The present invention is improved in that the steps for obtaining the network load balancing index are as follows:

[0019] S211: Based on the device performance monitoring dataset, obtain the bandwidth utilization, signal strength and network response time of the smart device in the edge network, align the time series of network parameters, and group them according to the location of network nodes to establish initial network load data.

[0020] S212: Retrieve the initial network load data, compare the load of each network node with the average load of all nodes, using the formula:

[0021]

[0022] RT of computational network resource transfer performance j Identify and adjust network nodes that have reached their load limits to obtain network load balancing metrics, including BT. j This represents the bandwidth utilization of the current node j, BT. z ST represents the bandwidth utilization of other nodes z compared to the current node j. z TR represents the signal strength of other nodes z. z This represents the network response time of other nodes z, where α and β are weights used to adjust the bandwidth difference and the ratio of signal strength to response time, respectively. rt It represents the total number of nodes participating in the calculation.

[0023] The present invention is improved in that the step of obtaining the access priority indicator is specifically as follows:

[0024] S311: Based on the network load balancing index, analyze the CPU utilization and memory usage of the smart devices, collect network node data for each smart device, sort the connection requests of different devices, and obtain a connection request sorting table.

[0025] S312: Invoke the connection request sorting table, and based on the response time and signal strength of the network nodes to which the device is connected, use the following formula:

[0026]

[0027] Calculate the access priority score (PR) and automatically sort connection requests based on the score to obtain the device connection ranking result, where GR... ij GR represents the response time of device i at node j. max GS represents the maximum response time of all devices across all nodes. ij GS represents the signal strength of device i at node j. max GL represents the maximum signal strength of all devices across all nodes. ij GL represents the network load balancing metric for device i at node j. max N represents the maximum network load balancing metric for all devices across all nodes. pr It is the total number of terms in the weighted average;

[0028] S313: Based on the device connection sorting result, mark the high-priority device as having priority connection right, and postpone the connection of the remaining devices. At the same time, call the connection request sorting table to sort the postponed devices again to obtain the access priority index.

[0029] The present invention is improved in that the step of obtaining the task load management information is specifically as follows:

[0030] S411: Based on the access priority index, evaluate the real-time task queue data and current memory usage data of the connected devices, compare the number of task requests with the set device request capacity, memory usage and memory capacity, determine the current load level of the device, and obtain the device load judgment result;

[0031] S412: Based on the equipment load judgment result, the following formula is used:

[0032]

[0033] Calculate the task allocation offset value ΔGD, where CU represents the device's data processing performance parameters, QD represents the device's current number of task requests, RD represents the task response rate, MD represents the device's free memory capacity, and K... GD For adjustment coefficients;

[0034] S413: Based on the task allocation offset value, the number of device task requests is proportionally redistributed, and the scheduling information field is reconstructed in conjunction with the original task queue structure to obtain task load management information.

[0035] The present invention is improved in that the steps further include:

[0036] S5: Call the task load management information, analyze the task execution density and memory usage based on the current working status of the smart device, dynamically adjust the connection time interval and task cycle to match real-time task requirements, and synchronously adjust the device connection frequency to obtain device connection control feedback results.

[0037] The device connection control feedback results include connection adjustment data, periodic update information, and frequency synchronization indicators.

[0038] The present invention is improved in that the step of obtaining the device connection control feedback result is specifically as follows:

[0039] The task load management information is invoked, and based on the current working status of the smart device, the correspondence between task execution frequency and memory usage rate is compared to determine whether the task load exceeds the standard. The task load change trend is determined by combining the number of threads of the smart device and the task cycle interval.

[0040] Based on the aforementioned task load change trend, the matching degree between task load and connection cycle is analyzed. According to the changes in task frequency and device connection success rate, the device connection frequency and task cycle configuration are adjusted synchronously to obtain device connection control feedback results.

[0041] A remote collaborative control system for smart devices based on the Internet of Things (IoT), the system comprising:

[0042] The device status monitoring module is based on the Internet of Things platform. It monitors the CPU utilization and memory usage of smart devices, collects the status data of smart devices regularly, and dynamically adjusts the data transmission interval by analyzing the performance of smart devices in real time to obtain a device performance monitoring dataset.

[0043] Based on the device performance monitoring dataset, the network load management module obtains the bandwidth utilization, signal strength and network response time of the smart devices in the edge network, compares the network parameters, identifies and adjusts the network nodes whose load has reached the upper limit, and obtains the network load balance index.

[0044] Based on the network load balancing index, the device access priority module analyzes the CPU utilization and memory usage of smart devices, and automatically prioritizes connection requests according to the response time and signal strength of network nodes, marking high-priority devices as having priority connection rights, and delaying the connection of other devices, thus obtaining the access priority index.

[0045] Based on the access priority index, the intelligent task scheduling module evaluates the task queue length and memory usage of connected devices, adjusts the task allocation ratio according to the data processing performance of the devices, and obtains task load management information.

[0046] The connection dynamic control module calls the task load management information to analyze task execution density and memory usage, dynamically adjusts the connection time interval and task cycle to match real-time task requirements, and synchronously adjusts the device connection frequency to obtain device connection control feedback results.

[0047] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0048] In this invention, by monitoring the performance indicators of the equipment in real time and dynamically adjusting the data transmission interval, the data processing speed is significantly improved and resource waste is reduced. Real-time load analysis and optimization of network nodes ensure the efficient use of network resources and avoid data delays caused by network congestion. In terms of device connection management, the intelligent priority determination mechanism allows critical devices to quickly access the network in emergency situations, enhancing the overall responsiveness of intelligent devices. Through intelligent analysis and adjustment of task allocation, the work collaboration between devices is optimized, improving control efficiency and device stability. Attached Figure Description

[0049] Figure 1 This is a flowchart of the main steps proposed in this invention;

[0050] Figure 2 This is a flowchart illustrating the process of obtaining the equipment performance monitoring dataset in this invention.

[0051] Figure 3 This is a flowchart illustrating the process of obtaining network load balancing indicators in this invention.

[0052] Figure 4 This is a flowchart illustrating the process of obtaining access priority indicators in this invention.

[0053] Figure 5 This is a flowchart illustrating the process of obtaining task load management information in this invention.

[0054] Figure 6 This is a flowchart illustrating the process of obtaining device connection control feedback results in this invention. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0056] In the description of this invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention 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, and therefore should not be construed as a limitation of the invention. Furthermore, in the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0057] Example

[0058] Please see Figure 1 This invention provides a technical solution: a remote collaborative control method for smart devices based on the Internet of Things, comprising the following steps:

[0059] S1: Based on the Internet of Things (IoT) platform, monitor the CPU utilization and memory usage of smart devices, periodically collect status data of smart devices using IoT communication interfaces, and dynamically adjust the data transmission interval by analyzing the performance of smart devices in real time, thereby optimizing data collection efficiency and obtaining a device performance monitoring dataset.

[0060] S2: Based on the device performance monitoring dataset, obtain the bandwidth utilization, signal strength and network response time of smart devices in the edge network, compare the network parameters, identify and adjust network nodes that have reached their load limit, optimize network resource allocation, and obtain network load balance indicators.

[0061] S3: Based on network load balancing indicators, analyze the CPU utilization and memory usage of smart devices. According to the response time and signal strength of the network nodes connected to each smart device, automatically prioritize connection requests, mark high-priority devices as having priority connection rights, and postpone the connection of other devices to obtain access priority indicators.

[0062] S4: Based on the access priority index, evaluate the task queue length and memory usage of connected devices, adjust the task allocation ratio according to the data processing performance of the devices, optimize the device workload, and obtain task load management information;

[0063] S5: Calls task load management information, analyzes task execution density and memory usage based on the current working status of the smart device, dynamically adjusts connection time intervals and task cycles to match real-time task requirements, and synchronously adjusts device connection frequency to obtain device connection control feedback results.

[0064] The device performance monitoring dataset includes performance trends, resource utilization, and status feedback information; network load balancing indicators include load capacity and adjustment response results; access priority indicators include weight level, sorting logic, and response priority; task load management information includes processing capacity, queue optimization results, and task response speed; and device connection control feedback results include connection adjustment data, periodic update information, and frequency synchronization indicators.

[0065] Please see Figure 2 The specific steps for obtaining the device performance monitoring dataset are as follows:

[0066] S111: Based on the Internet of Things platform, use the communication interface to collect the status data of smart devices, monitor CPU utilization, memory usage and current network bandwidth usage, identify missing data and fill it in, and obtain the resource utilization time series.

[0067] Based on an IoT platform, the system connects to smart devices via communication interfaces, using serial or Ethernet ports to access and identify device numbers. After determining the device's hardware structure, it sequentially calls the CPU utilization, memory utilization, and network bandwidth interfaces to collect status data. Within each preset sampling period, the above metrics are recorded in seconds. CPU utilization data is captured through the device's own operating system's resource management functions. For example, in Windows, the PerformanceMonitor data interface is used to obtain the process-level CPU utilization percentage. If the initial value is 35% and the ending value is 65%, then the CPU utilization change of the device within that period is 30%. Memory utilization is obtained by the ratio of memory page file accesses to total available memory. If the initial value is 40% and the ending value is 75%, then the memory utilization change is 35%. Network bandwidth is calculated by reading network card traffic statistics to determine the average bandwidth usage, with the initial collection time being 20Mbps. The system operates at 50 Mbps with a variation of 30 Mbps. To identify missing data, the system checks if the continuous time difference in the sampling timestamp sequence exceeds a set period of ±5%. If two sets of data are missing within a sampling period, a placeholder is inserted into the timeline, and linear interpolation or a moving average is used to fill the gap. If the CPU utilization is 60% and 70% at a given time, the missing point is estimated at 65%. The above sampling and repair data form a resource utilization time series on the timeline. This series is used for subsequent fluctuation trend analysis and dynamic control decisions. The resource utilization time series is ultimately stored in the database as a one-dimensional vector. For example, if device 1 samples every 30 seconds within 5 minutes, there will be 10 records. The data storage structure is [timestamp, device number, CPU utilization, memory utilization, bandwidth usage]. If sampling times overlap or offset by more than 1 second within a continuous operating period, the corresponding sampling group is marked as an anomaly, thus obtaining a stable and continuous time series.

[0068] S112: Based on the resource utilization time series, analyze the state data of intelligent devices in continuous operation cycles, calculate their rate of change over time, compare it with the known stable variation range, mark the period exceeding the fluctuation benchmark, and obtain the stability fluctuation trend.

[0069] Based on the constructed resource utilization time series, the device operation data is divided into multiple continuous periods according to the set sampling period. For example, 5 minutes is divided into 10 30-second periods. The rate of change of three parameters—CPU utilization, memory utilization, and network bandwidth—is calculated for each period. The rate of change is obtained by subtracting the previous period's value from the current value and then dividing by the previous period's value. For example, if a device's CPU utilization increases from 65% to 75%, the rate of change is (75% - 65%) / 65% = 15.38%. Similarly, if memory utilization decreases from 75% to 70%, the rate of change is (70% - 75%) / 75% = -6.67%. The three parameters are combined into a ternary change vector. The Euclidean norm of the ternary change vector generated in each cycle is then calculated as the overall resource fluctuation intensity for that cycle. This value is compared with the system's preset stable fluctuation threshold range. For example, if the stable fluctuation range is set to [-10%, +10%], 15.38% will be identified as exceeding the fluctuation benchmark range. The system marks this cycle as an unstable period and then labels the status of each cycle to form a "stable / unstable" sequence for long-term trend modeling and statistical analysis. This stability fluctuation trend is further recorded as a scalar sequence and updated synchronously with the equipment operation log.

[0070] S113: Regarding the trend of stability fluctuations, analyze the fluctuation range within the current cycle and the fluctuation change level within historical stable cycles, using the following formula:

[0071]

[0072] Obtain the performance variation intensity DE of the i-th device. i The data transmission interval is dynamically adjusted to obtain a device performance monitoring dataset, where Δce i Let Δme be the change in CPU utilization of the i-th device, representing the change in CPU utilization of the device during the evaluation period. i Let be the change in memory utilization of the i-th device, representing the change in memory utilization of the device during the evaluation period. i Let re be the bandwidth fluctuation frequency of the i-th device, used to reflect the fluctuation of network bandwidth usage by the device within a period. i Let de be the response time lag factor of the i-th device, considering the impact of device response time delay on performance evaluation. i Let qe be the data interaction density factor of the i-th device, reflecting the frequency and density of data interaction between the device and other devices or systems in the network. ik Let n be the concurrent device impact coefficient of device i in time period k, which measures the impact of other devices on the performance of device i in the same time period. de The total number of time periods represents the total number of time segments across all devices.

[0073] Based on the acquired stability fluctuation trend data, select the status data of the i-th device within a certain operating cycle. In this cycle, first obtain its CPU utilization change value Δce. i By subtracting the maximum and minimum CPU values ​​within a cycle and normalizing the result, for example, if the maximum CPU value within a cycle is 80% and the minimum is 60%, the normalization result is: (80-60) / 100 = 0.20, thus obtaining Δce. i =0.20; Similarly, the change in memory usage Δme i If the maximum value is 90% and the minimum value is 70%, then the normalized change is (90-70) / 100 = 0.20, resulting in Δme. i =0.20; bandwidth fluctuation frequency be i The bandwidth value is determined by the number of inflection points on the curve per unit time. Assuming there are 6 inflection points on the bandwidth curve within this period, and the maximum supported fluctuation frequency of the device is 10 times, this is normalized to 6 / 10 = 0.60, yielding be. i =0.60; Response time lag factor re i The hysteresis threshold is calculated based on the proportion of all sampled response values ​​that exceed the system standard value (e.g., a standard delay of 200ms). For example, if 3 out of 10 samples exceed 250ms, and the hysteresis threshold is set to 250ms, then the normalization is 3 / 10 = 0.30, resulting in re... i =0.30; Data interaction density factor de i Let this be the ratio of the total number of data transmissions and receptions per unit time to the maximum expected interaction frequency. If the current device has a total of 200 interactions within a cycle, and the maximum designed interaction frequency is 400, then after normalization, it becomes 200 / 400 = 0.50, resulting in de. i =0.50; Concurrent device impact coefficient qe ik This represents the degree to which other devices consume the performance of the current device. Let the observed impact percentages in the three sub-time periods be 0.40, 0.30, and 0.20, respectively. Summing these values ​​yields:

[0074]

[0075] Substitute the above values ​​into the formula:

[0076]

[0077] The calculation results show that the performance variation intensity of the i-th device in the current period is 0.2947. Comparing it with the preset performance fluctuation benchmark value (e.g., the maximum allowable intensity under stable operation is 0.25), it is determined that the device is in an excessively volatile state. Therefore, it is necessary to adjust the sampling frequency and data transmission interval of the device, for example, by extending the transmission period from the original 10 seconds to 20 seconds to reduce system interference. The variation intensity and adjustment strategy are then recorded synchronously in the device performance monitoring dataset.

[0078] Please see Figure 3 The specific steps for obtaining network load balancing metrics are as follows:

[0079] S211: Based on the device performance monitoring dataset, obtain the bandwidth utilization, signal strength and network response time of the smart device in the edge network, align the time series of network parameters, and group them according to the location of network nodes to establish initial network load data.

[0080] Acquire a device performance monitoring dataset, parse each record in the dataset to extract the bandwidth utilization, signal strength, and network response time parameters corresponding to the smart devices, and align the time series of these three parameters based on the timestamp field. During the alignment process, records from different devices are grouped into the same time period in milliseconds. A unified time base is set as a sampling interval of 5 seconds. Multiple smart camera devices in the same office area in a real-world scenario are selected as monitoring objects, and the network parameters corresponding to the devices are extracted synchronously according to the time interval. For example, if device A has a bandwidth of 65%, a signal strength of -50dBm, and a response time of 20ms at time t1, and device B has values ​​of 60%, -48dBm, and 22ms at the same time, then they are respectively grouped into the same time period. In the same group of data, after completing the time registration of network parameters for multiple devices, the nodes are classified according to the installation location coordinates of the devices in the actual physical scene. For example, all devices in the southeast corner of an office area are defined as node 1. The three network parameters corresponding to multiple devices in the node are averaged to obtain the average bandwidth utilization, average signal strength and average response time of the node in that time period. This is used as the initial network load data value of the node. Assuming that a total of 6 devices are collected in node 1, the average bandwidth utilization can be expressed as (65+63+64+66+62+64) / 6=64%. The other parameters are averaged in the same way, and an initial parameter data table is constructed for subsequent calls. The data of this node will serve as the basis for subsequent load identification.

[0081] S212: Retrieve initial network load data, compare the load of each network node with the average load of all nodes, using the formula:

[0082]

[0083] RT of computational network resource transfer performance j Identify and adjust network nodes that have reached their load limits to obtain network load balancing metrics, including BT. j This represents the bandwidth utilization of the current node j, and is an indicator that measures the current bandwidth usage of that node. (BT) z ST represents the bandwidth utilization of other nodes z compared to the current node j, used to determine the difference in bandwidth usage between nodes. z TR represents the signal strength of other nodes z and is an indicator of the efficiency and quality of node communication. z This represents the network response time of other nodes z, used to evaluate the speed at which a node processes requests. A shorter response time indicates higher node efficiency. α and β are weights used to adjust the ratio of bandwidth difference and signal strength to response time. n rt This is the total number of nodes participating in the calculation;

[0084] Let the total number of nodes be n rt =3. Node j is selected as the node to be calculated, and nodes z1 and z2 are compared. The original and normalized values ​​of the network parameters of the nodes are as follows: Node j's bandwidth utilization is 65% (normalized value 1.0), node z1's bandwidth utilization is 60% (normalized value 0.5), and node z2's bandwidth utilization is 55% (normalized value 0.0); node z1's signal strength is -48dBm (normalized value 0.8), and z2's signal strength is -52dBm (normalized value 0.0); node z1's response time is 22ms (normalized value 0.4286), and z2's response time is 25ms (normalized value 0.0). Using weighting coefficients α = 0.6 and β = 0.4, the values ​​are substituted into the formula:

[0085]

[0086] Calculation of group 1 yields:

[0087] Group 2 is: (Treat as 0), calculate:

[0088]

[0089] Get RT j =0.8234. This result indicates that node j has a moderate level of transferability in terms of resource parameters compared with its neighboring nodes. When the system sets the resource transfer benchmark value to 0.8, the node meets the scheduling adjustment conditions, indicating that it has partial network load balancing capability. The higher the value, the more suitable the node is as a network resource carrier or transfer target. Furthermore, by horizontally sorting and comparing the RT values ​​of all nodes, nodes with RT values ​​higher than the benchmark value can be screened as load scheduling nodes, thereby generating a network load balancing index.

[0090] Please see Figure 4 The specific steps for obtaining the access priority indicator are as follows:

[0091] S311: Based on network load balancing indicators, analyze the CPU utilization and memory usage of smart devices, collect network node data for each smart device, sort the connection requests of different devices, and obtain a connection request sorting table.

[0092] By reading real-time resource utilization data recorded in the device's operating system or device management interface, the system collects status data of the device across multiple network nodes. Response time is obtained through network request round-trip time measurement, signal strength is obtained through RSSI detection, and network load balancing index is obtained from network traffic distribution monitoring. After data collection, the system compares the parameter differences between different devices. For example, device D1 has a response time of 120ms, a signal strength of -65dBm, and a load index of 0.6 on node N1. This is compared with device D2 on the same node, which has a response time of 150ms, a signal strength of -70dBm, and a load index of 0.8, to determine which device has better connection efficiency. In this process, the lower the response time, the closer the signal strength is to 0, and the smaller the load index, the better the performance. The three indicators are standardized and normalized, and the ranking priority is calculated based on the difference between the indicators of the devices. A multi-round comparison method is used to reasonably arrange the order of connection requests according to the device resource utilization, and the ranking sequence is recorded.

[0093] S312: Invoke the connection request sorting table, and based on the response time and signal strength of the network node to which the device is connected, use the following formula:

[0094]

[0095] Calculate the access priority score (PR) and automatically sort connection requests based on the score to obtain the device connection ranking result, where GR... ij GR represents the response time of device i at node j, reflecting the time from when the device sends a signal to when it receives a response. max GS represents the maximum response time of all devices across all nodes and is a reference value used to standardize response time. ij GS represents the signal strength of device i at node j, and is a key indicator for measuring network connection quality, affecting the stability and speed of data transmission. max GL represents the maximum signal strength of all devices across all nodes and is a reference value used to standardize signal strength. ij GL represents the network load balancing metric for device i at node j, used to assess the balance of network load. max N represents the maximum network load balancing metric for all devices across all nodes. It is a reference value used to standardize network load balancing metrics.pr It is the weighted average total number of items, which is 3, and includes response time, signal strength and network load balance indicators;

[0096] The ranking of each device in the connection request sorting table is retrieved, and its response time, signal strength, and load balancing under the current connection node are analyzed again. A score is calculated based on the parameters using the applicable formula. For example, if device D2's response time under node N1 is 150ms, GR... max Set the maximum response time in the same batch of devices to 150ms, GS ij This represents the signal strength value of the device at this node, in dBm. It needs to be measured via RSSI. For example, if D2 measures -70dBm, the corresponding maximum signal strength is GS. max The value is -60dBm. In actual processing, its absolute value is converted to a positive value and used in the normalization calculation, resulting in... GL ij This is a network load indicator, with values ​​ranging from 0 to 1. For example, D2 is 0.8, and GL... max The maximum load value is 0.8, which is normalized to 1.0000, because N pr =3, indicating that the three parameters are weighted averaged and substituted into the formula to calculate the access priority score of D2:

[0097]

[0098] Similarly, if D3 has a response time of 90ms at node N2, a signal strength of -60dBm, and a load index of 0.5, substituting these values ​​into the calculation yields:

[0099]

[0100] This score indicates the priority of a device's access to the current node. A higher score indicates better overall performance. After sorting, the device connection ranking result is obtained, which serves as the basis for subsequent priority connection determination.

[0101] S313: Based on the device connection sorting result, mark the high-priority device as the priority connection right, and postpone the connection of the remaining devices. At the same time, call the connection request sorting table to sort the postponed devices again to obtain the access priority index.

[0102] First, the device number with the highest ranking value is read and prioritized according to a preset access scoring benchmark value of 0.8. If the score value is greater than this benchmark value, priority connection is granted. For example, D2's score value is 1.0556, which is significantly greater than the benchmark value of 0.8, so D2 is marked as a high-priority device. Next, D3 with a score value of 0.7417 and D4 with a score value of 0.7333 are read. Because their scores are lower than the access scoring benchmark value, they are classified as ordinary devices and do not participate in the first round of connection allocation. This process is based on a numerical comparison between the score result and the benchmark value. Then, the connection requests marked as ordinary devices are rewritten into the connection request sorting table and sorted again according to their original ranking values. The remaining requesting devices are arranged from high to low score value, for example, D3 is ranked before D4. The updated sorting table is used as the basis for the final connection strategy and the sorting data is mapped to the access hierarchical control system to generate a unified connection sequence control command, ultimately obtaining the access priority index.

[0103] Please see Figure 5 The specific steps for obtaining task load management information are as follows:

[0104] S411: Based on the access priority index, evaluate the real-time task queue data and current memory usage data of connected devices, compare the number of task requests with the set device request capacity, memory usage and memory capacity, determine the current load level of the device, and obtain the device load judgment result;

[0105] Acquire real-time task queue data and current memory usage data for all connected devices. Access priority can be established based on factors such as device type, runtime, physical location, or historical performance. For example, prioritize access for critical data acquisition devices. Assuming device D01 is an edge node with 25 incomplete requests in its current task queue, this data can be obtained through system polling command lines or the SNMP protocol. Simultaneously, calling the operating system's memory monitoring reveals that the device is currently using 5.5GB of memory. With a total memory of 8GB, the remaining memory capacity is 2.5GB, resulting in a memory utilization rate of 5.5 ÷ 8 = 0.6875, or 68.75%. If the system's preset task capacity threshold is 30 requests and the memory utilization threshold is 70%, then the number of current task requests and the task capacity threshold need to be adjusted. The comparison shows that if the number of tasks (25) is less than the threshold (30), the item is considered normal. Comparing the memory usage, 68.75% is also less than 70%, both results being below the preset threshold. Therefore, the device load is considered normal, and the corresponding load judgment value is set to 0.6875. If we switch to another device, D02, its task request count is 40, and its memory usage is 6.2GB. The calculated memory usage rate is 6.2 ÷ 8 = 0.775, or 77.5%, both exceeding the preset threshold. In this case, the task request judgment is 1.0, and the memory usage is also 1.0. The combined load judgment value is 1.0. Therefore, in this process, each data point needs to be compared with both the actual value and the set threshold. The maximum value is used as the final device load judgment result, which will serve as an important reference for subsequent task allocation adjustments.

[0106] S412: Based on the equipment load judgment result, the following formula is used:

[0107]

[0108] The task allocation offset value ΔGD is calculated to adjust tasks to optimize the device's workload. Here, CU represents the device's data processing performance parameter, a coefficient that quantifies the device's processing capacity and is used to evaluate the device's performance under a specific task load. QD represents the device's current task request count, reflecting the number of tasks the device is currently processing or waiting to process. RD represents the task response rate, a metric measuring the speed or efficiency of the device's response to task requests. MD represents the device's free memory capacity, indicating the amount of unused memory at a specific point in time. K... GD An adjustment factor is used to adjust the task allocation ratio based on the relationship between equipment performance and load.

[0109] Based on the data processing performance parameters, number of task requests, response rate, and remaining memory capacity of each device, taking device D01 as an example, its processing performance (CU) is 3.2 GFLOPS, which is normalized to 0.53; the current number of task requests (QD) is 25, normalized to 0.42; the task response rate (RD) is 50 req / s, corresponding to a normalized value of 0.51; and the free memory (MD) is 2.5 GB, normalized to 0.38. The adjustment coefficient K_GD remains unchanged at a set value of 1.1. Substituting these values ​​into the formula:

[0110]

[0111] Taking device D02 as an example, its CU is 4.5, which is 0.74 after normalization; QD is 40, which is 0.67 after normalization; RD is 65, which is 0.68 after normalization; MD is 1.8, which is 0.29 after normalization; and K_GD is 1.1. Substituting these values ​​into the formula, the calculation is as follows:

[0112]

[0113] The task allocation offset value for device D01 is 0.2751, and for D02 it is 0.5622. This offset value will be used to set the task weight in the subsequent task ratio adjustment step. The higher the value, the greater the task allocation pressure of the current device, and the task ratio needs to be reduced accordingly to balance the execution pressure between devices. Finally, the task allocation offset value is output.

[0114] S413: Based on the task allocation offset value, the number of device task requests is proportionally redistributed, and combined with the original task queue structure, the scheduling information field is reconstructed to obtain task load management information.

[0115] The total number of task requests is statistically set. For example, if the current system scheduling needs to allocate a total of 90 tasks, the task allocation ratio needs to be calculated based on the offset value of each device. The offset value is calculated using the proportional normalization method. The total offset value is 0.2751 + 0.5622 = 0.8373. The proportion that D01 should bear is 0.2751 ÷ 0.8373 = 0.3285, or 32.85%, and that of D02 is 0.5622 ÷ 0.8373 = 0.6715, or 67.15%. Then, the total number of tasks is allocated. D01 is allocated 90 × 0.3285 = 29.565 tasks, which is rounded down to 29. D02 is allocated 90 × 0.6715 = 60.435 tasks, which is rounded down to 60. The remaining 1 task can be handled by the device with the lowest response time in the task queue. This is recorded as part of the post-allocation surplus supplementation mechanism. The adjustment strategy combines the current operating status of the device with the offset comparison results to perform task reallocation. In the actual scenario, the task scheduling field of D01 will be updated to the task manager, including key elements such as the updated fields "Device Code = D01", "Number of Assigned Tasks = 29", "Task Segment Number Start and End Range = 0001-0029", "Schedule Timestamp = 20250409T102500", and "Expected Response Window = 3-7 seconds". Similarly, the D02 field structure will contain content such as Device Code = D02, Number of Assigned Tasks = 60, and Task Number Range = 0030-0089. The scheduling fields will eventually be written to the scheduling control table and encapsulated in JSON structure, and updated synchronously on the task scheduling and control bus to further ensure the consistency of data status between the scheduling control layer and the device task layer during the task execution phase. After integrating all device scheduling information, the system generates a unified field structure and outputs task load management information.

[0116] Please see Figure 6 The specific steps for obtaining the device connection control feedback results are as follows:

[0117] The task load management information is invoked. Based on the current working status of the smart device, the correspondence between the task execution frequency and the memory usage rate is compared to determine whether the task load exceeds the standard. The task load change trend is determined by combining the number of threads of the smart device and the task cycle interval.

[0118] First, the task execution frequency is extracted, and the single-thread processing load is calculated based on the number of threads. For example, if a device has a task frequency of 20Hz and 8 threads, the single-thread load is 2.5Hz. This metric is used to determine the task scheduling pressure distribution. Next, memory usage is collected, and the current operating status of the device is determined based on a preset memory usage threshold. The threshold is divided into three ranges: 0%–70% is controllable load, 70%–85% is strained load, and above 85% is overload. If the device's current memory usage is 92%, it has obviously entered the overload range. At this point, the task scheduling density is analyzed by combining the task cycle and connection time interval. Assuming the task cycle is 1600ms and the connection time interval is 300ms, the theoretical number of connections per unit cycle is 5. Combining this with the frequency, the number of tasks to be processed in this cycle is 20Hz × 1.6s = 32. The task is allocated to 5 connection operations, with an average of 6.4 tasks per connection. This density exceeds the load capacity of a single connection. Combined with the current memory pressure, the task density is determined to be overloaded. Conversely, if the task frequency is 10Hz, there are 4 threads, memory usage is 65%, the cycle is 2000ms, and the connection interval is 500ms, then there are 4 connections within the cycle, a total of 20 tasks, and an average of 5 tasks per connection. The single-thread load is 2.5Hz, and the memory status is within a controllable range. Therefore, the task density is determined to be reasonable. By comparing and judging the above multiple indicators, a system evaluation of the task execution frequency, thread load, memory pressure, and connection frequency is completed. Finally, based on the task density, memory capacity, and time matching degree, the task density fluctuation trend of the device under the current configuration is obtained, and the task load status within the current cycle is summarized accordingly.

[0119] Based on the trend of task load changes, the matching degree between task load and connection cycle is analyzed. According to the changes in task frequency and device connection success rate, the device connection frequency and task cycle configuration are adjusted synchronously to obtain device connection control feedback results.

[0120] By combining the current connection interval and task cycle of the device, the coverage of task density within the connection cycle and its dynamic adaptation capability are further analyzed to determine whether there are problems with insufficient or excessive connection frequency configuration. Specifically, the task density variation values ​​are first mapped to the connection frequency according to the time distribution for matching analysis. Assuming a device's current task cycle is 1800ms and the connection interval is 400ms, the number of connections within the cycle is 4.5, rounded down to 4. If the task frequency is 15Hz, the total number of tasks is 27, with an average of 6.75 tasks processed per connection. If there are currently 6 threads, each thread needs to handle 1.125 tasks. If the device's memory utilization is 80%, it is in a "stressful" range, and the connection success rate is 85%, lower than the 90% baseline threshold, indicating poor connection efficiency. If the connection rate shows a downward trend, it is necessary to determine whether the decline in connection performance is due to an increase in task load density. Given that the current number of connections is insufficient to cover the task density, it is recommended to adjust the connection interval to 300ms, thereby increasing the number of connections per cycle to 6, reducing the task pressure per connection to 4.5, and also reducing the thread load sharing intensity. At the same time, compare the connection success rate and task loss rate of the device in the past three cycles. If the connection success rate increases to over 90% and the task loss rate decreases to a tolerable range after the adjustment, it can be confirmed that the adjustment is targeted. If there is no improvement, it is necessary to continue to adjust the task frequency or extend the task cycle to alleviate the density pressure. In this way, a dynamic feedback mechanism between the connection control strategy adjustment and the task density status is established to obtain the device connection control feedback results.

[0121] A remote collaborative control system for smart devices based on the Internet of Things (IoT), the system comprising:

[0122] The device status monitoring module is based on the Internet of Things platform. It monitors the CPU utilization and memory usage of smart devices, collects the status data of smart devices regularly, and dynamically adjusts the data transmission interval by analyzing the performance of smart devices in real time to obtain a device performance monitoring dataset.

[0123] Based on the device performance monitoring dataset, the network load management module obtains the bandwidth utilization, signal strength and network response time of smart devices in the edge network, compares the network parameters, identifies and adjusts network nodes that have reached their load limits, and obtains network load balancing indicators.

[0124] The device access priority module analyzes the CPU utilization and memory usage of smart devices based on network load balancing indicators. According to the response time and signal strength of network nodes, it automatically prioritizes connection requests, marks high-priority devices as having priority connection rights, and postpones the connection of other devices to obtain the access priority index.

[0125] The intelligent task scheduling module evaluates the task queue length and memory usage of connected devices based on access priority indicators, and adjusts the task allocation ratio according to the data processing performance of the devices to obtain task load management information.

[0126] The connection dynamic control module calls the task load management information, analyzes the task execution density and memory usage, dynamically adjusts the connection time interval and task cycle to match real-time task requirements, and synchronously adjusts the device connection frequency to obtain device connection control feedback results.

[0127] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A method for remote collaborative control of intelligent devices based on the Internet of Things, characterized in that, Includes the following steps: S1: Based on the Internet of Things (IoT) platform, monitor the CPU utilization and memory usage of smart devices, collect the status data of smart devices periodically through IoT communication interfaces, and dynamically adjust the data transmission interval by analyzing the performance of smart devices in real time to obtain a device performance monitoring dataset. S2: Based on the device performance monitoring dataset, obtain the bandwidth utilization, signal strength and network response time of the smart device in the edge network, compare the network parameters, identify and adjust the network nodes whose load has reached the upper limit, and obtain the network load balance index. S3: Based on the network load balancing index, analyze the CPU utilization and memory usage of the smart devices, and automatically prioritize connection requests according to the response time and signal strength of the network nodes connected to each smart device. Mark high-priority devices as having priority connection rights, and postpone the connection of other devices to obtain the access priority index. S4: Based on the access priority index, evaluate the task queue length and memory usage of the connected devices, adjust the task allocation ratio according to the data processing performance of the devices, and obtain task load management information; S5: Call the task load management information, analyze the task execution density and memory usage based on the current working status of the smart device, dynamically adjust the connection time interval and task cycle to match real-time task requirements, and synchronously adjust the device connection frequency to obtain device connection control feedback results. The device connection control feedback results include connection adjustment data, periodic update information, and frequency synchronization indicators.

2. The method for remote collaborative control of intelligent devices based on the Internet of Things according to claim 1, characterized in that, The device performance monitoring dataset includes performance trends, resource utilization, and status feedback information; the network load balancing indicators include load capacity and adjustment response results; the access priority indicators include weight level, sorting logic, and response priority; and the task load management information includes processing capacity, queue optimization results, and task response speed.

3. The method for remote collaborative control of intelligent devices based on the Internet of Things according to claim 1, characterized in that, The specific steps for obtaining the device performance monitoring dataset are as follows: S111: Based on the Internet of Things platform, use the communication interface to collect the status data of smart devices, monitor CPU utilization, memory usage and current network bandwidth usage, identify missing data and fill it in, and obtain the resource utilization time series. S112: Based on the resource utilization time series, analyze the state data of the intelligent device in the continuous operation cycle, calculate its rate of change within the time period, compare it with the known stable variation range, mark the period exceeding the fluctuation benchmark, and obtain the stability fluctuation trend. S113: Regarding the aforementioned stability fluctuation trend, analyze the fluctuation range within the current cycle and the fluctuation change level within historical stable cycles, using the following formula: ； Get the Performance variation intensity of the equipment The data transmission interval is dynamically adjusted to obtain a device performance monitoring dataset, in which... For the first CPU utilization change of the device For the first The change in memory usage of the device. For the first The frequency of bandwidth fluctuations of the device. For the first The response time lag factor of the device. For the first Data interaction density factor of the devices For the first The equipment in The impact coefficient of concurrent devices within a time period. This represents the total number of time periods.

4. The method for remote collaborative control of intelligent devices based on the Internet of Things according to claim 1, characterized in that, The specific steps for obtaining the network load balancing index are as follows: S211: Based on the device performance monitoring dataset, obtain the bandwidth utilization, signal strength and network response time of the smart device in the edge network, align the time series of network parameters, and group them according to the location of network nodes to establish initial network load data. S212: Retrieve the initial network load data, compare the load of each network node with the average load of all nodes, using the formula: ； Computational network resource transfer performance Identify and adjust network nodes whose load has reached its limit to obtain network load balancing metrics, among which... Indicates the current node bandwidth utilization Indicates the relationship with the current node Other nodes in comparison bandwidth utilization Indicates other nodes signal strength, Indicates other nodes Network response time, and It involves adjusting the weights of bandwidth difference and the ratio of signal strength to response time. It represents the total number of nodes participating in the calculation.

5. The method for remote collaborative control of intelligent devices based on the Internet of Things according to claim 1, characterized in that, The specific steps for obtaining the access priority indicator are as follows: S311: Based on the network load balancing index, analyze the CPU utilization and memory usage of the smart devices, collect network node data for each smart device, sort the connection requests of different devices, and obtain a connection request sorting table. S312: Invoke the connection request sorting table, and based on the response time and signal strength of the network nodes to which the device is connected, use the following formula: ； Calculate access priority score The system automatically sorts connection requests based on scores to obtain device connection ranking results. Representative equipment At the node The response time is as follows This represents the maximum response time for all devices across all nodes. Indicates device At the node Signal strength below, This represents the maximum signal strength of all devices across all nodes. Indicates equipment At the node The following network load balancing indicators This represents the maximum network load balancing metric for all devices across all nodes. It is the total number of terms in the weighted average; S313: Based on the device connection sorting result, mark the high-priority device as having priority connection right, and postpone the connection of the remaining devices. At the same time, call the connection request sorting table to sort the postponed devices again to obtain the access priority index.

6. The method for remote collaborative control of intelligent devices based on the Internet of Things according to claim 1, characterized in that, The specific steps for obtaining the task load management information are as follows: S411: Based on the access priority index, evaluate the real-time task queue data and current memory usage data of the connected devices, compare the number of task requests with the set device request capacity, memory usage and memory capacity, determine the current load level of the device, and obtain the device load judgment result; S412: Based on the equipment load judgment result, the following formula is used: ； Calculate task allocation offset value ,in, This represents the data processing performance parameters of the device. This represents the current number of task requests for the device. Represents the task response rate. Represents the device's free memory capacity. For adjustment coefficients; S413: Based on the task allocation offset value, the number of device task requests is proportionally redistributed, and the scheduling information field is reconstructed in conjunction with the original task queue structure to obtain task load management information.

7. The method for remote collaborative control of intelligent devices based on the Internet of Things according to claim 1, characterized in that, The specific steps for obtaining the device connection control feedback result are as follows: The task load management information is invoked, and based on the current working status of the smart device, the correspondence between task execution frequency and memory usage rate is compared to determine whether the task load exceeds the standard. The task load change trend is determined by combining the number of threads of the smart device and the task cycle interval. Based on the aforementioned task load change trend, the matching degree between task load and connection cycle is analyzed. According to the changes in task frequency and device connection success rate, the device connection frequency and task cycle configuration are adjusted synchronously to obtain device connection control feedback results.

8. A remote collaborative control system for intelligent devices based on the Internet of Things, characterized in that, The system is used to implement the IoT-based remote collaborative control method for smart devices as described in any one of claims 1-7, and the system comprises: The device status monitoring module is based on the Internet of Things platform. It monitors the CPU utilization and memory usage of smart devices, collects the status data of smart devices regularly, and dynamically adjusts the data transmission interval by analyzing the performance of smart devices in real time to obtain a device performance monitoring dataset. Based on the device performance monitoring dataset, the network load management module obtains the bandwidth utilization, signal strength and network response time of the smart devices in the edge network, compares the network parameters, identifies and adjusts the network nodes whose load has reached the upper limit, and obtains the network load balance index. Based on the network load balancing index, the device access priority module analyzes the CPU utilization and memory usage of smart devices, and automatically prioritizes connection requests according to the response time and signal strength of network nodes, marking high-priority devices as having priority connection rights, and delaying the connection of other devices, thus obtaining the access priority index. Based on the access priority index, the intelligent task scheduling module evaluates the task queue length and memory usage of connected devices, adjusts the task allocation ratio according to the data processing performance of the devices, and obtains task load management information. The connection dynamic control module calls the task load management information to analyze task execution density and memory usage, dynamically adjusts the connection time interval and task cycle to match real-time task requirements, and synchronously adjusts the device connection frequency to obtain device connection control feedback results.

Images