Communication performance optimization method and system based on Internet of Things

Abstract

The present invention relates to the field of signal communication transmission technology, a communication performance optimization method and system based on the Internet of Things, including: obtaining real-time monitoring data and merging and formatting to obtain a data set to be transmitted; obtaining a task set in the edge node set, and obtaining an edge node state set; using a pre-built task scheduling algorithm, scheduling the task set according to the task set and the edge node state set to obtain a scheduled edge node set; performing edge computing on the scheduled edge node set to obtain a primary processing data set; preliminarily deleting the service set according to the user preference portrait to obtain a candidate service set; using a service composite strategy generation model to composite the candidate service set to obtain a composite service sequence, using the composite service sequence to calculate and process the primary processing data set, and sending the service processing result to a pre-built cloud storage space. The present invention can improve the data communication efficiency of the Internet of Things.

Description

Technical Field

[0001] The present invention relates to the field of signal communication transmission technology, and in particular to a communication performance optimization method and system based on the Internet of Things. Background Art

[0002] The Internet of Things (IoT) refers to connecting various physical devices, sensors, controllers and other smart devices through the network to collect, transmit and process data. The application scope of the IoT is wide, and now includes smart homes, smart cities, industrial automation, medical health and other fields.

[0003] However, in order to further improve the intelligence of IoT life, more and more terminal devices, services and tasks are integrated into a single IoT platform. This leads to problems such as low system resource utilization, increased latency, and increased bandwidth and computing resource costs, which in turn makes the communication efficiency of IoT gradually deteriorate. Slow and unstable communication speeds greatly reduce the user experience. Summary of the invention

[0004] The present invention provides a communication performance optimization method based on the Internet of Things, the main purpose of which is to improve the data communication efficiency of the Internet of Things.

[0005] To achieve the above-mentioned purpose, the present invention provides a communication performance optimization method based on the Internet of Things, comprising: using a terminal device cluster in a pre-built Internet of Things platform to collect a real-time monitoring data set, and formatting the real-time monitoring data set according to a preset data processing strategy to obtain a data set to be transmitted, wherein each terminal device in the terminal device cluster is equipped with an edge node, and each edge node is connected according to a pre-built edge gateway, and each edge node is combined to obtain an edge node set; using the edge gateway, obtaining a task set in the edge node set, and obtaining the edge node status of each edge node in the edge node set to obtain an edge node status set, wherein there are multiple tasks in an edge node, and one task is distributed to multiple edge nodes, and the edge node status includes computing power, resource utilization, power consumption and the total number of edge nodes; using the pre-built A task scheduling algorithm is used to schedule the data set to be transmitted to each edge node in the edge node set according to the task set and the edge node state set, so as to obtain a scheduled edge node set, and to perform edge computing on the data set to be transmitted by using the scheduled edge node set to obtain a primary processed data set; a service set called by the edge node set according to the primary processed data set is obtained, and a user preference profile of a user of the Internet of Things platform is obtained, and the service set is preliminarily deleted according to the user preference profile to obtain a candidate service set; a pre-trained service composite strategy generation model is used to perform a service composite operation based on service quality calculation on the candidate service set to obtain a composite service sequence; the primary processed data set is calculated and processed by using the composite service sequence to obtain a service processing result, and the service processing result is sent to a pre-built cloud storage space.

[0006] Optionally, the real-time monitoring data set is formatted according to a preset data processing strategy to obtain a data set to be transmitted, including: according to the preset data processing strategy, performing a data cleaning operation based on missing values, outliers and noise on the real-time monitoring data set to obtain a cleaned data set; performing a data filtering operation based on preset filtering conditions on the cleaned data set to obtain a valid monitoring data set, and performing a time alignment operation on the valid monitoring data set to obtain a synchronized monitoring data set; identifying the data type of each synchronized monitoring data in the synchronized monitoring data set, using the data type to query a pre-constructed data formatting standard table to obtain the standard strategy corresponding to each data type, and performing a data formatting operation on the synchronized monitoring data set according to each standard strategy to obtain the data set to be transmitted.

[0007] Optionally, the use of a pre-built task scheduling algorithm, according to the task set and the edge node state set, schedules the data set to be transmitted to each edge node in the edge node set to obtain a scheduled edge node set, including: extracting a target task from the task set in turn; using the pre-built task scheduling algorithm to calculate the time overhead, energy overhead and total execution overhead of the target task on each edge node; obtaining a task unloading strategy, and calculating the unloading time overhead and unloading energy overhead when the edge node unloads the target task according to the task unloading strategy, time overhead and energy overhead, and performing weighted calculation on the unloading time overhead and unloading energy overhead to obtain the unloading total overhead; calculating the difference between the total execution overhead and the total unloading overhead to obtain the system total overhead, and minimizing the system total overhead to obtain a task unloading distribution with a minimum value of the system total overhead, wherein the task unloading distribution is expressed as:

[0008] , where Indicates the target task The distribution of task offloading, Indicates the target task In the The total execution overhead on edge nodes is Indicates that from the edge node The total offloading cost of offloading the target task, represents the total number of edge nodes, Represents a minimum value function; summarizes the task offloading distribution corresponding to each task in the task set to obtain a task scheduling strategy set, and schedules the data set to be transmitted to each edge node in the edge node set according to the task scheduling strategy set to obtain a scheduled edge node set.

[0009] Optionally, the calculating the time cost, energy cost and total execution cost of the target task on each edge node includes: obtaining the computing resource amount of the target task, and calculating the time cost according to the computing resource amount and computing power, and calculating the energy cost according to the computing resource amount and resource utilization; performing weighted calculation on the time cost and energy cost to obtain the total execution cost, wherein the total execution cost is expressed as:

[0010] , , , where and is the weight coefficient, Indicates the target task In the The time overhead on the edge nodes is Indicates the target task In the The amount of computing resources required by an edge node to complete the task, Indicates The computing power of edge nodes, Indicates the target task In the The energy consumption on the edge nodes is Indicates The resource utilization on each edge node.

[0011] Optionally, the total offloading overhead is expressed as:

[0012] , , , where is the task offloading strategy, indicating that the task is offloaded from the edge node Offloading to edge nodes , Indicates edge nodes Belongs to the edge node set In, when , indicating that the task is on the edge node When the task calculation is performed in When , it indicates that the task is offloaded to the edge node Perform task calculations in Indicates the target task The size of the input data, Represents an edge node To edge node The data transmission impedance between Represents an edge node of power consumption.

[0013] Optionally, obtaining a user preference portrait of a user of the Internet of Things platform includes: obtaining user interaction records of the Internet of Things, using a pre-built data analysis tool to perform feature extraction operations on the user interaction records based on access frequency, usage duration and preferred functions, to obtain user preference tags and tag proportions; constructing a user preference portrait based on the user preference tags and tag proportions; obtaining a user questionnaire based on a preset time frequency, and updating parameters of the user preference portrait based on the user questionnaire to obtain a real-time updated user preference portrait.

[0014] Optionally, the service set is preliminarily deleted according to the user preference portrait to obtain a candidate service set, including: calculating the service quality of each service in the service set to obtain a service quality sequence set; summing up the average of each service quality sequence in the service quality sequence set to obtain a comprehensive service quality score set, wherein the service quality sequence includes cost, response time, reliability and availability; performing weighted calculation on each comprehensive service quality score in the comprehensive service quality score set according to the user preference portrait to obtain a preferred service quality score; according to a preset deletion threshold, deleting services in the service set whose preferred service quality scores are lower than the deletion threshold to obtain a candidate service set.

[0015] Optionally, the use of a pre-trained service composite strategy generation model to perform a service composite operation based on service quality calculation on the candidate service set to obtain a composite service sequence includes: using a pre-trained service composite strategy generation model to perform a feature recognition operation on the candidate service set to obtain a virtual service set; randomly compounding each virtual service in the virtual service set to obtain a virtual composite service sequence; calculating the service quality of the virtual composite service sequence according to a pre-constructed composite service quality calculation table to obtain a virtual service quality score; and traversing and combining the virtual service set along the direction in which the virtual service quality score gradually increases according to a pre-constructed genetic algorithm to obtain a composite service sequence when the virtual service quality score is maximum.

[0016] Optionally, sending the service processing result to a pre-built cloud storage space includes: using the edge gateway to perform data aggregation operations on the service processing results generated by each edge node to obtain an aggregated service processing result; obtaining the real-time network load, and adjusting the pre-built initialization network bandwidth according to a preset adjustment strategy and the real-time network load to obtain an adaptive network bandwidth; using a pre-built strong encryption algorithm to encrypt the aggregated service processing result to obtain an encrypted service result, and transmitting the encrypted service result to the pre-built cloud storage space according to the adaptive network bandwidth.

[0017] To achieve the above-mentioned purpose, the present invention also provides a communication performance optimization system based on the Internet of Things, including: a terminal information collection module, which is used to use a terminal device cluster in a pre-built Internet of Things platform to collect a real-time monitoring data set, and format the real-time monitoring data set according to a preset data processing strategy to obtain a data set to be transmitted, wherein each terminal device in the terminal device cluster is equipped with an edge node, and each edge node is connected according to a pre-built edge gateway, and each edge node is combined to obtain an edge node set; an edge node state identification module, which is used to use the edge gateway to obtain a task set in the edge node set, and obtain the edge node state of each edge node in the edge node set to obtain an edge node state set, wherein there are multiple tasks in an edge node, and a task is assigned to multiple edge nodes, and the edge node state includes computing power, resource utilization, power consumption and the total number of edge nodes; a task scheduling module, which is used to Using a pre-built task scheduling algorithm, according to the task set and the edge node state set, the data set to be transmitted is scheduled to each edge node in the edge node set to obtain a scheduled edge node set, and the scheduled edge node set is used to perform edge computing on the data set to be transmitted to obtain a primary processed data set; a service compound module is used to obtain a service set called by the edge node set according to the primary processed data set, and to obtain a user preference profile of the user of the Internet of Things platform, and to perform a preliminary deletion of the service set according to the user preference profile to obtain a candidate service set, and to use a pre-trained service compound strategy generation model to perform a service compound operation based on service quality calculation on the candidate service set to obtain a composite service sequence; an edge computing result transmission module is used to use the composite service sequence to perform computational processing on the primary processed data set to obtain a service processing result, and to send the service processing result to a pre-built cloud storage space.

[0018] In order to solve the above problem, the present invention also provides an electronic device, which includes: a memory storing at least one instruction; and a processor executing the instructions stored in the memory to implement the above-mentioned communication performance optimization method based on the Internet of Things.

[0019] In order to solve the above problem, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned communication performance optimization method based on the Internet of Things.

[0020] The present invention solves the problem described in the background technology. The present invention first obtains a real-time monitoring data set collected by a terminal device, and then obtains a data set to be transmitted through formatting processing. The formatting processing can delete useless parts of the data collected by the terminal device, reduce the amount of data processing, and increase data availability, thereby improving the efficiency and accuracy of subsequent processing calculations. Then, the present invention obtains tasks in each edge node to obtain a task set, and obtains an edge node state set of the edge node. The edge node state includes computing power, resource utilization, power consumption, and the total number of edge nodes. The computing power distribution of the edge node can be understood, so as to better call tasks, so that each task can be executed in the most suitable edge node. The present invention uses a task scheduling algorithm to find a scheduling method with the minimum resource overhead by comparing the total overhead of executing tasks and unloading tasks. Then, each edge node of the present invention can call different services, but when there are many services, they need to be combined into a composite service to reduce the number of data transfers and improve service call efficiency and processing efficiency. The present invention maximizes the service composite efficiency by combining user preferences and genetic algorithms, thereby obtaining an edge computing part of the Internet of Things platform using a composite service sequence, obtaining a service processing result, and sending it to a cloud storage space. Therefore, the present invention can improve the data communication efficiency of the Internet of Things. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A flow chart of a method for optimizing communication performance based on the Internet of Things provided by one embodiment of the present invention; Figure 2 A functional module diagram of a communication performance optimization system based on the Internet of Things provided by an embodiment of the present invention; Figure 3 A schematic diagram of the structure of an electronic device for implementing the communication performance optimization method based on the Internet of Things provided by an embodiment of the present invention.

[0022] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0023] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0024] The embodiment of the present application provides a method for optimizing communication performance based on the Internet of Things. The execution subject of the method for optimizing communication performance based on the Internet of Things includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the method for optimizing communication performance based on the Internet of Things can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0025] Reference Figure 1 As shown, it is a flow chart of a communication performance optimization method based on the Internet of Things provided by an embodiment of the present invention. In this embodiment, the communication performance optimization method based on the Internet of Things includes: S1, using a terminal device cluster in a pre-built Internet of Things platform to collect a real-time monitoring data set, and formatting the real-time monitoring data set according to a preset data processing strategy to obtain a data set to be transmitted, wherein each terminal device in the terminal device cluster is equipped with an edge node, and each edge node is connected according to a pre-built edge gateway, and each edge node is combined to obtain an edge node set.

[0026] In an embodiment of the present invention, the Internet of Things platform refers to connecting various physical devices, sensors, controllers and other intelligent devices through a network to realize data collection, transmission and processing, such as a vehicle signal platform, a school teaching equipment management platform, road intelligent monitoring, etc.

[0027] Taking road monitoring as an example, the terminal device cluster includes speed meters and surveillance cameras, and there is an edge node near each terminal device. The edge node has certain energy resources and computing resources and can perform preliminary processing on the collected data, such as formatting.

[0028] In detail, in an embodiment of the present invention, the real-time monitoring data set is formatted according to a preset data processing strategy to obtain a data set to be transmitted, including: according to the preset data processing strategy, the real-time monitoring data set is subjected to a data cleaning operation based on missing values, outliers and noise to obtain a cleaned data set; the cleaned data set is subjected to a data filtering operation based on preset filtering conditions to obtain a valid monitoring data set, and the valid monitoring data set is subjected to a time alignment operation to obtain a synchronized monitoring data set; the data type of each synchronized monitoring data in the synchronized monitoring data set is identified, a pre-constructed data formatting standard table is queried using the data type to obtain a standard strategy corresponding to each data type, and a data formatting operation is performed on the synchronized monitoring data set according to each standard strategy to obtain a data set to be transmitted.

[0029] The data processing strategy refers to the method and order of data processing, which may include missing value processing, outlier processing, noise reduction, conditional filtering, data synchronization and format standardization.

[0030] Specifically, the embodiment of the present invention uses a database tool to process missing values ​​and abnormal values ​​according to the data processing strategy, and then uses a Gaussian filter algorithm to perform a noise reduction operation on the data, and then further deletes the cleaned data set according to the filtering conditions, such as the edge of the image needs to be deleted, and then aligns the data through the time axis to obtain a synchronous monitoring data set. Finally, the present invention queries each data type and performs format standardization, such as converting data types, such as converting strings to numbers, floating point numbers to integers, etc., or ensuring that data units such as speed and time are unified, such as temperature data is unified as Celsius or Fahrenheit.

[0031] In addition, in the embodiment of the present invention, each edge node can be connected by wire or wirelessly through an edge gateway, so that in special cases, the data collected by each terminal device can be sent to other edge nodes for calculation, thereby increasing the system stability of the Internet of Things platform. The edge gateway is a bridge connecting edge nodes and network resources such as cloud storage space and cloud services.

[0032] S2. Utilize the edge gateway to obtain a task set in the edge node set, and obtain an edge node status of each edge node in the edge node set, to obtain an edge node status set, wherein there are multiple tasks in an edge node, and one task is distributed to multiple edge nodes, and the edge node status includes computing power, resource utilization, power consumption and the total number of edge nodes.

[0033] It should be understood that the task refers to a set of operations or activities that need to be performed, usually has a clear start and end, and can be independent or a combination of multiple tasks.

[0034] Specifically, in the embodiment of the present invention, a task set in the edge node is first obtained, such as data processing tasks, image processing tasks, text processing tasks, and system backup tasks, etc. There are multiple tasks in one edge node, and one task is distributed to multiple edge nodes.

[0035] Furthermore, in the embodiment of the present invention, it is also necessary to obtain the edge node status of each edge node in the edge node set to obtain an edge node status set.

[0036] Specifically, the edge node status set obtained in the embodiment of the present invention includes computing power, resource utilization, power consumption and the total number of edge nodes. According to the edge node status set, it can be known whether each edge node is working normally, whether the working computing power is relaxed or tense, etc.

[0037] S3. Using a pre-built task scheduling algorithm, according to the task set and the edge node status set, schedule the data set to be transmitted to each edge node in the edge node set to obtain a scheduled edge node set, and use the scheduled edge node set to perform edge computing on the data set to be transmitted to obtain a primary processed data set.

[0038] In an embodiment of the present invention, the task scheduling algorithm is a method with lower overhead of selecting a local edge node to execute a task or offloading the task to another edge node to execute the task. If the overhead of executing the task by itself is low, it is executed by itself; if the overhead of offloading the task to another edge node is low, it is offloaded to another edge node.

[0039] Furthermore, edge computing refers to performing calculations near the IoT terminal without uploading to the cloud for calculation, which reduces the amount of data transmission.

[0040] In detail, in an embodiment of the present invention, the use of a pre-constructed task scheduling algorithm, according to the task set and the edge node state set, schedules the data set to be transmitted to each edge node in the edge node set to obtain a scheduled edge node set, including: extracting a target task from the task set in turn; using the pre-constructed task scheduling algorithm, calculating the time overhead, energy overhead and total execution overhead of the target task on each edge node; obtaining a task unloading strategy, and calculating the unloading time overhead and unloading energy overhead when the edge node unloads the target task according to the task unloading strategy, time overhead and energy overhead, and performing weighted calculation on the unloading time overhead and unloading energy overhead to obtain the unloading total overhead; calculating the difference between the execution total overhead and the unloading total overhead to obtain the system total overhead, and minimizing the system total overhead to obtain a task unloading distribution with the minimum value of the system total overhead, wherein the task unloading distribution is expressed as:

[0041] , where Indicates the target task The distribution of task offloading, Indicates the target task In the The total execution overhead on edge nodes is Indicates that from the edge node The total offloading cost of offloading the target task, represents the total number of edge nodes, Represents a minimum value function; summarizes the task offloading distribution corresponding to each task in the task set to obtain a task scheduling strategy set, and schedules the data set to be transmitted to each edge node in the edge node set according to the task scheduling strategy set to obtain a scheduled edge node set.

[0042] In the embodiment of the present invention, the most suitable edge node for each target task is selected by traversing the target tasks, thereby ensuring the normal and efficient execution of the target tasks.

[0043] In detail, in an embodiment of the present invention, the calculation of the time cost, energy cost and total execution cost of the target task on each edge node includes: obtaining the computing resource amount of the target task, and calculating the time cost according to the computing resource amount and computing power, and calculating the energy cost according to the computing resource amount and resource utilization; performing weighted calculation on the time cost and energy cost to obtain the total execution cost, wherein the total execution cost is expressed as:

[0044] , , , where and is the weight coefficient, Indicates the target task In the The time overhead on the edge nodes is Indicates the target task In the The amount of computing resources required by an edge node to complete the task, Indicates The computing power of edge nodes, Indicates the target task In the The energy consumption on the edge nodes is Indicates The resource utilization on each edge node.

[0045] In an embodiment of the present invention, the time overhead is calculated based on the ratio of the amount of computing resources to the computing power, the energy overhead is calculated by multiplying the amount of computing resources by the resource utilization rate, and then the total execution overhead of executing the target task is obtained through weighted calculation of the time overhead and the energy overhead.

[0046] Furthermore, the task offloading strategy refers to constructing a binary number ,when , indicating that the task is on the edge node When the task calculation is performed in When , it indicates that the task is offloaded to the edge node Perform task calculations in .

[0047] In detail, in the embodiment of the present invention, the total offloading overhead is expressed as:

[0048] , , , where is the task offloading strategy, indicating that the task is offloaded from the edge node Offloading to edge nodes , Indicates edge nodes Belongs to the edge node set In, when , indicating that the task is on the edge node When the task calculation is performed in When , it indicates that the task is offloaded to the edge node Perform task calculations in Indicates the target task The size of the input data, Represents an edge node To edge node The data transmission impedance between Represents an edge node of power consumption.

[0049] In an embodiment of the present invention, the purpose of the task calling algorithm is to find an optimal scheduling strategy to minimize the overall overhead of the Internet of Things platform system. The total system overhead can be obtained by calculating the difference between the total execution overhead and the total unloading overhead, and then minimized to obtain the task unloading distribution, wherein the task unloading distribution includes whether unloading is required and, if unloading is required, to which specific edge node it needs to be transferred.

[0050] In the embodiment of the present invention, the task offloading distributions corresponding to the various tasks are merged to obtain a task scheduling strategy set, and then tasks are allocated according to the task scheduling strategy set to obtain a scheduled edge node set.

[0051] S4. Obtain a service set called by the edge node set according to the primary processing data set, obtain a user preference profile of a user of the Internet of Things platform, and preliminarily delete the service set according to the user preference profile to obtain a candidate service set.

[0052] It should be known that the service refers to a module or component that provides specific functions or business logic and can be called and used by other applications, systems or users. Compared with the above tasks, services are larger in scale, such as identity authentication services, database services, temperature monitoring services, lighting control services, security monitoring services, etc., while tasks are smaller, such as collecting temperature data, switches, etc., and detecting the status of doors and windows.

[0053] Specifically, in the embodiment of the present invention, the primary processing data set is first obtained to check which service sets need to be called, such as some phased services and services manually controlled by the user do not need to be called. Although the number of services called according to the primary processing data set has been reduced in magnitude, there are still many that need to be further reduced.

[0054] In the embodiment of the present invention, a user preference profiling method is adopted to delete services related to functions that are not frequently used by users or data that are not frequently viewed by users, thereby obtaining a candidate service set.

[0055] In detail, in an embodiment of the present invention, obtaining a user preference portrait of a user of the Internet of Things platform includes: obtaining user interaction records of the Internet of Things, using a pre-built data analysis tool to perform feature extraction operations on the user interaction records based on access frequency, usage duration and preferred functions, to obtain user preference tags and tag proportions; constructing a user preference portrait based on the user preference tags and tag proportions; obtaining a user questionnaire based on a preset time frequency, and updating parameters of the user preference portrait based on the user questionnaire to obtain a real-time updated user preference portrait.

[0056] In an embodiment of the present invention, the user interaction record includes the functions used by the user through the Internet of Things platform, or the frequency of viewing a certain data. The present invention uses the Google Analytics data analysis tool to identify the user's preference characteristics and obtain the user's preference label and label weight. In addition, the present invention can also use a pre-trained neural network or ELKStack tool to achieve the above operation, and is not limited to a specific tool.

[0057] Furthermore, after obtaining the user preference labels and label proportions, the embodiment of the present invention can construct a neural network through a pre-constructed portrait, construct a portrait according to the user preference labels and label proportions, and obtain a user preference portrait. In order to increase the real-time accuracy of the user preference portrait and reduce the use of unpopular functions by users, and the situation where the unpopular function data service starts slowly, the user preference portrait can be updated periodically through a pre-constructed user questionnaire. Among them, the user questionnaire can be: which functions do you expect to achieve a quick response, which data and functions do you think are redundant, etc.

[0058] Furthermore, in an embodiment of the present invention, the service set is preliminarily deleted according to the user preference profile to obtain a candidate service set, including: calculating the service quality of each service in the service set to obtain a service quality sequence set; summing up the average of each service quality sequence in the service quality sequence set to obtain a comprehensive service quality score set, wherein the service quality sequence includes cost, response time, reliability and availability; weighted calculation of each comprehensive service quality score in the comprehensive service quality score set according to the user preference profile to obtain a preferred service quality score; and according to a preset deletion threshold, deleting services in the service set whose preferred service quality scores are lower than the deletion threshold to obtain a candidate service set.

[0059] Specifically, in the embodiment of the present invention, the service quality includes: cost, response time, reliability and availability.

[0060] Among them, the cost represents the cost of executing the service, which is generally provided by the service provider; the response time represents the average time cost from the user making a service request to the service being fully executed, and the common unit is seconds or milliseconds. Because the service is provided by the IoT device alone, the service response time is also dynamically changing, affected by factors such as the transmission rate, state, stability of the network and the performance of the device itself, and therefore becomes an important indicator of service quality; the reliability service reliability refers to the probability that the service can be accurately executed, which is the ratio of the number of successful executions of the service to the total number of executions of the service; the availability represents the probability that the service can be called normally within a certain interval, which is the ratio of the number of successful service accesses to the total number of service accesses within a certain time period, and is usually converted into a percentage. If the availability index is high, it means that it can be successfully accessed "all the time" within a certain time period; otherwise, it means that the probability of the service being successfully accessed within the interval is small.

[0061] The present invention first calculates multiple tags of a single service, and then performs weighted calculation through user preference profiles to obtain a preferred service quality score. Finally, the score is controlled by a preset deletion threshold, and the services in the service set whose preferred service quality scores are lower than the deletion threshold are deleted to obtain a candidate service set. The deletion threshold can be adjusted according to the application scenario and service function of the specific IoT platform.

[0062] S5. Using the pre-trained service composite strategy generation model, perform a service composite operation based on service quality calculation on the candidate service set to obtain a composite service sequence.

[0063] In the embodiment of the present invention, the service composite strategy generation model is a service random composite model based on a genetic algorithm, with the minimum comprehensive service quality score of the composite service as the composite direction, and the goal is to ultimately obtain a composite service sequence with the minimum comprehensive service quality score.

[0064] In detail, in an embodiment of the present invention, the pre-trained service composite strategy generation model is used to perform a service composite operation based on service quality calculation on the candidate service set to obtain a composite service sequence, including: using the pre-trained service composite strategy generation model, performing a feature recognition operation on the candidate service set to obtain a virtual service set; randomly compounding each virtual service in the virtual service set to obtain a virtual composite service sequence; calculating the service quality of the virtual composite service sequence according to a pre-constructed composite service quality calculation table to obtain a virtual service quality score; and according to a pre-constructed genetic algorithm, traversing and combining the virtual service set along the direction in which the virtual service quality score gradually increases to obtain a composite service sequence when the virtual service quality score is maximum.

[0065] Specifically, in the embodiment of the present invention, the composite service after compounding has changed in structure compared with the single service, so the service quality calculation method of the composite service has also changed, wherein the composite structure in the composite service includes a sequential structure, a parallel structure, a branch structure and a loop structure. The embodiment of the present invention arranges the calculation methods of each service quality indicator of each composite structure according to the following Table 1:

[0066]

[0067] Table 1 is a service quality calculation table for different composite structures. In the embodiment of the present invention, the type of the composite service and the calculation algorithm of each service quality index are found according to the above table, where: Indicates the composite function The quality score function of a service, Indicates the composite structure The weight of the service, K represents the Kth service quality indicator, and n represents the total number of services in the composite service. Thus, the service quality of the virtual composite service sequence is calculated to obtain a virtual service quality score.

[0068] Furthermore, the embodiment of the present invention continuously combines various services according to the genetic algorithm to obtain composite services, and calculates the composite service sequence with the maximum virtual service quality score. The genetic algorithm is an optimization and search algorithm based on natural selection and genetics principles, which can imitate the process of biological evolution and find the optimal solution or approximate optimal solution to the problem through operations such as selection, crossover, and mutation. The present invention can improve the efficiency of finding the maximum value of the virtual service quality score through the genetic algorithm and reduce the number of data calculations.

[0069] S6. Utilize the composite service sequence to perform computational processing on the primary processing data set to obtain a service processing result, and send the service processing result to a pre-built cloud storage space.

[0070] In the embodiment of the present invention, after the composite service sequence is found, edge computing can be directly performed to obtain the service processing result, thereby increasing the computing execution efficiency of the IoT platform on the edge side, reducing data transmission, and only the final service processing result needs to be uploaded.

[0071] Furthermore, in an embodiment of the present invention, the sending of the service processing result to a pre-built cloud storage space includes: utilizing the edge gateway to perform data aggregation operations on the service processing results generated by each edge node to obtain an aggregated service processing result; obtaining a real-time network load, and adjusting a pre-built initialization network bandwidth according to a preset adjustment strategy and the real-time network load to obtain an adaptive network bandwidth; utilizing a pre-built strong encryption algorithm to encrypt the aggregated service processing result to obtain an encrypted service result, and transmitting the encrypted service result to a pre-built cloud storage space according to the adaptive network bandwidth.

[0072] The service processing result may be a record of a successful service operation, or a final result generated by a service, such as a record of automatic adjustment of the indoor temperature according to the ambient temperature, or a license plate number of a speeding vehicle automatically captured by the traffic environment.

[0073] Furthermore, the adjustment strategy is an adaptive network configuration, which performs fluctuation adjustment on the network bandwidth within a certain area according to the percentage change of the size of the network load.

[0074] Specifically, in the embodiment of the present invention, an edge gateway is used to aggregate data before the service processing result is transmitted, data redundancy is reduced, and invalid data is discarded through filtering technology. In addition, the present invention also adopts an adaptive network configuration method to automatically detect the real-time network load and select adaptive network bandwidth for data transmission. And the present invention also encrypts the aggregated service processing results through the AES strong encryption algorithm to ensure that the data is not stolen or tampered with during the transmission process, so as to efficiently and securely transmit the data to the pre-built cloud storage space. Among them, the cloud storage space is a bridge connecting the user and the terminal device, and the user can obtain historical data or perform special services through the cloud storage space.

[0075] The present invention solves the problem described in the background technology. The present invention first obtains a real-time monitoring data set collected by a terminal device, and then obtains a data set to be transmitted through formatting processing. The formatting processing can delete useless parts of the data collected by the terminal device, reduce the amount of data processing, and increase data availability, thereby improving the efficiency and accuracy of subsequent processing calculations. Then, the present invention obtains tasks in each edge node to obtain a task set, and obtains an edge node state set of the edge node. The edge node state includes computing power, resource utilization, power consumption, and the total number of edge nodes. The computing power distribution of the edge node can be understood, so as to better call tasks, so that each task can be executed in the most suitable edge node. The present invention uses a task scheduling algorithm to find a scheduling method with the minimum resource overhead by comparing the total overhead of executing tasks and unloading tasks. Then, each edge node of the present invention can call different services, but when there are many services, they need to be combined into a composite service to reduce the number of data transfers and improve service call efficiency and processing efficiency. The present invention maximizes the service composite efficiency by combining user preferences and genetic algorithms, thereby obtaining an edge computing part of the Internet of Things platform using a composite service sequence, obtaining a service processing result, and sending it to a cloud storage space. Therefore, the present invention can improve the data communication efficiency of the Internet of Things.

[0076] like Figure 2 , which is a functional module diagram of a communication performance optimization system based on the Internet of Things provided by an embodiment of the present invention.

[0077] The communication performance optimization system 100 based on the Internet of Things of the present invention can be installed in an electronic device. According to the functions implemented, the communication performance optimization system 100 based on the Internet of Things can include a terminal information collection module 101, an edge node state identification module 102, a task scheduling module 103, a service compound module 104 and an edge computing result transmission module 105. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0078] The terminal information collection module 101 is used to use the terminal device cluster in the pre-built Internet of Things platform to collect a real-time monitoring data set, and format the real-time monitoring data set according to a preset data processing strategy to obtain a data set to be transmitted, wherein each terminal device in the terminal device cluster is equipped with an edge node, and each edge node is connected according to a pre-built edge gateway, and each edge node is combined to obtain an edge node set; the edge node state identification module 102 is used to use the edge gateway to obtain a task set in the edge node set, and obtain the edge node state of each edge node in the edge node set to obtain an edge node state set, wherein there are multiple tasks in an edge node, and a task is assigned to multiple edge nodes, and the edge node state includes computing power, resource utilization, power consumption and the total number of edge nodes; the task scheduling module 103 is used to use a pre-built task scheduling algorithm, based on According to the task set and the edge node status set, the data set to be transmitted is scheduled to each edge node in the edge node set to obtain a scheduled edge node set, and the scheduled edge node set is used to perform edge computing on the data set to be transmitted to obtain a primary processed data set; the service compound module 104 is used to obtain the service set called by the edge node set according to the primary processed data set, and to obtain the user preference profile of the user of the Internet of Things platform, and to perform preliminary deletion of the service set according to the user preference profile to obtain a candidate service set, and to use a pre-trained service compound strategy generation model to perform service compound operations based on service quality calculation on the candidate service set to obtain a composite service sequence; the edge computing result transmission module 105 is used to use the composite service sequence to perform computational processing on the primary processed data set to obtain a service processing result, and to send the service processing result to a pre-built cloud storage space.

[0079] In detail, each module in the communication performance optimization system 100 based on the Internet of Things in the embodiment of the present invention is used in the same manner as described above. Figure 1The same technical means as the communication performance optimization method based on the Internet of Things described in the previous section can produce the same technical effects, so they will not be repeated here.

[0080] like Figure 3 , is a schematic diagram of the structure of an electronic device for implementing a method for optimizing communication performance based on the Internet of Things provided by an embodiment of the present invention.

[0081] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a communication performance optimization method program based on the Internet of Things.

[0082] Among them, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 also includes an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the communication performance optimization method program based on the Internet of Things, but also can be used to temporarily store data that has been output or is to be output.

[0083] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules (such as a communication performance optimization method program based on the Internet of Things, etc.) stored in the memory 11, and calls data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

[0084] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0085] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0086] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0087] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0088] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0089] The communication performance optimization method program based on the Internet of Things stored in the memory 11 in the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can be achieved: using the terminal device cluster in the pre-built Internet of Things platform to collect a real-time monitoring data set, and formatting the real-time monitoring data set according to a preset data processing strategy to obtain a data set to be transmitted, wherein each terminal device in the terminal device cluster is equipped with an edge node, and each edge node is connected according to a pre-built edge gateway, and each edge node is combined to obtain an edge node set; using the edge gateway, obtain a task set in the edge node set, and obtain the edge node status of each edge node in the edge node set to obtain an edge node status set, wherein there are multiple tasks in an edge node, and a task is distributed to multiple edge nodes. The edge node status includes computing power, resource utilization, and power consumption. and the total number of edge nodes; using a pre-built task scheduling algorithm, according to the task set and the edge node state set, schedule the data set to be transmitted to each edge node in the edge node set to obtain a scheduled edge node set, and use the scheduled edge node set to perform edge computing on the data set to be transmitted to obtain a primary processed data set; obtain a service set called by the edge node set according to the primary processed data set, and obtain a user preference profile of the user of the Internet of Things platform, and preliminarily prune the service set according to the user preference profile to obtain a candidate service set; using a pre-trained service composite strategy generation model, perform a service composite operation based on service quality calculation on the candidate service set to obtain a composite service sequence; using the composite service sequence, perform computational processing on the primary processed data set to obtain a service processing result, and send the service processing result to a pre-built cloud storage space.

[0090] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0091] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0092] The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor of an electronic device, it can achieve: using a terminal device cluster in a pre-built Internet of Things platform to collect a real-time monitoring data set, and formatting the real-time monitoring data set according to a preset data processing strategy to obtain a data set to be transmitted, wherein each terminal device in the terminal device cluster is equipped with an edge node, and each edge node is connected according to a pre-built edge gateway, and each edge node is combined to obtain an edge node set; using the edge gateway, obtaining a task set in the edge node set, and obtaining the edge node status of each edge node in the edge node set to obtain an edge node status set, wherein there are multiple tasks in an edge node, and a task is distributed to multiple edge nodes. The edge node status includes computing power, resource utilization, and power consumption. and the total number of edge nodes; using a pre-built task scheduling algorithm, according to the task set and the edge node state set, schedule the data set to be transmitted to each edge node in the edge node set to obtain a scheduled edge node set, and use the scheduled edge node set to perform edge computing on the data set to be transmitted to obtain a primary processed data set; obtain a service set called by the edge node set according to the primary processed data set, and obtain a user preference profile of the user of the Internet of Things platform, and preliminarily prune the service set according to the user preference profile to obtain a candidate service set; using a pre-trained service composite strategy generation model, perform a service composite operation based on service quality calculation on the candidate service set to obtain a composite service sequence; using the composite service sequence, perform computational processing on the primary processed data set to obtain a service processing result, and send the service processing result to a pre-built cloud storage space.

[0093] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, and actual implementation may have other division methods.

[0094] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0095] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0096] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A communication performance optimization method based on the Internet of Things, characterized in that: The method comprises: using a terminal device cluster in a pre-built Internet of Things platform to collect a real-time monitoring data set, and formatting the real-time monitoring data set according to a preset data processing strategy to obtain a data set to be transmitted, wherein each terminal device in the terminal device cluster is equipped with an edge node, and each edge node is connected according to a pre-built edge gateway, and each edge node is combined to obtain an edge node set; using the edge gateway, obtaining a task set in the edge node set, and obtaining the edge node state of each edge node in the edge node set to obtain an edge node state set, wherein there are multiple tasks in an edge node, and a task is allocated to multiple edge nodes, and the edge node state includes computing power, resource utilization, power consumption and the total number of edge nodes; using a pre-built task scheduling algorithm, based on According to the task set and the edge node state set, the data set to be transmitted is scheduled to each edge node in the edge node set to obtain a scheduled edge node set, including: extracting a target task from the task set in turn; using a pre-built task scheduling algorithm to calculate the time overhead, energy overhead and total execution overhead of the target task on each edge node; obtaining a task unloading strategy, and calculating the unloading time overhead and unloading energy overhead when the edge node unloads the target task according to the task unloading strategy, time overhead and energy overhead, and performing weighted calculation on the unloading time overhead and unloading energy overhead to obtain the unloading total overhead; calculating the difference between the execution total overhead and the unloading total overhead to obtain the system total overhead, and minimizing the system total overhead to obtain a task unloading distribution with a minimum value of the system total overhead, wherein the task unloading distribution is expressed as: , where Indicates the target task The distribution of task offloading, Indicates the target task In the The total execution overhead on edge nodes is Indicates that from the edge node The total offloading cost of offloading the target task, represents the total number of edge nodes, represents a minimum value function; summarizing the task offloading distribution corresponding to each task in the task set to obtain a task scheduling strategy set, and scheduling the data set to be transmitted to each edge node in the edge node set according to the task scheduling strategy set to obtain a scheduled edge node set; The total offloading cost is expressed as: , , , where is the task offloading strategy, indicating that the task is offloaded from the edge node Offloading to edge nodes ,when , indicating that the task is on the edge node When the task calculation is performed in When , it indicates that the task is offloaded to the edge node Perform task calculations in Indicates the target task The size of the input data, Represents an edge node To edge node The data transmission impedance between Represents an edge node power consumption; using the scheduled edge node set, edge computing is performed on the data set to be transmitted to obtain a primary processing data set; obtaining a service set called by the edge node set according to the primary processing data set, and obtaining a user preference profile of the user of the Internet of Things platform, and preliminarily pruning the service set according to the user preference profile to obtain a candidate service set; using a pre-trained service composite strategy generation model, a service composite operation based on service quality calculation is performed on the candidate service set to obtain a composite service sequence; using the composite service sequence, computing and processing the primary processing data set to obtain a service processing result, and sending the service processing result to a pre-built cloud storage space.

2. The method for optimizing communication performance based on the Internet of Things according to claim 1, characterized in that: The real-time monitoring data set is formatted according to a preset data processing strategy to obtain a data set to be transmitted, including: according to the preset data processing strategy, the real-time monitoring data set is subjected to a data cleaning operation based on missing values, abnormal values ​​and noise to obtain a cleaned data set; the cleaned data set is subjected to a data filtering operation based on preset filtering conditions to obtain a valid monitoring data set, and the valid monitoring data set is subjected to a time alignment operation to obtain a synchronized monitoring data set; the data type of each synchronized monitoring data in the synchronized monitoring data set is identified, a pre-constructed data formatting standard table is queried using the data type to obtain a standard strategy corresponding to each data type, and the synchronized monitoring data set is subjected to a data formatting operation according to each standard strategy to obtain a data set to be transmitted.

3. The method for optimizing communication performance based on the Internet of Things according to claim 2, characterized in that: The calculating of the time cost, energy cost and total execution cost of the target task on each edge node includes: obtaining the computing resource amount of the target task, and calculating the time cost according to the computing resource amount and computing power, and calculating the energy cost according to the computing resource amount and resource utilization; performing weighted calculation on the time cost and energy cost to obtain the total execution cost, wherein the total execution cost is expressed as: , , , where and is the weight coefficient, Indicates the target task In the The time overhead on the edge nodes is Indicates the target task In the The amount of computing resources required by an edge node to complete the task, Indicates The computing power of edge nodes, Indicates the target task In the The energy consumption on the edge nodes is Indicates The resource utilization on each edge node.

4. The method for optimizing communication performance based on the Internet of Things according to claim 3, characterized in that: The method of obtaining a user preference portrait of a user of the Internet of Things platform includes: obtaining user interaction records of the Internet of Things, using a pre-built data analysis tool to perform feature extraction operations on the user interaction records based on access frequency, usage duration, and preferred functions, to obtain user preference tags and tag proportions; constructing a user preference portrait based on the user preference tags and tag proportions; obtaining a user questionnaire based on a preset time frequency, and updating parameters of the user preference portrait based on the user questionnaire to obtain a real-time updated user preference portrait.

5. The method for optimizing communication performance based on the Internet of Things according to claim 4, characterized in that: The preliminary deletion of the service set according to the user preference portrait to obtain a candidate service set includes: calculating the service quality of each service in the service set to obtain a service quality sequence set; summing up the average of each service quality sequence in the service quality sequence set to obtain a comprehensive service quality score set, wherein the service quality sequence includes cost, response time, reliability and availability; performing weighted calculation on each comprehensive service quality score in the comprehensive service quality score set according to the user preference portrait to obtain a preferred service quality score; and deleting services in the service set whose preferred service quality scores are lower than the deletion threshold according to a preset deletion threshold to obtain a candidate service set.

6. The method for optimizing communication performance based on the Internet of Things according to claim 5, characterized in that: The method uses a pre-trained service composite strategy generation model to perform a service composite operation based on service quality calculation on the candidate service set to obtain a composite service sequence, including: using a pre-trained service composite strategy generation model to perform a feature recognition operation on the candidate service set to obtain a virtual service set; randomly compositely arranging each virtual service in the virtual service set to obtain a virtual composite service sequence; calculating the service quality of the virtual composite service sequence according to a pre-constructed composite service quality calculation table to obtain a virtual service quality score; and traversing and combining the virtual service set along the direction in which the virtual service quality score gradually increases according to a pre-constructed genetic algorithm to obtain a composite service sequence when the virtual service quality score is maximum.

7. The method for optimizing communication performance based on the Internet of Things according to claim 6, characterized in that: The sending of the service processing result to the pre-built cloud storage space includes: using the edge gateway to perform data aggregation operations on the service processing results generated by each edge node to obtain an aggregated service processing result; obtaining a real-time network load, and adjusting a pre-built initialization network bandwidth according to a preset adjustment strategy and the real-time network load to obtain an adaptive network bandwidth; using a pre-built strong encryption algorithm to encrypt the aggregated service processing result to obtain an encrypted service result, and transmitting the encrypted service result to the pre-built cloud storage space according to the adaptive network bandwidth.

8. A communication performance optimization system based on the Internet of Things, used to execute the communication performance optimization method based on the Internet of Things according to claim 1, characterized in that: The system includes: a terminal information collection module, which is used to use the terminal device cluster in the pre-built Internet of Things platform to collect a real-time monitoring data set, and format the real-time monitoring data set according to a preset data processing strategy to obtain a data set to be transmitted, wherein each terminal device in the terminal device cluster is equipped with an edge node, and each edge node is connected according to a pre-built edge gateway, and each edge node is combined to obtain an edge node set; an edge node state identification module, which is used to use the edge gateway to obtain a task set in the edge node set, and obtain the edge node state of each edge node in the edge node set to obtain an edge node state set, wherein there are multiple tasks in an edge node, and a task is assigned to multiple edge nodes, and the edge node state includes computing power, resource utilization, power consumption and the total number of edge nodes; a task scheduling module, which is used to use a pre-built task scheduling algorithm, According to the task set and the edge node status set, the data set to be transmitted is scheduled to each edge node in the edge node set to obtain a scheduled edge node set, and the scheduled edge node set is used to perform edge computing on the data set to be transmitted to obtain a primary processed data set; a service compound module is used to obtain a service set called by the edge node set according to the primary processed data set, and to obtain a user preference profile of the user of the Internet of Things platform, and to perform a preliminary deletion of the service set according to the user preference profile to obtain a candidate service set, and to use a pre-trained service compound strategy generation model to perform a service compound operation based on service quality calculation on the candidate service set to obtain a composite service sequence; an edge computing result transmission module is used to use the composite service sequence to perform computational processing on the primary processed data set to obtain a service processing result, and to send the service processing result to a pre-built cloud storage space.

Images