Device correlation self-organizing network method, system, terminal and readable storage medium

Abstract

The present invention relates to the field of computer technology, and discloses a device correlation self-organizing network method, system, terminal and readable storage medium, the method comprising: collecting device performance data and device operation data of all devices participating in the networking; performing correlation evaluation on all the devices according to the device operation data to obtain correlation evaluation data; dividing all the devices into different subnets according to the correlation evaluation data, and networking each subnet separately. The present invention reduces the overall complexity of the network by performing correlation analysis on the devices according to the device operation data, and then subnetting the devices in the network dense area according to the device correlation. When in use, it can quickly generate a super device networking template that adapts to a specific application scenario, thereby improving the flexibility of the system and the resource utilization efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to a device correlation self-organizing network method, system, terminal and readable storage medium. Background Art

[0002] With the popularization of IoT devices, the collaborative work of different devices in various application scenarios has become increasingly important. Due to the large number of devices and their different functions, how to divide the various devices and then network them has become a technical challenge.

[0003] Traditional networking methods mostly rely on static configuration and cannot adapt to rapidly changing application requirements and device status. For this reason, the existing technology has proposed a variety of self-organizing networking methods, such as methods of self-organizing devices according to network conditions or device performance. This not only saves manpower configuration at the beginning of networking, but also can be adjusted according to the self-organizing networking method when application requirements and device status change.

[0004] However, when the self-organizing networking method of the prior art is applied to large-scale complex networks, as the number and scale of devices increase, the solvable space of the network also grows explosively, resulting in the infeasibility of obtaining the optimal solution of the network in the solvable space. Therefore, a feasible method is to partition the devices according to their geographical location, thereby reducing the solvable space of each sub-partition and ensuring the smooth progress of the network. However, for densely populated areas of the network, it is difficult to divide the subnets by geographical partitioning. Therefore, if the network density in a certain area exceeds a certain threshold, the solvable space in the area will also expand to the point where it is difficult to solve, or even impossible to solve. Summary of the invention

[0005] The purpose of the present invention is to provide a device-related self-organizing network method, system, terminal and readable storage medium, which is intended to solve the problems of high complexity and difficulty in networking in densely populated areas in the prior art.

[0006] The technical solution adopted by the present invention to solve the technical problem is as follows:

[0007] The present invention provides a device correlation self-organizing network method, the device correlation self-organizing network method comprising:

[0008] Collect equipment performance data and equipment operation data of all equipment involved in the network;

[0009] Performing correlation evaluation on all the devices according to the device operation data to obtain correlation evaluation data;

[0010] All devices are divided into different subnets according to the correlation evaluation data, and each subnet is networked separately.

[0011] Further, the performing correlation evaluation on all the devices according to the device operation data to obtain correlation evaluation data specifically includes:

[0012] Performing co-occurrence analysis on all the devices according to the device operation data to obtain co-occurrence analysis data;

[0013] A correlation evaluation is performed based on the co-occurrence analysis data to obtain the correlation evaluation data.

[0014] Further, performing co-occurrence analysis on all the devices according to the device operation data to obtain co-occurrence analysis data specifically includes:

[0015] Obtaining task contexts of all tasks, and determining a set of devices included in each task according to the task contexts;

[0016] For each of the tasks, the number of co-occurrences between any two devices in the corresponding device set is counted to obtain co-occurrence data;

[0017] Data cleaning and deduplication processing are performed on all the co-occurrence data, and a collection of all the co-occurrence data after data cleaning and deduplication processing is used as the co-occurrence analysis data.

[0018] Further, performing correlation evaluation according to the co-occurrence analysis data to obtain the correlation evaluation data specifically includes:

[0019] According to the equipment operation data, count the total number of events and the number of occurrences of all equipment;

[0020] Calculate the occurrence probability of all devices according to the total number of events and each of the occurrence numbers, and calculate the co-occurrence probability between any two devices according to the total number of events and each of the co-occurrence numbers;

[0021] The point mutual information between any two devices is calculated according to each of the co-occurrence probabilities and each of the occurrence probabilities, and the set of all the point mutual information is used as the correlation evaluation data.

[0022] Furthermore, the method of dividing all devices into different subnets according to the correlation evaluation data and networking each subnet separately includes:

[0023] According to the correlation evaluation data, all devices are divided into different subnets;

[0024] According to the device performance data, each subnet is networked separately.

[0025] Further, all devices are divided into different subnets according to the correlation evaluation data, including multiple iterations of subnet selection, each subnet selection includes:

[0026] According to the correlation evaluation data, a central device with the highest point mutual information is selected;

[0027] According to the central device, multiple devices whose point mutual information with the central device is greater than a set point mutual information threshold are selected as auxiliary devices of the central device;

[0028] The central device and each of the auxiliary devices are taken as a subnet.

[0029] Furthermore, the networking of each subnet is performed according to the device performance data, specifically including:

[0030] According to the device performance data, set the device role of each device in the subnet;

[0031] The network structure of the subnet is set according to the device performance data and the roles of each device.

[0032] In addition, to achieve the above-mentioned purpose, the present invention further provides a device correlation self-organizing network system, the device correlation self-organizing network system comprising:

[0033] Data collection module, used to collect equipment performance data and equipment operation data of all equipment involved in the network;

[0034] A correlation evaluation module, used for performing correlation evaluation on all the devices according to the device operation data to obtain correlation evaluation data;

[0035] The self-organizing network module divides all devices into different subnets according to the correlation evaluation data, and organizes each subnet separately.

[0036] In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal, which includes: a memory, a processor, and a device-related self-organizing network program stored in the memory and executable on the processor, and when the device-related self-organizing network program is executed by the processor, the terminal is controlled to implement the steps of the device-related self-organizing network method as described above.

[0037] In addition, to achieve the above objectives, the present invention also provides a readable storage medium, which stores a device-related self-organizing network program, and when the device-related self-organizing network program is executed by a processor, the steps of the device-related self-organizing network method described above are implemented.

[0038] The present invention adopts the above technical solution to achieve the following effects:

[0039] The present invention performs correlation analysis on devices according to their operating data, and then divides the devices in the densely populated area into subnets according to the correlation of the devices, thereby taking into account the correlation between different devices, establishing connections between devices with high correlation, reducing the overall complexity of the network, thereby reducing the size of the solvable space of the networking calculation, avoiding the problem of networking difficulties caused by too large a solvable space in the densely populated area, and being able to quickly generate a super device networking template that adapts to specific application scenarios when in use, thereby improving the flexibility of the system and the efficiency of resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a flow chart of the steps of a device correlation self-organizing network method in a preferred embodiment of the present invention;

[0041] Figure 2 It is a schematic diagram of the principle of a device correlation self-organizing network system in a preferred embodiment of the present invention;

[0042] Figure 3 It is a schematic diagram of the operating environment of a preferred embodiment of the terminal of the present invention. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. It should be understood that the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments. The specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention. All other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0044] Embodiment 1

[0045] Embodiment 1 of the present application is a device-related self-organizing network method, which can be applied to management terminals of various types of Internet of Things systems, such as management terminals of edge computing systems, management terminals of smart home systems, or management terminals of other types of Internet of Things systems.

[0046] In addition, a device-related self-organizing networking method of the present embodiment can also be run outside the Internet of Things system to provide networking support services for the Internet of Things system. It can be run in a server. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, big data and artificial intelligence platforms.

[0047] See also Figure 1 A device correlation self-organizing network method of this embodiment includes the following steps:

[0048] S1. Collect performance data and operation data of all devices involved in the networking.

[0049] In this embodiment, the device performance data includes the hardware capability data and the software capability data of the devices participating in the networking. The hardware capability data of the devices includes the number of central processing unit (CPU) cores, memory size, network bandwidth and storage capacity. The software capability data of the devices includes supported protocols and special functions, such as image processing capabilities.

[0050] After collecting device performance data, a super object model is constructed based on the device performance data to describe the capabilities of the device, and the model is stored in the super object model database. The device capabilities include static capabilities and dynamic capabilities. Static capabilities include capabilities that do not change with time, such as hardware specifications and supported protocols, and dynamic capabilities include capabilities that change with tasks and time, such as currently available resources.

[0051] In addition, the Super IoT Model also defines additional metadata fields to describe devices, including device manufacturer, firmware version, and geographic location, to support more sophisticated analysis and data management of devices.

[0052] Specifically, the method for collecting device performance data is to deploy a device monitoring module. The device monitoring module regularly collects the status data of each device, including CPU load, memory usage, network latency and throughput, etc., to achieve real-time monitoring of the device. After collecting the device performance data, the device monitoring module uploads the collected device performance data in real time and updates it to the super object model to ensure the validity and accuracy of the device performance data.

[0053] Equipment operation data refers to the record of each task in which the equipment participates, including task number, start time, end time, list of participating equipment, and other information.

[0054] In addition, in this embodiment, the device monitoring module also sets thresholds and rules for each device to automatically monitor abnormal conditions of each device, such as device overload or network fluctuations, and alarms for abnormalities to ensure the overall stable operation of the system.

[0055] S2. Performing a correlation evaluation on all the devices according to the device operation data to obtain correlation evaluation data.

[0056] In this embodiment, considering the need to ensure that each subnet can operate normally, and since each subnet is subsequently networked separately, the interaction performance between subnets is obviously not as good as the interaction performance within the subnet. Therefore, it is necessary to reduce the interaction between subnets and ensure that each device interacts with devices outside the subnet as little as possible. To this end, it is necessary to perform correlation analysis on all devices and assign devices with higher correlation to the same subnet, so as to ensure that the devices communicate only within the subnet as much as possible and reduce the interaction between subnets.

[0057] Specifically, in this embodiment, firstly, a co-occurrence analysis is performed on all devices according to the device operation data to obtain co-occurrence analysis data.

[0058] At the beginning of this step, you first need to define the task context and define which tasks or scenarios fall within the scope of co-occurrence analysis to determine the set of devices involved in each task. Specifically, in a lighting task of a smart home system, it may include light sensors, human presence sensors, and smart bulbs; in an air conditioning task, it may include smart air conditioners, temperature sensors, and humidity sensors. After that, retrieve the device operation records to obtain co-occurrence data, thereby reducing the possibility of misjudgment of co-occurrence.

[0059] In this embodiment, co-occurrence data is obtained for each task. According to the task context corresponding to the task, the device set involved in the task is obtained, and the number of co-occurrences between any two devices in all the devices in the device set is obtained, such as the number of co-occurrences between a light sensor and a temperature sensor. Then, a co-occurrence number matrix is ​​formed based on all the co-occurrence numbers to serve as the co-occurrence analysis data.

[0060] In this embodiment, after the co-occurrence analysis data is obtained, the co-occurrence analysis data is also processed, including data cleaning, normalization and deduplication, wherein data cleaning is to remove incomplete and inconsistent co-occurrence records, such as records that lack task numbers or equipment numbers in tasks, and inconsistent co-occurrence records, such as records with inconsistent co-occurrence information collected from different sources. Normalization is to standardize the data formats of different sources such as device names and task descriptions for subsequent processing. Deduplication is to merge duplicate co-occurrence events to ensure the uniqueness and accuracy of each co-occurrence relationship.

[0061] Afterwards, based on the co-occurrence data, the pointwise mutual information (PMI) data between all devices is calculated, that is, the pointwise mutual information between any two devices is calculated, and then the pointwise mutual information matrix is ​​formed based on all the pointwise mutual information as the correlation evaluation data. Among them, pointwise mutual information is a statistic used to measure the degree of association between two events occurring at the same time, and is usually used in the fields of natural language processing and information retrieval. It expresses the correlation between two events by calculating the ratio of the joint probability of the two events to their independent probability.

[0062] Specifically, the occurrence probability of all devices is counted, and the co-occurrence probability between any two devices is counted in turn. The occurrence probability is the ratio of the number of device occurrences to the total number of events, and the co-occurrence probability is the ratio of the number of co-occurrences of two devices to the total number of events.

[0063] After that, the point mutual information between any two devices is calculated in turn:

[0064] ;

[0065] in, is the point mutual information between the first device x and the second device y, is the co-occurrence probability between the first device x and the second device y, that is, the ratio of the number of co-occurrences between the first device x and the second device y to the total number of events, is the occurrence probability of the first device x, that is, the ratio of the number of occurrences of the first device x to the total number of events, is the occurrence probability of the second device y, that is, the ratio of the number of occurrences of the second device y to the total number of events.

[0066] S3. Divide all devices into different subnets according to the correlation evaluation data, and network each subnet separately.

[0067] In this embodiment, the devices are first divided into different subnets based on the correlation evaluation data, and then the subnets are specifically structured and the device roles are set based on the device performance data.

[0068] Among them, equipment division is performed according to correlation evaluation data. Specifically, subnet selection is performed in multiple iterations. Each time the subnet is selected, a device pair with the highest point mutual information is first selected from the point mutual information matrix, and then a device is selected from the device pair as the central device. The specific selection method can be random selection to save computing resources, or selection can be performed based on the point mutual information between the two devices and all devices. The device pair with the highest point mutual information is usually the device with the highest frequency or the most abundant resources in the task. Then, according to the set point mutual information threshold, the device whose point mutual information with the central device is greater than the point mutual information threshold is selected as a high-correlation device, and the high-correlation device is divided into a subnet as an auxiliary device of the central device.

[0069] Afterwards, the specific structure and device role of each subnet are defined according to the device performance data to generate a subnet template. The device roles include core nodes, edge nodes, and support nodes. This embodiment uses the defined rules and algorithms to automatically generate subnet templates. The generated subnet template contains detailed information such as device lists, device roles, communication protocols, and data flows.

[0070] The specific subnet template generation method can refer to the generation method of the prior art. The prior art proposes a variety of subnet structure networking generation methods based on device performance technology, such as a method for networking based on delay, a method for networking based on computing resources, and a method for networking based on data flow. The networking method used can be one of the above methods or a combination of the above methods, and the present invention does not limit this. For example, it can use the performance data of all devices in a subnet as the state space, the roles and data flows of all devices in a subnet as the action space, and set the reward function with the overall delay as the optimization target, thereby constructing a network solution model, and solving the solution model to obtain a networking solution.

[0071] After completing the networking of all subnets, the overall network can be optimized based on the device performance data. According to actual needs and resource status, the template structure can be optimized, and the device roles and resource allocation can be adjusted. It can determine the resource load of all networks to appropriately allocate spare devices that are not networked. On this basis, the load of all subnets can be further counted. For subnets with lighter loads, some devices can be allocated to other subnets to allocate resources more flexibly.

[0072] The present invention performs correlation analysis on devices according to their operating data, determines the co-occurrence between devices, calculates point mutual information as correlation based on the co-occurrence, and then performs self-networking based on the correlation of devices, thereby taking into account the correlation between different devices, so as to establish connections between devices with high correlation, and assigning connected devices to the same subnet, and then subnetting the devices in densely populated areas of the network according to the correlation of the devices, thereby taking into account the correlation between different devices, so as to establish connections between devices with high correlation, reducing the overall complexity of the network, thereby reducing the size of the solvable space of the networking calculation, avoiding the problem of networking difficulties caused by too large a solvable space in densely populated areas, and quickly generating a super device networking template adapted to specific application scenarios when in use, thereby improving the flexibility of the system and the efficiency of resource utilization.

[0073] Embodiment 2

[0074] See also Figure 2 Based on the above method, the present invention also provides a device correlation self-organizing network system, the device correlation self-organizing network system comprising:

[0075] The data collection module 51 is used to collect device performance data and device operation data of all devices participating in the network;

[0076] A correlation evaluation module 52, configured to perform correlation evaluation on all the devices according to the device operation data to obtain correlation evaluation data;

[0077] Further, the performing correlation evaluation on all the devices according to the device operation data to obtain correlation evaluation data specifically includes:

[0078] Performing co-occurrence analysis on all the devices according to the device operation data to obtain co-occurrence analysis data;

[0079] A correlation evaluation is performed based on the co-occurrence analysis data to obtain the correlation evaluation data.

[0080] Further, performing co-occurrence analysis on all the devices according to the device operation data to obtain co-occurrence analysis data specifically includes:

[0081] Obtaining task contexts of all tasks, and determining a set of devices included in each task according to the task contexts;

[0082] For each of the tasks, the number of co-occurrences between any two devices in the corresponding device set is counted to obtain co-occurrence data;

[0083] Data cleaning and deduplication processing are performed on all the co-occurrence data, and a collection of all the co-occurrence data after data cleaning and deduplication processing is used as the co-occurrence analysis data.

[0084] Further, performing correlation evaluation according to the co-occurrence analysis data to obtain the correlation evaluation data specifically includes:

[0085] According to the equipment operation data, count the total number of events and the number of occurrences of all equipment;

[0086] Calculate the occurrence probability of all devices according to the total number of events and each of the occurrence numbers, and calculate the co-occurrence probability between any two devices according to the total number of events and each of the co-occurrence numbers;

[0087] The point mutual information between any two devices is calculated according to each of the co-occurrence probabilities and each of the occurrence probabilities, and the set of all the point mutual information is used as the correlation evaluation data.

[0088] The self-organizing network module 53 divides all devices into different subnets according to the correlation evaluation data, and organizes each subnet separately.

[0089] Furthermore, the method of dividing all devices into different subnets according to the correlation evaluation data and networking each subnet separately includes:

[0090] According to the correlation evaluation data, all devices are divided into different subnets;

[0091] According to the device performance data, each subnet is networked separately.

[0092] Further, all devices are divided into different subnets according to the correlation evaluation data, including multiple iterations of subnet selection, each subnet selection includes:

[0093] According to the correlation evaluation data, a central device with the highest point mutual information is selected;

[0094] According to the central device, multiple devices whose point mutual information with the central device is greater than a set point mutual information threshold are selected as auxiliary devices of the central device;

[0095] The central device and each of the auxiliary devices are taken as a subnet.

[0096] Furthermore, the networking of each subnet is performed according to the device performance data, specifically including:

[0097] According to the device performance data, set the device role of each device in the subnet;

[0098] The network structure of the subnet is set according to the device performance data and the roles of each device.

[0099] Embodiment 3

[0100] See also Figure 3 Based on the above method, the present invention also provides a terminal, which includes a processor 10, a memory 20 and a display 30. Figure 3 Only some components of the terminal are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0101] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code of the installation terminal. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a device-related self-organizing network program 40 is stored on the memory 20, and the device-related self-organizing network program 40 can be executed by the processor 10.

[0102] In some embodiments, the processor 10 may be a central processing unit, a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 20, such as executing the relevant programs of the device-related self-organizing network method.

[0103] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 30 is used to display information on the terminal and to display a visual user interface. The components of the terminal communicate with each other via a system bus.

[0104] In one embodiment, when the processor 10 executes the device correlation self-organizing network program 40 in the memory 20 , the steps of the device correlation self-organizing network method described above are implemented.

[0105] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), etc. equipped on the terminal. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code of the installation terminal, etc. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a device-related self-organizing network program is stored on the memory 20, and the device-related self-organizing network program can be executed by the processor 10, thereby realizing the device-related self-organizing network method in the present application.

[0106] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 20, such as executing the device-related self-organizing network method.

[0107] Embodiment 4

[0108] This embodiment provides a storage medium, wherein the readable storage medium stores a device correlation self-organizing network program, and when the device correlation self-organizing network program is executed by a processor, the steps of the device correlation self-organizing network method described above are implemented.

[0109] To summarize, the present invention performs correlation analysis on devices according to their operating data, and then divides the devices in densely populated areas into subnets according to the correlation of the devices, thereby taking into account the correlation between different devices, so as to establish connections between devices with high correlation, thereby reducing the overall complexity of the network, thereby reducing the size of the solvable space for networking calculations, avoiding the problem of networking difficulties caused by too large a solvable space in densely populated areas, and being able to quickly generate a super device networking template that adapts to specific application scenarios when in use, thereby improving the flexibility of the system and resource utilization efficiency.

[0110] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or terminal including the element.

[0111] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the program can be stored in a computer-readable storage medium, and the program can include the processes of the above-mentioned method embodiments when executed. The storage medium can be a memory, a disk, an optical disk, etc.

[0112] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A device correlation self-organizing network method, characterized in that: The device correlation self-organizing network method comprises: Collect equipment performance data and equipment operation data of all equipment involved in the network; Performing correlation evaluation on all the devices according to the device operation data to obtain correlation evaluation data; Divide all devices into different subnets according to the correlation evaluation data, and network each subnet separately; The performing correlation evaluation on all the devices according to the device operation data to obtain correlation evaluation data specifically includes: Performing co-occurrence analysis on all the devices according to the device operation data to obtain co-occurrence analysis data; A correlation evaluation is performed based on the co-occurrence analysis data to obtain the correlation evaluation data.

2. A device correlation self-organizing network method according to claim 1, characterized in that: The performing co-occurrence analysis on all the devices according to the device operation data to obtain co-occurrence analysis data specifically includes: Obtaining task contexts of all tasks, and determining a set of devices included in each task according to the task contexts; For each of the tasks, the number of co-occurrences between any two devices in the corresponding device set is counted to obtain co-occurrence data; Data cleaning and deduplication processing are performed on all the co-occurrence data, and a collection of all the co-occurrence data after data cleaning and deduplication processing is used as the co-occurrence analysis data.

3. A device correlation self-organizing network method according to claim 2, characterized in that: The performing correlation evaluation according to the co-occurrence analysis data to obtain the correlation evaluation data specifically includes: According to the equipment operation data, count the total number of events and the number of occurrences of all equipment; Calculate the occurrence probability of all devices according to the total number of events and each of the occurrence numbers, and calculate the co-occurrence probability between any two devices according to the total number of events and each of the co-occurrence numbers; The point mutual information between any two devices is calculated according to each of the co-occurrence probabilities and each of the occurrence probabilities, and the set of all the point mutual information is used as the correlation evaluation data.

4. A device correlation self-organizing network method according to claim 3, characterized in that: The method of dividing all devices into different subnets according to the correlation evaluation data and networking each subnet separately includes: According to the correlation evaluation data, all devices are divided into different subnets; According to the device performance data, each subnet is networked separately.

5. A device correlation self-organizing network method according to claim 4, characterized in that: The method of dividing all devices into different subnets according to the correlation evaluation data includes multiple iterations of subnet selection, each of which includes: According to the correlation evaluation data, a central device with the highest point mutual information is selected; According to the central device, multiple devices whose point mutual information with the central device is greater than a set point mutual information threshold are selected as auxiliary devices of the central device; The central device and each of the auxiliary devices are taken as a subnet.

6. A device correlation self-organizing network method according to claim 4, characterized in that: The networking of each subnet according to the device performance data specifically includes: According to the device performance data, set the device role of each device in the subnet; The network structure of the subnet is set according to the device performance data and the roles of each device.

7. A device-related self-organizing network system, characterized in that: The device correlation self-organizing network system includes: Data collection module, used to collect equipment performance data and equipment operation data of all equipment involved in the network; A correlation evaluation module, used for performing correlation evaluation on all the devices according to the device operation data to obtain correlation evaluation data; A self-organizing network module, which divides all devices into different subnets according to the correlation evaluation data, and networks each subnet separately; The performing correlation evaluation on all the devices according to the device operation data to obtain correlation evaluation data specifically includes: Performing co-occurrence analysis on all the devices according to the device operation data to obtain co-occurrence analysis data; A correlation evaluation is performed based on the co-occurrence analysis data to obtain the correlation evaluation data.

8. A terminal, characterized in that: The terminal includes: a memory, a processor, and a device-related self-organizing network program stored in the memory and executable on the processor. When the device-related self-organizing network program is executed by the processor, the terminal is controlled to implement the steps of the device-related self-organizing network method as described in any one of claims 1 to 6.

9. A readable storage medium, characterized in that: The readable storage medium stores a device correlation self-organizing network program, and when the device correlation self-organizing network program is executed by a processor, the steps of the device correlation self-organizing network method according to any one of claims 1 to 6 are implemented.

Images