A device self-organizing network method and system based on profile coefficients

Abstract

The application relates to the computer technical field and discloses a device self-organizing network method and system based on contour coefficients, which comprises the following steps: collecting device information of all devices, dividing all the devices into different subnets according to the device information, calculating contour coefficients of all the devices, adjusting each subnet according to the contour coefficients, and controlling each subnet to organize a network according to the device information of the devices contained in the subnet. After the subnet division of the network organizing system, the contour coefficients of all the devices are calculated, the division rationality of the subnets is judged through the contour coefficients, the unreasonable part is adjusted according to the contour coefficients, each subnet is organized after the adjustment, the rationality of the subnet division is ensured, the network structure is better optimized, the influence of the subnet division on the network organizing effect is reduced as much as possible, and the final network organizing effect is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a device self-organizing network method and system based on contour coefficient, a terminal and a readable storage medium. BACKGROUND

[0002] With the popularity of Internet of Things devices, the collaborative work of different devices in various application scenarios becomes increasingly important. Due to the large number of devices and different functions, how to divide various devices and then form a network becomes a technical problem.

[0003] Traditional network forming methods mostly rely on static configuration and cannot adapt to rapidly changing application requirements and device states. Therefore, various self-organizing network methods have been proposed in the prior art, such as a method of forming a network according to network conditions or device performance. This method not only saves manpower during network formation, but also adjusts the network according to the self-organizing network method when the application requirements and device states change.

[0004] When these self-organizing network methods of the prior art are applied to large-scale complex networks, as the number and scale of devices increase, the solvable space of network formation also increases explosively, which leads to slow calculation or even inability to solve the optimal solution in the solvable space. Therefore, a feasible method is to divide devices into sub-zones according to geographical location, thereby reducing the solvable space of each sub-zone and improving the speed of network formation to meet the real-time requirements of network formation.

[0005] However, when dividing sub-networks according to regions, the algorithm may sometimes make incorrect divisions, leading to unreasonable sub-network division and affecting the subsequent network formation effect. SUMMARY

[0006] The purpose of the present application is to provide a device self-organizing network method and system based on contour coefficient, which aims to solve the problem of unreasonable division when dividing the entire network system into multiple sub-networks for network formation in the prior art.

[0007] The technical solution adopted by the present application to solve the technical problem is as follows:

[0008] The present application provides a device self-organizing network method based on contour coefficient, which comprises the following steps:

[0009] Collecting device information of all devices and dividing all devices into different sub-networks according to the device information;

[0010] Calculating the contour coefficients of all devices and adjusting each sub-network according to each contour coefficient;

[0011] Controlling each sub-network to form a network according to the device information of the devices included in the sub-network.

[0012] Further, the dividing all the devices into different subnets according to the device information specifically comprises:

[0013] dividing a plurality of geographical areas, and selecting a cluster center for each geographical area;

[0014] clustering all the devices according to all the cluster centers and the device information, and dividing all the devices into different subnets.

[0015] Further, the calculating the silhouette coefficients of all the devices and adjusting each of the subnets according to the respective silhouette coefficients specifically comprises:

[0016] calculating a silhouette coefficient S(i) of the ith device:

[0017]

[0018] wherein a(i) represents an average distance of the ith device to other devices in the same subnet, and b(i) represents an average distance of the ith device to devices in a different subnet;

[0019] evaluating the subnet division effect according to the silhouette coefficients of all the devices, and adjusting each of the subnets according to the evaluation result.

[0020] Further, the evaluating the subnet division effect according to the silhouette coefficients of all the devices, and adjusting each of the subnets according to the evaluation result specifically comprises:

[0021] determining whether the subnet division needs to be performed again according to the silhouette coefficients of all the devices, and if so, performing the subnet division again;

[0022] controlling each of the subnets to be adjusted according to the silhouette coefficients of the devices included in the corresponding subnet.

[0023] Further, the determining whether the subnet division needs to be performed again according to the silhouette coefficients of all the devices, and if so, performing the subnet division again specifically comprises:

[0024] calculating an average value of the silhouette coefficients of all the devices to obtain an overall average silhouette coefficient;

[0025] determining whether the overall average silhouette coefficient is less than a set overall threshold value, and if so, performing the subnet division and clustering again.

[0026] Further, the controlling each of the subnets to be adjusted according to the silhouette coefficients of the devices included in the corresponding subnet specifically comprises:

[0027] control each sub-network to calculate the average value of the profile coefficient of the device contained in the sub-network, and obtain the average profile coefficient of each sub-network;

[0028] determine whether the average profile coefficient of each sub-network is less than a set sub-network threshold value, and if yes, adjust the clustering center of the corresponding sub-network and re-cluster.

[0029] Further, the control each sub-network adjusts the sub-network according to the profile coefficient of the device contained in the sub-network, and further comprises:

[0030] determine whether the profile coefficient of the device is lower than a set device threshold value, and if yes, adjust the sub-network to which the device belongs.

[0031] In addition, to achieve the above object, the present application also provides a device ad hoc network system based on profile coefficient, which comprises:

[0032] a sub-network division module, which is used for collecting device information of all devices, and dividing all the devices into different sub-networks according to the device information;

[0033] a sub-network adjustment module, which is used for calculating the profile coefficient of all devices, and adjusting each sub-network according to each profile coefficient;

[0034] a sub-network networking module, which is used for controlling each sub-network to respectively perform networking according to the device information of the device contained in the sub-network.

[0035] In addition, to achieve the above object, the present application also provides a terminal, which comprises a memory, a processor, and a device ad hoc network program based on profile coefficient stored in the memory and executable on the processor, and the device ad hoc network program based on profile coefficient controls the terminal to implement the steps of the device ad hoc network method based on profile coefficient when executed by the processor.

[0036] In addition, to achieve the above object, the present application also provides a readable storage medium, which stores a device ad hoc network program based on profile coefficient, and the device ad hoc network program based on profile coefficient implements the steps of the device ad hoc network method based on profile coefficient when executed by the processor.

[0037] The present application has the following effects by adopting the above technical solutions:

[0038] The application calculates the profile coefficients of all devices after subnetting the networking system, judges whether the subnetting is reasonable through the profile coefficients, adjusts the unreasonable part according to the profile coefficients, and completes the networking of each subnet after the adjustment, so as to ensure the rationality of subnetting, better optimize the network structure, reduce the influence of subnetting on the networking effect as much as possible, and improve the final networking effect. BRIEF DESCRIPTION OF DRAWINGS

[0039] Figure 1 is a step flow chart of a device self-networking method based on a profile coefficient in a preferred embodiment of the application;

[0040] Figure 2 is a structural schematic diagram of a device self-networking system based on a profile coefficient in a preferred embodiment of the application;

[0041] Figure 3 is a running environment schematic diagram of a terminal in a preferred embodiment of the application. DETAILED DESCRIPTION

[0042] To make the objectives, technical solutions and advantages of the present application clearer and more explicit, the present application is further described in detail below with reference to the drawings and examples. It should be understood that the described examples are only some of the embodiments of the present disclosure, not all the embodiments. The specific examples described herein are only used to explain the present application, and do not limit the present application. All other embodiments obtained by those skilled in the art without creative labor are within the scope of the present disclosure.

[0043] Example One

[0044] Please refer to Figure 1 The example one of the present application is a device self-networking method based on a profile coefficient, which can be applied to the management terminal of various Internet of Things systems, such as the management terminal of an edge computing system, the management terminal of an intelligent home system or the management terminal of other various Internet of Things systems. In addition, the device self-networking method of the present embodiment can also run outside the Internet of Things system to provide networking support services for the Internet of Things system. It can run in a server, which can be a physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud service, cloud database, cloud computing, cloud storage, big data and artificial intelligence platform.

[0045] The device self-networking method based on a profile coefficient of the present embodiment includes the following steps:

[0046] S1, collecting device information of all devices, and dividing all the devices into different subnets according to the device information.

[0047] Specifically, in this embodiment, the uploaded device data of each device is collected, and the device data includes position information, hardware information, function information, environment information and running state information of the device. The position information refers to information describing the position of the device, including coordinate information of the coordinate of the device, and height information describing the height of the device considering that the device can exist in different floors.

[0048] In this embodiment, the coordinate information is obtained through the GPS (Global Positioning System) integrated by the device, the hardware information refers to information describing the hardware performance of the device that does not change, including CPU (Central Processing Unit) information, memory information, storage information and sensor type information, the function information refers to information describing the software functions supported by the device, including protocol information describing the communication protocol supported by the device and application program information describing the special software functions possessed by the device, such as the function of graphic processing, the environment information is the information of the environment where the device is located, which is used to describe the running environment of the device, including temperature information, humidity information and illumination information, and the running state information is the running state of the device under the current task, including CPU load, memory usage, storage usage and network delay.

[0049] Then, a networking model is established according to the device information. In this embodiment, the networking model is a super thing model used to describe each device participating in networking. The super thing model is an abstract model used to describe and manage device capabilities, covering hardware resources, software functions, current states and environment information and other aspects, so as to not only help manage a single device, but also serve as a unified representation of a virtual device collection.

[0050] Thus, a unified model is used to describe the spatial attributes, hardware characteristics, software functions and real-time running state information of each device, and the devices are classified and managed according to different function levels, such as the perception layer (sensor device), the processing layer (edge computing node) and the communication layer (network device). Each layer establishes a corresponding super thing model, and finally forms a hierarchical super thing model system.

[0051] After the construction of the networking model, the subnets can be divided according to the position information of the device, the hardware information of the user and the function information of the user, so as to divide the overall system into multiple different areas. In this embodiment, the K-means clustering method is used for subnet division.

[0052] First, according to the location information of the device, the device is preliminarily divided, specifically, the whole system is divided into multiple different areas, specifically, the relatively independent geographical area is divided into a separate area, the number of divided areas can be determined according to the distribution density of the network, to ensure that each area has a certain scale of network, and at the same time, it will not have a large scale network, to ensure that the network of each area can meet the demand of work, at the same time, it will not lead to the network time of the sub-network of the area is too long, the specific division method can be artificial division, or can be divided according to the coordinate information by algorithm, for example, the graph algorithm is used for division.

[0053] Then, a position in each area is selected as a clustering center as the basis for subsequent clustering, specifically, the center point of each area can be calculated as the initial clustering center, or the clustering center can be calculated according to other setting rules, for example, a device that interacts most frequently with other devices in the area can be selected as the cluster center, that is, the cluster center.

[0054] Then, the distance between each device and each clustering center is calculated to cluster each device and divide each device into different clusters, and the devices in each cluster form a sub-network.

[0055] In this embodiment, the distance adopts a multi-dimensional distance measurement method, including spatial distance and functional distance, wherein the spatial distance adopts Euclidean distance, the Euclidean distance between each device and each clustering center is calculated according to the coordinate information of each device, and the functional distance adopts Manhattan distance for calculation, which first needs to vectorize the functional information and hardware information of each device, wherein for the hardware information, the central processing unit information, memory information, storage information and sensor type information are converted into distance vectors by using a set of proportion values, respectively becoming an element of the distance vector, for the functional information, if the device has the function, the corresponding element is set to 1, and if the device does not have the function, the corresponding element is set to 0, then the Manhattan distance between each device and each clustering center is calculated by using the converted distance vector, and finally the Manhattan distance and Euclidean distance are clustered.

[0056] It is worth noting that in this embodiment, the functional distance of the device is fine-tuned, the purpose is to ensure that the functionally complementary devices can be in the same cluster, such a selection can improve the efficiency of networking. Similarly, in an optional embodiment, the distance can also include load distance, which is also calculated by using Manhattan distance and weighted calculation, so as to further optimize the effect of clustering. It is worth noting that since the distance is used to measure the similarity between two devices, and in this embodiment, the complementarity between different devices needs to be realized, therefore, the weighted value of the Manhattan distance in this embodiment is negative.

[0057] S2, calculate the profile coefficient of all devices, and adjust each sub-network according to the profile coefficient of each device.

[0058] Specifically, first, the profile coefficient of each device is calculated respectively, wherein the profile coefficient S(i) of the i-th device is:

[0059]

[0060] Wherein a(i) represents the average distance of the i-th device to other devices in the same sub-network, which is used to measure the closeness of the i-th device to the devices in the sub-network, and b(i) represents the average distance of the i-th device to the devices in other sub-networks, which is used to measure the separation degree of the i-th device to other sub-networks.

[0061] Then, according to the profile coefficients of all devices, the rationality of the sub-network division is evaluated, and the unreasonable part is adjusted. Specifically, the rationality of the sub-network division includes device evaluation, sub-network internal evaluation and overall network evaluation.

[0062] Wherein, the overall network evaluation is to calculate the average value of the profile coefficients of all devices to obtain the overall average profile coefficient, so as to evaluate the effect of the sub-network division in the whole network. If the overall average profile coefficient is greater than the set overall threshold, it indicates that the sub-network division structure is reasonable, and only minor adjustments are needed. If the overall average profile coefficient is less than the set overall threshold, the clustering of the devices may need to be adjusted.

[0063] Specifically, when adjusting, the overall network evaluation is first judged. If the overall network evaluation does not pass, the step of dividing all the devices into different sub-networks is re-performed, that is, the division of the region is adjusted, including the division of the number of regions and the division of the position of the region.

[0064] After the overall network evaluation passes, the sub-network internal evaluation is performed on each sub-network respectively, and the sub-network that does not pass is adjusted. In this embodiment, the adjustment is performed by adjusting the position of the cluster center of the sub-network.

[0065] The sub-network internal evaluation is to calculate the average value of the profile coefficients of all devices in each sub-network to obtain the average profile coefficient of the sub-network. If the average profile coefficient of a certain sub-network is low, for example, lower than the set sub-network threshold, or lower than a certain proportion of the overall average profile coefficient, it indicates that the closeness between the devices in the sub-network is insufficient or the separation degree from other sub-networks is insufficient, and there may be unreasonable device attribution, which needs to adjust the boundary of the sub-network or the position of the cluster center corresponding to the sub-network.

[0066] The device evaluation is to judge whether the profile coefficient of the device is lower than the set device threshold. If yes, the device may need to be adjusted to adjust the sub-network to which the device belongs.

[0067] Afterwards, for each device, device evaluation is performed respectively, and for the device whose profile coefficient is lower than the set device threshold, the subnet where the device is located is adjusted.

[0068] S3, control each subnet to perform networking according to the device information of the devices contained in the subnet respectively.

[0069] Specifically, in the embodiment, the core device of each subnet is selected according to the networking model. In the embodiment, the core device is specifically the device that interacts with other devices most. The core device serves as the center node of the subnet and is responsible for communication coordination and data processing within the subnet.

[0070] After the core device is selected, each device in the subnet is assigned a function according to the networking model. In the embodiment, the Internet of Things system is introduced in the field of augmented reality, so the function assignment is specifically assigning as an edge node, a data processing node and a sensor node. The edge node is mainly responsible for data preprocessing and transmission, the data processing node is responsible for complex calculation, and the sensor node is responsible for environmental data acquisition.

[0071] After the roles of all nodes are divided, the specific networking structure is determined according to the networking model. Specifically, according to the communication protocol supported by each device, the role of each device, and the performance possessed by each device, the data flow direction and fault handling mechanism of each device are defined.

[0072] For example, according to the performance of the downstream node required by the task of each node, the performance constraint of the networking is defined, that is, each node can meet the task of the upstream node through the constraint. Then, according to the index, the specific networking structure is defined, for example, according to the total delay of each node and other nodes, the total delay of the system is calculated, and the total delay is taken as the target to establish a solving model. Then, the specific structure of the subnet is obtained by solving the solving model.

[0073] After the networking is completed, in addition, in the embodiment, the device information is updated to the super object model by the edge computing node regularly, so as to ensure that the model reflects the latest state and ability of the device, and still use the device ability description and state information provided by the super object model to dynamically allocate computing resources and network bandwidth. Through the soft bus technology, the unified management of the virtual resource pool is realized, the resources are allocated to each device in the networking, so as to realize load balancing. In the running process, the load condition of each device is monitored in real time, the resource allocation is dynamically adjusted, and the overload or resource waste of some devices is avoided.

[0074] In addition, with the real-time changes of the dynamic state, resource utilization rate and spatial position information of the device in the running process, the profile coefficient of the device, the average profile coefficient of each subnet and the overall average profile coefficient will also change. At this time, real-time adjustment can be performed according to the actual situation.

[0075] Specifically, if the real-time profile coefficient of a certain device is lower than a set device threshold, the subnet to which the device belongs is adjusted, if the subnet average profile coefficient of a certain subnet is lower, or even the overall average profile coefficient is less than a set overall threshold, the adjustment is followed by networking, and the adjustment method can refer to the aforementioned adjustment method.

[0076] Embodiment Two

[0077] Please refer to Figure 2 Based on the above method, the application further provides a device self-networking system based on profile coefficient, which comprises:

[0078] A subnet division module 51 is configured to collect device information of all devices, and divide all the devices into different subnets according to the device information.

[0079] A subnet adjustment module 52 is configured to calculate profile coefficients of all devices, and adjust each of the subnets according to each of the profile coefficients.

[0080] A subnet networking module 53 is configured to control each of the subnets to perform networking according to device information of devices included in the subnet.

[0081] Further, the division of all the devices into different subnets according to the device information specifically comprises:

[0082] A plurality of geographical areas are divided, and a cluster center is selected for each geographical area.

[0083] All the devices are clustered according to all the cluster centers and the device information, and all the devices are divided into different subnets.

[0084] Further, the calculation of profile coefficients of all devices, and the adjustment of each of the subnets according to each of the profile coefficients specifically comprises:

[0085] The profile coefficient S(i) of the i-th device is calculated as follows:

[0086]

[0087] Wherein, a(i) represents the average distance from the i-th device to other devices in the same subnet, and b(i) represents the average distance from the i-th device to devices in other subnets.

[0088] The effect of subnet division is evaluated according to the profile coefficients of all devices, and each of the subnets is adjusted according to the evaluation result.

[0089] Further, the evaluation of the effect of subnet division according to the profile coefficients of all devices, and the adjustment of each of the subnets according to the evaluation result specifically comprises:

[0090] According to the profile coefficients of all the devices, it is determined whether the subnet division needs to be performed again, and if so, the subnet division is performed again.

[0091] The profile coefficients of the devices included in each subnet are calculated, and the average value of the profile coefficients of the devices included in each subnet is obtained.

[0092] Further, according to the profile coefficients of all the devices, it is determined whether the subnet division needs to be performed again, and if so, the subnet division is performed again, and specifically includes:

[0093] The average value of the profile coefficients of all the devices is calculated to obtain an overall average profile coefficient.

[0094] It is determined whether the overall average profile coefficient is less than a set overall threshold value, and if so, the subnet division is performed again and the clustering is performed again.

[0095] Further, the control of each subnet according to the profile coefficients of the devices included in the subnet to adjust the subnet specifically includes:

[0096] The average value of the profile coefficients of the devices included in each subnet is calculated to obtain a subnet average profile coefficient of each subnet.

[0097] It is determined whether each subnet average profile coefficient is less than a set subnet threshold value, and if so, the clustering center of the corresponding subnet is adjusted and the clustering is performed again.

[0098] Further, the control of each subnet according to the profile coefficients of the devices included in the subnet to adjust the subnet further includes:

[0099] It is determined whether the profile coefficient of the device is lower than a set device threshold value, and if so, the subnet to which the device belongs is adjusted.

[0100] Embodiment three

[0101] Please refer to Figure 3 Based on the above method, the application further provides a terminal, which includes a processor 10, a memory 20 and a display 30. Figure 3 Only part of the components of the terminal are shown, but it should be understood that all the shown components are not required to be implemented, and more or less components can be alternatively implemented.

[0102] The memory 20 can be an internal storage unit of the terminal in some embodiments, such as a hard disk or a memory of the terminal. The memory 20 can also be an external storage device of the terminal in other embodiments, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 20 can include both an internal storage unit and an external storage device of the terminal. The memory 20 is used to store application software and various data installed in the terminal, such as program codes of the terminal, etc. The memory 20 can also be used to temporarily store data that has been output or will be output. In an embodiment, the memory 20 stores a profile coefficient-based device ad hoc network program 40, which can be executed by the processor 10.

[0103] The processor 10 can be a central processing unit (CPU), a microprocessor or other data processing chip in some embodiments, which is used to run program codes stored in the memory 20 or process data, such as to execute a program related to the profile coefficient-based device ad hoc network method, etc.

[0104] The display 30 can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, etc. in some embodiments. The display 30 is used to display information of the terminal and to display a visualized user interface. The components of the terminal communicate with each other through a system bus.

[0105] In an embodiment, the steps of the profile coefficient-based device ad hoc network method as described above are implemented when the processor 10 executes the profile coefficient-based device ad hoc network program 40 in the memory 20.

[0106] The memory 20 can be an internal storage unit of the terminal in some embodiments, such as a hard disk or a memory of the terminal. The memory 20 can also be an external storage device of the terminal in other embodiments, 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 can include both the internal storage unit and the external storage device of the terminal. The memory 20 is used to store application software and various data installed on the terminal, such as program codes of the terminal, etc. The memory 20 can also be used to temporarily store data that has been output or will be output. In an embodiment, a profile coefficient-based device ad hoc network program is stored on the memory 20, and the profile coefficient-based device ad hoc network program can be executed by the processor 10 to implement the profile coefficient-based device ad hoc network method.

[0107] The processor 10 can be a central processing unit, a microprocessor or other data processing chip in some embodiments, and is used to run program codes or process data stored in the memory 20, such as to execute the profile coefficient-based device ad hoc network method, etc.

[0108] Embodiment Four

[0109] The embodiment provides a storage medium, and the readable storage medium stores a profile coefficient-based device ad hoc network program. The profile coefficient-based device ad hoc network program is executed by a processor to implement the steps of the profile coefficient-based device ad hoc network method as described above.

[0110] In summary, the present application calculates the profile coefficients of all devices after subnetting of the networking system, judges whether the subnetting is reasonable by the profile coefficients, adjusts the unreasonable part according to the profile coefficients, and completes the networking of each subnet after the adjustment, so as to ensure the rationality of the subnetting, better optimize the network structure, reduce the influence of the subnetting on the networking effect as much as possible, and improve the final networking effect while ensuring the networking efficiency.

[0111] It should be noted that, in the present document, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element preceded by "comprises a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0112] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing relevant hardware (such as a processor, a controller, etc.) through a computer program. 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 magnetic disk, an optical disk, etc.

[0113] It should be understood that the application is not limited to the above examples, and those skilled in the art can make improvements or changes according to the above description, and all these improvements and changes shall fall within the protection scope of the appended claims of the present application.

Claims

1. A device self-organizing network method based on silhouette coefficient, characterized in that: The device self-organizing network method based on the silhouette coefficient comprises the steps of: Collect device information of all devices, and divide all the devices into different subnets according to the device information; Calculating the silhouette coefficients of all devices, and adjusting each of the subnets according to each of the silhouette coefficients; Control each subnet to form a network based on the device information of the devices contained in the subnet; The dividing all the devices into different subnets according to the device information specifically includes: Divide into multiple geographical areas and select a cluster center for each geographical area; respectively calculating the distance between each device and each cluster center to cluster the devices, clustering all the devices according to all the cluster centers and the device information, and dividing all the devices into different subnets; The distance adopts a multi-dimensional distance measurement method, including spatial distance and functional distance; The spatial distance adopts the Euclidean distance, and the Euclidean distance between each device and each cluster center is calculated according to the coordinate information of each device. The functional distance is calculated using the Manhattan distance, and the functional information and hardware information of each device are vectorized. Among them, for the hardware information, the central processing unit information, memory information, storage information and sensor type information are converted using a set ratio value to become an element of the distance vector respectively. For the functional information, the corresponding element is set to 1 if the device has the functional information, and the corresponding element is set to 0 if the device does not have the functional information. The converted distance vector is used to calculate the Manhattan distance between each device and each cluster center, and clustering is performed according to the Manhattan distance and the Euclidean distance.

2. The device self-organizing network method based on silhouette coefficient according to claim 1, characterized in that: Calculating the silhouette coefficients of all devices and adjusting each subnet according to each silhouette coefficient specifically includes: Calculate the Profile factor of the device : ； in, Indicates the The average distance from a device to other devices in its subnet, Indicates the The average distance between a device and devices outside its subnet; The subnet division effect is evaluated according to the silhouette coefficients of all devices, and each subnet is adjusted according to the evaluation result.

3. The device self-organizing network method based on silhouette coefficient according to claim 2, characterized in that: The subnet division effect is evaluated according to the silhouette coefficients of all devices, and each subnet is adjusted according to the evaluation result, specifically including: Determine whether re-subnetting is necessary based on the silhouette coefficients of all devices. If necessary, re-subnetting is performed. Control each subnet and adjust the corresponding subnet according to the silhouette coefficient of the devices contained in the subnet.

4. The device self-organizing network method based on silhouette coefficient according to claim 3, characterized in that: Determine whether re-subnetting is necessary based on the silhouette coefficients of all devices. If necessary, re-subnetting is performed, including: Calculate the average of the silhouette coefficients of all devices to obtain the overall average silhouette coefficient; It is determined whether the overall average silhouette coefficient is less than a set overall threshold. If so, subnet division and re-clustering are performed.

5. The device self-organizing network method based on silhouette coefficient according to claim 3, characterized in that: The controlling of each subnet is to adjust the subnet according to the profile coefficient of the devices included in the subnet, specifically including: Control each subnet to calculate the average value of the silhouette coefficients of the devices contained in the subnet, and obtain the average silhouette coefficient of each subnet; It is determined whether the average silhouette coefficient of each subnet is less than a set subnet threshold. If so, the cluster center of the corresponding subnet is adjusted and clustering is performed again.

6. The device self-organizing network method based on silhouette coefficient according to claim 3, characterized in that: The controlling of each subnet adjusts the subnet according to the profile coefficient of the devices included in the subnet, and further includes: Determine whether the device's silhouette coefficient is lower than a set device threshold. If so, adjust the subnet to which the device belongs.

7. A device self-organizing network system based on silhouette coefficient, characterized in that: The device self-organizing network system based on the silhouette coefficient is applied to the device self-organizing network method based on the silhouette coefficient according to any one of claims 1 to 6, and the device self-organizing network system based on the silhouette coefficient includes: A subnet division module is used to collect device information of all devices and divide all the devices into different subnets according to the device information; A subnet adjustment module, configured to calculate the silhouette coefficients of all devices and adjust each subnet according to each silhouette coefficient; The subnet networking module is used to control each subnet to be networked according to the device information of the devices included in the subnet.

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

Images