Dynamic networking method, apparatus, system, storage medium and computer program product

Abstract

The application discloses a dynamic networking method, device, system, storage medium and computer program product, and relates to the technical field of Internet of Things, and comprises the following steps: monitoring real-time device state information and actual service demand of network node devices in a current networking structure in real time, wherein the current networking structure is constructed by an adversarial generative network according to initial device state information of the network node devices stored in a super physical model; if it is determined that the network node devices are abnormal according to the device state information, and / or it is detected that the actual service demand of the network node devices changes, a new networking structure is regenerated by the adversarial generative network according to the real-time device state information stored in the super physical model. The application can avoid resource waste caused by fixed resource allocation in static networking, and improves the resource utilization rate of devices in the networking structure.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of Internet of Things, and in particular to a dynamic networking method, a dynamic networking device, a dynamic networking system, a storage medium and a computer program product. BACKGROUND

[0002] At present, after the network topology structure and the connection relationship are determined, the traditional static networking method cannot timely adjust the network structure for the scenes of device dynamic change and business demand change, and the support for bandwidth management and load balancing is relatively limited, thereby causing low resource utilization of devices in the network structure. SUMMARY

[0003] The main purpose of the present application is to provide a dynamic networking method, a dynamic networking device, a dynamic networking device, a storage medium and a computer program product, which aims to solve the technical problem of low resource utilization of devices in the network structure.

[0004] To achieve the above-mentioned purpose, the present application provides a dynamic networking method, which comprises:

[0005] Real-time monitoring of real-time device state information and actual business demand of network node devices in the current networking structure, wherein the current networking structure is constructed by an adversarial generative network according to initial device state information of the network node devices stored in a super physical model;

[0006] If it is determined that the network node device is abnormal according to the device state information, and / or it is detected that the actual business demand of the network node device changes, a new networking structure is regenerated by the adversarial generative network according to real-time device state information stored in the super physical model.

[0007] In an embodiment, after the step of regenerating a new networking structure by the adversarial generative network according to real-time device state information stored in the super physical model, the method comprises:

[0008] Based on the real-time device state information in the super physical model, determining the current resource demand of the network node devices in the new networking structure;

[0009] According to the current resource demand, allocating network resources of the network node devices in the new networking structure.

[0010] In an embodiment, the adversarial generative network comprises a generator and a discriminator, and the step of constructing the current networking structure by the adversarial generative network according to the initial device state information of the network node devices stored in the super physical model comprises:

[0011] According to the initial device state information, generating an initial networking structure by the generator;

[0012] The initial network structure is evaluated by a preset evaluation standard in the discriminator to obtain an evaluation result, so that the generator adjusts the initial network structure according to the evaluation result to obtain the current network structure.

[0013] In an embodiment, the step of generating the initial network structure by the generator according to the initial device state information comprises:

[0014] The initial device state information is standardized by the generator to obtain standardized device information, wherein the initial device state information comprises software functions and / or geographic positions;

[0015] The collaborative devices are clustered into the same subnet, wherein the collaborative devices are devices with close geographic positions and complementary software functions;

[0016] The initial network structure is generated according to the network topology between at least one subnet, the connection relationship between the collaborative devices in the subnet, and the roles of the collaborative devices in the subnet in the connection relationship, wherein the connection relationship is determined according to the device state information of the network node devices.

[0017] In an embodiment, the step of evaluating the initial network structure by the preset evaluation standard in the discriminator comprises:

[0018] The correlation matrix between the network node devices in the initial network structure is used to evaluate the closeness of the network node devices in the initial network structure for collaborative networking; and / or

[0019] The key performance indicator values of the network node devices in the initial network structure are obtained by simulating actual business loads, and the running situation of the initial network structure in the actual network environment is evaluated by the key performance indicator values.

[0020] In an embodiment, the super object model is constructed from the hardware resources, software functions, geographic positions, firmware versions, communication protocols, and running states of the network node devices.

[0021] In addition, to achieve the above-mentioned purpose, the application further provides a dynamic networking device, which comprises:

[0022] The monitoring module is configured to monitor the real-time device state information and actual business demands of the network node devices in the current network structure in real time, wherein the current network structure is constructed by the generative adversarial network according to the initial device state information of the network node devices stored in the super object model.

[0023] The networking module is configured to, if it is determined that the network node device is abnormal according to the device state information and / or it is detected that the actual service demand of the network node device changes, regenerate a new networking structure by the generative adversarial network according to the real-time device state information stored in the super object model.

[0024] In addition, to achieve the above-mentioned purpose, the application further provides a dynamic networking system, which comprises a dynamic networking device, and the device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the dynamic networking method as described above.

[0025] In addition, to achieve the above-mentioned purpose, the application further provides a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the dynamic networking method as described above.

[0026] In addition, to achieve the above-mentioned purpose, the application further provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the steps of the dynamic networking method as described above.

[0027] The application detects the abnormality or change of the real-time device state information and the actual service demand of the network node device in real time, and then regenerates a new networking structure according to the real-time device state information. Compared with the traditional static networking mechanism which cannot dynamically adjust according to the real-time state of the device and the actual service demand, the dynamic networking mechanism of the application which adjusts the network topology structure based on the super object model and the generative adversarial network can learn and optimize itself based on the real-time device state information and the service demand, and adjust the allocation of network resources, thereby avoiding the waste of resources caused by the fixed allocation of resources in the static networking, and improving the resource utilization rate of the devices in the networking structure. BRIEF DESCRIPTION OF DRAWINGS

[0028] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the application and, together with the specification, serve to explain the principles of the application.

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the accompanying drawings needed in the embodiments or prior art description will be briefly introduced as follows. Obviously, for those skilled in the art, other drawings can also be obtained based on these drawings without creative labor.

[0030] Figure 1 The flowchart provided by the first embodiment of the dynamic networking method of the application;

[0031] Figure 2 The flowchart provided for the second embodiment of the dynamic networking method of the present application;

[0032] Figure 3 The module structure diagram of the dynamic networking device of the present application;

[0033] Figure 4 The device structure diagram of the hardware running environment involved in the dynamic networking method of the present application.

[0034] The purpose implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0035] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application, and are not used to limit the present application.

[0036] In order to better understand the technical solutions of the present application, the following will be described in detail in combination with the drawings and specific embodiments of the specification.

[0037] In the static networking mode, the connection relationship of the device is determined at the initial stage of network structure design, and the resources are fixedly allocated, which lacks flexibility. When the device state information changes, such as work load, energy consumption or device itself condition, the static networking mode often cannot capture these changes in time due to the lack of dynamic monitoring mechanism. Therefore, the network resource allocation cannot be adjusted according to the latest device state, resulting in uneven resource allocation and low efficiency.

[0038] In order to solve this challenge, the super object model is introduced in the dynamic networking process using the generative adversarial network in the present application. The super object model can not only collect and store the dynamic state information of the device in real time to provide data basis for the dynamic networking of the generative adversarial network, but also can form a virtual resource pool according to these information, dynamically adjust the network architecture and resource allocation. When the device state information changes, the super object model can immediately capture and analyze these changes, automatically adjust the resource allocation, ensure that the resources are used efficiently, and at the same time improve the response speed and overall performance of the network.

[0039] In addition, the super physical model is an upgrade of the traditional physical model. It not only manages the basic hardware resources of the device, such as processor, memory, storage, etc., but also stores and manages rich information of the device, such as geographic location, physical height, manufacturer information, firmware version, etc., enhancing the comprehensive description ability of the device. The collection and management of these additional information enables the super physical model to better understand the characteristics of each device, so as to make more accurate decisions when networking. For example, based on the geographic location information, the coverage of the wireless signal can be optimized; using the firmware version information, the software compatibility of all devices can be ensured, avoiding potential communication problems.

[0040] It should be noted that the execution subject of the embodiment can be a dynamic networking system (hereinafter referred to as system), or a computing service device with data processing, network communication and program running functions, such as tablet computers, personal computers, mobile phones, etc., or an electronic device or processor capable of realizing the above functions. The following takes the system as an example to illustrate the embodiment and the following embodiments.

[0041] Based on this, the embodiment of the present application provides a dynamic networking method, referring to Figure 1 , Figure 1 is a flowchart of the first embodiment of the dynamic networking method of the present application.

[0042] In this embodiment, the dynamic networking method comprises steps S10-S20:

[0043] Step S10, real-time monitoring of real-time device state information and actual business requirements of network node devices in the current networking structure, wherein the current networking structure is constructed by the generative network according to the initial device state information of the network node devices stored in the super physical model;

[0044] It should be noted that the system real-time monitors the current device state information of the current device and the actual business requirements of the network node device in the current networking structure, wherein the device state information includes but is not limited to: hardware resources (such as processor core number, memory size, network bandwidth) of the device, software functions (such as communication protocol, processing capability), geographic location (such as physical coordinates, physical space position, etc.); actual business requirements include but are not limited to data transmission rate, packet loss rate, throughput, load……; the current networking structure includes all network node devices and their connection modes. The network node device is each component in the network, which can be a server, router, switch, workstation, etc.

[0045] GANs are a type of machine learning technique that consists of two deep neural networks: a generator and a discriminator. GANs are used to construct network structures based on stored device state information. The super object model stores detailed information of all network node devices (hardware resources, software functions, geographic locations, metadata fields) and is the basis for GANs to construct network structures.

[0046] In an embodiment, the super object model is constructed based on hardware resources, software functions, geographic locations, firmware versions, communication protocols, and operating states of network node devices.

[0047] It should be noted that hardware resources refer to the physical components of network node devices, including processors, memories, storage devices, network interface cards, etc. Hardware resources determine the processing power, storage capacity, and network communication capabilities of devices. Software functions involve software programs and applications running on network node devices, including operating systems, network services, application programs, general protocols, etc. Software functions determine the types and capabilities of services that devices can provide. Geographic location refers to the specific location of network node devices in the real world. Firmware is low-level software embedded in device hardware to control basic hardware functions. Communication protocols define how devices exchange data, including TCP / IP, UDP, HTTP, HTTPS, etc. Operating state refers to the current real-time working state of devices, including whether online, performance indicators (such as CPU usage, memory usage), service status (such as whether services are running normally), network connection state, etc.

[0048] In this embodiment, the super object model is an abstract model constructed by integrating key information dimensions of devices, containing hardware, software, location, communication methods, and real-time state of node devices in the network. Through the super object model, comprehensive device information can be provided for dynamic networking, supporting dynamic evaluation and resource scheduling of devices, and enabling intelligent management and dynamic optimization of network resources.

[0049] Step S20, if the network node device is abnormal according to the device state information, and / or, the actual business demand of the network node device changes, a new network structure is regenerated by GANs according to the real-time device state information stored in the super object model.

[0050] It should be noted that the network node device abnormality refers to the running state of the device deviating from the normal range, which may be hardware failure, software error, performance bottleneck, device drop, etc. The system determines the device abnormality by monitoring the device state information. The actual business demand changes refer to the network node device data transmission speed becomes faster or slower, delay increases, throughput increases, etc.

[0051] When the system detects device abnormality or changes in device business demand or detects device abnormality and changes in device business demand, the system will use GANs to regenerate a network structure that better meets current demand based on real-time device state information in the super object model. This may include adjusting network configuration, optimizing resource allocation, enhancing security measures, etc. to ensure that the network can run efficiently and stably.

[0052] During the operation of the device, the state information of the network node device will be updated in real time, and the updated device state information reflects the current actual situation of the network. It can be understood that since the state information of the network node device is updated in real time, the super model that stores and manages the device state information will be updated in real time to ensure that GANs make decisions based on the latest device state.

[0053] In one embodiment, after step S20, steps A10-A20 are included:

[0054] Step A10, based on real-time device state information in the super object model, determine the current resource demand of the network node device in the new network structure;

[0055] It should be noted that the new network structure refers to the network layout and configuration that is re-planned by GANs based on real-time device state information. The resource demand of the network node device refers to the various resources required to meet the current running state and business demand of the device, such as CPU processing power, memory, storage space, network bandwidth, etc.

[0056] Based on real-time device state information in the super object model, the system can analyze the current running state and resource usage of each network node device, thereby accurately determining the resource demand of the device. For example, if the CPU usage of a server approaches the upper limit, the system will identify this state and then adjust resource allocation in the new network structure, possibly by load balancing to distribute some tasks to other servers, or increasing computing resources, to prevent overload and maintain efficient service response.

[0057] Step A20, allocate network resources of network node devices in the new networking structure according to current resource requirements.

[0058] It should be noted that resource allocation refers to the process of reasonably allocating computing power, storage space, bandwidth and other resources of the network to each network node device under the new networking structure according to the current resource requirements of the device. Based on the analysis of the current resource requirements of the network node device, the system will allocate resources in the new networking structure to ensure that the device can obtain sufficient resources to meet its operation and business requirements. For example, when the CPU usage of a server is high, the system may allocate more computing resources to the server, or distribute part of the task to other servers with sufficient resources through load balancing to avoid single-point overload and ensure the stability and efficiency of network services.

[0059] In this embodiment, based on the real-time device state information in the super object model, the system can analyze the current running state and resource usage of each network node device, and based on the analysis of the current resource requirements of the network node device, the system will allocate resources in the new networking structure; this process can ensure effective allocation of resources, avoid waste of resources, and at the same time meet business requirements, maintain the high performance and stability of the network.

[0060] In this embodiment, GANs are used to construct the current networking structure in combination with the initial state data of the device stored in the super object model. In actual operation, the dynamic networking system will continuously optimize the networking scheme according to real-time monitoring data. The adversarial training of the generator and the discriminator can continuously adjust and optimize the network structure to ensure that the system is always in the optimal state; at the same time, the dynamic networking system performs dynamic allocation of resources according to the current resource state and business requirements of the device to ensure load balancing and efficient use.

[0061] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as the above first embodiment can refer to the above introduction, and will not be repeated hereinafter. On this basis, please refer to Figure 2 , the step of constructing the current networking structure by the generative adversarial network according to the initial device state information of the network node device stored in the super object model includes steps D10-D20:

[0062] Step D10, generating an initial networking structure by a generator according to initial device state information;

[0063] It should be noted that the initial device state information refers to the basic state data of the network node device at the time of deployment. The initial networking structure is a network configuration scheme generated by the generator algorithm based on the initial state information of the network node device. This includes the connection mode between devices, the preliminary allocation of resources, the initial deployment of services, etc. The system will generate an initial network layout using the generator based on the initial state information of the network node device.

[0064] In one embodiment, step D10 includes steps E10-E30:

[0065] Step E10, standardizing the initial device state information by the generator to obtain standardized device information, wherein the initial device state information includes software functions and / or geographic locations;

[0066] It should be noted that the generator converts the initial device state information into a unified and standardized data format by processing the device state information in the super object model, which includes but is not limited to software functions and geographic locations. This facilitates subsequent data processing. The standardized device information is processed by a unified data format and standard, which facilitates computer system processing and analysis, and can effectively support device state monitoring, management and optimization. Through this standardization process, not only does it simplify the complexity of data processing, but also improves the readability and comparability of data, and provides more unified and efficient data support for device state monitoring, resource optimization and fault diagnosis.

[0067] Step E20, clustering the collaborative devices into the same subnet, wherein the collaborative devices are devices with close geographic locations and complementary software functions;

[0068] It should be noted that clustering is an unsupervised learning method used to group objects in a data set based on their characteristics or similarities. In the device management scenario, the clustering algorithm can analyze the standardized device information and group devices with similar characteristics into the same subnet. These characteristics may include geographic location, software function, etc. A subnet usually refers to a network unit composed of a group of devices with close geographic locations and complementary functions. Through clustering analysis, devices that work collaboratively can be classified into the same subnet to facilitate optimal allocation of resources and more efficient management.

[0069] The cooperative devices refer to a group of devices that can cooperate with each other to provide services, wherein the geographical proximity refers to the proximity of the positions of the devices in the physical space. In device management and network planning, devices with geographical proximity are often easier to be physically connected and communicated, which helps to reduce communication delay and improve response speed. The software function complementation refers to the complementation of resources and functions of different devices. For example, one device has high-performance computing capability, and another device has large-capacity storage capability. Placing them in the same subnet can improve the computing and storage efficiency of the overall network.

[0070] In step E30, an initial networking structure is generated according to the network topology between the at least one subnet, the connection relationship between the cooperative devices in the subnet, and the roles assigned to each cooperative device in the connection relationship in the subnet, wherein the connection relationship is determined according to the device state information of the network node device.

[0071] It should be noted that the network topology describes the physical and logical connection mode between devices in the network, which reflects the layout and structure of the network. The connection relationship between the cooperative devices refers to how the devices are connected to each other through physical or logical links, and how they exchange information and communicate data. The connection relationship can be direct (direct communication between devices) or indirect (routing through intermediate nodes), for example, device A is directly connected to device B, and device B is connected to device D through router A, ensuring information sharing and cooperative work between devices. Role assignment refers to assigning a role to each device in the connection relationship according to the characteristics and capabilities of the device in the networking structure. For example, some devices with strong computing power, large storage capacity, high communication bandwidth, and close to the data source are core devices, and devices with weak computing power, small storage capacity, low communication bandwidth, and far from the data source are edge devices.

[0072] In this embodiment, the initial networking structure is generated according to the network topology between the at least one subnet, the connection relationship between the cooperative devices in the subnet, and the roles assigned to each cooperative device in the connection relationship in the subnet, which not only optimizes the network layout and device configuration, but also improves the efficiency of cooperative work between devices, ensuring stable operation and performance optimization of each device in the actual network environment.

[0073] In step D20, the initial networking structure is evaluated by a preset evaluation standard in the discriminator to obtain an evaluation result, so that the generator adjusts the initial networking structure to obtain the current networking structure according to the evaluation result.

[0074] It should be noted that the discriminator is used to evaluate the performance and effectiveness of the initial networking structure, and the preset evaluation criteria include network efficiency, inter-device communication delay, data processing capacity, energy consumption, security and other dimensions, which are used to quantify and compare the advantages and disadvantages of different networking structures. The evaluation results are obtained by analyzing and judging the initial networking structure according to the preset scoring criteria by the discriminator. These results can include comprehensive scores, advantages and disadvantages analysis, improvement suggestions and other aspects, which are used for subsequent networking optimization work. Through the preset evaluation criteria in the discriminator, the initial networking structure is evaluated to obtain the evaluation results. The discriminator analyzes and evaluates the initial networking structure based on the pre-set evaluation criteria, and the evaluation results help to more reasonably allocate network resources.

[0075] The generator iteratively adjusts and improves the initial networking structure according to the evaluation results to improve network performance, resource utilization efficiency or meet specific security and functional requirements. By feeding back the evaluation results to the generator, the generator optimizes the initial networking structure according to the feedback until the generated networking structure meets the preset evaluation criteria. The generator iteratively optimizes the initial networking structure according to the evaluation results until it meets the actual network environment demand criteria.

[0076] In one embodiment, step D20 includes steps F10-F20:

[0077] Step F10, according to the correlation matrix between the network node devices in the initial networking structure, evaluating the tightness of the cooperative networking between the network node devices in the initial networking structure;

[0078] It should be noted that the correlation matrix is used to represent the matrix of the relationship strength between devices in the network. In the matrix, the rows and columns usually represent different devices in the network, and each element of the matrix represents the correlation or association degree between the corresponding two devices. The tightness of cooperative networking refers to the tightness or strength of cooperation between devices in the network, which reflects the degree of mutual dependence of devices when performing tasks, sharing resources or communicating. High tightness means that the cooperation between devices is frequent and in-depth, and low tightness means that the devices are relatively independent or less cooperative. Devices with high correlation should be in the same subnet, and devices with low correlation should reduce connections.

[0079] Step F20, and / or, by simulating actual business load, obtaining the key performance indicator values of the network node devices in the initial networking structure, and evaluating the running situation of the initial networking structure in the actual network environment through the key performance indicator values.

[0080] It should be noted that simulating actual business load means creating similar traffic and operation mode as actual business running through software tools or special equipment in network environment. This includes simulating user access, data transmission, service request, etc. to evaluate network performance in real environment. The initial networking structure is a network architecture constructed based on the initial state information of the equipment and the preset network requirements. The key performance indicator value is the quantitative data for measuring network performance and health status, including but not limited to delay, throughput, packet loss rate, memory usage, network bandwidth utilization; the running situation of the network in the real environment is evaluated to ensure the stability and efficiency of the network under actual business pressure.

[0081] In an embodiment, the utilization of each device resource can also be evaluated to ensure that the devices in the network do not overload or waste resources. At the same time, the discriminator detects whether the load is balanced to avoid partial device overload or ineffective utilization; the discriminator can also evaluate the security of the network, for example, by analyzing the connection and transmission protocol between devices to determine whether there is a potential security risk. For high-risk devices, the discriminator will reduce the connection priority; for resource-limited devices, the discriminator will additionally evaluate the power consumption to ensure that the generated networking scheme is optimal in terms of energy consumption.

[0082] In the present embodiment, by evaluating the degree of cooperation of network node devices and the performance indicators under simulated actual business load, the resource allocation can be targetedly optimized, and the network stability and efficiency can be improved.

[0083] In the present embodiment, the discriminator continuously evaluates the generated initial networking structure and sends feedback to the generator to prompt the generator to continuously improve the generated networking structure, which helps to improve the quality of the networking structure and makes the networking structure generated by the generator closer to the requirements of the real network environment; the generated networking structure can better adapt to the changing network environment and business requirements, improve the flexibility and response speed of the network, and the continuous optimization of the networking structure helps to more reasonably allocate and use resources, avoid resource waste, and improve the overall performance of the network.

[0084] It should be noted that the above examples are only for understanding the present application and do not constitute a limitation on the dynamic networking method of the present application. More forms of simple changes based on this technical concept are within the protection scope of the present application.

[0085] The present application also provides a dynamic networking device, please refer to Figure 3 The dynamic networking device comprises:

[0086] The monitoring module 10 is configured to monitor real-time device state information and actual service requirements of network node devices in a current networking structure in real time, wherein the current networking structure is constructed by the GAN based on initial device state information of the network node devices stored in the super object model.

[0087] The networking module 20 is configured to, if it is determined that the network node devices are abnormal and / or it is detected that the actual service requirements of the network node devices change, re-generate a new networking structure by the GAN based on real-time device state information stored in the super object model.

[0088] Optionally, the monitoring module 10 is further configured to generate an initial networking structure by the generator based on the initial device state information.

[0089] The initial networking structure is evaluated by a preset evaluation standard in the discriminator to obtain an evaluation result, so that the generator adjusts the initial networking structure to obtain the current networking structure based on the evaluation result.

[0090] Optionally, the monitoring module 10 is further configured to generate an initial networking structure by the generator based on the initial device state information.

[0091] The initial networking structure is evaluated by a preset evaluation standard in the discriminator to obtain an evaluation result, so that the generator adjusts the initial networking structure to obtain the current networking structure based on the evaluation result.

[0092] Optionally, the monitoring module 10 is further configured to perform standardization processing on the initial device state information by the generator to obtain standardized device information, wherein the initial device state information includes software functions and / or geographic positions.

[0093] The collaborative devices are clustered into the same subnet, wherein the collaborative devices are devices with close geographic positions and complementary software functions.

[0094] The initial networking structure is generated based on a network topology between at least one subnet, a connection relationship between the collaborative devices in the subnet, and roles of the collaborative devices in the subnet in the connection relationship, wherein the connection relationship is determined based on the device state information of the network node devices.

[0095] Optionally, the monitoring module 10 is further configured to evaluate a closeness degree of the network node devices in the initial networking structure for collaborative networking based on a correlation matrix between the network node devices in the initial networking structure; and / or

[0096] The key performance indicator values of the network node devices in the initial networking structure are obtained by simulating actual service load, and the running situation of the initial networking structure in the actual network environment is evaluated based on the key performance indicator values.

[0097] Optionally, the networking module 20 is further configured to determine the current resource requirement of the network node device in the new networking structure based on the real-time device state information in the super object model.

[0098] According to the current resource requirement, the network resource of the network node device in the new networking structure is allocated.

[0099] The dynamic networking device provided by the application can solve the technical problem of low resource utilization rate of the device in the network structure. Compared with the prior art, the dynamic networking device provided by the application has the same beneficial effects as the dynamic networking method provided by the above-mentioned embodiments, and other technical features in the dynamic networking device are the same as the features disclosed in the above-mentioned embodiments, which will not be repeated here.

[0100] The application provides a dynamic networking system, which comprises a dynamic networking device, and the dynamic networking device comprises at least one processor and a memory connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the dynamic networking method in the first embodiment.

[0101] Reference will be made to the following description Figure 4 which shows a structural diagram of a dynamic networking device suitable for implementing the embodiments of the application. The dynamic networking device in the embodiments of the application can include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistant), PADs (Portable Application Description), PMPs (Portable Media Player), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. Figure 4 The dynamic networking device shown is only an example, and should not bring any limitation to the functions and use range of the embodiments of the application.

[0102] As Figure 4As shown, the dynamic networking device can include a processing apparatus 1001 (e.g., a central processor, a graphics processor, etc.) that can perform various appropriate actions and processes according to programs stored in a read only memory (ROM) 1002 or loaded from a storage apparatus 1003 into a random access memory (RAM) 1004. Various programs and data required for operation of the dynamic networking device are also stored in the RAM 1004. The processing apparatus 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: input apparatuses 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output apparatuses 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; the storage apparatus 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication apparatus 1009. The communication apparatus 1009 can allow the dynamic networking device to communicate with other devices wirelessly or by wire to exchange data. Although the dynamic networking device with various systems is shown in the figure, it should be understood that all the shown systems are not required to be implemented or possessed. More or less systems can be alternatively implemented or possessed.

[0103] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by a communication apparatus, or installed from the storage apparatus 1003, or installed from the ROM 1002. When the computer program is executed by the processing apparatus 1001, the above-mentioned functions defined in the methods of embodiments of the present disclosure are performed.

[0104] The dynamic networking device provided by the present disclosure adopts the dynamic networking method in the above-mentioned embodiments, and can solve the technical problem of low resource utilization rate of devices in a network structure. Compared with the prior art, the dynamic networking device provided by the present disclosure has the same beneficial effects as the dynamic networking method provided by the above-mentioned embodiments, and other technical features in the dynamic networking device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0105] It should be understood that various parts of the present application can be realized by hardware, software, firmware or a combination thereof. In the above description of embodiments, specific features, structures, materials or characteristics can be combined in any appropriate manner in any one or more embodiments or examples.

[0106] The above description is merely illustrative of the application and is not intended to limit the scope of the application. Any variations and modifications that can be made by any person skilled in the art within the spirit and scope of the application are intended to be encompassed by the application. Therefore, the scope of the application should be determined by the appended claims.

[0107] The present application provides a computer readable storage medium having stored thereon computer readable program instructions (i.e., a computer program) for performing the dynamic networking method in the above-described embodiments.

[0108] The computer readable storage medium provided by the present application may, for example, be a U disk, but is not limited to an electric, magnetic, optical, electromagnetic, infrared, or semiconductor system or device, or any combination thereof. More specific examples of the computer readable storage medium can include, but are not limited to, an electric connection having one or more conductive wires, a portable computer disk, a hard disk, a random access memory (RAM), a read only memory (ROM), an erasable programmable read only memory (EPROM or flash memory), an optical fiber, a portable compact disk read only memory (CD-ROM), an optical storage device, a magnetic storage device, or any appropriate combination thereof. In the present embodiment, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer readable storage medium can be transmitted by any appropriate medium, including but not limited to an electric wire, an optical cable, an RF (Radio Frequency), etc., or any appropriate combination thereof.

[0109] The above-described computer readable storage medium can be contained in the dynamic networking device; or can exist separately without being assembled into the dynamic networking device.

[0110] The computer readable storage medium described above carries one or more programs, when the one or more programs are executed by the dynamic networking device, cause the dynamic networking device to: monitor real-time device state information and actual service demand of network node devices in a current networking structure in real time, wherein the current networking structure is constructed by the GAN according to initial device state information of the network node devices stored in the super object model;

[0111] If it is determined that the network node device is abnormal according to the device state information, and / or, it is detected that the actual service demand of the network node device changes, a new networking structure is regenerated by the GAN according to real-time device state information stored in the super object model.

[0112] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0113] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a procedure, or a part of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or in the reverse order, depending on the functionality involved. It is also noted that each block in the block diagrams and / or flow diagrams and combinations of blocks in the block diagrams and / or flow diagrams can be implemented by special-purpose hardware-based systems that perform the specified functions or operations, or combinations of special-purpose hardware and computer instructions.

[0114] The modules described in the embodiments of the present application can be implemented in the form of software or in the form of hardware. In some cases, the names of the modules do not constitute a limitation on the modules themselves.

[0115] The computer readable storage medium provided in the present application is a computer readable storage medium, which stores computer readable program instructions (i.e., a computer program) for executing the dynamic networking method described above, and can solve the technical problem of low resource utilization rate of devices in a network structure. Compared with the prior art, the computer readable storage medium provided in the present application has the same beneficial effects as the dynamic networking method provided in the above embodiments, and will not be described here.

[0116] The present application also provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the dynamic networking method as described above.

[0117] The computer program product provided in the present application can solve the technical problem of low resource utilization rate of devices in a network structure. Compared with the prior art, the computer program product provided in the present application has the same beneficial effects as the dynamic networking method provided in the above embodiments, and will not be described here.

[0118] The above only describes some embodiments of the present application, and does not limit the patent scope of the present application. Any equivalent structural transformation, direct / indirect application in other related technical fields based on the technical concept of the present application, and the content of the specification and drawings are included in the patent protection scope of the present application.

Claims

1. A dynamic networking method, characterized in that: The method comprises: Real-time monitoring of real-time device status information and actual business needs of network node devices within a current networking structure, wherein the current networking structure is constructed using a generative adversarial network based on initial device status information of network node devices stored in a hyper-object model; If a network node device is determined to be abnormal based on the device status information, and / or it is detected that the actual business needs of the network node device have changed, a new networking structure is regenerated through an adversarial generation network based on the real-time device status information stored in the super object model, wherein the super object model collects and stores the real-time dynamic status information of the network node device in real time during the networking process, forms a virtual resource pool based on the dynamic status information, and dynamically adjusts the network architecture and network resource allocation to regenerate a new networking structure.

2. The dynamic networking method according to claim 1, wherein: After the step of regenerating a new networking structure through a generative adversarial network based on the real-time device status information stored in the super object model, the method includes: Determine the current resource requirements of network node devices in the new networking structure based on the real-time device status information in the hyper-object model; Based on current resource requirements, network resources of network node devices in the new networking structure are allocated.

3. The dynamic networking method according to claim 1, wherein: The adversarial generative network includes a generator and a discriminator. The steps of constructing the current networking structure by the adversarial generative network according to the initial device state information of the network node devices stored in the super object model include: Generate the initial network structure through the generator according to the initial device status information; The initial networking structure is evaluated by a preset evaluation standard in the discriminator to obtain an evaluation result, so that the generator adjusts the initial networking structure according to the evaluation result to obtain the current networking structure.

4. The dynamic networking method according to claim 3, wherein: The step of generating an initial networking structure by a generator according to the initial device state information includes: Standardizing the initial device status information by a generator to obtain standardized device information, wherein the initial device status information includes software functions and / or geographic location; Clustering collaborative devices into the same subnet, wherein the collaborative devices are devices that are geographically close and have complementary software functions; An initial networking structure is generated based on the network topology between at least one subnet, the connection relationship between collaborative devices in the subnet, and the role assigned to each collaborative device in the subnet in the connection relationship, wherein the connection relationship is determined based on the device status information of the network node device.

5. The dynamic networking method according to claim 3, wherein: The step of evaluating the initial networking structure using a preset evaluation criterion in the discriminator includes: Evaluate the closeness of collaborative networking between network node devices in the initial networking structure based on a correlation matrix between network node devices in the initial networking structure; and / or By simulating actual business loads, key performance indicator values ​​of network node devices in the initial networking structure are obtained, and the operation of the initial networking structure in the actual network environment is evaluated using the key performance indicator values.

6. The dynamic networking method according to claim 1, wherein: The super object model is constructed based on the hardware resources, software functions, geographical location, firmware version, communication protocol and operating status of network node devices.

7. A dynamic networking device, characterized in that: The dynamic networking device includes: A monitoring module, configured to monitor in real time the real-time device status information and actual service requirements of network node devices within a current networking structure, wherein the current networking structure is constructed using a generative adversarial network based on the initial device status information of the network node devices stored in the hyper-object model; A networking module is used to regenerate a new networking structure through an adversarial generation network based on the real-time device status information stored in the super-thing model if it is determined that the network node device is abnormal based on the device status information, and / or if it is detected that the actual business needs of the network node device have changed. The super-thing model collects and stores the real-time dynamic status information of the network node device in real time during the networking process, forms a virtual resource pool based on the dynamic status information, and dynamically adjusts the network architecture and network resource allocation to regenerate a new networking structure.

8. A dynamic networking system, characterized in that: The system includes a dynamic networking device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the dynamic networking method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the dynamic networking method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the dynamic networking method according to any one of claims 1 to 6 are implemented.

Images