Method and system for applying AR virtual reality technology to intelligent network virtual mapping

Abstract

The invention discloses a method and a system for applying an AR virtual reality technology to intelligent network virtual mapping. The method comprises the following steps: learning workflow data of a virtual network management node through a real-time federal learning process; a real-time federal learning process is mapped through a mapping process of a virtual network, and a virtual network mapping model is constructed, which comprises the following steps: obtaining 3D coordinates for positioning virtual network management nodes in the network, and establishing an information base according to the characteristics of the virtual network management nodes; constructing a virtual learning process according to different virtual network management node environments by adopting a feature matching algorithm, and detecting whether a virtual learning process model result is normal or not through a nearest neighbor algorithm flow with a rejection decision; an AR application scene is constructed, and visualization is completed; and performing intelligent network virtual mapping by adopting the virtual network mapping model. According to the invention, the AR virtual reality technology is used for intelligent network virtual mapping, so that the application scene is visualized, and the development of a network system structure is promoted.

Description

Technical Field

[0001] The present invention relates to the field of smart networks, and in particular to a method and system for using AR virtual reality technology for virtual mapping of smart networks. Background Art

[0002] In order to solve the many problems faced in the development of the Internet, since the late 1990s, relevant research institutions at home and abroad have carried out a lot of research on new network technologies, such as IP multicast technology, secure routing technology, IPv6, etc. However, these technologies have not been widely used after long-term research and development and testing. The root causes include two aspects: First, under the current network architecture, the premise of applying the above new technologies is that the network must be upgraded and transformed, and the huge scale of the Internet will make the transformation cost unacceptable; second, the current Internet is composed of many heterogeneous autonomous domains, and the construction, management and maintenance of these autonomous domains are the responsibility of different Internet Service Providers (ISPs). The process of all Internet service providers deploying a new network architecture at the same time will face many practical difficulties. Therefore, compared with the rapid development trend of the Internet application level, the development progress of the network architecture is relatively slow. Summary of the invention

[0003] The purpose of the present invention is to provide a method and system for using AR virtual reality technology for intelligent network virtual mapping to promote the development of network architecture.

[0004] To achieve the above purpose, the technical solution provided by the present invention is:

[0005] The first aspect of the present application provides a method for using AR virtual reality technology for intelligent network virtual mapping, comprising the following steps:

[0006] S1: Learning the workflow data of the virtual network management node through a real-time federated learning process;

[0007] S2: Map the real-time federated learning process through the virtual network mapping process to build a virtual network mapping model, including: obtaining the 3D coordinates of the virtual network management node in the network, and establishing an information library according to the characteristics of the virtual network management node; using a feature matching algorithm to build a virtual learning process according to the different virtual network management node environments, and using a nearest neighbor algorithm process with a rejection decision to detect whether the construction result of the virtual network mapping model is normal; building an AR application scenario and completing visualization;

[0008] S3: Use the virtual network mapping model to perform intelligent network virtual mapping.

[0009] To optimize the above technical solutions, the specific measures taken also include:

[0010] The workflow data of the virtual network management node includes the network topology, link available bandwidth, resource attributes and status of nodes; the learning includes resource perception, demand analysis, mapping decision and mapping command.

[0011] The real-time federated learning iteratively analyzes massive data in a log-layered manner through a server, and uses the best analysis result of each iteration for the next iteration training update.

[0012] Furthermore, the workflow data of the virtual network management node is obtained in the following manner:

[0013] The application service topology is mined using the association relationship in the log service application database, and is associated with the virtual network topology to obtain the first-layer application service topology relationship;

[0014] A data set based on the topological relationship of the first-layer application services is mined from the log of each service to form a topological data set. The data in the topological data set records the monitoring data and operating health status under different time dimensions.

[0015] Furthermore, the virtual network mapping process includes:

[0016] The virtual network management node collects the resource usage of each underlying node and link through the resource detection mechanism;

[0017] Parse the virtual network mapping request submitted by the service provider to obtain the resource requirements and service category information of the virtual network;

[0018] The virtual network management node obtains the mapping scheme of the virtual network request through a specific mapping algorithm based on the current resource situation;

[0019] The corresponding mapping command is generated according to the mapping decision and sent to each reconfigurable routing virtual network management node. After receiving the command, each virtual network management node divides node resources or reconstructs internally to map a virtual network that meets business needs.

[0020] Furthermore, the nearest neighbor algorithm with rejection decision is specifically:

[0021] Step 1: Divide the network area consisting of the virtual network management node itself and its associated nodes into a category w i , i=1,2,3,....C, i represents the i-th category, C represents the total number of categories, and the device at the center of the network area is a sample in this category;

[0022] Step 2: Calculate the real-time positioning coordinates p and category w of the mobile object i The distance between each sample within:

[0023] G i (x) = min||pp*||

[0024] Among them, G i (x) represents the real-time positioning coordinates p and category w of the mobile object i The distance between each sample in the network, p represents the real-time positioning coordinates of the mobile object, and p* represents the device coordinates of the center of the network area;

[0025] Find the real-time positioning coordinates p and category w of the moving object i The minimum distance between each sample in the range is defined as the distance between the real-time positioning coordinates and the category w i Distance between:

[0026] Ng i (p) = ming(p)

[0027] Among them, Ng i (p) represents the real-time positioning coordinates and category w i The distance between

[0028] Step 4: Determine:

[0029] Ng i (p)≤l

[0030] If the real-time positioning coordinates and category w i If the distance between them is less than the set distance l, the real-time positioning coordinates are classified into this category and the match is successful; otherwise, the decision is rejected.

[0031] The virtual network mapping model includes:

[0032] Underlying network:

[0033] The underlying network topology is represented by a weighted undirected graph:

[0034]

[0035] Among them, G s Represents the underlying network topology, N s and L s They are the bottom-level node set and bottom-level link set respectively; and They are the maximum transmission processing capabilities that can be provided by the nodes and links of the underlying network respectively;

[0036] Virtual network mapping request:

[0037] The virtual network mapping request includes the virtual network topology G v , request arrival time t a and request duration td0 , the virtual network mapping request topology is represented by a weighted undirected graph:

[0038]

[0039] Among them, G v Represents the virtual network mapping request topology, N v and L v are the collections of virtual nodes and virtual links respectively, and are resource constraints for virtual nodes and virtual links respectively; virtual network requests are a After arrival, the underlying network allocates and Constrained network resources; virtual networks are running t d0 After that time, the resources it occupies will be reclaimed by the underlying network;

[0040] Virtual network mapping:

[0041] Virtual network mapping is a constraint-satisfying mapping from the virtual network mapping request topology to the underlying network topology, expressed as:

[0042]

[0043] Where M represents the virtual network mapping, N′∪N s , L′∪L s , R N and R L They are the node and link resources allocated by the underlying network for the virtual network request;

[0044] Virtual network mapping can be decomposed into node mapping and link mapping; multiple virtual nodes belonging to the same virtual network cannot be repeatedly mapped to an underlying node, but multiple virtual links can be repeatedly mapped to an underlying path; if during the virtual network mapping process, a mapping target with sufficient remaining resources cannot be found in the underlying network for a virtual node or virtual link, it means that the virtual network mapping has failed and the mapping request will be rejected.

[0045] The second aspect of the present application provides a system for using AR virtual reality technology for intelligent network virtual mapping, including:

[0046] A learning module for learning the workflow data of the virtual network management node through a real-time federated learning process;

[0047] The virtual network mapping model building module is used to map the real-time federated learning process through the virtual network mapping process and build a virtual network mapping model, including: obtaining the 3D coordinates of the virtual network management node in the network, and establishing an information library according to the characteristics of the virtual network management node; using the feature matching algorithm to build a virtual learning process according to the different virtual network management node environments, and using the nearest neighbor algorithm process with rejection decision to detect whether the virtual network mapping model construction result is normal; building an AR application scenario and completing visualization;

[0048] The virtual mapping module is used to perform intelligent network virtual mapping using a virtual network mapping model.

[0049] The third aspect of the present application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for using AR virtual reality technology for intelligent network virtual mapping as described above is implemented.

[0050] The fourth aspect of the present application provides a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the above-mentioned AR virtual reality technology for the smart network virtual mapping method.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] The method of using AR virtual reality technology for intelligent network virtual mapping of the present invention adds virtual reality information to the real production scene, realizes the visual management and guidance of the network production process to discover the loss of the real environment caused by the abnormality of the intelligent network in the process of federated learning.

[0053] The present invention can map out a virtual network that meets business needs, and detect whether the virtual learning process model result is normal through a nearest neighbor algorithm process with rejection decision, so as to realize visualization of application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 : A flow chart of the method for using AR virtual reality technology of the present invention for intelligent network virtual mapping.

[0055] Figure 2 : The AR virtual reality technology of the present invention is used for the system structure diagram of intelligent network virtual mapping.

[0056] Figure 3 : Schematic diagram of the nearest neighbor algorithm flow chart with rejection decision of the present invention. DETAILED DESCRIPTION

[0057] The above contents of the present invention are further described in detail below in the form of embodiments, but this should not be understood as the scope of the above subject matter of the present invention being limited to the following embodiments, and all technologies realized based on the above contents of the present invention belong to the scope of the present invention.

[0058] Some of the terms in the present invention are explained as follows:

[0059] Federated machine learning (Federated Machine Learning / Federated Learning), also known as federated learning, joint learning, and alliance learning, is a machine learning framework that can effectively help multiple institutions use data and conduct machine learning modeling while meeting the requirements of user privacy protection, data security, and government regulations.

[0060] Augmented Reality (AR) technology is a technology that cleverly integrates virtual information with the real world. It widely uses multimedia, three-dimensional modeling, real-time tracking and registration, intelligent interaction, sensing and other technical means to simulate computer-generated text, images, three-dimensional models, music, video and other virtual information, and apply them to the real world. The two types of information complement each other, thereby achieving "enhancement" of the real world. Unlike VR, AR emphasizes the integration of virtual and reality rather than completely replacing reality. The existing asset positioning technology has large coordinate positioning errors, and there is an overlap problem in the positioning of multiple sensors at close range.

[0061] "Digital twin" makes full use of physical models, sensor updates, operation history and other data, integrates multi-disciplinary, multi-physical quantity, multi-scale, and multi-probability simulation processes, completes mapping in virtual space, and thus reflects the entire life cycle of the corresponding physical equipment.

[0062] In one embodiment, the present invention proposes a method for using AR virtual reality technology for intelligent network virtual mapping, such as Figure 1 As shown, the following steps are included:

[0063] S1: Learning the workflow data of the virtual network management node through a real-time federated learning process;

[0064] S2: Map the real-time federated learning process through the virtual network mapping process to build a virtual network mapping model, including: obtaining the 3D coordinates of the virtual network management node in the network, and establishing an information library according to the characteristics of the virtual network management node; using a feature matching algorithm to build a virtual learning process according to the different virtual network management node environments, and using a nearest neighbor algorithm process with a rejection decision to detect whether the construction result of the virtual network mapping model is normal; building an AR application scenario and completing visualization;

[0065] S3: Use the virtual network mapping model to perform intelligent network virtual mapping.

[0066] To optimize the above technical solutions, the specific measures taken also include:

[0067] The workflow data of the virtual network management node includes the network topology, link available bandwidth, node resource attributes and status, including monitoring data and operational health status between servers and databases, middleware, server CPU, memory, disk, and processes; learning includes resource perception, demand analysis, mapping decisions, and mapping commands.

[0068] Real-time federated learning uses the server to iteratively analyze massive data in a log-layered manner, and uses the best analysis results of each iteration for the next iteration training update.

[0069] The workflow data of the virtual network management node is obtained as follows:

[0070] The application service topology is mined using the association relationship in the log service application database, and is associated with the virtual network topology to obtain the first-layer application service topology relationship;

[0071] A data set based on the topological relationship of the first-layer application services is mined from the log of each service to form a topological data set. The data in the topological data set records the monitoring data and operating health status under different time dimensions.

[0072] The virtual network mapping process includes:

[0073] The virtual network management node collects the resource usage of each underlying node and link through the resource detection mechanism;

[0074] Parse the virtual network mapping request submitted by the service provider to obtain the resource requirements and service category information of the virtual network;

[0075] The virtual network management node obtains the mapping scheme of the virtual network request through a specific mapping algorithm based on the current resource situation;

[0076] The corresponding mapping command is generated according to the mapping decision and sent to each reconfigurable routing virtual network management node. After receiving the command, each virtual network management node divides node resources or reconstructs internally to map a virtual network that meets business needs.

[0077] Nearest neighbor algorithms with rejection decisions such as Figure 3 As shown, specifically:

[0078] Step 1: Divide the network area consisting of the virtual network management node itself and its associated nodes into a category w i, i=1,2,3,....C, i represents the i-th category, C represents the total number of categories, and the device at the center of the network area is a sample in this category;

[0079] Step 2: Calculate the real-time positioning coordinates p and category w of the mobile object i The distance between each sample within:

[0080] G i (x) = min||pp * ||

[0081] Among them, G i (x) represents the real-time positioning coordinates p and category w of the mobile object i The distance between each sample in the network, p represents the real-time positioning coordinates of the mobile object, and p* represents the device coordinates of the center of the network area;

[0082] Find the real-time positioning coordinates p and category w of the moving object i The minimum distance between each sample in the range is defined as the distance between the real-time positioning coordinates and the category w i Distance between:

[0083] Ng i (p) = ming(p)

[0084] Among them, Ng i (p) represents the real-time positioning coordinates and category w i The distance between

[0085] Step 4: Determine:

[0086] Ng i (p)≤l

[0087] If the real-time positioning coordinates and category w i If the distance between them is less than the set distance l, the real-time positioning coordinates are classified into this category and the match is successful; otherwise, the decision is rejected.

[0088] The virtual network mapping model includes:

[0089] Underlying network:

[0090] The underlying network topology is represented by a weighted undirected graph:

[0091]

[0092] Among them, G s Represents the underlying network topology, N s and L s They are the bottom-level node set and bottom-level link set respectively; and They are the maximum transmission processing capabilities that can be provided by the nodes and links of the underlying network respectively;

[0093] Virtual network mapping request:

[0094] The virtual network mapping request includes the virtual network topology G v , request arrival time t a and request duration t d0 , the virtual network mapping request topology is represented by a weighted undirected graph:

[0095]

[0096] Among them, G v Represents the virtual network mapping request topology, N v and L v are the collections of virtual nodes and virtual links respectively, and are resource constraints for virtual nodes and virtual links respectively; virtual network requests are a After arrival, the underlying network allocates and Constrained network resources; virtual networks are running t d0 After that time, the resources it occupies will be reclaimed by the underlying network;

[0097] Virtual network mapping:

[0098] Virtual network mapping is a constraint-satisfying mapping from the virtual network mapping request topology to the underlying network topology, expressed as:

[0099]

[0100] Where M represents the virtual network mapping, N′∪N s , L′∪L s , R N and R L They are the node and link resources allocated by the underlying network for the virtual network request;

[0101] Virtual network mapping can be decomposed into node mapping and link mapping; multiple virtual nodes belonging to the same virtual network cannot be repeatedly mapped to an underlying node, but multiple virtual links can be repeatedly mapped to an underlying path; if during the virtual network mapping process, a mapping target with sufficient remaining resources cannot be found in the underlying network for a virtual node or virtual link, it means that the virtual network mapping has failed and the mapping request will be rejected.

[0102] In a disclosed embodiment of the present invention, the real-time federated learning process is:

[0103] In the Nth training iteration, the terminal performs local training using locally collected images / videos based on the global model downloaded from the FL server. The terminal then reports the intermediate training results of the Nth iteration, such as the gradient of the DNN, to the FL server through the uplink channel. At the same time, the FL server sends the N+1th global model and training configuration to the terminal. While the FL server aggregates the gradients collected in the Nth iteration, the terminal can perform training for the N+1th iteration. Federated Aggregation outputs an updated global model for the next iteration of training, and distributes the model to the terminal together with the updated training configuration.

[0104] In a disclosed embodiment of the present invention, an AR application scene is constructed by Unity to achieve visualization.

[0105] The present invention is further described in detail below with reference to specific application scenarios:

[0106] The application scenario is a network area centered on a discrete data center or an associated node in the network, and the device monitoring function in the area is realized. First, the visualization content and visualization UI of the device deployed at a node in the area are designed. According to the visualization design, a virtual visualization model is built in Unity, and finally the mobile monitoring function of the device is realized by using indoor positioning technology and AR.

[0107] When the production personnel are within a certain range of the device DMC-80H with the associated node as the center, the indoor positioning system is used to obtain the indoor positioning coordinate information of the mobile device, and the positioning information is used as the positioning coordinate information of the mobile device camera. The camera positioning information is transmitted to the system server and matched with the positioning feature information of the device (target point of interest). If the match is successful, the virtual monitoring information of the device is pushed and displayed in fusion with the device based on the estimated camera posture of the mobile device.

[0108] After building the AR application scene in Unity, you can publish it to the Android system and install the application. After opening the application, there are two selectable buttons on the home page, namely device basic data and device operation data.

[0109] In another embodiment, the present invention proposes a system for using AR virtual reality technology for intelligent network virtual mapping, such as Figure 2 As shown, including:

[0110] A learning module for learning the workflow data of the virtual network management node through a real-time federated learning process;

[0111] The virtual network mapping model building module is used to map the real-time federated learning process through the virtual network mapping process and build a virtual network mapping model, including: obtaining the 3D coordinates of the virtual network management node in the network, and establishing an information library according to the characteristics of the virtual network management node; using the feature matching algorithm to build a virtual learning process according to the different virtual network management node environments, and using the nearest neighbor algorithm process with rejection decision to detect whether the virtual network mapping model construction result is normal; building an AR application scenario and completing visualization;

[0112] The virtual mapping module is used to perform intelligent network virtual mapping using a virtual network mapping model.

[0113] In another embodiment of the present invention, an electronic device is proposed, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned AR virtual reality technology is used for the method of virtual mapping of a smart network.

[0114] In another embodiment, the present invention provides a computer-readable storage medium storing a computer program, which enables a computer to execute an AR virtual reality technology for a smart network virtual mapping method.

[0115] In the embodiments disclosed in the present application, the computer storage medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. The computer storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the above. More specific examples of computer storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0116] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Any technician familiar with the profession, without departing from the scope of the technical solution of the present invention, according to the technical essence of the present invention, any simple modification, equivalent replacement and improvement made to the above embodiment still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for using AR virtual reality technology for intelligent network virtual mapping, characterized in that: The following steps are involved: S1: Learning the workflow data of the virtual network management node through a real-time federated learning process; S2: Map the real-time federated learning process through the virtual network mapping process and build a virtual network mapping model, including: Obtain the 3D coordinates of the virtual network management node in the network and establish an information base based on the characteristics of the virtual network management node; A feature matching algorithm is used to construct a virtual learning process according to the different virtual network management node environments, and a nearest neighbor algorithm process with rejection decision is used to detect whether the construction result of the virtual network mapping model is normal; an AR application scenario is constructed to complete visualization; S3: Use the virtual network mapping model to perform intelligent network virtual mapping.

2. The method for using AR virtual reality technology for intelligent network virtual mapping according to claim 1 is characterized by: The workflow data of the virtual network management node includes the network topology, link available bandwidth, resource attributes and status of nodes; the learning includes resource perception, demand analysis, mapping decision and mapping command.

3. The method for using AR virtual reality technology for intelligent network virtual mapping according to claim 1, characterized in that: The real-time federated learning iteratively analyzes massive data in a log-layered manner through a server, and uses the best analysis result of each iteration for the next iteration training update.

4. The method for using AR virtual reality technology for intelligent network virtual mapping according to claim 1, characterized in that: The method for acquiring the workflow data of the virtual network management node is as follows: The application service topology is mined using the association relationship in the log service application database, and is associated with the virtual network topology to obtain the first-layer application service topology relationship; A data set based on the topological relationship of the first-layer application services is mined from the log of each service to form a topological data set. The data in the topological data set records the monitoring data and operating health status under different time dimensions.

5. The method for using AR virtual reality technology for intelligent network virtual mapping according to claim 1 is characterized in that: The virtual network mapping process includes: The virtual network management node collects the resource usage of each underlying node and link through the resource detection mechanism; Parse the virtual network mapping request submitted by the service provider to obtain the resource requirements and service category information of the virtual network; The virtual network management node obtains the mapping scheme of the virtual network request through a specific mapping algorithm based on the current resource situation; The corresponding mapping command is generated according to the mapping decision and sent to each reconfigurable routing virtual network management node. After receiving the command, each virtual network management node divides node resources or reconstructs internally to map a virtual network that meets business needs.

6. The method for using AR virtual reality technology for intelligent network virtual mapping according to claim 1, characterized in that: The nearest neighbor algorithm with rejection decision is specifically: Step 1: Divide the network area consisting of the virtual network management node itself and its associated nodes into a category w i , i = 1, 2, 3, ... C, i represents the i-th category, C represents the total number of categories, and the device at the center of the network area is a sample in this category; Step 2: Calculate the distance between the real-time positioning coordinates p of the mobile object and each sample in the category w: G i (x)=min||p-p * || Among them, G i (x) represents the real-time positioning coordinates p and category w of the mobile object i The distance between each sample within, p represents the real-time positioning coordinates of the moving object, p * The device coordinates representing the center of the network area; Find the minimum distance between the real-time positioning coordinates p of the mobile object and each sample in the category w, and define the distance as the distance between the real-time positioning coordinates and the category w i Distance between: Of i (p)=some(p) Among them, Ng i (p) represents the real-time positioning coordinates and category w i The distance between Step 4: Determine: Of i (p)≤l If the real-time positioning coordinates and category w i If the distance between them is less than the set distance l, the real-time positioning coordinates are classified into this category and the match is successful; otherwise, the decision is rejected.

7. The method for using AR virtual reality technology for intelligent network virtual mapping according to claim 1, characterized in that: The virtual network mapping model includes: Underlying network: The underlying network topology is represented by a weighted undirected graph: Among them, G s Represents the underlying network topology, N s and L s They are the bottom-level node set and bottom-level link set respectively; and They are the maximum transmission processing capabilities that can be provided by the nodes and links of the underlying network respectively; Virtual network mapping request: The virtual network mapping request includes the virtual network topology G v , request arrival time t a and request duration t d0 , the virtual network mapping request topology is represented by a weighted undirected graph: Among them, G v Represents the virtual network mapping request topology, N v and L v are the collections of virtual nodes and virtual links respectively, and are resource constraints for virtual nodes and virtual links respectively; virtual network requests are a After arrival, the underlying network allocates and Constrained network resources; virtual networks are running t d0 After that time, the resources it occupies will be reclaimed by the underlying network; Virtual network mapping: Virtual network mapping is a constraint-satisfying mapping from the virtual network mapping request topology to the underlying network topology, expressed as: Where M represents the virtual network mapping, N′∪N s , L′∪L s , R N and R L They are the node and link resources allocated by the underlying network for the virtual network request; Virtual network mapping can be decomposed into node mapping and link mapping; multiple virtual nodes belonging to the same virtual network cannot be repeatedly mapped to an underlying node, but multiple virtual links can be repeatedly mapped to an underlying path; if during the virtual network mapping process, a mapping target with sufficient remaining resources cannot be found in the underlying network for a virtual node or virtual link, it means that the virtual network mapping has failed and the mapping request will be rejected.

8. A system for using AR virtual reality technology for intelligent network virtual mapping, characterized in that: include: A learning module for learning the workflow data of the virtual network management node through a real-time federated learning process; The virtual network mapping model building module is used to map the real-time federated learning process through the virtual network mapping process and build a virtual network mapping model, including: obtaining the 3D coordinates of the virtual network management node in the network, and establishing an information library according to the characteristics of the virtual network management node; using the feature matching algorithm to build a virtual learning process according to the different virtual network management node environments, and using the nearest neighbor algorithm process with rejection decision to detect whether the virtual network mapping model construction result is normal; building an AR application scenario and completing visualization; The virtual mapping module is used to perform intelligent network virtual mapping using a virtual network mapping model.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for using the AR virtual reality technology for intelligent network virtual mapping as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the method for using AR virtual reality technology for intelligent network virtual mapping as described in any one of claims 1 to 7.

Images