Method, device and non-transitory storage medium for determining network topology

Abstract

The application discloses a network topology determination method and device and a nonvolatile storage medium. The method comprises the following steps: acquiring call detail record data of a core network, wherein the call detail record data at least comprises a network type, a network element type, a protocol type, a source network element IP address and a destination network element IP address of a service route; determining effective service route information according to the call detail record data; obtaining a first-level network topology based on the effective service route information and a preset topology relationship; and expanding the first-level network topology into a multi-layer network topology according to a service logic relationship layer by layer. The application solves the technical problem that related technologies are focused on automatic layout of a single-layer network topology, and it is difficult to automatically discover and clearly display a core network topology when a multi-layer complex network is processed, and the layout efficiency is low and the effect is poor.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of information technology, in particular to a network topology determination method and device and a nonvolatile storage medium. BACKGROUND

[0002] With the rapid development of communication networks, increasing business application scenarios have put forward higher requirements for network construction and maintenance. Network devices connected to the core network are of more and more types, network scale is more and more large, and routing topology is more and more complex. Most of the traditional network topologies are fixed and presented by configuration. However, modern communication networks are heterogeneous and dynamically changing. How to enable network maintenance personnel to quickly master network conditions, intuitively judge and locate network faults, and improve the professionalism, accuracy and real-time performance of network topology is a hotspot and difficulty in core network operation and maintenance at present. Not only in the field of communication, in recent years, with the rapid development of network and electronic communication, complex network research has become a frontier field of science and engineering, and many important achievements have been made. However, in the related art, most of the research in the field of complex networks still focuses on single-layer networks (or single networks) and ignores the existence of multiple network interactions in actual complex systems, such as various business networks including different network devices and logical relationships, and transportation networks of different transportation tools. The relationship between individuals in the network is becoming more and more complex, and if only single-layer relationship or each layer relationship is considered in isolation, the requirements of actual complex system research cannot be met. The related art focuses on the automatic layout of single-layer network topology. When dealing with multi-layer complex networks, it is difficult to automatically discover and clearly display the core network topology structure, and there are problems of low layout efficiency, poor effect and unclear node association.

[0003] For the above problems, no effective solution has been proposed so far. SUMMARY

[0004] The embodiments of the present application provide a network topology determination method and device and a nonvolatile storage medium, to at least solve the technical problems that the related art focuses on the automatic layout of single-layer network topology, and when dealing with multi-layer complex networks, it is difficult to automatically discover and clearly display the core network topology structure, and there are problems of low layout efficiency and poor effect.

[0005] According to an aspect of some embodiments of the present application, a method for determining a network topology is provided. The method comprises: obtaining call detail record data of a core network, wherein the call detail record data comprises at least network type, network element type, protocol type, source network element IP address, and destination network element IP address of a service route; determining valid service route information according to the call detail record data, wherein the valid service route is a service route that has a number of specified sub-periods with service route data greater than a preset threshold in a continuous preset statistical period, and the specified sub-period is a sub-period with service route data; obtaining a first-level network topology based on the valid service route information and a preset topology relationship; and expanding the first-level network topology into a multi-level network topology according to a service logic relationship, wherein the service logic relationship is used to indicate at least a service association relationship of network devices under each first-level network topology node in the first-level network topology.

[0006] In some embodiments of the present application, the multi-level network topology comprises at least a first-level network topology and a second-level network topology. The first-level network topology is a network topology obtained by topologically sorting network element types of service routes in the valid service route information according to network types. The second-level network topology is a network topology obtained by topologically sorting network devices under network element types in each network type in the first-level network topology according to a service logic relationship.

[0007] In some embodiments of the present application, obtaining the first-level network topology based on the valid service route information and the preset topology relationship comprises: obtaining network types and network element types of all service routes in the valid service route information; and topologically sorting the network element types according to a preset topology relationship to obtain the first-level network topology, wherein the preset topology relationship is a connection rule for topologically sorting the network element types according to the network types.

[0008] In some embodiments of the present application, expanding the first-level network topology into the multi-level network topology according to the service logic relationship comprises: expanding each first-level network topology node in the first-level network topology into a second-level network topology by the following manner, wherein one first-level network topology node corresponds to one network element type: determining network devices under the network element type; and topologically sorting the network devices according to a service logic relationship to obtain a second-level network topology of the first-level network topology node, wherein each second-level network topology node in the second-level network topology corresponds to one network device.

[0009] In some embodiments of the present application, the first-level network topology is expanded into a second-level network topology according to the service logic relationship, including: when the service logic relationship indicates that there is no service logic relationship between the areas of different levels between the network devices, the network devices are topologically sorted according to the preset service priority corresponding to the network devices, to obtain the second-level network topology of the first-level network topology nodes.

[0010] In some embodiments of the present application, the first-level network topology is expanded into a second-level network topology according to the service logic relationship, including: when the service logic relationship indicates that there is no service logic relationship between the areas of different levels between the network devices, the network devices are topologically sorted according to the preset service priority corresponding to the network devices, to obtain the second-level network topology of the first-level network topology nodes.

[0011] In some embodiments of the present application, the method further includes: in the case that the network quality index of the link between any two first-level network topology nodes in the first-level network topology is greater than a first preset threshold, determining the first-level network topology nodes at both ends of the link as first-level target network topology nodes; determining the target second-level network topology corresponding to the first-level target network topology nodes, and determining the target network devices in the target second-level network topology based on the network quality index; generating alarm information corresponding to the target network devices, and displaying the alarm information in a visual form at the second-level target network topology nodes corresponding to the target network devices and at the first-level target network topology nodes.

[0012] In some embodiments of the present application, the method further includes: obtaining, according to a time period, a predicted value of predicting a plurality of quality indicators of all links in the first-level network topology based on historical quality indicators within a preset time; determining a deviation value between the predicted value corresponding to each quality indicator and the real quality indicator value; determining the product of the deviation value corresponding to each quality and a preset weight as a severity component; determining the sum of the severity components of all quality indicators as the severity, and the severity greater than a second preset threshold is a first-level severe alarm, and the severity greater than a third preset threshold is a second-level severe alarm, wherein the second preset threshold is less than the third preset threshold; when it is identified that the severity of a second time period is higher than the severity of a first time period, the severity of the second time period is pushed to the user terminal, wherein the first time period is a time period before the second time period.

[0013] According to a further aspect of the embodiments of the present application, a network topology determination apparatus is also provided, comprising: an obtaining module configured to obtain call detail record data of a core network, wherein the call detail record data comprises at least network type, network element type, protocol type, source network element IP address, and destination network element IP address of a service route; a first determination module configured to determine valid service route information according to the call detail record data, wherein the valid service route is a service route in which a number of specified sub-periods with service route data in a continuous preset statistical period is greater than a preset threshold, and the specified sub-period is a sub-period with service route data; a second determination module configured to obtain a first-level network topology based on the valid service route information and a preset topology relationship; and an expansion module configured to expand the first-level network topology into a multi-level network topology according to service logic relationships layer by layer, wherein the service logic relationships are used at least to indicate service association relationships of network devices under each first-level network topology node in the first-level network topology.

[0014] According to a further aspect of the embodiments of the present application, a non-volatile storage medium is also provided, which stores a program, wherein the program, when executed, controls a device in which the non-volatile storage medium is located to perform the network topology determination method described above.

[0015] According to a further aspect of the embodiments of the present application, an electronic device is also provided, comprising a memory and a processor, wherein the processor is configured to execute a program stored in the memory, and the program, when executed, performs the network topology determination method described above.

[0016] According to a further aspect of the embodiments of the present application, a computer program product is also provided, comprising computer instructions, which, when executed by a processor, implement the network topology determination method described above.

[0017] In the embodiment of the present application, the call detail record data of the core network is acquired, wherein the call detail record data at least includes network type of service route, network element type, protocol type, source network element IP address, and destination network element IP address; valid service route information is determined according to the call detail record data, wherein the valid service route is that the number of specified sub-periods with service route data in a continuous preset statistical period is greater than a preset threshold, and the specified sub-period is a sub-period with service route data; a first network topology structure is obtained based on the valid service route information and a preset topology relationship; and the first network topology structure is expanded into a multi-layer network topology structure according to service logic relationship, wherein the service logic relationship is at least used to indicate the service association relationship of network devices under each first network topology node in the first network topology structure. By determining the valid service route information, the first network topology structure is obtained based on the valid service route information and the preset topology relationship; and the first network topology structure is expanded into the multi-layer network topology structure according to the service logic relationship, so as to achieve the purpose of generating network topology structures of different levels according to different layout methods when processing a multi-layer complex network, and further solve the technical problems of related technologies that focus on automatic layout of single-layer network topology, and are difficult to automatically discover and clearly display the core network topology structure when processing a multi-layer complex network, and have low layout efficiency and poor effect. BRIEF DESCRIPTION OF DRAWINGS

[0018] The drawings described herein are used to provide further understanding of the present application, and form a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application, and do not constitute improper limitations on the present application. In the drawings:

[0019] Figure 1 FIG. 1 is a hardware structure block diagram of a computer terminal for implementing a network topology structure determination method according to an embodiment of the present application;

[0020] Figure 2 FIG. 2 is a flowchart of a network topology structure determination method according to an embodiment of the present application;

[0021] Figure 3 FIG. 3 is a CDR data acquisition flowchart according to an embodiment of the present application;

[0022] Figure 4 FIG. 4 is a flowchart of acquiring network quality prediction indexes according to an embodiment of the present application;

[0023] Figure 5 FIG. 5 is a flowchart of determining deviation according to an embodiment of the present application;

[0024] Figure 6 FIG. 6 is a flowchart of confirming route alarm severity according to an embodiment of the present application;

[0025] Figure 7 is a system module schematic diagram provided by an embodiment of the application.

[0026] Figure 8 is a structural schematic diagram of a network topology determination device according to an embodiment of the application. DETAILED DESCRIPTION

[0027] In order for those skilled in the art to better understand the scheme of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0028] The information collected by the embodiments of the present application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of related data all comply with relevant laws, regulations and standards in the relevant region, necessary security measures are taken, public order and good customs are not violated, and appropriate operation portals are provided for the user to choose authorization or refuse automatic decision results; if the user chooses to refuse, the expert decision process is entered.

[0029] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not have to be used to describe a particular order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] In order to better understand the embodiments of the present application, the technical terms involved in the embodiments of the present application are explained as follows:

[0031] Core network (Core Network): The core network is located in the mobile network subsystem, and the functions of the core network mainly include providing user connection, managing users and completing the bearing of services, and providing an interface to external networks as a bearing network.

[0032] In the related art, most researches in the field of complex networks still focus on single-layer networks (or single networks) and ignore the existence of multiple network interactions in actual complex systems, such as various business networks including different network devices and logical relationships, and traffic networks of different transportation tools. Therefore, the related art focuses on the automatic layout of the topology of a single-layer network. When processing a multi-layer complex network, it is difficult to automatically discover and clearly display the core network topology structure, and there are problems of low layout efficiency and poor effect. In order to solve this problem, the related solutions are provided in the embodiments of the present application, which are described in detail below.

[0033] According to the embodiments of the present application, an embodiment of a method for determining a network topology structure is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0034] The method embodiments provided in the embodiments of the present application can be executed in a computer terminal or similar computing device. Figure 1 A hardware structure block diagram of a computer terminal for implementing the method for determining a network topology structure is shown. As shown in Figure 1 , the computer terminal 10 can include one or more (in the figure, 102a, 102b, …, 102n are shown) processors 102 (the processor 102 can include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission module 106 for communication functions. In addition, it can also include a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which can be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. Those skilled in the art can understand that Figure 1 The structure shown is only schematic, and does not limit the structure of the above-mentioned electronic device. For example, the computer terminal 10 can also include more or fewer components than those shown in Figure 1 , or have a different configuration from Figure 1 .

[0035] It should be noted that the one or more processors 102 and / or other data processing circuitry described above can be generally referred to herein as "data processing circuitry". The data processing circuitry can be embodied in whole or in part as software, hardware, firmware, or any combination thereof. In addition, the data processing circuitry can be a single standalone processing module or incorporated in whole or in part within any of the other elements of the computer terminal 10. As referred to in the embodiments herein, the data processing circuitry functions as a processor to control, for example, the selection of the variable resistance terminal path in connection with the interface.

[0036] The memory 104 can be used to store software programs of application software and modules, such as program instructions / data storage means corresponding to the method for determining network topology in the embodiments herein, and the processor 102 can execute various functional applications and data processing by running the software programs and modules stored in the memory 104, i.e. implement the method for determining network topology described above. The memory 104 can include a high-speed random access memory, and can also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include a memory remotely arranged with respect to the processor 102, which can be connected to the computer terminal 10 through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0037] The transmission device 106 is used to receive or send data via a network. Specific examples of the network can include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (NIC) which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module which is used to communicate with the Internet in a wireless manner.

[0038] The display can be, for example, a touch screen type liquid crystal display (LCD) which can enable a user to interact with the user interface of the computer terminal 10.

[0039] Under the above operating environment, the embodiments herein provide a method for determining network topology. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0040] As Figure 2As shown, a flowchart of a method for determining a network topology structure is provided according to an embodiment of the present application, which includes the following steps:

[0041] In step S202, call detail record data of the core network is acquired, wherein the call detail record data at least includes network type of service routing, network element type, protocol type, source network element IP address, and destination network element IP address.

[0042] The following is a specific embodiment:

[0043] Real-time subscription is performed to acquire full-network (entire core network) Session Initiation Protocol (SIP) message records from a signaling sharing platform. The SIP message records are original signaling data exchanged between network element devices in a communication process. The full-network SIP messages refer to a collection of SIP messages exchanged between network element devices using SIP protocol for service communication. The SIP messages include session establishment request (INVITE) (a request for initiating a new session), session modification request (ReINVITE) (a request for modifying session parameters in an established session, including but not limited to media type, codec, address information, etc.), and other control messages. Each SIP message carries specific session information, such as session identifier (Call-ID), source network element IP address, destination network element IP address, and session parameters. Based on the SIP messages, all service routings in the core network can be determined. Specifically, the direction of routing is obtained through the source and destination IP addresses of the first INVITE message of the SIP protocol. If the INVITE message is sent from IP1 to IP2, it indicates that there is a service routing IP1->IP2. The SIP network element is effective when initiating a call, and the message may not pass through the SIP network element after the call is established. For example, a call process is IP1->IP2->IP3, but after the call is established, the ReINVITE message in the call process is not sent through IP2, but is directly sent from IP1 to IP3. Although there is a direct message, it does not belong to a service routing. The session identifier is used to associate these messages, and the routing information IP1->IP3 is excluded, and only the service routings IP1->IP2 and IP2->IP3 are retained.

[0044] In the network operation and fault diagnosis of the core network, the whole network signaling call detail record (CDR) data is indispensable, which provides detailed records of each part of the network (including different types of network elements and links) in the communication process, and is crucial for understanding network behavior, optimizing network performance, detecting abnormal conditions, and locating faults. The signaling sharing platform is a system that centrally processes and stores network signaling data. It receives whole network signaling call detail record (CDR) data of all service routes from multiple signaling monitoring points in the core network. The whole network signaling call detail record (CDR) data is obtained by analyzing and processing SIP message records. Specifically, the real-time CDR data is sent to the southbound interface service of the signaling sharing platform through a socket interface, which provides a mechanism for inter-process communication, enabling processes on different computers to communicate with each other over a network. The southbound interface service of the platform is responsible for receiving data from network monitoring devices (such as signaling monitoring systems). Then, the shared interface of the sharing platform sends real-time CDR data streams to subscribers, meaning that subscribers can immediately obtain the latest signaling CDR data. This minimizes the calculation field and reduces the storage and computing resource overhead, saving intermediate process time. The whole network signaling CDR data refers to the call detail record data collected from all service routes in the entire core network. CDR data includes detailed information such as network type (e.g., IP Multimedia Subsystem (IMS) for providing multimedia services, Voice Over LTE (Volte) for providing high-quality voice call services, Circuit-Switched Network (C-network) for traditional telephone network type, fixed bandwidth allocation during communication), network element type, protocol type, source network element IP address, and destination network element IP address. These information is crucial for network management and troubleshooting.

[0045] As shown in Figure 3 , it is a flowchart of CDR data acquisition according to an embodiment of the present application, which shows the above process. The signaling sharing platform is used for control service, management of southbound interface and shared interface. First, the southbound interface of the signaling sharing platform receives real-time pushed CDR data from the signaling network (such as the C-network collection layer, fixed IMS collection layer, and Volte network collection layer in the figure), and then sends it to the subscriber through the shared interface, realizing real-time subscription reception.

[0046] In step S204, valid service routing information is determined according to the call detail record data, wherein the valid service routing is that the number of specified sub-periods with service routing data in a continuous preset statistical period is greater than a preset threshold, and the specified sub-period is a sub-period with service routing data.

[0047] The following is a specific embodiment:

[0048] The collected CDR data is parsed to extract key fields such as network type, network element type, protocol type, source network element IP address, destination network element IP address, and timestamp. Invalid or redundant records are removed, such as excluding test, debugging, or error session records to ensure the accuracy of service routing information. To confirm the validity of the routing, the continuity and stability of the service routing data in a preset statistical period need to be evaluated. Valid service routing is that the number of specified sub-periods with service routing data in a continuous preset statistical period is greater than a preset threshold, and the specified sub-period is a sub-period with service routing data. The time is divided into finer-grained statistical periods, for example, 1 minute (i.e., the above-mentioned sub-period) as a unit, and a time window is created for data aggregation and statistics. In each time window, the number of service routings in that period is counted. For each service routing, check whether there is x (e.g., x takes 60) 1-minute periods (y (e.g., y takes 60) 1-minute periods are the above-mentioned continuous preset statistical period) with service data for at least 12 hours (i.e., the above-mentioned preset threshold) in each of the continuous n days (e.g., n takes 14 days). This is to confirm the continuity and stability of the routing to ensure its reliability as valid service routing. The stable service data flow with x (e.g., x takes 60) 1-minute periods in at least 12 hours of each of the continuous n days (e.g., 14 days) is taken as valid service routing information.

[0049] To improve the accuracy of identifying valid service routes, for historical valid service route information, extract its key attributes as features, including network type, network element type, protocol type, source network element IP address, destination network element IP address, and the number of services appearing within a time period, etc. Use machine learning algorithms (such as logistic regression, decision tree, random forest or deep learning model) to train these features to identify and predict the pattern of valid service routes. Evaluate the trained model using cross-validation, precision, recall and other indicators to test its performance. According to the evaluation results, adjust the model parameters or feature selection to improve the accuracy and generalization ability of the model. Apply the trained model to all collected CDR data, and according to the model prediction results, mark the service routes identified by the model as meeting the continuity and stability requirements as "valid" as valid service route information. Store the information confirmed as valid service route in the database or data structure, and set up a mechanism to update these information regularly to reflect the network dynamic changes, such as the addition of new devices or the retirement of old devices.

[0050] Step S206, based on the valid service route information and the preset topological relationship, the first-level network topology structure is obtained.

[0051] In the technical solution provided in step S206, there are many implementation methods for obtaining the first-level network topology structure based on the valid service route information and the preset topological relationship, for example: obtaining the network type and network element type of all service routes in the valid service route information; based on the preset topological relationship, the network element type is topologically sorted to obtain the first-level network topology structure, wherein the preset topological relationship is the connection rule of the network element type when topologically sorted according to the network type.

[0052] In the technical solution provided in step S206, the preset topological relationship refers to the connection rule between network element types set according to network design and operation and maintenance experience before building the network topology structure. These rules usually reflect the hierarchy and logical relationship of the network architecture. For example, the relative position and function of each network element type in the network. The preset topological relationship helps to classify and sort network element types when analyzing valid service route information, ensuring that the generated topology map not only reflects the actual network connection, but also follows the logical architecture of the network. After determining all network element types and their connection relationships, use topology layout algorithms (such as tree, ring or force-directed layout algorithms) to generate the first-level network topology structure. These algorithms will automatically arrange and layout network elements according to the connection relationship between network elements and the preset network type topological rules to form the first-level network topology structure. The first-level topology structure is the top view of the network topology map, which shows the highest level of connection between different network types and the basic relationship between network element types.

[0053] Step S208, the first-level network topology is expanded into a multi-layer network topology according to the service logic relationship, wherein the service logic relationship is used to indicate at least the service association relationship of the network devices under each first-level network topology node in the first-level network topology.

[0054] In the technical solution provided in step S208, there are various implementation manners for expanding the first-level network topology into a multi-layer network topology according to the service logic relationship, for example: each first-level network topology node in the first-level network topology is expanded into a second-level network topology by the following manner, wherein one first-level network topology node corresponds to one type of network element: determining the network devices under the network element type; and performing topology sorting on the network devices based on the service logic relationship to obtain the second-level network topology of the first-level network topology node, wherein each second-level network topology node in the second-level network topology corresponds to one network device.

[0055] There are various implementation manners for expanding the first-level network topology into a second-level network topology according to the service logic relationship, for example: when the service logic relationship indicates that there are different levels of areas between the network devices, the topology is sorted in the form of a map according to the positions of the areas where the network devices are located to obtain the second-level network topology of the first-level network topology node, wherein the service logic relationship between the areas of different levels indicates that there are different levels of area differences between the deployment positions of the network devices that are associated in service. When the service logic relationship indicates that there are no different levels of areas between the network devices, the topology is sorted according to the preset service priority corresponding to the network devices to obtain the second-level network topology of the first-level network topology node.

[0056] The following is a specific embodiment:

[0057] The service logic relationship information at least includes protocol type, service range, geographical position, service processing capacity, etc., and the geographical position is used to indicate whether there are different levels of areas between the network devices in service. The service logic relationship between the areas of different levels specifically indicates that there are different levels of area differences between the deployment positions of the network devices that are associated in service, and the different levels of area differences refer to different geographical positions, such as provincial and municipal differences, wherein the network devices are located in different provinces and cities, and the service routing and traffic flow direction are intuitively presented.

[0058] The first-level network topology is expanded into a multi-level network topology according to the service logic relationship, and at most three-level topology structure. First, each first-level network topology node (corresponding to a type of network element) in the first-level network topology is expanded into a second-level network topology in the following manner: when the service logic relationship indicates that there is a service logic relationship between different levels of areas between network devices, the network devices are topologically sorted according to the positions of the network devices in the form of a map to obtain a second-level network topology of the first-level network topology node. The positions of the second-level network topology nodes are determined by the service logic relationship, and the topological connections between the second-level network topology nodes are determined by the source network element IP address and the destination network element IP address in the service route CDR data corresponding to the service. A topology layout algorithm (such as a tree, ring, or force-directed layout algorithm) is used to generate the second-level network topology. For example, a tree structure layout is used to display a network topology with a hierarchical structure, and a force-directed layout is used for network topology nodes without obvious hierarchical relationships to reduce intersections and overlaps. When the service logic relationship indicates that there is no service logic relationship between different levels of areas between network devices, the network devices are topologically sorted according to the preset service priority corresponding to the network devices to obtain a second-level network topology of the first-level network topology node. The preset service priority is a priority of all services and a priority of all network devices corresponding to each service that is set in advance. A topology layout algorithm (such as a tree, ring, or force-directed layout algorithm) is used to generate the second-level network topology. For such a second-level network topology, the network devices can be further topologically sorted according to the positions of the network devices in the form of a map to obtain a third-level network topology of the second-level network topology node. A third-level network topology node indicates the deployment position of the corresponding network device.

[0059] The network devices corresponding to the network topology nodes with problems in the topology structure can also be alarmed, for example, in the following manner: in the case that the network quality indicator of the link between any two first-level network topology nodes in the first-level network topology is greater than a first preset threshold, the first-level network topology nodes at both ends of the link are determined as first target network topology nodes; a target second-level network topology corresponding to the first target network topology nodes is determined, and target network devices in the target second-level network topology are determined based on the network quality indicator; alarm information corresponding to the target network devices is generated, and is displayed in a visual form at the second-level target network topology nodes corresponding to the target network devices and at the first target network topology nodes.

[0060] The following are specific embodiments:

[0061] The network quality indicators (e.g., call times, network connection times, network connection rates, response times, response rates, error times, etc.) of each link (i.e., a topological connection between network topology nodes in a network topology structure) are obtained from the network quality indicator prediction module. If the network quality indicator of the link between any two primary network topology nodes in the primary network topology structure is greater than a first preset threshold (the first threshold is a constant set according to service requirements and historical data statistics, and is used to determine whether the link is in an abnormal state), the primary network topology nodes at both ends of the link are taken as primary target network topology nodes, indicating that the link between these nodes needs to be further paid attention to and checked. The corresponding secondary network topology structure is automatically expanded, and the target secondary network topology structure corresponding to the primary target network topology nodes is determined. In the secondary network topology structure, matching and association are performed, the target network device in the target secondary network topology structure is matched based on the source network element IP address and the destination network element IP address of the abnormal network indicator in the network quality indicator, the alarm information corresponding to the target network device is generated, and the alarm information is displayed in a visual form at the secondary target network topology node corresponding to the target network device and at the primary target network topology node. The alarm information should include detailed information of the network device, specific values of the abnormal indicators, time of exceeding the threshold, severity assessment, etc. The alarm information is not only visually displayed at the secondary network topology node corresponding to the target network device to help network maintenance personnel intuitively locate the problem device and the link, but also displayed at the primary target network topology node to provide a macro-to-micro fault alarm view. In addition, the alarm information can be highlighted on the topology structure through color coding, flashing effect, pop-up window, etc.

[0062] In order to better understand the service routing and service flow direction of the service, the network quality indicator prediction module can be used to monitor the key routes, wherein the key routes are the primary network topology nodes in all primary network topology structures. The average value of the historical network quality indicators in a preset time is used as the prediction of the current period, and the period is taken as a period of 1 minute. The historical network quality indicators of the same period in the preset time are obtained and averaged to obtain the network quality prediction indicators, as shown in Figure 4 The prediction mode is divided into weekdays, weekends and holidays. For weekdays, the historical network quality indicators (e.g., call times, network connection times, network connection rates, response times, response rates, error times, etc.) of the same period in a preset time are obtained, and the average value of the historical network quality indicators of all periods is obtained. As a network quality prediction index, for example, as shown in the figure, the quality prediction index of the period indicated in the figure of the current day is averaged from the historical network quality indexes of the same period of time of multiple historical working days including the day before yesterday, the day before the day before yesterday, and yesterday. For a holiday, the same holiday (Saturday / Sunday) same period data is used for prediction, that is, when the current day is Sunday, the historical network quality indexes of the same period of time of multiple Sundays within a preset time (for example, 3 months) are obtained and averaged. For a holiday, the same holiday (Saturday / Sunday) same period data is used for prediction, that is, when the current day is a holiday, the historical network quality indexes of the same period of time of multiple Saturdays and holidays within a preset time (for example, 3 months) are obtained and averaged. If there is a period of missing data, "0" will be filled in.

[0063] In order to verify the accuracy of the network quality prediction index, the predicted value (i.e. the value of each index in the network quality prediction index) and the true value (the value of each index in the network quality index actually obtained after the prediction time arrives) of each index in the network quality prediction index are compared in each period, the percentage difference between the indexes is calculated, and the deviation is obtained. The index values of different data levels are mapped to the same data range, and the deviation is used to realize more intelligent abnormal judgment. The deviation is obtained by the following formula: the deviation of each index in the network quality prediction index = Abs((true value-predicted value) / predicted value) x 100. As shown in Figure 5 The flow chart for determining the deviation provided by the embodiment of the present application is shown in the figure. As shown in the figure, in the case that the true value (i.e. the true value) of an index is 80 and the predicted value (i.e. the predicted value) is 100, the deviation obtained by the above formula is 20%; in the case that the true value (i.e. the true value) of an index is 800 and the predicted value (i.e. the predicted value) is 1000, the deviation obtained by the above formula is 20%. When the deviation is too large, the alarm service module will generate an alarm for the prediction result, and the most serious route alarm of each period will be selected for pushing. Specifically: the deviation of each index in the network quality index is determined separately, then normalized to 0-1 using the S-type function (sigmoid function for limiting the output result to 0-1), multiplied by the preset index weight (each index corresponds to a preset weight) and the corresponding index, then the index multiplied by the preset index weight is added to obtain the severity of the route alarm. As shown in Figure 6As shown, for indicators 1, 2 and 3, deviations 1, 2 and 3 are obtained based on a deviation formula, and after normalization, the deviations are multiplied by weights 1, 2 and 3 respectively, and finally added to obtain the severity (i.e. the above-mentioned route alarm severity, for example, divided into three levels of low, medium and high, the severity greater than the first alarm value is low, greater than the second alarm value is medium, and greater than the third alarm value is high, the first alarm value, the second alarm value and the third alarm value are pre-set constants gradually increasing). The route alarm severity is generated every period, and the current most serious alarm is obtained and pushed to the network management system through an interface, that is, the current most serious route alarm severity is inconsistent with the route alarm severity pushed last time, so as to push, realize alarm deduplication filtering and improve alarm effectiveness.

[0064] Through the above steps of analyzing the multi-layer complex network topology data, the node layer filtering is realized, the mixed layout of the multi-layer complex network topology is realized, the layer display is realized, and the prediction and alarm are provided, so that the network fault is more timely, intelligently and accurately identified, and the intelligent operation and maintenance level is further improved. The related art focuses on the automatic layout of single-layer network topology, and when processing multi-layer complex network, it is difficult to automatically discover and clearly display the core network topology structure, and there is a problem of low layout efficiency, poor effect and unclear node association.

[0065] Figure 7 The system module schematic diagram is provided according to the embodiment of the application, and is used to display each module of the system for realizing the above-mentioned embodiments of the application, including a signaling subscription module, a route learning module, a network quality index prediction module and an alarm service module. The signaling subscription module is used to change the traditional signaling bill file data providing mode into real-time streaming data service, which can improve timeliness and save processing resources, and the specific implementation is as follows Figure 3The route learning module is configured to obtain effective service routing data between network elements in the communication network, and form the basis of the network topology by learning and accumulation, that is, the machine learning algorithm (such as logistic regression, decision tree, random forest or deep learning model) is used to train these features to identify and predict the mode of effective service routing. The trained model is evaluated, and the performance is tested by using cross-validation, precision, recall rate and other indicators. According to the evaluation result, the model parameters or feature selection are adjusted to improve the accuracy and generalization ability of the model. The trained model is applied to all collected CDR data, and according to the model prediction result, the service routing identified by the model as meeting the continuity and stability requirements is marked as "effective" as the effective service routing information. The signaling network includes C network, VOLTE (Volte) network, IMS network (fixed network IMS), which is configured to provide CDR data, the network quality index prediction module is configured to obtain abnormal data with network quality index fluctuation deviation exceeding prediction, and perform monitoring on the key routing. The network quality difference digital topology is configured to display the generated multi-level network topology structure. The alarm service module is configured to obtain network quality difference index alarm data, and push the alarm through the interface to realize automatic operation and maintenance. The external interface is configured to receive the alarm pushed through the interface.

[0066] The embodiment of the present application also provides a structural schematic diagram of a network topology determination device, as shown in the figure, which comprises: Figure 8

[0067] The obtaining module 802 is configured to obtain call detail record data of the core network, wherein the call detail record data at least comprises network type, network element type, protocol type, source network element IP address and destination network element IP address of the service routing.

[0068] The first determination module 804 is configured to determine effective service routing information according to the call detail record data, wherein the effective service routing is that the number of specified sub-periods with service routing data in a continuous preset statistical period is greater than a preset threshold, and the specified sub-period is a sub-period with service routing data.

[0069] The second determination module 806 is configured to obtain a first-level network topology structure based on the effective service routing information and a preset topology relationship.

[0070] The expansion module 808 is configured to expand the first-level network topology structure into a multi-layer network topology structure layer by layer according to a service logic relationship, wherein the service logic relationship is at least used to indicate the service association relationship of the network devices under each first-level network topology node in the first-level network topology structure.

[0071] It should be noted that, Figure 8 The network topology determination device shown in the figure is configured to execute Figure 2 ​The determination method of the network topology of the illustrated network topology is thus Figure 2 The relevant explanations in the determination method of the network topology in the foregoing network topology determination method also apply to the network topology determination apparatus, which will not be described here again.

[0072] It should be noted that each module in the network topology determination apparatus described above can be a program module (for example, a program instruction set for implementing a certain specific function) or a hardware module. For the latter, it can be in the following form, but is not limited thereto: the form of each module is a processor, or the functions of each module are implemented by a processor.

[0073] The embodiment of the present application also provides a non-volatile storage medium, which comprises a stored program, wherein when the program is running, the non-volatile storage medium controls the device in which the non-volatile storage medium is located to execute the network topology determination method described above. For example, call detail record data of a core network is acquired, wherein the call detail record data at least comprises network types of service routes, network element types, protocol types, source network element IP addresses, and destination network element IP addresses; effective service route information is determined according to the call detail record data, wherein an effective service route is a service route in which the number of specified sub-periods in which service route data exists in a continuous preset statistical period is greater than a preset threshold, and the specified sub-period is a sub-period in which service route data exists; a first-level network topology is obtained based on the effective service route information and a preset topological relationship; and the first-level network topology is expanded into a multi-level network topology layer by layer according to a service logic relationship, wherein the service logic relationship is at least used to indicate a service association relationship of network devices under each first-level network topology node in the first-level network topology.

[0074] The embodiment of the present application also provides an electronic device, which comprises a processor, and the processor is used to run a program, wherein when the program is running, the network topology determination method described above is executed. For example, call detail record data of a core network is acquired, wherein the call detail record data at least comprises network types of service routes, network element types, protocol types, source network element IP addresses, and destination network element IP addresses; effective service route information is determined according to the call detail record data, wherein an effective service route is a service route in which the number of specified sub-periods in which service route data exists in a continuous preset statistical period is greater than a preset threshold, and the specified sub-period is a sub-period in which service route data exists; a first-level network topology is obtained based on the effective service route information and a preset topological relationship; and the first-level network topology is expanded into a multi-level network topology layer by layer according to a service logic relationship, wherein the service logic relationship is at least used to indicate a service association relationship of network devices under each first-level network topology node in the first-level network topology.

[0075] According to another aspect of the embodiments of the present application, a computer program product is also provided, which comprises a computer program, and the computer program, when executed by a processor, implements the above network topology determination method. For example, call detail record data of a core network is acquired, wherein the call detail record data at least comprises network types of service routing, network element types, protocol types, source network element IP addresses, and destination network element IP addresses; valid service routing information is determined according to the call detail record data, wherein the valid service routing is that a number of specified sub-periods in which service routing data exists in a continuous preset statistical period is greater than a preset threshold, and the specified sub-period is a sub-period in which service routing data exists; a first-level network topology is obtained based on the valid service routing information and a preset topology relationship; and the first-level network topology is expanded into a multi-level network topology layer by layer according to service logic relationships, wherein the service logic relationships are used at least to indicate service association relationships of network devices under each first-level network topology node in the first-level network topology.

[0076] In the above-described embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0077] In the several embodiments provided by the present application, it should be understood that the disclosed technology can be implemented in other ways. Of course, the embodiment described above is only illustrative, and for example, the division of units can be a logical function division, and actual implementation can be in another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, unit or module, and can be electrical or other forms.

[0078] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0079] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The above integrated unit can be realized in the form of hardware or in the form of software functional unit.

[0080] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the part that essentially contributes to the related art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present application. The aforementioned storage medium includes a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0081] The above only describes the preferred embodiments of the present application. It should be noted that, for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, which should also be considered as the protection scope of the present application.

Claims

1. A method of determining a network topology, characterized by, The method comprises: obtaining call detail record data of a core network, wherein the call detail record data comprises at least network type, network element type, protocol type, source network element IP address, and destination network element IP address of service routing; determining effective service routing information according to the call detail record data, wherein the effective service routing is a service routing data existing in a specified sub-period of a continuous preset statistical period and the number of the service routing data is greater than a preset threshold, and the specified sub-period is a sub-period in which service routing data exists; obtaining a first network topology structure based on the effective service routing information and a preset topology relationship; expanding the first network topology structure into a multi-layer network topology structure according to a service logic relationship, wherein the service logic relationship is used at least to indicate a service association relationship of network devices under each first network topology node in the first network topology structure; the obtaining of the first network topology structure based on the effective service routing information and the preset topology relationship comprises: obtaining network types and network element types of all service routings in the effective service routing information; topologically sorting the network element types based on the preset topology relationship to obtain the first network topology structure, wherein the preset topology relationship is a connection rule when the network element types are topologically sorted according to network types. the expanding of the first network topology structure into the multi-layer network topology structure according to the service logic relationship comprises: expanding each first network topology node in the first network topology structure into a second network topology structure by the following way, wherein one first network topology node corresponds to one type of network element types: determining network devices under the network element types; topologically sorting the network devices based on the service logic relationship to obtain the second network topology structure of the first network topology node, wherein each second network topology node in the second network topology structure corresponds to one network device.

2. The method of claim 1, wherein, The multi-layer network topology structure comprises at least the first network topology structure and the second network topology structure, the first network topology structure is a network topology structure obtained by topologically sorting network element types of service routings in the effective service routing information according to network types, and the second network topology structure is a network topology structure obtained by topologically sorting network devices under the network element types according to the service logic relationship for each network type in the first network topology structure.

3. The method of claim 1, wherein, the expanding of the first network topology structure into the second network topology structure according to the service logic relationship comprises: when the service logic relationship indicates that there are different levels of areas between the network devices, topologically sorting the network devices according to positions of areas in which the network devices are located in a form of a map to obtain the second network topology structure of the first network topology node, wherein the different levels of areas between the network devices indicate that there are different levels of area differences between deployment positions of network devices that are associated in service.

4. The method of claim 1, wherein, the expanding of the first network topology structure into the second network topology structure according to the service logic relationship comprises: When the service logic relationship indicates that there is no service logic relationship between different levels of areas between the network devices, a topology is sorted according to a preset service priority corresponding to the network device, and a secondary network topology structure of the primary network topology node is obtained.

5. The method of claim 1, wherein, The method further comprises: In a case where a network quality index of a link between any two primary network topology nodes in the primary network topology structure is greater than a first preset threshold, the primary network topology nodes at two ends of the link are determined as primary target network topology nodes; A target secondary network topology structure corresponding to the primary target topology nodes is determined, and target network devices in the target secondary network topology structure are determined based on the network quality index; Alarm information corresponding to the target network devices is generated, and is displayed in a visual form at the secondary target network topology nodes corresponding to the target network devices and at the primary target network topology nodes.

6. The method of claim 1, wherein, The method further comprises: A prediction value of a plurality of quality indexes of all links in the primary network topology structure is obtained based on a historical quality index in a preset time period according to a time period; A deviation value between the prediction value and an actual quality index value corresponding to each quality index is determined; and a product of the deviation value corresponding to each quality index and a preset weight is determined as a severity component; A sum of severity components of all quality indexes is determined as a severity, and the severity is a primary severity alarm when the severity is greater than a second preset threshold, and the severity is a secondary severity alarm when the severity is greater than a third preset threshold, wherein the second preset threshold is less than the third preset threshold; When it is identified that the severity of a second time period is higher than the severity of a first time period, the severity of the second time period is pushed to a user terminal, wherein the first time period is a previous time period of the second time period.

7. An apparatus for determining a network topology, characterized in that Comprise: An acquisition module is configured to acquire call detail record (CDR) data of a core network, wherein the CDR data comprises at least network types, network element types, protocol types, source network element IP addresses, and destination network element IP addresses of service routes; A first determination module is configured to determine valid service route information according to the CDR data, wherein the valid service route is a service route for which a number of specified sub-periods with service route data is greater than a preset threshold in a continuous preset statistical period, and the specified sub-period is a sub-period with service route data; A second determination module is configured to obtain a primary network topology structure based on the valid service route information and a preset topology relationship: acquire network types and network element types of all service routes in the valid service route information; and perform topology sorting on the network element types based on the preset topology relationship to obtain the primary network topology structure, wherein the preset topology relationship is a connection rule when the network element types are topologically sorted according to the network types. The expansion module is configured to expand the first-level network topology into a multi-level network topology according to a service logic relationship, wherein the service logic relationship is used to indicate at least a service association relationship of network devices under each first-level network topology node in the first-level network topology; each first-level network topology node in the first-level network topology is expanded into a second-level network topology by the following manner, wherein one first-level network topology node corresponds to one type of network element: determining network devices of the type of network element; and performing a topology sorting on the network devices based on the service logic relationship to obtain a second-level network topology of the first-level network topology node, wherein each second-level network topology node in the second-level network topology corresponds to one network device.

8. A non-volatile storage medium, comprising: The non-volatile storage medium stores a program, wherein the program controls a device in which the non-volatile storage medium is located to perform the network topology structure determination method in any one of claims 1 to 6 when the program is running.

9. An electronic device, comprising: The program is configured to perform the network topology structure determination method in any one of claims 1 to 6. The memory and the processor are configured to run a program stored in the memory, wherein the program performs the network topology structure determination method in any one of claims 1 to 6 when the program is running.

10. A computer program product comprising computer instructions, characterized in that, The computer instructions are executed by the processor to implement the network topology structure determination method in any one of claims 1 to 6.

Images