Electronic tag spatio-temporal topology generation method, device and system based on multi-dimensional features and storage medium

Abstract

The invention discloses an electronic tag spatio-temporal topology generation method, device and system based on multi-dimensional features and a storage medium, and belongs to the technical field of data identification. The method comprises the following steps: constructing a unified multi-dimensional feature set by extracting multi-dimensional feature information, such as identity information, space information and time information, written in an electronic tag; a system event timestamp is further combined, a spatio-temporal topological graph is constructed based on a graph theory and a spatio-temporal event association model, state tracking and life prediction of a communication port identified by a tag are realized by adopting an intelligent algorithm, and intelligent management is extended to a full life cycle of equipment. And the maintenance efficiency of optical fiber resources in a large-scale communication network and the cooperative capability among multiple operation and maintenance main bodies are improved.

Description

TECHNICAL FIELD

[0001] The application discloses a multi-dimensional feature-based electronic tag space-time topology generation method, device and system and a storage medium, relates to intelligent management of a fiber distribution system in optical fiber communication, and belongs to the technical field of data identification. BACKGROUND

[0002] In the optical fiber distribution system of a communication network, such as an optical fiber distribution frame of a data center and an intelligent optical distribution box for connecting backbone and distribution optical cables, the current management of distribution interfaces usually relies on electronic tags to identify optical fiber backboard interfaces and optical fiber joints. Operation and maintenance personnel need to manually input the interface numbers, connection relationships and other information stored by the electronic tags on site, and realize the query and management of node distribution information in the background management system.

[0003] With the continuous deepening of digital applications such as smart cities, industrial intelligence, smart medical treatment and the like, the global data volume is growing exponentially, and the number of optical interfaces and optical fiber joints on the optical fiber backboard also increases sharply. In a large data center, the number of optical fiber interfaces of a single rack can reach several thousand, forming a highly complex interface-joint-fiber interconnection system.

[0004] At present, the industry generally uses electronic tags to independently identify and manage optical fiber backboard interfaces and joints, relies on manual on-site collection and input of interface numbers, belonging devices, connection relationships and operation and maintenance records and the like to support basic information query at a single node level. However, this management mode based on individual identification lacks centralized and visualized management and control capabilities for a large number of electronic tags, and in actual operation and maintenance, the following outstanding problems are faced:

[0005] 1. Lack of centralized management and control capabilities: although each port has a plurality of characteristic attribute information recorded by an electronic tag, systematic integration is lacked, and the associated relationship between interfaces and joints, the overall connection state of a complete rack and even the entire data center and historical operation and maintenance events cannot be quickly obtained;

[0006] 2. Insufficient visual support: operation and maintenance personnel can only identify and locate interfaces through text information, and lack graphical presentation of physical interface positions, connection topologies and layouts in a data center room and rack structures, and in the process of fault locating such as link interruption positioning and equipment expansion, a large amount of time is consumed for manual on-site checking;

[0007] 3. Difficulty in cooperation and real-time operation and maintenance: in the scenario of dynamic changes in business load, manual allocation and scheduling of optical fiber interfaces and joints are still relied on, the connection relationship and operation and maintenance state in the electronic tag cannot be updated in real time, and the cooperation efficiency is low.

[0008] In view of the above problems, the present application aims to provide a multi-dimensional feature-based electronic tag space-time topology generation method, which is applied to a visualized and intelligent optical fiber operation and maintenance environment, thereby supporting high-reliability and high-efficiency key intelligent applications. SUMMARY

[0009] The present application aims to solve the technical problem of low operation and maintenance coordination efficiency of the optical fiber resource management mode based on individual electronic tag identification, and achieve the purpose of comprehensively, dynamically and intelligently managing and controlling the optical fiber backplane interface and joint of a large data center.

[0010] The present application adopts the following technical solutions to achieve the above-mentioned purposes:

[0011] A multi-dimensional feature-based electronic tag space-time topology generation method, comprising the following steps:

[0012] Collect multi-dimensional feature data of the electronic tag, extract multi-dimensional feature parameters of the electronic tag, and the multi-dimensional feature data includes identity dimension feature data, spatial dimension feature data and time dimension feature data, and the time dimension feature data includes event stamp;

[0013] Associate the extracted multi-dimensional feature parameters with the location information of the optical network physical facility, construct a spatial topology and generate a topology index;

[0014] Look up the topology index, fill the event stamp information in the time dimension feature data of the electronic tag into the spatial topology, establish a mapping relationship between the multi-dimensional feature parameters of the electronic tag and the nodes, construct a space-time topology through multi-dimensional space-time feature fusion and association, and the space-time topology is a node distribution graph with time and location as the vertical and horizontal axes.

[0015] As a further optimization scheme of the multi-dimensional feature-based electronic tag space-time topology generation method, the identity dimension feature data includes a device unique identifier and a serial number; the spatial dimension feature data includes a physical location and a logical grouping; and the time dimension feature data further includes a time stamp and a device life cycle state.

[0016] As a further optimization scheme of the multi-dimensional feature-based electronic tag space-time topology generation method, the physical location includes a building, a computer room, a cabinet number and a row / column number; and the logical grouping includes a device belonging business cluster and a network partition.

[0017] As a further optimization scheme of the electronic tag space-time topology generation method based on multi-dimensional features, the time stamp includes: device on-shelf time and warranty expiration time, the event stamp includes: change event and maintenance event, and the device life cycle state includes: in-service, idle and offline.

[0018] As a further optimization scheme of the electronic tag space-time topology generation method based on multi-dimensional features, the space-time topology is used to mine the association between the behavior rule and the state of the electronic tag identification device in the space-time dimension, monitor the state of the electronic tag identification device, predict the key indicators of the electronic tag identification device, and evaluate the life cycle state of the electronic tag identification device.

[0019] As a further optimization scheme of the electronic tag space-time topology generation method based on multi-dimensional features, according to the evaluation result of the life cycle state of the electronic tag identification device, the health state of the electronic tag identification device is visualized through node color.

[0020] An electronic tag space-time topology generation device based on multi-dimensional features, comprising: a multi-dimensional feature data acquisition module, a space topology generation module and a space-time topology generation module; the multi-dimensional feature data acquisition module is used for multi-dimensional feature data acquisition of the electronic tag, and extracts multi-dimensional feature parameters of the electronic tag; the multi-dimensional feature data includes: identity dimension feature data, space dimension feature data and time dimension feature data; the time dimension feature data includes time stamp, event stamp and life cycle state; the space topology generation module is used for associating the extracted multi-dimensional feature parameters with the location information of the optical network physical facility, constructing a space topology and generating a topology index; the space-time topology generation module is used for searching the topology index, filling the event stamp information in the time dimension feature data of the electronic tag into the space topology, establishing the mapping relationship between the multi-dimensional feature parameters of the electronic tag and the nodes, constructing the space-time topology through multi-dimensional space-time feature fusion and association, and the space-time topology is a node distribution diagram with time and location as the vertical and horizontal axes respectively.

[0021] As a further optimization scheme of the electronic tag space-time topology generation device based on multi-dimensional features, the space-time topology generation module mines the association between the behavior rule and the state of the electronic tag identification device in the space-time dimension based on the space-time topology, monitors the state of the electronic tag identification device, predicts the key indicators of the electronic tag identification device, and evaluates the life cycle state of the electronic tag identification device, and grades and warns potential risks based on the monitoring result and the prediction result.

[0022] A computer system comprises a memory and a processor, the memory stores a computer program running on the processor, and the processor executes the steps of the electronic tag space-time topology generation method described above when running the computer program.

[0023] A computer readable storage medium, having stored thereon a computer program, the computer program being executed by a processor to implement the steps of the above-mentioned electronic tag space-time topology generation method.

[0024] The present application has the following beneficial effects by adopting the above technical solution:

[0025] 1. Realize the visualization management and efficient collaborative operation of global fiber resources: through multi-dimensional information mapping and topology construction, a unified management and control view is formed, which greatly improves the efficiency of fault location and resource scheduling, and overcomes the dispersion and lag problem under the traditional manual management mode.

[0026] 2. Realize the intelligent transformation from passive fault handling to active fault prevention: by deeply integrating time dimension event information into topology relationship and using deep learning model for trend analysis, key risks such as port damage and life cycle state can be predicted and early warned.

[0027] 3. Form a data asset covering the whole life cycle of the equipment: through recording the multi-dimensional data of the equipment from installation, operation to offline retirement, complete and reliable data basis is provided for fiber asset fine management, capacity planning and operation decision. BRIEF DESCRIPTION OF DRAWINGS

[0028] Figure 1 The schematic diagram of the cabinet provided by an embodiment of the present application identifies the fiber backboard port information through electronic tags.

[0029] Figure 2 For Figure 1 The local enlarged view of part A in the figure.

[0030] Figure 3 The flowchart of the electronic tag space-time topology generation method.

[0031] Figure 4 The space topology diagram provided by an embodiment of the present application.

[0032] Figure 5 The space-time topology provided by an embodiment of the present application.

[0033] Figure 6 The event list of ID15 port provided by an embodiment of the present application. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme of the present application will be further described in detail below in combination with the drawings and embodiments of the present application. It should be understood that the specific embodiments described herein are part of the embodiments of the present application, but not all embodiments.

[0035] In one embodiment of the present application, there is provided a fiber tray as shown in Figure 1 The fiber backboard provides at least one row of ports, each port is attached with a sub-label, and the fiber backboard is also attached with group labels corresponding to each row of ports, and the local enlarged view of the device accessing the fiber backboard identified by the group label is as shown in Figure 2 .

[0036] First, the multi-dimensional characteristic quantity of the electronic label is defined, which specifically includes:

[0037] 1. Identity dimension characteristic quantity, used for uniquely identifying the object: including device unique identifier (User Identification, UID), serial number (Serial Number, SN), etc.

[0038] 2. Spatial dimension characteristic quantity, used for describing physical and logical positions: including physical position and logical grouping, the physical position includes: building, computer room, cabinet number, row / column number, and the logical grouping includes: belonging business cluster, network partition, and this dimension characteristic quantity is the basis for constructing the spatial connection relationship in the space-time topology graph;

[0039] 3. Time dimension characteristic quantity, used for recording time-related states and events: including time stamp, event stamp and life cycle state, the time stamp includes: device mounting time, warranty expiration time, the event stamp includes: change event, maintenance event, and the life cycle state includes: in service, idle, offline, etc., and this dimension characteristic quantity supports historical state tracing and future event prediction.

[0040] Then, the electronic label information is accurately mapped with the actual physical positions of the computer room rack and the fiber backboard, and the multi-dimensional space-time characteristic parameters are associated through an algorithm to generate a unified characteristic parameter set, which is used as the index basis of the electronic label space-time topology graph.

[0041] Finally, based on the above characteristic parameter set, the electronic label space-time topology graph is generated, and a set of intelligent, visual and full-life-cycle device operation and maintenance decision system is constructed to realize the comprehensive management and dynamic early warning of the fiber interface resources.

[0042] The flow of the space-time topology generation method based on multi-dimensional characteristics provided by the present application is as shown in Figure 3 , which includes the following steps. First, multi-dimensional characteristic data including identity dimension, spatial dimension and time dimension are collected, and multi-dimensional characteristic parameters are extracted. Then two processing branches are started.

[0043] Branch one: topology new or update, construction of spatial topology and index generation. First, multi-dimensional information mapping is performed, multi-dimensional characteristic parameter information extracted to the electronic tag is accurately associated with the location information of actual physical facilities such as machine room racks, fiber backplanes, etc., one-to-one correspondence between abstract device information and actual physical location is achieved, and the topology relationship structure between devices and between devices and physical space is constructed. On this basis, a topology index for fast retrieval and positioning is generated, supporting efficient query of specific device information, topology location and its associated relationship in the space-time topology graph. In an embodiment of the present application, the multi-dimensional characteristic parameter information of all sub-tags and group tags of racks A and B in a certain building is accurately associated with the physical location of the racks and fiber backplanes, and the topology index is generated Figure 4 The spatial topology graph is shown in FIG. 1.

[0044] Branch two: time dimension update and event filling, space-time characteristic state monitoring and prediction warning. By looking up the topology index, the event information of the device in the time dimension, such as fault records and maintenance times, is dynamically filled into the spatial topology graph. Subsequently, the mapping relationship between the multi-dimensional characteristic parameters of the electronic tag and the node is established, the multi-dimensional space-time characteristic fusion and association are performed based on the device identification in the identity dimension, the physical location in the space dimension, and the life cycle state change and event record in the time dimension, the node distribution graph with time and location as the vertical and horizontal axes is generated, the nodes on a certain time line can reproduce the spatial topology, the nodes on a certain location line can reproduce the time dimension characteristics of the current node, and the event list can be seen by clicking on each node. In an embodiment of the present application, a space-time topology is provided as shown in FIG. 2, reading any row of the topology can obtain the spatial topology graph corresponding to the time of the row, reading any column of the topology can obtain the time dimension characteristics of the electronic tag having a mapping relationship with the physical location corresponding to the column, for example, the port event list described by electronic tag 15 in the third row of rack B in a certain building is as shown in FIG. 3. Figure 5 Figure 6

[0045] Further mining of the behavior rules and state association of the device in the space-time dimension, monitoring of the device state, and prediction of key indicators such as the next failure occurrence time based on the historical damage times of the port and evaluation of the life cycle state, the color of the node can represent its health status, for example, the yellow node indicates that the device has a risk of failure, the red node indicates that the device has failed, and the green node indicates that the device is healthy. Based on the monitoring or prediction results, potential risks are graded and warned, and a space-time topology graph of multi-dimensional characteristic quantities is generated to assist operation and maintenance decision-making. The space-time topology of multi-dimensional characteristic quantities can provide information query, state monitoring, and historical data tracing functions of sub-tags; at the same time, a number of sub-tags managed by each group tag will appear after clicking, which also provides information query, state monitoring, life cycle management, etc. functions of these sub-tags. ​​

[0046] In one embodiment of the present application, a multi-dimensional feature-based electronic tag space-time topology generation device is provided, which comprises a multi-dimensional feature data acquisition module, a space topology generation module, and a space-time topology generation module.

[0047] The multi-dimensional feature data acquisition module is configured to acquire multi-dimensional feature data of the electronic tag, and extract multi-dimensional feature parameters of the electronic tag. The multi-dimensional feature data includes identity dimension feature data, space dimension feature data, and time dimension feature data. The time dimension feature data includes a timestamp, an event timestamp, and a life cycle state.

[0048] The space topology generation module is configured to associate the extracted multi-dimensional feature parameters with location information of an optical network physical facility, construct a space topology, and generate a topology index.

[0049] The space-time topology generation module is configured to search the topology index, fill event timestamp information in the time dimension feature data of the electronic tag into the space topology, establish a mapping relationship between the multi-dimensional feature parameters of the electronic tag and nodes, construct a space-time topology through multi-dimensional space-time feature fusion and association, and monitor the state of the electronic tag identification device, predict key indicators of the electronic tag identification device, and evaluate the life cycle state of the electronic tag identification device based on the space-time topology. The space-time topology is a node distribution graph with time and location as the vertical and horizontal axes, respectively. Based on the space-time topology, the behavior rules and the state association of the electronic tag identification device in the space-time dimension are mined, the state of the electronic tag identification device is monitored, the key indicators of the electronic tag identification device are predicted, and the life cycle state of the electronic tag identification device is evaluated. Based on the monitoring results and the prediction results, potential risks are graded and early warned.

[0050] In one embodiment of the present application, an intelligent, visual, and full-life-cycle device operation and maintenance decision system is provided, which comprises a memory and a processor. The memory stores a computer program that runs on the processor. When the processor runs the computer program, the steps of the above-mentioned electronic tag space-time topology generation method are executed.

[0051] In one embodiment of the present application, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned electronic tag space-time topology generation method are implemented.

[0052] The basic principles, main features, and advantages of the present application are shown and described above. Those skilled in the art should understand that the present application is not limited to the above specific embodiments, and the above specific embodiments and descriptions in the specification are only for further illustration of the principles and preparation effects of the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the present application. The scope of the present application is defined by the claims and their equivalents.

Claims

1. A method for generating a space-time topology of an electronic tag based on multi-dimensional features, characterized in that, The method comprises the following steps: Multi-dimensional feature data of the electronic tag is collected, and multi-dimensional feature parameters of the electronic tag are extracted, wherein the multi-dimensional feature data comprises identity dimension feature data, spatial dimension feature data, and time dimension feature data, and the time dimension feature data comprises an event timestamp; The extracted multi-dimensional feature parameters are associated with location information of optical network physical facilities, a spatial topology is constructed, and a topology index is generated; The topology index is searched, event timestamp information in the time dimension feature data of the electronic tag is filled into the spatial topology, a mapping relationship between the multi-dimensional feature parameters of the electronic tag and nodes is established, a space-time topology is constructed through multi-dimensional space-time feature fusion and association, and the space-time topology is a node distribution diagram with time and location as the vertical and horizontal axes respectively. 2.The method of claim 1, wherein, The identity dimension feature data comprises a device unique identifier and a serial number, the spatial dimension feature data comprises a physical location and a logical grouping, and the time dimension feature data further comprises a timestamp and a device life cycle state. 3.The method of claim 2, wherein, The physical location comprises a building, a machine room, a cabinet number, and row / column numbers, and the logical grouping comprises a device belonging business cluster and a network partition. 4.The method of claim 3, wherein, The timestamp comprises device mounting time and warranty expiration time, the event timestamp comprises a change event and a maintenance event, and the device life cycle state comprises in-service, idle, and offline. 5.The method of claim 1, wherein, Based on the space-time topology, an association between behavior rules and states of the electronic tag identification device in the space-time dimension is mined, a state of the electronic tag identification device is monitored, key indicators of the electronic tag identification device are predicted, and a life cycle state of the electronic tag identification device is evaluated. 6.The method of claim 5, wherein, According to an evaluation result of the life cycle state of the electronic tag identification device, a health state of the electronic tag identification device is visualized through node color.

7. A multi-dimensional feature-based electronic tag spatiotemporal topology generation device, characterized by, The method comprises: A multi-dimensional feature data collection module is configured to collect multi-dimensional feature data of the electronic tag, and extract multi-dimensional feature parameters of the electronic tag, wherein the multi-dimensional feature data comprises identity dimension feature data, spatial dimension feature data, and time dimension feature data, and the time dimension feature data comprises a timestamp, an event timestamp, and a life cycle state; A spatial topology generation module is configured to associate the extracted multi-dimensional feature parameters with location information of optical network physical facilities, construct a spatial topology, and generate a topology index; and A space-time topology generation module is configured to search the topology index, fill event timestamp information in the time dimension feature data of the electronic tag into the spatial topology, establish a mapping relationship between the multi-dimensional feature parameters of the electronic tag and nodes, construct a space-time topology through multi-dimensional space-time feature fusion and association, and the space-time topology is a node distribution diagram with time and location as the vertical and horizontal axes respectively. 8.The multi-dimensional feature based electronic tag spatio-temporal topology generation device of claim 7, wherein, The space-time topology generation module mines an association between behavior rules and states of the electronic tag identification device in the space-time dimension based on the space-time topology, monitors a state of the electronic tag identification device, predicts key indicators of the electronic tag identification device, evaluates a life cycle state of the electronic tag identification device, and grades and warns potential risks based on a monitoring result and a prediction result.

9. A computer system comprising a memory and a processor, said memory having stored thereon a computer program to run on the processor, characterised in that, The processor executes the steps of the electronic tag space-time topology generation method of claim 1 when running the computer program.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the electronic tag space-time topology generation method of claim 1.

Images