CN117714390A - Cloud platform early warning feedback method based on AI intelligent reasoning algorithm - Google Patents
Cloud platform early warning feedback method based on AI intelligent reasoning algorithm Download PDFInfo
- Publication number
- CN117714390A CN117714390A CN202311707017.6A CN202311707017A CN117714390A CN 117714390 A CN117714390 A CN 117714390A CN 202311707017 A CN202311707017 A CN 202311707017A CN 117714390 A CN117714390 A CN 117714390A
- Authority
- CN
- China
- Prior art keywords
- network switching
- switching node
- cloud platform
- data
- operation data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 18
- 230000000007 visual effect Effects 0.000 claims description 14
- 230000002354 daily effect Effects 0.000 claims description 6
- 230000003203 everyday effect Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 description 2
- 241000700605 Viruses Species 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
Abstract
The invention relates to a cloud platform early warning feedback method based on an AI intelligent reasoning algorithm, which comprises the steps of firstly, respectively marking each router in an IT network as a network switching node, and acquiring historical data of each network switching node through a cloud platform; the cloud platform predicts the operation data of each network switching node in a future preset period through AI intelligent reasoning based on the historical data of each network switching node; finally, the cloud platform judges the predicted operation data, if the predicted operation data has faults, the network switching node is judged to have faults, and then the network switching node, the historical data corresponding to the network switching node and the prediction result are transmitted to the display equipment for display; by the method, the network switching node with fault information is early warned in advance, so that the prediction precision is improved, and meanwhile, the loss caused by hardware faults is reduced.
Description
Technical Field
The invention relates to the technical field of network monitoring, in particular to a cloud platform early warning feedback method based on an AI intelligent reasoning algorithm.
Background
The router is a hardware device connected with two or more networks, plays a role of a gateway among the networks, is a special intelligent network device for reading addresses in each data packet and then deciding how to transmit, and is one of the most important network hardware in an IT network;
in an IT network, during working time, a router cannot perform communication work due to serious packet loss, virus propagation or other unknown reasons, and at the moment, downtime accidents are extremely easy to occur, and a subsequent series of associated problems, such as immeasurable loss to individuals or enterprises, are caused; when the router fails, a mode of checking logs step by step is generally adopted, or a network sniffing mode is adopted for checking in sequence, so that the probing process is extremely complicated and a large amount of time is consumed; therefore, at present, a method for early warning a router is urgently needed, so that the loss caused by the sudden loss of communication capability of the router is avoided.
Disclosure of Invention
The invention aims to provide a cloud platform early warning feedback method based on an AI intelligent reasoning algorithm, which is used for solving the problems in the background technology.
In order to achieve the above purpose, the invention provides a cloud platform early warning feedback method based on an AI intelligent reasoning algorithm, which comprises the following steps:
step one, each router in an IT network is respectively recorded as a network switching node;
step two, acquiring historical data of each network switching node through a cloud platform;
thirdly, the cloud platform predicts the operation data of each network switching node in a future preset period through AI intelligent reasoning based on the historical data of each network switching node;
and fourthly, the cloud platform judges the prediction result, and if the judgment result is that the network switching node fails, the network switching node, the historical data corresponding to the network switching node and the prediction result are transmitted to the display equipment for display.
Further, the operation data includes an operation log of the network switching node, traffic data, operation parameters, and load parameters.
Further, the AI intelligent reasoning is specifically as follows:
s1, recording historical data of each network switching node by using an hour as a unit by a cloud platform, and generating a plurality of first data sets X corresponding to each network switching node;
s2, classifying the first data set X corresponding to each network switching node by taking a day as a unit to generate a plurality of second data sets Y corresponding to each network switching node;
s3, the cloud platform generates a first visual chart X' based on the first data set X; generating a second visual chart Y' based on the second dataset Y;
s4, predicting operation data M 'of each hour of network switching nodes in the next M hours in units of hours based on the graph trend of the historical operation data in the first visual graph X'; predicting daily operation data N 'of the network switching node in the next N days in units of days based on graph trend of the historical operation data in the second visual graph Y';
s5, dividing the data M 'by taking the day as a unit, calculating the average value of the daily data M', and marking the average value as M 1 'A'; m of data N' and corresponding period 1 Two numerical values of' are taken as two end values, and a prediction range of future operation data taking a day as a unit is formed;
and S6, taking the average value of each prediction range to obtain the predicted operation data of each network switching node in the future every day, namely a predicted result.
Further, a numerical range of operation data of the network switching node in a normal working state is prestored in the cloud platform, and the judgment of the result of predicting the operation data is specifically as follows: the cloud platform compares the predicted result with the numerical range in the normal state, and if the numerical value of the predicted result is not in the numerical range in the normal state, the network switching node is judged to have a problem; otherwise, the network switching node is in a normal state.
Further, if the predicted operation data is within the numerical range in the normal state, but the predicted operation data is close to two end values of the numerical range, the network switching node is determined to be suspected of having a problem, and the network switching node suspected of having the problem is displayed on the display device.
Compared with the prior art, the invention has the remarkable advantages that:
1. acquiring historical operation data of each network switching node, classifying the historical operation data by taking preset time as a unit, deducing the operation data of each network switching node in a future preset period based on the historical operation data, comparing the predicted data with an operation numerical range of the network switching node in a normal state, and judging whether the network switching node has a fault or not, so that early warning is carried out on the network switching node with a problem in advance;
2. the data set is converted into the visual icons, so that the data display is more visual; meanwhile, by combining the first data set and the second data set in the invention, the prediction range of future running data taking the day as a unit is formed, and the average value of each prediction range is taken as a prediction result.
Drawings
Fig. 1 is a flow chart of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. All other embodiments, which are obtained by a person skilled in the art based on the described embodiments of the invention, fall within the scope of protection of the invention.
As shown in fig. 1, the invention provides a cloud platform early warning feedback method based on an AI intelligent reasoning algorithm, which comprises the following steps:
step one, each router in an IT network is respectively recorded as a network switching node;
step two, acquiring historical data of each network switching node through a cloud platform;
thirdly, the cloud platform predicts the operation data of each network switching node in a future preset period through AI intelligent reasoning based on the historical data of each network switching node;
and fourthly, the cloud platform judges the prediction result, and if the judgment result is that the network switching node fails, the network switching node, the historical data corresponding to the network switching node and the prediction result are transmitted to the display equipment for display.
In one embodiment, the operational data includes an operational log of the network switching node, traffic data, operational parameters, and load parameters.
In one embodiment, the AI intelligent reasoning is specifically as follows:
s1, recording historical data of each network switching node by using an hour as a unit by a cloud platform, and generating a plurality of first data sets X corresponding to each network switching node;
s2, classifying the first data set X corresponding to each network switching node by taking a day as a unit to generate a plurality of second data sets Y corresponding to each network switching node;
s3, the cloud platform generates a first visual chart X' based on the first data set X; generating a second visual chart Y' based on the second dataset Y;
s4, predicting operation data M 'of each hour of network switching nodes in the next M hours in units of hours based on the graph trend of the historical operation data in the first visual graph X'; predicting daily operation data N 'of the network switching node in the next N days in units of days based on graph trend of the historical operation data in the second visual graph Y';
s5, dividing the data M 'by taking the day as a unit, calculating the average value of the daily data M', and marking the average value as M 1 'A'; data N' is compared with the corresponding periodM 1 Two numerical values of' are taken as two end values, and a prediction range of future operation data taking a day as a unit is formed;
and S6, taking the average value of each prediction range to obtain the predicted operation data of each network switching node in the future every day, namely a predicted result.
In one embodiment, a numerical range of operation data of a network switching node in a normal working state is pre-stored in a cloud platform, and the judgment of the result of predicting the operation data is specifically: the cloud platform compares the predicted result with the numerical range in the normal state, and if the numerical value of the predicted result is not in the numerical range in the normal state, the network switching node is judged to have a problem; otherwise, the network switching node is in a normal state.
In one embodiment, if the predicted operation data is within the numerical range in the normal state, but the predicted operation data is close to two end values of the numerical range, the network switching node is determined to be suspected of having a problem, and the network switching node suspected of having the problem is displayed on the display device.
In one embodiment, a worker pays attention to the network switching node according to the network switching node displayed on the display device and the historical data and the prediction result related to the network switching node, and overhauls the network switching node with problems in practice.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (5)
1. A cloud platform early warning feedback method based on an AI intelligent reasoning algorithm is characterized by comprising the following steps:
step one, each router in an IT network is respectively recorded as a network switching node;
step two, acquiring historical data of each network switching node through a cloud platform;
thirdly, the cloud platform predicts the operation data of each network switching node in a future preset period through AI intelligent reasoning based on the historical data of each network switching node;
and fourthly, the cloud platform judges the prediction result, and if the judgment result is that the network switching node fails, the network switching node, the historical data corresponding to the network switching node and the prediction result are transmitted to the display equipment for display.
2. The cloud platform early warning feedback method based on the AI intelligent reasoning algorithm of claim 1, which is characterized in that: the operation data comprises operation log, flow data, operation parameters and load parameters of the network switching node.
3. The cloud platform early warning feedback method based on the AI intelligent reasoning algorithm as set forth in claim 2, wherein the method is characterized in that: the AI intelligent reasoning is specifically as follows:
s1, recording historical data of each network switching node by using an hour as a unit by a cloud platform, and generating a plurality of first data sets X corresponding to each network switching node;
s2, classifying the first data set X corresponding to each network switching node by taking a day as a unit to generate a plurality of second data sets Y corresponding to each network switching node;
s3, the cloud platform generates a first visual chart X' based on the first data set X; generating a second visual chart Y' based on the second dataset Y;
s4, predicting operation data M 'of each hour of network switching nodes in the next M hours in units of hours based on the graph trend of the historical operation data in the first visual graph X'; predicting daily operation data N 'of the network switching node in the next N days in units of days based on graph trend of the historical operation data in the second visual graph Y';
s5, dividing the data M 'by taking the day as a unit, calculating the average value of the daily data M', and marking the average value as M 1 'A'; m of data N' and corresponding period 1 Two numerical values of' are taken as two end values, and a prediction range of future operation data taking a day as a unit is formed;
and S6, taking the average value of each prediction range to obtain the predicted operation data of each network switching node in the future every day, namely a predicted result.
4. The cloud platform early warning feedback method based on the AI intelligent reasoning algorithm as set forth in claim 3, wherein the method is characterized in that: the cloud platform is pre-stored with a numerical range of operation data of the network switching node in a normal working state, and the judgment of the result of the predicted operation data is specifically as follows: the cloud platform compares the predicted result with the numerical range in the normal state, and if the numerical value of the predicted result is not in the numerical range in the normal state, the network switching node is judged to have a problem; otherwise, the network switching node is in a normal state.
5. The cloud platform early warning feedback method based on the AI intelligent reasoning algorithm as set forth in claim 4, wherein the method is characterized in that: if the predicted operation data is in the numerical range in the normal state, but the predicted operation data is similar to the two end values of the numerical range, judging that the network switching node is suspected to have a problem, and displaying the suspected network switching node with the problem on the display equipment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311707017.6A CN117714390A (en) | 2023-12-13 | 2023-12-13 | Cloud platform early warning feedback method based on AI intelligent reasoning algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311707017.6A CN117714390A (en) | 2023-12-13 | 2023-12-13 | Cloud platform early warning feedback method based on AI intelligent reasoning algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117714390A true CN117714390A (en) | 2024-03-15 |
Family
ID=90145591
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311707017.6A Pending CN117714390A (en) | 2023-12-13 | 2023-12-13 | Cloud platform early warning feedback method based on AI intelligent reasoning algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117714390A (en) |
-
2023
- 2023-12-13 CN CN202311707017.6A patent/CN117714390A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US5621664A (en) | Monitoring system status | |
US5699403A (en) | Network vulnerability management apparatus and method | |
CN106941423B (en) | Failure cause localization method and device | |
AU671194B2 (en) | Event correlation | |
US5872911A (en) | Method and system of service impact analysis in a communications network | |
US7081823B2 (en) | System and method of predicting future behavior of a battery of end-to-end probes to anticipate and prevent computer network performance degradation | |
US6353902B1 (en) | Network fault prediction and proactive maintenance system | |
US7007084B1 (en) | Proactive predictive preventative network management technique | |
WO1997024839A9 (en) | Fault impact analysis | |
CN106385339B (en) | Monitoring method and monitoring system for access performance of enterprise network | |
JPH07183948A (en) | Processing method for data that generates rule that predicts phenomenon that arises in communication system | |
CN105659528A (en) | Method and apparatus for realizing fault location | |
EP0598484B1 (en) | Monitoring system status | |
CN113762604B (en) | Industrial Internet big data service system | |
CN111953530A (en) | Network equipment monitoring management method and system | |
CN113037562A (en) | Gateway fault assessment method and device and server | |
CN117714390A (en) | Cloud platform early warning feedback method based on AI intelligent reasoning algorithm | |
CN1972221A (en) | A detection method of service reliability and apparatus and circuit planning method | |
CN110609761A (en) | Method and device for determining fault source, storage medium and electronic equipment | |
US11337087B2 (en) | Methods, systems and computer readable media for predicting risk in network elements using machine learning | |
CN113300914A (en) | Network quality monitoring method, device, system, electronic equipment and storage medium | |
CN113746688B (en) | Method and device for updating anomaly detection model and computing equipment | |
CN116112285B (en) | Network attack path prediction method and system based on artificial intelligence | |
CN112039436B (en) | Method for analyzing power station state by integrating working state and real-time data of photovoltaic inverter | |
CN117614527A (en) | Optical fiber transmission management system and method based on data analysis |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |