System and method for generating autonomous alert in the network

IN604917BActive Publication Date: 2026-10-05CHITKARA UNIV +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
IN202311067171
Authority / Receiving Office
IN · IN
Patent Type
Patents
Current Assignee / Owner
Filing Date
2023-10-06
Publication Date
2026-10-05

AI Technical Summary

Technical Problem

Current systems for monitoring computer networks are inefficient in detecting and categorizing significant changes, leading to false alarms and missed alerts, and struggle to manage the complexity of evolving network environments.

Method used

A system utilizing a machine learning engine with deep neural network architecture to analyze data packets from network nodes, categorize incidents based on severity and type, and generate alerts, while integrating with existing network management tools to streamline management processes.

Benefits of technology

The system provides timely, accurate alerts that facilitate appropriate actions, adapts to evolving network patterns, and enhances network security by automatically detecting modifications and anomalies, ensuring proactive issue resolution.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000022_0000
    Figure 00000022_0000
Patent Text Reader

Abstract

The present invention discloses a system 100 and method for generating an autonomous alert in the network. The system 100 includes a processing unit 102 comprising a machine learning and a processor 104 configured to receive a set of data packets from a plurality of nodes 112 associated with the network 110 and extract one or more incident from the received set of data packets, wherein the one or more incident pertains to malfunctioning of at least one node 112. The system 100 further categorise the one or more incident through machine learning technique based on severity and type of malfunctioning node 112 and generate alerts based on the categorization of the one or more incidents.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of computer network andspecifically a system and method for generating an autonomous alert in the network.BACKGROUND

[0002] In today's rapidly evolving technological landscape, computer networkshave become an integral part of modern business operations. Network administratorsare tasked with managing complex networks that often span multiple geographiclocations and have numerous devices and applications. With the increasing complexityof these networks, keeping track of all the changes that occur within such networks canbe a daunting task, and it is often difficult to determine which changes are significantand which are not. Furthermore, the network administrators need to be notified ofimportant changes in real-time to be able to respond quickly and effectively.

[0003] Traditionally, the network administrators have relied on manualmethods to monitor and detect changes within the network. This involves manuallyinspecting logs and other data sources to identify changes and determine theirsignificance. However, this method is time-consuming and error-prone, as the networkadministrators may overlook important changes or misinterpret their significance.

[0004] To address this issue, various automated systems have been developedto assist the network administrators in detecting and analyzing changes within thenetwork. These systems use various methods to detect changes, such as analyzingnetwork traffic, monitoring system logs, and comparing the network configurations.However, these systems often lack the ability to accurately categorize changes basedon their significance, leading to false alarms, or missed alerts.

[0005] Moreover, with the increasing complexity of computer networks and theever-growing number of devices and applications, it is becoming increasingly difficultto manage and monitor the network changes.

[0006] Therefore, there is a need in the art to provide an effective system toovercome the above-mentioned problems in the ineffectiveness of the existing systemand method for generating an autonomous alert in the network.OBJECTS OF THE PRESENT DISCLOSURE

[0007] Some of the objectives of the present invention, which at least oneembodiment herein satisfies are listed herein below.

[0008] It is an object of the present disclosure to provide a system that detectsany modifications, anomalies, or suspicious activities occurring within a computernetwork and notify automatically.

[0009] It is an object of the present disclosure to identify any potential changesand indicate any potential security threats or operational issues.

[0010] It is an object of the present disclosure to provide a system that alertstimely, and accurately and provides sufficient information to facilitate appropriateactions.

[0011] It is an object of the present disclosure to provide a system that isadaptable to different network environments and capable of learning and adapting toevolving network patterns and changes over time.

[0012] It is an object of the present disclosure to provide a system thatintegrates with existing network infrastructure, management systems, or security toolsto leverage their functionalities and enhance the overall network security posture.SUMMARY OF THE INVENTION

[0013] The present disclosure relates to the field of computer network andspecifically a system and method for generating an autonomous alert in the network.

[0014] According to an aspect, the present disclosure pertains to a system forfacilitating a system and method for generating an autonomous alert in the network.The system comprises a processing unit comprising a machine learning, and aprocessor coupled to a memory, wherein the memory comprises a set of instructionswhich when executed, cause the processor to receive a set of data packets from aplurality of nodes associated with the network and extract one or more incident fromthe received set of data packets, wherein the one or more incident pertains tomalfunctioning of at least one node among the plurality of nodes. The processorcategorise the one or more incident through machine learning technique based onseverity and type of malfunctioning node and generate alerts based on thecategorization of the one or more incidents.

[0015] In an aspect, the system architecture of the machine learning engine maycomprise any or a combination of a deep neural network, a convolutional neuralnetwork, and a recurrent neural network architecture.

[0016] In an aspect, the categorization of the one or more incident may be basedon criteria comprising any or a combination of type of node, type of protocol, severityof change, and the impact on the network.

[0017] In an aspect, the system may further comprise an integration moduleconfigured to integrate with other network management tools and systems, includingticketing systems and change management systems, to streamline networkmanagement process.

[0018] In an aspect, a display unit may be coupled to the processing unit, andconfigured to display the generated alerts.

[0019] In an aspect, the categorization may be carried out by comparing thenetwork changes pertaining to the malfunctioning nodes to a baseline configuration,and to alert the network administrators when the changes deviate from the baselineconfiguration.

[0020] According to an aspect, the present disclosure pertains to a system andmethod for generating an autonomous alert in a network, the method comprising thesteps of receiving, at a processing unit comprising a machine learning engine, aset of data packets from a plurality of nodes associated with the network and extractingat the processing unit, one or more incident from the received set of data packets,wherein the one or more incident pertains to malfunctioning of at least one node amongthe plurality of nodes, and categorizing at the processing unit, the one or more incidentthrough machine learning technique based on severity and type of malfunctioning nodeand generating alerts based on the categorization of the one or more incidents.

[0021] In an aspect, the method may comprise categorizing the one or moreincident based on criteria comprising any or a combination of type of node, type ofprotocol, severity of change, and the impact on the network.

[0022] In another aspect, the method may comprise integrating, through anintegration module, with other network management tools and systems, includingticketing systems and change management systems, and correspondingly streamliningnetwork management process.

[0023] In an aspect, the method may comprise carrying out the categorizationby comparing network changes pertaining to the malfunctioning nodes to a baselineconfiguration and to alert network administrators when the changes deviate from thebaseline configuration.

[0024] Various objects, features, aspects, and advantages of the inventivesubject matter will become more apparent from the following detailed description ofpreferred embodiments, along with the accompanying drawing figures in which likenumerals represent like components.BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings are included to provide a furtherunderstanding of the present disclosure and are incorporated in and constitute a part ofthis specification. The drawings illustrate exemplary embodiments of the presentdisclosure and, together with the description, serve to explain the principles of thepresent disclosure.

[0026] In the figures, similar components, and / or features may have the samereference label. Further, various components of the same type may be distinguished byfollowing the reference label with a second label that distinguishes among the similarcomponents. If only the first reference label is used in the specification, the descriptionis applicable to any one of the similar components having the same first reference labelirrespective of the second reference label.

[0027] FIG. 1 illustrates an exemplary block diagram of the proposed systemand method for generating an autonomous alert in the network according to oneembodiment of the present invention.

[0028] FIG. 2 illustrates an exemplary block diagram of a processing unitimplemented in the system, in accordance with an embodiment of the presentdisclosure.

[0029] FIG. 3 illustrates an exemplary view of a flow diagram of the proposedmethod of system and method for generating an autonomous in a network.

[0030] FIG. 4 illustrates an exemplary computer system in which or with whichembodiments of the present invention can be utilized in accordance with embodimentsof the present disclosure.DETAILED DESCRIPTION OF THE INVENTION

[0031] The present disclosure relates to the field of computer networks andspecifically a system and method for generating an autonomous alert in the network.

[0032] In an embodiment, the present disclosure will now be described morefully hereinafter with reference to the accompanying drawings, which form a parthereof, and which show, by way of illustration, certain example embodiments. Subjectmatter may, however, be embodied in a variety of different forms and, therefore,covered or claimed subject matter is intended to be construed as not being limited toany example embodiments set forth herein; example embodiments are provided merelyto be illustrative. Likewise, a reasonably broad scope for claimed or covered subjectmatter is intended.

[0033] In an embodiment, before explaining at least one embodiment of theinvention in detail, it is to be understood that the invention is not limited in itsapplication to the details of construction and to the arrangements of the components setforth in the following description or illustrated in various ways. Also, it is to beunderstood that the phraseology and terminology employed herein are for the purposeof description and should not be regarded as limiting.

[0034] In an embodiment, the present disclosure pertains to a system andmethod for generating an autonomous alert in the network. The system includes aprocessing unit comprising a machine learning, and a processor coupled to a memory,wherein the memory comprising a set of instructions which when executed, cause theprocessor to receive a set of data packets from a plurality of nodes associated with thenetwork. The processor extract one or more incident from the received set of datapackets, wherein the one or more incident pertains to malfunctioning of at least onenode among the plurality of nodes and categorise the one or more incident throughmachine learning technique based on severity and type of malfunctioning node andgenerate alerts based on the categorization of the one or more incidents.

[0035] In an embodiment, the system architecture of the machine learningengine can include any or a combination of a deep neural network, a convolutionalneural network, and a recurrent neural network architecture.

[0036] In an embodiment, the categorization of the one or more incident can bebased on criteria including any or a combination of type of node, type of protocol,severity of change, and the impact on the network.

[0037] In an embodiment, the system can further comprise an integrationmodule configured to integrate with other network management tools and systems,including ticketing systems and change management systems, to streamline networkmanagement process.

[0038] In an embodiment, a display unit can be coupled to the processing unit,and configured to display the generated alerts.

[0039] In an aspect, the categorization can be carried out by comparing networkchanges pertaining to the malfunctioning nodes to a baseline configuration, and to alertnetwork administrators when the changes deviate from the baseline configuration.

[0040] According to an embodiment, the present disclosure pertains to a systemand method for an autonomous alert in a network, the method comprises the steps ofreceiving, at a processing unit comprising a machine learning engine, a set ofdata packets from a plurality of nodes associated with the network and extracting, atthe processing unit, one or more incident from the received set of data packets, whereinthe one or more incident pertains to malfunctioning of at least one node among theplurality of nodes and also categorizing, at the processing unit, the one or more incidentthrough machine learning technique based on severity and type of malfunctioning nodeand generating alerts based on the categorization of the one or more incidents.

[0041] In an another embodiment, the method can comprise categorizing theone or more incident based on criteria comprising any or a combination of type of node,type of protocol, severity of change, and the impact on the network.

[0042] In another embodiment, the method can comprise, integrating, throughan integration module, with other network management tools and systems, includingticketing systems and change management systems, and correspondingly streamliningnetwork management process.

[0043] In an aspect, the method can comprise, carrying out the categorizationby comparing network changes pertaining to the malfunctioning nodes to a baselineconfiguration, and to alert network administrators when the changes deviate from thebaseline configuration.

[0044] FIG. 1 illustrates an exemplary block diagram of the proposed systemfor an autonomous alert in the network according to one embodiment of the presentinvention.

[0045] In an embodiment, the proposed system 100 (interchangeably, referredto as system 100, hereinafter) can facilitate generation of an autonomous alert in thenetwork, The proposed system 100 can include a processing unit 102 includes ofmachine learning and a processor 104 coupled to a memory 106. The memory includess set of instructions for execution. The processor 104 is communicably coupled with aplurality of nodes 112-1, 112-2, ….112-N (interchangeably referred to as nodes 112,hereinafter) through a network 110.

[0046] In an exemplary embodiment, the processor 104 can receive a set of datapackets from a plurality of nodes 112 associated with the network 110 and extract oneor more incident from the received set of data packets, where the one or more incidentsmay pertain to malfunctioning of at least one node 112 among the plurality of nodes112. The processor can categorize the one or more incident through machine learningtechnique based on severity and type of malfunctioning node and generate alerts basedon the categorization of the one or more incidents.

[0047] In another embodiment, the system 100 can establish a communicationchannel between the processor 104 and the nodes 112. The communication channelincludes Wi-Fi, intranet, and any other internet.

[0048] In an embodiment, the processor 104 can include suitable logic,circuitry, and / or interfaces that can be operable to execute one or more instructionsstored in the memory 106 to perform pre-determined operations. The memory 106 maybe operable to store the one or more instructions. Examples of processor 106 caninclude but are not limited to, a x86 processor, a RISC processor, a microprocessor, anASIC processor, a CISC processor, ESP 32, or any other processor. The processor 104includes a database 222. The data either stored or generated as a result of functionalitiesimplemented by any of the components of the processor 104.

[0049] In an embodiment, the architecture of the machine learning engine cancomprise any or a combination of a deep neural network, a convolutional neuralnetwork, and a recurrent neural network architecture.

[0050] In an embodiment, the categorization of the one or more incident can bebased on criteria comprising any or a combination of type of node, type of protocol,severity of change, and the impact on the network.

[0051] In an embodiment, the system 100 further can include an integrationmodule configured to integrate with other network management tools and systems,including ticketing systems and change management systems, to streamline networkmanagement process.

[0052] In an embodiment, a display unit can be coupled to the processing unit102, and configured to display the generated alerts.

[0053] In an embodiment, the categorization can be carried out by comparingnetwork changes pertaining to the malfunctioning nodes to a baseline configuration,and to alert network administrators when the changes deviate from the baselineconfiguration.

[0054] In some embodiments, the nodes 112 can be smartphone, tabletcomputer, personal digital assistant, laptop, portable media device, or the like.Moreover, the node 112 can include any web client or application that facilitatescommunication and interaction. In another exemplary embodiment, informationcommunicated between the system 100 and the node 112 can involve user-selectedfunctions available through one or more user interfaces (UIs). The UIs may bespecifically associated with the web client (e.g., a browser) or the application.

[0055] In another embodiment, the memory 106 stores a set of instructions anddata. Some of the commonly known memory implementations include but are notlimited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a HardDisk Drive (HDD), and a Secure Digital (SD) card. Further, the memory 106 includesthe one or more instructions that are executable by the processor 104 to performspecific operations. It will be apparent to a subject having ordinary skill in the art thatthe one or more instructions stored in the memory 106 enable the hardware of thesystem 100 to perform the predetermined operation.

[0056] In an embodiment, transceiver 108 coupled with the processing unit totransmits and receives messages and data to / from various components of the system100. Examples of the transceiver 108 may include, but are not limited to, an antenna,an Ethernet port, a USB port, or any other port that can be configured to receive andtransmit data. The transceiver 108 transmits and receives data / messages in accordancewith various communication protocols, such as TCP / IP, UDP, and 2G, 3G, or 4Gcommunication protocols.

[0057] In an embodiment, examples of the network 110 may include, but arenot limited to, a Wireless Fidelity (Wi-Fi) network, a Local Area Network (LAN), or aMetropolitan Area Network (MAN). Various devices in the system 100 can connect tothe network 110 in accordance with the various wired and wireless communicationprotocols such as Transmission Control Protocol and Internet Protocol (TCP / IP), UserDatagram Protocol (UDP), and 2G, 3G, and 4G communication protocols. In anotherembodiment, the communications network may be a Zigbee connection developedby the ZigBee Alliance such as IEEE 802.15.4-2003 (Zigbee 2003), IEEE 802.15.4-2006 (Zigbee 2006), IEEE 802.15.4-2007 (Zigbee Pro).

[0058] In an embodiment, the processor 104 may be configured to receive a setof alert data from the plurality of nodes 112, correspondingly generating one or morealerts. Additionally, the processor 104 applies at least one query language to create oneor more queries that facilitate visualization and search of the received log data in aCloudWatch, and create one or more custom rules using a set of an autonomous alertfor the network. Further, the processor 104 generates and transmits an alert to show iton a display upon detection of one or more alerts. In an exemplary embodiment, thesystem offers significant benefits, it provides organizations with a robust autonomousalert system for the network and ensures adherence to compliance standards andidentifying potential security risks promptly. The real-time processing capabilities ofthe system enable continuous monitoring and analysis of data, allowing organizationsto proactively address issues and maintain a secure cloud environment.

[0059] FIG. 2 illustrates an exemplary block diagram of a processing unitimplemented in the system, in accordance with an embodiment of the presentdisclosure.

[0060] As illustrated in FIG. 2, a module diagram 200 for the system 100 mayinclude one or more processor(s) 104, a memory 106, and an interface(s) 206. TheInterface (s) 206 includes a variety of interfaces, for example, interfaces for data inputand output devices referred to as I / O devices, storage devices, and the like. Theinterface(s) 206 facilitates communication of the processor 104 with various devicesor servers. The interface(s) 206 also provides a communication pathway for one ormore components of the system 100. Examples of such components include but are notlimited to, processing engine(s) and database. Interface 206 includes a platform forcommunication with the devices / servers to read real-time data / write data in the system100. The interfaces 206 includes a graphical interface that allows the user to feedinputs, to type / write / upload the data and certificates, and other software and hardwareinterfaces, for example, interfaces for peripheral device(s), such as a keyboard, amouse, an external memory, and a printer.

[0061] In an embodiment, the processing engine(s) 208 are implemented as acombination of hardware and programming (for example, programmable instructions)to implement one or more functionalities of the processing engine(s) 208. In theexamples described herein, such combinations of hardware and programming may beimplemented in several different ways. For example, the programming for theprocessing engine(s) 208 are processor-executable instructions stored on a non-transitory machine-readable storage medium, and the hardware for the processingengine(s) includes a processing resource (for example, one or more processors), toexecute such instructions. In the present examples, the machine-readable storagemedium stores instructions that, when executed by the processing resource, implementthe processing engine(s) 208. In other examples, the processing engine(s) 208 isimplemented by electronic circuitry. The processing engine 208 includes a database222 that is either stored or generated as a result of functionalities implemented by anyof the components of the processing engine(s) 208. In an embodiment, the processingengine(s) 208 can include a time monitoring module 210, receiving module 212, acategorisation module 214, a rule generation module 216, an alert finding module 218,and a feedback unit 220, but not limited to the likes. The feedback unit 220 implementsfunctionalities that supplement applications or functions performed by the system 100or the processing engine(s) 208. The database 222 serves, amongst other things, as arepository for storing data processed, received, and generated by one or more of theengines.

[0062] In an embodiment, the receiving module 212 may be configured toreceive a set of autonomous alerts in the network by one or more nodes 112. Thereceived set of data may include a plurality of alerts corresponding to any or acombination of network, sensor activity, machine behavior, security risk, or the like.In an exemplary embodiment, the received set of data can contain various types ofalerts, which may include information related to user activities, such as requests,interactions, or transmissions performed within the autonomous alert system fornetwork and boundary changes.

[0063] In an embodiment, the categorisation module 214 may be configured tocategorise alerts of received data, where the data is centralized, it brings together intoa unified location or system, which makes it easier to manage and analyze the dataeffectively. Additionally, the categorisation module 214 analyse the data, extractingrelevant information and organizing it in a structured manner, and this analysingprocess enables better understanding and utilization of the data. Further, based on theanalysed data, the module generates summaries, and these summaries provide conciseinformation or overviews of the alert data, allowing for a quick understanding of theoverall state of an autonomous alert in the network. Furthermore, the module generatesone or more warnings that highlight potential issues, discrepancies, or non-compliantconfigurations detected within the data, and served as indicators of alert findings thatrequire attention or further investigation.

[0064] Moreover, the categorisation module 214, applies at least one querylanguage to create one or more queries that facilitate visualization and search of thereceived data in a CloudWatch which is monitoring for an autonomous alert system innetwork. By creating queries, users can specify certain criteria or conditions to filterand extract desired information from the alert data. This enables effective visualizationand searching capabilities within the CloudWatch environment. Moreover, thecategorisation module 214 saves and reuses the created one or more queries, whichallows for repeated analysis of the data without the need to recreate the queries fromscratch.

[0065] In an embodiment, the rule generation module 216 may be configuredto create one or more custom rules using a set of autonomous alert systems for networkand boundary change rules to address one or more compliance requirements. The rulegeneration module 216 leverages the capabilities of an autonomous alert system for thenetwork, which are predefined rules provided by an autonomous alert system for thenetwork to assess and evaluate the configurations. By creating custom rules, themodule adapts these predefined rules to meet the specific compliance requirements thatneed to be addressed. In addition to creating custom rules, the rule generation module216 also provides a set of prebuilt rules for a predefined set of security standards. Thesepre-built rules are already defined and ready to be used for assessing complianceagainst well-known security standards. Further, by combining custom rules and prebuilt rules, the module offers a comprehensive set of rules to ensure compliance withspecific requirements and security standards. These rules help identify and flag anynon-compliant configurations or potential security vulnerabilities within theautonomous alert system for network and boundary changes environment, enablingproactive measures to address and mitigate them.

[0066] FIG. 3 illustrates an exemplary view of a flow diagram of the proposedmethod of system for an autonomous alert in the network.

[0067] As illustrated in FIG. 3, the method 300 for an autonomous alert in thenetwork, which includes the step 302 of receiving, at a processing unit comprising amachine learning engine, a set of data packets from a plurality of nodes associated withthe network; and step 304 of extracting, at the processing unit, one or more incidentfrom the received set of data packets, wherein the one or more incident pertains tomalfunctioning of at least one node among the plurality of nodes; and step 306 ofcategorizing, at the processing unit, the one or more incident through machine learningtechnique based on severity and type of malfunctioning node; and step 308 ofgenerating alerts based on the categorization of the one or more incidents.

[0068] In an embodiment, the method 300 may include categorizing the one ormore incident based on criteria comprising any or a combination of type of node, typeof protocol, severity of change, and the impact on the network.

[0069] In another embodiment, the method 300 may include integrating,through an integration module, with other network management tools and systems,including ticketing systems and change management systems, and correspondinglystreamlining network management process.

[0070] In another embodiment, the method 300 may include carrying out thecategorization by comparing network changes pertaining to the malfunctioning nodesto a baseline configuration, and to alert network administrators when the changesdeviate from the baseline configuration.

[0071] FIG. 4 illustrates an exemplary computer system in which or with whichembodiments of the present invention can be utilized in accordance with embodimentsof the present disclosure.

[0072] Referring to FIG.4, the computer system includes an external storagedevice 410, a bus 420, a main memory 430, a read-only memory 440, a mass storagedevice 450, a communication port 460, and a processor 470. Those skilled in the artwill appreciate that a computer system can include more than one processor andcommunication ports. Examples of processor 470 include, but are not limited to, anIntel Itanium or Itanium 2 processor(s), or AMD Opteron or Athlon MPprocessor(s), Motorola lines of processors, FortiSOC system on chip (SoC)processors, or other future processors. Processor 470 can include various modulesassociated with embodiments of the present invention. Communication port 460 can beany of an RS-232 port for use with a modem-based dialup connection, a 10 / 100Ethernet port, a Gigabit or 10 Gigabit port using copper or fiber, a serial port, a parallelport, or other existing or future ports. Communication port 460 can be chosendepending on a network, such as a Local Area Network (LAN), Wide Area Network(WAN), or any network to which computer system connects.

[0073] Memory 430 can be Random Access Memory (RAM), or any otherdynamic storage device commonly known in the art. Read only memory 440 can beany static storage device(s) e.g., but not limited to, a Programmable Read OnlyMemory (PROM) chips forstoring static information e.g., start-up or BIOS instructionsfor processor 470. Mass storage 450 can be any current or future mass storage solution,which can be used to store information and / or instructions. Exemplary mass storagesolutions include but are not limited to, Parallel Advanced Technology Attachment(PATA) or Serial Advanced Technology Attachment (SATA) hard disk drives or solidstate drives (internal or external, e.g., having Universal Serial Bus (USB) and / orFirewire interfaces), e.g. those available from Seagate (e.g., the Seagate Barracuda7112 family) or Hitachi (e.g., the Hitachi Deskstar 7K1000), one or more optical discs,Redundant Array of Independent Disks (RAID) storage, e.g. an array of disks (e.g.,SATA arrays), available from various vendors including Dot Hill Systems Corp.,LaCie, Nexsan Technologies, Inc. and Enhance Technology, Inc.

[0074] Bus 420 communicatively couples processor(s) 470 with the othermemory, storage, and communication blocks. Bus 420 can be, e.g., a PeripheralComponent Interconnect (PCI) / PCI Extended (PCI-X) bus, Small Computer SystemInterface (SCSI), USB or the like, for connecting expansion cards, drives, and othersubsystems as well as other buses, such a front side bus (FSB), which connectsprocessor 470 to software system.

[0075] Optionally, operator and administrative interfaces, e.g., a display,keyboard, and a cursor control device, can also be coupled to bus 420 to support directoperator interaction with the computer system. Other operator and administrativeinterfaces can be provided through network connections connected throughcommunication port 460. External storage device 410 can be any kind of external harddrives, floppy drives, IOMEGA Zip Drives, Compact Disc - Read Only Memory(CD-ROM), Compact Disc - Re-Writable (CDRW), Digital Video Disk - Read OnlyMemory (DVD-ROM). The components described above are meant only to exemplifyvarious possibilities. In no way should the aforementioned exemplary computer systemlimits the scope of the present disclosure.

[0076] Above disclosed embodiments discloses system and method thatprovide comprehensive data tracking capabilities, allowing for the monitoring of socialmedia data, backlinks, keyword rankings, and Google Analytics statistics, this ensuresa thorough examination, also empower users to extract meaningful information fromsocial media data, While the foregoing describes various embodiments of the invention,other and further embodiments of the invention may be devised without departing fromthe basic scope thereof. The scope of the invention is determined by the claims thatfollow. The invention is not limited to the described embodiments, versions, orexamples, which are included to enable a person having ordinary skill in the art to makeand use the invention when combined with information and knowledge available tothose having ordinary skill in the art optimize messaging strategies, and make informeddecisions.

[0077] Those skilled in this technology can make various alterations andmodifications without departing from the scope and spirit of the invention. Therefore,the scope of the invention shall be defined and protected by the following claims andtheir equivalents.

[0078] In an embodiment, the headings are used for organizational purposesonly and are not meant to limit the scope of the description or the claims. As usedthroughout this description, the word "may" be used in a permissive sense (i.e.,meaning having the potential to), rather than the mandatory sense (i.e., meaning must).Further, the words "a" or "a" mean "at least one" and the word "plurality" means oneor more, unless otherwise mentioned. Furthermore, the terminology and phraseologyused herein is solely used for descriptive purposes and should not be construed aslimiting in scope.

[0079] Language such as "including," "comprising," "having," "containing,"or "involving," and variations thereof, is intended to be broad and encompass thesubject matter listed thereafter, equivalents, and any additional subject matter notrecited, and is not intended to exclude any other additives, components, integers orsteps. Likewise, the term "comprising" is considered synonymous with the terms"including" or "containing" for applicable legal purposes. Any discussion ofdocuments, acts, materials, devices, articles, and the like are included in thespecification solely for the purpose of providing a context for the present invention. Inthis disclosure, whenever an element or a group of elements is preceded with thetransitional phrase "comprising", it is understood that we also contemplate the sameelement or group of elements with transitional phrases "consisting essentially of,"consisting", "selected from the group consisting of," "including", or "is" preceding therecitation of the element or group of elements and vice versa.

[0080] In the following description, for the purpose of explanation, numerousspecific details are set forth in order to provide a thorough understanding of thearrangement of the system according to an embodiment herein. It will be apparent,however, to one skilled in the art that the present embodiment can be practiced withoutthese specific details. In other instances, structures are shown in block diagram formonly in order to avoid obscuring the present invention.ADVANTAGES OF THE PRESENT INVENTION

[0081] It is an advantage of the invention to detect and notify anymodifications, anomalies, or suspicious activities occurring within a computer networkautomatically.

[0082] It is an advantage of the invention to analyze network data andcategorize changes based on predefined criteria, allowing for more accurate andefficient alerting.

[0083] It is an advantage of the present invention to identify deviations orchanges that may indicate potential security threats or operational issues.

[0084] It is an advantage of the present invention to alerts timely, andaccurately, and provides sufficient information to facilitate appropriate actions.

[0085] It is an advantage of the present invention to adapt different networkenvironments and capable of learning and adapting to evolving network patterns andchanges over time.

[0086] It is an advantage of the present invention to integrate with existingnetwork infrastructure, management systems, or security tools to leverage theirfunctionalities and enhance the overall network security posture.

Claims

1. A system (100) and method for generating an autonomous alert in a network, the system comprising: a processing unit (102) comprising a machine learning, and a processor (104) coupled to a memory (106), wherein the memory (106) comprising a set of instructions which when executed, cause the processor (102) to: receive a set of data packets from a plurality of nodes (112) associated with the network (110); extract one or more incident from the received set of data packets, wherein the one or more incident pertains to malfunctioning of at least one node (112) among the plurality of nodes (112); categorise the one or more incident through machine learning technique based on severity and type of malfunctioning node (112); and generate alerts based on the categorization of the one or more incidents.

2. The system (100) as claimed in claim 1, wherein architecture of the machine learning engine comprises any or a combination of a deep neural network, a convolutional neural network, and a recurrent neural network architecture.

3. The system (100) as claimed in claim 1, wherein the categorization of the one or more incident is based on criteria comprising any or a combination of type of node (112), type of protocol, severity of change, and the impact on the network (110).

4. The system (100) as claimed in claim 1, wherein the system (100) further comprises an integration module configured to integrate with other network management tools and systems, including ticketing systems and change management systems, to streamline network management process.

5. The system (100) as claimed in claim 1, wherein a display unit is coupled to the processing unit (112), and configured to display the generated alerts.

6. The system (100) as claimed in claim 1, wherein the categorization is carried out by comparing network changes pertaining to the malfunctioning nodes (112) to a baseline configuration, and to alert network administrators when the changes deviate from the baseline configuration.

7. A method (300) for an autonomous alert in a network, the method (300) comprises: receiving (302), at a processing unit (102) comprising a machine learning engine, a set of data packets from a plurality of nodes associated with the network (110); extracting (304), at the processing unit (102), one or more incident from the received set of data packets, wherein the one or more incident pertains to malfunctioning of at least one node (112) among the plurality of nodes (112); categorizing (306), at the processing unit, the one or more incident through machine learning technique based on severity and type of malfunctioning node (112); and generating (308) alerts based on the categorization of the one or more incidents.

8. The method (300) as claimed in claim 7, wherein the method (300) comprises categorizing the one or more incident based on criteria comprising any or a combination of type of node, type of protocol, severity of change, and the impact on the network.

9. The method (300) as claimed in claim 7, wherein the method (300) comprises integrating, through an integration module, with other network management tools and systems, including ticketing systems and change management systems, and correspondingly streamlining network management process.

10. The method (300) as claimed in claim 7, wherein the method (300) comprises carrying out the categorization by comparing network changes pertaining to the malfunctioning nodes to a baseline configuration, and to alert network administrators when the changes deviate from the baseline configuration.